fs/buffer.c: support buffer cache allocations with gfp modifiers

A buffer cache is allocated from movable area because it is referred
for a while and released soon.  But some filesystems are taking buffer
cache for a long time and it can disturb page migration.

New APIs are introduced to allocate buffer cache with user specific
flag.  *_gfp APIs are for user want to set page allocation flag for
page cache allocation.  And *_unmovable APIs are for the user wants to
allocate page cache from non-movable area.

Signed-off-by: Gioh Kim <gioh.kim@lge.com>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
Reviewed-by: Jan Kara <jack@suse.cz>

fs/buffer.c

@@ -993,7 +993,7 @@ init_page_buffers(struct page *page, struct block_device *bdev,
  */
 static int
 grow_dev_page(struct block_device *bdev, sector_t block,
-		pgoff_t index, int size, int sizebits)
+	      pgoff_t index, int size, int sizebits, gfp_t gfp)
 {
 	struct inode *inode = bdev->bd_inode;
 	struct page *page;
@@ -1002,8 +1002,8 @@ grow_dev_page(struct block_device *bdev, sector_t block,
 	int ret = 0;		/* Will call free_more_memory() */
 	gfp_t gfp_mask;
 
-	gfp_mask = mapping_gfp_mask(inode->i_mapping) & ~__GFP_FS;
-	gfp_mask |= __GFP_MOVABLE;
+	gfp_mask = (mapping_gfp_mask(inode->i_mapping) & ~__GFP_FS) | gfp;
+
 	/*
 	 * XXX: __getblk_slow() can not really deal with failure and
 	 * will endlessly loop on improvised global reclaim.  Prefer
@@ -1058,7 +1058,7 @@ failed:
  * that page was dirty, the buffers are set dirty also.
  */
 static int
-grow_buffers(struct block_device *bdev, sector_t block, int size)
+grow_buffers(struct block_device *bdev, sector_t block, int size, gfp_t gfp)
 {
 	pgoff_t index;
 	int sizebits;
@@ -1085,11 +1085,12 @@ grow_buffers(struct block_device *bdev, sector_t block, int size)
 	}
 
 	/* Create a page with the proper size buffers.. */
-	return grow_dev_page(bdev, block, index, size, sizebits);
+	return grow_dev_page(bdev, block, index, size, sizebits, gfp);
 }
 
-static struct buffer_head *
-__getblk_slow(struct block_device *bdev, sector_t block, int size)
+struct buffer_head *
+__getblk_slow(struct block_device *bdev, sector_t block,
+	     unsigned size, gfp_t gfp)
 {
 	/* Size must be multiple of hard sectorsize */
 	if (unlikely(size & (bdev_logical_block_size(bdev)-1) ||
@@ -1111,13 +1112,14 @@ __getblk_slow(struct block_device *bdev, sector_t block, int size)
 		if (bh)
 			return bh;
 
-		ret = grow_buffers(bdev, block, size);
+		ret = grow_buffers(bdev, block, size, gfp);
 		if (ret < 0)
 			return NULL;
 		if (ret == 0)
 			free_more_memory();
 	}
 }
+EXPORT_SYMBOL(__getblk_slow);
 
 /*
  * The relationship between dirty buffers and dirty pages:
@@ -1371,24 +1373,25 @@ __find_get_block(struct block_device *bdev, sector_t block, unsigned size)
 EXPORT_SYMBOL(__find_get_block);
 
 /*
- * __getblk will locate (and, if necessary, create) the buffer_head
+ * __getblk_gfp() will locate (and, if necessary, create) the buffer_head
  * which corresponds to the passed block_device, block and size. The
  * returned buffer has its reference count incremented.
  *
- * __getblk() will lock up the machine if grow_dev_page's try_to_free_buffers()
- * attempt is failing.  FIXME, perhaps?
+ * __getblk_gfp() will lock up the machine if grow_dev_page's
+ * try_to_free_buffers() attempt is failing.  FIXME, perhaps?
  */
 struct buffer_head *
-__getblk(struct block_device *bdev, sector_t block, unsigned size)
+__getblk_gfp(struct block_device *bdev, sector_t block,
+	     unsigned size, gfp_t gfp)
 {
 	struct buffer_head *bh = __find_get_block(bdev, block, size);
 
 	might_sleep();
 	if (bh == NULL)
-		bh = __getblk_slow(bdev, block, size);
+		bh = __getblk_slow(bdev, block, size, gfp);
 	return bh;
 }
-EXPORT_SYMBOL(__getblk);
+EXPORT_SYMBOL(__getblk_gfp);
 
 /*
  * Do async read-ahead on a buffer..
@@ -1404,24 +1407,28 @@ void __breadahead(struct block_device *bdev, sector_t block, unsigned size)
 EXPORT_SYMBOL(__breadahead);
 
 /**
- *  __bread() - reads a specified block and returns the bh
+ *  __bread_gfp() - reads a specified block and returns the bh
  *  @bdev: the block_device to read from
  *  @block: number of block
  *  @size: size (in bytes) to read
+ *  @gfp: page allocation flag
  *
  *  Reads a specified block, and returns buffer head that contains it.
+ *  The page cache can be allocated from non-movable area
+ *  not to prevent page migration if you set gfp to zero.
  *  It returns NULL if the block was unreadable.
  */
 struct buffer_head *
-__bread(struct block_device *bdev, sector_t block, unsigned size)
+__bread_gfp(struct block_device *bdev, sector_t block,
+		   unsigned size, gfp_t gfp)
 {
-	struct buffer_head *bh = __getblk(bdev, block, size);
+	struct buffer_head *bh = __getblk_gfp(bdev, block, size, gfp);
 
 	if (likely(bh) && !buffer_uptodate(bh))
 		bh = __bread_slow(bh);
 	return bh;
 }
-EXPORT_SYMBOL(__bread);
+EXPORT_SYMBOL(__bread_gfp);
 
 /*
  * invalidate_bh_lrus() is called rarely - but not only at unmount.

include/linux/buffer_head.h

@@ -175,12 +175,13 @@ void __wait_on_buffer(struct buffer_head *);
 wait_queue_head_t *bh_waitq_head(struct buffer_head *bh);
 struct buffer_head *__find_get_block(struct block_device *bdev, sector_t block,
 			unsigned size);
-struct buffer_head *__getblk(struct block_device *bdev, sector_t block,
-			unsigned size);
+struct buffer_head *__getblk_gfp(struct block_device *bdev, sector_t block,
+				  unsigned size, gfp_t gfp);
 void __brelse(struct buffer_head *);
 void __bforget(struct buffer_head *);
 void __breadahead(struct block_device *, sector_t block, unsigned int size);
-struct buffer_head *__bread(struct block_device *, sector_t block, unsigned size);
+struct buffer_head *__bread_gfp(struct block_device *,
+				sector_t block, unsigned size, gfp_t gfp);
 void invalidate_bh_lrus(void);
 struct buffer_head *alloc_buffer_head(gfp_t gfp_flags);
 void free_buffer_head(struct buffer_head * bh);
@@ -295,7 +296,13 @@ static inline void bforget(struct buffer_head *bh)
 static inline struct buffer_head *
 sb_bread(struct super_block *sb, sector_t block)
 {
-	return __bread(sb->s_bdev, block, sb->s_blocksize);
+	return __bread_gfp(sb->s_bdev, block, sb->s_blocksize, __GFP_MOVABLE);
+}
+
+static inline struct buffer_head *
+sb_bread_unmovable(struct super_block *sb, sector_t block)
+{
+	return __bread_gfp(sb->s_bdev, block, sb->s_blocksize, 0);
 }
 
 static inline void
@@ -307,7 +314,7 @@ sb_breadahead(struct super_block *sb, sector_t block)
 static inline struct buffer_head *
 sb_getblk(struct super_block *sb, sector_t block)
 {
-	return __getblk(sb->s_bdev, block, sb->s_blocksize);
+	return __getblk_gfp(sb->s_bdev, block, sb->s_blocksize, __GFP_MOVABLE);
 }
 
 static inline struct buffer_head *
@@ -344,6 +351,36 @@ static inline void lock_buffer(struct buffer_head *bh)
 		__lock_buffer(bh);
 }
 
+static inline struct buffer_head *getblk_unmovable(struct block_device *bdev,
+						   sector_t block,
+						   unsigned size)
+{
+	return __getblk_gfp(bdev, block, size, 0);
+}
+
+static inline struct buffer_head *__getblk(struct block_device *bdev,
+					   sector_t block,
+					   unsigned size)
+{
+	return __getblk_gfp(bdev, block, size, __GFP_MOVABLE);
+}
+
+/**
+ *  __bread() - reads a specified block and returns the bh
+ *  @bdev: the block_device to read from
+ *  @block: number of block
+ *  @size: size (in bytes) to read
+ *
+ *  Reads a specified block, and returns buffer head that contains it.
+ *  The page cache is allocated from movable area so that it can be migrated.
+ *  It returns NULL if the block was unreadable.
+ */
+static inline struct buffer_head *
+__bread(struct block_device *bdev, sector_t block, unsigned size)
+{
+	return __bread_gfp(bdev, block, size, __GFP_MOVABLE);
+}
+
 extern int __set_page_dirty_buffers(struct page *page);
 
 #else /* CONFIG_BLOCK */