aboutsummaryrefslogtreecommitdiffstats
path: root/drivers/misc/vmw_balloon.c
blob: 2421835d5daf65cfccbeb5b9c6d373c836658658 (plain) (blame)
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
/*
 * VMware Balloon driver.
 *
 * Copyright (C) 2000-2010, VMware, Inc. All Rights Reserved.
 *
 * 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; version 2 of the License and no 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, GOOD TITLE or
 * NON INFRINGEMENT.  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, write to the Free Software
 * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
 *
 * Maintained by: Dmitry Torokhov <dtor@vmware.com>
 */

/*
 * This is VMware physical memory management driver for Linux. The driver
 * acts like a "balloon" that can be inflated to reclaim physical pages by
 * reserving them in the guest and invalidating them in the monitor,
 * freeing up the underlying machine pages so they can be allocated to
 * other guests.  The balloon can also be deflated to allow the guest to
 * use more physical memory. Higher level policies can control the sizes
 * of balloons in VMs in order to manage physical memory resources.
 */

//#define DEBUG
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/sched.h>
#include <linux/module.h>
#include <linux/workqueue.h>
#include <linux/debugfs.h>
#include <linux/seq_file.h>
#include <asm/hypervisor.h>

MODULE_AUTHOR("VMware, Inc.");
MODULE_DESCRIPTION("VMware Memory Control (Balloon) Driver");
MODULE_VERSION("1.2.1.3-k");
MODULE_ALIAS("dmi:*:svnVMware*:*");
MODULE_ALIAS("vmware_vmmemctl");
MODULE_LICENSE("GPL");

/*
 * Various constants controlling rate of inflaint/deflating balloon,
 * measured in pages.
 */

/*
 * Rate of allocating memory when there is no memory pressure
 * (driver performs non-sleeping allocations).
 */
#define VMW_BALLOON_NOSLEEP_ALLOC_MAX	16384U

/*
 * Rates of memory allocaton when guest experiences memory pressure
 * (driver performs sleeping allocations).
 */
#define VMW_BALLOON_RATE_ALLOC_MIN	512U
#define VMW_BALLOON_RATE_ALLOC_MAX	2048U
#define VMW_BALLOON_RATE_ALLOC_INC	16U

/*
 * Rates for releasing pages while deflating balloon.
 */
#define VMW_BALLOON_RATE_FREE_MIN	512U
#define VMW_BALLOON_RATE_FREE_MAX	16384U
#define VMW_BALLOON_RATE_FREE_INC	16U

/*
 * When guest is under memory pressure, use a reduced page allocation
 * rate for next several cycles.
 */
#define VMW_BALLOON_SLOW_CYCLES		4

/*
 * Use __GFP_HIGHMEM to allow pages from HIGHMEM zone. We don't
 * allow wait (__GFP_WAIT) for NOSLEEP page allocations. Use
 * __GFP_NOWARN, to suppress page allocation failure warnings.
 */
#define VMW_PAGE_ALLOC_NOSLEEP		(__GFP_HIGHMEM|__GFP_NOWARN)

/*
 * Use GFP_HIGHUSER when executing in a separate kernel thread
 * context and allocation can sleep.  This is less stressful to
 * the guest memory system, since it allows the thread to block
 * while memory is reclaimed, and won't take pages from emergency
 * low-memory pools.
 */
#define VMW_PAGE_ALLOC_CANSLEEP		(GFP_HIGHUSER)

/* Maximum number of page allocations without yielding processor */
#define VMW_BALLOON_YIELD_THRESHOLD	1024

/* Maximum number of refused pages we accumulate during inflation cycle */
#define VMW_BALLOON_MAX_REFUSED		16

/*
 * Hypervisor communication port definitions.
 */
#define VMW_BALLOON_HV_PORT		0x5670
#define VMW_BALLOON_HV_MAGIC		0x456c6d6f
#define VMW_BALLOON_PROTOCOL_VERSION	2
#define VMW_BALLOON_GUEST_ID		1	/* Linux */

#define VMW_BALLOON_CMD_START		0
#define VMW_BALLOON_CMD_GET_TARGET	1
#define VMW_BALLOON_CMD_LOCK		2
#define VMW_BALLOON_CMD_UNLOCK		3
#define VMW_BALLOON_CMD_GUEST_ID	4

/* error codes */
#define VMW_BALLOON_SUCCESS		0
#define VMW_BALLOON_FAILURE		-1
#define VMW_BALLOON_ERROR_CMD_INVALID	1
#define VMW_BALLOON_ERROR_PPN_INVALID	2
#define VMW_BALLOON_ERROR_PPN_LOCKED	3
#define VMW_BALLOON_ERROR_PPN_UNLOCKED	4
#define VMW_BALLOON_ERROR_PPN_PINNED	5
#define VMW_BALLOON_ERROR_PPN_NOTNEEDED	6
#define VMW_BALLOON_ERROR_RESET		7
#define VMW_BALLOON_ERROR_BUSY		8

#define VMWARE_BALLOON_CMD(cmd, data, result)		\
({							\
	unsigned long __stat, __dummy1, __dummy2;	\
	__asm__ __volatile__ ("inl %%dx" :		\
		"=a"(__stat),				\
		"=c"(__dummy1),				\
		"=d"(__dummy2),				\
		"=b"(result) :				\
		"0"(VMW_BALLOON_HV_MAGIC),		\
		"1"(VMW_BALLOON_CMD_##cmd),		\
		"2"(VMW_BALLOON_HV_PORT),		\
		"3"(data) :				\
		"memory");				\
	result &= -1UL;					\
	__stat & -1UL;					\
})

#ifdef CONFIG_DEBUG_FS
struct vmballoon_stats {
	unsigned int timer;

	/* allocation statistics */
	unsigned int alloc;
	unsigned int alloc_fail;
	unsigned int sleep_alloc;
	unsigned int sleep_alloc_fail;
	unsigned int refused_alloc;
	unsigned int refused_free;
	unsigned int free;

	/* monitor operations */
	unsigned int lock;
	unsigned int lock_fail;
	unsigned int unlock;
	unsigned int unlock_fail;
	unsigned int target;
	unsigned int target_fail;
	unsigned int start;
	unsigned int start_fail;
	unsigned int guest_type;
	unsigned int guest_type_fail;
};

#define STATS_INC(stat) (stat)++
#else
#define STATS_INC(stat)
#endif

struct vmballoon {

	/* list of reserved physical pages */
	struct list_head pages;

	/* transient list of non-balloonable pages */
	struct list_head refused_pages;
	unsigned int n_refused_pages;

	/* balloon size in pages */
	unsigned int size;
	unsigned int target;

	/* reset flag */
	bool reset_required;

	/* adjustment rates (pages per second) */
	unsigned int rate_alloc;
	unsigned int rate_free;

	/* slowdown page allocations for next few cycles */
	unsigned int slow_allocation_cycles;

#ifdef CONFIG_DEBUG_FS
	/* statistics */
	struct vmballoon_stats stats;

	/* debugfs file exporting statistics */
	struct dentry *dbg_entry;
#endif

	struct sysinfo sysinfo;

	struct delayed_work dwork;
};

static struct vmballoon balloon;

/*
 * Send "start" command to the host, communicating supported version
 * of the protocol.
 */
static bool vmballoon_send_start(struct vmballoon *b)
{
	unsigned long status, dummy;

	STATS_INC(b->stats.start);

	status = VMWARE_BALLOON_CMD(START, VMW_BALLOON_PROTOCOL_VERSION, dummy);
	if (status == VMW_BALLOON_SUCCESS)
		return true;

	pr_debug("%s - failed, hv returns %ld\n", __func__, status);
	STATS_INC(b->stats.start_fail);
	return false;
}

static bool vmballoon_check_status(struct vmballoon *b, unsigned long status)
{
	switch (status) {
	case VMW_BALLOON_SUCCESS:
		return true;

	case VMW_BALLOON_ERROR_RESET:
		b->reset_required = true;
		/* fall through */

	default:
		return false;
	}
}

/*
 * Communicate guest type to the host so that it can adjust ballooning
 * algorithm to the one most appropriate for the guest. This command
 * is normally issued after sending "start" command and is part of
 * standard reset sequence.
 */
static bool vmballoon_send_guest_id(struct vmballoon *b)
{
	unsigned long status, dummy;

	status = VMWARE_BALLOON_CMD(GUEST_ID, VMW_BALLOON_GUEST_ID, dummy);

	STATS_INC(b->stats.guest_type);

	if (vmballoon_check_status(b, status))
		return true;

	pr_debug("%s - failed, hv returns %ld\n", __func__, status);
	STATS_INC(b->stats.guest_type_fail);
	return false;
}

/*
 * Retrieve desired balloon size from the host.
 */
static bool vmballoon_send_get_target(struct vmballoon *b, u32 *new_target)
{
	unsigned long status;
	unsigned long target;
	unsigned long limit;
	u32 limit32;

	/*
	 * si_meminfo() is cheap. Moreover, we want to provide dynamic
	 * max balloon size later. So let us call si_meminfo() every
	 * iteration.
	 */
	si_meminfo(&b->sysinfo);
	limit = b->sysinfo.totalram;

	/* Ensure limit fits in 32-bits */
	limit32 = (u32)limit;
	if (limit != limit32)
		return false;

	/* update stats */
	STATS_INC(b->stats.target);

	status = VMWARE_BALLOON_CMD(GET_TARGET, limit, target);
	if (vmballoon_check_status(b, status)) {
		*new_target = target;
		return true;
	}

	pr_debug("%s - failed, hv returns %ld\n", __func__, status);
	STATS_INC(b->stats.target_fail);
	return false;
}

/*
 * Notify the host about allocated page so that host can use it without
 * fear that guest will need it. Host may reject some pages, we need to
 * check the return value and maybe submit a different page.
 */
static int vmballoon_send_lock_page(struct vmballoon *b, unsigned long pfn,
				     unsigned int *hv_status)
{
	unsigned long status, dummy;
	u32 pfn32;

	pfn32 = (u32)pfn;
	if (pfn32 != pfn)
		return -1;

	STATS_INC(b->stats.lock);

	*hv_status = status = VMWARE_BALLOON_CMD(LOCK, pfn, dummy);
	if (vmballoon_check_status(b, status))
		return 0;

	pr_debug("%s - ppn %lx, hv returns %ld\n", __func__, pfn, status);
	STATS_INC(b->stats.lock_fail);
	return 1;
}

/*
 * Notify the host that guest intends to release given page back into
 * the pool of available (to the guest) pages.
 */
static bool vmballoon_send_unlock_page(struct vmballoon *b, unsigned long pfn)
{
	unsigned long status, dummy;
	u32 pfn32;

	pfn32 = (u32)pfn;
	if (pfn32 != pfn)
		return false;

	STATS_INC(b->stats.unlock);

	status = VMWARE_BALLOON_CMD(UNLOCK, pfn, dummy);
	if (vmballoon_check_status(b, status))
		return true;

	pr_debug("%s - ppn %lx, hv returns %ld\n", __func__, pfn, status);
	STATS_INC(b->stats.unlock_fail);
	return false;
}

/*
 * Quickly release all pages allocated for the balloon. This function is
 * called when host decides to "reset" balloon for one reason or another.
 * Unlike normal "deflate" we do not (shall not) notify host of the pages
 * being released.
 */
static void vmballoon_pop(struct vmballoon *b)
{
	struct page *page, *next;
	unsigned int count = 0;

	list_for_each_entry_safe(page, next, &b->pages, lru) {
		list_del(&page->lru);
		__free_page(page);
		STATS_INC(b->stats.free);
		b->size--;

		if (++count >= b->rate_free) {
			count = 0;
			cond_resched();
		}
	}
}

/*
 * Perform standard reset sequence by popping the balloon (in case it
 * is not  empty) and then restarting protocol. This operation normally
 * happens when host responds with VMW_BALLOON_ERROR_RESET to a command.
 */
static void vmballoon_reset(struct vmballoon *b)
{
	/* free all pages, skipping monitor unlock */
	vmballoon_pop(b);

	if (vmballoon_send_start(b)) {
		b->reset_required = false;
		if (!vmballoon_send_guest_id(b))
			pr_err("failed to send guest ID to the host\n");
	}
}

/*
 * Allocate (or reserve) a page for the balloon and notify the host.  If host
 * refuses the page put it on "refuse" list and allocate another one until host
 * is satisfied. "Refused" pages are released at the end of inflation cycle
 * (when we allocate b->rate_alloc pages).
 */
static int vmballoon_reserve_page(struct vmballoon *b, bool can_sleep)
{
	struct page *page;
	gfp_t flags;
	unsigned int hv_status;
	int locked;
	flags = can_sleep ? VMW_PAGE_ALLOC_CANSLEEP : VMW_PAGE_ALLOC_NOSLEEP;

	do {
		if (!can_sleep)
			STATS_INC(b->stats.alloc);
		else
			STATS_INC(b->stats.sleep_alloc);

		page = alloc_page(flags);
		if (!page) {
			if (!can_sleep)
				STATS_INC(b->stats.alloc_fail);
			else
				STATS_INC(b->stats.sleep_alloc_fail);
			return -ENOMEM;
		}

		/* inform monitor */
		locked = vmballoon_send_lock_page(b, page_to_pfn(page), &hv_status);
		if (locked > 0) {
			STATS_INC(b->stats.refused_alloc);

			if (hv_status == VMW_BALLOON_ERROR_RESET ||
			    hv_status == VMW_BALLOON_ERROR_PPN_NOTNEEDED) {
				__free_page(page);
				return -EIO;
			}

			/*
			 * Place page on the list of non-balloonable pages
			 * and retry allocation, unless we already accumulated
			 * too many of them, in which case take a breather.
			 */
			list_add(&page->lru, &b->refused_pages);
			if (++b->n_refused_pages >= VMW_BALLOON_MAX_REFUSED)
				return -EIO;
		}
	} while (locked != 0);

	/* track allocated page */
	list_add(&page->lru, &b->pages);

	/* update balloon size */
	b->size++;

	return 0;
}

/*
 * Release the page allocated for the balloon. Note that we first notify
 * the host so it can make sure the page will be available for the guest
 * to use, if needed.
 */
static int vmballoon_release_page(struct vmballoon *b, struct page *page)
{
	if (!vmballoon_send_unlock_page(b, page_to_pfn(page)))
		return -EIO;

	list_del(&page->lru);

	/* deallocate page */
	__free_page(page);
	STATS_INC(b->stats.free);

	/* update balloon size */
	b->size--;

	return 0;
}

/*
 * Release pages that were allocated while attempting to inflate the
 * balloon but were refused by the host for one reason or another.
 */
static void vmballoon_release_refused_pages(struct vmballoon *b)
{
	struct page *page, *next;

	list_for_each_entry_safe(page, next, &b->refused_pages, lru) {
		list_del(&page->lru);
		__free_page(page);
		STATS_INC(b->stats.refused_free);
	}

	b->n_refused_pages = 0;
}

/*
 * Inflate the balloon towards its target size. Note that we try to limit
 * the rate of allocation to make sure we are not choking the rest of the
 * system.
 */
static void vmballoon_inflate(struct vmballoon *b)
{
	unsigned int goal;
	unsigned int rate;
	unsigned int i;
	unsigned int allocations = 0;
	int error = 0;
	bool alloc_can_sleep = false;

	pr_debug("%s - size: %d, target %d\n", __func__, b->size, b->target);

	/*
	 * First try NOSLEEP page allocations to inflate balloon.
	 *
	 * If we do not throttle nosleep allocations, we can drain all
	 * free pages in the guest quickly (if the balloon target is high).
	 * As a side-effect, draining free pages helps to inform (force)
	 * the guest to start swapping if balloon target is not met yet,
	 * which is a desired behavior. However, balloon driver can consume
	 * all available CPU cycles if too many pages are allocated in a
	 * second. Therefore, we throttle nosleep allocations even when
	 * the guest is not under memory pressure. OTOH, if we have already
	 * predicted that the guest is under memory pressure, then we
	 * slowdown page allocations considerably.
	 */

	goal = b->target - b->size;
	/*
	 * Start with no sleep allocation rate which may be higher
	 * than sleeping allocation rate.
	 */
	rate = b->slow_allocation_cycles ?
			b->rate_alloc : VMW_BALLOON_NOSLEEP_ALLOC_MAX;

	pr_debug("%s - goal: %d, no-sleep rate: %d, sleep rate: %d\n",
		 __func__, goal, rate, b->rate_alloc);

	for (i = 0; i < goal; i++) {

		error = vmballoon_reserve_page(b, alloc_can_sleep);
		if (error) {
			if (error != -ENOMEM) {
				/*
				 * Not a page allocation failure, stop this
				 * cycle. Maybe we'll get new target from
				 * the host soon.
				 */
				break;
			}

			if (alloc_can_sleep) {
				/*
				 * CANSLEEP page allocation failed, so guest
				 * is under severe memory pressure. Quickly
				 * decrease allocation rate.
				 */
				b->rate_alloc = max(b->rate_alloc / 2,
						    VMW_BALLOON_RATE_ALLOC_MIN);
				break;
			}

			/*
			 * NOSLEEP page allocation failed, so the guest is
			 * under memory pressure. Let us slow down page
			 * allocations for next few cycles so that the guest
			 * gets out of memory pressure. Also, if we already
			 * allocated b->rate_alloc pages, let's pause,
			 * otherwise switch to sleeping allocations.
			 */
			b->slow_allocation_cycles = VMW_BALLOON_SLOW_CYCLES;

			if (i >= b->rate_alloc)
				break;

			alloc_can_sleep = true;
			/* Lower rate for sleeping allocations. */
			rate = b->rate_alloc;
		}

		if (++allocations > VMW_BALLOON_YIELD_THRESHOLD) {
			cond_resched();
			allocations = 0;
		}

		if (i >= rate) {
			/* We allocated enough pages, let's take a break. */
			break;
		}
	}

	/*
	 * We reached our goal without failures so try increasing
	 * allocation rate.
	 */
	if (error == 0 && i >= b->rate_alloc) {
		unsigned int mult = i / b->rate_alloc;

		b->rate_alloc =
			min(b->rate_alloc + mult * VMW_BALLOON_RATE_ALLOC_INC,
			    VMW_BALLOON_RATE_ALLOC_MAX);
	}

	vmballoon_release_refused_pages(b);
}

/*
 * Decrease the size of the balloon allowing guest to use more memory.
 */
static void vmballoon_deflate(struct vmballoon *b)
{
	struct page *page, *next;
	unsigned int i = 0;
	unsigned int goal;
	int error;

	pr_debug("%s - size: %d, target %d\n", __func__, b->size, b->target);

	/* limit deallocation rate */
	goal = min(b->size - b->target, b->rate_free);

	pr_debug("%s - goal: %d, rate: %d\n", __func__, goal, b->rate_free);

	/* free pages to reach target */
	list_for_each_entry_safe(page, next, &b->pages, lru) {
		error = vmballoon_release_page(b, page);
		if (error) {
			/* quickly decrease rate in case of error */
			b->rate_free = max(b->rate_free / 2,
					   VMW_BALLOON_RATE_FREE_MIN);
			return;
		}

		if (++i >= goal)
			break;
	}

	/* slowly increase rate if there were no errors */
	b->rate_free = min(b->rate_free + VMW_BALLOON_RATE_FREE_INC,
			   VMW_BALLOON_RATE_FREE_MAX);
}

/*
 * Balloon work function: reset protocol, if needed, get the new size and
 * adjust balloon as needed. Repeat in 1 sec.
 */
static void vmballoon_work(struct work_struct *work)
{
	struct delayed_work *dwork = to_delayed_work(work);
	struct vmballoon *b = container_of(dwork, struct vmballoon, dwork);
	unsigned int target;

	STATS_INC(b->stats.timer);

	if (b->reset_required)
		vmballoon_reset(b);

	if (b->slow_allocation_cycles > 0)
		b->slow_allocation_cycles--;

	if (vmballoon_send_get_target(b, &target)) {
		/* update target, adjust size */
		b->target = target;

		if (b->size < target)
			vmballoon_inflate(b);
		else if (b->size > target)
			vmballoon_deflate(b);
	}

	/*
	 * We are using a freezable workqueue so that balloon operations are
	 * stopped while the system transitions to/from sleep/hibernation.
	 */
	queue_delayed_work(system_freezable_wq,
			   dwork, round_jiffies_relative(HZ));
}

/*
 * DEBUGFS Interface
 */
#ifdef CONFIG_DEBUG_FS

static int vmballoon_debug_show(struct seq_file *f, void *offset)
{
	struct vmballoon *b = f->private;
	struct vmballoon_stats *stats = &b->stats;

	/* format size info */
	seq_printf(f,
		   "target:             %8d pages\n"
		   "current:            %8d pages\n",
		   b->target, b->size);

	/* format rate info */
	seq_printf(f,
		   "rateNoSleepAlloc:   %8d pages/sec\n"
		   "rateSleepAlloc:     %8d pages/sec\n"
		   "rateFree:           %8d pages/sec\n",
		   VMW_BALLOON_NOSLEEP_ALLOC_MAX,
		   b->rate_alloc, b->rate_free);

	seq_printf(f,
		   "\n"
		   "timer:              %8u\n"
		   "start:              %8u (%4u failed)\n"
		   "guestType:          %8u (%4u failed)\n"
		   "lock:               %8u (%4u failed)\n"
		   "unlock:             %8u (%4u failed)\n"
		   "target:             %8u (%4u failed)\n"
		   "primNoSleepAlloc:   %8u (%4u failed)\n"
		   "primCanSleepAlloc:  %8u (%4u failed)\n"
		   "primFree:           %8u\n"
		   "errAlloc:           %8u\n"
		   "errFree:            %8u\n",
		   stats->timer,
		   stats->start, stats->start_fail,
		   stats->guest_type, stats->guest_type_fail,
		   stats->lock,  stats->lock_fail,
		   stats->unlock, stats->unlock_fail,
		   stats->target, stats->target_fail,
		   stats->alloc, stats->alloc_fail,
		   stats->sleep_alloc, stats->sleep_alloc_fail,
		   stats->free,
		   stats->refused_alloc, stats->refused_free);

	return 0;
}

static int vmballoon_debug_open(struct inode *inode, struct file *file)
{
	return single_open(file, vmballoon_debug_show, inode->i_private);
}

static const struct file_operations vmballoon_debug_fops = {
	.owner		= THIS_MODULE,
	.open		= vmballoon_debug_open,
	.read		= seq_read,
	.llseek		= seq_lseek,
	.release	= single_release,
};

static int __init vmballoon_debugfs_init(struct vmballoon *b)
{
	int error;

	b->dbg_entry = debugfs_create_file("vmmemctl", S_IRUGO, NULL, b,
					   &vmballoon_debug_fops);
	if (IS_ERR(b->dbg_entry)) {
		error = PTR_ERR(b->dbg_entry);
		pr_err("failed to create debugfs entry, error: %d\n", error);
		return error;
	}

	return 0;
}

static void __exit vmballoon_debugfs_exit(struct vmballoon *b)
{
	debugfs_remove(b->dbg_entry);
}

#else

static inline int vmballoon_debugfs_init(struct vmballoon *b)
{
	return 0;
}

static inline void vmballoon_debugfs_exit(struct vmballoon *b)
{
}

#endif	/* CONFIG_DEBUG_FS */

static int __init vmballoon_init(void)
{
	int error;

	/*
	 * Check if we are running on VMware's hypervisor and bail out
	 * if we are not.
	 */
	if (x86_hyper != &x86_hyper_vmware)
		return -ENODEV;

	INIT_LIST_HEAD(&balloon.pages);
	INIT_LIST_HEAD(&balloon.refused_pages);

	/* initialize rates */
	balloon.rate_alloc = VMW_BALLOON_RATE_ALLOC_MAX;
	balloon.rate_free = VMW_BALLOON_RATE_FREE_MAX;

	INIT_DELAYED_WORK(&balloon.dwork, vmballoon_work);

	/*
	 * Start balloon.
	 */
	if (!vmballoon_send_start(&balloon)) {
		pr_err("failed to send start command to the host\n");
		return -EIO;
	}

	if (!vmballoon_send_guest_id(&balloon)) {
		pr_err("failed to send guest ID to the host\n");
		return -EIO;
	}

	error = vmballoon_debugfs_init(&balloon);
	if (error)
		return error;

	queue_delayed_work(system_freezable_wq, &balloon.dwork, 0);

	return 0;
}
module_init(vmballoon_init);

static void __exit vmballoon_exit(void)
{
	cancel_delayed_work_sync(&balloon.dwork);

	vmballoon_debugfs_exit(&balloon);

	/*
	 * Deallocate all reserved memory, and reset connection with monitor.
	 * Reset connection before deallocating memory to avoid potential for
	 * additional spurious resets from guest touching deallocated pages.
	 */
	vmballoon_send_start(&balloon);
	vmballoon_pop(&balloon);
}
module_exit(vmballoon_exit);
t;jeremy@xensource.com> 2007-07-17 21:37:06 -0400 committer Jeremy Fitzhardinge <jeremy@goop.org> 2007-07-18 11:47:45 -0400 xen: add virtual block device driver.' href='/cgit/cgit.cgi/litmus-rt-budgetable-locks.git/.git/commit/drivers/block/xen-blkfront.c?h=update_litmus_2019&id=9f27ee595038653ddf8bca871200d39247d6f4fc'>9f27ee595038
fa1bd3591a66






















d54142c71f05



7b32d1044ae7
fa1bd3591a66

0e3458269939
fa1bd3591a66



9f27ee595038



1d78d7055629

a1b4b12b372e
1d78d7055629
5d7ed20e822e
1d78d7055629

a63c848b0405
9f27ee595038
139617437aff


6e9624b8caec
2a48fc0ab242
6e9624b8caec
139617437aff














139617437aff
2a48fc0ab242
139617437aff
9f27ee595038

a63c848b0405
9f27ee595038
a63c848b0405
7fd152f4b6ae


2a48fc0ab242
7fd152f4b6ae



acfca3c622a0


7fd152f4b6ae









d54142c71f05
7fd152f4b6ae







d54142c71f05
7fd152f4b6ae


9f27ee595038
7fd152f4b6ae
a4cc14ec9f0e
2a48fc0ab242
9f27ee595038


83d5cde47ded
9f27ee595038

a63c848b0405

597592d951cd
8a6cfeb6deca
9f27ee595038


ec9c42ec793d
9f27ee595038










203fd61f42fe
1d78d7055629
9f27ee595038



6e833587e11e
9f27ee595038












5a60d0cd4ff2
9f27ee595038







d2f0c52bec95
4f93f09b72d6
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
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320






































                                                                               
                        
                        
                         
                       
                        
                              
 
                    



                            
                             


                                      
                                       










                                 
                                


                                                            
                                    
                                                             
 
                                                         







                                                                    
                           
                                    





                                     
                                                              





                                                
                                   
                     



                                      



                                   




                                                        
                                   



                                       



                                                
 
                                                  



                                                           
                                      








                                                           
                                        


                               
















































                                                                           





                                                                 
                                                                        














                                                                            
                                                               
                                                                
 
                                                                 




























                                                                                      
  


                                                                      
  
                         





                                                                

                                  
                   
                              
                               
















                                                                          
                                       

                          
                                                                  



                                                









                                                                      
                                                             
         
 






                                                                       




                                                               




                                                         

                                                                   



                                                                


























                                                                             
                                                      








                                               
                                                      
                                                  



                                           
                                       
 
                                                   



                                                         
                                                           



                                                                           
 
















                                                                    
                                 




                                                              
                                                     

                                                                               
                                                      
                                          





                                                                         
                                                                   



                                                            


                                                    





                       
                                                   
 
                                                       
                                                       

                                                             


 


                                                               



                           


                            



                                 















                                                                                                                     
 




                                                    

                                   
                             
 


















                                                                               









                                                    
                             




                             
                          











                                                

                                              



                   

















                                                                          
                                     













                                              

































                                                                                    
                                     



























                                                                           
                  













                                                                 


                                                         
                                                




                                                    
                                                                    




                                                                                              
                                                    









                                                                                                    

                                                        







                                                                                         
                                                          































                                                                        
                                                                             





                                                                         

                                                                






























                                                                           
                                                     





























                                                                   





                                                                 






















                                                                     















                                                                             






                                                                                

         



                                                                              
                                                                       



















                                                                                                        

                                       
                            
         





                                                                            
                                 










                                                                              
                                         
 
                                         

                            
                                                 














                                                            

                                                             













                                                              
                                     















                                                                               
                                                                            
































                                                                              
                                                                





                                                                   
                                         





                                                             
























                                                  
                               










                                                                     










                                                                     
                    
 












                                                                  
                                          


                                   

                       

                      
         
















                                                                
                                                               
                                  



                                                                 
                                        
          
                                                    
           
                                
 
                            
                                                          
 
                                                                     














                                                                     

                           


   

                                                      
                                                      

                                                            
                                                                
 
                                                                                     




                                     

                                      








                                       
                                       



                      
                                                       
 


                                                                  
 
                                                            


                            






















                                                                  



                                                            
                                        

                                            
                            



                                      



                 

                                                       
                                                                
 
                                             

 
                                                              
 


                                             
 
                                    
 














                                     
    
                                      
                   

 
                                                            
 
                                                        


                                    
                                    



                                   


                             









                                                                  
                                                                         







                                                    
                                                                         


                                            
         
 
    
                                      


                 
                                                              

                             

                                 
                               
                             


  
                                                       










                                        
                                            
                                      



                                  
                          












                                                                                 
                                   







                                                        
                        
                       
/*
 * blkfront.c
 *
 * XenLinux virtual block device driver.
 *
 * Copyright (c) 2003-2004, Keir Fraser & Steve Hand
 * Modifications by Mark A. Williamson are (c) Intel Research Cambridge
 * Copyright (c) 2004, Christian Limpach
 * Copyright (c) 2004, Andrew Warfield
 * Copyright (c) 2005, Christopher Clark
 * 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/interrupt.h>
#include <linux/blkdev.h>
#include <linux/hdreg.h>
#include <linux/cdrom.h>
#include <linux/module.h>
#include <linux/slab.h>
#include <linux/mutex.h>
#include <linux/scatterlist.h>

#include <xen/xen.h>
#include <xen/xenbus.h>
#include <xen/grant_table.h>
#include <xen/events.h>
#include <xen/page.h>
#include <xen/platform_pci.h>

#include <xen/interface/grant_table.h>
#include <xen/interface/io/blkif.h>
#include <xen/interface/io/protocols.h>

#include <asm/xen/hypervisor.h>

enum blkif_state {
	BLKIF_STATE_DISCONNECTED,
	BLKIF_STATE_CONNECTED,
	BLKIF_STATE_SUSPENDED,
};

struct blk_shadow {
	struct blkif_request req;
	struct request *request;
	unsigned long frame[BLKIF_MAX_SEGMENTS_PER_REQUEST];
};

static DEFINE_MUTEX(blkfront_mutex);
static const struct block_device_operations xlvbd_block_fops;

#define BLK_RING_SIZE __CONST_RING_SIZE(blkif, PAGE_SIZE)

/*
 * We have one of these per vbd, whether ide, scsi or 'other'.  They
 * hang in private_data off the gendisk structure. We may end up
 * putting all kinds of interesting stuff here :-)
 */
struct blkfront_info
{
	struct mutex mutex;
	struct xenbus_device *xbdev;
	struct gendisk *gd;
	int vdevice;
	blkif_vdev_t handle;
	enum blkif_state connected;
	int ring_ref;
	struct blkif_front_ring ring;
	struct scatterlist sg[BLKIF_MAX_SEGMENTS_PER_REQUEST];
	unsigned int evtchn, irq;
	struct request_queue *rq;
	struct work_struct work;
	struct gnttab_free_callback callback;
	struct blk_shadow shadow[BLK_RING_SIZE];
	unsigned long shadow_free;
	unsigned int feature_flush;
	int is_ready;
};

static DEFINE_SPINLOCK(blkif_io_lock);

static unsigned int nr_minors;
static unsigned long *minors;
static DEFINE_SPINLOCK(minor_lock);

#define MAXIMUM_OUTSTANDING_BLOCK_REQS \
	(BLKIF_MAX_SEGMENTS_PER_REQUEST * BLK_RING_SIZE)
#define GRANT_INVALID_REF	0

#define PARTS_PER_DISK		16
#define PARTS_PER_EXT_DISK      256

#define BLKIF_MAJOR(dev) ((dev)>>8)
#define BLKIF_MINOR(dev) ((dev) & 0xff)

#define EXT_SHIFT 28
#define EXTENDED (1<<EXT_SHIFT)
#define VDEV_IS_EXTENDED(dev) ((dev)&(EXTENDED))
#define BLKIF_MINOR_EXT(dev) ((dev)&(~EXTENDED))

#define DEV_NAME	"xvd"	/* name in /dev */

static int get_id_from_freelist(struct blkfront_info *info)
{
	unsigned long free = info->shadow_free;
	BUG_ON(free >= BLK_RING_SIZE);
	info->shadow_free = info->shadow[free].req.id;
	info->shadow[free].req.id = 0x0fffffee; /* debug */
	return free;
}

static void add_id_to_freelist(struct blkfront_info *info,
			       unsigned long id)
{
	info->shadow[id].req.id  = info->shadow_free;
	info->shadow[id].request = NULL;
	info->shadow_free = id;
}

static int xlbd_reserve_minors(unsigned int minor, unsigned int nr)
{
	unsigned int end = minor + nr;
	int rc;

	if (end > nr_minors) {
		unsigned long *bitmap, *old;

		bitmap = kzalloc(BITS_TO_LONGS(end) * sizeof(*bitmap),
				 GFP_KERNEL);
		if (bitmap == NULL)
			return -ENOMEM;

		spin_lock(&minor_lock);
		if (end > nr_minors) {
			old = minors;
			memcpy(bitmap, minors,
			       BITS_TO_LONGS(nr_minors) * sizeof(*bitmap));
			minors = bitmap;
			nr_minors = BITS_TO_LONGS(end) * BITS_PER_LONG;
		} else
			old = bitmap;
		spin_unlock(&minor_lock);
		kfree(old);
	}

	spin_lock(&minor_lock);
	if (find_next_bit(minors, end, minor) >= end) {
		for (; minor < end; ++minor)
			__set_bit(minor, minors);
		rc = 0;
	} else
		rc = -EBUSY;
	spin_unlock(&minor_lock);

	return rc;
}

static void xlbd_release_minors(unsigned int minor, unsigned int nr)
{
	unsigned int end = minor + nr;

	BUG_ON(end > nr_minors);
	spin_lock(&minor_lock);
	for (; minor < end; ++minor)
		__clear_bit(minor, minors);
	spin_unlock(&minor_lock);
}

static void blkif_restart_queue_callback(void *arg)
{
	struct blkfront_info *info = (struct blkfront_info *)arg;
	schedule_work(&info->work);
}

static int blkif_getgeo(struct block_device *bd, struct hd_geometry *hg)
{
	/* We don't have real geometry info, but let's at least return
	   values consistent with the size of the device */
	sector_t nsect = get_capacity(bd->bd_disk);
	sector_t cylinders = nsect;

	hg->heads = 0xff;
	hg->sectors = 0x3f;
	sector_div(cylinders, hg->heads * hg->sectors);
	hg->cylinders = cylinders;
	if ((sector_t)(hg->cylinders + 1) * hg->heads * hg->sectors < nsect)
		hg->cylinders = 0xffff;
	return 0;
}

static int blkif_ioctl(struct block_device *bdev, fmode_t mode,
		       unsigned command, unsigned long argument)
{
	struct blkfront_info *info = bdev->bd_disk->private_data;
	int i;

	dev_dbg(&info->xbdev->dev, "command: 0x%x, argument: 0x%lx\n",
		command, (long)argument);

	switch (command) {
	case CDROMMULTISESSION:
		dev_dbg(&info->xbdev->dev, "FIXME: support multisession CDs later\n");
		for (i = 0; i < sizeof(struct cdrom_multisession); i++)
			if (put_user(0, (char __user *)(argument + i)))
				return -EFAULT;
		return 0;

	case CDROM_GET_CAPABILITY: {
		struct gendisk *gd = info->gd;
		if (gd->flags & GENHD_FL_CD)
			return 0;
		return -EINVAL;
	}

	default:
		/*printk(KERN_ALERT "ioctl %08x not supported by Xen blkdev\n",
		  command);*/
		return -EINVAL; /* same return as native Linux */
	}

	return 0;
}

/*
 * Generate a Xen blkfront IO request from a blk layer request.  Reads
 * and writes are handled as expected.  Since we lack a loose flush
 * request, we map flushes into a full ordered barrier.
 *
 * @req: a request struct
 */
static int blkif_queue_request(struct request *req)
{
	struct blkfront_info *info = req->rq_disk->private_data;
	unsigned long buffer_mfn;
	struct blkif_request *ring_req;
	unsigned long id;
	unsigned int fsect, lsect;
	int i, ref;
	grant_ref_t gref_head;
	struct scatterlist *sg;

	if (unlikely(info->connected != BLKIF_STATE_CONNECTED))
		return 1;

	if (gnttab_alloc_grant_references(
		BLKIF_MAX_SEGMENTS_PER_REQUEST, &gref_head) < 0) {
		gnttab_request_free_callback(
			&info->callback,
			blkif_restart_queue_callback,
			info,
			BLKIF_MAX_SEGMENTS_PER_REQUEST);
		return 1;
	}

	/* Fill out a communications ring structure. */
	ring_req = RING_GET_REQUEST(&info->ring, info->ring.req_prod_pvt);
	id = get_id_from_freelist(info);
	info->shadow[id].request = req;

	ring_req->id = id;
	ring_req->sector_number = (blkif_sector_t)blk_rq_pos(req);
	ring_req->handle = info->handle;

	ring_req->operation = rq_data_dir(req) ?
		BLKIF_OP_WRITE : BLKIF_OP_READ;

	if (req->cmd_flags & (REQ_FLUSH | REQ_FUA)) {
		/*
		 * Ideally we could just do an unordered
		 * flush-to-disk, but all we have is a full write
		 * barrier at the moment.  However, a barrier write is
		 * a superset of FUA, so we can implement it the same
		 * way.  (It's also a FLUSH+FUA, since it is
		 * guaranteed ordered WRT previous writes.)
		 */
		ring_req->operation = BLKIF_OP_WRITE_BARRIER;
	}

	ring_req->nr_segments = blk_rq_map_sg(req->q, req, info->sg);
	BUG_ON(ring_req->nr_segments > BLKIF_MAX_SEGMENTS_PER_REQUEST);

	for_each_sg(info->sg, sg, ring_req->nr_segments, i) {
		buffer_mfn = pfn_to_mfn(page_to_pfn(sg_page(sg)));
		fsect = sg->offset >> 9;
		lsect = fsect + (sg->length >> 9) - 1;
		/* install a grant reference. */
		ref = gnttab_claim_grant_reference(&gref_head);
		BUG_ON(ref == -ENOSPC);

		gnttab_grant_foreign_access_ref(
				ref,
				info->xbdev->otherend_id,
				buffer_mfn,
				rq_data_dir(req) );

		info->shadow[id].frame[i] = mfn_to_pfn(buffer_mfn);
		ring_req->seg[i] =
				(struct blkif_request_segment) {
					.gref       = ref,
					.first_sect = fsect,
					.last_sect  = lsect };
	}

	info->ring.req_prod_pvt++;

	/* Keep a private copy so we can reissue requests when recovering. */
	info->shadow[id].req = *ring_req;

	gnttab_free_grant_references(gref_head);

	return 0;
}


static inline void flush_requests(struct blkfront_info *info)
{
	int notify;

	RING_PUSH_REQUESTS_AND_CHECK_NOTIFY(&info->ring, notify);

	if (notify)
		notify_remote_via_irq(info->irq);
}

/*
 * do_blkif_request
 *  read a block; request is in a request queue
 */
static void do_blkif_request(struct request_queue *rq)
{
	struct blkfront_info *info = NULL;
	struct request *req;
	int queued;

	pr_debug("Entered do_blkif_request\n");

	queued = 0;

	while ((req = blk_peek_request(rq)) != NULL) {
		info = req->rq_disk->private_data;

		if (RING_FULL(&info->ring))
			goto wait;

		blk_start_request(req);

		if (req->cmd_type != REQ_TYPE_FS) {
			__blk_end_request_all(req, -EIO);
			continue;
		}

		pr_debug("do_blk_req %p: cmd %p, sec %lx, "
			 "(%u/%u) buffer:%p [%s]\n",
			 req, req->cmd, (unsigned long)blk_rq_pos(req),
			 blk_rq_cur_sectors(req), blk_rq_sectors(req),
			 req->buffer, rq_data_dir(req) ? "write" : "read");

		if (blkif_queue_request(req)) {
			blk_requeue_request(rq, req);
wait:
			/* Avoid pointless unplugs. */
			blk_stop_queue(rq);
			break;
		}

		queued++;
	}

	if (queued != 0)
		flush_requests(info);
}

static int xlvbd_init_blk_queue(struct gendisk *gd, u16 sector_size)
{
	struct request_queue *rq;

	rq = blk_init_queue(do_blkif_request, &blkif_io_lock);
	if (rq == NULL)
		return -1;

	queue_flag_set_unlocked(QUEUE_FLAG_VIRT, rq);

	/* Hard sector size and max sectors impersonate the equiv. hardware. */
	blk_queue_logical_block_size(rq, sector_size);
	blk_queue_max_hw_sectors(rq, 512);

	/* Each segment in a request is up to an aligned page in size. */
	blk_queue_segment_boundary(rq, PAGE_SIZE - 1);
	blk_queue_max_segment_size(rq, PAGE_SIZE);

	/* Ensure a merged request will fit in a single I/O ring slot. */
	blk_queue_max_segments(rq, BLKIF_MAX_SEGMENTS_PER_REQUEST);

	/* Make sure buffer addresses are sector-aligned. */
	blk_queue_dma_alignment(rq, 511);

	/* Make sure we don't use bounce buffers. */
	blk_queue_bounce_limit(rq, BLK_BOUNCE_ANY);

	gd->queue = rq;

	return 0;
}


static void xlvbd_flush(struct blkfront_info *info)
{
	blk_queue_flush(info->rq, info->feature_flush);
	printk(KERN_INFO "blkfront: %s: barriers %s\n",
	       info->gd->disk_name,
	       info->feature_flush ? "enabled" : "disabled");
}


static int xlvbd_alloc_gendisk(blkif_sector_t capacity,
			       struct blkfront_info *info,
			       u16 vdisk_info, u16 sector_size)
{
	struct gendisk *gd;
	int nr_minors = 1;
	int err = -ENODEV;
	unsigned int offset;
	int minor;
	int nr_parts;

	BUG_ON(info->gd != NULL);
	BUG_ON(info->rq != NULL);

	if ((info->vdevice>>EXT_SHIFT) > 1) {
		/* this is above the extended range; something is wrong */
		printk(KERN_WARNING "blkfront: vdevice 0x%x is above the extended range; ignoring\n", info->vdevice);
		return -ENODEV;
	}

	if (!VDEV_IS_EXTENDED(info->vdevice)) {
		minor = BLKIF_MINOR(info->vdevice);
		nr_parts = PARTS_PER_DISK;
	} else {
		minor = BLKIF_MINOR_EXT(info->vdevice);
		nr_parts = PARTS_PER_EXT_DISK;
	}

	if ((minor % nr_parts) == 0)
		nr_minors = nr_parts;

	err = xlbd_reserve_minors(minor, nr_minors);
	if (err)
		goto out;
	err = -ENODEV;

	gd = alloc_disk(nr_minors);
	if (gd == NULL)
		goto release;

	offset = minor / nr_parts;

	if (nr_minors > 1) {
		if (offset < 26)
			sprintf(gd->disk_name, "%s%c", DEV_NAME, 'a' + offset);
		else
			sprintf(gd->disk_name, "%s%c%c", DEV_NAME,
				'a' + ((offset / 26)-1), 'a' + (offset % 26));
	} else {
		if (offset < 26)
			sprintf(gd->disk_name, "%s%c%d", DEV_NAME,
				'a' + offset,
				minor & (nr_parts - 1));
		else
			sprintf(gd->disk_name, "%s%c%c%d", DEV_NAME,
				'a' + ((offset / 26) - 1),
				'a' + (offset % 26),
				minor & (nr_parts - 1));
	}

	gd->major = XENVBD_MAJOR;
	gd->first_minor = minor;
	gd->fops = &xlvbd_block_fops;
	gd->private_data = info;
	gd->driverfs_dev = &(info->xbdev->dev);
	set_capacity(gd, capacity);

	if (xlvbd_init_blk_queue(gd, sector_size)) {
		del_gendisk(gd);
		goto release;
	}

	info->rq = gd->queue;
	info->gd = gd;

	xlvbd_flush(info);

	if (vdisk_info & VDISK_READONLY)
		set_disk_ro(gd, 1);

	if (vdisk_info & VDISK_REMOVABLE)
		gd->flags |= GENHD_FL_REMOVABLE;

	if (vdisk_info & VDISK_CDROM)
		gd->flags |= GENHD_FL_CD;

	return 0;

 release:
	xlbd_release_minors(minor, nr_minors);
 out:
	return err;
}

static void xlvbd_release_gendisk(struct blkfront_info *info)
{
	unsigned int minor, nr_minors;
	unsigned long flags;

	if (info->rq == NULL)
		return;

	spin_lock_irqsave(&blkif_io_lock, flags);

	/* No more blkif_request(). */
	blk_stop_queue(info->rq);

	/* No more gnttab callback work. */
	gnttab_cancel_free_callback(&info->callback);
	spin_unlock_irqrestore(&blkif_io_lock, flags);

	/* Flush gnttab callback work. Must be done with no locks held. */
	flush_work_sync(&info->work);

	del_gendisk(info->gd);

	minor = info->gd->first_minor;
	nr_minors = info->gd->minors;
	xlbd_release_minors(minor, nr_minors);

	blk_cleanup_queue(info->rq);
	info->rq = NULL;

	put_disk(info->gd);
	info->gd = NULL;
}

static void kick_pending_request_queues(struct blkfront_info *info)
{
	if (!RING_FULL(&info->ring)) {
		/* Re-enable calldowns. */
		blk_start_queue(info->rq);
		/* Kick things off immediately. */
		do_blkif_request(info->rq);
	}
}

static void blkif_restart_queue(struct work_struct *work)
{
	struct blkfront_info *info = container_of(work, struct blkfront_info, work);

	spin_lock_irq(&blkif_io_lock);
	if (info->connected == BLKIF_STATE_CONNECTED)
		kick_pending_request_queues(info);
	spin_unlock_irq(&blkif_io_lock);
}

static void blkif_free(struct blkfront_info *info, int suspend)
{
	/* Prevent new requests being issued until we fix things up. */
	spin_lock_irq(&blkif_io_lock);
	info->connected = suspend ?
		BLKIF_STATE_SUSPENDED : BLKIF_STATE_DISCONNECTED;
	/* No more blkif_request(). */
	if (info->rq)
		blk_stop_queue(info->rq);
	/* No more gnttab callback work. */
	gnttab_cancel_free_callback(&info->callback);
	spin_unlock_irq(&blkif_io_lock);

	/* Flush gnttab callback work. Must be done with no locks held. */
	flush_work_sync(&info->work);

	/* Free resources associated with old device channel. */
	if (info->ring_ref != GRANT_INVALID_REF) {
		gnttab_end_foreign_access(info->ring_ref, 0,
					  (unsigned long)info->ring.sring);
		info->ring_ref = GRANT_INVALID_REF;
		info->ring.sring = NULL;
	}
	if (info->irq)
		unbind_from_irqhandler(info->irq, info);
	info->evtchn = info->irq = 0;

}

static void blkif_completion(struct blk_shadow *s)
{
	int i;
	for (i = 0; i < s->req.nr_segments; i++)
		gnttab_end_foreign_access(s->req.seg[i].gref, 0, 0UL);
}

static irqreturn_t blkif_interrupt(int irq, void *dev_id)
{
	struct request *req;
	struct blkif_response *bret;
	RING_IDX i, rp;
	unsigned long flags;
	struct blkfront_info *info = (struct blkfront_info *)dev_id;
	int error;

	spin_lock_irqsave(&blkif_io_lock, flags);

	if (unlikely(info->connected != BLKIF_STATE_CONNECTED)) {
		spin_unlock_irqrestore(&blkif_io_lock, flags);
		return IRQ_HANDLED;
	}

 again:
	rp = info->ring.sring->rsp_prod;
	rmb(); /* Ensure we see queued responses up to 'rp'. */

	for (i = info->ring.rsp_cons; i != rp; i++) {
		unsigned long id;

		bret = RING_GET_RESPONSE(&info->ring, i);
		id   = bret->id;
		req  = info->shadow[id].request;

		blkif_completion(&info->shadow[id]);

		add_id_to_freelist(info, id);

		error = (bret->status == BLKIF_RSP_OKAY) ? 0 : -EIO;
		switch (bret->operation) {
		case BLKIF_OP_WRITE_BARRIER:
			if (unlikely(bret->status == BLKIF_RSP_EOPNOTSUPP)) {
				printk(KERN_WARNING "blkfront: %s: write barrier op failed\n",
				       info->gd->disk_name);
				error = -EOPNOTSUPP;
			}
			if (unlikely(bret->status == BLKIF_RSP_ERROR &&
				     info->shadow[id].req.nr_segments == 0)) {
				printk(KERN_WARNING "blkfront: %s: empty write barrier op failed\n",
				       info->gd->disk_name);
				error = -EOPNOTSUPP;
			}
			if (unlikely(error)) {
				if (error == -EOPNOTSUPP)
					error = 0;
				info->feature_flush = 0;
				xlvbd_flush(info);
			}
			/* fall through */
		case BLKIF_OP_READ:
		case BLKIF_OP_WRITE:
			if (unlikely(bret->status != BLKIF_RSP_OKAY))
				dev_dbg(&info->xbdev->dev, "Bad return from blkdev data "
					"request: %x\n", bret->status);

			__blk_end_request_all(req, error);
			break;
		default:
			BUG();
		}
	}

	info->ring.rsp_cons = i;

	if (i != info->ring.req_prod_pvt) {
		int more_to_do;
		RING_FINAL_CHECK_FOR_RESPONSES(&info->ring, more_to_do);
		if (more_to_do)
			goto again;
	} else
		info->ring.sring->rsp_event = i + 1;

	kick_pending_request_queues(info);

	spin_unlock_irqrestore(&blkif_io_lock, flags);

	return IRQ_HANDLED;
}


static int setup_blkring(struct xenbus_device *dev,
			 struct blkfront_info *info)
{
	struct blkif_sring *sring;
	int err;

	info->ring_ref = GRANT_INVALID_REF;

	sring = (struct blkif_sring *)__get_free_page(GFP_NOIO | __GFP_HIGH);
	if (!sring) {
		xenbus_dev_fatal(dev, -ENOMEM, "allocating shared ring");
		return -ENOMEM;
	}
	SHARED_RING_INIT(sring);
	FRONT_RING_INIT(&info->ring, sring, PAGE_SIZE);

	sg_init_table(info->sg, BLKIF_MAX_SEGMENTS_PER_REQUEST);

	err = xenbus_grant_ring(dev, virt_to_mfn(info->ring.sring));
	if (err < 0) {
		free_page((unsigned long)sring);
		info->ring.sring = NULL;
		goto fail;
	}
	info->ring_ref = err;

	err = xenbus_alloc_evtchn(dev, &info->evtchn);
	if (err)
		goto fail;

	err = bind_evtchn_to_irqhandler(info->evtchn,
					blkif_interrupt,
					IRQF_SAMPLE_RANDOM, "blkif", info);
	if (err <= 0) {
		xenbus_dev_fatal(dev, err,
				 "bind_evtchn_to_irqhandler failed");
		goto fail;
	}
	info->irq = err;

	return 0;
fail:
	blkif_free(info, 0);
	return err;
}


/* Common code used when first setting up, and when resuming. */
static int talk_to_blkback(struct xenbus_device *dev,
			   struct blkfront_info *info)
{
	const char *message = NULL;
	struct xenbus_transaction xbt;
	int err;

	/* Create shared ring, alloc event channel. */
	err = setup_blkring(dev, info);
	if (err)
		goto out;

again:
	err = xenbus_transaction_start(&xbt);
	if (err) {
		xenbus_dev_fatal(dev, err, "starting transaction");
		goto destroy_blkring;
	}

	err = xenbus_printf(xbt, dev->nodename,
			    "ring-ref", "%u", info->ring_ref);
	if (err) {
		message = "writing ring-ref";
		goto abort_transaction;
	}
	err = xenbus_printf(xbt, dev->nodename,
			    "event-channel", "%u", info->evtchn);
	if (err) {
		message = "writing event-channel";
		goto abort_transaction;
	}
	err = xenbus_printf(xbt, dev->nodename, "protocol", "%s",
			    XEN_IO_PROTO_ABI_NATIVE);
	if (err) {
		message = "writing protocol";
		goto abort_transaction;
	}

	err = xenbus_transaction_end(xbt, 0);
	if (err) {
		if (err == -EAGAIN)
			goto again;
		xenbus_dev_fatal(dev, err, "completing transaction");
		goto destroy_blkring;
	}

	xenbus_switch_state(dev, XenbusStateInitialised);

	return 0;

 abort_transaction:
	xenbus_transaction_end(xbt, 1);
	if (message)
		xenbus_dev_fatal(dev, err, "%s", message);
 destroy_blkring:
	blkif_free(info, 0);
 out:
	return err;
}

/**
 * Entry point to this code when a new device is created.  Allocate the basic
 * structures and the ring buffer for communication with the backend, and
 * inform the backend of the appropriate details for those.  Switch to
 * Initialised state.
 */
static int blkfront_probe(struct xenbus_device *dev,
			  const struct xenbus_device_id *id)
{
	int err, vdevice, i;
	struct blkfront_info *info;

	/* FIXME: Use dynamic device id if this is not set. */
	err = xenbus_scanf(XBT_NIL, dev->nodename,
			   "virtual-device", "%i", &vdevice);
	if (err != 1) {
		/* go looking in the extended area instead */
		err = xenbus_scanf(XBT_NIL, dev->nodename, "virtual-device-ext",
				   "%i", &vdevice);
		if (err != 1) {
			xenbus_dev_fatal(dev, err, "reading virtual-device");
			return err;
		}
	}

	if (xen_hvm_domain()) {
		char *type;
		int len;
		/* no unplug has been done: do not hook devices != xen vbds */
		if (xen_platform_pci_unplug & XEN_UNPLUG_UNNECESSARY) {
			int major;

			if (!VDEV_IS_EXTENDED(vdevice))
				major = BLKIF_MAJOR(vdevice);
			else
				major = XENVBD_MAJOR;

			if (major != XENVBD_MAJOR) {
				printk(KERN_INFO
						"%s: HVM does not support vbd %d as xen block device\n",
						__FUNCTION__, vdevice);
				return -ENODEV;
			}
		}
		/* do not create a PV cdrom device if we are an HVM guest */
		type = xenbus_read(XBT_NIL, dev->nodename, "device-type", &len);
		if (IS_ERR(type))
			return -ENODEV;
		if (strncmp(type, "cdrom", 5) == 0) {
			kfree(type);
			return -ENODEV;
		}
		kfree(type);
	}
	info = kzalloc(sizeof(*info), GFP_KERNEL);
	if (!info) {
		xenbus_dev_fatal(dev, -ENOMEM, "allocating info structure");
		return -ENOMEM;
	}

	mutex_init(&info->mutex);
	info->xbdev = dev;
	info->vdevice = vdevice;
	info->connected = BLKIF_STATE_DISCONNECTED;
	INIT_WORK(&info->work, blkif_restart_queue);

	for (i = 0; i < BLK_RING_SIZE; i++)
		info->shadow[i].req.id = i+1;
	info->shadow[BLK_RING_SIZE-1].req.id = 0x0fffffff;

	/* Front end dir is a number, which is used as the id. */
	info->handle = simple_strtoul(strrchr(dev->nodename, '/')+1, NULL, 0);
	dev_set_drvdata(&dev->dev, info);

	err = talk_to_blkback(dev, info);
	if (err) {
		kfree(info);
		dev_set_drvdata(&dev->dev, NULL);
		return err;
	}

	return 0;
}


static int blkif_recover(struct blkfront_info *info)
{
	int i;
	struct blkif_request *req;
	struct blk_shadow *copy;
	int j;

	/* Stage 1: Make a safe copy of the shadow state. */
	copy = kmalloc(sizeof(info->shadow),
		       GFP_NOIO | __GFP_REPEAT | __GFP_HIGH);
	if (!copy)
		return -ENOMEM;
	memcpy(copy, info->shadow, sizeof(info->shadow));

	/* Stage 2: Set up free list. */
	memset(&info->shadow, 0, sizeof(info->shadow));
	for (i = 0; i < BLK_RING_SIZE; i++)
		info->shadow[i].req.id = i+1;
	info->shadow_free = info->ring.req_prod_pvt;
	info->shadow[BLK_RING_SIZE-1].req.id = 0x0fffffff;

	/* Stage 3: Find pending requests and requeue them. */
	for (i = 0; i < BLK_RING_SIZE; i++) {
		/* Not in use? */
		if (!copy[i].request)
			continue;

		/* Grab a request slot and copy shadow state into it. */
		req = RING_GET_REQUEST(&info->ring, info->ring.req_prod_pvt);
		*req = copy[i].req;

		/* We get a new request id, and must reset the shadow state. */
		req->id = get_id_from_freelist(info);
		memcpy(&info->shadow[req->id], &copy[i], sizeof(copy[i]));

		/* Rewrite any grant references invalidated by susp/resume. */
		for (j = 0; j < req->nr_segments; j++)
			gnttab_grant_foreign_access_ref(
				req->seg[j].gref,
				info->xbdev->otherend_id,
				pfn_to_mfn(info->shadow[req->id].frame[j]),
				rq_data_dir(info->shadow[req->id].request));
		info->shadow[req->id].req = *req;

		info->ring.req_prod_pvt++;
	}

	kfree(copy);

	xenbus_switch_state(info->xbdev, XenbusStateConnected);

	spin_lock_irq(&blkif_io_lock);

	/* Now safe for us to use the shared ring */
	info->connected = BLKIF_STATE_CONNECTED;

	/* Send off requeued requests */
	flush_requests(info);

	/* Kick any other new requests queued since we resumed */
	kick_pending_request_queues(info);

	spin_unlock_irq(&blkif_io_lock);

	return 0;
}

/**
 * We are reconnecting to the backend, due to a suspend/resume, or a backend
 * driver restart.  We tear down our blkif structure and recreate it, but
 * leave the device-layer structures intact so that this is transparent to the
 * rest of the kernel.
 */
static int blkfront_resume(struct xenbus_device *dev)
{
	struct blkfront_info *info = dev_get_drvdata(&dev->dev);
	int err;

	dev_dbg(&dev->dev, "blkfront_resume: %s\n", dev->nodename);

	blkif_free(info, info->connected == BLKIF_STATE_CONNECTED);

	err = talk_to_blkback(dev, info);
	if (info->connected == BLKIF_STATE_SUSPENDED && !err)
		err = blkif_recover(info);

	return err;
}

static void
blkfront_closing(struct blkfront_info *info)
{
	struct xenbus_device *xbdev = info->xbdev;
	struct block_device *bdev = NULL;

	mutex_lock(&info->mutex);

	if (xbdev->state == XenbusStateClosing) {
		mutex_unlock(&info->mutex);
		return;
	}

	if (info->gd)
		bdev = bdget_disk(info->gd, 0);

	mutex_unlock(&info->mutex);

	if (!bdev) {
		xenbus_frontend_closed(xbdev);
		return;
	}

	mutex_lock(&bdev->bd_mutex);

	if (bdev->bd_openers) {
		xenbus_dev_error(xbdev, -EBUSY,
				 "Device in use; refusing to close");
		xenbus_switch_state(xbdev, XenbusStateClosing);
	} else {
		xlvbd_release_gendisk(info);
		xenbus_frontend_closed(xbdev);
	}

	mutex_unlock(&bdev->bd_mutex);
	bdput(bdev);
}

/*
 * Invoked when the backend is finally 'ready' (and has told produced
 * the details about the physical device - #sectors, size, etc).
 */
static void blkfront_connect(struct blkfront_info *info)
{
	unsigned long long sectors;
	unsigned long sector_size;
	unsigned int binfo;
	int err;
	int barrier;

	switch (info->connected) {
	case BLKIF_STATE_CONNECTED:
		/*
		 * Potentially, the back-end may be signalling
		 * a capacity change; update the capacity.
		 */
		err = xenbus_scanf(XBT_NIL, info->xbdev->otherend,
				   "sectors", "%Lu", &sectors);
		if (XENBUS_EXIST_ERR(err))
			return;
		printk(KERN_INFO "Setting capacity to %Lu\n",
		       sectors);
		set_capacity(info->gd, sectors);
		revalidate_disk(info->gd);

		/* fall through */
	case BLKIF_STATE_SUSPENDED:
		return;

	default:
		break;
	}

	dev_dbg(&info->xbdev->dev, "%s:%s.\n",
		__func__, info->xbdev->otherend);

	err = xenbus_gather(XBT_NIL, info->xbdev->otherend,
			    "sectors", "%llu", &sectors,
			    "info", "%u", &binfo,
			    "sector-size", "%lu", &sector_size,
			    NULL);
	if (err) {
		xenbus_dev_fatal(info->xbdev, err,
				 "reading backend fields at %s",
				 info->xbdev->otherend);
		return;
	}

	err = xenbus_gather(XBT_NIL, info->xbdev->otherend,
			    "feature-barrier", "%lu", &barrier,
			    NULL);

	/*
	 * If there's no "feature-barrier" defined, then it means
	 * we're dealing with a very old backend which writes
	 * synchronously; nothing to do.
	 *
	 * If there are barriers, then we use flush.
	 */
	info->feature_flush = 0;

	if (!err && barrier)
		info->feature_flush = REQ_FLUSH | REQ_FUA;

	err = xlvbd_alloc_gendisk(sectors, info, binfo, sector_size);
	if (err) {
		xenbus_dev_fatal(info->xbdev, err, "xlvbd_add at %s",
				 info->xbdev->otherend);
		return;
	}

	xenbus_switch_state(info->xbdev, XenbusStateConnected);

	/* Kick pending requests. */
	spin_lock_irq(&blkif_io_lock);
	info->connected = BLKIF_STATE_CONNECTED;
	kick_pending_request_queues(info);
	spin_unlock_irq(&blkif_io_lock);

	add_disk(info->gd);

	info->is_ready = 1;
}

/**
 * Callback received when the backend's state changes.
 */
static void blkback_changed(struct xenbus_device *dev,
			    enum xenbus_state backend_state)
{
	struct blkfront_info *info = dev_get_drvdata(&dev->dev);

	dev_dbg(&dev->dev, "blkfront:blkback_changed to state %d.\n", backend_state);

	switch (backend_state) {
	case XenbusStateInitialising:
	case XenbusStateInitWait:
	case XenbusStateInitialised:
	case XenbusStateReconfiguring:
	case XenbusStateReconfigured:
	case XenbusStateUnknown:
	case XenbusStateClosed:
		break;

	case XenbusStateConnected:
		blkfront_connect(info);
		break;

	case XenbusStateClosing:
		blkfront_closing(info);
		break;
	}
}

static int blkfront_remove(struct xenbus_device *xbdev)
{
	struct blkfront_info *info = dev_get_drvdata(&xbdev->dev);
	struct block_device *bdev = NULL;
	struct gendisk *disk;

	dev_dbg(&xbdev->dev, "%s removed", xbdev->nodename);

	blkif_free(info, 0);

	mutex_lock(&info->mutex);

	disk = info->gd;
	if (disk)
		bdev = bdget_disk(disk, 0);

	info->xbdev = NULL;
	mutex_unlock(&info->mutex);

	if (!bdev) {
		kfree(info);
		return 0;
	}

	/*
	 * The xbdev was removed before we reached the Closed
	 * state. See if it's safe to remove the disk. If the bdev
	 * isn't closed yet, we let release take care of it.
	 */

	mutex_lock(&bdev->bd_mutex);
	info = disk->private_data;

	dev_warn(disk_to_dev(disk),
		 "%s was hot-unplugged, %d stale handles\n",
		 xbdev->nodename, bdev->bd_openers);

	if (info && !bdev->bd_openers) {
		xlvbd_release_gendisk(info);
		disk->private_data = NULL;
		kfree(info);
	}

	mutex_unlock(&bdev->bd_mutex);
	bdput(bdev);

	return 0;
}

static int blkfront_is_ready(struct xenbus_device *dev)
{
	struct blkfront_info *info = dev_get_drvdata(&dev->dev);

	return info->is_ready && info->xbdev;
}

static int blkif_open(struct block_device *bdev, fmode_t mode)
{
	struct gendisk *disk = bdev->bd_disk;
	struct blkfront_info *info;
	int err = 0;

	mutex_lock(&blkfront_mutex);

	info = disk->private_data;
	if (!info) {
		/* xbdev gone */
		err = -ERESTARTSYS;
		goto out;
	}

	mutex_lock(&info->mutex);

	if (!info->gd)
		/* xbdev is closed */
		err = -ERESTARTSYS;

	mutex_unlock(&info->mutex);

out:
	mutex_unlock(&blkfront_mutex);
	return err;
}

static int blkif_release(struct gendisk *disk, fmode_t mode)
{
	struct blkfront_info *info = disk->private_data;
	struct block_device *bdev;
	struct xenbus_device *xbdev;

	mutex_lock(&blkfront_mutex);

	bdev = bdget_disk(disk, 0);
	bdput(bdev);

	if (bdev->bd_openers)
		goto out;

	/*
	 * Check if we have been instructed to close. We will have
	 * deferred this request, because the bdev was still open.
	 */

	mutex_lock(&info->mutex);
	xbdev = info->xbdev;

	if (xbdev && xbdev->state == XenbusStateClosing) {
		/* pending switch to state closed */
		dev_info(disk_to_dev(bdev->bd_disk), "releasing disk\n");
		xlvbd_release_gendisk(info);
		xenbus_frontend_closed(info->xbdev);
 	}

	mutex_unlock(&info->mutex);

	if (!xbdev) {
		/* sudden device removal */
		dev_info(disk_to_dev(bdev->bd_disk), "releasing disk\n");
		xlvbd_release_gendisk(info);
		disk->private_data = NULL;
		kfree(info);
	}

out:
	mutex_unlock(&blkfront_mutex);
	return 0;
}

static const struct block_device_operations xlvbd_block_fops =
{
	.owner = THIS_MODULE,
	.open = blkif_open,
	.release = blkif_release,
	.getgeo = blkif_getgeo,
	.ioctl = blkif_ioctl,
};


static const struct xenbus_device_id blkfront_ids[] = {
	{ "vbd" },
	{ "" }
};

static struct xenbus_driver blkfront = {
	.name = "vbd",
	.owner = THIS_MODULE,
	.ids = blkfront_ids,
	.probe = blkfront_probe,
	.remove = blkfront_remove,
	.resume = blkfront_resume,
	.otherend_changed = blkback_changed,
	.is_ready = blkfront_is_ready,
};

static int __init xlblk_init(void)
{
	if (!xen_domain())
		return -ENODEV;

	if (register_blkdev(XENVBD_MAJOR, DEV_NAME)) {
		printk(KERN_WARNING "xen_blk: can't get major %d with name %s\n",
		       XENVBD_MAJOR, DEV_NAME);
		return -ENODEV;
	}

	return xenbus_register_frontend(&blkfront);
}
module_init(xlblk_init);


static void __exit xlblk_exit(void)
{
	return xenbus_unregister_driver(&blkfront);
}
module_exit(xlblk_exit);

MODULE_DESCRIPTION("Xen virtual block device frontend");
MODULE_LICENSE("GPL");
MODULE_ALIAS_BLOCKDEV_MAJOR(XENVBD_MAJOR);
MODULE_ALIAS("xen:vbd");
MODULE_ALIAS("xenblk");