diff options
Diffstat (limited to 'include/linux/backing-dev-defs.h')
| -rw-r--r-- | include/linux/backing-dev-defs.h | 148 |
1 files changed, 94 insertions, 54 deletions
diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h index 866c433e7d32..0217c1073735 100644 --- a/include/linux/backing-dev-defs.h +++ b/include/linux/backing-dev-defs.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_BACKING_DEV_DEFS_H #define __LINUX_BACKING_DEV_DEFS_H @@ -11,6 +12,7 @@ #include <linux/timer.h> #include <linux/workqueue.h> #include <linux/kref.h> +#include <linux/refcount.h> struct page; struct device; @@ -21,18 +23,11 @@ struct dentry; */ enum wb_state { WB_registered, /* bdi_register() was done */ - WB_shutting_down, /* wb_shutdown() in progress */ WB_writeback_running, /* Writeback is in progress */ WB_has_dirty_io, /* Dirty inodes on ->b_{dirty|io|more_io} */ + WB_start_all, /* nr_pages == 0 (all) work pending */ }; -enum wb_congested_state { - WB_async_congested, /* The async (write) queue is getting full */ - WB_sync_congested, /* The sync queue is getting full */ -}; - -typedef int (congested_fn)(void *, int); - enum wb_stat_item { WB_RECLAIMABLE, WB_WRITEBACK, @@ -44,25 +39,49 @@ enum wb_stat_item { #define WB_STAT_BATCH (8*(1+ilog2(nr_cpu_ids))) /* - * For cgroup writeback, multiple wb's may map to the same blkcg. Those - * wb's can operate mostly independently but should share the congested - * state. To facilitate such sharing, the congested state is tracked using - * the following struct which is created on demand, indexed by blkcg ID on - * its bdi, and refcounted. + * why some writeback work was initiated */ -struct bdi_writeback_congested { - unsigned long state; /* WB_[a]sync_congested flags */ - atomic_t refcnt; /* nr of attached wb's and blkg */ +enum wb_reason { + WB_REASON_BACKGROUND, + WB_REASON_VMSCAN, + WB_REASON_SYNC, + WB_REASON_PERIODIC, + WB_REASON_LAPTOP_TIMER, + 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_FOREIGN_FLUSH, -#ifdef CONFIG_CGROUP_WRITEBACK - struct backing_dev_info *__bdi; /* the associated bdi, set to NULL - * on bdi unregistration. For memcg-wb - * internal use only! */ - int blkcg_id; /* ID of the associated blkcg */ - struct rb_node rb_node; /* on bdi->cgwb_congestion_tree */ -#endif + WB_REASON_MAX, +}; + +struct wb_completion { + atomic_t cnt; + wait_queue_head_t *waitq; + unsigned long progress_stamp; /* The jiffies when slow progress is detected */ + unsigned long wait_start; /* The jiffies when waiting for the writeback work to finish */ }; +#define __WB_COMPLETION_INIT(_waitq) \ + (struct wb_completion){ .cnt = ATOMIC_INIT(1), .waitq = (_waitq) } + +/* + * If one wants to wait for one or more wb_writeback_works, each work's + * ->done should be set to a wb_completion defined using the following + * macro. Once all work items are issued with wb_queue_work(), the caller + * can wait for the completion of all using wb_wait_for_completion(). Work + * items which are waited upon aren't freed automatically on completion. + */ +#define WB_COMPLETION_INIT(bdi) __WB_COMPLETION_INIT(&(bdi)->wb_waitq) + +#define DEFINE_WB_COMPLETION(cmpl, bdi) \ + struct wb_completion cmpl = WB_COMPLETION_INIT(bdi) + /* * Each wb (bdi_writeback) can perform writeback operations, is measured * and throttled, independently. Without cgroup writeback, each bdi @@ -81,6 +100,9 @@ struct bdi_writeback_congested { * change as blkcg is disabled and enabled higher up in the hierarchy, a wb * is tested for blkcg after lookup and removed from index on mismatch so * that a new wb for the combination can be created. + * + * Each bdi_writeback that is not embedded into the backing_dev_info must hold + * a reference to the parent backing_dev_info. See cgwb_create() for details. */ struct bdi_writeback { struct backing_dev_info *bdi; /* our parent bdi */ @@ -94,10 +116,9 @@ struct bdi_writeback { struct list_head b_dirty_time; /* time stamps are dirty */ spinlock_t list_lock; /* protects the b_* lists */ + atomic_t writeback_inodes; /* number of inodes under writeback */ struct percpu_counter stat[NR_WB_STAT_ITEMS]; - struct bdi_writeback_congested *congested; - 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 */ @@ -115,12 +136,12 @@ struct bdi_writeback { struct fprop_local_percpu completions; int dirty_exceeded; + enum wb_reason start_all_reason; spinlock_t work_lock; /* protects work_list & dwork scheduling */ struct list_head work_list; struct delayed_work dwork; /* work item used for writeback */ - - unsigned long dirty_sleep; /* last wait */ + struct delayed_work bw_dwork; /* work item used for bandwidth estimate */ struct list_head bdi_node; /* anchored at bdi->wb_list */ @@ -131,6 +152,12 @@ struct bdi_writeback { struct cgroup_subsys_state *blkcg_css; /* and blkcg */ struct list_head memcg_node; /* anchored at memcg->cgwb_list */ struct list_head blkcg_node; /* anchored at blkcg->cgwb_list */ + struct list_head b_attached; /* attached inodes, protected by list_lock */ + struct list_head offline_node; /* anchored at offline_cgwbs */ + struct work_struct switch_work; /* work used to perform inode switching + * to this wb */ + struct llist_head switch_wbs_ctxs; /* queued contexts for + * writeback switching */ union { struct work_struct release_work; @@ -140,13 +167,13 @@ struct bdi_writeback { }; struct backing_dev_info { + u64 id; + struct rb_node rb_node; /* keyed by ->id */ struct list_head bdi_list; - unsigned long ra_pages; /* max readahead in PAGE_SIZE units */ - unsigned long io_pages; /* max allowed IO size */ - congested_fn *congested_fn; /* Function pointer if device is md/dm */ - void *congested_data; /* Pointer to aux data for congested func */ + /* max readahead in PAGE_SIZE units */ + unsigned long __data_racy ra_pages; - const char *name; + unsigned long io_pages; /* max allowed IO size */ struct kref refcnt; /* Reference counter for the structure */ unsigned int capabilities; /* Device capabilities */ @@ -158,46 +185,37 @@ struct backing_dev_info { * any dirty wbs, which is depended upon by bdi_has_dirty(). */ atomic_long_t tot_write_bandwidth; + /* + * Jiffies when last process was dirty throttled on this bdi. Used by + * blk-wbt. + */ + unsigned long last_bdp_sleep; struct bdi_writeback wb; /* the root writeback info for this bdi */ struct list_head wb_list; /* list of all wbs */ #ifdef CONFIG_CGROUP_WRITEBACK struct radix_tree_root cgwb_tree; /* radix tree of active cgroup wbs */ - struct rb_root cgwb_congested_tree; /* their congested states */ -#else - struct bdi_writeback_congested *wb_congested; + struct mutex cgwb_release_mutex; /* protect shutdown of wb structs */ + struct rw_semaphore wb_switch_rwsem; /* no cgwb switch while syncing */ #endif wait_queue_head_t wb_waitq; struct device *dev; + char dev_name[64]; struct device *owner; struct timer_list laptop_mode_wb_timer; #ifdef CONFIG_DEBUG_FS struct dentry *debug_dir; - struct dentry *debug_stats; #endif }; -enum { - BLK_RW_ASYNC = 0, - BLK_RW_SYNC = 1, +struct wb_lock_cookie { + bool locked; + unsigned long flags; }; -void clear_wb_congested(struct bdi_writeback_congested *congested, int sync); -void set_wb_congested(struct bdi_writeback_congested *congested, int sync); - -static inline void clear_bdi_congested(struct backing_dev_info *bdi, int sync) -{ - clear_wb_congested(bdi->wb.congested, sync); -} - -static inline void set_bdi_congested(struct backing_dev_info *bdi, int sync) -{ - set_wb_congested(bdi->wb.congested, sync); -} - #ifdef CONFIG_CGROUP_WRITEBACK /** @@ -224,11 +242,29 @@ static inline void wb_get(struct bdi_writeback *wb) /** * wb_put - decrement a wb's refcount * @wb: bdi_writeback to put + * @nr: number of references to put */ -static inline void wb_put(struct bdi_writeback *wb) +static inline void wb_put_many(struct bdi_writeback *wb, unsigned long nr) { + if (WARN_ON_ONCE(!wb->bdi)) { + /* + * A driver bug might cause a file to be removed before bdi was + * initialized. + */ + return; + } + if (wb != &wb->bdi->wb) - percpu_ref_put(&wb->refcnt); + percpu_ref_put_many(&wb->refcnt, nr); +} + +/** + * wb_put - decrement a wb's refcount + * @wb: bdi_writeback to put + */ +static inline void wb_put(struct bdi_writeback *wb) +{ + wb_put_many(wb, 1); } /** @@ -257,6 +293,10 @@ static inline void wb_put(struct bdi_writeback *wb) { } +static inline void wb_put_many(struct bdi_writeback *wb, unsigned long nr) +{ +} + static inline bool wb_dying(struct bdi_writeback *wb) { return false; |