GitHub-Mirror/Star64_linux
2
0
Fork 0
mirror of https://github.com/Fishwaldo/Star64_linux.git synced 2025-07-08 07:21:27 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'for-4.2/writeback' of git://git.kernel.dk/linux-block

Browse source 
Pull cgroup writeback support from Jens Axboe:
 "This is the big pull request for adding cgroup writeback support.

  This code has been in development for a long time, and it has been
  simmering in for-next for a good chunk of this cycle too.  This is one
  of those problems that has been talked about for at least half a
  decade, finally there's a solution and code to go with it.

  Also see last weeks writeup on LWN:

        http://lwn.net/Articles/648292/"

* 'for-4.2/writeback' of git://git.kernel.dk/linux-block: (85 commits)
  writeback, blkio: add documentation for cgroup writeback support
  vfs, writeback: replace FS_CGROUP_WRITEBACK with SB_I_CGROUPWB
  writeback: do foreign inode detection iff cgroup writeback is enabled
  v9fs: fix error handling in v9fs_session_init()
  bdi: fix wrong error return value in cgwb_create()
  buffer: remove unusued 'ret' variable
  writeback: disassociate inodes from dying bdi_writebacks
  writeback: implement foreign cgroup inode bdi_writeback switching
  writeback: add lockdep annotation to inode_to_wb()
  writeback: use unlocked_inode_to_wb transaction in inode_congested()
  writeback: implement unlocked_inode_to_wb transaction and use it for stat updates
  writeback: implement [locked_]inode_to_wb_and_lock_list()
  writeback: implement foreign cgroup inode detection
  writeback: make writeback_control track the inode being written back
  writeback: relocate wb[_try]_get(), wb_put(), inode_{attach|detach}_wb()
  mm: vmscan: disable memcg direct reclaim stalling if cgroup writeback support is in use
  writeback: implement memcg writeback domain based throttling
  writeback: reset wb_domain->dirty_limit[_tstmp] when memcg domain size changes
  writeback: implement memcg wb_domain
  writeback: update wb_over_bg_thresh() to use wb_domain aware operations
  ...
This commit is contained in:
Linus Torvalds 2015-06-25 16:00:17 -07:00
commit e4bc13adfd
74 changed files with 3907 additions and 1259 deletions
Download patch file Download diff file Expand all files Collapse all files

569
include/linux/backing-dev.h
View file

@ -8,106 +8,13 @@
#ifndef _LINUX_BACKING_DEV_H
#define _LINUX_BACKING_DEV_H
#include <linux/percpu_counter.h>
#include <linux/log2.h>
#include <linux/flex_proportions.h>
#include <linux/kernel.h>
#include <linux/fs.h>
#include <linux/sched.h>
#include <linux/timer.h>
#include <linux/blkdev.h>
#include <linux/writeback.h>
#include <linux/atomic.h>
#include <linux/sysctl.h>
#include <linux/workqueue.h>
struct page;
struct device;
struct dentry;
/*
* Bits in backing_dev_info.state
*/
enum bdi_state {
BDI_async_congested, /* The async (write) queue is getting full */
BDI_sync_congested, /* The sync queue is getting full */
BDI_registered, /* bdi_register() was done */
BDI_writeback_running, /* Writeback is in progress */
};
typedef int (congested_fn)(void *, int);
enum bdi_stat_item {
BDI_RECLAIMABLE,
BDI_WRITEBACK,
BDI_DIRTIED,
BDI_WRITTEN,
NR_BDI_STAT_ITEMS
};
#define BDI_STAT_BATCH (8*(1+ilog2(nr_cpu_ids)))
struct bdi_writeback {
struct backing_dev_info *bdi; /* our parent bdi */
unsigned long last_old_flush; /* last old data flush */
struct delayed_work dwork; /* work item used for writeback */
struct list_head b_dirty; /* dirty inodes */
struct list_head b_io; /* parked for writeback */
struct list_head b_more_io; /* parked for more writeback */
struct list_head b_dirty_time; /* time stamps are dirty */
spinlock_t list_lock; /* protects the b_* lists */
};
struct backing_dev_info {
struct list_head bdi_list;
unsigned long ra_pages; /* max readahead in PAGE_CACHE_SIZE units */
unsigned long state; /* Always use atomic bitops on this */
unsigned int capabilities; /* Device capabilities */
congested_fn *congested_fn; /* Function pointer if device is md/dm */
void *congested_data; /* Pointer to aux data for congested func */
char *name;
struct percpu_counter bdi_stat[NR_BDI_STAT_ITEMS];
unsigned long bw_time_stamp; /* last time write bw is updated */
unsigned long dirtied_stamp;
unsigned long written_stamp; /* pages written at bw_time_stamp */
unsigned long write_bandwidth; /* the estimated write bandwidth */
unsigned long avg_write_bandwidth; /* further smoothed write bw */
/*
* The base dirty throttle rate, re-calculated on every 200ms.
* All the bdi tasks' dirty rate will be curbed under it.
* @dirty_ratelimit tracks the estimated @balanced_dirty_ratelimit
* in small steps and is much more smooth/stable than the latter.
*/
unsigned long dirty_ratelimit;
unsigned long balanced_dirty_ratelimit;
struct fprop_local_percpu completions;
int dirty_exceeded;
unsigned int min_ratio;
unsigned int max_ratio, max_prop_frac;
struct bdi_writeback wb; /* default writeback info for this bdi */
spinlock_t wb_lock; /* protects work_list & wb.dwork scheduling */
struct list_head work_list;
struct device *dev;
struct timer_list laptop_mode_wb_timer;
#ifdef CONFIG_DEBUG_FS
struct dentry *debug_dir;
struct dentry *debug_stats;
#endif
};
struct backing_dev_info *inode_to_bdi(struct inode *inode);
#include <linux/blk-cgroup.h>
#include <linux/backing-dev-defs.h>
int __must_check bdi_init(struct backing_dev_info *bdi);
void bdi_destroy(struct backing_dev_info *bdi);
@ -117,97 +24,99 @@ int bdi_register(struct backing_dev_info *bdi, struct device *parent,
const char *fmt, ...);
int bdi_register_dev(struct backing_dev_info *bdi, dev_t dev);
int __must_check bdi_setup_and_register(struct backing_dev_info *, char *);
void bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages,
enum wb_reason reason);
void bdi_start_background_writeback(struct backing_dev_info *bdi);
void bdi_writeback_workfn(struct work_struct *work);
int bdi_has_dirty_io(struct backing_dev_info *bdi);
void bdi_wakeup_thread_delayed(struct backing_dev_info *bdi);
void wb_start_writeback(struct bdi_writeback *wb, long nr_pages,
bool range_cyclic, enum wb_reason reason);
void wb_start_background_writeback(struct bdi_writeback *wb);
void wb_workfn(struct work_struct *work);
void wb_wakeup_delayed(struct bdi_writeback *wb);
extern spinlock_t bdi_lock;
extern struct list_head bdi_list;
extern struct workqueue_struct *bdi_wq;
static inline int wb_has_dirty_io(struct bdi_writeback *wb)
static inline bool wb_has_dirty_io(struct bdi_writeback *wb)
{
return !list_empty(&wb->b_dirty) ||
!list_empty(&wb->b_io) ||
!list_empty(&wb->b_more_io);
return test_bit(WB_has_dirty_io, &wb->state);
}
static inline void __add_bdi_stat(struct backing_dev_info *bdi,
enum bdi_stat_item item, s64 amount)
static inline bool bdi_has_dirty_io(struct backing_dev_info *bdi)
{
__percpu_counter_add(&bdi->bdi_stat[item], amount, BDI_STAT_BATCH);
/*
* @bdi->tot_write_bandwidth is guaranteed to be > 0 if there are
* any dirty wbs. See wb_update_write_bandwidth().
*/
return atomic_long_read(&bdi->tot_write_bandwidth);
}
static inline void __inc_bdi_stat(struct backing_dev_info *bdi,
enum bdi_stat_item item)
static inline void __add_wb_stat(struct bdi_writeback *wb,
enum wb_stat_item item, s64 amount)
{
__add_bdi_stat(bdi, item, 1);
__percpu_counter_add(&wb->stat[item], amount, WB_STAT_BATCH);
}
static inline void inc_bdi_stat(struct backing_dev_info *bdi,
enum bdi_stat_item item)
static inline void __inc_wb_stat(struct bdi_writeback *wb,
enum wb_stat_item item)
{
__add_wb_stat(wb, item, 1);
}
static inline void inc_wb_stat(struct bdi_writeback *wb, enum wb_stat_item item)
{
unsigned long flags;
local_irq_save(flags);
__inc_bdi_stat(bdi, item);
__inc_wb_stat(wb, item);
local_irq_restore(flags);
}
static inline void __dec_bdi_stat(struct backing_dev_info *bdi,
enum bdi_stat_item item)
static inline void __dec_wb_stat(struct bdi_writeback *wb,
enum wb_stat_item item)
{
__add_bdi_stat(bdi, item, -1);
__add_wb_stat(wb, item, -1);
}
static inline void dec_bdi_stat(struct backing_dev_info *bdi,
enum bdi_stat_item item)
static inline void dec_wb_stat(struct bdi_writeback *wb, enum wb_stat_item item)
{
unsigned long flags;
local_irq_save(flags);
__dec_bdi_stat(bdi, item);
__dec_wb_stat(wb, item);
local_irq_restore(flags);
}
static inline s64 bdi_stat(struct backing_dev_info *bdi,
enum bdi_stat_item item)
static inline s64 wb_stat(struct bdi_writeback *wb, enum wb_stat_item item)
{
return percpu_counter_read_positive(&bdi->bdi_stat[item]);
return percpu_counter_read_positive(&wb->stat[item]);
}
static inline s64 __bdi_stat_sum(struct backing_dev_info *bdi,
enum bdi_stat_item item)
static inline s64 __wb_stat_sum(struct bdi_writeback *wb,
enum wb_stat_item item)
{
return percpu_counter_sum_positive(&bdi->bdi_stat[item]);
return percpu_counter_sum_positive(&wb->stat[item]);
}
static inline s64 bdi_stat_sum(struct backing_dev_info *bdi,
enum bdi_stat_item item)
static inline s64 wb_stat_sum(struct bdi_writeback *wb, enum wb_stat_item item)
{
s64 sum;
unsigned long flags;
local_irq_save(flags);
sum = __bdi_stat_sum(bdi, item);
sum = __wb_stat_sum(wb, item);
local_irq_restore(flags);
return sum;
}
extern void bdi_writeout_inc(struct backing_dev_info *bdi);
extern void wb_writeout_inc(struct bdi_writeback *wb);
/*
* maximal error of a stat counter.
*/
static inline unsigned long bdi_stat_error(struct backing_dev_info *bdi)
static inline unsigned long wb_stat_error(struct bdi_writeback *wb)
{
#ifdef CONFIG_SMP
return nr_cpu_ids * BDI_STAT_BATCH;
return nr_cpu_ids * WB_STAT_BATCH;
#else
return 1;
#endif
@ -231,50 +140,57 @@ int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned int max_ratio);
* BDI_CAP_NO_WRITEBACK: Don't write pages back
* BDI_CAP_NO_ACCT_WB: Don't automatically account writeback pages
* BDI_CAP_STRICTLIMIT: Keep number of dirty pages below bdi threshold.
*
* BDI_CAP_CGROUP_WRITEBACK: Supports cgroup-aware writeback.
*/
#define BDI_CAP_NO_ACCT_DIRTY 0x00000001
#define BDI_CAP_NO_WRITEBACK 0x00000002
#define BDI_CAP_NO_ACCT_WB 0x00000004
#define BDI_CAP_STABLE_WRITES 0x00000008
#define BDI_CAP_STRICTLIMIT 0x00000010
#define BDI_CAP_CGROUP_WRITEBACK 0x00000020
#define BDI_CAP_NO_ACCT_AND_WRITEBACK \
(BDI_CAP_NO_WRITEBACK | BDI_CAP_NO_ACCT_DIRTY | BDI_CAP_NO_ACCT_WB)
extern struct backing_dev_info noop_backing_dev_info;
int writeback_in_progress(struct backing_dev_info *bdi);
static inline int bdi_congested(struct backing_dev_info *bdi, int bdi_bits)
/**
* writeback_in_progress - determine whether there is writeback in progress
* @wb: bdi_writeback of interest
*
* Determine whether there is writeback waiting to be handled against a
* bdi_writeback.
*/
static inline bool writeback_in_progress(struct bdi_writeback *wb)
{
return test_bit(WB_writeback_running, &wb->state);
}
static inline struct backing_dev_info *inode_to_bdi(struct inode *inode)
{
struct super_block *sb;
if (!inode)
return &noop_backing_dev_info;
sb = inode->i_sb;
#ifdef CONFIG_BLOCK
if (sb_is_blkdev_sb(sb))
return blk_get_backing_dev_info(I_BDEV(inode));
#endif
return sb->s_bdi;
}
static inline int wb_congested(struct bdi_writeback *wb, int cong_bits)
{
struct backing_dev_info *bdi = wb->bdi;
if (bdi->congested_fn)
return bdi->congested_fn(bdi->congested_data, bdi_bits);
return (bdi->state & bdi_bits);
return bdi->congested_fn(bdi->congested_data, cong_bits);
return wb->congested->state & cong_bits;
}
static inline int bdi_read_congested(struct backing_dev_info *bdi)
{
return bdi_congested(bdi, 1 << BDI_sync_congested);
}
static inline int bdi_write_congested(struct backing_dev_info *bdi)
{
return bdi_congested(bdi, 1 << BDI_async_congested);
}
static inline int bdi_rw_congested(struct backing_dev_info *bdi)
{
return bdi_congested(bdi, (1 << BDI_sync_congested) |
(1 << BDI_async_congested));
}
enum {
BLK_RW_ASYNC = 0,
BLK_RW_SYNC = 1,
};
void clear_bdi_congested(struct backing_dev_info *bdi, int sync);
void set_bdi_congested(struct backing_dev_info *bdi, int sync);
long congestion_wait(int sync, long timeout);
long wait_iff_congested(struct zone *zone, int sync, long timeout);
int pdflush_proc_obsolete(struct ctl_table *table, int write,
@ -318,4 +234,333 @@ static inline int bdi_sched_wait(void *word)
return 0;
}
#endif /* _LINUX_BACKING_DEV_H */
#ifdef CONFIG_CGROUP_WRITEBACK
struct bdi_writeback_congested *
wb_congested_get_create(struct backing_dev_info *bdi, int blkcg_id, gfp_t gfp);
void wb_congested_put(struct bdi_writeback_congested *congested);
struct bdi_writeback *wb_get_create(struct backing_dev_info *bdi,
struct cgroup_subsys_state *memcg_css,
gfp_t gfp);
void wb_memcg_offline(struct mem_cgroup *memcg);
void wb_blkcg_offline(struct blkcg *blkcg);
int inode_congested(struct inode *inode, int cong_bits);
/**
* inode_cgwb_enabled - test whether cgroup writeback is enabled on an inode
* @inode: inode of interest
*
* cgroup writeback requires support from both the bdi and filesystem.
* Test whether @inode has both.
*/
static inline bool inode_cgwb_enabled(struct inode *inode)
{
struct backing_dev_info *bdi = inode_to_bdi(inode);
return bdi_cap_account_dirty(bdi) &&
(bdi->capabilities & BDI_CAP_CGROUP_WRITEBACK) &&
(inode->i_sb->s_iflags & SB_I_CGROUPWB);
}
/**
* wb_find_current - find wb for %current on a bdi
* @bdi: bdi of interest
*
* Find the wb of @bdi which matches both the memcg and blkcg of %current.
* Must be called under rcu_read_lock() which protects the returend wb.
* NULL if not found.
*/
static inline struct bdi_writeback *wb_find_current(struct backing_dev_info *bdi)
{
struct cgroup_subsys_state *memcg_css;
struct bdi_writeback *wb;
memcg_css = task_css(current, memory_cgrp_id);
if (!memcg_css->parent)
return &bdi->wb;
wb = radix_tree_lookup(&bdi->cgwb_tree, memcg_css->id);
/*
* %current's blkcg equals the effective blkcg of its memcg. No
* need to use the relatively expensive cgroup_get_e_css().
*/
if (likely(wb && wb->blkcg_css == task_css(current, blkio_cgrp_id)))
return wb;
return NULL;
}
/**
* wb_get_create_current - get or create wb for %current on a bdi
* @bdi: bdi of interest
* @gfp: allocation mask
*
* Equivalent to wb_get_create() on %current's memcg. This function is
* called from a relatively hot path and optimizes the common cases using
* wb_find_current().
*/
static inline struct bdi_writeback *
wb_get_create_current(struct backing_dev_info *bdi, gfp_t gfp)
{
struct bdi_writeback *wb;
rcu_read_lock();
wb = wb_find_current(bdi);
if (wb && unlikely(!wb_tryget(wb)))
wb = NULL;
rcu_read_unlock();
if (unlikely(!wb)) {
struct cgroup_subsys_state *memcg_css;
memcg_css = task_get_css(current, memory_cgrp_id);
wb = wb_get_create(bdi, memcg_css, gfp);
css_put(memcg_css);
}
return wb;
}
/**
* inode_to_wb_is_valid - test whether an inode has a wb associated
* @inode: inode of interest
*
* Returns %true if @inode has a wb associated. May be called without any
* locking.
*/
static inline bool inode_to_wb_is_valid(struct inode *inode)
{
return inode->i_wb;
}
/**
* inode_to_wb - determine the wb of an inode
* @inode: inode of interest
*
* Returns the wb @inode is currently associated with. The caller must be
* holding either @inode->i_lock, @inode->i_mapping->tree_lock, or the
* associated wb's list_lock.
*/
static inline struct bdi_writeback *inode_to_wb(struct inode *inode)
{
#ifdef CONFIG_LOCKDEP
WARN_ON_ONCE(debug_locks &&
(!lockdep_is_held(&inode->i_lock) &&
!lockdep_is_held(&inode->i_mapping->tree_lock) &&
!lockdep_is_held(&inode->i_wb->list_lock)));
#endif
return inode->i_wb;
}
/**
* unlocked_inode_to_wb_begin - begin unlocked inode wb access transaction
* @inode: target inode
* @lockedp: temp bool output param, to be passed to the end function
*
* The caller wants to access the wb associated with @inode but isn't
* holding inode->i_lock, mapping->tree_lock or wb->list_lock. This
* function determines the wb associated with @inode and ensures that the
* association doesn't change until the transaction is finished with
* unlocked_inode_to_wb_end().
*
* The caller must call unlocked_inode_to_wb_end() with *@lockdep
* afterwards and can't sleep during transaction. IRQ may or may not be
* disabled on return.
*/
static inline struct bdi_writeback *
unlocked_inode_to_wb_begin(struct inode *inode, bool *lockedp)
{
rcu_read_lock();
/*
* Paired with store_release in inode_switch_wb_work_fn() and
* ensures that we see the new wb if we see cleared I_WB_SWITCH.
*/
*lockedp = smp_load_acquire(&inode->i_state) & I_WB_SWITCH;
if (unlikely(*lockedp))
spin_lock_irq(&inode->i_mapping->tree_lock);
/*
* Protected by either !I_WB_SWITCH + rcu_read_lock() or tree_lock.
* inode_to_wb() will bark. Deref directly.
*/
return inode->i_wb;
}
/**
* unlocked_inode_to_wb_end - end inode wb access transaction
* @inode: target inode
* @locked: *@lockedp from unlocked_inode_to_wb_begin()
*/
static inline void unlocked_inode_to_wb_end(struct inode *inode, bool locked)
{
if (unlikely(locked))
spin_unlock_irq(&inode->i_mapping->tree_lock);
rcu_read_unlock();
}
struct wb_iter {
int start_blkcg_id;
struct radix_tree_iter tree_iter;
void **slot;
};
static inline struct bdi_writeback *__wb_iter_next(struct wb_iter *iter,
struct backing_dev_info *bdi)
{
struct radix_tree_iter *titer = &iter->tree_iter;
WARN_ON_ONCE(!rcu_read_lock_held());
if (iter->start_blkcg_id >= 0) {
iter->slot = radix_tree_iter_init(titer, iter->start_blkcg_id);
iter->start_blkcg_id = -1;
} else {
iter->slot = radix_tree_next_slot(iter->slot, titer, 0);
}
if (!iter->slot)
iter->slot = radix_tree_next_chunk(&bdi->cgwb_tree, titer, 0);
if (iter->slot)
return *iter->slot;
return NULL;
}
static inline struct bdi_writeback *__wb_iter_init(struct wb_iter *iter,
struct backing_dev_info *bdi,
int start_blkcg_id)
{
iter->start_blkcg_id = start_blkcg_id;
if (start_blkcg_id)
return __wb_iter_next(iter, bdi);
else
return &bdi->wb;
}
/**
* bdi_for_each_wb - walk all wb's of a bdi in ascending blkcg ID order
* @wb_cur: cursor struct bdi_writeback pointer
* @bdi: bdi to walk wb's of
* @iter: pointer to struct wb_iter to be used as iteration buffer
* @start_blkcg_id: blkcg ID to start iteration from
*
* Iterate @wb_cur through the wb's (bdi_writeback's) of @bdi in ascending
* blkcg ID order starting from @start_blkcg_id. @iter is struct wb_iter
* to be used as temp storage during iteration. rcu_read_lock() must be
* held throughout iteration.
*/
#define bdi_for_each_wb(wb_cur, bdi, iter, start_blkcg_id) \
for ((wb_cur) = __wb_iter_init(iter, bdi, start_blkcg_id); \
(wb_cur); (wb_cur) = __wb_iter_next(iter, bdi))
#else /* CONFIG_CGROUP_WRITEBACK */
static inline bool inode_cgwb_enabled(struct inode *inode)
{
return false;
}
static inline struct bdi_writeback_congested *
wb_congested_get_create(struct backing_dev_info *bdi, int blkcg_id, gfp_t gfp)
{
return bdi->wb.congested;
}
static inline void wb_congested_put(struct bdi_writeback_congested *congested)
{
}
static inline struct bdi_writeback *wb_find_current(struct backing_dev_info *bdi)
{
return &bdi->wb;
}
static inline struct bdi_writeback *
wb_get_create_current(struct backing_dev_info *bdi, gfp_t gfp)
{
return &bdi->wb;
}
static inline bool inode_to_wb_is_valid(struct inode *inode)
{
return true;
}
static inline struct bdi_writeback *inode_to_wb(struct inode *inode)
{
return &inode_to_bdi(inode)->wb;
}
static inline struct bdi_writeback *
unlocked_inode_to_wb_begin(struct inode *inode, bool *lockedp)
{
return inode_to_wb(inode);
}
static inline void unlocked_inode_to_wb_end(struct inode *inode, bool locked)
{
}
static inline void wb_memcg_offline(struct mem_cgroup *memcg)
{
}
static inline void wb_blkcg_offline(struct blkcg *blkcg)
{
}
struct wb_iter {
int next_id;
};
#define bdi_for_each_wb(wb_cur, bdi, iter, start_blkcg_id) \
for ((iter)->next_id = (start_blkcg_id); \
({ (wb_cur) = !(iter)->next_id++ ? &(bdi)->wb : NULL; }); )
static inline int inode_congested(struct inode *inode, int cong_bits)
{
return wb_congested(&inode_to_bdi(inode)->wb, cong_bits);
}
#endif /* CONFIG_CGROUP_WRITEBACK */
static inline int inode_read_congested(struct inode *inode)
{
return inode_congested(inode, 1 << WB_sync_congested);
}
static inline int inode_write_congested(struct inode *inode)
{
return inode_congested(inode, 1 << WB_async_congested);
}
static inline int inode_rw_congested(struct inode *inode)
{
return inode_congested(inode, (1 << WB_sync_congested) |
(1 << WB_async_congested));
}
static inline int bdi_congested(struct backing_dev_info *bdi, int cong_bits)
{
return wb_congested(&bdi->wb, cong_bits);
}
static inline int bdi_read_congested(struct backing_dev_info *bdi)
{
return bdi_congested(bdi, 1 << WB_sync_congested);
}
static inline int bdi_write_congested(struct backing_dev_info *bdi)
{
return bdi_congested(bdi, 1 << WB_async_congested);
}
static inline int bdi_rw_congested(struct backing_dev_info *bdi)
{
return bdi_congested(bdi, (1 << WB_sync_congested) |
(1 << WB_async_congested));
}
#endif /* _LINUX_BACKING_DEV_H */