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
|
/* Copyright (C) 2009 Red Hat, Inc.
* Author: Michael S. Tsirkin <mst@redhat.com>
*
* This work is licensed under the terms of the GNU GPL, version 2.
*
* test virtio server in host kernel.
*/
#include <linux/compat.h>
#include <linux/eventfd.h>
#include <linux/vhost.h>
#include <linux/miscdevice.h>
#include <linux/module.h>
#include <linux/mutex.h>
#include <linux/workqueue.h>
#include <linux/rcupdate.h>
#include <linux/file.h>
#include <linux/slab.h>
#include "test.h"
#include "vhost.c"
/* Max number of bytes transferred before requeueing the job.
* Using this limit prevents one virtqueue from starving others. */
#define VHOST_TEST_WEIGHT 0x80000
enum {
VHOST_TEST_VQ = 0,
VHOST_TEST_VQ_MAX = 1,
};
struct vhost_test {
struct vhost_dev dev;
struct vhost_virtqueue vqs[VHOST_TEST_VQ_MAX];
};
/* Expects to be always run from workqueue - which acts as
* read-size critical section for our kind of RCU. */
static void handle_vq(struct vhost_test *n)
{
struct vhost_virtqueue *vq = &n->dev.vqs[VHOST_TEST_VQ];
unsigned out, in;
int head;
size_t len, total_len = 0;
void *private;
private = rcu_dereference_check(vq->private_data, 1);
if (!private)
return;
mutex_lock(&vq->mutex);
vhost_disable_notify(&n->dev, vq);
for (;;) {
head = vhost_get_vq_desc(&n->dev, vq, vq->iov,
ARRAY_SIZE(vq->iov),
&out, &in,
NULL, NULL);
/* On error, stop handling until the next kick. */
if (unlikely(head < 0))
break;
/* Nothing new? Wait for eventfd to tell us they refilled. */
if (head == vq->num) {
if (unlikely(vhost_enable_notify(&n->dev, vq))) {
vhost_disable_notify(&n->dev, vq);
continue;
}
break;
}
if (in) {
vq_err(vq, "Unexpected descriptor format for TX: "
"out %d, int %d\n", out, in);
break;
}
len = iov_length(vq->iov, out);
/* Sanity check */
if (!len) {
vq_err(vq, "Unexpected 0 len for TX\n");
break;
}
vhost_add_used_and_signal(&n->dev, vq, head, 0);
total_len += len;
if (unlikely(total_len >= VHOST_TEST_WEIGHT)) {
vhost_poll_queue(&vq->poll);
break;
}
}
mutex_unlock(&vq->mutex);
}
static void handle_vq_kick(struct vhost_work *work)
{
struct vhost_virtqueue *vq = container_of(work, struct vhost_virtqueue,
poll.work);
struct vhost_test *n = container_of(vq->dev, struct vhost_test, dev);
handle_vq(n);
}
static int vhost_test_open(struct inode *inode, struct file *f)
{
struct vhost_test *n = kmalloc(sizeof *n, GFP_KERNEL);
struct vhost_dev *dev;
int r;
if (!n)
return -ENOMEM;
dev = &n->dev;
n->vqs[VHOST_TEST_VQ].handle_kick = handle_vq_kick;
r = vhost_dev_init(dev, n->vqs, VHOST_TEST_VQ_MAX);
if (r < 0) {
kfree(n);
return r;
}
f->private_data = n;
return 0;
}
static void *vhost_test_stop_vq(struct vhost_test *n,
struct vhost_virtqueue *vq)
{
void *private;
mutex_lock(&vq->mutex);
private = rcu_dereference_protected(vq->private_data,
lockdep_is_held(&vq->mutex));
rcu_assign_pointer(vq->private_data, NULL);
mutex_unlock(&vq->mutex);
return private;
}
static void vhost_test_stop(struct vhost_test *n, void **privatep)
{
*privatep = vhost_test_stop_vq(n, n->vqs + VHOST_TEST_VQ);
}
static void vhost_test_flush_vq(struct vhost_test *n, int index)
{
vhost_poll_flush(&n->dev.vqs[index].poll);
}
static void vhost_test_flush(struct vhost_test *n)
{
vhost_test_flush_vq(n, VHOST_TEST_VQ);
}
static int vhost_test_release(struct inode *inode, struct file *f)
{
struct vhost_test *n = f->private_data;
void *private;
vhost_test_stop(n, &private);
vhost_test_flush(n);
vhost_dev_cleanup(&n->dev);
/* We do an extra flush before freeing memory,
* since jobs can re-queue themselves. */
vhost_test_flush(n);
kfree(n);
return 0;
}
static long vhost_test_run(struct vhost_test *n, int test)
{
void *priv, *oldpriv;
struct vhost_virtqueue *vq;
int r, index;
if (test < 0 || test > 1)
return -EINVAL;
mutex_lock(&n->dev.mutex);
r = vhost_dev_check_owner(&n->dev);
if (r)
goto err;
for (index = 0; index < n->dev.nvqs; ++index) {
/* Verify that ring has been setup correctly. */
if (!vhost_vq_access_ok(&n->vqs[index])) {
r = -EFAULT;
goto err;
}
}
for (index = 0; index < n->dev.nvqs; ++index) {
vq = n->vqs + index;
mutex_lock(&vq->mutex);
priv = test ? n : NULL;
/* start polling new socket */
oldpriv = rcu_dereference_protected(vq->private_data,
lockdep_is_held(&vq->mutex));
rcu_assign_pointer(vq->private_data, priv);
r = vhost_init_used(&n->vqs[index]);
mutex_unlock(&vq->mutex);
if (r)
goto err;
if (oldpriv) {
vhost_test_flush_vq(n, index);
}
}
mutex_unlock(&n->dev.mutex);
return 0;
err:
mutex_unlock(&n->dev.mutex);
return r;
}
static long vhost_test_reset_owner(struct vhost_test *n)
{
void *priv = NULL;
long err;
mutex_lock(&n->dev.mutex);
err = vhost_dev_check_owner(&n->dev);
if (err)
goto done;
vhost_test_stop(n, &priv);
vhost_test_flush(n);
err = vhost_dev_reset_owner(&n->dev);
done:
mutex_unlock(&n->dev.mutex);
return err;
}
static int vhost_test_set_features(struct vhost_test *n, u64 features)
{
mutex_lock(&n->dev.mutex);
if ((features & (1 << VHOST_F_LOG_ALL)) &&
!vhost_log_access_ok(&n->dev)) {
mutex_unlock(&n->dev.mutex);
return -EFAULT;
}
n->dev.acked_features = features;
smp_wmb();
vhost_test_flush(n);
mutex_unlock(&n->dev.mutex);
return 0;
}
static long vhost_test_ioctl(struct file *f, unsigned int ioctl,
unsigned long arg)
{
struct vhost_test *n = f->private_data;
void __user *argp = (void __user *)arg;
u64 __user *featurep = argp;
int test;
u64 features;
int r;
switch (ioctl) {
case VHOST_TEST_RUN:
if (copy_from_user(&test, argp, sizeof test))
return -EFAULT;
return vhost_test_run(n, test);
case VHOST_GET_FEATURES:
features = VHOST_FEATURES;
if (copy_to_user(featurep, &features, sizeof features))
return -EFAULT;
return 0;
case VHOST_SET_FEATURES:
if (copy_from_user(&features, featurep, sizeof features))
return -EFAULT;
if (features & ~VHOST_FEATURES)
return -EOPNOTSUPP;
return vhost_test_set_features(n,
|