[PATCHv3 1/3] fs/buffer.c: allocate buffer cache with user specific flag

[Gioh Kim]

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@xxxxxxx>
---
 fs/buffer.c                 |   54 +++++++++++++++++++++++++++++++++----------
 include/linux/buffer_head.h |   14 ++++++++++-
 2 files changed, 55 insertions(+), 13 deletions(-)

diff --git a/fs/buffer.c b/fs/buffer.c
index 8f05111..ee29bc4 100644
--- a/fs/buffer.c
+++ b/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;
@@ -1002,10 +1002,10 @@ 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
+        * XXX: __getblk_gfp() can not really deal with failure and
         * will endlessly loop on improvised global reclaim.  Prefer
         * looping in the allocator rather than here, at least that
         * code knows what it's doing.
@@ -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_gfp(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 +1112,21 @@ __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_gfp);
+
+struct buffer_head *getblk_unmovable(struct block_device *bdev, sector_t block,
+                                    unsigned size)
+{
+       return __getblk_gfp(bdev, block, size, 0);
+}
+EXPORT_SYMBOL(getblk_unmovable);

 /*
  * The relationship between dirty buffers and dirty pages:
@@ -1385,7 +1394,7 @@ __getblk(struct block_device *bdev, sector_t block, unsigned size)

        might_sleep();
        if (bh == NULL)
-               bh = __getblk_slow(bdev, block, size);
+               bh = __getblk_gfp(bdev, block, size, __GFP_MOVABLE);
        return bh;
 }
 EXPORT_SYMBOL(__getblk);
@@ -1410,18 +1419,39 @@ EXPORT_SYMBOL(__breadahead);
  *  @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.
  */
 struct buffer_head *
 __bread(struct block_device *bdev, sector_t block, unsigned size)
 {
-       struct buffer_head *bh = __getblk(bdev, block, size);
+       return __bread_gfp(bdev, block, size, __GFP_MOVABLE);
+}
+EXPORT_SYMBOL(__bread);
+
+/**
+ *  __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_gfp(struct block_device *bdev, sector_t block,
+                  unsigned size, gfp_t gfp)
+{
+       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.
diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h
index 324329c..c3f89d3 100644
--- a/include/linux/buffer_head.h
+++ b/include/linux/buffer_head.h
@@ -177,10 +177,16 @@ 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);
+struct buffer_head *getblk_unmovable(struct block_device *bdev, sector_t block,
+                                    unsigned size);
 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 +301,13 @@ 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
--
1.7.9.5
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/