summaryrefslogtreecommitdiffstats
path: root/drivers/xen/xenbus/xenbus_client.c
blob: 96b2011d25f35f628288c523dea84c4150e8ce35 (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
/******************************************************************************
 * Client-facing interface for the Xenbus driver.  In other words, the
 * interface between the Xenbus and the device-specific code, be it the
 * frontend or the backend of that driver.
 *
 * 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 version 2
 * as published by the Free Software Foundation; or, when distributed
 * separately from the Linux kernel or incorporated into other
 * software packages, subject to the following license:
 *
 * Permission is hereby granted, free of charge, to any person obtaining a copy
 * of this source file (the "Software"), to deal in the Software without
 * restriction, including without limitation the rights to use, copy, modify,
 * merge, publish, distribute, sublicense, and/or sell copies of the Software,
 * and to permit persons to whom the Software is furnished to do so, subject to
 * the following conditions:
 *
 * The above copyright notice and this permission notice shall be included in
 * all copies or substantial portions of the Software.
 *
 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
 * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
 * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
 * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
 * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
 * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
 * IN THE SOFTWARE.
 */

#include <linux/mm.h>
#include <linux/slab.h>
#include <linux/types.h>
#include <linux/spinlock.h>
#include <linux/vmalloc.h>
#include <linux/export.h>
#include <asm/xen/hypervisor.h>
#include <asm/xen/page.h>
#include <xen/interface/xen.h>
#include <xen/interface/event_channel.h>
#include <xen/balloon.h>
#include <xen/events.h>
#include <xen/grant_table.h>
#include <xen/xenbus.h>
#include <xen/xen.h>
#include <xen/features.h>

#include "xenbus_probe.h"

struct xenbus_map_node {
	struct list_head next;
	union {
		struct {
			struct vm_struct *area;
		} pv;
		struct {
			struct page *pages[XENBUS_MAX_RING_PAGES];
			void *addr;
		} hvm;
	};
	grant_handle_t handles[XENBUS_MAX_RING_PAGES];
	unsigned int   nr_handles;
};

static DEFINE_SPINLOCK(xenbus_valloc_lock);
static LIST_HEAD(xenbus_valloc_pages);

struct xenbus_ring_ops {
	int (*map)(struct xenbus_device *dev,
		   grant_ref_t *gnt_refs, unsigned int nr_grefs,
		   void **vaddr);
	int (*unmap)(struct xenbus_device *dev, void *vaddr);
};

static const struct xenbus_ring_ops *ring_ops __read_mostly;

const char *xenbus_strstate(enum xenbus_state state)
{
	static const char *const name[] = {
		[ XenbusStateUnknown      ] = "Unknown",
		[ XenbusStateInitialising ] = "Initialising",
		[ XenbusStateInitWait     ] = "InitWait",
		[ XenbusStateInitialised  ] = "Initialised",
		[ XenbusStateConnected    ] = "Connected",
		[ XenbusStateClosing      ] = "Closing",
		[ XenbusStateClosed	  ] = "Closed",
		[XenbusStateReconfiguring] = "Reconfiguring",
		[XenbusStateReconfigured] = "Reconfigured",
	};
	return (state < ARRAY_SIZE(name)) ? name[state] : "INVALID";
}
EXPORT_SYMBOL_GPL(xenbus_strstate);

/**
 * xenbus_watch_path - register a watch
 * @dev: xenbus device
 * @path: path to watch
 * @watch: watch to register
 * @callback: callback to register
 *
 * Register a @watch on the given path, using the given xenbus_watch structure
 * for storage, and the given @callback function as the callback.  Return 0 on
 * success, or -errno on error.  On success, the given @path will be saved as
 * @watch->node, and remains the caller's to free.  On error, @watch->node will
 * be NULL, the device will switch to %XenbusStateClosing, and the error will
 * be saved in the store.
 */
int xenbus_watch_path(struct xenbus_device *dev, const char *path,
		      struct xenbus_watch *watch,
		      void (*callback)(struct xenbus_watch *,
				       const char **, unsigned int))
{
	int err;

	watch->node = path;
	watch->callback = callback;

	err = register_xenbus_watch(watch);

	if (err) {
		watch->node = NULL;
		watch->callback = NULL;
		xenbus_dev_fatal(dev, err, "adding watch on %s", path);
	}

	return err;
}
EXPORT_SYMBOL_GPL(xenbus_watch_path);


/**
 * xenbus_watch_pathfmt - register a watch on a sprintf-formatted path
 * @dev: xenbus device
 * @watch: watch to register
 * @callback: callback to register
 * @pathfmt: format of path to watch
 *
 * Register a watch on the given @path, using the given xenbus_watch
 * structure for storage, and the given @callback function as the callback.
 * Return 0 on success, or -errno on error.  On success, the watched path
 * (@path/@path2) will be saved as @watch->node, and becomes the caller's to
 * kfree().  On error, watch->node will be NULL, so the caller has nothing to
 * free, the device will switch to %XenbusStateClosing, and the error will be
 * saved in the store.
 */
int xenbus_watch_pathfmt(struct xenbus_device *dev,
			 struct xenbus_watch *watch,
			 void (*callback)(struct xenbus_watch *,
					const char **, unsigned int),
			 const char *pathfmt, ...)
{
	int err;
	va_list ap;
	char *path;

	va_start(ap, pathfmt);
	path = kvasprintf(GFP_NOIO | __GFP_HIGH, pathfmt, ap);
	va_end(ap);

	if (!path) {
		xenbus_dev_fatal(dev, -ENOMEM, "allocating path for watch");
		return -ENOMEM;
	}
	err = xenbus_watch_path(dev, path, watch, callback);

	if (err)
		kfree(path);
	return err;
}
EXPORT_SYMBOL_GPL(xenbus_watch_pathfmt);

static void xenbus_switch_fatal(struct xenbus_device *, int, int,
				const char *, ...);

static int
__xenbus_switch_state(struct xenbus_device *dev,
		      enum xenbus_state state, int depth)
{
	/* We check whether the state is currently set to the given value, and
	   if not, then the state is set.  We don't want to unconditionally
	   write the given state, because we don't want to fire watches
	   unnecessarily.  Furthermore, if the node has gone, we don't write
	   to it, as the device will be tearing down, and we don't want to
	   resurrect that directory.

	   Note that, because of this cached value of our state, this
	   function will not take a caller's Xenstore transaction
	   (something it was trying to in the past) because dev->state
	   would not get reset if the transaction was aborted.
	 */

	struct xenbus_transaction xbt;
	int current_state;
	int err, abort;

	if (state == dev->state)
		return 0;

again:
	abort = 1;

	err = xenbus_transaction_start(&xbt);
	if (err) {
		xenbus_switch_fatal(dev, depth, err, "starting transaction");
		return 0;
	}

	err = xenbus_scanf(xbt, dev->nodename, "state", "%d", &current_state);
	if (err != 1)
		goto abort;

	err = xenbus_printf(xbt, dev->nodename, "state", "%d", state);
	if (err) {
		xenbus_switch_fatal(dev, depth, err, "writing new state");
		goto abort;
	}

	abort = 0;
abort:
	err = xenbus_transaction_end(xbt, abort);
	if (err) {
		if (err == -EAGAIN && !abort)
			goto again;
		xenbus_switch_fatal(dev, depth, err, "ending transaction");
	} else
		dev->state = state;

	return 0;
}

/**
 * xenbus_switch_state
 * @dev: xenbus device
 * @state: new state
 *
 * Advertise in the store a change of the given driver to the given new_state.
 * Return 0 on success, or -errno on error.  On error, the device will switch
 * to XenbusStateClosing, and the error will be saved in the store.
 */
int xenbus_switch_state(struct xenbus_device *dev, enum xenbus_state state)
{
	return __xenbus_switch_state(dev, state, 0);
}

EXPORT_SYMBOL_GPL(xenbus_switch_state);

int xenbus_frontend_closed(struct xenbus_device *dev)
{
	xenbus_switch_state(dev, XenbusStateClosed);
	complete(&dev->down);
	return 0;
}
EXPORT_SYMBOL_GPL(xenbus_frontend_closed);

/**
 * Return the path to the error node for the given device, or NULL on failure.
 * If the value returned is non-NULL, then it is the caller's to kfree.
 */
static char *error_path(struct xenbus_device *dev)
{
	return kasprintf(GFP_KERNEL, "error/%s", dev->nodename);
}


static void xenbus_va_dev_error(struct xenbus_device *dev, int err,
				const char *fmt, va_list ap)
{
	unsigned int len;
	char *printf_buffer = NULL;
	char *path_buffer = NULL;

#define PRINTF_BUFFER_SIZE 4096
	printf_buffer = kmalloc(PRINTF_BUFFER_SIZE, GFP_KERNEL);
	if (printf_buffer == NULL)
		goto fail;

	len = sprintf(printf_buffer, "%i ", -err);
	vsnprintf(printf_buffer+len, PRINTF_BUFFER_SIZE-len, fmt, ap);

	dev_err(&dev->dev, "%s\n", printf_buffer);

	path_buffer = error_path(dev);

	if (path_buffer == NULL) {
		dev_err(&dev->dev, "failed to write error node for %s (%s)\n",
		       dev->nodename, printf_buffer);
		goto fail;
	}

	if (xenbus_write(XBT_NIL, path_buffer, "error", printf_buffer) != 0) {
		dev_err(&dev->dev, "failed to write error node for %s (%s)\n",
		       dev->nodename, printf_buffer);
		goto fail;
	}

fail:
	kfree(printf_buffer);
	kfree(path_buffer);
}


/**
 * xenbus_dev_error
 * @dev: xenbus device
 * @err: error to report
 * @fmt: error message format
 *
 * Report the given negative errno into the store, along with the given
 * formatted message.
 */
void xenbus_dev_error(struct xenbus_device *dev, int err, const char *fmt, ...)
{
	va_list ap;

	va_start(ap, fmt);
	xenbus_va_dev_error(dev, err, fmt, ap);
	va_end(ap);
}
EXPORT_SYMBOL_GPL(xenbus_dev_error);

/**
 * xenbus_dev_fatal
 * @dev: xenbus device
 * @err: error to report
 * @fmt: error message format
 *
 * Equivalent to xenbus_dev_error(dev, err, fmt, args), followed by
 * xenbus_switch_state(dev, XenbusStateClosing) to schedule an orderly
 * closedown of this driver and its peer.
 */

void xenbus_dev_fatal(struct xenbus_device *dev, int err, const char *fmt, ...)
{
	va_list ap;

	va_start(ap, fmt);
	xenbus_va_dev_error(dev, err, fmt, ap);
	va_end(ap);

	xenbus_switch_state(dev, XenbusStateClosing);
}
EXPORT_SYMBOL_GPL(xenbus_dev_fatal);

/**
 * Equivalent to xenbus_dev_fatal(dev, err, fmt, args), but helps
 * avoiding recursion within xenbus_switch_state.
 */
static void xenbus_switch_fatal(struct xenbus_device *dev, int depth, int err,
				const char *fmt, ...)
{
	va_list ap;

	va_start(ap, fmt);
	xenbus_va_dev_error(dev, err, fmt, ap);
	va_end(ap);

	if (!depth)
		__xenbus_switch_state(dev, XenbusStateClosing, 1);
}

/**
 * xenbus_grant_ring
 * @dev: xenbus device
 * @vaddr: starting virtual address of the ring
 * @nr_pages: number of pages to be granted
 * @grefs: grant reference array to be filled in
 *
 * Grant access to the given @vaddr to the peer of the given device.
 * Then fill in @grefs with grant references.  Return 0 on success, or
 * -errno on error.  On error, the device will switch to
 * XenbusStateClosing, and the error will be saved in the store.
 */
int xenbus_grant_ring(struct xenbus_device *dev, void *vaddr,
		      unsigned int nr_pages, grant_ref_t *grefs)
{
	int err;
	int i, j;

	for (i = 0; i < nr_pages; i++) {
		unsigned long addr = (unsigned long)vaddr +
			(PAGE_SIZE * i);
		err = gnttab_grant_foreign_access(dev->otherend_id,
						  virt_to_mfn(addr), 0);
		if (err < 0) {
			xenbus_dev_fatal(dev, err,
					 "granting access to ring page");
			goto fail;
		}
		grefs[i] = err;
	}

	return 0;

fail:
	for (j = 0; j < i; j++)
		gnttab_end_foreign_access_ref(grefs[j], 0);
	return err;
}
EXPORT_SYMBOL_GPL(xenbus_grant_ring);


/**
 * Allocate an event channel for the given xenbus_device, assigning the newly
 * created local port to *port.  Return 0 on success, or -errno on error.  On
 * error, the device will switch to XenbusStateClosing, and the error will be
 * saved in the store.
 */
int xenbus_alloc_evtchn(struct xenbus_device *dev, int *port)
{
	struct evtchn_alloc_unbound alloc_unbound;
	int err;

	alloc_unbound.dom = DOMID_SELF;
	alloc_unbound.remote_dom = dev->otherend_id;

	err = HYPERVISOR_event_channel_op(EVTCHNOP_alloc_unbound,
					  &alloc_unbound);
	if (err)
		xenbus_dev_fatal(dev, err, "allocating event channel");
	else
		*port = alloc_unbound.port;

	return err;
}
EXPORT_SYMBOL_GPL(xenbus_alloc_evtchn);


/**
 * Free an existing event channel. Returns 0 on success or -errno on error.
 */
int xenbus_free_evtchn(struct xenbus_device *dev, int port)
{
	struct evtchn_close close;
	int err;

	close.port = port;

	err = HYPERVISOR_event_channel_op(EVTCHNOP_close, &close);
	if (err)
		xenbus_dev_error(dev, err, "freeing event channel %d", port);

	return err;
}
EXPORT_SYMBOL_GPL(xenbus_free_evtchn);


/**
 * xenbus_map_ring_valloc
 * @dev: xenbus device
 * @gnt_refs: grant reference array
 * @nr_grefs: number of grant references
 * @vaddr: pointer to address to be filled out by mapping
 *
 * Map @nr_grefs pages of memory into this domain from another
 * domain's grant table.  xenbus_map_ring_valloc allocates @nr_grefs
 * pages of virtual address space, maps the pages to that address, and
 * sets *vaddr to that address.  Returns 0 on success, and GNTST_*
 * (see xen/include/interface/grant_table.h) or -ENOMEM / -EINVAL on
 * error. If an error is returned, device will switch to
 * XenbusStateClosing and the error message will be saved in XenStore.
 */
int xenbus_map_ring_valloc(struct xenbus_device *dev, grant_ref_t *gnt_refs,
			   unsigned int nr_grefs, void **vaddr)
{
	return ring_ops->map(dev, gnt_refs, nr_grefs, vaddr);
}
EXPORT_SYMBOL_GPL(xenbus_map_ring_valloc);

/* N.B. sizeof(phys_addr_t) doesn't always equal to sizeof(unsigned
 * long), e.g. 32-on-64.  Caller is responsible for preparing the
 * right array to feed into this function */
static int __xenbus_map_ring(struct xenbus_device *dev,
			     grant_ref_t *gnt_refs,
			     unsigned int nr_grefs,
			     grant_handle_t *handles,
			     phys_addr_t *addrs,
			     unsigned int flags,
			     bool *leaked)
{
	struct gnttab_map_grant_ref map[XENBUS_MAX_RING_PAGES];
	struct gnttab_unmap_grant_ref unmap[XENBUS_MAX_RING_PAGES];
	int i, j;
	int err = GNTST_okay;

	if (nr_grefs > XENBUS_MAX_RING_PAGES)
		return -EINVAL;

	for (i = 0; i < nr_grefs; i++) {
		memset(&map[i], 0, sizeof(map[i]));
		gnttab_set_map_op(&map[i], addrs[i], flags, gnt_refs[i],
				  dev->otherend_id);
		handles[i] = INVALID_GRANT_HANDLE;
	}

	gnttab_batch_map(map, i);

	for (i = 0; i < nr_grefs; i++) {
		if (map[i].status != GNTST_okay) {
			err = map[i].status;
			xenbus_dev_fatal(dev, map[i].status,
					 "mapping in shared page %d from domain %d",
					 gnt_refs[i], dev->otherend_id);
			goto fail;
		} else
			handles[i] = map[i].handle;
	}

	return GNTST_okay;

 fail:
	for (i = j = 0; i < nr_grefs; i++) {
		if (handles[i] != INVALID_GRANT_HANDLE) {
			memset(&unmap[j], 0, sizeof(unmap[j]));
			gnttab_set_unmap_op(&unmap[j], (phys_addr_t)addrs[i],
					    GNTMAP_host_map, handles[i]);
			j++;
		}
	}

	if (HYPERVISOR_grant_table_op(GNTTABOP_unmap_grant_ref, unmap, j))
		BUG();

	*leaked = false;
	for (i = 0; i < j; i++) {
		if (unmap[i].status != GNTST_okay) {
			*leaked = true;
			break;
		}
	}

	return err;
}

static int xenbus_map_ring_valloc_pv(struct xenbus_device *dev,
				     grant_ref_t *gnt_refs,
				     unsigned int nr_grefs,
				     void **vaddr)
{
	struct xenbus_map_node *node;
	struct vm_struct *area;
	pte_t *ptes[XENBUS_MAX_RING_PAGES];
	phys_addr_t phys_addrs[XENBUS_MAX_RING_PAGES];
	int err = GNTST_okay;
	int i;
	bool leaked;

	*vaddr = NULL;

	if (nr_grefs > XENBUS_MAX_RING_PAGES)
		return -EINVAL;

	node = kzalloc(sizeof(*node), GFP_KERNEL);
	if (!node)
		return -ENOMEM;

	area = alloc_vm_area(PAGE_SIZE * nr_grefs, ptes);
	if (!area) {
		kfree(node);
		return -ENOMEM;
	}

	for (i = 0; i < nr_grefs; i++)
		phys_addrs[i] = arbitrary_virt_to_machine(ptes[i]).maddr;

	err = __xenbus_map_ring(dev, gnt_refs, nr_grefs, node->handles,
				phys_addrs,
				GNTMAP_host_map | GNTMAP_contains_pte,
				&leaked);
	if (err)
		goto failed;

	node->nr_handles = nr_grefs;
	node->pv.area = area;

	spin_lock(&xenbus_valloc_lock);
	list_add(&node->next, &xenbus_valloc_pages);
	spin_unlock(&xenbus_valloc_lock);

	*vaddr = area->addr;
	return 0;

failed:
	if (!leaked)
		free_vm_area(area);
	else
		pr_alert("leaking VM area %p size %u page(s)", area, nr_grefs);

	kfree(node);
	return err;
}

static int xenbus_map_ring_valloc_hvm(struct xenbus_device *dev,
				      grant_ref_t *gnt_ref,
				      unsigned int nr_grefs,
				      void **vaddr)
{
	struct xenbus_map_node *node;
	int i;
	int err;
	void *addr;
	bool leaked = false;
	/* Why do we need two arrays? See comment of __xenbus_map_ring */
	phys_addr_t phys_addrs[XENBUS_MAX_RING_PAGES];
	unsigned long addrs[XENBUS_MAX_RING_PAGES];

	if (nr_grefs > XENBUS_MAX_RING_PAGES)
		return -EINVAL;

	*vaddr = NULL;

	node = kzalloc(sizeof(*node), GFP_KERNEL);
	if (!node)
		return -ENOMEM;

	err = alloc_xenballooned_pages(nr_grefs, node->hvm.pages,
				       false /* lowmem */);
	if (err)
		goto out_err;

	for (i = 0; i < nr_grefs; i++) {
		unsigned long pfn = page_to_pfn(node->hvm.pages[i]);
		phys_addrs[i] = (unsigned long)pfn_to_kaddr(pfn);
		addrs[i] = (unsigned long)pfn_to_kaddr(pfn);
	}

	err = __xenbus_map_ring(dev, gnt_ref, nr_grefs, node->handles,
				phys_addrs, GNTMAP_host_map, &leaked);
	node->nr_handles = nr_grefs;

	if (err)
		goto out_free_ballooned_pages;

	addr = vmap(node->hvm.pages, nr_grefs, VM_MAP | VM_IOREMAP,
		    PAGE_KERNEL);
	if (!addr) {
		err = -ENOMEM;
		goto out_xenbus_unmap_ring;
	}

	node->hvm.addr = addr;

	spin_lock(&xenbus_valloc_lock);
	list_add(&node->next, &xenbus_valloc_pages);
	spin_unlock(&xenbus_valloc_lock);

	*vaddr = addr;
	return 0;

 out_xenbus_unmap_ring:
	if (!leaked)
		xenbus_unmap_ring(dev, node->handles, node->nr_handles,
				  addrs);
	else
		pr_alert("leaking %p size %u page(s)",
			 addr, nr_grefs);
 out_free_ballooned_pages:
	if (!leaked)
		free_xenballooned_pages(nr_grefs, node->hvm.pages);
 out_err:
	kfree(node);
	return err;
}


/**
 * xenbus_map_ring
 * @dev: xenbus device
 * @gnt_refs: grant reference array
 * @nr_grefs: number of grant reference
 * @handles: pointer to grant handle to be filled
 * @vaddrs: addresses to be mapped to
 * @leaked: fail to clean up a failed map, caller should not free vaddr
 *
 * Map pages of memory into this domain from another domain's grant table.
 * xenbus_map_ring does not allocate the virtual address space (you must do
 * this yourself!). It only maps in the pages to the specified address.
 * Returns 0 on success, and GNTST_* (see xen/include/interface/grant_table.h)
 * or -ENOMEM / -EINVAL on error. If an error is returned, device will switch to
 * XenbusStateClosing and the first error message will be saved in XenStore.
 * Further more if we fail to map the ring, caller should check @leaked.
 * If @leaked is not zero it means xenbus_map_ring fails to clean up, caller
 * should not free the address space of @vaddr.
 */
int xenbus_map_ring(struct xenbus_device *dev, grant_ref_t *gnt_refs,
		    unsigned int nr_grefs, grant_handle_t *handles,
		    unsigned long *vaddrs, bool *leaked)
{
	phys_addr_t phys_addrs[XENBUS_MAX_RING_PAGES];
	int i;

	if (nr_grefs > XENBUS_MAX_RING_PAGES)
		return -EINVAL;

	for (i = 0; i < nr_grefs; i++)
		phys_addrs[i] = (unsigned long)vaddrs[i];

	return __xenbus_map_ring(dev, gnt_refs, nr_grefs, handles,
				 phys_addrs, GNTMAP_host_map, leaked);
}
EXPORT_SYMBOL_GPL(xenbus_map_ring);


/**
 * xenbus_unmap_ring_vfree
 * @dev: xenbus device
 * @vaddr: addr to unmap
 *
 * Based on Rusty Russell's skeleton driver's unmap_page.
 * Unmap a page of memory in this domain that was imported from another domain.
 * Use xenbus_unmap_ring_vfree if you mapped in your memory with
 * xenbus_map_ring_valloc (it will free the virtual address space).
 * Returns 0 on success and returns GNTST_* on error
 * (see xen/include/interface/grant_table.h).
 */
int xenbus_unmap_ring_vfree(struct xenbus_device *dev, void *vaddr)
{
	return ring_ops->unmap(dev, vaddr);
}
EXPORT_SYMBOL_GPL(xenbus_unmap_ring_vfree);

static int xenbus_unmap_ring_vfree_pv(struct xenbus_device *dev, void *vaddr)
{
	struct xenbus_map_node *node;
	struct gnttab_unmap_grant_ref unmap[XENBUS_MAX_RING_PAGES];
	unsigned int level;
	int i;
	bool leaked = false;
	int err;

	spin_lock(&xenbus_valloc_lock);
	list_for_each_entry(node, &xenbus_valloc_pages, next) {
		if (node->pv.area->addr == vaddr) {
			list_del(&node->next);
			goto found;
		}
	}
	node = NULL;
 found:
	spin_unlock(&xenbus_valloc_lock);

	if (!node) {
		xenbus_dev_error(dev, -ENOENT,
				 "can't find mapped virtual address %p", vaddr);
		return GNTST_bad_virt_addr;
	}

	for (i = 0; i < node->nr_handles; i++) {
		unsigned long addr;

		memset(&unmap[i], 0, sizeof(unmap[i]));
		addr = (unsigned long)vaddr + (PAGE_SIZE * i);
		unmap[i].host_addr = arbitrary_virt_to_machine(
			lookup_address(addr, &level)).maddr;
		unmap[i].dev_bus_addr = 0;
		unmap[i].handle = node->handles[i];
	}

	if (HYPERVISOR_grant_table_op(GNTTABOP_unmap_grant_ref, unmap, i))
		BUG();

	err = GNTST_okay;
	leaked = false;
	for (i = 0; i < node->nr_handles; i++) {
		if (unmap[i].status != GNTST_okay) {
			leaked = true;
			xenbus_dev_error(dev, unmap[i].status,
					 "unmapping page at handle %d error %d",
					 node->handles[i], unmap[i].status);
			err = unmap[i].status;
			break;
		}
	}

	if (!leaked)
		free_vm_area(node->pv.area);
	else
		pr_alert("leaking VM area %p size %u page(s)",
			 node->pv.area, node->nr_handles);

	kfree(node);
	return err;
}

static int xenbus_unmap_ring_vfree_hvm(struct xenbus_device *dev, void *vaddr)
{
	int rv;
	struct xenbus_map_node *node;
	void *addr;
	unsigned long addrs[XENBUS_MAX_RING_PAGES];
	int i;

	spin_lock(&xenbus_valloc_lock);
	list_for_each_entry(node, &xenbus_valloc_pages, next) {
		addr = node->hvm.addr;
		if (addr == vaddr) {
			list_del(&node->next);
			goto found;
		}
	}
	node = addr = NULL;
 found:
	spin_unlock(&xenbus_valloc_lock);

	if (!node) {
		xenbus_dev_error(dev, -ENOENT,
				 "can't find mapped virtual address %p", vaddr);
		return GNTST_bad_virt_addr;
	}

	for (i = 0; i < node->nr_handles; i++)
		addrs[i] = (unsigned long)pfn_to_kaddr(page_to_pfn(node->hvm.pages[i]));

	rv = xenbus_unmap_ring(dev, node->handles, node->nr_handles,
			       addrs);
	if (!rv)
		vunmap(vaddr);
	else
		WARN(1, "Leaking %p, size %u page(s)\n", vaddr,
		     node->nr_handles);

	kfree(node);
	return rv;
}

/**
 * xenbus_unmap_ring
 * @dev: xenbus device
 * @handles: grant handle array
 * @nr_handles: number of handles in the array
 * @vaddrs: addresses to unmap
 *
 * Unmap memory in this domain that was imported from another domain.
 * Returns 0 on success and returns GNTST_* on error
 * (see xen/include/interface/grant_table.h).
 */
int xenbus_unmap_ring(struct xenbus_device *dev,
		      grant_handle_t *handles, unsigned int nr_handles,
		      unsigned long *vaddrs)
{
	struct gnttab_unmap_grant_ref unmap[XENBUS_MAX_RING_PAGES];
	int i;
	int err;

	if (nr_handles > XENBUS_MAX_RING_PAGES)
		return -EINVAL;

	for (i = 0; i < nr_handles; i++)
		gnttab_set_unmap_op(&unmap[i], vaddrs[i],
				    GNTMAP_host_map, handles[i]);

	if (HYPERVISOR_grant_table_op(GNTTABOP_unmap_grant_ref, unmap, i))
		BUG();

	err = GNTST_okay;
	for (i = 0; i < nr_handles; i++) {
		if (unmap[i].status != GNTST_okay) {
			xenbus_dev_error(dev, unmap[i].status,
					 "unmapping page at handle %d error %d",
					 handles[i], unmap[i].status);
			err = unmap[i].status;
			break;
		}
	}

	return err;
}
EXPORT_SYMBOL_GPL(xenbus_unmap_ring);


/**
 * xenbus_read_driver_state
 * @path: path for driver
 *
 * Return the state of the driver rooted at the given store path, or
 * XenbusStateUnknown if no state can be read.
 */
enum xenbus_state xenbus_read_driver_state(const char *path)
{
	enum xenbus_state result;
	int err = xenbus_gather(XBT_NIL, path, "state", "%d", &result, NULL);
	if (err)
		result = XenbusStateUnknown;

	return result;
}
EXPORT_SYMBOL_GPL(xenbus_read_driver_state);

static const struct xenbus_ring_ops ring_ops_pv = {
	.map = xenbus_map_ring_valloc_pv,
	.unmap = xenbus_unmap_ring_vfree_pv,
};

static const struct xenbus_ring_ops ring_ops_hvm = {
	.map = xenbus_map_ring_valloc_hvm,
	.unmap = xenbus_unmap_ring_vfree_hvm,
};

void __init xenbus_ring_ops_init(void)
{
	if (!xen_feature(XENFEAT_auto_translated_physmap))
		ring_ops = &ring_ops_pv;
	else
		ring_ops = &ring_ops_hvm;
}