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
|
/*P:050 Lguest guests use a very simple method to describe devices. It's a
* series of device descriptors contained just above the top of normal
* memory.
*
* We use the standard "virtio" device infrastructure, which provides us with a
* console, a network and a block driver. Each one expects some configuration
* information and a "virtqueue" mechanism to send and receive data. :*/
#include <linux/init.h>
#include <linux/bootmem.h>
#include <linux/lguest_launcher.h>
#include <linux/virtio.h>
#include <linux/virtio_config.h>
#include <linux/interrupt.h>
#include <linux/virtio_ring.h>
#include <linux/err.h>
#include <asm/io.h>
#include <asm/paravirt.h>
#include <asm/lguest_hcall.h>
/* The pointer to our (page) of device descriptions. */
static void *lguest_devices;
/* Unique numbering for lguest devices. */
static unsigned int dev_index;
/* For Guests, device memory can be used as normal memory, so we cast away the
* __iomem to quieten sparse. */
static inline void *lguest_map(unsigned long phys_addr, unsigned long pages)
{
return (__force void *)ioremap(phys_addr, PAGE_SIZE*pages);
}
static inline void lguest_unmap(void *addr)
{
iounmap((__force void __iomem *)addr);
}
/*D:100 Each lguest device is just a virtio device plus a pointer to its entry
* in the lguest_devices page. */
struct lguest_device {
struct virtio_device vdev;
/* The entry in the lguest_devices page for this device. */
struct lguest_device_desc *desc;
};
/* Since the virtio infrastructure hands us a pointer to the virtio_device all
* the time, it helps to have a curt macro to get a pointer to the struct
* lguest_device it's enclosed in. */
#define to_lgdev(vdev) container_of(vdev, struct lguest_device, vdev)
/*D:130
* Device configurations
*
* The configuration information for a device consists of a series of fields.
* We don't really care what they are: the Launcher set them up, and the driver
* will look at them during setup.
*
* For us these fields come immediately after that device's descriptor in the
* lguest_devices page.
*
* Each field starts with a "type" byte, a "length" byte, then that number of
* bytes of configuration information. The device descriptor tells us the
* total configuration length so we know when we've reached the last field. */
/* type + length bytes */
#define FHDR_LEN 2
/* This finds the first field of a given type for a device's configuration. */
static void *lg_find(struct virtio_device *vdev, u8 type, unsigned int *len)
{
struct lguest_device_desc *desc = to_lgdev(vdev)->desc;
int i;
for (i = 0; i < desc->config_len; i += FHDR_LEN + desc->config[i+1]) {
if (desc->config[i] == type) {
/* Mark it used, so Host can know we looked at it, and
* also so we won't find the same one twice. */
desc->config[i] |= 0x80;
/* Remember, the second byte is the length. */
*len = desc->config[i+1];
/* We return a pointer to the field header. */
return desc->config + i;
}
}
/* Not found: return NULL for failure. */
return NULL;
}
/* Once they've found a field, getting a copy of it is easy. */
static void lg_get(struct virtio_device *vdev, void *token,
void *buf, unsigned len)
{
/* Check they didn't ask for more than the length of the field! */
BUG_ON(len > ((u8 *)token)[1]);
memcpy(buf, token + FHDR_LEN, len);
}
/* Setting the contents is also trivial. */
static void lg_set(struct virtio_device *vdev, void *token,
const void *buf, unsigned len)
{
BUG_ON(len > ((u8 *)token)[1]);
memcpy(token + FHDR_LEN, buf, len);
}
/* The operations to get and set the status word just access the status field
* of the device descriptor. */
static u8 lg_get_status(struct virtio_device *vdev)
{
return to_lgdev(vdev)->desc->status;
}
static void lg_set_status(struct virtio_device *vdev, u8 status)
{
to_lgdev(vdev)->desc->status = status;
}
/*
* Virtqueues
*
* The other piece of infrastructure virtio needs is a "virtqueue": a way of
* the Guest device registering buffers for the other side to read from or
* write into (ie. send and receive buffers). Each device can have multiple
* virtqueues: for example the console driver uses one queue for sending and
* another for receiving.
*
* Fortunately for us, a very fast shared-memory-plus-descriptors virtqueue
* already exists in virtio_ring.c. We just need to connect it up.
*
* We start with the information we need to keep about each virtqueue.
*/
/*D:140 This is the information we remember about each virtqueue. */
struct lguest_vq_info
{
/* A copy of the information contained in the device config. */
struct lguest_vqconfig config;
/* The address where we mapped the virtio ring, so we can unmap it. */
void *pages;
};
/* When the virtio_ring code wants to prod the Host, it calls us here and we
* make a hypercall. We hand the page number of the virtqueue so the Host
* knows which virtqueue we're talking about. */
static void lg_notify(struct virtqueue *vq)
{
/* We store our virtqueue information in the "priv" pointer of the
* virtqueue structure. */
struct lguest_vq_info *lvq = vq->priv;
hcall(LHCALL_NOTIFY, lvq->config.pfn << PAGE_SHIFT, 0, 0);
}
/* This routine finds the first virtqueue described in the configuration of
* this device and sets it up.
*
* This is kind of an ugly duckling. It'd be nicer to have a standard
* representation of a virtqueue in the configuration space, but it seems that
* everyone wants to do it differently. The KVM coders want the Guest to
* allocate its own pages and tell the Host where they are, but for lguest it's
* simpler for the Host to simply tell us where the pages are.
*
* So we provide devices with a "find virtqueue and set it up" function. */
static struct virtqueue *lg_find_vq(struct virtio_device *vdev,
bool (*callback)(struct virtqueue *vq))
{
struct lguest_vq_info *lvq;
struct virtqueue *vq;
unsigned int len;
void *token;
int err;
/* Look for a field of the correct type to mark a virtqueue. Note that
* if this succeeds, then the type will be changed so it won't be found
* again, and future lg_find_vq() calls will find the next
* virtqueue (if any). */
token = vdev->config->find(vdev, VIRTIO_CONFIG_F_VIRTQUEUE, &len);
if (!token)
return ERR_PTR(-ENOENT);
lvq = kmalloc(sizeof(*lvq), GFP_KERNEL);
if (!lvq)
return ERR_PTR(-ENOMEM);
/* Note: we could use a configuration space inside here, just like we
* do for the device. This would allow expansion in future, because
* our configuration system is designed to be expansible. But this is
* way easier. */
if (len != sizeof(lvq->config)) {
dev_err(&vdev->dev, "Unexpected virtio config len %u\n", len);
err = -EIO;
goto free_lvq;
}
/* Make a copy of the "struct lguest_vqconfig" field. We need a copy
* because the config space might not be aligned correctly. */
vdev->config->get(vdev, token, &lvq->config, sizeof(lvq->config));
/* Figure out how many pages the ring will take, and map that memory */
lvq->pages = lguest_map((unsigned long)lvq->config.pfn << PAGE_SHIFT,
DIV_ROUND_UP(vring_size(lvq->config.num,
PAGE_SIZE),
PAGE_SIZE));
if (!lvq->pages) {
err = -ENOMEM;
goto free_lvq;
}
/* OK, tell virtio_ring.c to set up a virtqueue now we know its size
* and we've got a pointer to its pages. */
vq = vring_new_virtqueue(lvq->config.num, vdev, lvq->pages,
lg_notify, callback);
if (!vq) {
err = -ENOMEM;
goto unmap;
}
/* Tell the interrupt for this virtqueue to go to the virtio_ring
* interrupt handler. */
/* FIXME: We used to have a flag for the Host to tell us we could use
* the interrupt as a source of randomness: it'd be nice to have that
* back.. */
err = request_irq(lvq->config.irq, vring_interrupt, IRQF_SHARED,
vdev->dev.bus_id, vq);
if (err)
goto destroy_vring;
/* Last of all we hook up our 'struct lguest_vq_info" to the
* virtqueue's priv pointer. */
vq->priv = lvq;
return vq;
destroy_vring:
vring_del_virtqueue(vq);
unmap:
lguest_unmap(lvq->pages);
free_lvq:
kfree(lvq);
return ERR_PTR(err);
}
/*:*/
/* Cleaning up a virtqueue is easy */
static void lg_del_vq(struct virtqueue *vq)
{
struct lguest_vq_info *lvq = vq->priv;
/* Release the interrupt */
free_irq(lvq->config.irq, vq);
/* Tell virtio_ring.c to free the virtqueue. */
vring_del_virtqueue(vq);
/* Unmap the pages containing the ring. */
lguest_unmap(lvq->pages);
/* Free our own queue information. */
kfree(lvq);
}
/* The ops structure which hooks everything together. */
static struct virtio_config_ops lguest_config_ops = {
.find = lg_find,
.get = lg_get,
.set = lg_set,
.get_status = lg_get_status,
.set_status = lg_set_status,
.find_vq = lg_find_vq,
.del_vq = lg_del_vq,
};
/* The root device for the lguest virtio devices. This makes them appear as
* /sys/devices/lguest/0,1,2 not /sys/devices/0,1,2. */
static struct device lguest_root = {
.parent = NULL,
.bus_id = "lguest",
};
/*D:120 This is the core of the lguest bus: actually adding a new device.
* It's a separate function because it's neater that way, and because an
* earlier version of the code supported hotplug and unplug. They were removed
* early on because they were never used.
*
* As Andrew Tridgell says, "Untested code is buggy code".
*
* It's worth reading this carefully: we start with a pointer to the new device
* descriptor in the "lguest_devices" page. */
static void add_lguest_device(struct lguest_device_desc *d)
{
struct lguest_device *ldev;
/* Start with zeroed memory; Linux's device layer seems to count on
* it. */
ldev = kzalloc(sizeof(*ldev), GFP_KERNEL);
if (!ldev) {
printk(KERN_EMERG "Cannot allocate lguest dev %u\n",
dev_index++);
return;
}
/* This devices' parent is the lguest/ dir. */
ldev->vdev.dev.parent = &lguest_root;
/* We have a unique device index thanks to the dev_index counter. */
ldev->vdev.index = dev_index++;
/* The device type comes straight from the descriptor. There's also a
* device vendor field in the virtio_device struct, which we leave as
* 0. */
ldev->vdev.id.device = d->type;
/* We have a simple set of routines for querying the device's
* configuration information and setting its status. */
ldev->vdev.config = &lguest_config_ops;
/* And we remember the device's descriptor for lguest_config_ops. */
ldev->desc = d;
/* register_virtio_device() sets up the generic fields for the struct
* virtio_device and calls device_register(). This makes the bus
* infrastructure look for a matching driver. */
if (register_virtio_device(&ldev->vdev) != 0) {
printk(
|