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
|
/*
* Virtio PCI driver
*
* 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
*
* Authors:
* Anthony Liguori <aliguori@us.ibm.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 <linux/module.h>
#include <linux/list.h>
#include <linux/pci.h>
#include <linux/interrupt.h>
#include <linux/virtio.h>
#include <linux/virtio_config.h>
#include <linux/virtio_ring.h>
#include <linux/virtio_pci.h>
#include <linux/highmem.h>
#include <linux/spinlock.h>
MODULE_AUTHOR("Anthony Liguori <aliguori@us.ibm.com>");
MODULE_DESCRIPTION("virtio-pci");
MODULE_LICENSE("GPL");
MODULE_VERSION("1");
/* Our device structure */
struct virtio_pci_device
{
struct virtio_device vdev;
struct pci_dev *pci_dev;
/* the IO mapping for the PCI config space */
void __iomem *ioaddr;
/* a list of queues so we can dispatch IRQs */
spinlock_t lock;
struct list_head virtqueues;
};
struct virtio_pci_vq_info
{
/* the actual virtqueue */
struct virtqueue *vq;
/* the number of entries in the queue */
int num;
/* the index of the queue */
int queue_index;
/* the virtual address of the ring queue */
void *queue;
/* the list node for the virtqueues list */
struct list_head node;
};
/* Qumranet donated their vendor ID for devices 0x1000 thru 0x10FF. */
static struct pci_device_id virtio_pci_id_table[] = {
{ 0x1af4, PCI_ANY_ID, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0 },
{ 0 },
};
MODULE_DEVICE_TABLE(pci, virtio_pci_id_table);
/* A PCI device has it's own struct device and so does a virtio device so
* we create a place for the virtio devices to show up in sysfs. I think it
* would make more sense for virtio to not insist on having it's own device. */
static struct device virtio_pci_root = {
.parent = NULL,
.bus_id = "virtio-pci",
};
/* Unique numbering for devices under the kvm root */
static unsigned int dev_index;
/* Convert a generic virtio device to our structure */
static struct virtio_pci_device *to_vp_device(struct virtio_device *vdev)
{
return container_of(vdev, struct virtio_pci_device, vdev);
}
/* virtio config->feature() implementation */
static bool vp_feature(struct virtio_device *vdev, unsigned bit)
{
struct virtio_pci_device *vp_dev = to_vp_device(vdev);
u32 mask;
/* Since this function is supposed to have the side effect of
* enabling a queried feature, we simulate that by doing a read
* from the host feature bitmask and then writing to the guest
* feature bitmask */
mask = ioread32(vp_dev->ioaddr + VIRTIO_PCI_HOST_FEATURES);
if (mask & (1 << bit)) {
mask |= (1 << bit);
iowrite32(mask, vp_dev->ioaddr + VIRTIO_PCI_GUEST_FEATURES);
}
return !!(mask & (1 << bit));
}
/* virtio config->get() implementation */
static void vp_get(struct virtio_device *vdev, unsigned offset,
void *buf, unsigned len)
{
struct virtio_pci_device *vp_dev = to_vp_device(vdev);
void __iomem *ioaddr = vp_dev->ioaddr + VIRTIO_PCI_CONFIG + offset;
u8 *ptr = buf;
int i;
for (i = 0; i < len; i++)
ptr[i] = ioread8(ioaddr + i);
}
/* the config->set() implementation. it's symmetric to the config->get()
* implementation */
static void vp_set(struct virtio_device *vdev, unsigned offset,
const void *buf, unsigned len)
{
struct virtio_pci_device *vp_dev = to_vp_device(vdev);
void __iomem *ioaddr = vp_dev->ioaddr + VIRTIO_PCI_CONFIG + offset;
const u8 *ptr = buf;
int i;
for (i = 0; i < len; i++)
iowrite8(ptr[i], ioaddr + i);
}
/* 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 ioread8(vp_dev->ioaddr + VIRTIO_PCI_STATUS);
}
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);
return iowrite8(status, vp_dev->ioaddr + VIRTIO_PCI_STATUS);
}
static void vp_reset(struct virtio_device *vdev)
{
struct virtio_pci_device *vp_dev = to_vp_device(vdev);
/* 0 status means a reset. */
return iowrite8(0, vp_dev->ioaddr + VIRTIO_PCI_STATUS);
}
/* the notify function used when creating a virt queue */
static void vp_notify(struct virtqueue *vq)
{
struct virtio_pci_device *vp_dev = to_vp_device(vq->vdev);
struct virtio_pci_vq_info *info = vq->priv;
/* we write the queue's selector into the notification register to
* signal the other end */
iowrite16(info->queue_index, vp_dev->ioaddr + VIRTIO_PCI_QUEUE_NOTIFY);
}
/* 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;
struct virtio_pci_vq_info *info;
irqreturn_t ret = IRQ_NONE;
unsigned long flags;
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->ioaddr + VIRTIO_PCI_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) {
struct virtio_driver *drv;
drv = container_of(vp_dev->vdev.dev.driver,
struct virtio_driver, driver);
if (drv->config_changed)
drv->config_changed(&vp_dev->vdev);
}
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;
}
/* the config->find_vq() implementation */
static struct virtqueue *vp_find_vq(struct virtio_device *vdev, unsigned index,
void (*callback)(struct virtqueue *vq))
{
struct virtio_pci_device *vp_dev = to_vp_device(vdev);
struct virtio_pci_vq_info *info;
struct virtqueue *vq;
unsigned long flags;
u16 num;
int err;
/* Select the queue we're interested in */
iowrite16(index, vp_dev->ioaddr + VIRTIO_PCI_QUEUE_SEL);
/* Check if queue is either not available or already active. */
num = ioread16(vp_dev->ioaddr + VIRTIO_PCI_QUEUE_NUM);
if (!num || ioread32(vp_dev->ioaddr + VIRTIO_PCI_QUEUE_PFN))
return ERR_PTR(-ENOENT);
/* allocate and fill out our structure the represents an active
* queue */
info = kmalloc(sizeof(struct virtio_pci_vq_info), GFP_KERNEL);
if (!info)
return ERR_PTR(-ENOMEM);
info->queue_index = index;
info->num = num;
info->queue = kzalloc(PAGE_ALIGN(vring_size(num,PAGE_SIZE)), GFP_KERNEL);
if (info->queue == NULL) {
err = -ENOMEM;
goto out_info;
}
/* activate the queue */
iowrite32(virt_to_phys(info->queue) >> PAGE_SHIFT,
vp_dev->ioaddr + VIRTIO_PCI_QUEUE_PFN);
/* create the vring */
vq = vring_new_virtqueue(info->num, vdev, info->queue,
vp_notify, callback);
if (!vq) {
err = -ENOMEM;
goto out_activate_queue;
}
vq->priv = info;
info->vq = vq;
spin_lock_irqsave(&vp_dev->lock, flags);
list_add(&info->node, &vp_dev->virtqueues);
spin_unlock_irqrestore(&vp_dev->lock, flags);
<
|