mm: compaction: determine if dirty pages can be migrated without blocking within ->migratepage

commit b969c4ab9f182a6e1b2a0848be349f99714947b0 upstream.

Stable note: Not tracked in Bugzilla. A fix aimed at preserving page
	aging information by reducing LRU list churning had the side-effect
	of reducing THP allocation success rates. This was part of a series
	to restore the success rates while preserving the reclaim fix.

Asynchronous compaction is used when allocating transparent hugepages to
avoid blocking for long periods of time.  Due to reports of stalling,
there was a debate on disabling synchronous compaction but this severely
impacted allocation success rates.  Part of the reason was that many dirty
pages are skipped in asynchronous compaction by the following check;

	if (PageDirty(page) && !sync &&
		mapping->a_ops->migratepage != migrate_page)
			rc = -EBUSY;

This skips over all mapping aops using buffer_migrate_page() even though
it is possible to migrate some of these pages without blocking.  This
patch updates the ->migratepage callback with a "sync" parameter.  It is
the responsibility of the callback to fail gracefully if migration would
block.

Signed-off-by: Mel Gorman <mgorman@suse.de>
Reviewed-by: Rik van Riel <riel@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Minchan Kim <minchan.kim@gmail.com>
Cc: Dave Jones <davej@redhat.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Andy Isaacson <adi@hexapodia.org>
Cc: Nai Xia <nai.xia@gmail.com>
Cc: Johannes Weiner <jweiner@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>

4 files changed, 7 insertions, 6 deletions

diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index f44b3928dc2..fa7cddf8979 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -872,7 +872,7 @@ static int btree_submit_bio_hook(struct inode *inode, int rw, struct bio *bio,
 
 #ifdef CONFIG_MIGRATION
 static int btree_migratepage(struct address_space *mapping,
-			struct page *newpage, struct page *page)
+			struct page *newpage, struct page *page, bool sync)
 {
 	/*
 	 * we can't safely write a btree page from here,
@@ -887,7 +887,7 @@ static int btree_migratepage(struct address_space *mapping,
 	if (page_has_private(page) &&
 	    !try_to_release_page(page, GFP_KERNEL))
 		return -EAGAIN;
-	return migrate_page(mapping, newpage, page);
+	return migrate_page(mapping, newpage, page, sync);
 }
 #endif
 
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index ebc2f4d5581..217b7718154 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -569,7 +569,8 @@ static int hugetlbfs_set_page_dirty(struct page *page)
 }
 
 static int hugetlbfs_migrate_page(struct address_space *mapping,
-				struct page *newpage, struct page *page)
+				struct page *newpage, struct page *page,
+				bool sync)
 {
 	int rc;
 
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index 3f4d95751d5..8d96ed6af6d 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -330,7 +330,7 @@ void nfs_commit_release_pages(struct nfs_write_data *data);
 
 #ifdef CONFIG_MIGRATION
 extern int nfs_migrate_page(struct address_space *,
-		struct page *, struct page *);
+		struct page *, struct page *, bool);
 #else
 #define nfs_migrate_page NULL
 #endif
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 4efd4216699..31b246194f8 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -1711,7 +1711,7 @@ out_error:
 
 #ifdef CONFIG_MIGRATION
 int nfs_migrate_page(struct address_space *mapping, struct page *newpage,
-		struct page *page)
+		struct page *page, bool sync)
 {
 	/*
 	 * If PagePrivate is set, then the page is currently associated with
@@ -1726,7 +1726,7 @@ int nfs_migrate_page(struct address_space *mapping, struct page *newpage,
 
 	nfs_fscache_release_page(page, GFP_KERNEL);
 
-	return migrate_page(mapping, newpage, page);
+	return migrate_page(mapping, newpage, page, sync);
 }
 #endif