mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-23 22:59:08 +07:00
743162013d
The current "wait_on_bit" interface requires an 'action' function to be provided which does the actual waiting. There are over 20 such functions, many of them identical. Most cases can be satisfied by one of just two functions, one which uses io_schedule() and one which just uses schedule(). So: Rename wait_on_bit and wait_on_bit_lock to wait_on_bit_action and wait_on_bit_lock_action to make it explicit that they need an action function. Introduce new wait_on_bit{,_lock} and wait_on_bit{,_lock}_io which are *not* given an action function but implicitly use a standard one. The decision to error-out if a signal is pending is now made based on the 'mode' argument rather than being encoded in the action function. All instances of the old wait_on_bit and wait_on_bit_lock which can use the new version have been changed accordingly and their action functions have been discarded. wait_on_bit{_lock} does not return any specific error code in the event of a signal so the caller must check for non-zero and interpolate their own error code as appropriate. The wait_on_bit() call in __fscache_wait_on_invalidate() was ambiguous as it specified TASK_UNINTERRUPTIBLE but used fscache_wait_bit_interruptible as an action function. David Howells confirms this should be uniformly "uninterruptible" The main remaining user of wait_on_bit{,_lock}_action is NFS which needs to use a freezer-aware schedule() call. A comment in fs/gfs2/glock.c notes that having multiple 'action' functions is useful as they display differently in the 'wchan' field of 'ps'. (and /proc/$PID/wchan). As the new bit_wait{,_io} functions are tagged "__sched", they will not show up at all, but something higher in the stack. So the distinction will still be visible, only with different function names (gds2_glock_wait versus gfs2_glock_dq_wait in the gfs2/glock.c case). Since first version of this patch (against 3.15) two new action functions appeared, on in NFS and one in CIFS. CIFS also now uses an action function that makes the same freezer aware schedule call as NFS. Signed-off-by: NeilBrown <neilb@suse.de> Acked-by: David Howells <dhowells@redhat.com> (fscache, keys) Acked-by: Steven Whitehouse <swhiteho@redhat.com> (gfs2) Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Steve French <sfrench@samba.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Link: http://lkml.kernel.org/r/20140707051603.28027.72349.stgit@notabene.brown Signed-off-by: Ingo Molnar <mingo@kernel.org>
188 lines
5.9 KiB
C
188 lines
5.9 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 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);
|
|
|
|
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 bdi_dirty_limit(struct backing_dev_info *bdi,
|
|
unsigned long dirty);
|
|
|
|
void __bdi_update_bandwidth(struct backing_dev_info *bdi,
|
|
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 set_page_dirty_balance(struct page *page);
|
|
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 */
|