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>

7 files changed, 106 insertions, 47 deletions

diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index f44b3928dc2d..fa7cddf8979b 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 ebc2f4d5581e..217b7718154c 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 3f4d95751d52..8d96ed6af6db 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 4efd42166992..31b246194f87 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
 
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 43d36b7992c4..2ae90d35c4c8 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -609,9 +609,12 @@ struct address_space_operations {
 			loff_t offset, unsigned long nr_segs);
 	int (*get_xip_mem)(struct address_space *, pgoff_t, int,
 						void **, unsigned long *);
-	/* migrate the contents of a page to the specified target */
+	/*
+	 * migrate the contents of a page to the specified target. If sync
+	 * is false, it must not block.
+	 */
 	int (*migratepage) (struct address_space *,
-			struct page *, struct page *);
+			struct page *, struct page *, bool);
 	int (*launder_page) (struct page *);
 	int (*is_partially_uptodate) (struct page *, read_descriptor_t *,
 					unsigned long);
@@ -2586,7 +2589,7 @@ extern int generic_check_addressable(unsigned, u64);
 
 #ifdef CONFIG_MIGRATION
 extern int buffer_migrate_page(struct address_space *,
-				struct page *, struct page *);
+				struct page *, struct page *, bool);
 #else
 #define buffer_migrate_page NULL
 #endif
diff --git a/include/linux/migrate.h b/include/linux/migrate.h
index e39aeecfe9a2..14e6d2a88475 100644
--- a/include/linux/migrate.h
+++ b/include/linux/migrate.h
@@ -11,7 +11,7 @@ typedef struct page *new_page_t(struct page *, unsigned long private, int **);
 
 extern void putback_lru_pages(struct list_head *l);
 extern int migrate_page(struct address_space *,
-			struct page *, struct page *);
+			struct page *, struct page *, bool);
 extern int migrate_pages(struct list_head *l, new_page_t x,
 			unsigned long private, bool offlining,
 			bool sync);
diff --git a/mm/migrate.c b/mm/migrate.c
index 177aca424a06..65c12d2bdfdb 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -220,6 +220,55 @@ out:
 	pte_unmap_unlock(ptep, ptl);
 }
 
+#ifdef CONFIG_BLOCK
+/* Returns true if all buffers are successfully locked */
+static bool buffer_migrate_lock_buffers(struct buffer_head *head, bool sync)
+{
+	struct buffer_head *bh = head;
+
+	/* Simple case, sync compaction */
+	if (sync) {
+		do {
+			get_bh(bh);
+			lock_buffer(bh);
+			bh = bh->b_this_page;
+
+		} while (bh != head);
+
+		return true;
+	}
+
+	/* async case, we cannot block on lock_buffer so use trylock_buffer */
+	do {
+		get_bh(bh);
+		if (!trylock_buffer(bh)) {
+			/*
+			 * We failed to lock the buffer and cannot stall in
+			 * async migration. Release the taken locks
+			 */
+			struct buffer_head *failed_bh = bh;
+			put_bh(failed_bh);
+			bh = head;
+			while (bh != failed_bh) {
+				unlock_buffer(bh);
+				put_bh(bh);
+				bh = bh->b_this_page;
+			}
+			return false;
+		}
+
+		bh = bh->b_this_page;
+	} while (bh != head);
+	return true;
+}
+#else
+static inline bool buffer_migrate_lock_buffers(struct buffer_head *head,
+								bool sync)
+{
+	return true;
+}
+#endif /* CONFIG_BLOCK */
+
 /*
  * Replace the page in the mapping.
  *
@@ -229,7 +278,8 @@ out:
  * 3 for pages with a mapping and PagePrivate/PagePrivate2 set.
  */
 static int migrate_page_move_mapping(struct address_space *mapping,
-		struct page *newpage, struct page *page)
+		struct page *newpage, struct page *page,
+		struct buffer_head *head, bool sync)
 {
 	int expected_count;
 	void **pslot;
@@ -259,6 +309,19 @@ static int migrate_page_move_mapping(struct address_space *mapping,
 	}
 
 	/*
+	 * In the async migration case of moving a page with buffers, lock the
+	 * buffers using trylock before the mapping is moved. If the mapping
+	 * was moved, we later failed to lock the buffers and could not move
+	 * the mapping back due to an elevated page count, we would have to
+	 * block waiting on other references to be dropped.
+	 */
+	if (!sync && head && !buffer_migrate_lock_buffers(head, sync)) {
+		page_unfreeze_refs(page, expected_count);
+		spin_unlock_irq(&mapping->tree_lock);
+		return -EAGAIN;
+	}
+
+	/*
 	 * Now we know that no one else is looking at the page.
 	 */
 	get_page(newpage);	/* add cache reference */
@@ -415,13 +478,13 @@ EXPORT_SYMBOL(fail_migrate_page);
  * Pages are locked upon entry and exit.
  */
 int migrate_page(struct address_space *mapping,
-		struct page *newpage, struct page *page)
+		struct page *newpage, struct page *page, bool sync)
 {
 	int rc;
 
 	BUG_ON(PageWriteback(page));	/* Writeback must be complete */
 
-	rc = migrate_page_move_mapping(mapping, newpage, page);
+	rc = migrate_page_move_mapping(mapping, newpage, page, NULL, sync);
 
 	if (rc)
 		return rc;
@@ -438,28 +501,28 @@ EXPORT_SYMBOL(migrate_page);
  * exist.
  */
 int buffer_migrate_page(struct address_space *mapping,
-		struct page *newpage, struct page *page)
+		struct page *newpage, struct page *page, bool sync)
 {
 	struct buffer_head *bh, *head;
 	int rc;
 
 	if (!page_has_buffers(page))
-		return migrate_page(mapping, newpage, page);
+		return migrate_page(mapping, newpage, page, sync);
 
 	head = page_buffers(page);
 
-	rc = migrate_page_move_mapping(mapping, newpage, page);
+	rc = migrate_page_move_mapping(mapping, newpage, page, head, sync);
 
 	if (rc)
 		return rc;
 
-	bh = head;
-	do {
-		get_bh(bh);
-		lock_buffer(bh);
-		bh = bh->b_this_page;
-
-	} while (bh != head);
+	/*
+	 * In the async case, migrate_page_move_mapping locked the buffers
+	 * with an IRQ-safe spinlock held. In the sync case, the buffers
+	 * need to be locked now
+	 */
+	if (sync)
+		BUG_ON(!buffer_migrate_lock_buffers(head, sync));
 
 	ClearPagePrivate(page);
 	set_page_private(newpage, page_private(page));
@@ -536,10 +599,13 @@ static int writeout(struct address_space *mapping, struct page *page)
  * Default handling if a filesystem does not provide a migration function.
  */
 static int fallback_migrate_page(struct address_space *mapping,
-	struct page *newpage, struct page *page)
+	struct page *newpage, struct page *page, bool sync)
 {
-	if (PageDirty(page))
+	if (PageDirty(page)) {
+		if (!sync)
+			return -EBUSY;
 		return writeout(mapping, page);
+	}
 
 	/*
 	 * Buffers may be managed in a filesystem specific way.
@@ -549,7 +615,7 @@ static int fallback_migrate_page(struct address_space *mapping,
 	    !try_to_release_page(page, GFP_KERNEL))
 		return -EAGAIN;
 
-	return migrate_page(mapping, newpage, page);
+	return migrate_page(mapping, newpage, page, sync);
 }
 
 /*
@@ -585,29 +651,18 @@ static int move_to_new_page(struct page *newpage, struct page *page,
 
 	mapping = page_mapping(page);
 	if (!mapping)
-		rc = migrate_page(mapping, newpage, page);
-	else {
+		rc = migrate_page(mapping, newpage, page, sync);
+	else if (mapping->a_ops->migratepage)
 		/*
-		 * Do not writeback pages if !sync and migratepage is
-		 * not pointing to migrate_page() which is nonblocking
-		 * (swapcache/tmpfs uses migratepage = migrate_page).
+		 * Most pages have a mapping and most filesystems provide a
+		 * migratepage callback. Anonymous pages are part of swap
+		 * space which also has its own migratepage callback. This
+		 * is the most common path for page migration.
 		 */
-		if (PageDirty(page) && !sync &&
-		    mapping->a_ops->migratepage != migrate_page)
-			rc = -EBUSY;
-		else if (mapping->a_ops->migratepage)
-			/*
-			 * Most pages have a mapping and most filesystems
-			 * should provide a migration function. Anonymous
-			 * pages are part of swap space which also has its
-			 * own migration function. This is the most common
-			 * path for page migration.
-			 */
-			rc = mapping->a_ops->migratepage(mapping,
-							newpage, page);
-		else
-			rc = fallback_migrate_page(mapping, newpage, page);
-	}
+		rc = mapping->a_ops->migratepage(mapping,
+						newpage, page, sync);
+	else
+		rc = fallback_migrate_page(mapping, newpage, page, sync);
 
 	if (rc) {
 		newpage->mapping = NULL;