summaryrefslogtreecommitdiff
path: root/drivers/virtio/virtio_pci_modern.c
blob: ee6a386d250b168bdd59153a62ddceb361c0af93 (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
// SPDX-License-Identifier: GPL-2.0-or-later
/*
 * Virtio PCI driver - modern (virtio 1.0) device support
 *
 * This module allows virtio devices to be used over a virtual PCI device.
 * This can be used with QEMU based VMMs like KVM or Xen.
 *
 * Copyright IBM Corp. 2007
 * Copyright Red Hat, Inc. 2014
 *
 * Authors:
 *  Anthony Liguori  <aliguori@us.ibm.com>
 *  Rusty Russell <rusty@rustcorp.com.au>
 *  Michael S. Tsirkin <mst@redhat.com>
 */

#include <linux/delay.h>
#define VIRTIO_PCI_NO_LEGACY
#define VIRTIO_RING_NO_LEGACY
#include "virtio_pci_common.h"

static u64 vp_get_features(struct virtio_device *vdev)
{
	struct virtio_pci_device *vp_dev = to_vp_device(vdev);

	return vp_modern_get_features(&vp_dev->mdev);
}

static void vp_transport_features(struct virtio_device *vdev, u64 features)
{
	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
	struct pci_dev *pci_dev = vp_dev->pci_dev;

	if ((features & BIT_ULL(VIRTIO_F_SR_IOV)) &&
			pci_find_ext_capability(pci_dev, PCI_EXT_CAP_ID_SRIOV))
		__virtio_set_bit(vdev, VIRTIO_F_SR_IOV);

	if (features & BIT_ULL(VIRTIO_F_RING_RESET))
		__virtio_set_bit(vdev, VIRTIO_F_RING_RESET);
}

static int __vp_check_common_size_one_feature(struct virtio_device *vdev, u32 fbit,
					    u32 offset, const char *fname)
{
	struct virtio_pci_device *vp_dev = to_vp_device(vdev);

	if (!__virtio_test_bit(vdev, fbit))
		return 0;

	if (likely(vp_dev->mdev.common_len >= offset))
		return 0;

	dev_err(&vdev->dev,
		"virtio: common cfg size(%zu) does not match the feature %s\n",
		vp_dev->mdev.common_len, fname);

	return -EINVAL;
}

#define vp_check_common_size_one_feature(vdev, fbit, field) \
	__vp_check_common_size_one_feature(vdev, fbit, \
		offsetofend(struct virtio_pci_modern_common_cfg, field), #fbit)

static int vp_check_common_size(struct virtio_device *vdev)
{
	if (vp_check_common_size_one_feature(vdev, VIRTIO_F_NOTIF_CONFIG_DATA, queue_notify_data))
		return -EINVAL;

	if (vp_check_common_size_one_feature(vdev, VIRTIO_F_RING_RESET, queue_reset))
		return -EINVAL;

	return 0;
}

/* virtio config->finalize_features() implementation */
static int vp_finalize_features(struct virtio_device *vdev)
{
	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
	u64 features = vdev->features;

	/* Give virtio_ring a chance to accept features. */
	vring_transport_features(vdev);

	/* Give virtio_pci a chance to accept features. */
	vp_transport_features(vdev, features);

	if (!__virtio_test_bit(vdev, VIRTIO_F_VERSION_1)) {
		dev_err(&vdev->dev, "virtio: device uses modern interface "
			"but does not have VIRTIO_F_VERSION_1\n");
		return -EINVAL;
	}

	if (vp_check_common_size(vdev))
		return -EINVAL;

	vp_modern_set_features(&vp_dev->mdev, vdev->features);

	return 0;
}

/* virtio config->get() implementation */
static void vp_get(struct virtio_device *vdev, unsigned int offset,
		   void *buf, unsigned int len)
{
	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
	struct virtio_pci_modern_device *mdev = &vp_dev->mdev;
	void __iomem *device = mdev->device;
	u8 b;
	__le16 w;
	__le32 l;

	BUG_ON(offset + len > mdev->device_len);

	switch (len) {
	case 1:
		b = ioread8(device + offset);
		memcpy(buf, &b, sizeof b);
		break;
	case 2:
		w = cpu_to_le16(ioread16(device + offset));
		memcpy(buf, &w, sizeof w);
		break;
	case 4:
		l = cpu_to_le32(ioread32(device + offset));
		memcpy(buf, &l, sizeof l);
		break;
	case 8:
		l = cpu_to_le32(ioread32(device + offset));
		memcpy(buf, &l, sizeof l);
		l = cpu_to_le32(ioread32(device + offset + sizeof l));
		memcpy(buf + sizeof l, &l, sizeof l);
		break;
	default:
		BUG();
	}
}

/* the config->set() implementation.  it's symmetric to the config->get()
 * implementation */
static void vp_set(struct virtio_device *vdev, unsigned int offset,
		   const void *buf, unsigned int len)
{
	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
	struct virtio_pci_modern_device *mdev = &vp_dev->mdev;
	void __iomem *device = mdev->device;
	u8 b;
	__le16 w;
	__le32 l;

	BUG_ON(offset + len > mdev->device_len);

	switch (len) {
	case 1:
		memcpy(&b, buf, sizeof b);
		iowrite8(b, device + offset);
		break;
	case 2:
		memcpy(&w, buf, sizeof w);
		iowrite16(le16_to_cpu(w), device + offset);
		break;
	case 4:
		memcpy(&l, buf, sizeof l);
		iowrite32(le32_to_cpu(l), device + offset);
		break;
	case 8:
		memcpy(&l, buf, sizeof l);
		iowrite32(le32_to_cpu(l), device + offset);
		memcpy(&l, buf + sizeof l, sizeof l);
		iowrite32(le32_to_cpu(l), device + offset + sizeof l);
		break;
	default:
		BUG();
	}
}

static u32 vp_generation(struct virtio_device *vdev)
{
	struct virtio_pci_device *vp_dev = to_vp_device(vdev);

	return vp_modern_generation(&vp_dev->mdev);
}

/* config->{get,set}_status() implementations */
static u8 vp_get_status(struct virtio_device *vdev)
{
	struct virtio_pci_device *vp_dev = to_vp_device(vdev);

	return vp_modern_get_status(&vp_dev->mdev);
}

static void vp_set_status(struct virtio_device *vdev, u8 status)
{
	struct virtio_pci_device *vp_dev = to_vp_device(vdev);

	/* We should never be setting status to 0. */
	BUG_ON(status == 0);
	vp_modern_set_status(&vp_dev->mdev, status);
}

static void vp_reset(struct virtio_device *vdev)
{
	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
	struct virtio_pci_modern_device *mdev = &vp_dev->mdev;

	/* 0 status means a reset. */
	vp_modern_set_status(mdev, 0);
	/* After writing 0 to device_status, the driver MUST wait for a read of
	 * device_status to return 0 before reinitializing the device.
	 * This will flush out the status write, and flush in device writes,
	 * including MSI-X interrupts, if any.
	 */
	while (vp_modern_get_status(mdev))
		msleep(1);
	/* Flush pending VQ/configuration callbacks. */
	vp_synchronize_vectors(vdev);
}

static int vp_active_vq(struct virtqueue *vq, u16 msix_vec)
{
	struct virtio_pci_device *vp_dev = to_vp_device(vq->vdev);
	struct virtio_pci_modern_device *mdev = &vp_dev->mdev;
	unsigned long index;

	index = vq->index;

	/* activate the queue */
	vp_modern_set_queue_size(mdev, index, virtqueue_get_vring_size(vq));
	vp_modern_queue_address(mdev, index, virtqueue_get_desc_addr(vq),
				virtqueue_get_avail_addr(vq),
				virtqueue_get_used_addr(vq));

	if (msix_vec != VIRTIO_MSI_NO_VECTOR) {
		msix_vec = vp_modern_queue_vector(mdev, index, msix_vec);
		if (msix_vec == VIRTIO_MSI_NO_VECTOR)
			return -EBUSY;
	}

	return 0;
}

static int vp_modern_disable_vq_and_reset(struct virtqueue *vq)
{
	struct virtio_pci_device *vp_dev = to_vp_device(vq->vdev);
	struct virtio_pci_modern_device *mdev = &vp_dev->mdev;
	struct virtio_pci_vq_info *info;
	unsigned long flags;

	if (!virtio_has_feature(vq->vdev, VIRTIO_F_RING_RESET))
		return -ENOENT;

	vp_modern_set_queue_reset(mdev, vq->index);

	info = vp_dev->vqs[vq->index];

	/* delete vq from irq handler */
	spin_lock_irqsave(&vp_dev->lock, flags);
	list_del(&info->node);
	spin_unlock_irqrestore(&vp_dev->lock, flags);

	INIT_LIST_HEAD(&info->node);

#ifdef CONFIG_VIRTIO_HARDEN_NOTIFICATION
	__virtqueue_break(vq);
#endif

	/* For the case where vq has an exclusive irq, call synchronize_irq() to
	 * wait for completion.
	 *
	 * note: We can't use disable_irq() since it conflicts with the affinity
	 * managed IRQ that is used by some drivers.
	 */
	if (vp_dev->per_vq_vectors && info->msix_vector != VIRTIO_MSI_NO_VECTOR)
		synchronize_irq(pci_irq_vector(vp_dev->pci_dev, info->msix_vector));

	vq->reset = true;

	return 0;
}

static int vp_modern_enable_vq_after_reset(struct virtqueue *vq)
{
	struct virtio_pci_device *vp_dev = to_vp_device(vq->vdev);
	struct virtio_pci_modern_device *mdev = &vp_dev->mdev;
	struct virtio_pci_vq_info *info;
	unsigned long flags, index;
	int err;

	if (!vq->reset)
		return -EBUSY;

	index = vq->index;
	info = vp_dev->vqs[index];

	if (vp_modern_get_queue_reset(mdev, index))
		return -EBUSY;

	if (vp_modern_get_queue_enable(mdev, index))
		return -EBUSY;

	err = vp_active_vq(vq, info->msix_vector);
	if (err)
		return err;

	if (vq->callback) {
		spin_lock_irqsave(&vp_dev->lock, flags);
		list_add(&info->node, &vp_dev->virtqueues);
		spin_unlock_irqrestore(&vp_dev->lock, flags);
	} else {
		INIT_LIST_HEAD(&info->node);
	}

#ifdef CONFIG_VIRTIO_HARDEN_NOTIFICATION
	__virtqueue_unbreak(vq);
#endif

	vp_modern_set_queue_enable(&vp_dev->mdev, index, true);
	vq->reset = false;

	return 0;
}

static u16 vp_config_vector(struct virtio_pci_device *vp_dev, u16 vector)
{
	return vp_modern_config_vector(&vp_dev->mdev, vector);
}

static bool vp_notify_with_data(struct virtqueue *vq)
{
	u32 data = vring_notification_data(vq);

	iowrite32(data, (void __iomem *)vq->priv);

	return true;
}

static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev,
				  struct virtio_pci_vq_info *info,
				  unsigned int index,
				  void (*callback)(struct virtqueue *vq),
				  const char *name,
				  bool ctx,
				  u16 msix_vec)
{

	struct virtio_pci_modern_device *mdev = &vp_dev->mdev;
	bool (*notify)(struct virtqueue *vq);
	struct virtqueue *vq;
	u16 num;
	int err;

	if (__virtio_test_bit(&vp_dev->vdev, VIRTIO_F_NOTIFICATION_DATA))
		notify = vp_notify_with_data;
	else
		notify = vp_notify;

	if (index >= vp_modern_get_num_queues(mdev))
		return ERR_PTR(-EINVAL);

	/* Check if queue is either not available or already active. */
	num = vp_modern_get_queue_size(mdev, index);
	if (!num || vp_modern_get_queue_enable(mdev, index))
		return ERR_PTR(-ENOENT);

	info->msix_vector = msix_vec;

	/* create the vring */
	vq = vring_create_virtqueue(index, num,
				    SMP_CACHE_BYTES, &vp_dev->vdev,
				    true, true, ctx,
				    notify, callback, name);
	if (!vq)
		return ERR_PTR(-ENOMEM);

	vq->num_max = num;

	err = vp_active_vq(vq, msix_vec);
	if (err)
		goto err;

	vq->priv = (void __force *)vp_modern_map_vq_notify(mdev, index, NULL);
	if (!vq->priv) {
		err = -ENOMEM;
		goto err;
	}

	return vq;

err:
	vring_del_virtqueue(vq);
	return ERR_PTR(err);
}

static int vp_modern_find_vqs(struct virtio_device *vdev, unsigned int nvqs,
			      struct virtqueue *vqs[],
			      vq_callback_t *callbacks[],
			      const char * const names[], const bool *ctx,
			      struct irq_affinity *desc)
{
	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
	struct virtqueue *vq;
	int rc = vp_find_vqs(vdev, nvqs, vqs, callbacks, names, ctx, desc);

	if (rc)
		return rc;

	/* Select and activate all queues. Has to be done last: once we do
	 * this, there's no way to go back except reset.
	 */
	list_for_each_entry(vq, &vdev->vqs, list)
		vp_modern_set_queue_enable(&vp_dev->mdev, vq->index, true);

	return 0;
}

static void del_vq(struct virtio_pci_vq_info *info)
{
	struct virtqueue *vq = info->vq;
	struct virtio_pci_device *vp_dev = to_vp_device(vq->vdev);
	struct virtio_pci_modern_device *mdev = &vp_dev->mdev;

	if (vp_dev->msix_enabled)
		vp_modern_queue_vector(mdev, vq->index,
				       VIRTIO_MSI_NO_VECTOR);

	if (!mdev->notify_base)
		pci_iounmap(mdev->pci_dev, (void __force __iomem *)vq->priv);

	vring_del_virtqueue(vq);
}

static int virtio_pci_find_shm_cap(struct pci_dev *dev, u8 required_id,
				   u8 *bar, u64 *offset, u64 *len)
{
	int pos;

	for (pos = pci_find_capability(dev, PCI_CAP_ID_VNDR); pos > 0;
	     pos = pci_find_next_capability(dev, pos, PCI_CAP_ID_VNDR)) {
		u8 type, cap_len, id, res_bar;
		u32 tmp32;
		u64 res_offset, res_length;

		pci_read_config_byte(dev, pos + offsetof(struct virtio_pci_cap,
							 cfg_type), &type);
		if (type != VIRTIO_PCI_CAP_SHARED_MEMORY_CFG)
			continue;

		pci_read_config_byte(dev, pos + offsetof(struct virtio_pci_cap,
							 cap_len), &cap_len);
		if (cap_len != sizeof(struct virtio_pci_cap64)) {
			dev_err(&dev->dev, "%s: shm cap with bad size offset:"
				" %d size: %d\n", __func__, pos, cap_len);
			continue;
		}

		pci_read_config_byte(dev, pos + offsetof(struct virtio_pci_cap,
							 id), &id);
		if (id != required_id)
			continue;

		pci_read_config_byte(dev, pos + offsetof(struct virtio_pci_cap,
							 bar), &res_bar);
		if (res_bar >= PCI_STD_NUM_BARS)
			continue;

		/* Type and ID match, and the BAR value isn't reserved.
		 * Looks good.
		 */

		/* Read the lower 32bit of length and offset */
		pci_read_config_dword(dev, pos + offsetof(struct virtio_pci_cap,
							  offset), &tmp32);
		res_offset = tmp32;
		pci_read_config_dword(dev, pos + offsetof(struct virtio_pci_cap,
							  length), &tmp32);
		res_length = tmp32;

		/* and now the top half */
		pci_read_config_dword(dev,
				      pos + offsetof(struct virtio_pci_cap64,
						     offset_hi), &tmp32);
		res_offset |= ((u64)tmp32) << 32;
		pci_read_config_dword(dev,
				      pos + offsetof(struct virtio_pci_cap64,
						     length_hi), &tmp32);
		res_length |= ((u64)tmp32) << 32;

		*bar = res_bar;
		*offset = res_offset;
		*len = res_length;

		return pos;
	}
	return 0;
}

static bool vp_get_shm_region(struct virtio_device *vdev,
			      struct virtio_shm_region *region, u8 id)
{
	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
	struct pci_dev *pci_dev = vp_dev->pci_dev;
	u8 bar;
	u64 offset, len;
	phys_addr_t phys_addr;
	size_t bar_len;

	if (!virtio_pci_find_shm_cap(pci_dev, id, &bar, &offset, &len))
		return false;

	phys_addr = pci_resource_start(pci_dev, bar);
	bar_len = pci_resource_len(pci_dev, bar);

	if ((offset + len) < offset) {
		dev_err(&pci_dev->dev, "%s: cap offset+len overflow detected\n",
			__func__);
		return false;
	}

	if (offset + len > bar_len) {
		dev_err(&pci_dev->dev, "%s: bar shorter than cap offset+len\n",
			__func__);
		return false;
	}

	region->len = len;
	region->addr = (u64) phys_addr + offset;

	return true;
}

static const struct virtio_config_ops virtio_pci_config_nodev_ops = {
	.get		= NULL,
	.set		= NULL,
	.generation	= vp_generation,
	.get_status	= vp_get_status,
	.set_status	= vp_set_status,
	.reset		= vp_reset,
	.find_vqs	= vp_modern_find_vqs,
	.del_vqs	= vp_del_vqs,
	.synchronize_cbs = vp_synchronize_vectors,
	.get_features	= vp_get_features,
	.finalize_features = vp_finalize_features,
	.bus_name	= vp_bus_name,
	.set_vq_affinity = vp_set_vq_affinity,
	.get_vq_affinity = vp_get_vq_affinity,
	.get_shm_region  = vp_get_shm_region,
	.disable_vq_and_reset = vp_modern_disable_vq_and_reset,
	.enable_vq_after_reset = vp_modern_enable_vq_after_reset,
};

static const struct virtio_config_ops virtio_pci_config_ops = {
	.get		= vp_get,
	.set		= vp_set,
	.generation	= vp_generation,
	.get_status	= vp_get_status,
	.set_status	= vp_set_status,
	.reset		= vp_reset,
	.find_vqs	= vp_modern_find_vqs,
	.del_vqs	= vp_del_vqs,
	.synchronize_cbs = vp_synchronize_vectors,
	.get_features	= vp_get_features,
	.finalize_features = vp_finalize_features,
	.bus_name	= vp_bus_name,
	.set_vq_affinity = vp_set_vq_affinity,
	.get_vq_affinity = vp_get_vq_affinity,
	.get_shm_region  = vp_get_shm_region,
	.disable_vq_and_reset = vp_modern_disable_vq_and_reset,
	.enable_vq_after_reset = vp_modern_enable_vq_after_reset,
};

/* the PCI probing function */
int virtio_pci_modern_probe(struct virtio_pci_device *vp_dev)
{
	struct virtio_pci_modern_device *mdev = &vp_dev->mdev;
	struct pci_dev *pci_dev = vp_dev->pci_dev;
	int err;

	mdev->pci_dev = pci_dev;

	err = vp_modern_probe(mdev);
	if (err)
		return err;

	if (mdev->device)
		vp_dev->vdev.config = &virtio_pci_config_ops;
	else
		vp_dev->vdev.config = &virtio_pci_config_nodev_ops;

	vp_dev->config_vector = vp_config_vector;
	vp_dev->setup_vq = setup_vq;
	vp_dev->del_vq = del_vq;
	vp_dev->isr = mdev->isr;
	vp_dev->vdev.id = mdev->id;

	return 0;
}

void virtio_pci_modern_remove(struct virtio_pci_device *vp_dev)
{
	struct virtio_pci_modern_device *mdev = &vp_dev->mdev;

	vp_modern_remove(mdev);
}