summaryrefslogtreecommitdiffstats
path: root/drivers/xen/balloon.c
blob: f77e499afdddb02c2d7595459a70b15f3a8c56d5 (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
/******************************************************************************
 * Xen balloon driver - enables returning/claiming memory to/from Xen.
 *
 * Copyright (c) 2003, B Dragovic
 * Copyright (c) 2003-2004, M Williamson, K Fraser
 * Copyright (c) 2005 Dan M. Smith, IBM Corporation
 * Copyright (c) 2010 Daniel Kiper
 *
 * Memory hotplug support was written by Daniel Kiper. Work on
 * it was sponsored by Google under Google Summer of Code 2010
 * program. Jeremy Fitzhardinge from Citrix was the mentor for
 * this project.
 *
 * 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.
 */

#define pr_fmt(fmt) "xen:" KBUILD_MODNAME ": " fmt

#include <linux/cpu.h>
#include <linux/kernel.h>
#include <linux/sched.h>
#include <linux/cred.h>
#include <linux/errno.h>
#include <linux/mm.h>
#include <linux/bootmem.h>
#include <linux/pagemap.h>
#include <linux/highmem.h>
#include <linux/mutex.h>
#include <linux/list.h>
#include <linux/gfp.h>
#include <linux/notifier.h>
#include <linux/memory.h>
#include <linux/memory_hotplug.h>
#include <linux/percpu-defs.h>
#include <linux/slab.h>
#include <linux/sysctl.h>

#include <asm/page.h>
#include <asm/pgalloc.h>
#include <asm/pgtable.h>
#include <asm/tlb.h>

#include <asm/xen/hypervisor.h>
#include <asm/xen/hypercall.h>

#include <xen/xen.h>
#include <xen/interface/xen.h>
#include <xen/interface/memory.h>
#include <xen/balloon.h>
#include <xen/features.h>
#include <xen/page.h>

static int xen_hotplug_unpopulated;

#ifdef CONFIG_XEN_BALLOON_MEMORY_HOTPLUG

static int zero;
static int one = 1;

static struct ctl_table balloon_table[] = {
	{
		.procname	= "hotplug_unpopulated",
		.data		= &xen_hotplug_unpopulated,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec_minmax,
		.extra1         = &zero,
		.extra2         = &one,
	},
	{ }
};

static struct ctl_table balloon_root[] = {
	{
		.procname	= "balloon",
		.mode		= 0555,
		.child		= balloon_table,
	},
	{ }
};

static struct ctl_table xen_root[] = {
	{
		.procname	= "xen",
		.mode		= 0555,
		.child		= balloon_root,
	},
	{ }
};

#endif

/*
 * Use one extent per PAGE_SIZE to avoid to break down the page into
 * multiple frame.
 */
#define EXTENT_ORDER (fls(XEN_PFN_PER_PAGE) - 1)

/*
 * balloon_process() state:
 *
 * BP_DONE: done or nothing to do,
 * BP_WAIT: wait to be rescheduled,
 * BP_EAGAIN: error, go to sleep,
 * BP_ECANCELED: error, balloon operation canceled.
 */

enum bp_state {
	BP_DONE,
	BP_WAIT,
	BP_EAGAIN,
	BP_ECANCELED
};


static DEFINE_MUTEX(balloon_mutex);

struct balloon_stats balloon_stats;
EXPORT_SYMBOL_GPL(balloon_stats);

/* We increase/decrease in batches which fit in a page */
static xen_pfn_t frame_list[PAGE_SIZE / sizeof(xen_pfn_t)];


/* List of ballooned pages, threaded through the mem_map array. */
static LIST_HEAD(ballooned_pages);
static DECLARE_WAIT_QUEUE_HEAD(balloon_wq);

/* Main work function, always executed in process context. */
static void balloon_process(struct work_struct *work);
static DECLARE_DELAYED_WORK(balloon_worker, balloon_process);

/* When ballooning out (allocating memory to return to Xen) we don't really
   want the kernel to try too hard since that can trigger the oom killer. */
#define GFP_BALLOON \
	(GFP_HIGHUSER | __GFP_NOWARN | __GFP_NORETRY | __GFP_NOMEMALLOC)

static void scrub_page(struct page *page)
{
#ifdef CONFIG_XEN_SCRUB_PAGES
	clear_highpage(page);
#endif
}

/* balloon_append: add the given page to the balloon. */
static void __balloon_append(struct page *page)
{
	/* Lowmem is re-populated first, so highmem pages go at list tail. */
	if (PageHighMem(page)) {
		list_add_tail(&page->lru, &ballooned_pages);
		balloon_stats.balloon_high++;
	} else {
		list_add(&page->lru, &ballooned_pages);
		balloon_stats.balloon_low++;
	}
	wake_up(&balloon_wq);
}

static void balloon_append(struct page *page)
{
	__balloon_append(page);
}

/* balloon_retrieve: rescue a page from the balloon, if it is not empty. */
static struct page *balloon_retrieve(bool require_lowmem)
{
	struct page *page;

	if (list_empty(&ballooned_pages))
		return NULL;

	page = list_entry(ballooned_pages.next, struct page, lru);
	if (require_lowmem && PageHighMem(page))
		return NULL;
	list_del(&page->lru);

	if (PageHighMem(page))
		balloon_stats.balloon_high--;
	else
		balloon_stats.balloon_low--;

	return page;
}

static struct page *balloon_next_page(struct page *page)
{
	struct list_head *next = page->lru.next;
	if (next == &ballooned_pages)
		return NULL;
	return list_entry(next, struct page, lru);
}

static enum bp_state update_schedule(enum bp_state state)
{
	if (state == BP_WAIT)
		return BP_WAIT;

	if (state == BP_ECANCELED)
		return BP_ECANCELED;

	if (state == BP_DONE) {
		balloon_stats.schedule_delay = 1;
		balloon_stats.retry_count = 1;
		return BP_DONE;
	}

	++balloon_stats.retry_count;

	if (balloon_stats.max_retry_count != RETRY_UNLIMITED &&
			balloon_stats.retry_count > balloon_stats.max_retry_count) {
		balloon_stats.schedule_delay = 1;
		balloon_stats.retry_count = 1;
		return BP_ECANCELED;
	}

	balloon_stats.schedule_delay <<= 1;

	if (balloon_stats.schedule_delay > balloon_stats.max_schedule_delay)
		balloon_stats.schedule_delay = balloon_stats.max_schedule_delay;

	return BP_EAGAIN;
}

#ifdef CONFIG_XEN_BALLOON_MEMORY_HOTPLUG
static void release_memory_resource(struct resource *resource)
{
	if (!resource)
		return;

	/*
	 * No need to reset region to identity mapped since we now
	 * know that no I/O can be in this region
	 */
	release_resource(resource);
	kfree(resource);
}

static struct resource *additional_memory_resource(phys_addr_t size)
{
	struct resource *res;
	int ret;

	res = kzalloc(sizeof(*res), GFP_KERNEL);
	if (!res)
		return NULL;

	res->name = "System RAM";
	res->flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;

	ret = allocate_resource(&iomem_resource, res,
				size, 0, -1,
				PAGES_PER_SECTION * PAGE_SIZE, NULL, NULL);
	if (ret < 0) {
		pr_err("Cannot allocate new System RAM resource\n");
		kfree(res);
		return NULL;
	}

#ifdef CONFIG_SPARSEMEM
	{
		unsigned long limit = 1UL << (MAX_PHYSMEM_BITS - PAGE_SHIFT);
		unsigned long pfn = res->start >> PAGE_SHIFT;

		if (pfn > limit) {
			pr_err("New System RAM resource outside addressable RAM (%lu > %lu)\n",
			       pfn, limit);
			release_memory_resource(res);
			return NULL;
		}
	}
#endif

	return res;
}

static enum bp_state reserve_additional_memory(void)
{
	long credit;
	struct resource *resource;
	int nid, rc;
	unsigned long balloon_hotplug;

	credit = balloon_stats.target_pages + balloon_stats.target_unpopulated
		- balloon_stats.total_pages;

	/*
	 * Already hotplugged enough pages?  Wait for them to be
	 * onlined.
	 */
	if (credit <= 0)
		return BP_WAIT;

	balloon_hotplug = round_up(credit, PAGES_PER_SECTION);

	resource = additional_memory_resource(balloon_hotplug * PAGE_SIZE);
	if (!resource)
		goto err;

	nid = memory_add_physaddr_to_nid(resource->start);

#ifdef CONFIG_XEN_HAVE_PVMMU
	/*
	 * We don't support PV MMU when Linux and Xen is using
	 * different page granularity.
	 */
	BUILD_BUG_ON(XEN_PAGE_SIZE != PAGE_SIZE);

        /*
         * add_memory() will build page tables for the new memory so
         * the p2m must contain invalid entries so the correct
         * non-present PTEs will be written.
         *
         * If a failure occurs, the original (identity) p2m entries
         * are not restored since this region is now known not to
         * conflict with any devices.
         */ 
	if (!xen_feature(XENFEAT_auto_translated_physmap)) {
		unsigned long pfn, i;

		pfn = PFN_DOWN(resource->start);
		for (i = 0; i < balloon_hotplug; i++) {
			if (!set_phys_to_machine(pfn + i, INVALID_P2M_ENTRY)) {
				pr_warn("set_phys_to_machine() failed, no memory added\n");
				goto err;
			}
                }
	}
#endif

	/*
	 * add_memory_resource() will call online_pages() which in its turn
	 * will call xen_online_page() callback causing deadlock if we don't
	 * release balloon_mutex here. Unlocking here is safe because the
	 * callers drop the mutex before trying again.
	 */
	mutex_unlock(&balloon_mutex);
	rc = add_memory_resource(nid, resource, memhp_auto_online);
	mutex_lock(&balloon_mutex);

	if (rc) {
		pr_warn("Cannot add additional memory (%i)\n", rc);
		goto err;
	}

	balloon_stats.total_pages += balloon_hotplug;

	return BP_WAIT;
  err:
	release_memory_resource(resource);
	return BP_ECANCELED;
}

static void xen_online_page(struct page *page)
{
	__online_page_set_limits(page);

	mutex_lock(&balloon_mutex);

	__balloon_append(page);

	mutex_unlock(&balloon_mutex);
}

static int xen_memory_notifier(struct notifier_block *nb, unsigned long val, void *v)
{
	if (val == MEM_ONLINE)
		schedule_delayed_work(&balloon_worker, 0);

	return NOTIFY_OK;
}

static struct notifier_block xen_memory_nb = {
	.notifier_call = xen_memory_notifier,
	.priority = 0
};
#else
static enum bp_state reserve_additional_memory(void)
{
	balloon_stats.target_pages = balloon_stats.current_pages;
	return BP_ECANCELED;
}
#endif /* CONFIG_XEN_BALLOON_MEMORY_HOTPLUG */

static long current_credit(void)
{
	return balloon_stats.target_pages - balloon_stats.current_pages;
}

static bool balloon_is_inflated(void)
{
	return balloon_stats.balloon_low || balloon_stats.balloon_high;
}

static enum bp_state increase_reservation(unsigned long nr_pages)
{
	int rc;
	unsigned long i;
	struct page   *page;
	struct xen_memory_reservation reservation = {
		.address_bits = 0,
		.extent_order = EXTENT_ORDER,
		.domid        = DOMID_SELF
	};

	if (nr_pages > ARRAY_SIZE(frame_list))
		nr_pages = ARRAY_SIZE(frame_list);

	page = list_first_entry_or_null(&ballooned_pages, struct page, lru);
	for (i = 0; i < nr_pages; i++) {
		if (!page) {
			nr_pages = i;
			break;
		}

		/* XENMEM_populate_physmap requires a PFN based on Xen
		 * granularity.
		 */
		frame_list[i] = page_to_xen_pfn(page);
		page = balloon_next_page(page);
	}

	set_xen_guest_handle(reservation.extent_start, frame_list);
	reservation.nr_extents = nr_pages;
	rc = HYPERVISOR_memory_op(XENMEM_populate_physmap, &reservation);
	if (rc <= 0)
		return BP_EAGAIN;

	for (i = 0; i < rc; i++) {
		page = balloon_retrieve(false);
		BUG_ON(page == NULL);

#ifdef CONFIG_XEN_HAVE_PVMMU
		/*
		 * We don't support PV MMU when Linux and Xen is using
		 * different page granularity.
		 */
		BUILD_BUG_ON(XEN_PAGE_SIZE != PAGE_SIZE);

		if (!xen_feature(XENFEAT_auto_translated_physmap)) {
			unsigned long pfn = page_to_pfn(page);

			set_phys_to_machine(pfn, frame_list[i]);

			/* Link back into the page tables if not highmem. */
			if (!PageHighMem(page)) {
				int ret;
				ret = HYPERVISOR_update_va_mapping(
						(unsigned long)__va(pfn << PAGE_SHIFT),
						mfn_pte(frame_list[i], PAGE_KERNEL),
						0);
				BUG_ON(ret);
			}
		}
#endif

		/* Relinquish the page back to the allocator. */
		free_reserved_page(page);
	}

	balloon_stats.current_pages += rc;

	return BP_DONE;
}

static enum bp_state decrease_reservation(unsigned long nr_pages, gfp_t gfp)
{
	enum bp_state state = BP_DONE;
	unsigned long i;
	struct page *page, *tmp;
	int ret;
	struct xen_memory_reservation reservation = {
		.address_bits = 0,
		.extent_order = EXTENT_ORDER,
		.domid        = DOMID_SELF
	};
	LIST_HEAD(pages);

	if (nr_pages > ARRAY_SIZE(frame_list))
		nr_pages = ARRAY_SIZE(frame_list);

	for (i = 0; i < nr_pages; i++) {
		page = alloc_page(gfp);
		if (page == NULL) {
			nr_pages = i;
			state = BP_EAGAIN;
			break;
		}
		adjust_managed_page_count(page, -1);
		scrub_page(page);
		list_add(&page->lru, &pages);
	}

	/*
	 * Ensure that ballooned highmem pages don't have kmaps.
	 *
	 * Do this before changing the p2m as kmap_flush_unused()
	 * reads PTEs to obtain pages (and hence needs the original
	 * p2m entry).
	 */
	kmap_flush_unused();

	/*
	 * Setup the frame, update direct mapping, invalidate P2M,
	 * and add to balloon.
	 */
	i = 0;
	list_for_each_entry_safe(page, tmp, &pages, lru) {
		/* XENMEM_decrease_reservation requires a GFN */
		frame_list[i++] = xen_page_to_gfn(page);

#ifdef CONFIG_XEN_HAVE_PVMMU
		/*
		 * We don't support PV MMU when Linux and Xen is using
		 * different page granularity.
		 */
		BUILD_BUG_ON(XEN_PAGE_SIZE != PAGE_SIZE);

		if (!xen_feature(XENFEAT_auto_translated_physmap)) {
			unsigned long pfn = page_to_pfn(page);

			if (!PageHighMem(page)) {
				ret = HYPERVISOR_update_va_mapping(
						(unsigned long)__va(pfn << PAGE_SHIFT),
						__pte_ma(0), 0);
				BUG_ON(ret);
			}
			__set_phys_to_machine(pfn, INVALID_P2M_ENTRY);
		}
#endif
		list_del(&page->lru);

		balloon_append(page);
	}

	flush_tlb_all();

	set_xen_guest_handle(reservation.extent_start, frame_list);
	reservation.nr_extents   = nr_pages;
	ret = HYPERVISOR_memory_op(XENMEM_decrease_reservation, &reservation);
	BUG_ON(ret != nr_pages);

	balloon_stats.current_pages -= nr_pages;

	return state;
}

/*
 * As this is a work item it is guaranteed to run as a single instance only.
 * We may of course race updates of the target counts (which are protected
 * by the balloon lock), or with changes to the Xen hard limit, but we will
 * recover from these in time.
 */
static void balloon_process(struct work_struct *work)
{
	enum bp_state state = BP_DONE;
	long credit;


	do {
		mutex_lock(&balloon_mutex);

		credit = current_credit();

		if (credit > 0) {
			if (balloon_is_inflated())
				state = increase_reservation(credit);
			else
				state = reserve_additional_memory();
		}

		if (credit < 0)
			state = decrease_reservation(-credit, GFP_BALLOON);

		state = update_schedule(state);

		mutex_unlock(&balloon_mutex);

		cond_resched();

	} while (credit && state == BP_DONE);

	/* Schedule more work if there is some still to be done. */
	if (state == BP_EAGAIN)
		schedule_delayed_work(&balloon_worker, balloon_stats.schedule_delay * HZ);
}

/* Resets the Xen limit, sets new target, and kicks off processing. */
void balloon_set_new_target(unsigned long target)
{
	/* No need for lock. Not read-modify-write updates. */
	balloon_stats.target_pages = target;
	schedule_delayed_work(&balloon_worker, 0);
}
EXPORT_SYMBOL_GPL(balloon_set_new_target);

static int add_ballooned_pages(int nr_pages)
{
	enum bp_state st;

	if (xen_hotplug_unpopulated) {
		st = reserve_additional_memory();
		if (st != BP_ECANCELED) {
			mutex_unlock(&balloon_mutex);
			wait_event(balloon_wq,
				   !list_empty(&ballooned_pages));
			mutex_lock(&balloon_mutex);
			return 0;
		}
	}

	st = decrease_reservation(nr_pages, GFP_USER);
	if (st != BP_DONE)
		return -ENOMEM;

	return 0;
}

/**
 * alloc_xenballooned_pages - get pages that have been ballooned out
 * @nr_pages: Number of pages to get
 * @pages: pages returned
 * @return 0 on success, error otherwise
 */
int alloc_xenballooned_pages(int nr_pages, struct page **pages)
{
	int pgno = 0;
	struct page *page;
	int ret;

	mutex_lock(&balloon_mutex);

	balloon_stats.target_unpopulated += nr_pages;

	while (pgno < nr_pages) {
		page = balloon_retrieve(true);
		if (page) {
			pages[pgno++] = page;
#ifdef CONFIG_XEN_HAVE_PVMMU
			/*
			 * We don't support PV MMU when Linux and Xen is using
			 * different page granularity.
			 */
			BUILD_BUG_ON(XEN_PAGE_SIZE != PAGE_SIZE);

			if (!xen_feature(XENFEAT_auto_translated_physmap)) {
				ret = xen_alloc_p2m_entry(page_to_pfn(page));
				if (ret < 0)
					goto out_undo;
			}
#endif
		} else {
			ret = add_ballooned_pages(nr_pages - pgno);
			if (ret < 0)
				goto out_undo;
		}
	}
	mutex_unlock(&balloon_mutex);
	return 0;
 out_undo:
	mutex_unlock(&balloon_mutex);
	free_xenballooned_pages(pgno, pages);
	return ret;
}
EXPORT_SYMBOL(alloc_xenballooned_pages);

/**
 * free_xenballooned_pages - return pages retrieved with get_ballooned_pages
 * @nr_pages: Number of pages
 * @pages: pages to return
 */
void free_xenballooned_pages(int nr_pages, struct page **pages)
{
	int i;

	mutex_lock(&balloon_mutex);

	for (i = 0; i < nr_pages; i++) {
		if (pages[i])
			balloon_append(pages[i]);
	}

	balloon_stats.target_unpopulated -= nr_pages;

	/* The balloon may be too large now. Shrink it if needed. */
	if (current_credit())
		schedule_delayed_work(&balloon_worker, 0);

	mutex_unlock(&balloon_mutex);
}
EXPORT_SYMBOL(free_xenballooned_pages);

#ifdef CONFIG_XEN_PV
static void __init balloon_add_region(unsigned long start_pfn,
				      unsigned long pages)
{
	unsigned long pfn, extra_pfn_end;
	struct page *page;

	/*
	 * If the amount of usable memory has been limited (e.g., with
	 * the 'mem' command line parameter), don't add pages beyond
	 * this limit.
	 */
	extra_pfn_end = min(max_pfn, start_pfn + pages);

	for (pfn = start_pfn; pfn < extra_pfn_end; pfn++) {
		page = pfn_to_page(pfn);
		/* totalram_pages and totalhigh_pages do not
		   include the boot-time balloon extension, so
		   don't subtract from it. */
		__balloon_append(page);
	}

	balloon_stats.total_pages += extra_pfn_end - start_pfn;
}
#endif

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

	pr_info("Initialising balloon driver\n");

#ifdef CONFIG_XEN_PV
	balloon_stats.current_pages = xen_pv_domain()
		? min(xen_start_info->nr_pages - xen_released_pages, max_pfn)
		: get_num_physpages();
#else
	balloon_stats.current_pages = get_num_physpages();
#endif
	balloon_stats.target_pages  = balloon_stats.current_pages;
	balloon_stats.balloon_low   = 0;
	balloon_stats.balloon_high  = 0;
	balloon_stats.total_pages   = balloon_stats.current_pages;

	balloon_stats.schedule_delay = 1;
	balloon_stats.max_schedule_delay = 32;
	balloon_stats.retry_count = 1;
	balloon_stats.max_retry_count = RETRY_UNLIMITED;

#ifdef CONFIG_XEN_BALLOON_MEMORY_HOTPLUG
	set_online_page_callback(&xen_online_page);
	register_memory_notifier(&xen_memory_nb);
	register_sysctl_table(xen_root);
#endif

#ifdef CONFIG_XEN_PV
	{
		int i;

		/*
		 * Initialize the balloon with pages from the extra memory
		 * regions (see arch/x86/xen/setup.c).
		 */
		for (i = 0; i < XEN_EXTRA_MEM_MAX_REGIONS; i++)
			if (xen_extra_mem[i].n_pfns)
				balloon_add_region(xen_extra_mem[i].start_pfn,
						   xen_extra_mem[i].n_pfns);
	}
#endif

	/* Init the xen-balloon driver. */
	xen_balloon_init();

	return 0;
}
subsys_initcall(balloon_init);