1// SPDX-License-Identifier: GPL-2.0-or-later
2/*
3 * Virtio balloon implementation, inspired by Dor Laor and Marcelo
4 * Tosatti's implementations.
5 *
6 *  Copyright 2008 Rusty Russell IBM Corporation
7 */
8
9#include <linux/virtio.h>
10#include <linux/virtio_balloon.h>
11#include <linux/swap.h>
12#include <linux/workqueue.h>
13#include <linux/delay.h>
14#include <linux/slab.h>
15#include <linux/module.h>
16#include <linux/balloon_compaction.h>
17#include <linux/oom.h>
18#include <linux/wait.h>
19#include <linux/mm.h>
20#include <linux/mount.h>
21#include <linux/magic.h>
22#include <linux/pseudo_fs.h>
23#include <linux/page_reporting.h>
24
25/*
26 * Balloon device works in 4K page units.  So each page is pointed to by
27 * multiple balloon pages.  All memory counters in this driver are in balloon
28 * page units.
29 */
30#define VIRTIO_BALLOON_PAGES_PER_PAGE (unsigned)(PAGE_SIZE >> VIRTIO_BALLOON_PFN_SHIFT)
31#define VIRTIO_BALLOON_ARRAY_PFNS_MAX 256
32/* Maximum number of (4k) pages to deflate on OOM notifications. */
33#define VIRTIO_BALLOON_OOM_NR_PAGES 256
34#define VIRTIO_BALLOON_OOM_NOTIFY_PRIORITY 80
35
36#define VIRTIO_BALLOON_FREE_PAGE_ALLOC_FLAG (__GFP_NORETRY | __GFP_NOWARN | \
37					     __GFP_NOMEMALLOC)
38/* The order of free page blocks to report to host */
39#define VIRTIO_BALLOON_HINT_BLOCK_ORDER (MAX_ORDER - 1)
40/* The size of a free page block in bytes */
41#define VIRTIO_BALLOON_HINT_BLOCK_BYTES \
42	(1 << (VIRTIO_BALLOON_HINT_BLOCK_ORDER + PAGE_SHIFT))
43#define VIRTIO_BALLOON_HINT_BLOCK_PAGES (1 << VIRTIO_BALLOON_HINT_BLOCK_ORDER)
44
45#ifdef CONFIG_BALLOON_COMPACTION
46static struct vfsmount *balloon_mnt;
47#endif
48
49enum virtio_balloon_vq {
50	VIRTIO_BALLOON_VQ_INFLATE,
51	VIRTIO_BALLOON_VQ_DEFLATE,
52	VIRTIO_BALLOON_VQ_STATS,
53	VIRTIO_BALLOON_VQ_FREE_PAGE,
54	VIRTIO_BALLOON_VQ_REPORTING,
55	VIRTIO_BALLOON_VQ_MAX
56};
57
58enum virtio_balloon_config_read {
59	VIRTIO_BALLOON_CONFIG_READ_CMD_ID = 0,
60};
61
62struct virtio_balloon {
63	struct virtio_device *vdev;
64	struct virtqueue *inflate_vq, *deflate_vq, *stats_vq, *free_page_vq;
65
66	/* Balloon's own wq for cpu-intensive work items */
67	struct workqueue_struct *balloon_wq;
68	/* The free page reporting work item submitted to the balloon wq */
69	struct work_struct report_free_page_work;
70
71	/* The balloon servicing is delegated to a freezable workqueue. */
72	struct work_struct update_balloon_stats_work;
73	struct work_struct update_balloon_size_work;
74
75	/* Prevent updating balloon when it is being canceled. */
76	spinlock_t stop_update_lock;
77	bool stop_update;
78	/* Bitmap to indicate if reading the related config fields are needed */
79	unsigned long config_read_bitmap;
80
81	/* The list of allocated free pages, waiting to be given back to mm */
82	struct list_head free_page_list;
83	spinlock_t free_page_list_lock;
84	/* The number of free page blocks on the above list */
85	unsigned long num_free_page_blocks;
86	/*
87	 * The cmd id received from host.
88	 * Read it via virtio_balloon_cmd_id_received to get the latest value
89	 * sent from host.
90	 */
91	u32 cmd_id_received_cache;
92	/* The cmd id that is actively in use */
93	__virtio32 cmd_id_active;
94	/* Buffer to store the stop sign */
95	__virtio32 cmd_id_stop;
96
97	/* Waiting for host to ack the pages we released. */
98	wait_queue_head_t acked;
99
100	/* Number of balloon pages we've told the Host we're not using. */
101	unsigned int num_pages;
102	/*
103	 * The pages we've told the Host we're not using are enqueued
104	 * at vb_dev_info->pages list.
105	 * Each page on this list adds VIRTIO_BALLOON_PAGES_PER_PAGE
106	 * to num_pages above.
107	 */
108	struct balloon_dev_info vb_dev_info;
109
110	/* Synchronize access/update to this struct virtio_balloon elements */
111	struct mutex balloon_lock;
112
113	/* The array of pfns we tell the Host about. */
114	unsigned int num_pfns;
115	__virtio32 pfns[VIRTIO_BALLOON_ARRAY_PFNS_MAX];
116
117	/* Memory statistics */
118	struct virtio_balloon_stat stats[VIRTIO_BALLOON_S_NR];
119
120	/* Shrinker to return free pages - VIRTIO_BALLOON_F_FREE_PAGE_HINT */
121	struct shrinker shrinker;
122
123	/* OOM notifier to deflate on OOM - VIRTIO_BALLOON_F_DEFLATE_ON_OOM */
124	struct notifier_block oom_nb;
125
126	/* Free page reporting device */
127	struct virtqueue *reporting_vq;
128	struct page_reporting_dev_info pr_dev_info;
129};
130
131static const struct virtio_device_id id_table[] = {
132	{ VIRTIO_ID_BALLOON, VIRTIO_DEV_ANY_ID },
133	{ 0 },
134};
135
136static u32 page_to_balloon_pfn(struct page *page)
137{
138	unsigned long pfn = page_to_pfn(page);
139
140	BUILD_BUG_ON(PAGE_SHIFT < VIRTIO_BALLOON_PFN_SHIFT);
141	/* Convert pfn from Linux page size to balloon page size. */
142	return pfn * VIRTIO_BALLOON_PAGES_PER_PAGE;
143}
144
145static void balloon_ack(struct virtqueue *vq)
146{
147	struct virtio_balloon *vb = vq->vdev->priv;
148
149	wake_up(&vb->acked);
150}
151
152static void tell_host(struct virtio_balloon *vb, struct virtqueue *vq)
153{
154	struct scatterlist sg;
155	unsigned int len;
156
157	sg_init_one(&sg, vb->pfns, sizeof(vb->pfns[0]) * vb->num_pfns);
158
159	/* We should always be able to add one buffer to an empty queue. */
160	virtqueue_add_outbuf(vq, &sg, 1, vb, GFP_KERNEL);
161	virtqueue_kick(vq);
162
163	/* When host has read buffer, this completes via balloon_ack */
164	wait_event(vb->acked, virtqueue_get_buf(vq, &len));
165
166}
167
168static int virtballoon_free_page_report(struct page_reporting_dev_info *pr_dev_info,
169				   struct scatterlist *sg, unsigned int nents)
170{
171	struct virtio_balloon *vb =
172		container_of(pr_dev_info, struct virtio_balloon, pr_dev_info);
173	struct virtqueue *vq = vb->reporting_vq;
174	unsigned int unused, err;
175
176	/* We should always be able to add these buffers to an empty queue. */
177	err = virtqueue_add_inbuf(vq, sg, nents, vb, GFP_NOWAIT | __GFP_NOWARN);
178
179	/*
180	 * In the extremely unlikely case that something has occurred and we
181	 * are able to trigger an error we will simply display a warning
182	 * and exit without actually processing the pages.
183	 */
184	if (WARN_ON_ONCE(err))
185		return err;
186
187	virtqueue_kick(vq);
188
189	/* When host has read buffer, this completes via balloon_ack */
190	wait_event(vb->acked, virtqueue_get_buf(vq, &unused));
191
192	return 0;
193}
194
195static void set_page_pfns(struct virtio_balloon *vb,
196			  __virtio32 pfns[], struct page *page)
197{
198	unsigned int i;
199
200	BUILD_BUG_ON(VIRTIO_BALLOON_PAGES_PER_PAGE > VIRTIO_BALLOON_ARRAY_PFNS_MAX);
201
202	/*
203	 * Set balloon pfns pointing at this page.
204	 * Note that the first pfn points at start of the page.
205	 */
206	for (i = 0; i < VIRTIO_BALLOON_PAGES_PER_PAGE; i++)
207		pfns[i] = cpu_to_virtio32(vb->vdev,
208					  page_to_balloon_pfn(page) + i);
209}
210
211static unsigned fill_balloon(struct virtio_balloon *vb, size_t num)
212{
213	unsigned num_allocated_pages;
214	unsigned num_pfns;
215	struct page *page;
216	LIST_HEAD(pages);
217
218	/* We can only do one array worth at a time. */
219	num = min(num, ARRAY_SIZE(vb->pfns));
220
221	for (num_pfns = 0; num_pfns < num;
222	     num_pfns += VIRTIO_BALLOON_PAGES_PER_PAGE) {
223		struct page *page = balloon_page_alloc();
224
225		if (!page) {
226			dev_info_ratelimited(&vb->vdev->dev,
227					     "Out of puff! Can't get %u pages\n",
228					     VIRTIO_BALLOON_PAGES_PER_PAGE);
229			/* Sleep for at least 1/5 of a second before retry. */
230			msleep(200);
231			break;
232		}
233
234		balloon_page_push(&pages, page);
235	}
236
237	mutex_lock(&vb->balloon_lock);
238
239	vb->num_pfns = 0;
240
241	while ((page = balloon_page_pop(&pages))) {
242		balloon_page_enqueue(&vb->vb_dev_info, page);
243
244		set_page_pfns(vb, vb->pfns + vb->num_pfns, page);
245		vb->num_pages += VIRTIO_BALLOON_PAGES_PER_PAGE;
246		if (!virtio_has_feature(vb->vdev,
247					VIRTIO_BALLOON_F_DEFLATE_ON_OOM))
248			adjust_managed_page_count(page, -1);
249		vb->num_pfns += VIRTIO_BALLOON_PAGES_PER_PAGE;
250	}
251
252	num_allocated_pages = vb->num_pfns;
253	/* Did we get any? */
254	if (vb->num_pfns != 0)
255		tell_host(vb, vb->inflate_vq);
256	mutex_unlock(&vb->balloon_lock);
257
258	return num_allocated_pages;
259}
260
261static void release_pages_balloon(struct virtio_balloon *vb,
262				 struct list_head *pages)
263{
264	struct page *page, *next;
265
266	list_for_each_entry_safe(page, next, pages, lru) {
267		if (!virtio_has_feature(vb->vdev,
268					VIRTIO_BALLOON_F_DEFLATE_ON_OOM))
269			adjust_managed_page_count(page, 1);
270		list_del(&page->lru);
271		put_page(page); /* balloon reference */
272	}
273}
274
275static unsigned leak_balloon(struct virtio_balloon *vb, size_t num)
276{
277	unsigned num_freed_pages;
278	struct page *page;
279	struct balloon_dev_info *vb_dev_info = &vb->vb_dev_info;
280	LIST_HEAD(pages);
281
282	/* We can only do one array worth at a time. */
283	num = min(num, ARRAY_SIZE(vb->pfns));
284
285	mutex_lock(&vb->balloon_lock);
286	/* We can't release more pages than taken */
287	num = min(num, (size_t)vb->num_pages);
288	for (vb->num_pfns = 0; vb->num_pfns < num;
289	     vb->num_pfns += VIRTIO_BALLOON_PAGES_PER_PAGE) {
290		page = balloon_page_dequeue(vb_dev_info);
291		if (!page)
292			break;
293		set_page_pfns(vb, vb->pfns + vb->num_pfns, page);
294		list_add(&page->lru, &pages);
295		vb->num_pages -= VIRTIO_BALLOON_PAGES_PER_PAGE;
296	}
297
298	num_freed_pages = vb->num_pfns;
299	/*
300	 * Note that if
301	 * virtio_has_feature(vdev, VIRTIO_BALLOON_F_MUST_TELL_HOST);
302	 * is true, we *have* to do it in this order
303	 */
304	if (vb->num_pfns != 0)
305		tell_host(vb, vb->deflate_vq);
306	release_pages_balloon(vb, &pages);
307	mutex_unlock(&vb->balloon_lock);
308	return num_freed_pages;
309}
310
311static inline void update_stat(struct virtio_balloon *vb, int idx,
312			       u16 tag, u64 val)
313{
314	BUG_ON(idx >= VIRTIO_BALLOON_S_NR);
315	vb->stats[idx].tag = cpu_to_virtio16(vb->vdev, tag);
316	vb->stats[idx].val = cpu_to_virtio64(vb->vdev, val);
317}
318
319#define pages_to_bytes(x) ((u64)(x) << PAGE_SHIFT)
320
321static unsigned int update_balloon_stats(struct virtio_balloon *vb)
322{
323	unsigned long events[NR_VM_EVENT_ITEMS];
324	struct sysinfo i;
325	unsigned int idx = 0;
326	long available;
327	unsigned long caches;
328
329	all_vm_events(events);
330	si_meminfo(&i);
331
332	available = si_mem_available();
333	caches = global_node_page_state(NR_FILE_PAGES);
334
335#ifdef CONFIG_VM_EVENT_COUNTERS
336	update_stat(vb, idx++, VIRTIO_BALLOON_S_SWAP_IN,
337				pages_to_bytes(events[PSWPIN]));
338	update_stat(vb, idx++, VIRTIO_BALLOON_S_SWAP_OUT,
339				pages_to_bytes(events[PSWPOUT]));
340	update_stat(vb, idx++, VIRTIO_BALLOON_S_MAJFLT, events[PGMAJFAULT]);
341	update_stat(vb, idx++, VIRTIO_BALLOON_S_MINFLT, events[PGFAULT]);
342#ifdef CONFIG_HUGETLB_PAGE
343	update_stat(vb, idx++, VIRTIO_BALLOON_S_HTLB_PGALLOC,
344		    events[HTLB_BUDDY_PGALLOC]);
345	update_stat(vb, idx++, VIRTIO_BALLOON_S_HTLB_PGFAIL,
346		    events[HTLB_BUDDY_PGALLOC_FAIL]);
347#endif
348#endif
349	update_stat(vb, idx++, VIRTIO_BALLOON_S_MEMFREE,
350				pages_to_bytes(i.freeram));
351	update_stat(vb, idx++, VIRTIO_BALLOON_S_MEMTOT,
352				pages_to_bytes(i.totalram));
353	update_stat(vb, idx++, VIRTIO_BALLOON_S_AVAIL,
354				pages_to_bytes(available));
355	update_stat(vb, idx++, VIRTIO_BALLOON_S_CACHES,
356				pages_to_bytes(caches));
357
358	return idx;
359}
360
361/*
362 * While most virtqueues communicate guest-initiated requests to the hypervisor,
363 * the stats queue operates in reverse.  The driver initializes the virtqueue
364 * with a single buffer.  From that point forward, all conversations consist of
365 * a hypervisor request (a call to this function) which directs us to refill
366 * the virtqueue with a fresh stats buffer.  Since stats collection can sleep,
367 * we delegate the job to a freezable workqueue that will do the actual work via
368 * stats_handle_request().
369 */
370static void stats_request(struct virtqueue *vq)
371{
372	struct virtio_balloon *vb = vq->vdev->priv;
373
374	spin_lock(&vb->stop_update_lock);
375	if (!vb->stop_update)
376		queue_work(system_freezable_wq, &vb->update_balloon_stats_work);
377	spin_unlock(&vb->stop_update_lock);
378}
379
380static void stats_handle_request(struct virtio_balloon *vb)
381{
382	struct virtqueue *vq;
383	struct scatterlist sg;
384	unsigned int len, num_stats;
385
386	num_stats = update_balloon_stats(vb);
387
388	vq = vb->stats_vq;
389	if (!virtqueue_get_buf(vq, &len))
390		return;
391	sg_init_one(&sg, vb->stats, sizeof(vb->stats[0]) * num_stats);
392	virtqueue_add_outbuf(vq, &sg, 1, vb, GFP_KERNEL);
393	virtqueue_kick(vq);
394}
395
396static inline s64 towards_target(struct virtio_balloon *vb)
397{
398	s64 target;
399	u32 num_pages;
400
401	/* Legacy balloon config space is LE, unlike all other devices. */
402	virtio_cread_le(vb->vdev, struct virtio_balloon_config, num_pages,
403			&num_pages);
404
405	/*
406	 * Aligned up to guest page size to avoid inflating and deflating
407	 * balloon endlessly.
408	 */
409	target = ALIGN(num_pages, VIRTIO_BALLOON_PAGES_PER_PAGE);
410	return target - vb->num_pages;
411}
412
413/* Gives back @num_to_return blocks of free pages to mm. */
414static unsigned long return_free_pages_to_mm(struct virtio_balloon *vb,
415					     unsigned long num_to_return)
416{
417	struct page *page;
418	unsigned long num_returned;
419
420	spin_lock_irq(&vb->free_page_list_lock);
421	for (num_returned = 0; num_returned < num_to_return; num_returned++) {
422		page = balloon_page_pop(&vb->free_page_list);
423		if (!page)
424			break;
425		free_pages((unsigned long)page_address(page),
426			   VIRTIO_BALLOON_HINT_BLOCK_ORDER);
427	}
428	vb->num_free_page_blocks -= num_returned;
429	spin_unlock_irq(&vb->free_page_list_lock);
430
431	return num_returned;
432}
433
434static void virtio_balloon_queue_free_page_work(struct virtio_balloon *vb)
435{
436	if (!virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_FREE_PAGE_HINT))
437		return;
438
439	/* No need to queue the work if the bit was already set. */
440	if (test_and_set_bit(VIRTIO_BALLOON_CONFIG_READ_CMD_ID,
441			     &vb->config_read_bitmap))
442		return;
443
444	queue_work(vb->balloon_wq, &vb->report_free_page_work);
445}
446
447static void virtballoon_changed(struct virtio_device *vdev)
448{
449	struct virtio_balloon *vb = vdev->priv;
450	unsigned long flags;
451
452	spin_lock_irqsave(&vb->stop_update_lock, flags);
453	if (!vb->stop_update) {
454		queue_work(system_freezable_wq,
455			   &vb->update_balloon_size_work);
456		virtio_balloon_queue_free_page_work(vb);
457	}
458	spin_unlock_irqrestore(&vb->stop_update_lock, flags);
459}
460
461static void update_balloon_size(struct virtio_balloon *vb)
462{
463	u32 actual = vb->num_pages;
464
465	/* Legacy balloon config space is LE, unlike all other devices. */
466	virtio_cwrite_le(vb->vdev, struct virtio_balloon_config, actual,
467			 &actual);
468}
469
470static void update_balloon_stats_func(struct work_struct *work)
471{
472	struct virtio_balloon *vb;
473
474	vb = container_of(work, struct virtio_balloon,
475			  update_balloon_stats_work);
476	stats_handle_request(vb);
477}
478
479static void update_balloon_size_func(struct work_struct *work)
480{
481	struct virtio_balloon *vb;
482	s64 diff;
483
484	vb = container_of(work, struct virtio_balloon,
485			  update_balloon_size_work);
486	diff = towards_target(vb);
487
488	if (!diff)
489		return;
490
491	if (diff > 0)
492		diff -= fill_balloon(vb, diff);
493	else
494		diff += leak_balloon(vb, -diff);
495	update_balloon_size(vb);
496
497	if (diff)
498		queue_work(system_freezable_wq, work);
499}
500
501static int init_vqs(struct virtio_balloon *vb)
502{
503	struct virtqueue *vqs[VIRTIO_BALLOON_VQ_MAX];
504	vq_callback_t *callbacks[VIRTIO_BALLOON_VQ_MAX];
505	const char *names[VIRTIO_BALLOON_VQ_MAX];
506	int err;
507
508	/*
509	 * Inflateq and deflateq are used unconditionally. The names[]
510	 * will be NULL if the related feature is not enabled, which will
511	 * cause no allocation for the corresponding virtqueue in find_vqs.
512	 */
513	callbacks[VIRTIO_BALLOON_VQ_INFLATE] = balloon_ack;
514	names[VIRTIO_BALLOON_VQ_INFLATE] = "inflate";
515	callbacks[VIRTIO_BALLOON_VQ_DEFLATE] = balloon_ack;
516	names[VIRTIO_BALLOON_VQ_DEFLATE] = "deflate";
517	callbacks[VIRTIO_BALLOON_VQ_STATS] = NULL;
518	names[VIRTIO_BALLOON_VQ_STATS] = NULL;
519	callbacks[VIRTIO_BALLOON_VQ_FREE_PAGE] = NULL;
520	names[VIRTIO_BALLOON_VQ_FREE_PAGE] = NULL;
521	names[VIRTIO_BALLOON_VQ_REPORTING] = NULL;
522
523	if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_STATS_VQ)) {
524		names[VIRTIO_BALLOON_VQ_STATS] = "stats";
525		callbacks[VIRTIO_BALLOON_VQ_STATS] = stats_request;
526	}
527
528	if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_FREE_PAGE_HINT)) {
529		names[VIRTIO_BALLOON_VQ_FREE_PAGE] = "free_page_vq";
530		callbacks[VIRTIO_BALLOON_VQ_FREE_PAGE] = NULL;
531	}
532
533	if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_REPORTING)) {
534		names[VIRTIO_BALLOON_VQ_REPORTING] = "reporting_vq";
535		callbacks[VIRTIO_BALLOON_VQ_REPORTING] = balloon_ack;
536	}
537
538	err = vb->vdev->config->find_vqs(vb->vdev, VIRTIO_BALLOON_VQ_MAX,
539					 vqs, callbacks, names, NULL, NULL);
540	if (err)
541		return err;
542
543	vb->inflate_vq = vqs[VIRTIO_BALLOON_VQ_INFLATE];
544	vb->deflate_vq = vqs[VIRTIO_BALLOON_VQ_DEFLATE];
545	if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_STATS_VQ)) {
546		struct scatterlist sg;
547		unsigned int num_stats;
548		vb->stats_vq = vqs[VIRTIO_BALLOON_VQ_STATS];
549
550		/*
551		 * Prime this virtqueue with one buffer so the hypervisor can
552		 * use it to signal us later (it can't be broken yet!).
553		 */
554		num_stats = update_balloon_stats(vb);
555
556		sg_init_one(&sg, vb->stats, sizeof(vb->stats[0]) * num_stats);
557		err = virtqueue_add_outbuf(vb->stats_vq, &sg, 1, vb,
558					   GFP_KERNEL);
559		if (err) {
560			dev_warn(&vb->vdev->dev, "%s: add stat_vq failed\n",
561				 __func__);
562			return err;
563		}
564		virtqueue_kick(vb->stats_vq);
565	}
566
567	if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_FREE_PAGE_HINT))
568		vb->free_page_vq = vqs[VIRTIO_BALLOON_VQ_FREE_PAGE];
569
570	if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_REPORTING))
571		vb->reporting_vq = vqs[VIRTIO_BALLOON_VQ_REPORTING];
572
573	return 0;
574}
575
576static u32 virtio_balloon_cmd_id_received(struct virtio_balloon *vb)
577{
578	if (test_and_clear_bit(VIRTIO_BALLOON_CONFIG_READ_CMD_ID,
579			       &vb->config_read_bitmap)) {
580		/* Legacy balloon config space is LE, unlike all other devices. */
581		virtio_cread_le(vb->vdev, struct virtio_balloon_config,
582				free_page_hint_cmd_id,
583				&vb->cmd_id_received_cache);
584	}
585
586	return vb->cmd_id_received_cache;
587}
588
589static int send_cmd_id_start(struct virtio_balloon *vb)
590{
591	struct scatterlist sg;
592	struct virtqueue *vq = vb->free_page_vq;
593	int err, unused;
594
595	/* Detach all the used buffers from the vq */
596	while (virtqueue_get_buf(vq, &unused))
597		;
598
599	vb->cmd_id_active = cpu_to_virtio32(vb->vdev,
600					virtio_balloon_cmd_id_received(vb));
601	sg_init_one(&sg, &vb->cmd_id_active, sizeof(vb->cmd_id_active));
602	err = virtqueue_add_outbuf(vq, &sg, 1, &vb->cmd_id_active, GFP_KERNEL);
603	if (!err)
604		virtqueue_kick(vq);
605	return err;
606}
607
608static int send_cmd_id_stop(struct virtio_balloon *vb)
609{
610	struct scatterlist sg;
611	struct virtqueue *vq = vb->free_page_vq;
612	int err, unused;
613
614	/* Detach all the used buffers from the vq */
615	while (virtqueue_get_buf(vq, &unused))
616		;
617
618	sg_init_one(&sg, &vb->cmd_id_stop, sizeof(vb->cmd_id_stop));
619	err = virtqueue_add_outbuf(vq, &sg, 1, &vb->cmd_id_stop, GFP_KERNEL);
620	if (!err)
621		virtqueue_kick(vq);
622	return err;
623}
624
625static int get_free_page_and_send(struct virtio_balloon *vb)
626{
627	struct virtqueue *vq = vb->free_page_vq;
628	struct page *page;
629	struct scatterlist sg;
630	int err, unused;
631	void *p;
632
633	/* Detach all the used buffers from the vq */
634	while (virtqueue_get_buf(vq, &unused))
635		;
636
637	page = alloc_pages(VIRTIO_BALLOON_FREE_PAGE_ALLOC_FLAG,
638			   VIRTIO_BALLOON_HINT_BLOCK_ORDER);
639	/*
640	 * When the allocation returns NULL, it indicates that we have got all
641	 * the possible free pages, so return -EINTR to stop.
642	 */
643	if (!page)
644		return -EINTR;
645
646	p = page_address(page);
647	sg_init_one(&sg, p, VIRTIO_BALLOON_HINT_BLOCK_BYTES);
648	/* There is always 1 entry reserved for the cmd id to use. */
649	if (vq->num_free > 1) {
650		err = virtqueue_add_inbuf(vq, &sg, 1, p, GFP_KERNEL);
651		if (unlikely(err)) {
652			free_pages((unsigned long)p,
653				   VIRTIO_BALLOON_HINT_BLOCK_ORDER);
654			return err;
655		}
656		virtqueue_kick(vq);
657		spin_lock_irq(&vb->free_page_list_lock);
658		balloon_page_push(&vb->free_page_list, page);
659		vb->num_free_page_blocks++;
660		spin_unlock_irq(&vb->free_page_list_lock);
661	} else {
662		/*
663		 * The vq has no available entry to add this page block, so
664		 * just free it.
665		 */
666		free_pages((unsigned long)p, VIRTIO_BALLOON_HINT_BLOCK_ORDER);
667	}
668
669	return 0;
670}
671
672static int send_free_pages(struct virtio_balloon *vb)
673{
674	int err;
675	u32 cmd_id_active;
676
677	while (1) {
678		/*
679		 * If a stop id or a new cmd id was just received from host,
680		 * stop the reporting.
681		 */
682		cmd_id_active = virtio32_to_cpu(vb->vdev, vb->cmd_id_active);
683		if (unlikely(cmd_id_active !=
684			     virtio_balloon_cmd_id_received(vb)))
685			break;
686
687		/*
688		 * The free page blocks are allocated and sent to host one by
689		 * one.
690		 */
691		err = get_free_page_and_send(vb);
692		if (err == -EINTR)
693			break;
694		else if (unlikely(err))
695			return err;
696	}
697
698	return 0;
699}
700
701static void virtio_balloon_report_free_page(struct virtio_balloon *vb)
702{
703	int err;
704	struct device *dev = &vb->vdev->dev;
705
706	/* Start by sending the received cmd id to host with an outbuf. */
707	err = send_cmd_id_start(vb);
708	if (unlikely(err))
709		dev_err(dev, "Failed to send a start id, err = %d\n", err);
710
711	err = send_free_pages(vb);
712	if (unlikely(err))
713		dev_err(dev, "Failed to send a free page, err = %d\n", err);
714
715	/* End by sending a stop id to host with an outbuf. */
716	err = send_cmd_id_stop(vb);
717	if (unlikely(err))
718		dev_err(dev, "Failed to send a stop id, err = %d\n", err);
719}
720
721static void report_free_page_func(struct work_struct *work)
722{
723	struct virtio_balloon *vb = container_of(work, struct virtio_balloon,
724						 report_free_page_work);
725	u32 cmd_id_received;
726
727	cmd_id_received = virtio_balloon_cmd_id_received(vb);
728	if (cmd_id_received == VIRTIO_BALLOON_CMD_ID_DONE) {
729		/* Pass ULONG_MAX to give back all the free pages */
730		return_free_pages_to_mm(vb, ULONG_MAX);
731	} else if (cmd_id_received != VIRTIO_BALLOON_CMD_ID_STOP &&
732		   cmd_id_received !=
733		   virtio32_to_cpu(vb->vdev, vb->cmd_id_active)) {
734		virtio_balloon_report_free_page(vb);
735	}
736}
737
738#ifdef CONFIG_BALLOON_COMPACTION
739/*
740 * virtballoon_migratepage - perform the balloon page migration on behalf of
741 *			     a compation thread.     (called under page lock)
742 * @vb_dev_info: the balloon device
743 * @newpage: page that will replace the isolated page after migration finishes.
744 * @page   : the isolated (old) page that is about to be migrated to newpage.
745 * @mode   : compaction mode -- not used for balloon page migration.
746 *
747 * After a ballooned page gets isolated by compaction procedures, this is the
748 * function that performs the page migration on behalf of a compaction thread
749 * The page migration for virtio balloon is done in a simple swap fashion which
750 * follows these two macro steps:
751 *  1) insert newpage into vb->pages list and update the host about it;
752 *  2) update the host about the old page removed from vb->pages list;
753 *
754 * This function preforms the balloon page migration task.
755 * Called through balloon_mapping->a_ops->migratepage
756 */
757static int virtballoon_migratepage(struct balloon_dev_info *vb_dev_info,
758		struct page *newpage, struct page *page, enum migrate_mode mode)
759{
760	struct virtio_balloon *vb = container_of(vb_dev_info,
761			struct virtio_balloon, vb_dev_info);
762	unsigned long flags;
763
764	/*
765	 * In order to avoid lock contention while migrating pages concurrently
766	 * to leak_balloon() or fill_balloon() we just give up the balloon_lock
767	 * this turn, as it is easier to retry the page migration later.
768	 * This also prevents fill_balloon() getting stuck into a mutex
769	 * recursion in the case it ends up triggering memory compaction
770	 * while it is attempting to inflate the ballon.
771	 */
772	if (!mutex_trylock(&vb->balloon_lock))
773		return -EAGAIN;
774
775	get_page(newpage); /* balloon reference */
776
777	/*
778	  * When we migrate a page to a different zone and adjusted the
779	  * managed page count when inflating, we have to fixup the count of
780	  * both involved zones.
781	  */
782	if (!virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_DEFLATE_ON_OOM) &&
783	    page_zone(page) != page_zone(newpage)) {
784		adjust_managed_page_count(page, 1);
785		adjust_managed_page_count(newpage, -1);
786	}
787
788	/* balloon's page migration 1st step  -- inflate "newpage" */
789	spin_lock_irqsave(&vb_dev_info->pages_lock, flags);
790	balloon_page_insert(vb_dev_info, newpage);
791	vb_dev_info->isolated_pages--;
792	__count_vm_event(BALLOON_MIGRATE);
793	spin_unlock_irqrestore(&vb_dev_info->pages_lock, flags);
794	vb->num_pfns = VIRTIO_BALLOON_PAGES_PER_PAGE;
795	set_page_pfns(vb, vb->pfns, newpage);
796	tell_host(vb, vb->inflate_vq);
797
798	/* balloon's page migration 2nd step -- deflate "page" */
799	spin_lock_irqsave(&vb_dev_info->pages_lock, flags);
800	balloon_page_delete(page);
801	spin_unlock_irqrestore(&vb_dev_info->pages_lock, flags);
802	vb->num_pfns = VIRTIO_BALLOON_PAGES_PER_PAGE;
803	set_page_pfns(vb, vb->pfns, page);
804	tell_host(vb, vb->deflate_vq);
805
806	mutex_unlock(&vb->balloon_lock);
807
808	put_page(page); /* balloon reference */
809
810	return MIGRATEPAGE_SUCCESS;
811}
812
813static int balloon_init_fs_context(struct fs_context *fc)
814{
815	return init_pseudo(fc, BALLOON_KVM_MAGIC) ? 0 : -ENOMEM;
816}
817
818static struct file_system_type balloon_fs = {
819	.name           = "balloon-kvm",
820	.init_fs_context = balloon_init_fs_context,
821	.kill_sb        = kill_anon_super,
822};
823
824#endif /* CONFIG_BALLOON_COMPACTION */
825
826static unsigned long shrink_free_pages(struct virtio_balloon *vb,
827				       unsigned long pages_to_free)
828{
829	unsigned long blocks_to_free, blocks_freed;
830
831	pages_to_free = round_up(pages_to_free,
832				 VIRTIO_BALLOON_HINT_BLOCK_PAGES);
833	blocks_to_free = pages_to_free / VIRTIO_BALLOON_HINT_BLOCK_PAGES;
834	blocks_freed = return_free_pages_to_mm(vb, blocks_to_free);
835
836	return blocks_freed * VIRTIO_BALLOON_HINT_BLOCK_PAGES;
837}
838
839static unsigned long virtio_balloon_shrinker_scan(struct shrinker *shrinker,
840						  struct shrink_control *sc)
841{
842	struct virtio_balloon *vb = container_of(shrinker,
843					struct virtio_balloon, shrinker);
844
845	return shrink_free_pages(vb, sc->nr_to_scan);
846}
847
848static unsigned long virtio_balloon_shrinker_count(struct shrinker *shrinker,
849						   struct shrink_control *sc)
850{
851	struct virtio_balloon *vb = container_of(shrinker,
852					struct virtio_balloon, shrinker);
853
854	return vb->num_free_page_blocks * VIRTIO_BALLOON_HINT_BLOCK_PAGES;
855}
856
857static int virtio_balloon_oom_notify(struct notifier_block *nb,
858				     unsigned long dummy, void *parm)
859{
860	struct virtio_balloon *vb = container_of(nb,
861						 struct virtio_balloon, oom_nb);
862	unsigned long *freed = parm;
863
864	*freed += leak_balloon(vb, VIRTIO_BALLOON_OOM_NR_PAGES) /
865		  VIRTIO_BALLOON_PAGES_PER_PAGE;
866	update_balloon_size(vb);
867
868	return NOTIFY_OK;
869}
870
871static void virtio_balloon_unregister_shrinker(struct virtio_balloon *vb)
872{
873	unregister_shrinker(&vb->shrinker);
874}
875
876static int virtio_balloon_register_shrinker(struct virtio_balloon *vb)
877{
878	vb->shrinker.scan_objects = virtio_balloon_shrinker_scan;
879	vb->shrinker.count_objects = virtio_balloon_shrinker_count;
880	vb->shrinker.seeks = DEFAULT_SEEKS;
881
882	return register_shrinker(&vb->shrinker);
883}
884
885static int virtballoon_probe(struct virtio_device *vdev)
886{
887	struct virtio_balloon *vb;
888	int err;
889
890	if (!vdev->config->get) {
891		dev_err(&vdev->dev, "%s failure: config access disabled\n",
892			__func__);
893		return -EINVAL;
894	}
895
896	vdev->priv = vb = kzalloc(sizeof(*vb), GFP_KERNEL);
897	if (!vb) {
898		err = -ENOMEM;
899		goto out;
900	}
901
902	INIT_WORK(&vb->update_balloon_stats_work, update_balloon_stats_func);
903	INIT_WORK(&vb->update_balloon_size_work, update_balloon_size_func);
904	spin_lock_init(&vb->stop_update_lock);
905	mutex_init(&vb->balloon_lock);
906	init_waitqueue_head(&vb->acked);
907	vb->vdev = vdev;
908
909	balloon_devinfo_init(&vb->vb_dev_info);
910
911	err = init_vqs(vb);
912	if (err)
913		goto out_free_vb;
914
915#ifdef CONFIG_BALLOON_COMPACTION
916	balloon_mnt = kern_mount(&balloon_fs);
917	if (IS_ERR(balloon_mnt)) {
918		err = PTR_ERR(balloon_mnt);
919		goto out_del_vqs;
920	}
921
922	vb->vb_dev_info.migratepage = virtballoon_migratepage;
923	vb->vb_dev_info.inode = alloc_anon_inode(balloon_mnt->mnt_sb);
924	if (IS_ERR(vb->vb_dev_info.inode)) {
925		err = PTR_ERR(vb->vb_dev_info.inode);
926		goto out_kern_unmount;
927	}
928	vb->vb_dev_info.inode->i_mapping->a_ops = &balloon_aops;
929#endif
930	if (virtio_has_feature(vdev, VIRTIO_BALLOON_F_FREE_PAGE_HINT)) {
931		/*
932		 * There is always one entry reserved for cmd id, so the ring
933		 * size needs to be at least two to report free page hints.
934		 */
935		if (virtqueue_get_vring_size(vb->free_page_vq) < 2) {
936			err = -ENOSPC;
937			goto out_iput;
938		}
939		vb->balloon_wq = alloc_workqueue("balloon-wq",
940					WQ_FREEZABLE | WQ_CPU_INTENSIVE, 0);
941		if (!vb->balloon_wq) {
942			err = -ENOMEM;
943			goto out_iput;
944		}
945		INIT_WORK(&vb->report_free_page_work, report_free_page_func);
946		vb->cmd_id_received_cache = VIRTIO_BALLOON_CMD_ID_STOP;
947		vb->cmd_id_active = cpu_to_virtio32(vb->vdev,
948						  VIRTIO_BALLOON_CMD_ID_STOP);
949		vb->cmd_id_stop = cpu_to_virtio32(vb->vdev,
950						  VIRTIO_BALLOON_CMD_ID_STOP);
951		spin_lock_init(&vb->free_page_list_lock);
952		INIT_LIST_HEAD(&vb->free_page_list);
953		/*
954		 * We're allowed to reuse any free pages, even if they are
955		 * still to be processed by the host.
956		 */
957		err = virtio_balloon_register_shrinker(vb);
958		if (err)
959			goto out_del_balloon_wq;
960	}
961
962	if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_DEFLATE_ON_OOM)) {
963		vb->oom_nb.notifier_call = virtio_balloon_oom_notify;
964		vb->oom_nb.priority = VIRTIO_BALLOON_OOM_NOTIFY_PRIORITY;
965		err = register_oom_notifier(&vb->oom_nb);
966		if (err < 0)
967			goto out_unregister_shrinker;
968	}
969
970	if (virtio_has_feature(vdev, VIRTIO_BALLOON_F_PAGE_POISON)) {
971		/* Start with poison val of 0 representing general init */
972		__u32 poison_val = 0;
973
974		/*
975		 * Let the hypervisor know that we are expecting a
976		 * specific value to be written back in balloon pages.
977		 *
978		 * If the PAGE_POISON value was larger than a byte we would
979		 * need to byte swap poison_val here to guarantee it is
980		 * little-endian. However for now it is a single byte so we
981		 * can pass it as-is.
982		 */
983		if (!want_init_on_free())
984			memset(&poison_val, PAGE_POISON, sizeof(poison_val));
985
986		virtio_cwrite_le(vb->vdev, struct virtio_balloon_config,
987				 poison_val, &poison_val);
988	}
989
990	vb->pr_dev_info.report = virtballoon_free_page_report;
991	if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_REPORTING)) {
992		unsigned int capacity;
993
994		capacity = virtqueue_get_vring_size(vb->reporting_vq);
995		if (capacity < PAGE_REPORTING_CAPACITY) {
996			err = -ENOSPC;
997			goto out_unregister_oom;
998		}
999
1000		err = page_reporting_register(&vb->pr_dev_info);
1001		if (err)
1002			goto out_unregister_oom;
1003	}
1004
1005	virtio_device_ready(vdev);
1006
1007	if (towards_target(vb))
1008		virtballoon_changed(vdev);
1009	return 0;
1010
1011out_unregister_oom:
1012	if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_DEFLATE_ON_OOM))
1013		unregister_oom_notifier(&vb->oom_nb);
1014out_unregister_shrinker:
1015	if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_FREE_PAGE_HINT))
1016		virtio_balloon_unregister_shrinker(vb);
1017out_del_balloon_wq:
1018	if (virtio_has_feature(vdev, VIRTIO_BALLOON_F_FREE_PAGE_HINT))
1019		destroy_workqueue(vb->balloon_wq);
1020out_iput:
1021#ifdef CONFIG_BALLOON_COMPACTION
1022	iput(vb->vb_dev_info.inode);
1023out_kern_unmount:
1024	kern_unmount(balloon_mnt);
1025out_del_vqs:
1026#endif
1027	vdev->config->del_vqs(vdev);
1028out_free_vb:
1029	kfree(vb);
1030out:
1031	return err;
1032}
1033
1034static void remove_common(struct virtio_balloon *vb)
1035{
1036	/* There might be pages left in the balloon: free them. */
1037	while (vb->num_pages)
1038		leak_balloon(vb, vb->num_pages);
1039	update_balloon_size(vb);
1040
1041	/* There might be free pages that are being reported: release them. */
1042	if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_FREE_PAGE_HINT))
1043		return_free_pages_to_mm(vb, ULONG_MAX);
1044
1045	/* Now we reset the device so we can clean up the queues. */
1046	vb->vdev->config->reset(vb->vdev);
1047
1048	vb->vdev->config->del_vqs(vb->vdev);
1049}
1050
1051static void virtballoon_remove(struct virtio_device *vdev)
1052{
1053	struct virtio_balloon *vb = vdev->priv;
1054
1055	if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_REPORTING))
1056		page_reporting_unregister(&vb->pr_dev_info);
1057	if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_DEFLATE_ON_OOM))
1058		unregister_oom_notifier(&vb->oom_nb);
1059	if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_FREE_PAGE_HINT))
1060		virtio_balloon_unregister_shrinker(vb);
1061	spin_lock_irq(&vb->stop_update_lock);
1062	vb->stop_update = true;
1063	spin_unlock_irq(&vb->stop_update_lock);
1064	cancel_work_sync(&vb->update_balloon_size_work);
1065	cancel_work_sync(&vb->update_balloon_stats_work);
1066
1067	if (virtio_has_feature(vdev, VIRTIO_BALLOON_F_FREE_PAGE_HINT)) {
1068		cancel_work_sync(&vb->report_free_page_work);
1069		destroy_workqueue(vb->balloon_wq);
1070	}
1071
1072	remove_common(vb);
1073#ifdef CONFIG_BALLOON_COMPACTION
1074	if (vb->vb_dev_info.inode)
1075		iput(vb->vb_dev_info.inode);
1076
1077	kern_unmount(balloon_mnt);
1078#endif
1079	kfree(vb);
1080}
1081
1082#ifdef CONFIG_PM_SLEEP
1083static int virtballoon_freeze(struct virtio_device *vdev)
1084{
1085	struct virtio_balloon *vb = vdev->priv;
1086
1087	/*
1088	 * The workqueue is already frozen by the PM core before this
1089	 * function is called.
1090	 */
1091	remove_common(vb);
1092	return 0;
1093}
1094
1095static int virtballoon_restore(struct virtio_device *vdev)
1096{
1097	struct virtio_balloon *vb = vdev->priv;
1098	int ret;
1099
1100	ret = init_vqs(vdev->priv);
1101	if (ret)
1102		return ret;
1103
1104	virtio_device_ready(vdev);
1105
1106	if (towards_target(vb))
1107		virtballoon_changed(vdev);
1108	update_balloon_size(vb);
1109	return 0;
1110}
1111#endif
1112
1113static int virtballoon_validate(struct virtio_device *vdev)
1114{
1115	/*
1116	 * Inform the hypervisor that our pages are poisoned or
1117	 * initialized. If we cannot do that then we should disable
1118	 * page reporting as it could potentially change the contents
1119	 * of our free pages.
1120	 */
1121	if (!want_init_on_free() &&
1122	    (IS_ENABLED(CONFIG_PAGE_POISONING_NO_SANITY) ||
1123	     !page_poisoning_enabled()))
1124		__virtio_clear_bit(vdev, VIRTIO_BALLOON_F_PAGE_POISON);
1125	else if (!virtio_has_feature(vdev, VIRTIO_BALLOON_F_PAGE_POISON))
1126		__virtio_clear_bit(vdev, VIRTIO_BALLOON_F_REPORTING);
1127
1128	__virtio_clear_bit(vdev, VIRTIO_F_ACCESS_PLATFORM);
1129	return 0;
1130}
1131
1132static unsigned int features[] = {
1133	VIRTIO_BALLOON_F_MUST_TELL_HOST,
1134	VIRTIO_BALLOON_F_STATS_VQ,
1135	VIRTIO_BALLOON_F_DEFLATE_ON_OOM,
1136	VIRTIO_BALLOON_F_FREE_PAGE_HINT,
1137	VIRTIO_BALLOON_F_PAGE_POISON,
1138	VIRTIO_BALLOON_F_REPORTING,
1139};
1140
1141static struct virtio_driver virtio_balloon_driver = {
1142	.feature_table = features,
1143	.feature_table_size = ARRAY_SIZE(features),
1144	.driver.name =	KBUILD_MODNAME,
1145	.driver.owner =	THIS_MODULE,
1146	.id_table =	id_table,
1147	.validate =	virtballoon_validate,
1148	.probe =	virtballoon_probe,
1149	.remove =	virtballoon_remove,
1150	.config_changed = virtballoon_changed,
1151#ifdef CONFIG_PM_SLEEP
1152	.freeze	=	virtballoon_freeze,
1153	.restore =	virtballoon_restore,
1154#endif
1155};
1156
1157module_virtio_driver(virtio_balloon_driver);
1158MODULE_DEVICE_TABLE(virtio, id_table);
1159MODULE_DESCRIPTION("Virtio balloon driver");
1160MODULE_LICENSE("GPL");
1161