summaryrefslogtreecommitdiff
path: root/drivers/virtio/virtio_pci_common.c
blob: 953057d84185df93b54bc46081532d762e9ed9f3 (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
/*
 * Virtio PCI driver - common functionality for all device versions
 *
 * 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>
 *
 * This work is licensed under the terms of the GNU GPL, version 2 or later.
 * See the COPYING file in the top-level directory.
 *
 */

#include "virtio_pci_common.h"

/* wait for pending irq handlers */
void vp_synchronize_vectors(struct virtio_device *vdev)
{
	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
	int i;

	if (vp_dev->intx_enabled)
		synchronize_irq(vp_dev->pci_dev->irq);

	for (i = 0; i < vp_dev->msix_vectors; ++i)
		synchronize_irq(vp_dev->msix_entries[i].vector);
}

/* the notify function used when creating a virt queue */
bool vp_notify(struct virtqueue *vq)
{
	/* we write the queue's selector into the notification register to
	 * signal the other end */
	iowrite16(vq->index, (void __iomem *)vq->priv);
	return true;
}

/* Handle a configuration change: Tell driver if it wants to know. */
static irqreturn_t vp_config_changed(int irq, void *opaque)
{
	struct virtio_pci_device *vp_dev = opaque;

	virtio_config_changed(&vp_dev->vdev);
	return IRQ_HANDLED;
}

/* Notify all virtqueues on an interrupt. */
static irqreturn_t vp_vring_interrupt(int irq, void *opaque)
{
	struct virtio_pci_device *vp_dev = opaque;
	struct virtio_pci_vq_info *info;
	irqreturn_t ret = IRQ_NONE;
	unsigned long flags;

	spin_lock_irqsave(&vp_dev->lock, flags);
	list_for_each_entry(info, &vp_dev->virtqueues, node) {
		if (vring_interrupt(irq, info->vq) == IRQ_HANDLED)
			ret = IRQ_HANDLED;
	}
	spin_unlock_irqrestore(&vp_dev->lock, flags);

	return ret;
}

/* A small wrapper to also acknowledge the interrupt when it's handled.
 * I really need an EIO hook for the vring so I can ack the interrupt once we
 * know that we'll be handling the IRQ but before we invoke the callback since
 * the callback may notify the host which results in the host attempting to
 * raise an interrupt that we would then mask once we acknowledged the
 * interrupt. */
static irqreturn_t vp_interrupt(int irq, void *opaque)
{
	struct virtio_pci_device *vp_dev = opaque;
	u8 isr;

	/* reading the ISR has the effect of also clearing it so it's very
	 * important to save off the value. */
	isr = ioread8(vp_dev->isr);

	/* It's definitely not us if the ISR was not high */
	if (!isr)
		return IRQ_NONE;

	/* Configuration change?  Tell driver if it wants to know. */
	if (isr & VIRTIO_PCI_ISR_CONFIG)
		vp_config_changed(irq, opaque);

	return vp_vring_interrupt(irq, opaque);
}

static void vp_free_vectors(struct virtio_device *vdev)
{
	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
	int i;

	if (vp_dev->intx_enabled) {
		free_irq(vp_dev->pci_dev->irq, vp_dev);
		vp_dev->intx_enabled = 0;
	}

	for (i = 0; i < vp_dev->msix_used_vectors; ++i)
		free_irq(vp_dev->msix_entries[i].vector, vp_dev);

	for (i = 0; i < vp_dev->msix_vectors; i++)
		if (vp_dev->msix_affinity_masks[i])
			free_cpumask_var(vp_dev->msix_affinity_masks[i]);

	if (vp_dev->msix_enabled) {
		/* Disable the vector used for configuration */
		vp_dev->config_vector(vp_dev, VIRTIO_MSI_NO_VECTOR);

		pci_disable_msix(vp_dev->pci_dev);
		vp_dev->msix_enabled = 0;
	}

	vp_dev->msix_vectors = 0;
	vp_dev->msix_used_vectors = 0;
	kfree(vp_dev->msix_names);
	vp_dev->msix_names = NULL;
	kfree(vp_dev->msix_entries);
	vp_dev->msix_entries = NULL;
	kfree(vp_dev->msix_affinity_masks);
	vp_dev->msix_affinity_masks = NULL;
}

static int vp_request_msix_vectors(struct virtio_device *vdev, int nvectors,
				   bool per_vq_vectors)
{
	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
	const char *name = dev_name(&vp_dev->vdev.dev);
	unsigned i, v;
	int err = -ENOMEM;

	vp_dev->msix_vectors = nvectors;

	vp_dev->msix_entries = kmalloc(nvectors * sizeof *vp_dev->msix_entries,
				       GFP_KERNEL);
	if (!vp_dev->msix_entries)
		goto error;
	vp_dev->msix_names = kmalloc(nvectors * sizeof *vp_dev->msix_names,
				     GFP_KERNEL);
	if (!vp_dev->msix_names)
		goto error;
	vp_dev->msix_affinity_masks
		= kzalloc(nvectors * sizeof *vp_dev->msix_affinity_masks,
			  GFP_KERNEL);
	if (!vp_dev->msix_affinity_masks)
		goto error;
	for (i = 0; i < nvectors; ++i)
		if (!alloc_cpumask_var(&vp_dev->msix_affinity_masks[i],
					GFP_KERNEL))
			goto error;

	for (i = 0; i < nvectors; ++i)
		vp_dev->msix_entries[i].entry = i;

	err = pci_enable_msix_exact(vp_dev->pci_dev,
				    vp_dev->msix_entries, nvectors);
	if (err)
		goto error;
	vp_dev->msix_enabled = 1;

	/* Set the vector used for configuration */
	v = vp_dev->msix_used_vectors;
	snprintf(vp_dev->msix_names[v], sizeof *vp_dev->msix_names,
		 "%s-config", name);
	err = request_irq(vp_dev->msix_entries[v].vector,
			  vp_config_changed, 0, vp_dev->msix_names[v],
			  vp_dev);
	if (err)
		goto error;
	++vp_dev->msix_used_vectors;

	v = vp_dev->config_vector(vp_dev, v);
	/* Verify we had enough resources to assign the vector */
	if (v == VIRTIO_MSI_NO_VECTOR) {
		err = -EBUSY;
		goto error;
	}

	if (!per_vq_vectors) {
		/* Shared vector for all VQs */
		v = vp_dev->msix_used_vectors;
		snprintf(vp_dev->msix_names[v], sizeof *vp_dev->msix_names,
			 "%s-virtqueues", name);
		err = request_irq(vp_dev->msix_entries[v].vector,
				  vp_vring_interrupt, 0, vp_dev->msix_names[v],
				  vp_dev);
		if (err)
			goto error;
		++vp_dev->msix_used_vectors;
	}
	return 0;
error:
	vp_free_vectors(vdev);
	return err;
}

static int vp_request_intx(struct virtio_device *vdev)
{
	int err;
	struct virtio_pci_device *vp_dev = to_vp_device(vdev);

	err = request_irq(vp_dev->pci_dev->irq, vp_interrupt,
			  IRQF_SHARED, dev_name(&vdev->dev), vp_dev);
	if (!err)
		vp_dev->intx_enabled = 1;
	return err;
}

static struct virtqueue *vp_setup_vq(struct virtio_device *vdev, unsigned index,
				     void (*callback)(struct virtqueue *vq),
				     const char *name,
				     u16 msix_vec)
{
	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
	struct virtio_pci_vq_info *info = kmalloc(sizeof *info, GFP_KERNEL);
	struct virtqueue *vq;
	unsigned long flags;

	/* fill out our structure that represents an active queue */
	if (!info)
		return ERR_PTR(-ENOMEM);

	vq = vp_dev->setup_vq(vp_dev, info, index, callback, name, msix_vec);
	if (IS_ERR(vq))
		goto out_info;

	info->vq = vq;
	if (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);
	}

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

out_info:
	kfree(info);
	return vq;
}

static void vp_del_vq(struct virtqueue *vq)
{
	struct virtio_pci_device *vp_dev = to_vp_device(vq->vdev);
	struct virtio_pci_vq_info *info = vp_dev->vqs[vq->index];
	unsigned long flags;

	spin_lock_irqsave(&vp_dev->lock, flags);
	list_del(&info->node);
	spin_unlock_irqrestore(&vp_dev->lock, flags);

	vp_dev->del_vq(info);
	kfree(info);
}

/* the config->del_vqs() implementation */
void vp_del_vqs(struct virtio_device *vdev)
{
	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
	struct virtqueue *vq, *n;
	struct virtio_pci_vq_info *info;

	list_for_each_entry_safe(vq, n, &vdev->vqs, list) {
		info = vp_dev->vqs[vq->index];
		if (vp_dev->per_vq_vectors &&
			info->msix_vector != VIRTIO_MSI_NO_VECTOR)
			free_irq(vp_dev->msix_entries[info->msix_vector].vector,
				 vq);
		vp_del_vq(vq);
	}
	vp_dev->per_vq_vectors = false;

	vp_free_vectors(vdev);
	kfree(vp_dev->vqs);
}

static int vp_try_to_find_vqs(struct virtio_device *vdev, unsigned nvqs,
			      struct virtqueue *vqs[],
			      vq_callback_t *callbacks[],
			      const char *names[],
			      bool use_msix,
			      bool per_vq_vectors)
{
	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
	u16 msix_vec;
	int i, err, nvectors, allocated_vectors;

	vp_dev->vqs = kmalloc(nvqs * sizeof *vp_dev->vqs, GFP_KERNEL);
	if (!vp_dev->vqs)
		return -ENOMEM;

	if (!use_msix) {
		/* Old style: one normal interrupt for change and all vqs. */
		err = vp_request_intx(vdev);
		if (err)
			goto error_find;
	} else {
		if (per_vq_vectors) {
			/* Best option: one for change interrupt, one per vq. */
			nvectors = 1;
			for (i = 0; i < nvqs; ++i)
				if (callbacks[i])
					++nvectors;
		} else {
			/* Second best: one for change, shared for all vqs. */
			nvectors = 2;
		}

		err = vp_request_msix_vectors(vdev, nvectors, per_vq_vectors);
		if (err)
			goto error_find;
	}

	vp_dev->per_vq_vectors = per_vq_vectors;
	allocated_vectors = vp_dev->msix_used_vectors;
	for (i = 0; i < nvqs; ++i) {
		if (!names[i]) {
			vqs[i] = NULL;
			continue;
		} else if (!callbacks[i] || !vp_dev->msix_enabled)
			msix_vec = VIRTIO_MSI_NO_VECTOR;
		else if (vp_dev->per_vq_vectors)
			msix_vec = allocated_vectors++;
		else
			msix_vec = VP_MSIX_VQ_VECTOR;
		vqs[i] = vp_setup_vq(vdev, i, callbacks[i], names[i], msix_vec);
		if (IS_ERR(vqs[i])) {
			err = PTR_ERR(vqs[i]);
			goto error_find;
		}

		if (!vp_dev->per_vq_vectors || msix_vec == VIRTIO_MSI_NO_VECTOR)
			continue;

		/* allocate per-vq irq if available and necessary */
		snprintf(vp_dev->msix_names[msix_vec],
			 sizeof *vp_dev->msix_names,
			 "%s-%s",
			 dev_name(&vp_dev->vdev.dev), names[i]);
		err = request_irq(vp_dev->msix_entries[msix_vec].vector,
				  vring_interrupt, 0,
				  vp_dev->msix_names[msix_vec],
				  vqs[i]);
		if (err) {
			vp_del_vq(vqs[i]);
			goto error_find;
		}
	}
	return 0;

error_find:
	vp_del_vqs(vdev);
	return err;
}

/* the config->find_vqs() implementation */
int vp_find_vqs(struct virtio_device *vdev, unsigned nvqs,
		struct virtqueue *vqs[],
		vq_callback_t *callbacks[],
		const char *names[])
{
	int err;

	/* Try MSI-X with one vector per queue. */
	err = vp_try_to_find_vqs(vdev, nvqs, vqs, callbacks, names, true, true);
	if (!err)
		return 0;
	/* Fallback: MSI-X with one vector for config, one shared for queues. */
	err = vp_try_to_find_vqs(vdev, nvqs, vqs, callbacks, names,
				 true, false);
	if (!err)
		return 0;
	/* Finally fall back to regular interrupts. */
	return vp_try_to_find_vqs(vdev, nvqs, vqs, callbacks, names,
				  false, false);
}

const char *vp_bus_name(struct virtio_device *vdev)
{
	struct virtio_pci_device *vp_dev = to_vp_device(vdev);

	return pci_name(vp_dev->pci_dev);
}

/* Setup the affinity for a virtqueue:
 * - force the affinity for per vq vector
 * - OR over all affinities for shared MSI
 * - ignore the affinity request if we're using INTX
 */
int vp_set_vq_affinity(struct virtqueue *vq, int cpu)
{
	struct virtio_device *vdev = vq->vdev;
	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
	struct virtio_pci_vq_info *info = vp_dev->vqs[vq->index];
	struct cpumask *mask;
	unsigned int irq;

	if (!vq->callback)
		return -EINVAL;

	if (vp_dev->msix_enabled) {
		mask = vp_dev->msix_affinity_masks[info->msix_vector];
		irq = vp_dev->msix_entries[info->msix_vector].vector;
		if (cpu == -1)
			irq_set_affinity_hint(irq, NULL);
		else {
			cpumask_set_cpu(cpu, mask);
			irq_set_affinity_hint(irq, mask);
		}
	}
	return 0;
}

void virtio_pci_release_dev(struct device *_d)
{
	/*
	 * No need for a release method as we allocate/free
	 * all devices together with the pci devices.
	 * Provide an empty one to avoid getting a warning from core.
	 */
}

#ifdef CONFIG_PM_SLEEP
static int virtio_pci_freeze(struct device *dev)
{
	struct pci_dev *pci_dev = to_pci_dev(dev);
	struct virtio_pci_device *vp_dev = pci_get_drvdata(pci_dev);
	int ret;

	ret = virtio_device_freeze(&vp_dev->vdev);

	if (!ret)
		pci_disable_device(pci_dev);
	return ret;
}

static int virtio_pci_restore(struct device *dev)
{
	struct pci_dev *pci_dev = to_pci_dev(dev);
	struct virtio_pci_device *vp_dev = pci_get_drvdata(pci_dev);
	int ret;

	ret = pci_enable_device(pci_dev);
	if (ret)
		return ret;

	pci_set_master(pci_dev);
	return virtio_device_restore(&vp_dev->vdev);
}

const struct dev_pm_ops virtio_pci_pm_ops = {
	SET_SYSTEM_SLEEP_PM_OPS(virtio_pci_freeze, virtio_pci_restore)
};
#endif