aboutsummaryrefslogtreecommitdiff
path: root/drivers/hv/hv_snapshot.c
blob: 0d2184be16912559a8cfa784c762e6418ebd3279 (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
// SPDX-License-Identifier: GPL-2.0-only
/*
 * An implementation of host initiated guest snapshot.
 *
 * Copyright (C) 2013, Microsoft, Inc.
 * Author : K. Y. Srinivasan <kys@microsoft.com>
 */
#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 <asm/hyperv-tlfs.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_VER_COUNT 1
static const int vss_versions[] = {
	VSS_VERSION
};

#define FW_VER_COUNT 1
static const int fw_versions[] = {
	UTIL_FW_VERSION
};

/* See comment with struct hv_vss_msg regarding the max VMbus packet size */
#define VSS_MAX_PKT_SIZE (HV_HYP_PAGE_SIZE * 2)

/*
 * Timeout values are based on expecations from host
 */
#define VSS_FREEZE_TIMEOUT (15 * 60)

/*
 * 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 */
} 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_timeout_func(struct work_struct *dummy);
static void vss_handle_request(struct work_struct *dummy);

static DECLARE_DELAYED_WORK(vss_timeout_work, vss_timeout_func);
static DECLARE_WORK(vss_handle_request_work, vss_handle_request);

static void vss_poll_wrapper(void *channel)
{
	/* Transaction is finished, reset the state here to avoid races. */
	vss_transaction.state = HVUTIL_READY;
	tasklet_schedule(&((struct vmbus_channel *)channel)->callback_event);
}

/*
 * 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);

	hv_poll_channel(vss_transaction.recv_channel, vss_poll_wrapper);
}

static void vss_register_done(void)
{
	hv_poll_channel(vss_transaction.recv_channel, vss_poll_wrapper);
	pr_debug("VSS: userspace daemon registered\n");
}

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),
					  vss_register_done))
			return -EFAULT;
		dm_reg_value = VSS_OP_REGISTER1;
		break;
	default:
		return -EINVAL;
	}
	pr_info("VSS: userspace daemon ver. %d connected\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)) {
		pr_debug("VSS: Message size does not match length\n");
		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) {
			pr_debug("VSS: Got unexpected registration request\n");
			return -EINVAL;
		}

		return vss_handle_handshake(vss_msg);
	} else if (vss_transaction.state == HVUTIL_USERSPACE_REQ) {
		vss_transaction.state = HVUTIL_USERSPACE_RECV;

		if (vss_msg->vss_hdr.operation == VSS_OP_HOT_BACKUP)
			vss_transaction.msg->vss_cf.flags =
				VSS_HBU_NO_AUTO_RECOVERY;

		if (cancel_delayed_work_sync(&vss_timeout_work)) {
			vss_respond_to_host(vss_msg->error);
			/* Transaction is finished, reset the state. */
			hv_poll_channel(vss_transaction.recv_channel,
					vss_poll_wrapper);
		}
	} else {
		/* This is a spurious call! */
		pr_debug("VSS: Transaction not active\n");
		return -EINVAL;
	}
	return 0;
}

static void vss_send_op(void)
{
	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) {
		pr_debug("VSS: Unexpected attempt to send to daemon\n");
		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;

	schedule_delayed_work(&vss_timeout_work, op == VSS_OP_FREEZE ?
			VSS_FREEZE_TIMEOUT * HZ : HV_UTIL_TIMEOUT * HZ);

	rc = hvutil_transport_send(hvt, vss_msg, sizeof(*vss_msg), NULL);
	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);
}

static void vss_handle_request(struct work_struct *dummy)
{
	switch (vss_transaction.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_THAW:
	case VSS_OP_FREEZE:
	case VSS_OP_HOT_BACKUP:
		if (vss_transaction.state < HVUTIL_READY) {
			/* Userspace is not registered yet */
			pr_debug("VSS: Not ready for request.\n");
			vss_respond_to_host(HV_E_FAIL);
			return;
		}

		pr_debug("VSS: Received request for op code: %d\n",
			vss_transaction.msg->vss_hdr.operation);
		vss_transaction.state = HVUTIL_HOSTMSG_RECEIVED;
		vss_send_op();
		return;
	case VSS_OP_GET_DM_INFO:
		vss_transaction.msg->dm_info.flags = 0;
		break;
	default:
		break;
	}

	vss_respond_to_host(0);
	hv_poll_channel(vss_transaction.recv_channel, vss_poll_wrapper);
}

/*
 * 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;
	int vss_srv_version;

	struct icmsg_hdr *icmsghdrp;

	if (vss_transaction.state > HVUTIL_READY)
		return;

	if (vmbus_recvpacket(channel, recv_buffer, VSS_MAX_PKT_SIZE, &recvlen, &requestid)) {
		pr_err_ratelimited("VSS request received. Could not read into recv buf\n");
		return;
	}

	if (!recvlen)
		return;

	/* Ensure recvlen is big enough to read header data */
	if (recvlen < ICMSG_HDR) {
		pr_err_ratelimited("VSS request received. Packet length too small: %d\n",
				   recvlen);
		return;
	}

	icmsghdrp = (struct icmsg_hdr *)&recv_buffer[sizeof(struct vmbuspipe_hdr)];

	if (icmsghdrp->icmsgtype == ICMSGTYPE_NEGOTIATE) {
		if (vmbus_prep_negotiate_resp(icmsghdrp,
				recv_buffer, recvlen,
				fw_versions, FW_VER_COUNT,
				vss_versions, VSS_VER_COUNT,
				NULL, &vss_srv_version)) {

			pr_info("VSS IC version %d.%d\n",
				vss_srv_version >> 16,
				vss_srv_version & 0xFFFF);
		}
	} else if (icmsghdrp->icmsgtype == ICMSGTYPE_VSS) {
		/* Ensure recvlen is big enough to contain hv_vss_msg */
		if (recvlen < ICMSG_HDR + sizeof(struct hv_vss_msg)) {
			pr_err_ratelimited("Invalid VSS msg. Packet length too small: %u\n",
					   recvlen);
			return;
		}
		vss_msg = (struct hv_vss_msg *)&recv_buffer[ICMSG_HDR];

		/*
		 * Stash away this global state for completing the
		 * transaction; note transactions are serialized.
		 */

		vss_transaction.recv_len = recvlen;
		vss_transaction.recv_req_id = requestid;
		vss_transaction.msg = (struct hv_vss_msg *)vss_msg;

		schedule_work(&vss_handle_request_work);
		return;
	} else {
		pr_err_ratelimited("VSS request received. Invalid msg type: %d\n",
				   icmsghdrp->icmsgtype);
		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)
{
	if (vmbus_proto_version < VERSION_WIN8_1) {
		pr_warn("Integration service 'Backup (volume snapshot)'"
			" not supported on this host version.\n");
		return -ENOTSUPP;
	}
	recv_buffer = srv->recv_buffer;
	vss_transaction.recv_channel = srv->channel;
	vss_transaction.recv_channel->max_pkt_size = VSS_MAX_PKT_SIZE;

	/*
	 * 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) {
		pr_warn("VSS: Failed to initialize transport\n");
		return -EFAULT;
	}

	return 0;
}

static void hv_vss_cancel_work(void)
{
	cancel_delayed_work_sync(&vss_timeout_work);
	cancel_work_sync(&vss_handle_request_work);
}

int hv_vss_pre_suspend(void)
{
	struct vmbus_channel *channel = vss_transaction.recv_channel;
	struct hv_vss_msg *vss_msg;

	/*
	 * Fake a THAW message for the user space daemon in case the daemon
	 * has frozen the file systems. It doesn't matter if there is already
	 * a message pending to be delivered to the user space since we force
	 * vss_transaction.state to be HVUTIL_READY, so the user space daemon's
	 * write() will fail with EINVAL (see vss_on_msg()), and the daemon
	 * will reset the device by closing and re-opening it.
	 */
	vss_msg = kzalloc(sizeof(*vss_msg), GFP_KERNEL);
	if (!vss_msg)
		return -ENOMEM;

	tasklet_disable(&channel->callback_event);

	vss_msg->vss_hdr.operation = VSS_OP_THAW;

	/* Cancel any possible pending work. */
	hv_vss_cancel_work();

	/* We don't care about the return value. */
	hvutil_transport_send(hvt, vss_msg, sizeof(*vss_msg), NULL);

	kfree(vss_msg);

	vss_transaction.state = HVUTIL_READY;

	/* tasklet_enable() will be called in hv_vss_pre_resume(). */
	return 0;
}

int hv_vss_pre_resume(void)
{
	struct vmbus_channel *channel = vss_transaction.recv_channel;

	tasklet_enable(&channel->callback_event);

	return 0;
}

void hv_vss_deinit(void)
{
	vss_transaction.state = HVUTIL_DEVICE_DYING;

	hv_vss_cancel_work();

	hvutil_transport_destroy(hvt);
}