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
|
/*
* An implementation of host initiated guest snapshot.
*
*
* Copyright (C) 2013, Microsoft, Inc.
* Author : K. Y. Srinivasan <kys@microsoft.com>
*
* This program is free software; you can redistribute it and/or modify it
* under the terms of the GNU General Public License version 2 as published
* by the Free Software Foundation.
*
* This program is distributed in the hope that it will be useful, but
* WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
* NON INFRINGEMENT. See the GNU General Public License for more
* details.
*
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/net.h>
#include <linux/nls.h>
#include <linux/connector.h>
#include <linux/workqueue.h>
#include <linux/hyperv.h>
#include "hyperv_vmbus.h"
#include "hv_utils_transport.h"
#define VSS_MAJOR 5
#define VSS_MINOR 0
#define VSS_VERSION (VSS_MAJOR << 16 | VSS_MINOR)
#define VSS_USERSPACE_TIMEOUT (msecs_to_jiffies(10 * 1000))
/*
* Global state maintained for transaction that is being processed. For a class
* of integration services, including the "VSS service", the specified protocol
* is a "request/response" protocol which means that there can only be single
* outstanding transaction from the host at any given point in time. We use
* this to simplify memory management in this driver - we cache and process
* only one message at a time.
*
* While the request/response protocol is guaranteed by the host, we further
* ensure this by serializing packet processing in this driver - we do not
* read additional packets from the VMBUs until the current packet is fully
* handled.
*/
static struct {
int state; /* hvutil_device_state */
int recv_len; /* number of bytes received. */
struct vmbus_channel *recv_channel; /* chn we got the request */
u64 recv_req_id; /* request ID. */
struct hv_vss_msg *msg; /* current message */
void *vss_context; /* for the channel callback */
} vss_transaction;
static void vss_respond_to_host(int error);
/*
* This state maintains the version number registered by the daemon.
*/
static int dm_reg_value;
static const char vss_devname[] = "vmbus/hv_vss";
static __u8 *recv_buffer;
static struct hvutil_transport *hvt;
static void vss_send_op(struct work_struct *dummy);
static void vss_timeout_func(struct work_struct *dummy);
static DECLARE_DELAYED_WORK(vss_timeout_work, vss_timeout_func);
static DECLARE_WORK(vss_send_op_work, vss_send_op);
/*
* Callback when data is received from user mode.
*/
static void vss_timeout_func(struct work_struct *dummy)
{
/*
* Timeout waiting for userspace component to reply happened.
*/
pr_warn("VSS: timeout waiting for daemon to reply\n");
vss_respond_to_host(HV_E_FAIL);
/* Transaction is finished, reset the state. */
if (vss_transaction.state > HVUTIL_READY)
vss_transaction.state = HVUTIL_READY;
hv_poll_channel(vss_transaction.vss_context,
hv_vss_onchannelcallback);
}
static int vss_handle_handshake(struct hv_vss_msg *vss_msg)
{
u32 our_ver = VSS_OP_REGISTER1;
switch (vss_msg->vss_hdr.operation) {
case VSS_OP_REGISTER:
/* Daemon doesn't expect us to reply */
dm_reg_value = VSS_OP_REGISTER;
break;
case VSS_OP_REGISTER1:
/* Daemon expects us to reply with our own version*/
if (hvutil_transport_send(hvt, &our_ver, sizeof(our_ver)))
return -EFAULT;
dm_reg_value = VSS_OP_REGISTER1;
break;
default:
return -EINVAL;
}
vss_transaction.state = HVUTIL_READY;
pr_debug("VSS: userspace daemon ver. %d registered\n", dm_reg_value);
return 0;
}
static int vss_on_msg(void *msg, int len)
{
struct hv_vss_msg *vss_msg = (struct hv_vss_msg *)msg;
if (len != sizeof(*vss_msg))
return -EINVAL;
if (vss_msg->vss_hdr.operation == VSS_OP_REGISTER ||
vss_msg->vss_hdr.operation == VSS_OP_REGISTER1) {
/*
* Don't process registration messages if we're in the middle
* of a transaction processing.
*/
if (vss_transaction.state > HVUTIL_READY)
return -EINVAL;
return vss_handle_handshake(vss_msg);
} else if (vss_transaction.state == HVUTIL_USERSPACE_REQ) {
vss_transaction.state = HVUTIL_USERSPACE_RECV;
if (cancel_delayed_work_sync(&vss_timeout_work)) {
vss_respond_to_host(vss_msg->error);
/* Transaction is finished, reset the state. */
vss_transaction.state = HVUTIL_READY;
hv_poll_channel(vss_transaction.vss_context,
hv_vss_onchannelcallback);
}
} else {
/* This is a spurious call! */
pr_warn("VSS: Transaction not active\n");
return -EINVAL;
}
return 0;
}
static void vss_send_op(struct work_struct *dummy)
{
int op = vss_transaction.msg->vss_hdr.operation;
int rc;
struct hv_vss_msg *vss_msg;
/* The transaction state is wrong. */
if (vss_transaction.state != HVUTIL_HOSTMSG_RECEIVED)
return;
vss_msg = kzalloc(sizeof(*vss_msg), GFP_KERNEL);
if (!vss_msg)
return;
vss_msg->vss_hdr.operation = op;
vss_transaction.state = HVUTIL_USERSPACE_REQ;
rc = hvutil_transport_send(hvt, vss_msg, sizeof(*vss_msg));
if (rc) {
pr_warn("VSS: failed to communicate to the daemon: %d\n", rc);
if (cancel_delayed_work_sync(&vss_timeout_work)) {
vss_respond_to_host(HV_E_FAIL);
vss_transaction.state = HVUTIL_READY;
}
}
kfree(vss_msg);
return;
}
/*
* Send a response back to the host.
*/
static void
vss_respond_to_host(int error)
{
struct icmsg_hdr *icmsghdrp;
u32 buf_len;
struct vmbus_channel *channel;
u64 req_id;
/*
* Copy the global state for completing the transaction. Note that
* only one transaction can be active at a time.
*/
buf_len = vss_transaction.recv_len;
channel = vss_transaction.recv_channel;
req_id = vss_transaction.recv_req_id;
icmsghdrp = (struct icmsg_hdr *)
&recv_buffer[sizeof(struct vmbuspipe_hdr)];
if (channel->onchannel_callback == NULL)
/*
* We have raced with util driver being unloaded;
* silently return.
*/
return;
icmsghdrp->status = error;
icmsghdrp->icflags = ICMSGHDRFLAG_TRANSACTION | ICMSGHDRFLAG_RESPONSE;
vmbus_sendpacket(channel, recv_buffer, buf_len, req_id,
VM_PKT_DATA_INBAND, 0);
}
/*
* This callback is invoked when we get a VSS message from the host.
* The host ensures that only one VSS transaction can be active at a time.
*/
void hv_vss_onchannelcallback(void *context)
{
struct vmbus_channel *channel = context;
u32 recvlen;
u64 requestid;
struct hv_vss_msg *vss_msg;
struct icmsg_hdr *icmsghdrp;
struct icmsg_negotiate *negop = NULL;
if (vss_transaction.state > HVUTIL_READY) {
/*
* We will defer processing this callback once
* the current transaction is complete.
*/
vss_transaction.vss_context = context;
return;
}
vss_transaction.vss_context = NULL;
vmbus_recvpacket(channel, recv_buffer, PAGE_SIZE * 2, &recvlen,
&requestid);
if (recvlen > 0) {
icmsghdrp = (struct icmsg_hdr *)&recv_buffer[
sizeof(struct vmbuspipe_hdr)];
if (icmsghdrp->icmsgtype == ICMSGTYPE_NEGOTIATE) {
vmbus_prep_negotiate_resp(icmsghdrp, negop,
recv_buffer, UTIL_FW_VERSION,
VSS_VERSION);
} else {
vss_msg = (struct hv_vss_msg *)&recv_buffer[
sizeof(struct vmbuspipe_hdr) +
sizeof(struct icmsg_hdr)];
/*
* Stash away this global state for completing the
* transaction; note transactions are serialized.
*/
vss_transaction.recv_len = recvlen;
vss_transaction.recv_channel = channel;
vss_transaction.recv_req_id = requestid;
vss_transaction.msg = (struct hv_vss_msg *)vss_msg;
switch (vss_msg->vss_hdr.operation) {
/*
* Initiate a "freeze/thaw"
* operation in the guest.
* We respond to the host once
* the operation is complete.
*
* We send the message to the
* user space daemon and the
* operation is performed in
* the daemon.
*/
case VSS_OP_FREEZE:
case VSS_OP_THAW:
if (vss_transaction.state < HVUTIL_READY) {
/* Userspace is not registered yet */
vss_respond_to_host(HV_E_FAIL);
return;
}
vss_transaction.state = HVUTIL_HOSTMSG_RECEIVED;
schedule_work(&vss_send_op_work);
schedule_delayed_work(&vss_timeout_work,
VSS_USERSPACE_TIMEOUT);
return;
case VSS_OP_HOT_BACKUP:
vss_msg->vss_cf.flags =
VSS_HBU_NO_AUTO_RECOVERY;
vss_respond_to_host(0);
return;
case VSS_OP_GET_DM_INFO:
vss_msg->dm_info.flags = 0;
vss_respond_to_host(0);
return;
default:
vss_respond_to_host(0);
return;
}
}
icmsghdrp->icflags = ICMSGHDRFLAG_TRANSACTION
| ICMSGHDRFLAG_RESPONSE;
vmbus_sendpacket(channel, recv_buffer,
recvlen, requestid,
VM_PKT_DATA_INBAND, 0);
}
}
static void vss_on_reset(void)
{
if (cancel_delayed_work_sync(&vss_timeout_work))
vss_respond_to_host(HV_E_FAIL);
vss_transaction.state = HVUTIL_DEVICE_INIT;
}
int
hv_vss_init(struct hv_util_service *srv)
{
recv_buffer = srv->recv_buffer;
/*
* When this driver loads, the user level daemon that
* processes the host requests may not yet be running.
* Defer processing channel callbacks until the daemon
* has registered.
*/
vss_transaction.state = HVUTIL_DEVICE_INIT;
hvt = hvutil_transport_init(vss_devname, CN_VSS_IDX, CN_VSS_VAL,
vss_on_msg, vss_on_reset);
if (!hvt)
return -EFAULT;
return
|