summaryrefslogtreecommitdiff
path: root/drivers/virtio/virtio_balloon.c
blob: f19061b585a4f73a1fbecd1876592db4a6a39fee (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
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
/*
 * Virtio balloon implementation, inspired by Dor Laor and Marcelo
 * Tosatti's implementations.
 *
 *  Copyright 2008 Rusty Russell IBM Corporation
 *
 *  This program is free software; you can redistribute it and/or modify
 *  it under the terms of the GNU General Public License as published by
 *  the Free Software Foundation; either version 2 of the License, or
 *  (at your option) any later version.
 *
 *  This program is distributed in the hope that it will be useful,
 *  but WITHOUT ANY WARRANTY; without even the implied warranty of
 *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 *  GNU General Public License for more details.
 *
 *  You should have received a copy of the GNU General Public License
 *  along with this program; if not, write to the Free Software
 *  Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
 */

#include <linux/virtio.h>
#include <linux/virtio_balloon.h>
#include <linux/swap.h>
#include <linux/workqueue.h>
#include <linux/delay.h>
#include <linux/slab.h>
#include <linux/module.h>
#include <linux/balloon_compaction.h>
#include <linux/wait.h>
#include <linux/mm.h>
#include <linux/mount.h>
#include <linux/magic.h>

/*
 * Balloon device works in 4K page units.  So each page is pointed to by
 * multiple balloon pages.  All memory counters in this driver are in balloon
 * page units.
 */
#define VIRTIO_BALLOON_PAGES_PER_PAGE (unsigned)(PAGE_SIZE >> VIRTIO_BALLOON_PFN_SHIFT)
#define VIRTIO_BALLOON_ARRAY_PFNS_MAX 256
#define VIRTBALLOON_OOM_NOTIFY_PRIORITY 80

#define VIRTIO_BALLOON_FREE_PAGE_ALLOC_FLAG (__GFP_NORETRY | __GFP_NOWARN | \
					     __GFP_NOMEMALLOC)
/* The order of free page blocks to report to host */
#define VIRTIO_BALLOON_FREE_PAGE_ORDER (MAX_ORDER - 1)
/* The size of a free page block in bytes */
#define VIRTIO_BALLOON_FREE_PAGE_SIZE \
	(1 << (VIRTIO_BALLOON_FREE_PAGE_ORDER + PAGE_SHIFT))

#ifdef CONFIG_BALLOON_COMPACTION
static struct vfsmount *balloon_mnt;
#endif

enum virtio_balloon_vq {
	VIRTIO_BALLOON_VQ_INFLATE,
	VIRTIO_BALLOON_VQ_DEFLATE,
	VIRTIO_BALLOON_VQ_STATS,
	VIRTIO_BALLOON_VQ_FREE_PAGE,
	VIRTIO_BALLOON_VQ_MAX
};

enum virtio_balloon_config_read {
	VIRTIO_BALLOON_CONFIG_READ_CMD_ID = 0,
};

struct virtio_balloon {
	struct virtio_device *vdev;
	struct virtqueue *inflate_vq, *deflate_vq, *stats_vq, *free_page_vq;

	/* Balloon's own wq for cpu-intensive work items */
	struct workqueue_struct *balloon_wq;
	/* The free page reporting work item submitted to the balloon wq */
	struct work_struct report_free_page_work;

	/* The balloon servicing is delegated to a freezable workqueue. */
	struct work_struct update_balloon_stats_work;
	struct work_struct update_balloon_size_work;

	/* Prevent updating balloon when it is being canceled. */
	spinlock_t stop_update_lock;
	bool stop_update;
	/* Bitmap to indicate if reading the related config fields are needed */
	unsigned long config_read_bitmap;

	/* The list of allocated free pages, waiting to be given back to mm */
	struct list_head free_page_list;
	spinlock_t free_page_list_lock;
	/* The number of free page blocks on the above list */
	unsigned long num_free_page_blocks;
	/*
	 * The cmd id received from host.
	 * Read it via virtio_balloon_cmd_id_received to get the latest value
	 * sent from host.
	 */
	u32 cmd_id_received_cache;
	/* The cmd id that is actively in use */
	__virtio32 cmd_id_active;
	/* Buffer to store the stop sign */
	__virtio32 cmd_id_stop;

	/* Waiting for host to ack the pages we released. */
	wait_queue_head_t acked;

	/* Number of balloon pages we've told the Host we're not using. */
	unsigned int num_pages;
	/*
	 * The pages we've told the Host we're not using are enqueued
	 * at vb_dev_info->pages list.
	 * Each page on this list adds VIRTIO_BALLOON_PAGES_PER_PAGE
	 * to num_pages above.
	 */
	struct balloon_dev_info vb_dev_info;

	/* Synchronize access/update to this struct virtio_balloon elements */
	struct mutex balloon_lock;

	/* The array of pfns we tell the Host about. */
	unsigned int num_pfns;
	__virtio32 pfns[VIRTIO_BALLOON_ARRAY_PFNS_MAX];

	/* Memory statistics */
	struct virtio_balloon_stat stats[VIRTIO_BALLOON_S_NR];

	/* To register a shrinker to shrink memory upon memory pressure */
	struct shrinker shrinker;
};

static struct virtio_device_id id_table[] = {
	{ VIRTIO_ID_BALLOON, VIRTIO_DEV_ANY_ID },
	{ 0 },
};

static u32 page_to_balloon_pfn(struct page *page)
{
	unsigned long pfn = page_to_pfn(page);

	BUILD_BUG_ON(PAGE_SHIFT < VIRTIO_BALLOON_PFN_SHIFT);
	/* Convert pfn from Linux page size to balloon page size. */
	return pfn * VIRTIO_BALLOON_PAGES_PER_PAGE;
}

static void balloon_ack(struct virtqueue *vq)
{
	struct virtio_balloon *vb = vq->vdev->priv;

	wake_up(&vb->acked);
}

static void tell_host(struct virtio_balloon *vb, struct virtqueue *vq)
{
	struct scatterlist sg;
	unsigned int len;

	sg_init_one(&sg, vb->pfns, sizeof(vb->pfns[0]) * vb->num_pfns);

	/* We should always be able to add one buffer to an empty queue. */
	virtqueue_add_outbuf(vq, &sg, 1, vb, GFP_KERNEL);
	virtqueue_kick(vq);

	/* When host has read buffer, this completes via balloon_ack */
	wait_event(vb->acked, virtqueue_get_buf(vq, &len));

}

static void set_page_pfns(struct virtio_balloon *vb,
			  __virtio32 pfns[], struct page *page)
{
	unsigned int i;

	/*
	 * Set balloon pfns pointing at this page.
	 * Note that the first pfn points at start of the page.
	 */
	for (i = 0; i < VIRTIO_BALLOON_PAGES_PER_PAGE; i++)
		pfns[i] = cpu_to_virtio32(vb->vdev,
					  page_to_balloon_pfn(page) + i);
}

static unsigned fill_balloon(struct virtio_balloon *vb, size_t num)
{
	unsigned num_allocated_pages;
	unsigned num_pfns;
	struct page *page;
	LIST_HEAD(pages);

	/* We can only do one array worth at a time. */
	num = min(num, ARRAY_SIZE(vb->pfns));

	for (num_pfns = 0; num_pfns < num;
	     num_pfns += VIRTIO_BALLOON_PAGES_PER_PAGE) {
		struct page *page = balloon_page_alloc();

		if (!page) {
			dev_info_ratelimited(&vb->vdev->dev,
					     "Out of puff! Can't get %u pages\n",
					     VIRTIO_BALLOON_PAGES_PER_PAGE);
			/* Sleep for at least 1/5 of a second before retry. */
			msleep(200);
			break;
		}

		balloon_page_push(&pages, page);
	}

	mutex_lock(&vb->balloon_lock);

	vb->num_pfns = 0;

	while ((page = balloon_page_pop(&pages))) {
		balloon_page_enqueue(&vb->vb_dev_info, page);

		set_page_pfns(vb, vb->pfns + vb->num_pfns, page);
		vb->num_pages += VIRTIO_BALLOON_PAGES_PER_PAGE;
		if (!virtio_has_feature(vb->vdev,
					VIRTIO_BALLOON_F_DEFLATE_ON_OOM))
			adjust_managed_page_count(page, -1);
		vb->num_pfns += VIRTIO_BALLOON_PAGES_PER_PAGE;
	}

	num_allocated_pages = vb->num_pfns;
	/* Did we get any? */
	if (vb->num_pfns != 0)
		tell_host(vb, vb->inflate_vq);
	mutex_unlock(&vb->balloon_lock);

	return num_allocated_pages;
}

static void release_pages_balloon(struct virtio_balloon *vb,
				 struct list_head *pages)
{
	struct page *page, *next;

	list_for_each_entry_safe(page, next, pages, lru) {
		if (!virtio_has_feature(vb->vdev,
					VIRTIO_BALLOON_F_DEFLATE_ON_OOM))
			adjust_managed_page_count(page, 1);
		list_del(&page->lru);
		put_page(page); /* balloon reference */
	}
}

static unsigned leak_balloon(struct virtio_balloon *vb, size_t num)
{
	unsigned num_freed_pages;
	struct page *page;
	struct balloon_dev_info *vb_dev_info = &vb->vb_dev_info;
	LIST_HEAD(pages);

	/* We can only do one array worth at a time. */
	num = min(num, ARRAY_SIZE(vb->pfns));

	mutex_lock(&vb->balloon_lock);
	/* We can't release more pages than taken */
	num = min(num, (size_t)vb->num_pages);
	for (vb->num_pfns = 0; vb->num_pfns < num;
	     vb->num_pfns += VIRTIO_BALLOON_PAGES_PER_PAGE) {
		page = balloon_page_dequeue(vb_dev_info);
		if (!page)
			break;
		set_page_pfns(vb, vb->pfns + vb->num_pfns, page);
		list_add(&page->lru, &pages);
		vb->num_pages -= VIRTIO_BALLOON_PAGES_PER_PAGE;
	}

	num_freed_pages = vb->num_pfns;
	/*
	 * Note that if
	 * virtio_has_feature(vdev, VIRTIO_BALLOON_F_MUST_TELL_HOST);
	 * is true, we *have* to do it in this order
	 */
	if (vb->num_pfns != 0)
		tell_host(vb, vb->deflate_vq);
	release_pages_balloon(vb, &pages);
	mutex_unlock(&vb->balloon_lock);
	return num_freed_pages;
}

static inline void update_stat(struct virtio_balloon *vb, int idx,
			       u16 tag, u64 val)
{
	BUG_ON(idx >= VIRTIO_BALLOON_S_NR);
	vb->stats[idx].tag = cpu_to_virtio16(vb->vdev, tag);
	vb->stats[idx].val = cpu_to_virtio64(vb->vdev, val);
}

#define pages_to_bytes(x) ((u64)(x) << PAGE_SHIFT)

static unsigned int update_balloon_stats(struct virtio_balloon *vb)
{
	unsigned long events[NR_VM_EVENT_ITEMS];
	struct sysinfo i;
	unsigned int idx = 0;
	long available;
	unsigned long caches;

	all_vm_events(events);
	si_meminfo(&i);

	available = si_mem_available();
	caches = global_node_page_state(NR_FILE_PAGES);

#ifdef CONFIG_VM_EVENT_COUNTERS
	update_stat(vb, idx++, VIRTIO_BALLOON_S_SWAP_IN,
				pages_to_bytes(events[PSWPIN]));
	update_stat(vb, idx++, VIRTIO_BALLOON_S_SWAP_OUT,
				pages_to_bytes(events[PSWPOUT]));
	update_stat(vb, idx++, VIRTIO_BALLOON_S_MAJFLT, events[PGMAJFAULT]);
	update_stat(vb, idx++, VIRTIO_BALLOON_S_MINFLT, events[PGFAULT]);
#ifdef CONFIG_HUGETLB_PAGE
	update_stat(vb, idx++, VIRTIO_BALLOON_S_HTLB_PGALLOC,
		    events[HTLB_BUDDY_PGALLOC]);
	update_stat(vb, idx++, VIRTIO_BALLOON_S_HTLB_PGFAIL,
		    events[HTLB_BUDDY_PGALLOC_FAIL]);
#endif
#endif
	update_stat(vb, idx++, VIRTIO_BALLOON_S_MEMFREE,
				pages_to_bytes(i.freeram));
	update_stat(vb, idx++, VIRTIO_BALLOON_S_MEMTOT,
				pages_to_bytes(i.totalram));
	update_stat(vb, idx++, VIRTIO_BALLOON_S_AVAIL,
				pages_to_bytes(available));
	update_stat(vb, idx++, VIRTIO_BALLOON_S_CACHES,
				pages_to_bytes(caches));

	return idx;
}

/*
 * While most virtqueues communicate guest-initiated requests to the hypervisor,
 * the stats queue operates in reverse.  The driver initializes the virtqueue
 * with a single buffer.  From that point forward, all conversations consist of
 * a hypervisor request (a call to this function) which directs us to refill
 * the virtqueue with a fresh stats buffer.  Since stats collection can sleep,
 * we delegate the job to a freezable workqueue that will do the actual work via
 * stats_handle_request().
 */
static void stats_request(struct virtqueue *vq)
{
	struct virtio_balloon *vb = vq->vdev->priv;

	spin_lock(&vb->stop_update_lock);
	if (!vb->stop_update)
		queue_work(system_freezable_wq, &vb->update_balloon_stats_work);
	spin_unlock(&vb->stop_update_lock);
}

static void stats_handle_request(struct virtio_balloon *vb)
{
	struct virtqueue *vq;
	struct scatterlist sg;
	unsigned int len, num_stats;

	num_stats = update_balloon_stats(vb);

	vq = vb->stats_vq;
	if (!virtqueue_get_buf(vq, &len))
		return;
	sg_init_one(&sg, vb->stats, sizeof(vb->stats[0]) * num_stats);
	virtqueue_add_outbuf(vq, &sg, 1, vb, GFP_KERNEL);
	virtqueue_kick(vq);
}

static inline s64 towards_target(struct virtio_balloon *vb)
{
	s64 target;
	u32 num_pages;

	virtio_cread(vb->vdev, struct virtio_balloon_config, num_pages,
		     &num_pages);

	/* Legacy balloon config space is LE, unlike all other devices. */
	if (!virtio_has_feature(vb->vdev, VIRTIO_F_VERSION_1))
		num_pages = le32_to_cpu((__force __le32)num_pages);

	target = num_pages;
	return target - vb->num_pages;
}

/* Gives back @num_to_return blocks of free pages to mm. */
static unsigned long return_free_pages_to_mm(struct virtio_balloon *vb,
					     unsigned long num_to_return)
{
	struct page *page;
	unsigned long num_returned;

	spin_lock_irq(&vb->free_page_list_lock);
	for (num_returned = 0; num_returned < num_to_return; num_returned++) {
		page = balloon_page_pop(&vb->free_page_list);
		if (!page)
			break;
		free_pages((unsigned long)page_address(page),
			   VIRTIO_BALLOON_FREE_PAGE_ORDER);
	}
	vb->num_free_page_blocks -= num_returned;
	spin_unlock_irq(&vb->free_page_list_lock);

	return num_returned;
}

static void virtio_balloon_queue_free_page_work(struct virtio_balloon *vb)
{
	if (!virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_FREE_PAGE_HINT))
		return;

	/* No need to queue the work if the bit was already set. */
	if (test_and_set_bit(VIRTIO_BALLOON_CONFIG_READ_CMD_ID,
			     &vb->config_read_bitmap))
		return;

	queue_work(vb->balloon_wq, &vb->report_free_page_work);
}

static void virtballoon_changed(struct virtio_device *vdev)
{
	struct virtio_balloon *vb = vdev->priv;
	unsigned long flags;

	spin_lock_irqsave(&vb->stop_update_lock, flags);
	if (!vb->stop_update) {
		queue_work(system_freezable_wq,
			   &vb->update_balloon_size_work);
		virtio_balloon_queue_free_page_work(vb);
	}
	spin_unlock_irqrestore(&vb->stop_update_lock, flags);
}

static void update_balloon_size(struct virtio_balloon *vb)
{
	u32 actual = vb->num_pages;

	/* Legacy balloon config space is LE, unlike all other devices. */
	if (!virtio_has_feature(vb->vdev, VIRTIO_F_VERSION_1))
		actual = (__force u32)cpu_to_le32(actual);

	virtio_cwrite(vb->vdev, struct virtio_balloon_config, actual,
		      &actual);
}

static void update_balloon_stats_func(struct work_struct *work)
{
	struct virtio_balloon *vb;

	vb = container_of(work, struct virtio_balloon,
			  update_balloon_stats_work);
	stats_handle_request(vb);
}

static void update_balloon_size_func(struct work_struct *work)
{
	struct virtio_balloon *vb;
	s64 diff;

	vb = container_of(work, struct virtio_balloon,
			  update_balloon_size_work);
	diff = towards_target(vb);

	if (!diff)
		return;

	if (diff > 0)
		diff -= fill_balloon(vb, diff);
	else
		diff += leak_balloon(vb, -diff);
	update_balloon_size(vb);

	if (diff)
		queue_work(system_freezable_wq, work);
}

static int init_vqs(struct virtio_balloon *vb)
{
	struct virtqueue *vqs[VIRTIO_BALLOON_VQ_MAX];
	vq_callback_t *callbacks[VIRTIO_BALLOON_VQ_MAX];
	const char *names[VIRTIO_BALLOON_VQ_MAX];
	int err;

	/*
	 * Inflateq and deflateq are used unconditionally. The names[]
	 * will be NULL if the related feature is not enabled, which will
	 * cause no allocation for the corresponding virtqueue in find_vqs.
	 */
	callbacks[VIRTIO_BALLOON_VQ_INFLATE] = balloon_ack;
	names[VIRTIO_BALLOON_VQ_INFLATE] = "inflate";
	callbacks[VIRTIO_BALLOON_VQ_DEFLATE] = balloon_ack;
	names[VIRTIO_BALLOON_VQ_DEFLATE] = "deflate";
	names[VIRTIO_BALLOON_VQ_STATS] = NULL;
	names[VIRTIO_BALLOON_VQ_FREE_PAGE] = NULL;

	if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_STATS_VQ)) {
		names[VIRTIO_BALLOON_VQ_STATS] = "stats";
		callbacks[VIRTIO_BALLOON_VQ_STATS] = stats_request;
	}

	if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_FREE_PAGE_HINT)) {
		names[VIRTIO_BALLOON_VQ_FREE_PAGE] = "free_page_vq";
		callbacks[VIRTIO_BALLOON_VQ_FREE_PAGE] = NULL;
	}

	err = vb->vdev->config->find_vqs(vb->vdev, VIRTIO_BALLOON_VQ_MAX,
					 vqs, callbacks, names, NULL, NULL);
	if (err)
		return err;

	vb->inflate_vq = vqs[VIRTIO_BALLOON_VQ_INFLATE];
	vb->deflate_vq = vqs[VIRTIO_BALLOON_VQ_DEFLATE];
	if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_STATS_VQ)) {
		struct scatterlist sg;
		unsigned int num_stats;
		vb->stats_vq = vqs[VIRTIO_BALLOON_VQ_STATS];

		/*
		 * Prime this virtqueue with one buffer so the hypervisor can
		 * use it to signal us later (it can't be broken yet!).
		 */
		num_stats = update_balloon_stats(vb);

		sg_init_one(&sg, vb->stats, sizeof(vb->stats[0]) * num_stats);
		err = virtqueue_add_outbuf(vb->stats_vq, &sg, 1, vb,
					   GFP_KERNEL);
		if (err) {
			dev_warn(&vb->vdev->dev, "%s: add stat_vq failed\n",
				 __func__);
			return err;
		}
		virtqueue_kick(vb->stats_vq);
	}

	if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_FREE_PAGE_HINT))
		vb->free_page_vq = vqs[VIRTIO_BALLOON_VQ_FREE_PAGE];

	return 0;
}

static u32 virtio_balloon_cmd_id_received(struct virtio_balloon *vb)
{
	if (test_and_clear_bit(VIRTIO_BALLOON_CONFIG_READ_CMD_ID,
			       &vb->config_read_bitmap))
		virtio_cread(vb->vdev, struct virtio_balloon_config,
			     free_page_report_cmd_id,
			     &vb->cmd_id_received_cache);

	return vb->cmd_id_received_cache;
}

static int send_cmd_id_start(struct virtio_balloon *vb)
{
	struct scatterlist sg;
	struct virtqueue *vq = vb->free_page_vq;
	int err, unused;

	/* Detach all the used buffers from the vq */
	while (virtqueue_get_buf(vq, &unused))
		;

	vb->cmd_id_active = virtio32_to_cpu(vb->vdev,
					virtio_balloon_cmd_id_received(vb));
	sg_init_one(&sg, &vb->cmd_id_active, sizeof(vb->cmd_id_active));
	err = virtqueue_add_outbuf(vq, &sg, 1, &vb->cmd_id_active, GFP_KERNEL);
	if (!err)
		virtqueue_kick(vq);
	return err;
}

static int send_cmd_id_stop(struct virtio_balloon *vb)
{
	struct scatterlist sg;
	struct virtqueue *vq = vb->free_page_vq;
	int err, unused;

	/* Detach all the used buffers from the vq */
	while (virtqueue_get_buf(vq, &unused))
		;

	sg_init_one(&sg, &vb->cmd_id_stop, sizeof(vb->cmd_id_stop));
	err = virtqueue_add_outbuf(vq, &sg, 1, &vb->cmd_id_stop, GFP_KERNEL);
	if (!err)
		virtqueue_kick(vq);
	return err;
}

static int get_free_page_and_send(struct virtio_balloon *vb)
{
	struct virtqueue *vq = vb->free_page_vq;
	struct page *page;
	struct scatterlist sg;
	int err, unused;
	void *p;

	/* Detach all the used buffers from the vq */
	while (virtqueue_get_buf(vq, &unused))
		;

	page = alloc_pages(VIRTIO_BALLOON_FREE_PAGE_ALLOC_FLAG,
			   VIRTIO_BALLOON_FREE_PAGE_ORDER);
	/*
	 * When the allocation returns NULL, it indicates that we have got all
	 * the possible free pages, so return -EINTR to stop.
	 */
	if (!page)
		return -EINTR;

	p = page_address(page);
	sg_init_one(&sg, p, VIRTIO_BALLOON_FREE_PAGE_SIZE);
	/* There is always 1 entry reserved for the cmd id to use. */
	if (vq->num_free > 1) {
		err = virtqueue_add_inbuf(vq, &sg, 1, p, GFP_KERNEL);
		if (unlikely(err)) {
			free_pages((unsigned long)p,
				   VIRTIO_BALLOON_FREE_PAGE_ORDER);
			return err;
		}
		virtqueue_kick(vq);
		spin_lock_irq(&vb->free_page_list_lock);
		balloon_page_push(&vb->free_page_list, page);
		vb->num_free_page_blocks++;
		spin_unlock_irq(&vb->free_page_list_lock);
	} else {
		/*
		 * The vq has no available entry to add this page block, so
		 * just free it.
		 */
		free_pages((unsigned long)p, VIRTIO_BALLOON_FREE_PAGE_ORDER);
	}

	return 0;
}

static int send_free_pages(struct virtio_balloon *vb)
{
	int err;
	u32 cmd_id_active;

	while (1) {
		/*
		 * If a stop id or a new cmd id was just received from host,
		 * stop the reporting.
		 */
		cmd_id_active = virtio32_to_cpu(vb->vdev, vb->cmd_id_active);
		if (unlikely(cmd_id_active !=
			     virtio_balloon_cmd_id_received(vb)))
			break;

		/*
		 * The free page blocks are allocated and sent to host one by
		 * one.
		 */
		err = get_free_page_and_send(vb);
		if (err == -EINTR)
			break;
		else if (unlikely(err))
			return err;
	}

	return 0;
}

static void virtio_balloon_report_free_page(struct virtio_balloon *vb)
{
	int err;
	struct device *dev = &vb->vdev->dev;

	/* Start by sending the received cmd id to host with an outbuf. */
	err = send_cmd_id_start(vb);
	if (unlikely(err))
		dev_err(dev, "Failed to send a start id, err = %d\n", err);

	err = send_free_pages(vb);
	if (unlikely(err))
		dev_err(dev, "Failed to send a free page, err = %d\n", err);

	/* End by sending a stop id to host with an outbuf. */
	err = send_cmd_id_stop(vb);
	if (unlikely(err))
		dev_err(dev, "Failed to send a stop id, err = %d\n", err);
}

static void report_free_page_func(struct work_struct *work)
{
	struct virtio_balloon *vb = container_of(work, struct virtio_balloon,
						 report_free_page_work);
	u32 cmd_id_received;

	cmd_id_received = virtio_balloon_cmd_id_received(vb);
	if (cmd_id_received == VIRTIO_BALLOON_CMD_ID_DONE) {
		/* Pass ULONG_MAX to give back all the free pages */
		return_free_pages_to_mm(vb, ULONG_MAX);
	} else if (cmd_id_received != VIRTIO_BALLOON_CMD_ID_STOP &&
		   cmd_id_received !=
		   virtio32_to_cpu(vb->vdev, vb->cmd_id_active)) {
		virtio_balloon_report_free_page(vb);
	}
}

#ifdef CONFIG_BALLOON_COMPACTION
/*
 * virtballoon_migratepage - perform the balloon page migration on behalf of
 *			     a compation thread.     (called under page lock)
 * @vb_dev_info: the balloon device
 * @newpage: page that will replace the isolated page after migration finishes.
 * @page   : the isolated (old) page that is about to be migrated to newpage.
 * @mode   : compaction mode -- not used for balloon page migration.
 *
 * After a ballooned page gets isolated by compaction procedures, this is the
 * function that performs the page migration on behalf of a compaction thread
 * The page migration for virtio balloon is done in a simple swap fashion which
 * follows these two macro steps:
 *  1) insert newpage into vb->pages list and update the host about it;
 *  2) update the host about the old page removed from vb->pages list;
 *
 * This function preforms the balloon page migration task.
 * Called through balloon_mapping->a_ops->migratepage
 */
static int virtballoon_migratepage(struct balloon_dev_info *vb_dev_info,
		struct page *newpage, struct page *page, enum migrate_mode mode)
{
	struct virtio_balloon *vb = container_of(vb_dev_info,
			struct virtio_balloon, vb_dev_info);
	unsigned long flags;

	/*
	 * In order to avoid lock contention while migrating pages concurrently
	 * to leak_balloon() or fill_balloon() we just give up the balloon_lock
	 * this turn, as it is easier to retry the page migration later.
	 * This also prevents fill_balloon() getting stuck into a mutex
	 * recursion in the case it ends up triggering memory compaction
	 * while it is attempting to inflate the ballon.
	 */
	if (!mutex_trylock(&vb->balloon_lock))
		return -EAGAIN;

	get_page(newpage); /* balloon reference */

	/* balloon's page migration 1st step  -- inflate "newpage" */
	spin_lock_irqsave(&vb_dev_info->pages_lock, flags);
	balloon_page_insert(vb_dev_info, newpage);
	vb_dev_info->isolated_pages--;
	__count_vm_event(BALLOON_MIGRATE);
	spin_unlock_irqrestore(&vb_dev_info->pages_lock, flags);
	vb->num_pfns = VIRTIO_BALLOON_PAGES_PER_PAGE;
	set_page_pfns(vb, vb->pfns, newpage);
	tell_host(vb, vb->inflate_vq);

	/* balloon's page migration 2nd step -- deflate "page" */
	spin_lock_irqsave(&vb_dev_info->pages_lock, flags);
	balloon_page_delete(page);
	spin_unlock_irqrestore(&vb_dev_info->pages_lock, flags);
	vb->num_pfns = VIRTIO_BALLOON_PAGES_PER_PAGE;
	set_page_pfns(vb, vb->pfns, page);
	tell_host(vb, vb->deflate_vq);

	mutex_unlock(&vb->balloon_lock);

	put_page(page); /* balloon reference */

	return MIGRATEPAGE_SUCCESS;
}

static struct dentry *balloon_mount(struct file_system_type *fs_type,
		int flags, const char *dev_name, void *data)
{
	static const struct dentry_operations ops = {
		.d_dname = simple_dname,
	};

	return mount_pseudo(fs_type, "balloon-kvm:", NULL, &ops,
				BALLOON_KVM_MAGIC);
}

static struct file_system_type balloon_fs = {
	.name           = "balloon-kvm",
	.mount          = balloon_mount,
	.kill_sb        = kill_anon_super,
};

#endif /* CONFIG_BALLOON_COMPACTION */

static unsigned long shrink_free_pages(struct virtio_balloon *vb,
				       unsigned long pages_to_free)
{
	unsigned long blocks_to_free, blocks_freed;

	pages_to_free = round_up(pages_to_free,
				 1 << VIRTIO_BALLOON_FREE_PAGE_ORDER);
	blocks_to_free = pages_to_free >> VIRTIO_BALLOON_FREE_PAGE_ORDER;
	blocks_freed = return_free_pages_to_mm(vb, blocks_to_free);

	return blocks_freed << VIRTIO_BALLOON_FREE_PAGE_ORDER;
}

static unsigned long shrink_balloon_pages(struct virtio_balloon *vb,
					  unsigned long pages_to_free)
{
	unsigned long pages_freed = 0;

	/*
	 * One invocation of leak_balloon can deflate at most
	 * VIRTIO_BALLOON_ARRAY_PFNS_MAX balloon pages, so we call it
	 * multiple times to deflate pages till reaching pages_to_free.
	 */
	while (vb->num_pages && pages_to_free) {
		pages_freed += leak_balloon(vb, pages_to_free) /
					VIRTIO_BALLOON_PAGES_PER_PAGE;
		pages_to_free -= pages_freed;
	}
	update_balloon_size(vb);

	return pages_freed;
}

static unsigned long virtio_balloon_shrinker_scan(struct shrinker *shrinker,
						  struct shrink_control *sc)
{
	unsigned long pages_to_free, pages_freed = 0;
	struct virtio_balloon *vb = container_of(shrinker,
					struct virtio_balloon, shrinker);

	pages_to_free = sc->nr_to_scan * VIRTIO_BALLOON_PAGES_PER_PAGE;

	if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_FREE_PAGE_HINT))
		pages_freed = shrink_free_pages(vb, pages_to_free);

	if (pages_freed >= pages_to_free)
		return pages_freed;

	pages_freed += shrink_balloon_pages(vb, pages_to_free - pages_freed);

	return pages_freed;
}

static unsigned long virtio_balloon_shrinker_count(struct shrinker *shrinker,
						   struct shrink_control *sc)
{
	struct virtio_balloon *vb = container_of(shrinker,
					struct virtio_balloon, shrinker);
	unsigned long count;

	count = vb->num_pages / VIRTIO_BALLOON_PAGES_PER_PAGE;
	count += vb->num_free_page_blocks >> VIRTIO_BALLOON_FREE_PAGE_ORDER;

	return count;
}

static void virtio_balloon_unregister_shrinker(struct virtio_balloon *vb)
{
	unregister_shrinker(&vb->shrinker);
}

static int virtio_balloon_register_shrinker(struct virtio_balloon *vb)
{
	vb->shrinker.scan_objects = virtio_balloon_shrinker_scan;
	vb->shrinker.count_objects = virtio_balloon_shrinker_count;
	vb->shrinker.seeks = DEFAULT_SEEKS;

	return register_shrinker(&vb->shrinker);
}

static int virtballoon_probe(struct virtio_device *vdev)
{
	struct virtio_balloon *vb;
	__u32 poison_val;
	int err;

	if (!vdev->config->get) {
		dev_err(&vdev->dev, "%s failure: config access disabled\n",
			__func__);
		return -EINVAL;
	}

	vdev->priv = vb = kzalloc(sizeof(*vb), GFP_KERNEL);
	if (!vb) {
		err = -ENOMEM;
		goto out;
	}

	INIT_WORK(&vb->update_balloon_stats_work, update_balloon_stats_func);
	INIT_WORK(&vb->update_balloon_size_work, update_balloon_size_func);
	spin_lock_init(&vb->stop_update_lock);
	mutex_init(&vb->balloon_lock);
	init_waitqueue_head(&vb->acked);
	vb->vdev = vdev;

	balloon_devinfo_init(&vb->vb_dev_info);

	err = init_vqs(vb);
	if (err)
		goto out_free_vb;

#ifdef CONFIG_BALLOON_COMPACTION
	balloon_mnt = kern_mount(&balloon_fs);
	if (IS_ERR(balloon_mnt)) {
		err = PTR_ERR(balloon_mnt);
		goto out_del_vqs;
	}

	vb->vb_dev_info.migratepage = virtballoon_migratepage;
	vb->vb_dev_info.inode = alloc_anon_inode(balloon_mnt->mnt_sb);
	if (IS_ERR(vb->vb_dev_info.inode)) {
		err = PTR_ERR(vb->vb_dev_info.inode);
		kern_unmount(balloon_mnt);
		goto out_del_vqs;
	}
	vb->vb_dev_info.inode->i_mapping->a_ops = &balloon_aops;
#endif
	if (virtio_has_feature(vdev, VIRTIO_BALLOON_F_FREE_PAGE_HINT)) {
		/*
		 * There is always one entry reserved for cmd id, so the ring
		 * size needs to be at least two to report free page hints.
		 */
		if (virtqueue_get_vring_size(vb->free_page_vq) < 2) {
			err = -ENOSPC;
			goto out_del_vqs;
		}
		vb->balloon_wq = alloc_workqueue("balloon-wq",
					WQ_FREEZABLE | WQ_CPU_INTENSIVE, 0);
		if (!vb->balloon_wq) {
			err = -ENOMEM;
			goto out_del_vqs;
		}
		INIT_WORK(&vb->report_free_page_work, report_free_page_func);
		vb->cmd_id_received_cache = VIRTIO_BALLOON_CMD_ID_STOP;
		vb->cmd_id_active = cpu_to_virtio32(vb->vdev,
						  VIRTIO_BALLOON_CMD_ID_STOP);
		vb->cmd_id_stop = cpu_to_virtio32(vb->vdev,
						  VIRTIO_BALLOON_CMD_ID_STOP);
		spin_lock_init(&vb->free_page_list_lock);
		INIT_LIST_HEAD(&vb->free_page_list);
		if (virtio_has_feature(vdev, VIRTIO_BALLOON_F_PAGE_POISON)) {
			memset(&poison_val, PAGE_POISON, sizeof(poison_val));
			virtio_cwrite(vb->vdev, struct virtio_balloon_config,
				      poison_val, &poison_val);
		}
	}
	/*
	 * We continue to use VIRTIO_BALLOON_F_DEFLATE_ON_OOM to decide if a
	 * shrinker needs to be registered to relieve memory pressure.
	 */
	if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_DEFLATE_ON_OOM)) {
		err = virtio_balloon_register_shrinker(vb);
		if (err)
			goto out_del_balloon_wq;
	}
	virtio_device_ready(vdev);

	if (towards_target(vb))
		virtballoon_changed(vdev);
	return 0;

out_del_balloon_wq:
	if (virtio_has_feature(vdev, VIRTIO_BALLOON_F_FREE_PAGE_HINT))
		destroy_workqueue(vb->balloon_wq);
out_del_vqs:
	vdev->config->del_vqs(vdev);
out_free_vb:
	kfree(vb);
out:
	return err;
}

static void remove_common(struct virtio_balloon *vb)
{
	/* There might be pages left in the balloon: free them. */
	while (vb->num_pages)
		leak_balloon(vb, vb->num_pages);
	update_balloon_size(vb);

	/* Now we reset the device so we can clean up the queues. */
	vb->vdev->config->reset(vb->vdev);

	vb->vdev->config->del_vqs(vb->vdev);
}

static void virtballoon_remove(struct virtio_device *vdev)
{
	struct virtio_balloon *vb = vdev->priv;

	if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_DEFLATE_ON_OOM))
		virtio_balloon_unregister_shrinker(vb);
	spin_lock_irq(&vb->stop_update_lock);
	vb->stop_update = true;
	spin_unlock_irq(&vb->stop_update_lock);
	cancel_work_sync(&vb->update_balloon_size_work);
	cancel_work_sync(&vb->update_balloon_stats_work);

	if (virtio_has_feature(vdev, VIRTIO_BALLOON_F_FREE_PAGE_HINT)) {
		cancel_work_sync(&vb->report_free_page_work);
		destroy_workqueue(vb->balloon_wq);
	}

	remove_common(vb);
#ifdef CONFIG_BALLOON_COMPACTION
	if (vb->vb_dev_info.inode)
		iput(vb->vb_dev_info.inode);

	kern_unmount(balloon_mnt);
#endif
	kfree(vb);
}

#ifdef CONFIG_PM_SLEEP
static int virtballoon_freeze(struct virtio_device *vdev)
{
	struct virtio_balloon *vb = vdev->priv;

	/*
	 * The workqueue is already frozen by the PM core before this
	 * function is called.
	 */
	remove_common(vb);
	return 0;
}

static int virtballoon_restore(struct virtio_device *vdev)
{
	struct virtio_balloon *vb = vdev->priv;
	int ret;

	ret = init_vqs(vdev->priv);
	if (ret)
		return ret;

	virtio_device_ready(vdev);

	if (towards_target(vb))
		virtballoon_changed(vdev);
	update_balloon_size(vb);
	return 0;
}
#endif

static int virtballoon_validate(struct virtio_device *vdev)
{
	if (!page_poisoning_enabled())
		__virtio_clear_bit(vdev, VIRTIO_BALLOON_F_PAGE_POISON);

	__virtio_clear_bit(vdev, VIRTIO_F_IOMMU_PLATFORM);
	return 0;
}

static unsigned int features[] = {
	VIRTIO_BALLOON_F_MUST_TELL_HOST,
	VIRTIO_BALLOON_F_STATS_VQ,
	VIRTIO_BALLOON_F_DEFLATE_ON_OOM,
	VIRTIO_BALLOON_F_FREE_PAGE_HINT,
	VIRTIO_BALLOON_F_PAGE_POISON,
};

static struct virtio_driver virtio_balloon_driver = {
	.feature_table = features,
	.feature_table_size = ARRAY_SIZE(features),
	.driver.name =	KBUILD_MODNAME,
	.driver.owner =	THIS_MODULE,
	.id_table =	id_table,
	.validate =	virtballoon_validate,
	.probe =	virtballoon_probe,
	.remove =	virtballoon_remove,
	.config_changed = virtballoon_changed,
#ifdef CONFIG_PM_SLEEP
	.freeze	=	virtballoon_freeze,
	.restore =	virtballoon_restore,
#endif
};

module_virtio_driver(virtio_balloon_driver);
MODULE_DEVICE_TABLE(virtio, id_table);
MODULE_DESCRIPTION("Virtio balloon driver");
MODULE_LICENSE("GPL");