Commit b1123ea6 authored by Minchan Kim's avatar Minchan Kim Committed by Linus Torvalds
Browse files

mm: balloon: use general non-lru movable page feature 

Now, VM has a feature to migrate non-lru movable pages so balloon
doesn't need custom migration hooks in migrate.c and compaction.c.

Instead, this patch implements the page->mapping->a_ops->
{isolate|migrate|putback} functions.

With that, we could remove hooks for ballooning in general migration
functions and make balloon compaction simple.

[akpm@linux-foundation.org: compaction.h requires that the includer first include node.h]
Link: http://lkml.kernel.org/r/1464736881-24886-4-git-send-email-minchan@kernel.org


Signed-off-by: default avatarGioh Kim <gi-oh.kim@profitbricks.com>
Signed-off-by: default avatarMinchan Kim <minchan@kernel.org>
Acked-by: default avatarVlastimil Babka <vbabka@suse.cz>
Cc: Rafael Aquini <aquini@redhat.com>
Cc: Konstantin Khlebnikov <koct9i@gmail.com>
Signed-off-by: default avatarAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: default avatarLinus Torvalds <torvalds@linux-foundation.org>
parent bda807d4

drivers/virtio/virtio_balloon.c

+48 −6
Original line number Diff line number Diff line
@@ -30,6 +30,7 @@ 
#include <linux/oom.h>

#include <linux/wait.h>

#include <linux/mm.h>

#include <linux/mount.h>



/*

 * Balloon device works in 4K page units.  So each page is pointed to by
@@ -45,6 +46,10 @@ static int oom_pages = OOM_VBALLOON_DEFAULT_PAGES; 
module_param(oom_pages, int, S_IRUSR | S_IWUSR);

MODULE_PARM_DESC(oom_pages, "pages to free on OOM");



#ifdef CONFIG_BALLOON_COMPACTION

static struct vfsmount *balloon_mnt;

#endif



struct virtio_balloon {

	struct virtio_device *vdev;

	struct virtqueue *inflate_vq, *deflate_vq, *stats_vq;
@@ -488,8 +493,26 @@ static int virtballoon_migratepage(struct balloon_dev_info *vb_dev_info, 


	put_page(page); /* balloon reference */



	return MIGRATEPAGE_SUCCESS;

	return 0;

}



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 int virtballoon_probe(struct virtio_device *vdev)
@@ -519,9 +542,6 @@ static int virtballoon_probe(struct virtio_device *vdev) 
	vb->vdev = vdev;



	balloon_devinfo_init(&vb->vb_dev_info);

#ifdef CONFIG_BALLOON_COMPACTION

	vb->vb_dev_info.migratepage = virtballoon_migratepage;

#endif



	err = init_vqs(vb);

	if (err)
@@ -531,13 +551,33 @@ static int virtballoon_probe(struct virtio_device *vdev) 
	vb->nb.priority = VIRTBALLOON_OOM_NOTIFY_PRIORITY;

	err = register_oom_notifier(&vb->nb);

	if (err < 0)

		goto out_oom_notify;

		goto out_del_vqs;



#ifdef CONFIG_BALLOON_COMPACTION

	balloon_mnt = kern_mount(&balloon_fs);

	if (IS_ERR(balloon_mnt)) {

		err = PTR_ERR(balloon_mnt);

		unregister_oom_notifier(&vb->nb);

		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);

		unregister_oom_notifier(&vb->nb);

		vb->vb_dev_info.inode = NULL;

		goto out_del_vqs;

	}

	vb->vb_dev_info.inode->i_mapping->a_ops = &balloon_aops;

#endif



	virtio_device_ready(vdev);



	return 0;



out_oom_notify:

out_del_vqs:

	vdev->config->del_vqs(vdev);

out_free_vb:

	kfree(vb);
@@ -571,6 +611,8 @@ static void virtballoon_remove(struct virtio_device *vdev) 
	cancel_work_sync(&vb->update_balloon_stats_work);



	remove_common(vb);

	if (vb->vb_dev_info.inode)

		iput(vb->vb_dev_info.inode);

	kfree(vb);

}

include/linux/balloon_compaction.h

+17 −37
Original line number Diff line number Diff line
@@ -45,9 +45,11 @@ 
#define _LINUX_BALLOON_COMPACTION_H

#include <linux/pagemap.h>

#include <linux/page-flags.h>

#include <linux/migrate.h>

#include <linux/node.h>

#include <linux/compaction.h>

#include <linux/gfp.h>

#include <linux/err.h>

#include <linux/fs.h>



/*

 * Balloon device information descriptor.
@@ -62,6 +64,7 @@ struct balloon_dev_info { 
	struct list_head pages;		/* Pages enqueued & handled to Host */

	int (*migratepage)(struct balloon_dev_info *, struct page *newpage,

			struct page *page, enum migrate_mode mode);

	struct inode *inode;

};



extern struct page *balloon_page_enqueue(struct balloon_dev_info *b_dev_info);
@@ -73,44 +76,18 @@ static inline void balloon_devinfo_init(struct balloon_dev_info *balloon) 
	spin_lock_init(&balloon->pages_lock);

	INIT_LIST_HEAD(&balloon->pages);

	balloon->migratepage = NULL;

	balloon->inode = NULL;

}



#ifdef CONFIG_BALLOON_COMPACTION

extern bool balloon_page_isolate(struct page *page);

extern const struct address_space_operations balloon_aops;

extern bool balloon_page_isolate(struct page *page,

				isolate_mode_t mode);

extern void balloon_page_putback(struct page *page);

extern int balloon_page_migrate(struct page *newpage,

extern int balloon_page_migrate(struct address_space *mapping,

				struct page *newpage,

				struct page *page, enum migrate_mode mode);



/*

 * __is_movable_balloon_page - helper to perform @page PageBalloon tests

 */

static inline bool __is_movable_balloon_page(struct page *page)

{

	return PageBalloon(page);

}



/*

 * balloon_page_movable - test PageBalloon to identify balloon pages

 *			  and PagePrivate to check that the page is not

 *			  isolated and can be moved by compaction/migration.

 *

 * As we might return false positives in the case of a balloon page being just

 * released under us, this need to be re-tested later, under the page lock.

 */

static inline bool balloon_page_movable(struct page *page)

{

	return PageBalloon(page) && PagePrivate(page);

}



/*

 * isolated_balloon_page - identify an isolated balloon page on private

 *			   compaction/migration page lists.

 */

static inline bool isolated_balloon_page(struct page *page)

{

	return PageBalloon(page);

}



/*

 * balloon_page_insert - insert a page into the balloon's page list and make

 *			 the page->private assignment accordingly.
@@ -124,7 +101,7 @@ static inline void balloon_page_insert(struct balloon_dev_info *balloon, 
				       struct page *page)

{

	__SetPageBalloon(page);

	SetPagePrivate(page);

	__SetPageMovable(page, balloon->inode->i_mapping);

	set_page_private(page, (unsigned long)balloon);

	list_add(&page->lru, &balloon->pages);

}
@@ -140,12 +117,15 @@ static inline void balloon_page_insert(struct balloon_dev_info *balloon, 
static inline void balloon_page_delete(struct page *page)

{

	__ClearPageBalloon(page);

	__ClearPageMovable(page);

	set_page_private(page, 0);

	if (PagePrivate(page)) {

		ClearPagePrivate(page);

	/*

	 * No touch page.lru field once @page has been isolated

	 * because VM is using the field.

	 */

	if (!PageIsolated(page))

		list_del(&page->lru);

}

}



/*

 * balloon_page_device - get the b_dev_info descriptor for the balloon device

include/uapi/linux/magic.h

+1 −0
Original line number Diff line number Diff line
@@ -80,5 +80,6 @@ 
#define BPF_FS_MAGIC		0xcafe4a11

/* Since UDF 2.01 is ISO 13346 based... */

#define UDF_SUPER_MAGIC		0x15013346

#define BALLOON_KVM_MAGIC	0x13661366



#endif /* __LINUX_MAGIC_H__ */

mm/balloon_compaction.c

+17 −77
Original line number Diff line number Diff line
@@ -70,7 +70,7 @@ struct page *balloon_page_dequeue(struct balloon_dev_info *b_dev_info) 
		 */

		if (trylock_page(page)) {

#ifdef CONFIG_BALLOON_COMPACTION

			if (!PagePrivate(page)) {

			if (PageIsolated(page)) {

				/* raced with isolation */

				unlock_page(page);

				continue;
@@ -106,110 +106,50 @@ EXPORT_SYMBOL_GPL(balloon_page_dequeue); 


#ifdef CONFIG_BALLOON_COMPACTION



static inline void __isolate_balloon_page(struct page *page)

bool balloon_page_isolate(struct page *page, isolate_mode_t mode)



{

	struct balloon_dev_info *b_dev_info = balloon_page_device(page);

	unsigned long flags;



	spin_lock_irqsave(&b_dev_info->pages_lock, flags);

	ClearPagePrivate(page);

	list_del(&page->lru);

	b_dev_info->isolated_pages++;

	spin_unlock_irqrestore(&b_dev_info->pages_lock, flags);



	return true;

}



static inline void __putback_balloon_page(struct page *page)

void balloon_page_putback(struct page *page)

{

	struct balloon_dev_info *b_dev_info = balloon_page_device(page);

	unsigned long flags;



	spin_lock_irqsave(&b_dev_info->pages_lock, flags);

	SetPagePrivate(page);

	list_add(&page->lru, &b_dev_info->pages);

	b_dev_info->isolated_pages--;

	spin_unlock_irqrestore(&b_dev_info->pages_lock, flags);

}



/* __isolate_lru_page() counterpart for a ballooned page */

bool balloon_page_isolate(struct page *page)

{

	/*

	 * Avoid burning cycles with pages that are yet under __free_pages(),

	 * or just got freed under us.

	 *

	 * In case we 'win' a race for a balloon page being freed under us and

	 * raise its refcount preventing __free_pages() from doing its job

	 * the put_page() at the end of this block will take care of

	 * release this page, thus avoiding a nasty leakage.

	 */

	if (likely(get_page_unless_zero(page))) {

		/*

		 * As balloon pages are not isolated from LRU lists, concurrent

		 * compaction threads can race against page migration functions

		 * as well as race against the balloon driver releasing a page.

		 *

		 * In order to avoid having an already isolated balloon page

		 * being (wrongly) re-isolated while it is under migration,

		 * or to avoid attempting to isolate pages being released by

		 * the balloon driver, lets be sure we have the page lock

		 * before proceeding with the balloon page isolation steps.

		 */

		if (likely(trylock_page(page))) {

			/*

			 * A ballooned page, by default, has PagePrivate set.

			 * Prevent concurrent compaction threads from isolating

			 * an already isolated balloon page by clearing it.

			 */

			if (balloon_page_movable(page)) {

				__isolate_balloon_page(page);

				unlock_page(page);

				return true;

			}

			unlock_page(page);

		}

		put_page(page);

	}

	return false;

}



/* putback_lru_page() counterpart for a ballooned page */

void balloon_page_putback(struct page *page)

{

	/*

	 * 'lock_page()' stabilizes the page and prevents races against

	 * concurrent isolation threads attempting to re-isolate it.

	 */

	lock_page(page);



	if (__is_movable_balloon_page(page)) {

		__putback_balloon_page(page);

		/* drop the extra ref count taken for page isolation */

		put_page(page);

	} else {

		WARN_ON(1);

		dump_page(page, "not movable balloon page");

	}

	unlock_page(page);

}



/* move_to_new_page() counterpart for a ballooned page */

int balloon_page_migrate(struct page *newpage,

			 struct page *page, enum migrate_mode mode)

int balloon_page_migrate(struct address_space *mapping,

		struct page *newpage, struct page *page,

		enum migrate_mode mode)

{

	struct balloon_dev_info *balloon = balloon_page_device(page);

	int rc = -EAGAIN;



	VM_BUG_ON_PAGE(!PageLocked(page), page);

	VM_BUG_ON_PAGE(!PageLocked(newpage), newpage);



	if (WARN_ON(!__is_movable_balloon_page(page))) {

		dump_page(page, "not movable balloon page");

		return rc;

	return balloon->migratepage(balloon, newpage, page, mode);

}



	if (balloon && balloon->migratepage)

		rc = balloon->migratepage(balloon, newpage, page, mode);

const struct address_space_operations balloon_aops = {

	.migratepage = balloon_page_migrate,

	.isolate_page = balloon_page_isolate,

	.putback_page = balloon_page_putback,

};

EXPORT_SYMBOL_GPL(balloon_aops);



	return rc;

}

#endif /* CONFIG_BALLOON_COMPACTION */

mm/compaction.c

+0 −7
Original line number Diff line number Diff line
@@ -791,13 +791,6 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn, 
		 * Skip any other type of page

		 */

		if (!PageLRU(page)) {

			if (unlikely(balloon_page_movable(page))) {

				if (balloon_page_isolate(page)) {

					/* Successfully isolated */

					goto isolate_success;

				}

			}



			/*

			 * __PageMovable can return false positive so we need

			 * to verify it under page_lock.

CRA Git | Maintained and supported by SUSTech CRA and CCSE