linux-stable/include/linux/writeback.h
Tejun Heo a88a341a73 writeback: move bandwidth related fields from backing_dev_info into bdi_writeback
Currently, a bdi (backing_dev_info) embeds single wb (bdi_writeback)
and the role of the separation is unclear.  For cgroup support for
writeback IOs, a bdi will be updated to host multiple wb's where each
wb serves writeback IOs of a different cgroup on the bdi.  To achieve
that, a wb should carry all states necessary for servicing writeback
IOs for a cgroup independently.

This patch moves bandwidth related fields from backing_dev_info into
bdi_writeback.

* The moved fields are: bw_time_stamp, dirtied_stamp, written_stamp,
  write_bandwidth, avg_write_bandwidth, dirty_ratelimit,
  balanced_dirty_ratelimit, completions and dirty_exceeded.

* writeback_chunk_size() and over_bground_thresh() now take @wb
  instead of @bdi.

* bdi_writeout_fraction(bdi, ...)	-> wb_writeout_fraction(wb, ...)
  bdi_dirty_limit(bdi, ...)		-> wb_dirty_limit(wb, ...)
  bdi_position_ration(bdi, ...)		-> wb_position_ratio(wb, ...)
  bdi_update_writebandwidth(bdi, ...)	-> wb_update_write_bandwidth(wb, ...)
  [__]bdi_update_bandwidth(bdi, ...)	-> [__]wb_update_bandwidth(wb, ...)
  bdi_{max|min}_pause(bdi, ...)		-> wb_{max|min}_pause(wb, ...)
  bdi_dirty_limits(bdi, ...)		-> wb_dirty_limits(wb, ...)

* Init/exits of the relocated fields are moved to bdi_wb_init/exit()
  respectively.  Note that explicit zeroing is dropped in the process
  as wb's are cleared in entirety anyway.

* As there's still only one bdi_writeback per backing_dev_info, all
  uses of bdi->stat[] are mechanically replaced with bdi->wb.stat[]
  introducing no behavior changes.

v2: Typo in description fixed as suggested by Jan.

Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Jan Kara <jack@suse.cz>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Wu Fengguang <fengguang.wu@intel.com>
Cc: Jaegeuk Kim <jaegeuk@kernel.org>
Cc: Steven Whitehouse <swhiteho@redhat.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
2015-06-02 08:33:34 -06:00

188 lines
6 KiB
C

/*
* include/linux/writeback.h
*/
#ifndef WRITEBACK_H
#define WRITEBACK_H
#include <linux/sched.h>
#include <linux/workqueue.h>
#include <linux/fs.h>
DECLARE_PER_CPU(int, dirty_throttle_leaks);
/*
* The 1/4 region under the global dirty thresh is for smooth dirty throttling:
*
* (thresh - thresh/DIRTY_FULL_SCOPE, thresh)
*
* Further beyond, all dirtier tasks will enter a loop waiting (possibly long
* time) for the dirty pages to drop, unless written enough pages.
*
* The global dirty threshold is normally equal to the global dirty limit,
* except when the system suddenly allocates a lot of anonymous memory and
* knocks down the global dirty threshold quickly, in which case the global
* dirty limit will follow down slowly to prevent livelocking all dirtier tasks.
*/
#define DIRTY_SCOPE 8
#define DIRTY_FULL_SCOPE (DIRTY_SCOPE / 2)
struct backing_dev_info;
/*
* fs/fs-writeback.c
*/
enum writeback_sync_modes {
WB_SYNC_NONE, /* Don't wait on anything */
WB_SYNC_ALL, /* Wait on every mapping */
};
/*
* why some writeback work was initiated
*/
enum wb_reason {
WB_REASON_BACKGROUND,
WB_REASON_TRY_TO_FREE_PAGES,
WB_REASON_SYNC,
WB_REASON_PERIODIC,
WB_REASON_LAPTOP_TIMER,
WB_REASON_FREE_MORE_MEM,
WB_REASON_FS_FREE_SPACE,
/*
* There is no bdi forker thread any more and works are done
* by emergency worker, however, this is TPs userland visible
* and we'll be exposing exactly the same information,
* so it has a mismatch name.
*/
WB_REASON_FORKER_THREAD,
WB_REASON_MAX,
};
/*
* A control structure which tells the writeback code what to do. These are
* always on the stack, and hence need no locking. They are always initialised
* in a manner such that unspecified fields are set to zero.
*/
struct writeback_control {
long nr_to_write; /* Write this many pages, and decrement
this for each page written */
long pages_skipped; /* Pages which were not written */
/*
* For a_ops->writepages(): if start or end are non-zero then this is
* a hint that the filesystem need only write out the pages inside that
* byterange. The byte at `end' is included in the writeout request.
*/
loff_t range_start;
loff_t range_end;
enum writeback_sync_modes sync_mode;
unsigned for_kupdate:1; /* A kupdate writeback */
unsigned for_background:1; /* A background writeback */
unsigned tagged_writepages:1; /* tag-and-write to avoid livelock */
unsigned for_reclaim:1; /* Invoked from the page allocator */
unsigned range_cyclic:1; /* range_start is cyclic */
unsigned for_sync:1; /* sync(2) WB_SYNC_ALL writeback */
};
/*
* fs/fs-writeback.c
*/
struct bdi_writeback;
void writeback_inodes_sb(struct super_block *, enum wb_reason reason);
void writeback_inodes_sb_nr(struct super_block *, unsigned long nr,
enum wb_reason reason);
int try_to_writeback_inodes_sb(struct super_block *, enum wb_reason reason);
int try_to_writeback_inodes_sb_nr(struct super_block *, unsigned long nr,
enum wb_reason reason);
void sync_inodes_sb(struct super_block *);
void wakeup_flusher_threads(long nr_pages, enum wb_reason reason);
void inode_wait_for_writeback(struct inode *inode);
/* writeback.h requires fs.h; it, too, is not included from here. */
static inline void wait_on_inode(struct inode *inode)
{
might_sleep();
wait_on_bit(&inode->i_state, __I_NEW, TASK_UNINTERRUPTIBLE);
}
/*
* mm/page-writeback.c
*/
#ifdef CONFIG_BLOCK
void laptop_io_completion(struct backing_dev_info *info);
void laptop_sync_completion(void);
void laptop_mode_sync(struct work_struct *work);
void laptop_mode_timer_fn(unsigned long data);
#else
static inline void laptop_sync_completion(void) { }
#endif
void throttle_vm_writeout(gfp_t gfp_mask);
bool zone_dirty_ok(struct zone *zone);
extern unsigned long global_dirty_limit;
/* These are exported to sysctl. */
extern int dirty_background_ratio;
extern unsigned long dirty_background_bytes;
extern int vm_dirty_ratio;
extern unsigned long vm_dirty_bytes;
extern unsigned int dirty_writeback_interval;
extern unsigned int dirty_expire_interval;
extern unsigned int dirtytime_expire_interval;
extern int vm_highmem_is_dirtyable;
extern int block_dump;
extern int laptop_mode;
extern int dirty_background_ratio_handler(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp,
loff_t *ppos);
extern int dirty_background_bytes_handler(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp,
loff_t *ppos);
extern int dirty_ratio_handler(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp,
loff_t *ppos);
extern int dirty_bytes_handler(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp,
loff_t *ppos);
int dirtytime_interval_handler(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos);
struct ctl_table;
int dirty_writeback_centisecs_handler(struct ctl_table *, int,
void __user *, size_t *, loff_t *);
void global_dirty_limits(unsigned long *pbackground, unsigned long *pdirty);
unsigned long wb_dirty_limit(struct bdi_writeback *wb, unsigned long dirty);
void __wb_update_bandwidth(struct bdi_writeback *wb,
unsigned long thresh,
unsigned long bg_thresh,
unsigned long dirty,
unsigned long bdi_thresh,
unsigned long bdi_dirty,
unsigned long start_time);
void page_writeback_init(void);
void balance_dirty_pages_ratelimited(struct address_space *mapping);
typedef int (*writepage_t)(struct page *page, struct writeback_control *wbc,
void *data);
int generic_writepages(struct address_space *mapping,
struct writeback_control *wbc);
void tag_pages_for_writeback(struct address_space *mapping,
pgoff_t start, pgoff_t end);
int write_cache_pages(struct address_space *mapping,
struct writeback_control *wbc, writepage_t writepage,
void *data);
int do_writepages(struct address_space *mapping, struct writeback_control *wbc);
void writeback_set_ratelimit(void);
void tag_pages_for_writeback(struct address_space *mapping,
pgoff_t start, pgoff_t end);
void account_page_redirty(struct page *page);
#endif /* WRITEBACK_H */