1 files changed, 231 insertions, 105 deletions

diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c
index 95aeedf198f..25ebe8eecdb 100644
--- a/drivers/virtio/virtio_balloon.c
+++ b/drivers/virtio/virtio_balloon.c
@@ -27,6 +27,15 @@
 #include <linux/delay.h>
 #include <linux/slab.h>
 #include <linux/module.h>
+#include <linux/balloon_compaction.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
 
 struct virtio_balloon
 {
@@ -40,15 +49,24 @@ struct virtio_balloon
 	struct task_struct *thread;
 
 	/* Waiting for host to ack the pages we released. */
-	struct completion acked;
+	wait_queue_head_t acked;
 
-	/* The pages we've told the Host we're not using. */
+	/* Number of balloon pages we've told the Host we're not using. */
 	unsigned int num_pages;
-	struct list_head 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;
-	u32 pfns[256];
+	u32 pfns[VIRTIO_BALLOON_ARRAY_PFNS_MAX];
 
 	/* Memory statistics */
 	int need_stats_update;
@@ -66,88 +84,106 @@ static u32 page_to_balloon_pfn(struct page *page)
 
 	BUILD_BUG_ON(PAGE_SHIFT < VIRTIO_BALLOON_PFN_SHIFT);
 	/* Convert pfn from Linux page size to balloon page size. */
-	return pfn >> (PAGE_SHIFT - VIRTIO_BALLOON_PFN_SHIFT);
+	return pfn * VIRTIO_BALLOON_PAGES_PER_PAGE;
+}
+
+static struct page *balloon_pfn_to_page(u32 pfn)
+{
+	BUG_ON(pfn % VIRTIO_BALLOON_PAGES_PER_PAGE);
+	return pfn_to_page(pfn / VIRTIO_BALLOON_PAGES_PER_PAGE);
 }
 
 static void balloon_ack(struct virtqueue *vq)
 {
-	struct virtio_balloon *vb;
-	unsigned int len;
+	struct virtio_balloon *vb = vq->vdev->priv;
 
-	vb = virtqueue_get_buf(vq, &len);
-	if (vb)
-		complete(&vb->acked);
+	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);
 
-	init_completion(&vb->acked);
-
 	/* We should always be able to add one buffer to an empty queue. */
-	if (virtqueue_add_buf(vq, &sg, 1, 0, vb, GFP_KERNEL) < 0)
-		BUG();
+	virtqueue_add_outbuf(vq, &sg, 1, vb, GFP_KERNEL);
 	virtqueue_kick(vq);
 
 	/* When host has read buffer, this completes via balloon_ack */
-	wait_for_completion(&vb->acked);
+	wait_event(vb->acked, virtqueue_get_buf(vq, &len));
+}
+
+static void set_page_pfns(u32 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] = page_to_balloon_pfn(page) + i;
 }
 
 static void fill_balloon(struct virtio_balloon *vb, size_t num)
 {
+	struct balloon_dev_info *vb_dev_info = vb->vb_dev_info;
+
 	/* We can only do one array worth at a time. */
 	num = min(num, ARRAY_SIZE(vb->pfns));
 
-	for (vb->num_pfns = 0; vb->num_pfns < num; vb->num_pfns++) {
-		struct page *page = alloc_page(GFP_HIGHUSER | __GFP_NORETRY |
-					__GFP_NOMEMALLOC | __GFP_NOWARN);
+	mutex_lock(&vb->balloon_lock);
+	for (vb->num_pfns = 0; vb->num_pfns < num;
+	     vb->num_pfns += VIRTIO_BALLOON_PAGES_PER_PAGE) {
+		struct page *page = balloon_page_enqueue(vb_dev_info);
+
 		if (!page) {
-			if (printk_ratelimit())
-				dev_printk(KERN_INFO, &vb->vdev->dev,
-					   "Out of puff! Can't get %zu pages\n",
-					   num);
+			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;
 		}
-		vb->pfns[vb->num_pfns] = page_to_balloon_pfn(page);
-		totalram_pages--;
-		vb->num_pages++;
-		list_add(&page->lru, &vb->pages);
+		set_page_pfns(vb->pfns + vb->num_pfns, page);
+		vb->num_pages += VIRTIO_BALLOON_PAGES_PER_PAGE;
+		adjust_managed_page_count(page, -1);
 	}
 
-	/* Didn't get any?  Oh well. */
-	if (vb->num_pfns == 0)
-		return;
-
-	tell_host(vb, vb->inflate_vq);
+	/* Did we get any? */
+	if (vb->num_pfns != 0)
+		tell_host(vb, vb->inflate_vq);
+	mutex_unlock(&vb->balloon_lock);
 }
 
 static void release_pages_by_pfn(const u32 pfns[], unsigned int num)
 {
 	unsigned int i;
 
-	for (i = 0; i < num; i++) {
-		__free_page(pfn_to_page(pfns[i]));
-		totalram_pages++;
+	/* Find pfns pointing at start of each page, get pages and free them. */
+	for (i = 0; i < num; i += VIRTIO_BALLOON_PAGES_PER_PAGE) {
+		struct page *page = balloon_pfn_to_page(pfns[i]);
+		balloon_page_free(page);
+		adjust_managed_page_count(page, 1);
 	}
 }
 
 static void leak_balloon(struct virtio_balloon *vb, size_t num)
 {
 	struct page *page;
+	struct balloon_dev_info *vb_dev_info = vb->vb_dev_info;
 
 	/* We can only do one array worth at a time. */
 	num = min(num, ARRAY_SIZE(vb->pfns));
 
-	for (vb->num_pfns = 0; vb->num_pfns < num; vb->num_pfns++) {
-		page = list_first_entry(&vb->pages, struct page, lru);
-		list_del(&page->lru);
-		vb->pfns[vb->num_pfns] = page_to_balloon_pfn(page);
-		vb->num_pages--;
+	mutex_lock(&vb->balloon_lock);
+	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->pfns + vb->num_pfns, page);
+		vb->num_pages -= VIRTIO_BALLOON_PAGES_PER_PAGE;
 	}
 
 	/*
@@ -155,7 +191,9 @@ static void leak_balloon(struct virtio_balloon *vb, size_t num)
 	 * virtio_has_feature(vdev, VIRTIO_BALLOON_F_MUST_TELL_HOST);
 	 * is true, we *have* to do it in this order
 	 */
-	tell_host(vb, vb->deflate_vq);
+	if (vb->num_pfns != 0)
+		tell_host(vb, vb->deflate_vq);
+	mutex_unlock(&vb->balloon_lock);
 	release_pages_by_pfn(vb->pfns, vb->num_pfns);
 }
 
@@ -200,12 +238,8 @@ static void update_balloon_stats(struct virtio_balloon *vb)
  */
 static void stats_request(struct virtqueue *vq)
 {
-	struct virtio_balloon *vb;
-	unsigned int len;
+	struct virtio_balloon *vb = vq->vdev->priv;
 
-	vb = virtqueue_get_buf(vq, &len);
-	if (!vb)
-		return;
 	vb->need_stats_update = 1;
 	wake_up(&vb->config_change);
 }
@@ -214,14 +248,16 @@ static void stats_handle_request(struct virtio_balloon *vb)
 {
 	struct virtqueue *vq;
 	struct scatterlist sg;
+	unsigned int len;
 
 	vb->need_stats_update = 0;
 	update_balloon_stats(vb);
 
 	vq = vb->stats_vq;
+	if (!virtqueue_get_buf(vq, &len))
+		return;
 	sg_init_one(&sg, vb->stats, sizeof(vb->stats));
-	if (virtqueue_add_buf(vq, &sg, 1, 0, vb, GFP_KERNEL) < 0)
-		BUG();
+	virtqueue_add_outbuf(vq, &sg, 1, vb, GFP_KERNEL);
 	virtqueue_kick(vq);
 }
 
@@ -234,20 +270,21 @@ static void virtballoon_changed(struct virtio_device *vdev)
 
 static inline s64 towards_target(struct virtio_balloon *vb)
 {
-	u32 v;
-	vb->vdev->config->get(vb->vdev,
-			      offsetof(struct virtio_balloon_config, num_pages),
-			      &v, sizeof(v));
-	return (s64)v - vb->num_pages;
+	__le32 v;
+	s64 target;
+
+	virtio_cread(vb->vdev, struct virtio_balloon_config, num_pages, &v);
+
+	target = le32_to_cpu(v);
+	return target - vb->num_pages;
 }
 
 static void update_balloon_size(struct virtio_balloon *vb)
 {
 	__le32 actual = cpu_to_le32(vb->num_pages);
 
-	vb->vdev->config->set(vb->vdev,
-			      offsetof(struct virtio_balloon_config, actual),
-			      &actual, sizeof(actual));
+	virtio_cwrite(vb->vdev, struct virtio_balloon_config, actual,
+		      &actual);
 }
 
 static int balloon(void *_vballoon)
@@ -271,6 +308,12 @@ static int balloon(void *_vballoon)
 		else if (diff < 0)
 			leak_balloon(vb, -diff);
 		update_balloon_size(vb);
+
+		/*
+		 * For large balloon changes, we could spend a lot of time
+		 * and always have work to do.  Be nice if preempt disabled.
+		 */
+		cond_resched();
 	}
 	return 0;
 }
@@ -299,10 +342,10 @@ static int init_vqs(struct virtio_balloon *vb)
 
 		/*
 		 * Prime this virtqueue with one buffer so the hypervisor can
-		 * use it to signal us later.
+		 * use it to signal us later (it can't be broken yet!).
 		 */
 		sg_init_one(&sg, vb->stats, sizeof vb->stats);
-		if (virtqueue_add_buf(vb->stats_vq, &sg, 1, 0, vb, GFP_KERNEL)
+		if (virtqueue_add_outbuf(vb->stats_vq, &sg, 1, vb, GFP_KERNEL)
 		    < 0)
 			BUG();
 		virtqueue_kick(vb->stats_vq);
@@ -310,9 +353,84 @@ static int init_vqs(struct virtio_balloon *vb)
 	return 0;
 }
 
+static const struct address_space_operations virtio_balloon_aops;
+#ifdef CONFIG_BALLOON_COMPACTION
+/*
+ * virtballoon_migratepage - perform the balloon page migration on behalf of
+ *			     a compation thread.     (called under page lock)
+ * @mapping: the page->mapping which will be assigned to the new migrated page.
+ * @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 address_space *mapping,
+		struct page *newpage, struct page *page, enum migrate_mode mode)
+{
+	struct balloon_dev_info *vb_dev_info = balloon_page_device(page);
+	struct virtio_balloon *vb;
+	unsigned long flags;
+
+	BUG_ON(!vb_dev_info);
+
+	vb = vb_dev_info->balloon_device;
+
+	/*
+	 * 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;
+
+	/* balloon's page migration 1st step  -- inflate "newpage" */
+	spin_lock_irqsave(&vb_dev_info->pages_lock, flags);
+	balloon_page_insert(newpage, mapping, &vb_dev_info->pages);
+	vb_dev_info->isolated_pages--;
+	spin_unlock_irqrestore(&vb_dev_info->pages_lock, flags);
+	vb->num_pfns = VIRTIO_BALLOON_PAGES_PER_PAGE;
+	set_page_pfns(vb->pfns, newpage);
+	tell_host(vb, vb->inflate_vq);
+
+	/*
+	 * balloon's page migration 2nd step -- deflate "page"
+	 *
+	 * It's safe to delete page->lru here because this page is at
+	 * an isolated migration list, and this step is expected to happen here
+	 */
+	balloon_page_delete(page);
+	vb->num_pfns = VIRTIO_BALLOON_PAGES_PER_PAGE;
+	set_page_pfns(vb->pfns, page);
+	tell_host(vb, vb->deflate_vq);
+
+	mutex_unlock(&vb->balloon_lock);
+
+	return MIGRATEPAGE_BALLOON_SUCCESS;
+}
+
+/* define the balloon_mapping->a_ops callback to allow balloon page migration */
+static const struct address_space_operations virtio_balloon_aops = {
+			.migratepage = virtballoon_migratepage,
+};
+#endif /* CONFIG_BALLOON_COMPACTION */
+
 static int virtballoon_probe(struct virtio_device *vdev)
 {
 	struct virtio_balloon *vb;
+	struct address_space *vb_mapping;
+	struct balloon_dev_info *vb_devinfo;
 	int err;
 
 	vdev->priv = vb = kmalloc(sizeof(*vb), GFP_KERNEL);
@@ -321,15 +439,37 @@ static int virtballoon_probe(struct virtio_device *vdev)
 		goto out;
 	}
 
-	INIT_LIST_HEAD(&vb->pages);
 	vb->num_pages = 0;
+	mutex_init(&vb->balloon_lock);
 	init_waitqueue_head(&vb->config_change);
+	init_waitqueue_head(&vb->acked);
 	vb->vdev = vdev;
 	vb->need_stats_update = 0;
 
+	vb_devinfo = balloon_devinfo_alloc(vb);
+	if (IS_ERR(vb_devinfo)) {
+		err = PTR_ERR(vb_devinfo);
+		goto out_free_vb;
+	}
+
+	vb_mapping = balloon_mapping_alloc(vb_devinfo,
+					   (balloon_compaction_check()) ?
+					   &virtio_balloon_aops : NULL);
+	if (IS_ERR(vb_mapping)) {
+		/*
+		 * IS_ERR(vb_mapping) && PTR_ERR(vb_mapping) == -EOPNOTSUPP
+		 * This means !CONFIG_BALLOON_COMPACTION, otherwise we get off.
+		 */
+		err = PTR_ERR(vb_mapping);
+		if (err != -EOPNOTSUPP)
+			goto out_free_vb_devinfo;
+	}
+
+	vb->vb_dev_info = vb_devinfo;
+
 	err = init_vqs(vb);
 	if (err)
-		goto out_free_vb;
+		goto out_free_vb_mapping;
 
 	vb->thread = kthread_run(balloon, vb, "vballoon");
 	if (IS_ERR(vb->thread)) {
@@ -341,68 +481,66 @@ static int virtballoon_probe(struct virtio_device *vdev)
 
 out_del_vqs:
 	vdev->config->del_vqs(vdev);
+out_free_vb_mapping:
+	balloon_mapping_free(vb_mapping);
+out_free_vb_devinfo:
+	balloon_devinfo_free(vb_devinfo);
 out_free_vb:
 	kfree(vb);
 out:
 	return err;
 }
 
-static void __devexit virtballoon_remove(struct virtio_device *vdev)
+static void remove_common(struct virtio_balloon *vb)
 {
-	struct virtio_balloon *vb = vdev->priv;
-
-	kthread_stop(vb->thread);
-
 	/* 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. */
-	vdev->config->reset(vdev);
+	vb->vdev->config->reset(vb->vdev);
 
-	vdev->config->del_vqs(vdev);
+	vb->vdev->config->del_vqs(vb->vdev);
+}
+
+static void virtballoon_remove(struct virtio_device *vdev)
+{
+	struct virtio_balloon *vb = vdev->priv;
+
+	kthread_stop(vb->thread);
+	remove_common(vb);
+	balloon_mapping_free(vb->vb_dev_info->mapping);
+	balloon_devinfo_free(vb->vb_dev_info);
 	kfree(vb);
 }
 
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 static int virtballoon_freeze(struct virtio_device *vdev)
 {
+	struct virtio_balloon *vb = vdev->priv;
+
 	/*
 	 * The kthread is already frozen by the PM core before this
 	 * function is called.
 	 */
 
-	/* Ensure we don't get any more requests from the host */
-	vdev->config->reset(vdev);
-	vdev->config->del_vqs(vdev);
+	remove_common(vb);
 	return 0;
 }
 
-static int virtballoon_thaw(struct virtio_device *vdev)
-{
-	return init_vqs(vdev->priv);
-}
-
 static int virtballoon_restore(struct virtio_device *vdev)
 {
 	struct virtio_balloon *vb = vdev->priv;
-	struct page *page, *page2;
-
-	/* We're starting from a clean slate */
-	vb->num_pages = 0;
+	int ret;
 
-	/*
-	 * If a request wasn't complete at the time of freezing, this
-	 * could have been set.
-	 */
-	vb->need_stats_update = 0;
+	ret = init_vqs(vdev->priv);
+	if (ret)
+		return ret;
 
-	/* We don't have these pages in the balloon anymore! */
-	list_for_each_entry_safe(page, page2, &vb->pages, lru) {
-		list_del(&page->lru);
-		totalram_pages++;
-	}
-	return init_vqs(vdev->priv);
+	fill_balloon(vb, towards_target(vb));
+	update_balloon_size(vb);
+	return 0;
 }
 #endif
 
@@ -418,27 +556,15 @@ static struct virtio_driver virtio_balloon_driver = {
 	.driver.owner =	THIS_MODULE,
 	.id_table =	id_table,
 	.probe =	virtballoon_probe,
-	.remove =	__devexit_p(virtballoon_remove),
+	.remove =	virtballoon_remove,
 	.config_changed = virtballoon_changed,
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 	.freeze	=	virtballoon_freeze,
 	.restore =	virtballoon_restore,
-	.thaw =		virtballoon_thaw,
 #endif
 };
 
-static int __init init(void)
-{
-	return register_virtio_driver(&virtio_balloon_driver);
-}
-
-static void __exit fini(void)
-{
-	unregister_virtio_driver(&virtio_balloon_driver);
-}
-module_init(init);
-module_exit(fini);
-
+module_virtio_driver(virtio_balloon_driver);
 MODULE_DEVICE_TABLE(virtio, id_table);
 MODULE_DESCRIPTION("Virtio balloon driver");
 MODULE_LICENSE("GPL");