summaryrefslogtreecommitdiff
path: root/drivers/net/xen-netback/xenbus.c
blob: efbaf2ae1999a97982a8e57274e3cf09f95b42ec (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
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
/*
 * Xenbus code for netif backend
 *
 * Copyright (C) 2005 Rusty Russell <rusty@rustcorp.com.au>
 * Copyright (C) 2005 XenSource Ltd
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License as published by
 * the Free Software Foundation; either version 2 of the License, or
 * (at your option) any later version.
 *
 * 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.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program; if not, see <http://www.gnu.org/licenses/>.
*/

#include "common.h"
#include <linux/vmalloc.h>
#include <linux/rtnetlink.h>

struct backend_info {
	struct xenbus_device *dev;
	struct xenvif *vif;

	/* This is the state that will be reflected in xenstore when any
	 * active hotplug script completes.
	 */
	enum xenbus_state state;

	enum xenbus_state frontend_state;
	struct xenbus_watch hotplug_status_watch;
	u8 have_hotplug_status_watch:1;
};

static int connect_rings(struct backend_info *be, struct xenvif_queue *queue);
static void connect(struct backend_info *be);
static int read_xenbus_vif_flags(struct backend_info *be);
static int backend_create_xenvif(struct backend_info *be);
static void unregister_hotplug_status_watch(struct backend_info *be);
static void set_backend_state(struct backend_info *be,
			      enum xenbus_state state);

#ifdef CONFIG_DEBUG_FS
struct dentry *xen_netback_dbg_root = NULL;

static int xenvif_read_io_ring(struct seq_file *m, void *v)
{
	struct xenvif_queue *queue = m->private;
	struct xen_netif_tx_back_ring *tx_ring = &queue->tx;
	struct xen_netif_rx_back_ring *rx_ring = &queue->rx;
	struct netdev_queue *dev_queue;

	if (tx_ring->sring) {
		struct xen_netif_tx_sring *sring = tx_ring->sring;

		seq_printf(m, "Queue %d\nTX: nr_ents %u\n", queue->id,
			   tx_ring->nr_ents);
		seq_printf(m, "req prod %u (%d) cons %u (%d) event %u (%d)\n",
			   sring->req_prod,
			   sring->req_prod - sring->rsp_prod,
			   tx_ring->req_cons,
			   tx_ring->req_cons - sring->rsp_prod,
			   sring->req_event,
			   sring->req_event - sring->rsp_prod);
		seq_printf(m, "rsp prod %u (base) pvt %u (%d) event %u (%d)\n",
			   sring->rsp_prod,
			   tx_ring->rsp_prod_pvt,
			   tx_ring->rsp_prod_pvt - sring->rsp_prod,
			   sring->rsp_event,
			   sring->rsp_event - sring->rsp_prod);
		seq_printf(m, "pending prod %u pending cons %u nr_pending_reqs %u\n",
			   queue->pending_prod,
			   queue->pending_cons,
			   nr_pending_reqs(queue));
		seq_printf(m, "dealloc prod %u dealloc cons %u dealloc_queue %u\n\n",
			   queue->dealloc_prod,
			   queue->dealloc_cons,
			   queue->dealloc_prod - queue->dealloc_cons);
	}

	if (rx_ring->sring) {
		struct xen_netif_rx_sring *sring = rx_ring->sring;

		seq_printf(m, "RX: nr_ents %u\n", rx_ring->nr_ents);
		seq_printf(m, "req prod %u (%d) cons %u (%d) event %u (%d)\n",
			   sring->req_prod,
			   sring->req_prod - sring->rsp_prod,
			   rx_ring->req_cons,
			   rx_ring->req_cons - sring->rsp_prod,
			   sring->req_event,
			   sring->req_event - sring->rsp_prod);
		seq_printf(m, "rsp prod %u (base) pvt %u (%d) event %u (%d)\n\n",
			   sring->rsp_prod,
			   rx_ring->rsp_prod_pvt,
			   rx_ring->rsp_prod_pvt - sring->rsp_prod,
			   sring->rsp_event,
			   sring->rsp_event - sring->rsp_prod);
	}

	seq_printf(m, "NAPI state: %lx NAPI weight: %d TX queue len %u\n"
		   "Credit timer_pending: %d, credit: %lu, usec: %lu\n"
		   "remaining: %lu, expires: %lu, now: %lu\n",
		   queue->napi.state, queue->napi.weight,
		   skb_queue_len(&queue->tx_queue),
		   timer_pending(&queue->credit_timeout),
		   queue->credit_bytes,
		   queue->credit_usec,
		   queue->remaining_credit,
		   queue->credit_timeout.expires,
		   jiffies);

	dev_queue = netdev_get_tx_queue(queue->vif->dev, queue->id);

	seq_printf(m, "\nRx internal queue: len %u max %u pkts %u %s\n",
		   queue->rx_queue_len, queue->rx_queue_max,
		   skb_queue_len(&queue->rx_queue),
		   netif_tx_queue_stopped(dev_queue) ? "stopped" : "running");

	return 0;
}

#define XENVIF_KICK_STR "kick"
#define BUFFER_SIZE     32

static ssize_t
xenvif_write_io_ring(struct file *filp, const char __user *buf, size_t count,
		     loff_t *ppos)
{
	struct xenvif_queue *queue =
		((struct seq_file *)filp->private_data)->private;
	int len;
	char write[BUFFER_SIZE];

	/* don't allow partial writes and check the length */
	if (*ppos != 0)
		return 0;
	if (count >= sizeof(write))
		return -ENOSPC;

	len = simple_write_to_buffer(write,
				     sizeof(write) - 1,
				     ppos,
				     buf,
				     count);
	if (len < 0)
		return len;

	write[len] = '\0';

	if (!strncmp(write, XENVIF_KICK_STR, sizeof(XENVIF_KICK_STR) - 1))
		xenvif_interrupt(0, (void *)queue);
	else {
		pr_warn("Unknown command to io_ring_q%d. Available: kick\n",
			queue->id);
		count = -EINVAL;
	}
	return count;
}

static int xenvif_dump_open(struct inode *inode, struct file *filp)
{
	int ret;
	void *queue = NULL;

	if (inode->i_private)
		queue = inode->i_private;
	ret = single_open(filp, xenvif_read_io_ring, queue);
	filp->f_mode |= FMODE_PWRITE;
	return ret;
}

static const struct file_operations xenvif_dbg_io_ring_ops_fops = {
	.owner = THIS_MODULE,
	.open = xenvif_dump_open,
	.read = seq_read,
	.llseek = seq_lseek,
	.release = single_release,
	.write = xenvif_write_io_ring,
};

static void xenvif_debugfs_addif(struct xenvif *vif)
{
	struct dentry *pfile;
	int i;

	if (IS_ERR_OR_NULL(xen_netback_dbg_root))
		return;

	vif->xenvif_dbg_root = debugfs_create_dir(vif->dev->name,
						  xen_netback_dbg_root);
	if (!IS_ERR_OR_NULL(vif->xenvif_dbg_root)) {
		for (i = 0; i < vif->num_queues; ++i) {
			char filename[sizeof("io_ring_q") + 4];

			snprintf(filename, sizeof(filename), "io_ring_q%d", i);
			pfile = debugfs_create_file(filename,
						    S_IRUSR | S_IWUSR,
						    vif->xenvif_dbg_root,
						    &vif->queues[i],
						    &xenvif_dbg_io_ring_ops_fops);
			if (IS_ERR_OR_NULL(pfile))
				pr_warn("Creation of io_ring file returned %ld!\n",
					PTR_ERR(pfile));
		}
	} else
		netdev_warn(vif->dev,
			    "Creation of vif debugfs dir returned %ld!\n",
			    PTR_ERR(vif->xenvif_dbg_root));
}

static void xenvif_debugfs_delif(struct xenvif *vif)
{
	if (IS_ERR_OR_NULL(xen_netback_dbg_root))
		return;

	if (!IS_ERR_OR_NULL(vif->xenvif_dbg_root))
		debugfs_remove_recursive(vif->xenvif_dbg_root);
	vif->xenvif_dbg_root = NULL;
}
#endif /* CONFIG_DEBUG_FS */

static int netback_remove(struct xenbus_device *dev)
{
	struct backend_info *be = dev_get_drvdata(&dev->dev);

	set_backend_state(be, XenbusStateClosed);

	unregister_hotplug_status_watch(be);
	if (be->vif) {
		kobject_uevent(&dev->dev.kobj, KOBJ_OFFLINE);
		xenbus_rm(XBT_NIL, dev->nodename, "hotplug-status");
		xenvif_free(be->vif);
		be->vif = NULL;
	}
	kfree(be);
	dev_set_drvdata(&dev->dev, NULL);
	return 0;
}


/**
 * Entry point to this code when a new device is created.  Allocate the basic
 * structures and switch to InitWait.
 */
static int netback_probe(struct xenbus_device *dev,
			 const struct xenbus_device_id *id)
{
	const char *message;
	struct xenbus_transaction xbt;
	int err;
	int sg;
	struct backend_info *be = kzalloc(sizeof(struct backend_info),
					  GFP_KERNEL);
	if (!be) {
		xenbus_dev_fatal(dev, -ENOMEM,
				 "allocating backend structure");
		return -ENOMEM;
	}

	be->dev = dev;
	dev_set_drvdata(&dev->dev, be);

	sg = 1;

	do {
		err = xenbus_transaction_start(&xbt);
		if (err) {
			xenbus_dev_fatal(dev, err, "starting transaction");
			goto fail;
		}

		err = xenbus_printf(xbt, dev->nodename, "feature-sg", "%d", sg);
		if (err) {
			message = "writing feature-sg";
			goto abort_transaction;
		}

		err = xenbus_printf(xbt, dev->nodename, "feature-gso-tcpv4",
				    "%d", sg);
		if (err) {
			message = "writing feature-gso-tcpv4";
			goto abort_transaction;
		}

		err = xenbus_printf(xbt, dev->nodename, "feature-gso-tcpv6",
				    "%d", sg);
		if (err) {
			message = "writing feature-gso-tcpv6";
			goto abort_transaction;
		}

		/* We support partial checksum setup for IPv6 packets */
		err = xenbus_printf(xbt, dev->nodename,
				    "feature-ipv6-csum-offload",
				    "%d", 1);
		if (err) {
			message = "writing feature-ipv6-csum-offload";
			goto abort_transaction;
		}

		/* We support rx-copy path. */
		err = xenbus_printf(xbt, dev->nodename,
				    "feature-rx-copy", "%d", 1);
		if (err) {
			message = "writing feature-rx-copy";
			goto abort_transaction;
		}

		/*
		 * We don't support rx-flip path (except old guests who don't
		 * grok this feature flag).
		 */
		err = xenbus_printf(xbt, dev->nodename,
				    "feature-rx-flip", "%d", 0);
		if (err) {
			message = "writing feature-rx-flip";
			goto abort_transaction;
		}

		err = xenbus_transaction_end(xbt, 0);
	} while (err == -EAGAIN);

	if (err) {
		xenbus_dev_fatal(dev, err, "completing transaction");
		goto fail;
	}

	/*
	 * Split event channels support, this is optional so it is not
	 * put inside the above loop.
	 */
	err = xenbus_printf(XBT_NIL, dev->nodename,
			    "feature-split-event-channels",
			    "%u", separate_tx_rx_irq);
	if (err)
		pr_debug("Error writing feature-split-event-channels\n");

	/* Multi-queue support: This is an optional feature. */
	err = xenbus_printf(XBT_NIL, dev->nodename,
			    "multi-queue-max-queues", "%u", xenvif_max_queues);
	if (err)
		pr_debug("Error writing multi-queue-max-queues\n");

	err = xenbus_switch_state(dev, XenbusStateInitWait);
	if (err)
		goto fail;

	be->state = XenbusStateInitWait;

	/* This kicks hotplug scripts, so do it immediately. */
	err = backend_create_xenvif(be);
	if (err)
		goto fail;

	return 0;

abort_transaction:
	xenbus_transaction_end(xbt, 1);
	xenbus_dev_fatal(dev, err, "%s", message);
fail:
	pr_debug("failed\n");
	netback_remove(dev);
	return err;
}


/*
 * Handle the creation of the hotplug script environment.  We add the script
 * and vif variables to the environment, for the benefit of the vif-* hotplug
 * scripts.
 */
static int netback_uevent(struct xenbus_device *xdev,
			  struct kobj_uevent_env *env)
{
	struct backend_info *be = dev_get_drvdata(&xdev->dev);
	char *val;

	val = xenbus_read(XBT_NIL, xdev->nodename, "script", NULL);
	if (IS_ERR(val)) {
		int err = PTR_ERR(val);
		xenbus_dev_fatal(xdev, err, "reading script");
		return err;
	} else {
		if (add_uevent_var(env, "script=%s", val)) {
			kfree(val);
			return -ENOMEM;
		}
		kfree(val);
	}

	if (!be || !be->vif)
		return 0;

	return add_uevent_var(env, "vif=%s", be->vif->dev->name);
}


static int backend_create_xenvif(struct backend_info *be)
{
	int err;
	long handle;
	struct xenbus_device *dev = be->dev;
	struct xenvif *vif;

	if (be->vif != NULL)
		return 0;

	err = xenbus_scanf(XBT_NIL, dev->nodename, "handle", "%li", &handle);
	if (err != 1) {
		xenbus_dev_fatal(dev, err, "reading handle");
		return (err < 0) ? err : -EINVAL;
	}

	vif = xenvif_alloc(&dev->dev, dev->otherend_id, handle);
	if (IS_ERR(vif)) {
		err = PTR_ERR(vif);
		xenbus_dev_fatal(dev, err, "creating interface");
		return err;
	}
	be->vif = vif;

	kobject_uevent(&dev->dev.kobj, KOBJ_ONLINE);
	return 0;
}

static void backend_disconnect(struct backend_info *be)
{
	if (be->vif) {
#ifdef CONFIG_DEBUG_FS
		xenvif_debugfs_delif(be->vif);
#endif /* CONFIG_DEBUG_FS */
		xenvif_disconnect(be->vif);
	}
}

static void backend_connect(struct backend_info *be)
{
	if (be->vif)
		connect(be);
}

static inline void backend_switch_state(struct backend_info *be,
					enum xenbus_state state)
{
	struct xenbus_device *dev = be->dev;

	pr_debug("%s -> %s\n", dev->nodename, xenbus_strstate(state));
	be->state = state;

	/* If we are waiting for a hotplug script then defer the
	 * actual xenbus state change.
	 */
	if (!be->have_hotplug_status_watch)
		xenbus_switch_state(dev, state);
}

/* Handle backend state transitions:
 *
 * The backend state starts in InitWait and the following transitions are
 * allowed.
 *
 * InitWait -> Connected
 *
 *    ^    \         |
 *    |     \        |
 *    |      \       |
 *    |       \      |
 *    |        \     |
 *    |         \    |
 *    |          V   V
 *
 *  Closed  <-> Closing
 *
 * The state argument specifies the eventual state of the backend and the
 * function transitions to that state via the shortest path.
 */
static void set_backend_state(struct backend_info *be,
			      enum xenbus_state state)
{
	while (be->state != state) {
		switch (be->state) {
		case XenbusStateClosed:
			switch (state) {
			case XenbusStateInitWait:
			case XenbusStateConnected:
				pr_info("%s: prepare for reconnect\n",
					be->dev->nodename);
				backend_switch_state(be, XenbusStateInitWait);
				break;
			case XenbusStateClosing:
				backend_switch_state(be, XenbusStateClosing);
				break;
			default:
				BUG();
			}
			break;
		case XenbusStateInitWait:
			switch (state) {
			case XenbusStateConnected:
				backend_connect(be);
				backend_switch_state(be, XenbusStateConnected);
				break;
			case XenbusStateClosing:
			case XenbusStateClosed:
				backend_switch_state(be, XenbusStateClosing);
				break;
			default:
				BUG();
			}
			break;
		case XenbusStateConnected:
			switch (state) {
			case XenbusStateInitWait:
			case XenbusStateClosing:
			case XenbusStateClosed:
				backend_disconnect(be);
				backend_switch_state(be, XenbusStateClosing);
				break;
			default:
				BUG();
			}
			break;
		case XenbusStateClosing:
			switch (state) {
			case XenbusStateInitWait:
			case XenbusStateConnected:
			case XenbusStateClosed:
				backend_switch_state(be, XenbusStateClosed);
				break;
			default:
				BUG();
			}
			break;
		default:
			BUG();
		}
	}
}

/**
 * Callback received when the frontend's state changes.
 */
static void frontend_changed(struct xenbus_device *dev,
			     enum xenbus_state frontend_state)
{
	struct backend_info *be = dev_get_drvdata(&dev->dev);

	pr_debug("%s -> %s\n", dev->otherend, xenbus_strstate(frontend_state));

	be->frontend_state = frontend_state;

	switch (frontend_state) {
	case XenbusStateInitialising:
		set_backend_state(be, XenbusStateInitWait);
		break;

	case XenbusStateInitialised:
		break;

	case XenbusStateConnected:
		set_backend_state(be, XenbusStateConnected);
		break;

	case XenbusStateClosing:
		set_backend_state(be, XenbusStateClosing);
		break;

	case XenbusStateClosed:
		set_backend_state(be, XenbusStateClosed);
		if (xenbus_dev_is_online(dev))
			break;
		/* fall through if not online */
	case XenbusStateUnknown:
		set_backend_state(be, XenbusStateClosed);
		device_unregister(&dev->dev);
		break;

	default:
		xenbus_dev_fatal(dev, -EINVAL, "saw state %d at frontend",
				 frontend_state);
		break;
	}
}


static void xen_net_read_rate(struct xenbus_device *dev,
			      unsigned long *bytes, unsigned long *usec)
{
	char *s, *e;
	unsigned long b, u;
	char *ratestr;

	/* Default to unlimited bandwidth. */
	*bytes = ~0UL;
	*usec = 0;

	ratestr = xenbus_read(XBT_NIL, dev->nodename, "rate", NULL);
	if (IS_ERR(ratestr))
		return;

	s = ratestr;
	b = simple_strtoul(s, &e, 10);
	if ((s == e) || (*e != ','))
		goto fail;

	s = e + 1;
	u = simple_strtoul(s, &e, 10);
	if ((s == e) || (*e != '\0'))
		goto fail;

	*bytes = b;
	*usec = u;

	kfree(ratestr);
	return;

 fail:
	pr_warn("Failed to parse network rate limit. Traffic unlimited.\n");
	kfree(ratestr);
}

static int xen_net_read_mac(struct xenbus_device *dev, u8 mac[])
{
	char *s, *e, *macstr;
	int i;

	macstr = s = xenbus_read(XBT_NIL, dev->nodename, "mac", NULL);
	if (IS_ERR(macstr))
		return PTR_ERR(macstr);

	for (i = 0; i < ETH_ALEN; i++) {
		mac[i] = simple_strtoul(s, &e, 16);
		if ((s == e) || (*e != ((i == ETH_ALEN-1) ? '\0' : ':'))) {
			kfree(macstr);
			return -ENOENT;
		}
		s = e+1;
	}

	kfree(macstr);
	return 0;
}

static void unregister_hotplug_status_watch(struct backend_info *be)
{
	if (be->have_hotplug_status_watch) {
		unregister_xenbus_watch(&be->hotplug_status_watch);
		kfree(be->hotplug_status_watch.node);
	}
	be->have_hotplug_status_watch = 0;
}

static void hotplug_status_changed(struct xenbus_watch *watch,
				   const char **vec,
				   unsigned int vec_size)
{
	struct backend_info *be = container_of(watch,
					       struct backend_info,
					       hotplug_status_watch);
	char *str;
	unsigned int len;

	str = xenbus_read(XBT_NIL, be->dev->nodename, "hotplug-status", &len);
	if (IS_ERR(str))
		return;
	if (len == sizeof("connected")-1 && !memcmp(str, "connected", len)) {
		/* Complete any pending state change */
		xenbus_switch_state(be->dev, be->state);

		/* Not interested in this watch anymore. */
		unregister_hotplug_status_watch(be);
	}
	kfree(str);
}

static void connect(struct backend_info *be)
{
	int err;
	struct xenbus_device *dev = be->dev;
	unsigned long credit_bytes, credit_usec;
	unsigned int queue_index;
	unsigned int requested_num_queues;
	struct xenvif_queue *queue;

	/* Check whether the frontend requested multiple queues
	 * and read the number requested.
	 */
	err = xenbus_scanf(XBT_NIL, dev->otherend,
			   "multi-queue-num-queues",
			   "%u", &requested_num_queues);
	if (err < 0) {
		requested_num_queues = 1; /* Fall back to single queue */
	} else if (requested_num_queues > xenvif_max_queues) {
		/* buggy or malicious guest */
		xenbus_dev_fatal(dev, err,
				 "guest requested %u queues, exceeding the maximum of %u.",
				 requested_num_queues, xenvif_max_queues);
		return;
	}

	err = xen_net_read_mac(dev, be->vif->fe_dev_addr);
	if (err) {
		xenbus_dev_fatal(dev, err, "parsing %s/mac", dev->nodename);
		return;
	}

	xen_net_read_rate(dev, &credit_bytes, &credit_usec);
	read_xenbus_vif_flags(be);

	/* Use the number of queues requested by the frontend */
	be->vif->queues = vzalloc(requested_num_queues *
				  sizeof(struct xenvif_queue));
	be->vif->num_queues = requested_num_queues;
	be->vif->stalled_queues = requested_num_queues;

	for (queue_index = 0; queue_index < requested_num_queues; ++queue_index) {
		queue = &be->vif->queues[queue_index];
		queue->vif = be->vif;
		queue->id = queue_index;
		snprintf(queue->name, sizeof(queue->name), "%s-q%u",
				be->vif->dev->name, queue->id);

		err = xenvif_init_queue(queue);
		if (err) {
			/* xenvif_init_queue() cleans up after itself on
			 * failure, but we need to clean up any previously
			 * initialised queues. Set num_queues to i so that
			 * earlier queues can be destroyed using the regular
			 * disconnect logic.
			 */
			be->vif->num_queues = queue_index;
			goto err;
		}

		queue->remaining_credit = credit_bytes;

		err = connect_rings(be, queue);
		if (err) {
			/* connect_rings() cleans up after itself on failure,
			 * but we need to clean up after xenvif_init_queue() here,
			 * and also clean up any previously initialised queues.
			 */
			xenvif_deinit_queue(queue);
			be->vif->num_queues = queue_index;
			goto err;
		}
	}

#ifdef CONFIG_DEBUG_FS
	xenvif_debugfs_addif(be->vif);
#endif /* CONFIG_DEBUG_FS */

	/* Initialisation completed, tell core driver the number of
	 * active queues.
	 */
	rtnl_lock();
	netif_set_real_num_tx_queues(be->vif->dev, requested_num_queues);
	netif_set_real_num_rx_queues(be->vif->dev, requested_num_queues);
	rtnl_unlock();

	xenvif_carrier_on(be->vif);

	unregister_hotplug_status_watch(be);
	err = xenbus_watch_pathfmt(dev, &be->hotplug_status_watch,
				   hotplug_status_changed,
				   "%s/%s", dev->nodename, "hotplug-status");
	if (!err)
		be->have_hotplug_status_watch = 1;

	netif_tx_wake_all_queues(be->vif->dev);

	return;

err:
	if (be->vif->num_queues > 0)
		xenvif_disconnect(be->vif); /* Clean up existing queues */
	vfree(be->vif->queues);
	be->vif->queues = NULL;
	be->vif->num_queues = 0;
	return;
}


static int connect_rings(struct backend_info *be, struct xenvif_queue *queue)
{
	struct xenbus_device *dev = be->dev;
	unsigned int num_queues = queue->vif->num_queues;
	unsigned long tx_ring_ref, rx_ring_ref;
	unsigned int tx_evtchn, rx_evtchn;
	int err;
	char *xspath;
	size_t xspathsize;
	const size_t xenstore_path_ext_size = 11; /* sufficient for "/queue-NNN" */

	/* If the frontend requested 1 queue, or we have fallen back
	 * to single queue due to lack of frontend support for multi-
	 * queue, expect the remaining XenStore keys in the toplevel
	 * directory. Otherwise, expect them in a subdirectory called
	 * queue-N.
	 */
	if (num_queues == 1) {
		xspath = kzalloc(strlen(dev->otherend) + 1, GFP_KERNEL);
		if (!xspath) {
			xenbus_dev_fatal(dev, -ENOMEM,
					 "reading ring references");
			return -ENOMEM;
		}
		strcpy(xspath, dev->otherend);
	} else {
		xspathsize = strlen(dev->otherend) + xenstore_path_ext_size;
		xspath = kzalloc(xspathsize, GFP_KERNEL);
		if (!xspath) {
			xenbus_dev_fatal(dev, -ENOMEM,
					 "reading ring references");
			return -ENOMEM;
		}
		snprintf(xspath, xspathsize, "%s/queue-%u", dev->otherend,
			 queue->id);
	}

	err = xenbus_gather(XBT_NIL, xspath,
			    "tx-ring-ref", "%lu", &tx_ring_ref,
			    "rx-ring-ref", "%lu", &rx_ring_ref, NULL);
	if (err) {
		xenbus_dev_fatal(dev, err,
				 "reading %s/ring-ref",
				 xspath);
		goto err;
	}

	/* Try split event channels first, then single event channel. */
	err = xenbus_gather(XBT_NIL, xspath,
			    "event-channel-tx", "%u", &tx_evtchn,
			    "event-channel-rx", "%u", &rx_evtchn, NULL);
	if (err < 0) {
		err = xenbus_scanf(XBT_NIL, xspath,
				   "event-channel", "%u", &tx_evtchn);
		if (err < 0) {
			xenbus_dev_fatal(dev, err,
					 "reading %s/event-channel(-tx/rx)",
					 xspath);
			goto err;
		}
		rx_evtchn = tx_evtchn;
	}

	/* Map the shared frame, irq etc. */
	err = xenvif_connect(queue, tx_ring_ref, rx_ring_ref,
			     tx_evtchn, rx_evtchn);
	if (err) {
		xenbus_dev_fatal(dev, err,
				 "mapping shared-frames %lu/%lu port tx %u rx %u",
				 tx_ring_ref, rx_ring_ref,
				 tx_evtchn, rx_evtchn);
		goto err;
	}

	err = 0;
err: /* Regular return falls through with err == 0 */
	kfree(xspath);
	return err;
}

static int read_xenbus_vif_flags(struct backend_info *be)
{
	struct xenvif *vif = be->vif;
	struct xenbus_device *dev = be->dev;
	unsigned int rx_copy;
	int err, val;

	err = xenbus_scanf(XBT_NIL, dev->otherend, "request-rx-copy", "%u",
			   &rx_copy);
	if (err == -ENOENT) {
		err = 0;
		rx_copy = 0;
	}
	if (err < 0) {
		xenbus_dev_fatal(dev, err, "reading %s/request-rx-copy",
				 dev->otherend);
		return err;
	}
	if (!rx_copy)
		return -EOPNOTSUPP;

	if (xenbus_scanf(XBT_NIL, dev->otherend,
			 "feature-rx-notify", "%d", &val) < 0)
		val = 0;
	if (!val) {
		/* - Reduce drain timeout to poll more frequently for
		 *   Rx requests.
		 * - Disable Rx stall detection.
		 */
		be->vif->drain_timeout = msecs_to_jiffies(30);
		be->vif->stall_timeout = 0;
	}

	if (xenbus_scanf(XBT_NIL, dev->otherend, "feature-sg",
			 "%d", &val) < 0)
		val = 0;
	vif->can_sg = !!val;

	vif->gso_mask = 0;
	vif->gso_prefix_mask = 0;

	if (xenbus_scanf(XBT_NIL, dev->otherend, "feature-gso-tcpv4",
			 "%d", &val) < 0)
		val = 0;
	if (val)
		vif->gso_mask |= GSO_BIT(TCPV4);

	if (xenbus_scanf(XBT_NIL, dev->otherend, "feature-gso-tcpv4-prefix",
			 "%d", &val) < 0)
		val = 0;
	if (val)
		vif->gso_prefix_mask |= GSO_BIT(TCPV4);

	if (xenbus_scanf(XBT_NIL, dev->otherend, "feature-gso-tcpv6",
			 "%d", &val) < 0)
		val = 0;
	if (val)
		vif->gso_mask |= GSO_BIT(TCPV6);

	if (xenbus_scanf(XBT_NIL, dev->otherend, "feature-gso-tcpv6-prefix",
			 "%d", &val) < 0)
		val = 0;
	if (val)
		vif->gso_prefix_mask |= GSO_BIT(TCPV6);

	if (vif->gso_mask & vif->gso_prefix_mask) {
		xenbus_dev_fatal(dev, err,
				 "%s: gso and gso prefix flags are not "
				 "mutually exclusive",
				 dev->otherend);
		return -EOPNOTSUPP;
	}

	if (xenbus_scanf(XBT_NIL, dev->otherend, "feature-no-csum-offload",
			 "%d", &val) < 0)
		val = 0;
	vif->ip_csum = !val;

	if (xenbus_scanf(XBT_NIL, dev->otherend, "feature-ipv6-csum-offload",
			 "%d", &val) < 0)
		val = 0;
	vif->ipv6_csum = !!val;

	return 0;
}

static const struct xenbus_device_id netback_ids[] = {
	{ "vif" },
	{ "" }
};

static struct xenbus_driver netback_driver = {
	.ids = netback_ids,
	.probe = netback_probe,
	.remove = netback_remove,
	.uevent = netback_uevent,
	.otherend_changed = frontend_changed,
};

int xenvif_xenbus_init(void)
{
	return xenbus_register_backend(&netback_driver);
}

void xenvif_xenbus_fini(void)
{
	return xenbus_unregister_driver(&netback_driver);
}