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>
This commit is contained in:
parent
d26e2c4d72
commit
3b5e6454aa
45
fs/buffer.c
45
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.
|
||||
|
|
|
@ -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 */
|
||||
|
|
Loading…
Reference in New Issue