diff options
Diffstat (limited to 'include/linux/writeback.h')
| -rw-r--r-- | include/linux/writeback.h | 234 |
1 files changed, 107 insertions, 127 deletions
diff --git a/include/linux/writeback.h b/include/linux/writeback.h index d5815794416c..f48e8ccffe81 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * include/linux/writeback.h */ @@ -10,26 +11,19 @@ #include <linux/flex_proportions.h> #include <linux/backing-dev-defs.h> #include <linux/blk_types.h> +#include <linux/pagevec.h> struct bio; 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; @@ -42,33 +36,12 @@ enum writeback_sync_modes { }; /* - * why some writeback work was initiated - */ -enum wb_reason { - WB_REASON_BACKGROUND, - WB_REASON_VMSCAN, - 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 { + /* public fields that can be set and/or consumed by the caller: */ long nr_to_write; /* Write this many pages, and decrement this for each page written */ long pages_skipped; /* Pages which were not written */ @@ -86,9 +59,23 @@ struct writeback_control { 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 */ + unsigned unpinned_netfs_wb:1; /* Cleared I_PINNING_NETFS_WB */ + + /* + * When writeback IOs are bounced through async layers, only the + * initial synchronous phase should be accounted towards inode + * cgroup ownership arbitration to avoid confusion. Later stages + * can set the following flag to disable the accounting. + */ + unsigned no_cgroup_owner:1; + + /* internal fields used by the ->writepages implementation: */ + struct folio_batch fbatch; + pgoff_t index; + int saved_err; + #ifdef CONFIG_CGROUP_WRITEBACK struct bdi_writeback *wb; /* wb this writeback is issued under */ struct inode *inode; /* inode being written out */ @@ -103,16 +90,25 @@ struct writeback_control { #endif }; -static inline int wbc_to_write_flags(struct writeback_control *wbc) +static inline blk_opf_t wbc_to_write_flags(struct writeback_control *wbc) { + blk_opf_t flags = 0; + if (wbc->sync_mode == WB_SYNC_ALL) - return REQ_SYNC; + flags |= REQ_SYNC; else if (wbc->for_kupdate || wbc->for_background) - return REQ_BACKGROUND; + flags |= REQ_BACKGROUND; - return 0; + return flags; } +#ifdef CONFIG_CGROUP_WRITEBACK +#define wbc_blkcg_css(wbc) \ + ((wbc)->wb ? (wbc)->wb->blkcg_css : blkcg_root_css) +#else +#define wbc_blkcg_css(wbc) (blkcg_root_css) +#endif /* CONFIG_CGROUP_WRITEBACK */ + /* * A wb_domain represents a domain that wb's (bdi_writeback's) belong to * and are measured against each other in. There always is one global @@ -185,18 +181,19 @@ 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); -bool try_to_writeback_inodes_sb(struct super_block *, enum wb_reason reason); -bool try_to_writeback_inodes_sb_nr(struct super_block *, unsigned long nr, - enum wb_reason reason); +void try_to_writeback_inodes_sb(struct super_block *sb, enum wb_reason reason); void sync_inodes_sb(struct super_block *); -void wakeup_flusher_threads(long nr_pages, enum wb_reason reason); +void wakeup_flusher_threads(enum wb_reason reason); +void wakeup_flusher_threads_bdi(struct backing_dev_info *bdi, + enum wb_reason reason); void inode_wait_for_writeback(struct inode *inode); +void inode_io_list_del(struct inode *inode); -/* writeback.h requires fs.h; it, too, is not included from here. */ -static inline void wait_on_inode(struct inode *inode) +static inline xa_mark_t wbc_to_tag(struct writeback_control *wbc) { - might_sleep(); - wait_on_bit(&inode->i_state, __I_NEW, TASK_UNINTERRUPTIBLE); + if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages) + return PAGECACHE_TAG_TOWRITE; + return PAGECACHE_TAG_DIRTY; } #ifdef CONFIG_CGROUP_WRITEBACK @@ -204,28 +201,28 @@ static inline void wait_on_inode(struct inode *inode) #include <linux/cgroup.h> #include <linux/bio.h> -void __inode_attach_wb(struct inode *inode, struct page *page); -void wbc_attach_and_unlock_inode(struct writeback_control *wbc, - struct inode *inode) - __releases(&inode->i_lock); +void __inode_attach_wb(struct inode *inode, struct folio *folio); void wbc_detach_inode(struct writeback_control *wbc); -void wbc_account_io(struct writeback_control *wbc, struct page *page, - size_t bytes); -void cgroup_writeback_umount(void); +void wbc_account_cgroup_owner(struct writeback_control *wbc, struct folio *folio, + size_t bytes); +int cgroup_writeback_by_id(u64 bdi_id, int memcg_id, + enum wb_reason reason, struct wb_completion *done); +void cgroup_writeback_umount(struct super_block *sb); +bool cleanup_offline_cgwb(struct bdi_writeback *wb); /** * inode_attach_wb - associate an inode with its wb * @inode: inode of interest - * @page: page being dirtied (may be NULL) + * @folio: folio being dirtied (may be NULL) * * If @inode doesn't have its wb, associate it with the wb matching the - * memcg of @page or, if @page is NULL, %current. May be called w/ or w/o + * memcg of @folio or, if @folio is NULL, %current. May be called w/ or w/o * @inode->i_lock. */ -static inline void inode_attach_wb(struct inode *inode, struct page *page) +static inline void inode_attach_wb(struct inode *inode, struct folio *folio) { if (!inode->i_wb) - __inode_attach_wb(inode, page); + __inode_attach_wb(inode, folio); } /** @@ -237,28 +234,14 @@ static inline void inode_attach_wb(struct inode *inode, struct page *page) static inline void inode_detach_wb(struct inode *inode) { if (inode->i_wb) { - WARN_ON_ONCE(!(inode->i_state & I_CLEAR)); + WARN_ON_ONCE(!(inode_state_read_once(inode) & I_CLEAR)); wb_put(inode->i_wb); inode->i_wb = NULL; } } -/** - * wbc_attach_fdatawrite_inode - associate wbc and inode for fdatawrite - * @wbc: writeback_control of interest - * @inode: target inode - * - * This function is to be used by __filemap_fdatawrite_range(), which is an - * alternative entry point into writeback code, and first ensures @inode is - * associated with a bdi_writeback and attaches it to @wbc. - */ -static inline void wbc_attach_fdatawrite_inode(struct writeback_control *wbc, - struct inode *inode) -{ - spin_lock(&inode->i_lock); - inode_attach_wb(inode, NULL); - wbc_attach_and_unlock_inode(wbc, inode); -} +void wbc_attach_fdatawrite_inode(struct writeback_control *wbc, + struct inode *inode); /** * wbc_init_bio - writeback specific initializtion of bio @@ -267,7 +250,8 @@ static inline void wbc_attach_fdatawrite_inode(struct writeback_control *wbc, * * @bio is a part of the writeback in progress controlled by @wbc. Perform * writeback specific initialization. This is used to apply the cgroup - * writeback context. + * writeback context. Must be called after the bio has been associated with + * a device. */ static inline void wbc_init_bio(struct writeback_control *wbc, struct bio *bio) { @@ -278,12 +262,14 @@ static inline void wbc_init_bio(struct writeback_control *wbc, struct bio *bio) * regular writeback instead of writing things out itself. */ if (wbc->wb) - bio_associate_blkcg(bio, wbc->wb->blkcg_css); + bio_associate_blkg_from_css(bio, wbc->wb->blkcg_css); } +void inode_switch_wbs_work_fn(struct work_struct *work); + #else /* CONFIG_CGROUP_WRITEBACK */ -static inline void inode_attach_wb(struct inode *inode, struct page *page) +static inline void inode_attach_wb(struct inode *inode, struct folio *folio) { } @@ -291,13 +277,6 @@ static inline void inode_detach_wb(struct inode *inode) { } -static inline void wbc_attach_and_unlock_inode(struct writeback_control *wbc, - struct inode *inode) - __releases(&inode->i_lock) -{ - spin_unlock(&inode->i_lock); -} - static inline void wbc_attach_fdatawrite_inode(struct writeback_control *wbc, struct inode *inode) { @@ -311,12 +290,12 @@ static inline void wbc_init_bio(struct writeback_control *wbc, struct bio *bio) { } -static inline void wbc_account_io(struct writeback_control *wbc, - struct page *page, size_t bytes) +static inline void wbc_account_cgroup_owner(struct writeback_control *wbc, + struct folio *folio, size_t bytes) { } -static inline void cgroup_writeback_umount(void) +static inline void cgroup_writeback_umount(struct super_block *sb) { } @@ -325,14 +304,33 @@ static inline void cgroup_writeback_umount(void) /* * mm/page-writeback.c */ -#ifdef CONFIG_BLOCK +/* consolidated parameters for balance_dirty_pages() and its subroutines */ +struct dirty_throttle_control { +#ifdef CONFIG_CGROUP_WRITEBACK + struct wb_domain *dom; + struct dirty_throttle_control *gdtc; /* only set in memcg dtc's */ +#endif + struct bdi_writeback *wb; + struct fprop_local_percpu *wb_completions; + + unsigned long avail; /* dirtyable */ + unsigned long dirty; /* file_dirty + write + nfs */ + unsigned long thresh; /* dirty threshold */ + unsigned long bg_thresh; /* dirty background threshold */ + unsigned long limit; /* hard dirty limit */ + + unsigned long wb_dirty; /* per-wb counterparts */ + unsigned long wb_thresh; + unsigned long wb_bg_thresh; + + unsigned long pos_ratio; + bool freerun; + bool dirty_exceeded; +}; + 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 laptop_mode_timer_fn(struct timer_list *t); bool node_dirty_ok(struct pglist_data *pgdat); int wb_domain_init(struct wb_domain *dom, gfp_t gfp); #ifdef CONFIG_CGROUP_WRITEBACK @@ -342,61 +340,43 @@ void wb_domain_exit(struct wb_domain *dom); extern struct wb_domain global_wb_domain; /* 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_calc_thresh(struct bdi_writeback *wb, unsigned long thresh); +unsigned long cgwb_calc_thresh(struct bdi_writeback *wb); + +void wb_update_bandwidth(struct bdi_writeback *wb); + +/* Invoke balance dirty pages in async mode. */ +#define BDP_ASYNC 0x0001 -void wb_update_bandwidth(struct bdi_writeback *wb, unsigned long start_time); void balance_dirty_pages_ratelimited(struct address_space *mapping); +int balance_dirty_pages_ratelimited_flags(struct address_space *mapping, + unsigned int flags); + bool wb_over_bg_thresh(struct bdi_writeback *wb); -typedef int (*writepage_t)(struct page *page, struct writeback_control *wbc, - void *data); +struct folio *writeback_iter(struct address_space *mapping, + struct writeback_control *wbc, struct folio *folio, int *error); -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); +bool filemap_dirty_folio(struct address_space *mapping, struct folio *folio); +bool folio_redirty_for_writepage(struct writeback_control *, struct folio *); +bool redirty_page_for_writepage(struct writeback_control *, struct page *); void sb_mark_inode_writeback(struct inode *inode); void sb_clear_inode_writeback(struct inode *inode); +/* + * 4MB minimal write chunk size + */ +#define MIN_WRITEBACK_PAGES (4096UL >> (PAGE_SHIFT - 10)) + #endif /* WRITEBACK_H */ |