diff options
Diffstat (limited to 'fs/fs-writeback.c')
| -rw-r--r-- | fs/fs-writeback.c | 2505 |
1 files changed, 2005 insertions, 500 deletions
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 68851ff2fd41..6800886c4d10 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * fs/fs-writeback.c * @@ -13,6 +14,7 @@ * Additions for address_space-based writeback */ +#include <linux/sched/sysctl.h> #include <linux/kernel.h> #include <linux/export.h> #include <linux/spinlock.h> @@ -26,153 +28,1390 @@ #include <linux/blkdev.h> #include <linux/backing-dev.h> #include <linux/tracepoint.h> +#include <linux/device.h> +#include <linux/memcontrol.h> #include "internal.h" /* - * 4MB minimal write chunk size - */ -#define MIN_WRITEBACK_PAGES (4096UL >> (PAGE_CACHE_SHIFT - 10)) - -/* * Passed into wb_writeback(), essentially a subset of writeback_control */ struct wb_writeback_work { long nr_pages; struct super_block *sb; - unsigned long *older_than_this; enum writeback_sync_modes sync_mode; unsigned int tagged_writepages:1; unsigned int for_kupdate:1; unsigned int range_cyclic:1; unsigned int for_background:1; unsigned int for_sync:1; /* sync(2) WB_SYNC_ALL writeback */ + unsigned int auto_free:1; /* free on completion */ enum wb_reason reason; /* why was writeback initiated? */ struct list_head list; /* pending work list */ - struct completion *done; /* set if the caller waits */ + struct wb_completion *done; /* set if the caller waits */ }; +/* + * If an inode is constantly having its pages dirtied, but then the + * updates stop dirtytime_expire_interval seconds in the past, it's + * possible for the worst case time between when an inode has its + * timestamps updated and when they finally get written out to be two + * dirtytime_expire_intervals. We set the default to 12 hours (in + * seconds), which means most of the time inodes will have their + * timestamps written to disk after 12 hours, but in the worst case a + * few inodes might not their timestamps updated for 24 hours. + */ +static unsigned int dirtytime_expire_interval = 12 * 60 * 60; + +static inline struct inode *wb_inode(struct list_head *head) +{ + return list_entry(head, struct inode, i_io_list); +} + +/* + * Include the creation of the trace points after defining the + * wb_writeback_work structure and inline functions so that the definition + * remains local to this file. + */ +#define CREATE_TRACE_POINTS +#include <trace/events/writeback.h> + +EXPORT_TRACEPOINT_SYMBOL_GPL(wbc_writepage); + +static bool wb_io_lists_populated(struct bdi_writeback *wb) +{ + if (wb_has_dirty_io(wb)) { + return false; + } else { + set_bit(WB_has_dirty_io, &wb->state); + WARN_ON_ONCE(!wb->avg_write_bandwidth); + atomic_long_add(wb->avg_write_bandwidth, + &wb->bdi->tot_write_bandwidth); + return true; + } +} + +static void wb_io_lists_depopulated(struct bdi_writeback *wb) +{ + if (wb_has_dirty_io(wb) && list_empty(&wb->b_dirty) && + list_empty(&wb->b_io) && list_empty(&wb->b_more_io)) { + clear_bit(WB_has_dirty_io, &wb->state); + WARN_ON_ONCE(atomic_long_sub_return(wb->avg_write_bandwidth, + &wb->bdi->tot_write_bandwidth) < 0); + } +} + /** - * writeback_in_progress - determine whether there is writeback in progress - * @bdi: the device's backing_dev_info structure. + * inode_io_list_move_locked - move an inode onto a bdi_writeback IO list + * @inode: inode to be moved + * @wb: target bdi_writeback + * @head: one of @wb->b_{dirty|io|more_io|dirty_time} * - * Determine whether there is writeback waiting to be handled against a - * backing device. + * Move @inode->i_io_list to @list of @wb and set %WB_has_dirty_io. + * Returns %true if @inode is the first occupant of the !dirty_time IO + * lists; otherwise, %false. */ -int writeback_in_progress(struct backing_dev_info *bdi) +static bool inode_io_list_move_locked(struct inode *inode, + struct bdi_writeback *wb, + struct list_head *head) { - return test_bit(BDI_writeback_running, &bdi->state); + assert_spin_locked(&wb->list_lock); + assert_spin_locked(&inode->i_lock); + WARN_ON_ONCE(inode_state_read(inode) & I_FREEING); + + list_move(&inode->i_io_list, head); + + /* dirty_time doesn't count as dirty_io until expiration */ + if (head != &wb->b_dirty_time) + return wb_io_lists_populated(wb); + + wb_io_lists_depopulated(wb); + return false; } -EXPORT_SYMBOL(writeback_in_progress); -static inline struct backing_dev_info *inode_to_bdi(struct inode *inode) +static void wb_wakeup(struct bdi_writeback *wb) { - struct super_block *sb = inode->i_sb; + spin_lock_irq(&wb->work_lock); + if (test_bit(WB_registered, &wb->state)) + mod_delayed_work(bdi_wq, &wb->dwork, 0); + spin_unlock_irq(&wb->work_lock); +} - if (strcmp(sb->s_type->name, "bdev") == 0) - return inode->i_mapping->backing_dev_info; +/* + * This function is used when the first inode for this wb is marked dirty. It + * wakes-up the corresponding bdi thread which should then take care of the + * periodic background write-out of dirty inodes. Since the write-out would + * starts only 'dirty_writeback_interval' centisecs from now anyway, we just + * set up a timer which wakes the bdi thread up later. + * + * Note, we wouldn't bother setting up the timer, but this function is on the + * fast-path (used by '__mark_inode_dirty()'), so we save few context switches + * by delaying the wake-up. + * + * We have to be careful not to postpone flush work if it is scheduled for + * earlier. Thus we use queue_delayed_work(). + */ +static void wb_wakeup_delayed(struct bdi_writeback *wb) +{ + unsigned long timeout; - return sb->s_bdi; + timeout = msecs_to_jiffies(dirty_writeback_interval * 10); + spin_lock_irq(&wb->work_lock); + if (test_bit(WB_registered, &wb->state)) + queue_delayed_work(bdi_wq, &wb->dwork, timeout); + spin_unlock_irq(&wb->work_lock); } -static inline struct inode *wb_inode(struct list_head *head) +static void finish_writeback_work(struct wb_writeback_work *work) { - return list_entry(head, struct inode, i_wb_list); + struct wb_completion *done = work->done; + + if (work->auto_free) + kfree(work); + if (done) { + wait_queue_head_t *waitq = done->waitq; + + /* @done can't be accessed after the following dec */ + if (atomic_dec_and_test(&done->cnt)) + wake_up_all(waitq); + } } +static void wb_queue_work(struct bdi_writeback *wb, + struct wb_writeback_work *work) +{ + trace_writeback_queue(wb, work); + + if (work->done) + atomic_inc(&work->done->cnt); + + spin_lock_irq(&wb->work_lock); + + if (test_bit(WB_registered, &wb->state)) { + list_add_tail(&work->list, &wb->work_list); + mod_delayed_work(bdi_wq, &wb->dwork, 0); + } else + finish_writeback_work(work); + + spin_unlock_irq(&wb->work_lock); +} + +static bool wb_wait_for_completion_cb(struct wb_completion *done) +{ + unsigned long waited_secs = (jiffies - done->wait_start) / HZ; + + done->progress_stamp = jiffies; + if (waited_secs > sysctl_hung_task_timeout_secs) + pr_info("INFO: The task %s:%d has been waiting for writeback " + "completion for more than %lu seconds.", + current->comm, current->pid, waited_secs); + + return !atomic_read(&done->cnt); +} + +/** + * wb_wait_for_completion - wait for completion of bdi_writeback_works + * @done: target wb_completion + * + * Wait for one or more work items issued to @bdi with their ->done field + * set to @done, which should have been initialized with + * DEFINE_WB_COMPLETION(). This function returns after all such work items + * are completed. Work items which are waited upon aren't freed + * automatically on completion. + */ +void wb_wait_for_completion(struct wb_completion *done) +{ + done->wait_start = jiffies; + atomic_dec(&done->cnt); /* put down the initial count */ + wait_event(*done->waitq, wb_wait_for_completion_cb(done)); +} + +#ifdef CONFIG_CGROUP_WRITEBACK + /* - * Include the creation of the trace points after defining the - * wb_writeback_work structure and inline functions so that the definition - * remains local to this file. + * Parameters for foreign inode detection, see wbc_detach_inode() to see + * how they're used. + * + * These paramters are inherently heuristical as the detection target + * itself is fuzzy. All we want to do is detaching an inode from the + * current owner if it's being written to by some other cgroups too much. + * + * The current cgroup writeback is built on the assumption that multiple + * cgroups writing to the same inode concurrently is very rare and a mode + * of operation which isn't well supported. As such, the goal is not + * taking too long when a different cgroup takes over an inode while + * avoiding too aggressive flip-flops from occasional foreign writes. + * + * We record, very roughly, 2s worth of IO time history and if more than + * half of that is foreign, trigger the switch. The recording is quantized + * to 16 slots. To avoid tiny writes from swinging the decision too much, + * writes smaller than 1/8 of avg size are ignored. */ -#define CREATE_TRACE_POINTS -#include <trace/events/writeback.h> +#define WB_FRN_TIME_SHIFT 13 /* 1s = 2^13, upto 8 secs w/ 16bit */ +#define WB_FRN_TIME_AVG_SHIFT 3 /* avg = avg * 7/8 + new * 1/8 */ +#define WB_FRN_TIME_CUT_DIV 8 /* ignore rounds < avg / 8 */ +#define WB_FRN_TIME_PERIOD (2 * (1 << WB_FRN_TIME_SHIFT)) /* 2s */ + +#define WB_FRN_HIST_SLOTS 16 /* inode->i_wb_frn_history is 16bit */ +#define WB_FRN_HIST_UNIT (WB_FRN_TIME_PERIOD / WB_FRN_HIST_SLOTS) + /* each slot's duration is 2s / 16 */ +#define WB_FRN_HIST_THR_SLOTS (WB_FRN_HIST_SLOTS / 2) + /* if foreign slots >= 8, switch */ +#define WB_FRN_HIST_MAX_SLOTS (WB_FRN_HIST_THR_SLOTS / 2 + 1) + /* one round can affect upto 5 slots */ +#define WB_FRN_MAX_IN_FLIGHT 1024 /* don't queue too many concurrently */ + +/* + * Maximum inodes per isw. A specific value has been chosen to make + * struct inode_switch_wbs_context fit into 1024 bytes kmalloc. + */ +#define WB_MAX_INODES_PER_ISW ((1024UL - sizeof(struct inode_switch_wbs_context)) \ + / sizeof(struct inode *)) + +static atomic_t isw_nr_in_flight = ATOMIC_INIT(0); +static struct workqueue_struct *isw_wq; -static void bdi_queue_work(struct backing_dev_info *bdi, - struct wb_writeback_work *work) +void __inode_attach_wb(struct inode *inode, struct folio *folio) { - trace_writeback_queue(bdi, work); + struct backing_dev_info *bdi = inode_to_bdi(inode); + struct bdi_writeback *wb = NULL; - spin_lock_bh(&bdi->wb_lock); - list_add_tail(&work->list, &bdi->work_list); - spin_unlock_bh(&bdi->wb_lock); + if (inode_cgwb_enabled(inode)) { + struct cgroup_subsys_state *memcg_css; - mod_delayed_work(bdi_wq, &bdi->wb.dwork, 0); + if (folio) { + memcg_css = mem_cgroup_css_from_folio(folio); + wb = wb_get_create(bdi, memcg_css, GFP_ATOMIC); + } else { + /* must pin memcg_css, see wb_get_create() */ + memcg_css = task_get_css(current, memory_cgrp_id); + wb = wb_get_create(bdi, memcg_css, GFP_ATOMIC); + css_put(memcg_css); + } + } + + if (!wb) + wb = &bdi->wb; + + /* + * There may be multiple instances of this function racing to + * update the same inode. Use cmpxchg() to tell the winner. + */ + if (unlikely(cmpxchg(&inode->i_wb, NULL, wb))) + wb_put(wb); } -static void -__bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages, - bool range_cyclic, enum wb_reason reason) +/** + * inode_cgwb_move_to_attached - put the inode onto wb->b_attached list + * @inode: inode of interest with i_lock held + * @wb: target bdi_writeback + * + * Remove the inode from wb's io lists and if necessarily put onto b_attached + * list. Only inodes attached to cgwb's are kept on this list. + */ +static void inode_cgwb_move_to_attached(struct inode *inode, + struct bdi_writeback *wb) { - struct wb_writeback_work *work; + assert_spin_locked(&wb->list_lock); + assert_spin_locked(&inode->i_lock); + WARN_ON_ONCE(inode_state_read(inode) & I_FREEING); + + inode_state_clear(inode, I_SYNC_QUEUED); + if (wb != &wb->bdi->wb) + list_move(&inode->i_io_list, &wb->b_attached); + else + list_del_init(&inode->i_io_list); + wb_io_lists_depopulated(wb); +} + +/** + * locked_inode_to_wb_and_lock_list - determine a locked inode's wb and lock it + * @inode: inode of interest with i_lock held + * + * Returns @inode's wb with its list_lock held. @inode->i_lock must be + * held on entry and is released on return. The returned wb is guaranteed + * to stay @inode's associated wb until its list_lock is released. + */ +static struct bdi_writeback * +locked_inode_to_wb_and_lock_list(struct inode *inode) + __releases(&inode->i_lock) + __acquires(&wb->list_lock) +{ + while (true) { + struct bdi_writeback *wb = inode_to_wb(inode); + + /* + * inode_to_wb() association is protected by both + * @inode->i_lock and @wb->list_lock but list_lock nests + * outside i_lock. Drop i_lock and verify that the + * association hasn't changed after acquiring list_lock. + */ + wb_get(wb); + spin_unlock(&inode->i_lock); + spin_lock(&wb->list_lock); + + /* i_wb may have changed inbetween, can't use inode_to_wb() */ + if (likely(wb == inode->i_wb)) { + wb_put(wb); /* @inode already has ref */ + return wb; + } + + spin_unlock(&wb->list_lock); + wb_put(wb); + cpu_relax(); + spin_lock(&inode->i_lock); + } +} + +/** + * inode_to_wb_and_lock_list - determine an inode's wb and lock it + * @inode: inode of interest + * + * Same as locked_inode_to_wb_and_lock_list() but @inode->i_lock isn't held + * on entry. + */ +static struct bdi_writeback *inode_to_wb_and_lock_list(struct inode *inode) + __acquires(&wb->list_lock) +{ + spin_lock(&inode->i_lock); + return locked_inode_to_wb_and_lock_list(inode); +} + +struct inode_switch_wbs_context { + /* List of queued switching contexts for the wb */ + struct llist_node list; /* - * This is WB_SYNC_NONE writeback, so if allocation fails just - * wakeup the thread for old dirty data writeback + * Multiple inodes can be switched at once. The switching procedure + * consists of two parts, separated by a RCU grace period. To make + * sure that the second part is executed for each inode gone through + * the first part, all inode pointers are placed into a NULL-terminated + * array embedded into struct inode_switch_wbs_context. Otherwise + * an inode could be left in a non-consistent state. */ - work = kzalloc(sizeof(*work), GFP_ATOMIC); - if (!work) { - trace_writeback_nowork(bdi); - mod_delayed_work(bdi_wq, &bdi->wb.dwork, 0); + struct inode *inodes[]; +}; + +static void bdi_down_write_wb_switch_rwsem(struct backing_dev_info *bdi) +{ + down_write(&bdi->wb_switch_rwsem); +} + +static void bdi_up_write_wb_switch_rwsem(struct backing_dev_info *bdi) +{ + up_write(&bdi->wb_switch_rwsem); +} + +static bool inode_do_switch_wbs(struct inode *inode, + struct bdi_writeback *old_wb, + struct bdi_writeback *new_wb) +{ + struct address_space *mapping = inode->i_mapping; + XA_STATE(xas, &mapping->i_pages, 0); + struct folio *folio; + bool switched = false; + + spin_lock(&inode->i_lock); + xa_lock_irq(&mapping->i_pages); + + /* + * Once I_FREEING or I_WILL_FREE are visible under i_lock, the eviction + * path owns the inode and we shouldn't modify ->i_io_list. + */ + if (unlikely(inode_state_read(inode) & (I_FREEING | I_WILL_FREE))) + goto skip_switch; + + trace_inode_switch_wbs(inode, old_wb, new_wb); + + /* + * Count and transfer stats. Note that PAGECACHE_TAG_DIRTY points + * to possibly dirty folios while PAGECACHE_TAG_WRITEBACK points to + * folios actually under writeback. + */ + xas_for_each_marked(&xas, folio, ULONG_MAX, PAGECACHE_TAG_DIRTY) { + if (folio_test_dirty(folio)) { + long nr = folio_nr_pages(folio); + wb_stat_mod(old_wb, WB_RECLAIMABLE, -nr); + wb_stat_mod(new_wb, WB_RECLAIMABLE, nr); + } + } + + xas_set(&xas, 0); + xas_for_each_marked(&xas, folio, ULONG_MAX, PAGECACHE_TAG_WRITEBACK) { + long nr = folio_nr_pages(folio); + WARN_ON_ONCE(!folio_test_writeback(folio)); + wb_stat_mod(old_wb, WB_WRITEBACK, -nr); + wb_stat_mod(new_wb, WB_WRITEBACK, nr); + } + + if (mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK)) { + atomic_dec(&old_wb->writeback_inodes); + atomic_inc(&new_wb->writeback_inodes); + } + + wb_get(new_wb); + + /* + * Transfer to @new_wb's IO list if necessary. If the @inode is dirty, + * the specific list @inode was on is ignored and the @inode is put on + * ->b_dirty which is always correct including from ->b_dirty_time. + * If the @inode was clean, it means it was on the b_attached list, so + * move it onto the b_attached list of @new_wb. + */ + if (!list_empty(&inode->i_io_list)) { + inode->i_wb = new_wb; + + if (inode_state_read(inode) & I_DIRTY_ALL) { + /* + * We need to keep b_dirty list sorted by + * dirtied_time_when. However properly sorting the + * inode in the list gets too expensive when switching + * many inodes. So just attach inode at the end of the + * dirty list and clobber the dirtied_time_when. + */ + inode->dirtied_time_when = jiffies; + inode_io_list_move_locked(inode, new_wb, + &new_wb->b_dirty); + } else { + inode_cgwb_move_to_attached(inode, new_wb); + } + } else { + inode->i_wb = new_wb; + } + + /* ->i_wb_frn updates may race wbc_detach_inode() but doesn't matter */ + inode->i_wb_frn_winner = 0; + inode->i_wb_frn_avg_time = 0; + inode->i_wb_frn_history = 0; + switched = true; +skip_switch: + /* + * Paired with an acquire fence in unlocked_inode_to_wb_begin() and + * ensures that the new wb is visible if they see !I_WB_SWITCH. + */ + smp_wmb(); + inode_state_clear(inode, I_WB_SWITCH); + + xa_unlock_irq(&mapping->i_pages); + spin_unlock(&inode->i_lock); + + return switched; +} + +static void process_inode_switch_wbs(struct bdi_writeback *new_wb, + struct inode_switch_wbs_context *isw) +{ + struct backing_dev_info *bdi = inode_to_bdi(isw->inodes[0]); + struct bdi_writeback *old_wb = isw->inodes[0]->i_wb; + unsigned long nr_switched = 0; + struct inode **inodep; + + /* + * If @inode switches cgwb membership while sync_inodes_sb() is + * being issued, sync_inodes_sb() might miss it. Synchronize. + */ + down_read(&bdi->wb_switch_rwsem); + + inodep = isw->inodes; + /* + * By the time control reaches here, RCU grace period has passed + * since I_WB_SWITCH assertion and all wb stat update transactions + * between unlocked_inode_to_wb_begin/end() are guaranteed to be + * synchronizing against the i_pages lock. + * + * Grabbing old_wb->list_lock, inode->i_lock and the i_pages lock + * gives us exclusion against all wb related operations on @inode + * including IO list manipulations and stat updates. + */ +relock: + if (old_wb < new_wb) { + spin_lock(&old_wb->list_lock); + spin_lock_nested(&new_wb->list_lock, SINGLE_DEPTH_NESTING); + } else { + spin_lock(&new_wb->list_lock); + spin_lock_nested(&old_wb->list_lock, SINGLE_DEPTH_NESTING); + } + + while (*inodep) { + WARN_ON_ONCE((*inodep)->i_wb != old_wb); + if (inode_do_switch_wbs(*inodep, old_wb, new_wb)) + nr_switched++; + inodep++; + if (*inodep && need_resched()) { + spin_unlock(&new_wb->list_lock); + spin_unlock(&old_wb->list_lock); + cond_resched(); + goto relock; + } + } + + spin_unlock(&new_wb->list_lock); + spin_unlock(&old_wb->list_lock); + + up_read(&bdi->wb_switch_rwsem); + + if (nr_switched) { + wb_wakeup(new_wb); + wb_put_many(old_wb, nr_switched); + } + + for (inodep = isw->inodes; *inodep; inodep++) + iput(*inodep); + wb_put(new_wb); + kfree(isw); + atomic_dec(&isw_nr_in_flight); +} + +void inode_switch_wbs_work_fn(struct work_struct *work) +{ + struct bdi_writeback *new_wb = container_of(work, struct bdi_writeback, + switch_work); + struct inode_switch_wbs_context *isw, *next_isw; + struct llist_node *list; + + /* + * Grab out reference to wb so that it cannot get freed under us + * after we process all the isw items. + */ + wb_get(new_wb); + while (1) { + list = llist_del_all(&new_wb->switch_wbs_ctxs); + /* Nothing to do? */ + if (!list) + break; + /* + * In addition to synchronizing among switchers, I_WB_SWITCH + * tells the RCU protected stat update paths to grab the i_page + * lock so that stat transfer can synchronize against them. + * Let's continue after I_WB_SWITCH is guaranteed to be + * visible. + */ + synchronize_rcu(); + + llist_for_each_entry_safe(isw, next_isw, list, list) + process_inode_switch_wbs(new_wb, isw); + } + wb_put(new_wb); +} + +static bool inode_prepare_wbs_switch(struct inode *inode, + struct bdi_writeback *new_wb) +{ + /* + * Paired with smp_mb() in cgroup_writeback_umount(). + * isw_nr_in_flight must be increased before checking SB_ACTIVE and + * grabbing an inode, otherwise isw_nr_in_flight can be observed as 0 + * in cgroup_writeback_umount() and the isw_wq will be not flushed. + */ + smp_mb(); + + if (IS_DAX(inode)) + return false; + + /* while holding I_WB_SWITCH, no one else can update the association */ + spin_lock(&inode->i_lock); + if (!(inode->i_sb->s_flags & SB_ACTIVE) || + inode_state_read(inode) & (I_WB_SWITCH | I_FREEING | I_WILL_FREE) || + inode_to_wb(inode) == new_wb) { + spin_unlock(&inode->i_lock); + return false; + } + inode_state_set(inode, I_WB_SWITCH); + __iget(inode); + spin_unlock(&inode->i_lock); + + return true; +} + +static void wb_queue_isw(struct bdi_writeback *wb, + struct inode_switch_wbs_context *isw) +{ + if (llist_add(&isw->list, &wb->switch_wbs_ctxs)) + queue_work(isw_wq, &wb->switch_work); +} + +/** + * inode_switch_wbs - change the wb association of an inode + * @inode: target inode + * @new_wb_id: ID of the new wb + * + * Switch @inode's wb association to the wb identified by @new_wb_id. The + * switching is performed asynchronously and may fail silently. + */ +static void inode_switch_wbs(struct inode *inode, int new_wb_id) +{ + struct backing_dev_info *bdi = inode_to_bdi(inode); + struct cgroup_subsys_state *memcg_css; + struct inode_switch_wbs_context *isw; + struct bdi_writeback *new_wb = NULL; + + /* noop if seems to be already in progress */ + if (inode_state_read_once(inode) & I_WB_SWITCH) + return; + + /* avoid queueing a new switch if too many are already in flight */ + if (atomic_read(&isw_nr_in_flight) > WB_FRN_MAX_IN_FLIGHT) + return; + + isw = kzalloc(struct_size(isw, inodes, 2), GFP_ATOMIC); + if (!isw) return; + + atomic_inc(&isw_nr_in_flight); + + /* find and pin the new wb */ + rcu_read_lock(); + memcg_css = css_from_id(new_wb_id, &memory_cgrp_subsys); + if (memcg_css && !css_tryget(memcg_css)) + memcg_css = NULL; + rcu_read_unlock(); + if (!memcg_css) + goto out_free; + + new_wb = wb_get_create(bdi, memcg_css, GFP_ATOMIC); + css_put(memcg_css); + if (!new_wb) + goto out_free; + + if (!inode_prepare_wbs_switch(inode, new_wb)) + goto out_free; + + isw->inodes[0] = inode; + + trace_inode_switch_wbs_queue(inode->i_wb, new_wb, 1); + wb_queue_isw(new_wb, isw); + return; + +out_free: + atomic_dec(&isw_nr_in_flight); + if (new_wb) + wb_put(new_wb); + kfree(isw); +} + +static bool isw_prepare_wbs_switch(struct bdi_writeback *new_wb, + struct inode_switch_wbs_context *isw, + struct list_head *list, int *nr) +{ + struct inode *inode; + + list_for_each_entry(inode, list, i_io_list) { + if (!inode_prepare_wbs_switch(inode, new_wb)) + continue; + + isw->inodes[*nr] = inode; + (*nr)++; + + if (*nr >= WB_MAX_INODES_PER_ISW - 1) + return true; } + return false; +} - work->sync_mode = WB_SYNC_NONE; - work->nr_pages = nr_pages; - work->range_cyclic = range_cyclic; - work->reason = reason; +/** + * cleanup_offline_cgwb - detach associated inodes + * @wb: target wb + * + * Switch all inodes attached to @wb to a nearest living ancestor's wb in order + * to eventually release the dying @wb. Returns %true if not all inodes were + * switched and the function has to be restarted. + */ +bool cleanup_offline_cgwb(struct bdi_writeback *wb) +{ + struct cgroup_subsys_state *memcg_css; + struct inode_switch_wbs_context *isw; + struct bdi_writeback *new_wb; + int nr; + bool restart = false; + + isw = kzalloc(struct_size(isw, inodes, WB_MAX_INODES_PER_ISW), + GFP_KERNEL); + if (!isw) + return restart; + + atomic_inc(&isw_nr_in_flight); + + for (memcg_css = wb->memcg_css->parent; memcg_css; + memcg_css = memcg_css->parent) { + new_wb = wb_get_create(wb->bdi, memcg_css, GFP_KERNEL); + if (new_wb) + break; + } + if (unlikely(!new_wb)) + new_wb = &wb->bdi->wb; /* wb_get() is noop for bdi's wb */ + + nr = 0; + spin_lock(&wb->list_lock); + /* + * In addition to the inodes that have completed writeback, also switch + * cgwbs for those inodes only with dirty timestamps. Otherwise, those + * inodes won't be written back for a long time when lazytime is + * enabled, and thus pinning the dying cgwbs. It won't break the + * bandwidth restrictions, as writeback of inode metadata is not + * accounted for. + */ + restart = isw_prepare_wbs_switch(new_wb, isw, &wb->b_attached, &nr); + if (!restart) + restart = isw_prepare_wbs_switch(new_wb, isw, &wb->b_dirty_time, + &nr); + spin_unlock(&wb->list_lock); + + /* no attached inodes? bail out */ + if (nr == 0) { + atomic_dec(&isw_nr_in_flight); + wb_put(new_wb); + kfree(isw); + return restart; + } - bdi_queue_work(bdi, work); + trace_inode_switch_wbs_queue(wb, new_wb, nr); + wb_queue_isw(new_wb, isw); + + return restart; } /** - * bdi_start_writeback - start writeback - * @bdi: the backing device to write from - * @nr_pages: the number of pages to write - * @reason: reason why some writeback work was initiated + * wbc_attach_and_unlock_inode - associate wbc with target inode and unlock it + * @wbc: writeback_control of interest + * @inode: target inode * - * Description: - * This does WB_SYNC_NONE opportunistic writeback. The IO is only - * started when this function returns, we make no guarantees on - * completion. Caller need not hold sb s_umount semaphore. + * @inode is locked and about to be written back under the control of @wbc. + * Record @inode's writeback context into @wbc and unlock the i_lock. On + * writeback completion, wbc_detach_inode() should be called. This is used + * to track the cgroup writeback context. + */ +static void wbc_attach_and_unlock_inode(struct writeback_control *wbc, + struct inode *inode) + __releases(&inode->i_lock) +{ + if (!inode_cgwb_enabled(inode)) { + spin_unlock(&inode->i_lock); + return; + } + + wbc->wb = inode_to_wb(inode); + wbc->inode = inode; + + wbc->wb_id = wbc->wb->memcg_css->id; + wbc->wb_lcand_id = inode->i_wb_frn_winner; + wbc->wb_tcand_id = 0; + wbc->wb_bytes = 0; + wbc->wb_lcand_bytes = 0; + wbc->wb_tcand_bytes = 0; + + wb_get(wbc->wb); + spin_unlock(&inode->i_lock); + + /* + * A dying wb indicates that either the blkcg associated with the + * memcg changed or the associated memcg is dying. In the first + * case, a replacement wb should already be available and we should + * refresh the wb immediately. In the second case, trying to + * refresh will keep failing. + */ + if (unlikely(wb_dying(wbc->wb) && !css_is_dying(wbc->wb->memcg_css))) + inode_switch_wbs(inode, wbc->wb_id); +} + +/** + * 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_writeback(), which is an alternative + * entry point into writeback code, and first ensures @inode is associated with + * a bdi_writeback and attaches it to @wbc. + */ +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); +} +EXPORT_SYMBOL_GPL(wbc_attach_fdatawrite_inode); + +/** + * wbc_detach_inode - disassociate wbc from inode and perform foreign detection + * @wbc: writeback_control of the just finished writeback + * + * To be called after a writeback attempt of an inode finishes and undoes + * wbc_attach_and_unlock_inode(). Can be called under any context. + * + * As concurrent write sharing of an inode is expected to be very rare and + * memcg only tracks page ownership on first-use basis severely confining + * the usefulness of such sharing, cgroup writeback tracks ownership + * per-inode. While the support for concurrent write sharing of an inode + * is deemed unnecessary, an inode being written to by different cgroups at + * different points in time is a lot more common, and, more importantly, + * charging only by first-use can too readily lead to grossly incorrect + * behaviors (single foreign page can lead to gigabytes of writeback to be + * incorrectly attributed). + * + * To resolve this issue, cgroup writeback detects the majority dirtier of + * an inode and transfers the ownership to it. To avoid unnecessary + * oscillation, the detection mechanism keeps track of history and gives + * out the switch verdict only if the foreign usage pattern is stable over + * a certain amount of time and/or writeback attempts. * + * On each writeback attempt, @wbc tries to detect the majority writer + * using Boyer-Moore majority vote algorithm. In addition to the byte + * count from the majority voting, it also counts the bytes written for the + * current wb and the last round's winner wb (max of last round's current + * wb, the winner from two rounds ago, and the last round's majority + * candidate). Keeping track of the historical winner helps the algorithm + * to semi-reliably detect the most active writer even when it's not the + * absolute majority. + * + * Once the winner of the round is determined, whether the winner is + * foreign or not and how much IO time the round consumed is recorded in + * inode->i_wb_frn_history. If the amount of recorded foreign IO time is + * over a certain threshold, the switch verdict is given. + */ +void wbc_detach_inode(struct writeback_control *wbc) +{ + struct bdi_writeback *wb = wbc->wb; + struct inode *inode = wbc->inode; + unsigned long avg_time, max_bytes, max_time; + u16 history; + int max_id; + + if (!wb) + return; + + history = inode->i_wb_frn_history; + avg_time = inode->i_wb_frn_avg_time; + + /* pick the winner of this round */ + if (wbc->wb_bytes >= wbc->wb_lcand_bytes && + wbc->wb_bytes >= wbc->wb_tcand_bytes) { + max_id = wbc->wb_id; + max_bytes = wbc->wb_bytes; + } else if (wbc->wb_lcand_bytes >= wbc->wb_tcand_bytes) { + max_id = wbc->wb_lcand_id; + max_bytes = wbc->wb_lcand_bytes; + } else { + max_id = wbc->wb_tcand_id; + max_bytes = wbc->wb_tcand_bytes; + } + + /* + * Calculate the amount of IO time the winner consumed and fold it + * into the running average kept per inode. If the consumed IO + * time is lower than avag / WB_FRN_TIME_CUT_DIV, ignore it for + * deciding whether to switch or not. This is to prevent one-off + * small dirtiers from skewing the verdict. + */ + max_time = DIV_ROUND_UP((max_bytes >> PAGE_SHIFT) << WB_FRN_TIME_SHIFT, + wb->avg_write_bandwidth); + if (avg_time) + avg_time += (max_time >> WB_FRN_TIME_AVG_SHIFT) - + (avg_time >> WB_FRN_TIME_AVG_SHIFT); + else + avg_time = max_time; /* immediate catch up on first run */ + + if (max_time >= avg_time / WB_FRN_TIME_CUT_DIV) { + int slots; + + /* + * The switch verdict is reached if foreign wb's consume + * more than a certain proportion of IO time in a + * WB_FRN_TIME_PERIOD. This is loosely tracked by 16 slot + * history mask where each bit represents one sixteenth of + * the period. Determine the number of slots to shift into + * history from @max_time. + */ + slots = min(DIV_ROUND_UP(max_time, WB_FRN_HIST_UNIT), + (unsigned long)WB_FRN_HIST_MAX_SLOTS); + history <<= slots; + if (wbc->wb_id != max_id) + history |= (1U << slots) - 1; + + if (history) + trace_inode_foreign_history(inode, wbc, history); + + /* + * Switch if the current wb isn't the consistent winner. + * If there are multiple closely competing dirtiers, the + * inode may switch across them repeatedly over time, which + * is okay. The main goal is avoiding keeping an inode on + * the wrong wb for an extended period of time. + */ + if (hweight16(history) > WB_FRN_HIST_THR_SLOTS) + inode_switch_wbs(inode, max_id); + } + + /* + * Multiple instances of this function may race to update the + * following fields but we don't mind occassional inaccuracies. + */ + inode->i_wb_frn_winner = max_id; + inode->i_wb_frn_avg_time = min(avg_time, (unsigned long)U16_MAX); + inode->i_wb_frn_history = history; + + wb_put(wbc->wb); + wbc->wb = NULL; +} +EXPORT_SYMBOL_GPL(wbc_detach_inode); + +/** + * wbc_account_cgroup_owner - account writeback to update inode cgroup ownership + * @wbc: writeback_control of the writeback in progress + * @folio: folio being written out + * @bytes: number of bytes being written out + * + * @bytes from @folio are about to written out during the writeback + * controlled by @wbc. Keep the book for foreign inode detection. See + * wbc_detach_inode(). + */ +void wbc_account_cgroup_owner(struct writeback_control *wbc, struct folio *folio, + size_t bytes) +{ + struct cgroup_subsys_state *css; + int id; + + /* + * pageout() path doesn't attach @wbc to the inode being written + * out. This is intentional as we don't want the function to block + * behind a slow cgroup. Ultimately, we want pageout() to kick off + * regular writeback instead of writing things out itself. + */ + if (!wbc->wb || wbc->no_cgroup_owner) + return; + + css = mem_cgroup_css_from_folio(folio); + /* dead cgroups shouldn't contribute to inode ownership arbitration */ + if (!(css->flags & CSS_ONLINE)) + return; + + id = css->id; + + if (id == wbc->wb_id) { + wbc->wb_bytes += bytes; + return; + } + + if (id == wbc->wb_lcand_id) + wbc->wb_lcand_bytes += bytes; + + /* Boyer-Moore majority vote algorithm */ + if (!wbc->wb_tcand_bytes) + wbc->wb_tcand_id = id; + if (id == wbc->wb_tcand_id) + wbc->wb_tcand_bytes += bytes; + else + wbc->wb_tcand_bytes -= min(bytes, wbc->wb_tcand_bytes); +} +EXPORT_SYMBOL_GPL(wbc_account_cgroup_owner); + +/** + * wb_split_bdi_pages - split nr_pages to write according to bandwidth + * @wb: target bdi_writeback to split @nr_pages to + * @nr_pages: number of pages to write for the whole bdi + * + * Split @wb's portion of @nr_pages according to @wb's write bandwidth in + * relation to the total write bandwidth of all wb's w/ dirty inodes on + * @wb->bdi. + */ +static long wb_split_bdi_pages(struct bdi_writeback *wb, long nr_pages) +{ + unsigned long this_bw = wb->avg_write_bandwidth; + unsigned long tot_bw = atomic_long_read(&wb->bdi->tot_write_bandwidth); + + if (nr_pages == LONG_MAX) + return LONG_MAX; + + /* + * This may be called on clean wb's and proportional distribution + * may not make sense, just use the original @nr_pages in those + * cases. In general, we wanna err on the side of writing more. + */ + if (!tot_bw || this_bw >= tot_bw) + return nr_pages; + else + return DIV_ROUND_UP_ULL((u64)nr_pages * this_bw, tot_bw); +} + +/** + * bdi_split_work_to_wbs - split a wb_writeback_work to all wb's of a bdi + * @bdi: target backing_dev_info + * @base_work: wb_writeback_work to issue + * @skip_if_busy: skip wb's which already have writeback in progress + * + * Split and issue @base_work to all wb's (bdi_writeback's) of @bdi which + * have dirty inodes. If @base_work->nr_page isn't %LONG_MAX, it's + * distributed to the busy wbs according to each wb's proportion in the + * total active write bandwidth of @bdi. + */ +static void bdi_split_work_to_wbs(struct backing_dev_info *bdi, + struct wb_writeback_work *base_work, + bool skip_if_busy) +{ + struct bdi_writeback *last_wb = NULL; + struct bdi_writeback *wb = list_entry(&bdi->wb_list, + struct bdi_writeback, bdi_node); + + might_sleep(); +restart: + rcu_read_lock(); + list_for_each_entry_continue_rcu(wb, &bdi->wb_list, bdi_node) { + DEFINE_WB_COMPLETION(fallback_work_done, bdi); + struct wb_writeback_work fallback_work; + struct wb_writeback_work *work; + long nr_pages; + + if (last_wb) { + wb_put(last_wb); + last_wb = NULL; + } + + /* SYNC_ALL writes out I_DIRTY_TIME too */ + if (!wb_has_dirty_io(wb) && + (base_work->sync_mode == WB_SYNC_NONE || + list_empty(&wb->b_dirty_time))) + continue; + if (skip_if_busy && writeback_in_progress(wb)) + continue; + + nr_pages = wb_split_bdi_pages(wb, base_work->nr_pages); + + work = kmalloc(sizeof(*work), GFP_ATOMIC); + if (work) { + *work = *base_work; + work->nr_pages = nr_pages; + work->auto_free = 1; + wb_queue_work(wb, work); + continue; + } + + /* + * If wb_tryget fails, the wb has been shutdown, skip it. + * + * Pin @wb so that it stays on @bdi->wb_list. This allows + * continuing iteration from @wb after dropping and + * regrabbing rcu read lock. + */ + if (!wb_tryget(wb)) + continue; + + /* alloc failed, execute synchronously using on-stack fallback */ + work = &fallback_work; + *work = *base_work; + work->nr_pages = nr_pages; + work->auto_free = 0; + work->done = &fallback_work_done; + + wb_queue_work(wb, work); + last_wb = wb; + + rcu_read_unlock(); + wb_wait_for_completion(&fallback_work_done); + goto restart; + } + rcu_read_unlock(); + + if (last_wb) + wb_put(last_wb); +} + +/** + * cgroup_writeback_by_id - initiate cgroup writeback from bdi and memcg IDs + * @bdi_id: target bdi id + * @memcg_id: target memcg css id + * @reason: reason why some writeback work initiated + * @done: target wb_completion + * + * Initiate flush of the bdi_writeback identified by @bdi_id and @memcg_id + * with the specified parameters. + */ +int cgroup_writeback_by_id(u64 bdi_id, int memcg_id, + enum wb_reason reason, struct wb_completion *done) +{ + struct backing_dev_info *bdi; + struct cgroup_subsys_state *memcg_css; + struct bdi_writeback *wb; + struct wb_writeback_work *work; + unsigned long dirty; + int ret; + + /* lookup bdi and memcg */ + bdi = bdi_get_by_id(bdi_id); + if (!bdi) + return -ENOENT; + + rcu_read_lock(); + memcg_css = css_from_id(memcg_id, &memory_cgrp_subsys); + if (memcg_css && !css_tryget(memcg_css)) + memcg_css = NULL; + rcu_read_unlock(); + if (!memcg_css) { + ret = -ENOENT; + goto out_bdi_put; + } + + /* + * And find the associated wb. If the wb isn't there already + * there's nothing to flush, don't create one. + */ + wb = wb_get_lookup(bdi, memcg_css); + if (!wb) { + ret = -ENOENT; + goto out_css_put; + } + + /* + * The caller is attempting to write out most of + * the currently dirty pages. Let's take the current dirty page + * count and inflate it by 25% which should be large enough to + * flush out most dirty pages while avoiding getting livelocked by + * concurrent dirtiers. + * + * BTW the memcg stats are flushed periodically and this is best-effort + * estimation, so some potential error is ok. + */ + dirty = memcg_page_state(mem_cgroup_from_css(memcg_css), NR_FILE_DIRTY); + dirty = dirty * 10 / 8; + + /* issue the writeback work */ + work = kzalloc(sizeof(*work), GFP_NOWAIT); + if (work) { + work->nr_pages = dirty; + work->sync_mode = WB_SYNC_NONE; + work->range_cyclic = 1; + work->reason = reason; + work->done = done; + work->auto_free = 1; + wb_queue_work(wb, work); + ret = 0; + } else { + ret = -ENOMEM; + } + + wb_put(wb); +out_css_put: + css_put(memcg_css); +out_bdi_put: + bdi_put(bdi); + return ret; +} + +/** + * cgroup_writeback_umount - flush inode wb switches for umount + * @sb: target super_block + * + * This function is called when a super_block is about to be destroyed and + * flushes in-flight inode wb switches. An inode wb switch goes through + * RCU and then workqueue, so the two need to be flushed in order to ensure + * that all previously scheduled switches are finished. As wb switches are + * rare occurrences and synchronize_rcu() can take a while, perform + * flushing iff wb switches are in flight. + */ +void cgroup_writeback_umount(struct super_block *sb) +{ + + if (!(sb->s_bdi->capabilities & BDI_CAP_WRITEBACK)) + return; + + /* + * SB_ACTIVE should be reliably cleared before checking + * isw_nr_in_flight, see generic_shutdown_super(). + */ + smp_mb(); + + if (atomic_read(&isw_nr_in_flight)) { + /* + * Use rcu_barrier() to wait for all pending callbacks to + * ensure that all in-flight wb switches are in the workqueue. + */ + rcu_barrier(); + flush_workqueue(isw_wq); + } +} + +static int __init cgroup_writeback_init(void) +{ + isw_wq = alloc_workqueue("inode_switch_wbs", WQ_PERCPU, 0); + if (!isw_wq) + return -ENOMEM; + return 0; +} +fs_initcall(cgroup_writeback_init); + +#else /* CONFIG_CGROUP_WRITEBACK */ + +static void bdi_down_write_wb_switch_rwsem(struct backing_dev_info *bdi) { } +static void bdi_up_write_wb_switch_rwsem(struct backing_dev_info *bdi) { } + +static void inode_cgwb_move_to_attached(struct inode *inode, + struct bdi_writeback *wb) +{ + assert_spin_locked(&wb->list_lock); + assert_spin_locked(&inode->i_lock); + WARN_ON_ONCE(inode_state_read(inode) & I_FREEING); + + inode_state_clear(inode, I_SYNC_QUEUED); + list_del_init(&inode->i_io_list); + wb_io_lists_depopulated(wb); +} + +static struct bdi_writeback * +locked_inode_to_wb_and_lock_list(struct inode *inode) + __releases(&inode->i_lock) + __acquires(&wb->list_lock) +{ + struct bdi_writeback *wb = inode_to_wb(inode); + + spin_unlock(&inode->i_lock); + spin_lock(&wb->list_lock); + return wb; +} + +static struct bdi_writeback *inode_to_wb_and_lock_list(struct inode *inode) + __acquires(&wb->list_lock) +{ + struct bdi_writeback *wb = inode_to_wb(inode); + + spin_lock(&wb->list_lock); + return wb; +} + +static long wb_split_bdi_pages(struct bdi_writeback *wb, long nr_pages) +{ + return nr_pages; +} + +static void bdi_split_work_to_wbs(struct backing_dev_info *bdi, + struct wb_writeback_work *base_work, + bool skip_if_busy) +{ + might_sleep(); + + if (!skip_if_busy || !writeback_in_progress(&bdi->wb)) { + base_work->auto_free = 0; + wb_queue_work(&bdi->wb, base_work); + } +} + +static inline void wbc_attach_and_unlock_inode(struct writeback_control *wbc, + struct inode *inode) + __releases(&inode->i_lock) +{ + spin_unlock(&inode->i_lock); +} + +#endif /* CONFIG_CGROUP_WRITEBACK */ + +/* + * Add in the number of potentially dirty inodes, because each inode + * write can dirty pagecache in the underlying blockdev. */ -void bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages, - enum wb_reason reason) +static unsigned long get_nr_dirty_pages(void) { - __bdi_start_writeback(bdi, nr_pages, true, reason); + return global_node_page_state(NR_FILE_DIRTY) + + get_nr_dirty_inodes(); +} + +static void wb_start_writeback(struct bdi_writeback *wb, enum wb_reason reason) +{ + if (!wb_has_dirty_io(wb)) + return; + + /* + * All callers of this function want to start writeback of all + * dirty pages. Places like vmscan can call this at a very + * high frequency, causing pointless allocations of tons of + * work items and keeping the flusher threads busy retrieving + * that work. Ensure that we only allow one of them pending and + * inflight at the time. + */ + if (test_bit(WB_start_all, &wb->state) || + test_and_set_bit(WB_start_all, &wb->state)) + return; + + wb->start_all_reason = reason; + wb_wakeup(wb); } /** - * bdi_start_background_writeback - start background writeback - * @bdi: the backing device to write from + * wb_start_background_writeback - start background writeback + * @wb: bdi_writback to write from * * Description: * This makes sure WB_SYNC_NONE background writeback happens. When - * this function returns, it is only guaranteed that for given BDI + * this function returns, it is only guaranteed that for given wb * some IO is happening if we are over background dirty threshold. * Caller need not hold sb s_umount semaphore. */ -void bdi_start_background_writeback(struct backing_dev_info *bdi) +void wb_start_background_writeback(struct bdi_writeback *wb) { /* * We just wake up the flusher thread. It will perform background * writeback as soon as there is no other work to do. */ - trace_writeback_wake_background(bdi); - mod_delayed_work(bdi_wq, &bdi->wb.dwork, 0); + trace_writeback_wake_background(wb); + wb_wakeup(wb); } /* * Remove the inode from the writeback list it is on. */ -void inode_wb_list_del(struct inode *inode) +void inode_io_list_del(struct inode *inode) { - struct backing_dev_info *bdi = inode_to_bdi(inode); + struct bdi_writeback *wb; + + /* + * FIXME: ext4 can call here from ext4_evict_inode() after evict() already + * unlinked the inode. + */ + if (list_empty_careful(&inode->i_io_list)) + return; + + wb = inode_to_wb_and_lock_list(inode); + spin_lock(&inode->i_lock); + + inode_state_clear(inode, I_SYNC_QUEUED); + list_del_init(&inode->i_io_list); + wb_io_lists_depopulated(wb); + + spin_unlock(&inode->i_lock); + spin_unlock(&wb->list_lock); +} +EXPORT_SYMBOL(inode_io_list_del); + +/* + * mark an inode as under writeback on the sb + */ +void sb_mark_inode_writeback(struct inode *inode) +{ + struct super_block *sb = inode->i_sb; + unsigned long flags; + + if (list_empty(&inode->i_wb_list)) { + spin_lock_irqsave(&sb->s_inode_wblist_lock, flags); + if (list_empty(&inode->i_wb_list)) { + list_add_tail(&inode->i_wb_list, &sb->s_inodes_wb); + trace_sb_mark_inode_writeback(inode); + } + spin_unlock_irqrestore(&sb->s_inode_wblist_lock, flags); + } +} + +/* + * clear an inode as under writeback on the sb + */ +void sb_clear_inode_writeback(struct inode *inode) +{ + struct super_block *sb = inode->i_sb; + unsigned long flags; - spin_lock(&bdi->wb.list_lock); - list_del_init(&inode->i_wb_list); - spin_unlock(&bdi->wb.list_lock); + if (!list_empty(&inode->i_wb_list)) { + spin_lock_irqsave(&sb->s_inode_wblist_lock, flags); + if (!list_empty(&inode->i_wb_list)) { + list_del_init(&inode->i_wb_list); + trace_sb_clear_inode_writeback(inode); + } + spin_unlock_irqrestore(&sb->s_inode_wblist_lock, flags); + } } /* @@ -184,9 +1423,21 @@ void inode_wb_list_del(struct inode *inode) * the case then the inode must have been redirtied while it was being written * out and we don't reset its dirtied_when. */ -static void redirty_tail(struct inode *inode, struct bdi_writeback *wb) +static void redirty_tail_locked(struct inode *inode, struct bdi_writeback *wb) { - assert_spin_locked(&wb->list_lock); + assert_spin_locked(&inode->i_lock); + + inode_state_clear(inode, I_SYNC_QUEUED); + /* + * When the inode is being freed just don't bother with dirty list + * tracking. Flush worker will ignore this inode anyway and it will + * trigger assertions in inode_io_list_move_locked(). + */ + if (inode_state_read(inode) & I_FREEING) { + list_del_init(&inode->i_io_list); + wb_io_lists_depopulated(wb); + return; + } if (!list_empty(&wb->b_dirty)) { struct inode *tail; @@ -194,7 +1445,14 @@ static void redirty_tail(struct inode *inode, struct bdi_writeback *wb) if (time_before(inode->dirtied_when, tail->dirtied_when)) inode->dirtied_when = jiffies; } - list_move(&inode->i_wb_list, &wb->b_dirty); + inode_io_list_move_locked(inode, wb, &wb->b_dirty); +} + +static void redirty_tail(struct inode *inode, struct bdi_writeback *wb) +{ + spin_lock(&inode->i_lock); + redirty_tail_locked(inode, wb); + spin_unlock(&inode->i_lock); } /* @@ -202,18 +1460,18 @@ static void redirty_tail(struct inode *inode, struct bdi_writeback *wb) */ static void requeue_io(struct inode *inode, struct bdi_writeback *wb) { - assert_spin_locked(&wb->list_lock); - list_move(&inode->i_wb_list, &wb->b_more_io); + inode_io_list_move_locked(inode, wb, &wb->b_more_io); } static void inode_sync_complete(struct inode *inode) { - inode->i_state &= ~I_SYNC; + assert_spin_locked(&inode->i_lock); + + inode_state_clear(inode, I_SYNC); /* If inode is clean an unused, put it into LRU now... */ - inode_add_lru(inode); - /* Waiters must see I_SYNC cleared before being woken up */ - smp_mb(); - wake_up_bit(&inode->i_state, __I_SYNC); + inode_lru_list_add(inode); + /* Called with inode->i_lock which ensures memory ordering. */ + inode_wake_up_bit(inode, __I_SYNC); } static bool inode_dirtied_after(struct inode *inode, unsigned long t) @@ -232,12 +1490,12 @@ static bool inode_dirtied_after(struct inode *inode, unsigned long t) } /* - * Move expired (dirtied before work->older_than_this) dirty inodes from + * Move expired (dirtied before dirtied_before) dirty inodes from * @delaying_queue to @dispatch_queue. */ static int move_expired_inodes(struct list_head *delaying_queue, struct list_head *dispatch_queue, - struct wb_writeback_work *work) + unsigned long dirtied_before) { LIST_HEAD(tmp); struct list_head *pos, *node; @@ -248,14 +1506,18 @@ static int move_expired_inodes(struct list_head *delaying_queue, while (!list_empty(delaying_queue)) { inode = wb_inode(delaying_queue->prev); - if (work->older_than_this && - inode_dirtied_after(inode, *work->older_than_this)) + if (inode_dirtied_after(inode, dirtied_before)) break; + spin_lock(&inode->i_lock); + list_move(&inode->i_io_list, &tmp); + moved++; + inode_state_set(inode, I_SYNC_QUEUED); + spin_unlock(&inode->i_lock); + if (sb_is_blkdev_sb(inode->i_sb)) + continue; if (sb && sb != inode->i_sb) do_sb_sort = 1; sb = inode->i_sb; - list_move(&inode->i_wb_list, &tmp); - moved++; } /* just one sb in list, splice to dispatch_queue and we're done */ @@ -264,13 +1526,18 @@ static int move_expired_inodes(struct list_head *delaying_queue, goto out; } - /* Move inodes from one superblock together */ + /* + * Although inode's i_io_list is moved from 'tmp' to 'dispatch_queue', + * we don't take inode->i_lock here because it is just a pointless overhead. + * Inode is already marked as I_SYNC_QUEUED so writeback list handling is + * fully under our control. + */ while (!list_empty(&tmp)) { sb = wb_inode(tmp.prev)->i_sb; list_for_each_prev_safe(pos, node, &tmp) { inode = wb_inode(pos); if (inode->i_sb == sb) - list_move(&inode->i_wb_list, dispatch_queue); + list_move(&inode->i_io_list, dispatch_queue); } } out: @@ -288,13 +1555,22 @@ out: * | * +--> dequeue for IO */ -static void queue_io(struct bdi_writeback *wb, struct wb_writeback_work *work) +static void queue_io(struct bdi_writeback *wb, struct wb_writeback_work *work, + unsigned long dirtied_before) { int moved; + unsigned long time_expire_jif = dirtied_before; + assert_spin_locked(&wb->list_lock); list_splice_init(&wb->b_more_io, &wb->b_io); - moved = move_expired_inodes(&wb->b_dirty, &wb->b_io, work); - trace_writeback_queue_io(wb, work, moved); + moved = move_expired_inodes(&wb->b_dirty, &wb->b_io, dirtied_before); + if (!work->for_sync) + time_expire_jif = jiffies - dirtytime_expire_interval * HZ; + moved += move_expired_inodes(&wb->b_dirty_time, &wb->b_io, + time_expire_jif); + if (moved) + wb_io_lists_populated(wb); + trace_writeback_queue_io(wb, work, dirtied_before, moved); } static int write_inode(struct inode *inode, struct writeback_control *wbc) @@ -314,29 +1590,27 @@ static int write_inode(struct inode *inode, struct writeback_control *wbc) * Wait for writeback on an inode to complete. Called with i_lock held. * Caller must make sure inode cannot go away when we drop i_lock. */ -static void __inode_wait_for_writeback(struct inode *inode) - __releases(inode->i_lock) - __acquires(inode->i_lock) +void inode_wait_for_writeback(struct inode *inode) { - DEFINE_WAIT_BIT(wq, &inode->i_state, __I_SYNC); - wait_queue_head_t *wqh; + struct wait_bit_queue_entry wqe; + struct wait_queue_head *wq_head; + + assert_spin_locked(&inode->i_lock); - wqh = bit_waitqueue(&inode->i_state, __I_SYNC); - while (inode->i_state & I_SYNC) { + if (!(inode_state_read(inode) & I_SYNC)) + return; + + wq_head = inode_bit_waitqueue(&wqe, inode, __I_SYNC); + for (;;) { + prepare_to_wait_event(wq_head, &wqe.wq_entry, TASK_UNINTERRUPTIBLE); + /* Checking I_SYNC with inode->i_lock guarantees memory ordering. */ + if (!(inode_state_read(inode) & I_SYNC)) + break; spin_unlock(&inode->i_lock); - __wait_on_bit(wqh, &wq, inode_wait, TASK_UNINTERRUPTIBLE); + schedule(); spin_lock(&inode->i_lock); } -} - -/* - * Wait for writeback on an inode to complete. Caller must have inode pinned. - */ -void inode_wait_for_writeback(struct inode *inode) -{ - spin_lock(&inode->i_lock); - __inode_wait_for_writeback(inode); - spin_unlock(&inode->i_lock); + finish_wait(wq_head, &wqe.wq_entry); } /* @@ -347,16 +1621,20 @@ void inode_wait_for_writeback(struct inode *inode) static void inode_sleep_on_writeback(struct inode *inode) __releases(inode->i_lock) { - DEFINE_WAIT(wait); - wait_queue_head_t *wqh = bit_waitqueue(&inode->i_state, __I_SYNC); - int sleep; + struct wait_bit_queue_entry wqe; + struct wait_queue_head *wq_head; + bool sleep; - prepare_to_wait(wqh, &wait, TASK_UNINTERRUPTIBLE); - sleep = inode->i_state & I_SYNC; + assert_spin_locked(&inode->i_lock); + + wq_head = inode_bit_waitqueue(&wqe, inode, __I_SYNC); + prepare_to_wait_event(wq_head, &wqe.wq_entry, TASK_UNINTERRUPTIBLE); + /* Checking I_SYNC with inode->i_lock guarantees memory ordering. */ + sleep = !!(inode_state_read(inode) & I_SYNC); spin_unlock(&inode->i_lock); if (sleep) schedule(); - finish_wait(wqh, &wait); + finish_wait(wq_head, &wqe.wq_entry); } /* @@ -368,9 +1646,10 @@ static void inode_sleep_on_writeback(struct inode *inode) * thread's back can have unexpected consequences. */ static void requeue_inode(struct inode *inode, struct bdi_writeback *wb, - struct writeback_control *wbc) + struct writeback_control *wbc, + unsigned long dirtied_before) { - if (inode->i_state & I_FREEING) + if (inode_state_read(inode) & I_FREEING) return; /* @@ -378,16 +1657,21 @@ static void requeue_inode(struct inode *inode, struct bdi_writeback *wb, * shot. If still dirty, it will be redirty_tail()'ed below. Update * the dirty time to prevent enqueue and sync it again. */ - if ((inode->i_state & I_DIRTY) && + if ((inode_state_read(inode) & I_DIRTY) && (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages)) inode->dirtied_when = jiffies; if (wbc->pages_skipped) { /* - * writeback is not making progress due to locked - * buffers. Skip this inode for now. + * Writeback is not making progress due to locked buffers. + * Skip this inode for now. Although having skipped pages + * is odd for clean inodes, it can happen for some + * filesystems so handle that gracefully. */ - redirty_tail(inode, wb); + if (inode_state_read(inode) & I_DIRTY_ALL) + redirty_tail_locked(inode, wb); + else + inode_cgwb_move_to_attached(inode, wb); return; } @@ -396,7 +1680,8 @@ static void requeue_inode(struct inode *inode, struct bdi_writeback *wb, * We didn't write back all the pages. nfs_writepages() * sometimes bales out without doing anything. */ - if (wbc->nr_to_write <= 0) { + if (wbc->nr_to_write <= 0 && + !inode_dirtied_after(inode, dirtied_before)) { /* Slice used up. Queue for next turn. */ requeue_io(inode, wb); } else { @@ -407,25 +1692,35 @@ static void requeue_inode(struct inode *inode, struct bdi_writeback *wb, * retrying writeback of the dirty page/inode * that cannot be performed immediately. */ - redirty_tail(inode, wb); + redirty_tail_locked(inode, wb); } - } else if (inode->i_state & I_DIRTY) { + } else if (inode_state_read(inode) & I_DIRTY) { /* * Filesystems can dirty the inode during writeback operations, * such as delayed allocation during submission or metadata * updates after data IO completion. */ - redirty_tail(inode, wb); + redirty_tail_locked(inode, wb); + } else if (inode_state_read(inode) & I_DIRTY_TIME) { + inode->dirtied_when = jiffies; + inode_io_list_move_locked(inode, wb, &wb->b_dirty_time); + inode_state_clear(inode, I_SYNC_QUEUED); } else { /* The inode is clean. Remove from writeback lists. */ - list_del_init(&inode->i_wb_list); + inode_cgwb_move_to_attached(inode, wb); } } /* - * Write out an inode and its dirty pages. Do not update the writeback list - * linkage. That is left to the caller. The caller is also responsible for - * setting I_SYNC flag and calling inode_sync_complete() to clear it. + * Write out an inode and its dirty pages (or some of its dirty pages, depending + * on @wbc->nr_to_write), and clear the relevant dirty flags from i_state. + * + * This doesn't remove the inode from the writeback list it is on, except + * potentially to move it from b_dirty_time to b_dirty due to timestamp + * expiration. The caller is otherwise responsible for writeback list handling. + * + * The caller is also responsible for setting the I_SYNC flag beforehand and + * calling inode_sync_complete() to clear it afterwards. */ static int __writeback_single_inode(struct inode *inode, struct writeback_control *wbc) @@ -435,7 +1730,7 @@ __writeback_single_inode(struct inode *inode, struct writeback_control *wbc) unsigned dirty; int ret; - WARN_ON(!(inode->i_state & I_SYNC)); + WARN_ON(!(inode_state_read_once(inode) & I_SYNC)); trace_writeback_single_inode_start(inode, wbc, nr_to_write); @@ -455,80 +1750,141 @@ __writeback_single_inode(struct inode *inode, struct writeback_control *wbc) } /* - * Some filesystems may redirty the inode during the writeback - * due to delalloc, clear dirty metadata flags right before - * write_inode() + * If the inode has dirty timestamps and we need to write them, call + * mark_inode_dirty_sync() to notify the filesystem about it and to + * change I_DIRTY_TIME into I_DIRTY_SYNC. + */ + if ((inode_state_read_once(inode) & I_DIRTY_TIME) && + (wbc->sync_mode == WB_SYNC_ALL || + time_after(jiffies, inode->dirtied_time_when + + dirtytime_expire_interval * HZ))) { + trace_writeback_lazytime(inode); + mark_inode_dirty_sync(inode); + } + + /* + * Get and clear the dirty flags from i_state. This needs to be done + * after calling writepages because some filesystems may redirty the + * inode during writepages due to delalloc. It also needs to be done + * after handling timestamp expiration, as that may dirty the inode too. */ spin_lock(&inode->i_lock); - /* Clear I_DIRTY_PAGES if we've written out all dirty pages */ - if (!mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) - inode->i_state &= ~I_DIRTY_PAGES; - dirty = inode->i_state & I_DIRTY; - inode->i_state &= ~(I_DIRTY_SYNC | I_DIRTY_DATASYNC); + dirty = inode_state_read(inode) & I_DIRTY; + inode_state_clear(inode, dirty); + + /* + * Paired with smp_mb() in __mark_inode_dirty(). This allows + * __mark_inode_dirty() to test i_state without grabbing i_lock - + * either they see the I_DIRTY bits cleared or we see the dirtied + * inode. + * + * I_DIRTY_PAGES is always cleared together above even if @mapping + * still has dirty pages. The flag is reinstated after smp_mb() if + * necessary. This guarantees that either __mark_inode_dirty() + * sees clear I_DIRTY_PAGES or we see PAGECACHE_TAG_DIRTY. + */ + smp_mb(); + + if (mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) + inode_state_set(inode, I_DIRTY_PAGES); + else if (unlikely(inode_state_read(inode) & I_PINNING_NETFS_WB)) { + if (!(inode_state_read(inode) & I_DIRTY_PAGES)) { + inode_state_clear(inode, I_PINNING_NETFS_WB); + wbc->unpinned_netfs_wb = true; + dirty |= I_PINNING_NETFS_WB; /* Cause write_inode */ + } + } + spin_unlock(&inode->i_lock); + /* Don't write the inode if only I_DIRTY_PAGES was set */ - if (dirty & (I_DIRTY_SYNC | I_DIRTY_DATASYNC)) { + if (dirty & ~I_DIRTY_PAGES) { int err = write_inode(inode, wbc); if (ret == 0) ret = err; } + wbc->unpinned_netfs_wb = false; trace_writeback_single_inode(inode, wbc, nr_to_write); return ret; } /* - * Write out an inode's dirty pages. Either the caller has an active reference - * on the inode or the inode has I_WILL_FREE set. + * Write out an inode's dirty data and metadata on-demand, i.e. separately from + * the regular batched writeback done by the flusher threads in + * writeback_sb_inodes(). @wbc controls various aspects of the write, such as + * whether it is a data-integrity sync (%WB_SYNC_ALL) or not (%WB_SYNC_NONE). * - * This function is designed to be called for writing back one inode which - * we go e.g. from filesystem. Flusher thread uses __writeback_single_inode() - * and does more profound writeback list handling in writeback_sb_inodes(). + * To prevent the inode from going away, either the caller must have a reference + * to the inode, or the inode must have I_WILL_FREE or I_FREEING set. */ -static int -writeback_single_inode(struct inode *inode, struct bdi_writeback *wb, - struct writeback_control *wbc) +static int writeback_single_inode(struct inode *inode, + struct writeback_control *wbc) { + struct bdi_writeback *wb; int ret = 0; spin_lock(&inode->i_lock); - if (!atomic_read(&inode->i_count)) - WARN_ON(!(inode->i_state & (I_WILL_FREE|I_FREEING))); + if (!icount_read(inode)) + WARN_ON(!(inode_state_read(inode) & (I_WILL_FREE | I_FREEING))); else - WARN_ON(inode->i_state & I_WILL_FREE); + WARN_ON(inode_state_read(inode) & I_WILL_FREE); - if (inode->i_state & I_SYNC) { - if (wbc->sync_mode != WB_SYNC_ALL) - goto out; + if (inode_state_read(inode) & I_SYNC) { /* - * It's a data-integrity sync. We must wait. Since callers hold - * inode reference or inode has I_WILL_FREE set, it cannot go - * away under us. + * Writeback is already running on the inode. For WB_SYNC_NONE, + * that's enough and we can just return. For WB_SYNC_ALL, we + * must wait for the existing writeback to complete, then do + * writeback again if there's anything left. */ - __inode_wait_for_writeback(inode); + if (wbc->sync_mode != WB_SYNC_ALL) + goto out; + inode_wait_for_writeback(inode); } - WARN_ON(inode->i_state & I_SYNC); + WARN_ON(inode_state_read(inode) & I_SYNC); /* - * Skip inode if it is clean. We don't want to mess with writeback - * lists in this function since flusher thread may be doing for example - * sync in parallel and if we move the inode, it could get skipped. So - * here we make sure inode is on some writeback list and leave it there - * unless we have completely cleaned the inode. + * If the inode is already fully clean, then there's nothing to do. + * + * For data-integrity syncs we also need to check whether any pages are + * still under writeback, e.g. due to prior WB_SYNC_NONE writeback. If + * there are any such pages, we'll need to wait for them. */ - if (!(inode->i_state & I_DIRTY)) + if (!(inode_state_read(inode) & I_DIRTY_ALL) && + (wbc->sync_mode != WB_SYNC_ALL || + !mapping_tagged(inode->i_mapping, PAGECACHE_TAG_WRITEBACK))) goto out; - inode->i_state |= I_SYNC; - spin_unlock(&inode->i_lock); + inode_state_set(inode, I_SYNC); + wbc_attach_and_unlock_inode(wbc, inode); ret = __writeback_single_inode(inode, wbc); - spin_lock(&wb->list_lock); + wbc_detach_inode(wbc); + + wb = inode_to_wb_and_lock_list(inode); spin_lock(&inode->i_lock); /* - * If inode is clean, remove it from writeback lists. Otherwise don't - * touch it. See comment above for explanation. + * If the inode is freeing, its i_io_list shoudn't be updated + * as it can be finally deleted at this moment. */ - if (!(inode->i_state & I_DIRTY)) - list_del_init(&inode->i_wb_list); + if (!(inode_state_read(inode) & I_FREEING)) { + /* + * If the inode is now fully clean, then it can be safely + * removed from its writeback list (if any). Otherwise the + * flusher threads are responsible for the writeback lists. + */ + if (!(inode_state_read(inode) & I_DIRTY_ALL)) + inode_cgwb_move_to_attached(inode, wb); + else if (!(inode_state_read(inode) & I_SYNC_QUEUED)) { + if ((inode_state_read(inode) & I_DIRTY)) + redirty_tail_locked(inode, wb); + else if (inode_state_read(inode) & I_DIRTY_TIME) { + inode->dirtied_when = jiffies; + inode_io_list_move_locked(inode, + wb, + &wb->b_dirty_time); + } + } + } + spin_unlock(&wb->list_lock); inode_sync_complete(inode); out: @@ -536,8 +1892,8 @@ out: return ret; } -static long writeback_chunk_size(struct backing_dev_info *bdi, - struct wb_writeback_work *work) +static long writeback_chunk_size(struct super_block *sb, + struct bdi_writeback *wb, struct wb_writeback_work *work) { long pages; @@ -555,22 +1911,23 @@ static long writeback_chunk_size(struct backing_dev_info *bdi, * (maybe slowly) sync all tagged pages */ if (work->sync_mode == WB_SYNC_ALL || work->tagged_writepages) - pages = LONG_MAX; - else { - pages = min(bdi->avg_write_bandwidth / 2, - global_dirty_limit / DIRTY_SCOPE); - pages = min(pages, work->nr_pages); - pages = round_down(pages + MIN_WRITEBACK_PAGES, - MIN_WRITEBACK_PAGES); - } + return LONG_MAX; - return pages; + pages = min(wb->avg_write_bandwidth / 2, + global_wb_domain.dirty_limit / DIRTY_SCOPE); + pages = min(pages, work->nr_pages); + return round_down(pages + sb->s_min_writeback_pages, + sb->s_min_writeback_pages); } /* * Write a portion of b_io inodes which belong to @sb. * * Return the number of pages and/or inodes written. + * + * NOTE! This is called with wb->list_lock held, and will + * unlock and relock that for each inode it ends up doing + * IO for. */ static long writeback_sb_inodes(struct super_block *sb, struct bdi_writeback *wb, @@ -588,10 +1945,17 @@ static long writeback_sb_inodes(struct super_block *sb, }; unsigned long start_time = jiffies; long write_chunk; - long wrote = 0; /* count both pages and inodes */ + long total_wrote = 0; /* count both pages and inodes */ + unsigned long dirtied_before = jiffies; + + if (work->for_kupdate) + dirtied_before = jiffies - + msecs_to_jiffies(dirty_expire_interval * 10); while (!list_empty(&wb->b_io)) { struct inode *inode = wb_inode(wb->b_io.prev); + struct bdi_writeback *tmp_wb; + long wrote; if (inode->i_sb != sb) { if (work->sb) { @@ -618,12 +1982,12 @@ static long writeback_sb_inodes(struct super_block *sb, * kind writeout is handled by the freer. */ spin_lock(&inode->i_lock); - if (inode->i_state & (I_NEW | I_FREEING | I_WILL_FREE)) { + if (inode_state_read(inode) & (I_NEW | I_FREEING | I_WILL_FREE)) { + redirty_tail_locked(inode, wb); spin_unlock(&inode->i_lock); - redirty_tail(inode, wb); continue; } - if ((inode->i_state & I_SYNC) && wbc.sync_mode != WB_SYNC_ALL) { + if ((inode_state_read(inode) & I_SYNC) && wbc.sync_mode != WB_SYNC_ALL) { /* * If this inode is locked for writeback and we are not * doing writeback-for-data-integrity, move it to @@ -633,8 +1997,8 @@ static long writeback_sb_inodes(struct super_block *sb, * We'll have another go at writing back this inode * when we completed a full scan of b_io. */ - spin_unlock(&inode->i_lock); requeue_io(inode, wb); + spin_unlock(&inode->i_lock); trace_writeback_sb_inodes_requeue(inode); continue; } @@ -645,17 +2009,17 @@ static long writeback_sb_inodes(struct super_block *sb, * are doing WB_SYNC_NONE writeback. So this catches only the * WB_SYNC_ALL case. */ - if (inode->i_state & I_SYNC) { + if (inode_state_read(inode) & I_SYNC) { /* Wait for I_SYNC. This function drops i_lock... */ inode_sleep_on_writeback(inode); /* Inode may be gone, start again */ spin_lock(&wb->list_lock); continue; } - inode->i_state |= I_SYNC; - spin_unlock(&inode->i_lock); + inode_state_set(inode, I_SYNC); + wbc_attach_and_unlock_inode(&wbc, inode); - write_chunk = writeback_chunk_size(wb->bdi, work); + write_chunk = writeback_chunk_size(inode->i_sb, wb, work); wbc.nr_to_write = write_chunk; wbc.pages_skipped = 0; @@ -665,28 +2029,60 @@ static long writeback_sb_inodes(struct super_block *sb, */ __writeback_single_inode(inode, &wbc); + /* Report progress to inform the hung task detector of the progress. */ + if (work->done && work->done->progress_stamp && + (jiffies - work->done->progress_stamp) > HZ * + sysctl_hung_task_timeout_secs / 2) + wake_up_all(work->done->waitq); + + wbc_detach_inode(&wbc); work->nr_pages -= write_chunk - wbc.nr_to_write; - wrote += write_chunk - wbc.nr_to_write; - spin_lock(&wb->list_lock); + wrote = write_chunk - wbc.nr_to_write - wbc.pages_skipped; + wrote = wrote < 0 ? 0 : wrote; + total_wrote += wrote; + + if (need_resched()) { + /* + * We're trying to balance between building up a nice + * long list of IOs to improve our merge rate, and + * getting those IOs out quickly for anyone throttling + * in balance_dirty_pages(). cond_resched() doesn't + * unplug, so get our IOs out the door before we + * give up the CPU. + */ + blk_flush_plug(current->plug, false); + cond_resched(); + } + + /* + * Requeue @inode if still dirty. Be careful as @inode may + * have been switched to another wb in the meantime. + */ + tmp_wb = inode_to_wb_and_lock_list(inode); spin_lock(&inode->i_lock); - if (!(inode->i_state & I_DIRTY)) - wrote++; - requeue_inode(inode, wb, &wbc); + if (!(inode_state_read(inode) & I_DIRTY_ALL)) + total_wrote++; + requeue_inode(inode, tmp_wb, &wbc, dirtied_before); inode_sync_complete(inode); spin_unlock(&inode->i_lock); - cond_resched_lock(&wb->list_lock); + + if (unlikely(tmp_wb != wb)) { + spin_unlock(&tmp_wb->list_lock); + spin_lock(&wb->list_lock); + } + /* * bail out to wb_writeback() often enough to check * background threshold and other termination conditions. */ - if (wrote) { + if (total_wrote) { if (time_is_before_jiffies(start_time + HZ / 10UL)) break; if (work->nr_pages <= 0) break; } } - return wrote; + return total_wrote; } static long __writeback_inodes_wb(struct bdi_writeback *wb, @@ -699,9 +2095,9 @@ static long __writeback_inodes_wb(struct bdi_writeback *wb, struct inode *inode = wb_inode(wb->b_io.prev); struct super_block *sb = inode->i_sb; - if (!grab_super_passive(sb)) { + if (!super_trylock_shared(sb)) { /* - * grab_super_passive() may fail consistently due to + * super_trylock_shared() may fail consistently due to * s_umount being grabbed by someone else. Don't use * requeue_io() to avoid busy retrying the inode/sb. */ @@ -709,7 +2105,7 @@ static long __writeback_inodes_wb(struct bdi_writeback *wb, continue; } wrote += writeback_sb_inodes(sb, wb, work); - drop_super(sb); + up_read(&sb->s_umount); /* refer to the same tests at the end of writeback_sb_inodes */ if (wrote) { @@ -723,7 +2119,7 @@ static long __writeback_inodes_wb(struct bdi_writeback *wb, return wrote; } -long writeback_inodes_wb(struct bdi_writeback *wb, long nr_pages, +static long writeback_inodes_wb(struct bdi_writeback *wb, long nr_pages, enum wb_reason reason) { struct wb_writeback_work work = { @@ -732,43 +2128,19 @@ long writeback_inodes_wb(struct bdi_writeback *wb, long nr_pages, .range_cyclic = 1, .reason = reason, }; + struct blk_plug plug; + blk_start_plug(&plug); spin_lock(&wb->list_lock); if (list_empty(&wb->b_io)) - queue_io(wb, &work); + queue_io(wb, &work, jiffies); __writeback_inodes_wb(wb, &work); spin_unlock(&wb->list_lock); + blk_finish_plug(&plug); return nr_pages - work.nr_pages; } -static bool over_bground_thresh(struct backing_dev_info *bdi) -{ - unsigned long background_thresh, dirty_thresh; - - global_dirty_limits(&background_thresh, &dirty_thresh); - - if (global_page_state(NR_FILE_DIRTY) + - global_page_state(NR_UNSTABLE_NFS) > background_thresh) - return true; - - if (bdi_stat(bdi, BDI_RECLAIMABLE) > - bdi_dirty_limit(bdi, background_thresh)) - return true; - - return false; -} - -/* - * Called under wb->list_lock. If there are multiple wb per bdi, - * only the flusher working on the first wb should do it. - */ -static void wb_update_bandwidth(struct bdi_writeback *wb, - unsigned long start_time) -{ - __bdi_update_bandwidth(wb->bdi, 0, 0, 0, 0, 0, start_time); -} - /* * Explicit flushing or periodic writeback of "old" data. * @@ -781,22 +2153,20 @@ static void wb_update_bandwidth(struct bdi_writeback *wb, * takes longer than a dirty_writeback_interval interval, then leave a * one-second gap. * - * older_than_this takes precedence over nr_to_write. So we'll only write back + * dirtied_before takes precedence over nr_to_write. So we'll only write back * all dirty pages if they are all attached to "old" mappings. */ static long wb_writeback(struct bdi_writeback *wb, struct wb_writeback_work *work) { - unsigned long wb_start = jiffies; long nr_pages = work->nr_pages; - unsigned long oldest_jif; + unsigned long dirtied_before = jiffies; struct inode *inode; long progress; + struct blk_plug plug; + bool queued = false; - oldest_jif = jiffies; - work->older_than_this = &oldest_jif; - - spin_lock(&wb->list_lock); + blk_start_plug(&plug); for (;;) { /* * Stop writeback when nr_pages has been consumed @@ -811,38 +2181,42 @@ static long wb_writeback(struct bdi_writeback *wb, * after the other works are all done. */ if ((work->for_background || work->for_kupdate) && - !list_empty(&wb->bdi->work_list)) + !list_empty(&wb->work_list)) break; /* * For background writeout, stop when we are below the * background dirty threshold */ - if (work->for_background && !over_bground_thresh(wb->bdi)) + if (work->for_background && !wb_over_bg_thresh(wb)) break; - /* - * Kupdate and background works are special and we want to - * include all inodes that need writing. Livelock avoidance is - * handled by these works yielding to any other work so we are - * safe. - */ - if (work->for_kupdate) { - oldest_jif = jiffies - - msecs_to_jiffies(dirty_expire_interval * 10); - } else if (work->for_background) - oldest_jif = jiffies; - - trace_writeback_start(wb->bdi, work); - if (list_empty(&wb->b_io)) - queue_io(wb, work); + + spin_lock(&wb->list_lock); + + trace_writeback_start(wb, work); + if (list_empty(&wb->b_io)) { + /* + * Kupdate and background works are special and we want + * to include all inodes that need writing. Livelock + * avoidance is handled by these works yielding to any + * other work so we are safe. + */ + if (work->for_kupdate) { + dirtied_before = jiffies - + msecs_to_jiffies(dirty_expire_interval * + 10); + } else if (work->for_background) + dirtied_before = jiffies; + + queue_io(wb, work, dirtied_before); + queued = true; + } if (work->sb) progress = writeback_sb_inodes(work->sb, wb, work); else progress = __writeback_inodes_wb(wb, work); - trace_writeback_written(wb->bdi, work); - - wb_update_bandwidth(wb, wb_start); + trace_writeback_written(wb, work); /* * Did we write something? Try for more @@ -852,29 +2226,32 @@ static long wb_writeback(struct bdi_writeback *wb, * mean the overall work is done. So we keep looping as long * as made some progress on cleaning pages or inodes. */ - if (progress) + if (progress || !queued) { + spin_unlock(&wb->list_lock); continue; + } + /* * No more inodes for IO, bail */ - if (list_empty(&wb->b_more_io)) + if (list_empty(&wb->b_more_io)) { + spin_unlock(&wb->list_lock); break; + } + /* * Nothing written. Wait for some inode to * become available for writeback. Otherwise * we'll just busyloop. */ - if (!list_empty(&wb->b_more_io)) { - trace_writeback_wait(wb->bdi, work); - inode = wb_inode(wb->b_more_io.prev); - spin_lock(&inode->i_lock); - spin_unlock(&wb->list_lock); - /* This function drops i_lock... */ - inode_sleep_on_writeback(inode); - spin_lock(&wb->list_lock); - } + trace_writeback_wait(wb, work); + inode = wb_inode(wb->b_more_io.prev); + spin_lock(&inode->i_lock); + spin_unlock(&wb->list_lock); + /* This function drops i_lock... */ + inode_sleep_on_writeback(inode); } - spin_unlock(&wb->list_lock); + blk_finish_plug(&plug); return nr_pages - work->nr_pages; } @@ -882,35 +2259,23 @@ static long wb_writeback(struct bdi_writeback *wb, /* * Return the next wb_writeback_work struct that hasn't been processed yet. */ -static struct wb_writeback_work * -get_next_work_item(struct backing_dev_info *bdi) +static struct wb_writeback_work *get_next_work_item(struct bdi_writeback *wb) { struct wb_writeback_work *work = NULL; - spin_lock_bh(&bdi->wb_lock); - if (!list_empty(&bdi->work_list)) { - work = list_entry(bdi->work_list.next, + spin_lock_irq(&wb->work_lock); + if (!list_empty(&wb->work_list)) { + work = list_entry(wb->work_list.next, struct wb_writeback_work, list); list_del_init(&work->list); } - spin_unlock_bh(&bdi->wb_lock); + spin_unlock_irq(&wb->work_lock); return work; } -/* - * Add in the number of potentially dirty inodes, because each inode - * write can dirty pagecache in the underlying blockdev. - */ -static unsigned long get_nr_dirty_pages(void) -{ - return global_page_state(NR_FILE_DIRTY) + - global_page_state(NR_UNSTABLE_NFS) + - get_nr_dirty_inodes(); -} - static long wb_check_background_flush(struct bdi_writeback *wb) { - if (over_bground_thresh(wb->bdi)) { + if (wb_over_bg_thresh(wb)) { struct wb_writeback_work work = { .nr_pages = LONG_MAX, @@ -960,38 +2325,56 @@ static long wb_check_old_data_flush(struct bdi_writeback *wb) return 0; } +static long wb_check_start_all(struct bdi_writeback *wb) +{ + long nr_pages; + + if (!test_bit(WB_start_all, &wb->state)) + return 0; + + nr_pages = get_nr_dirty_pages(); + if (nr_pages) { + struct wb_writeback_work work = { + .nr_pages = wb_split_bdi_pages(wb, nr_pages), + .sync_mode = WB_SYNC_NONE, + .range_cyclic = 1, + .reason = wb->start_all_reason, + }; + + nr_pages = wb_writeback(wb, &work); + } + + clear_bit(WB_start_all, &wb->state); + return nr_pages; +} + + /* * Retrieve work items and do the writeback they describe */ static long wb_do_writeback(struct bdi_writeback *wb) { - struct backing_dev_info *bdi = wb->bdi; struct wb_writeback_work *work; long wrote = 0; - set_bit(BDI_writeback_running, &wb->bdi->state); - while ((work = get_next_work_item(bdi)) != NULL) { - - trace_writeback_exec(bdi, work); - + set_bit(WB_writeback_running, &wb->state); + while ((work = get_next_work_item(wb)) != NULL) { + trace_writeback_exec(wb, work); wrote += wb_writeback(wb, work); - - /* - * Notify the caller of completion if this is a synchronous - * work item, otherwise just free it. - */ - if (work->done) - complete(work->done); - else - kfree(work); + finish_writeback_work(work); } /* + * Check for a flush-everything request + */ + wrote += wb_check_start_all(wb); + + /* * Check for periodic writeback, kupdated() style */ wrote += wb_check_old_data_flush(wb); wrote += wb_check_background_flush(wb); - clear_bit(BDI_writeback_running, &wb->bdi->state); + clear_bit(WB_writeback_running, &wb->state); return wrote; } @@ -1000,107 +2383,167 @@ static long wb_do_writeback(struct bdi_writeback *wb) * Handle writeback of dirty data for the device backed by this bdi. Also * reschedules periodically and does kupdated style flushing. */ -void bdi_writeback_workfn(struct work_struct *work) +void wb_workfn(struct work_struct *work) { struct bdi_writeback *wb = container_of(to_delayed_work(work), struct bdi_writeback, dwork); - struct backing_dev_info *bdi = wb->bdi; long pages_written; - set_worker_desc("flush-%s", dev_name(bdi->dev)); - current->flags |= PF_SWAPWRITE; + set_worker_desc("flush-%s", bdi_dev_name(wb->bdi)); if (likely(!current_is_workqueue_rescuer() || - list_empty(&bdi->bdi_list))) { + !test_bit(WB_registered, &wb->state))) { /* - * The normal path. Keep writing back @bdi until its + * The normal path. Keep writing back @wb until its * work_list is empty. Note that this path is also taken - * if @bdi is shutting down even when we're running off the + * if @wb is shutting down even when we're running off the * rescuer as work_list needs to be drained. */ do { pages_written = wb_do_writeback(wb); trace_writeback_pages_written(pages_written); - } while (!list_empty(&bdi->work_list)); + } while (!list_empty(&wb->work_list)); } else { /* * bdi_wq can't get enough workers and we're running off * the emergency worker. Don't hog it. Hopefully, 1024 is * enough for efficient IO. */ - pages_written = writeback_inodes_wb(&bdi->wb, 1024, + pages_written = writeback_inodes_wb(wb, 1024, WB_REASON_FORKER_THREAD); trace_writeback_pages_written(pages_written); } - if (!list_empty(&bdi->work_list) || - (wb_has_dirty_io(wb) && dirty_writeback_interval)) - queue_delayed_work(bdi_wq, &wb->dwork, - msecs_to_jiffies(dirty_writeback_interval * 10)); + if (!list_empty(&wb->work_list)) + wb_wakeup(wb); + else if (wb_has_dirty_io(wb) && dirty_writeback_interval) + wb_wakeup_delayed(wb); +} + +/* + * Start writeback of all dirty pages on this bdi. + */ +static void __wakeup_flusher_threads_bdi(struct backing_dev_info *bdi, + enum wb_reason reason) +{ + struct bdi_writeback *wb; + + if (!bdi_has_dirty_io(bdi)) + return; - current->flags &= ~PF_SWAPWRITE; + list_for_each_entry_rcu(wb, &bdi->wb_list, bdi_node) + wb_start_writeback(wb, reason); +} + +void wakeup_flusher_threads_bdi(struct backing_dev_info *bdi, + enum wb_reason reason) +{ + rcu_read_lock(); + __wakeup_flusher_threads_bdi(bdi, reason); + rcu_read_unlock(); } /* - * Start writeback of `nr_pages' pages. If `nr_pages' is zero, write back - * the whole world. + * Wakeup the flusher threads to start writeback of all currently dirty pages */ -void wakeup_flusher_threads(long nr_pages, enum wb_reason reason) +void wakeup_flusher_threads(enum wb_reason reason) { struct backing_dev_info *bdi; - if (!nr_pages) { - nr_pages = global_page_state(NR_FILE_DIRTY) + - global_page_state(NR_UNSTABLE_NFS); - } + /* + * If we are expecting writeback progress we must submit plugged IO. + */ + blk_flush_plug(current->plug, true); + + rcu_read_lock(); + list_for_each_entry_rcu(bdi, &bdi_list, bdi_list) + __wakeup_flusher_threads_bdi(bdi, reason); + rcu_read_unlock(); +} + +/* + * Wake up bdi's periodically to make sure dirtytime inodes gets + * written back periodically. We deliberately do *not* check the + * b_dirtytime list in wb_has_dirty_io(), since this would cause the + * kernel to be constantly waking up once there are any dirtytime + * inodes on the system. So instead we define a separate delayed work + * function which gets called much more rarely. (By default, only + * once every 12 hours.) + * + * If there is any other write activity going on in the file system, + * this function won't be necessary. But if the only thing that has + * happened on the file system is a dirtytime inode caused by an atime + * update, we need this infrastructure below to make sure that inode + * eventually gets pushed out to disk. + */ +static void wakeup_dirtytime_writeback(struct work_struct *w); +static DECLARE_DELAYED_WORK(dirtytime_work, wakeup_dirtytime_writeback); + +static void wakeup_dirtytime_writeback(struct work_struct *w) +{ + struct backing_dev_info *bdi; rcu_read_lock(); list_for_each_entry_rcu(bdi, &bdi_list, bdi_list) { - if (!bdi_has_dirty_io(bdi)) - continue; - __bdi_start_writeback(bdi, nr_pages, false, reason); + struct bdi_writeback *wb; + + list_for_each_entry_rcu(wb, &bdi->wb_list, bdi_node) + if (!list_empty(&wb->b_dirty_time)) + wb_wakeup(wb); } rcu_read_unlock(); + schedule_delayed_work(&dirtytime_work, dirtytime_expire_interval * HZ); } -static noinline void block_dump___mark_inode_dirty(struct inode *inode) +static int dirtytime_interval_handler(const struct ctl_table *table, int write, + void *buffer, size_t *lenp, loff_t *ppos) { - if (inode->i_ino || strcmp(inode->i_sb->s_id, "bdev")) { - struct dentry *dentry; - const char *name = "?"; + int ret; - dentry = d_find_alias(inode); - if (dentry) { - spin_lock(&dentry->d_lock); - name = (const char *) dentry->d_name.name; - } - printk(KERN_DEBUG - "%s(%d): dirtied inode %lu (%s) on %s\n", - current->comm, task_pid_nr(current), inode->i_ino, - name, inode->i_sb->s_id); - if (dentry) { - spin_unlock(&dentry->d_lock); - dput(dentry); - } - } + ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); + if (ret == 0 && write) + mod_delayed_work(system_percpu_wq, &dirtytime_work, 0); + return ret; } +static const struct ctl_table vm_fs_writeback_table[] = { + { + .procname = "dirtytime_expire_seconds", + .data = &dirtytime_expire_interval, + .maxlen = sizeof(dirtytime_expire_interval), + .mode = 0644, + .proc_handler = dirtytime_interval_handler, + .extra1 = SYSCTL_ZERO, + }, +}; + +static int __init start_dirtytime_writeback(void) +{ + schedule_delayed_work(&dirtytime_work, dirtytime_expire_interval * HZ); + register_sysctl_init("vm", vm_fs_writeback_table); + return 0; +} +__initcall(start_dirtytime_writeback); + /** - * __mark_inode_dirty - internal function - * @inode: inode to mark - * @flags: what kind of dirty (i.e. I_DIRTY_SYNC) - * Mark an inode as dirty. Callers should use mark_inode_dirty or - * mark_inode_dirty_sync. + * __mark_inode_dirty - internal function to mark an inode dirty + * + * @inode: inode to mark + * @flags: what kind of dirty, e.g. I_DIRTY_SYNC. This can be a combination of + * multiple I_DIRTY_* flags, except that I_DIRTY_TIME can't be combined + * with I_DIRTY_PAGES. * - * Put the inode on the super block's dirty list. + * Mark an inode as dirty. We notify the filesystem, then update the inode's + * dirty flags. Then, if needed we add the inode to the appropriate dirty list. * - * CAREFUL! We mark it dirty unconditionally, but move it onto the - * dirty list only if it is hashed or if it refers to a blockdev. - * If it was not hashed, it will never be added to the dirty list - * even if it is later hashed, as it will have been marked dirty already. + * Most callers should use mark_inode_dirty() or mark_inode_dirty_sync() + * instead of calling this directly. * - * In short, make sure you hash any inodes _before_ you start marking - * them dirty. + * CAREFUL! We only add the inode to the dirty list if it is hashed or if it + * refers to a blockdev. Unhashed inodes will never be added to the dirty list + * even if they are later hashed, as they will have been marked dirty already. + * + * In short, ensure you hash any inodes _before_ you start marking them dirty. * * Note that for blockdevs, inode->dirtied_when represents the dirtying time of * the block-special inode (/dev/hda1) itself. And the ->dirtied_when field of @@ -1112,47 +2555,87 @@ static noinline void block_dump___mark_inode_dirty(struct inode *inode) void __mark_inode_dirty(struct inode *inode, int flags) { struct super_block *sb = inode->i_sb; - struct backing_dev_info *bdi = NULL; + int dirtytime = 0; + struct bdi_writeback *wb = NULL; - /* - * Don't do this for I_DIRTY_PAGES - that doesn't actually - * dirty the inode itself - */ - if (flags & (I_DIRTY_SYNC | I_DIRTY_DATASYNC)) { - trace_writeback_dirty_inode_start(inode, flags); + trace_writeback_mark_inode_dirty(inode, flags); - if (sb->s_op->dirty_inode) - sb->s_op->dirty_inode(inode, flags); + if (flags & I_DIRTY_INODE) { + /* + * Inode timestamp update will piggback on this dirtying. + * We tell ->dirty_inode callback that timestamps need to + * be updated by setting I_DIRTY_TIME in flags. + */ + if (inode_state_read_once(inode) & I_DIRTY_TIME) { + spin_lock(&inode->i_lock); + if (inode_state_read(inode) & I_DIRTY_TIME) { + inode_state_clear(inode, I_DIRTY_TIME); + flags |= I_DIRTY_TIME; + } + spin_unlock(&inode->i_lock); + } + /* + * Notify the filesystem about the inode being dirtied, so that + * (if needed) it can update on-disk fields and journal the + * inode. This is only needed when the inode itself is being + * dirtied now. I.e. it's only needed for I_DIRTY_INODE, not + * for just I_DIRTY_PAGES or I_DIRTY_TIME. + */ + trace_writeback_dirty_inode_start(inode, flags); + if (sb->s_op->dirty_inode) + sb->s_op->dirty_inode(inode, + flags & (I_DIRTY_INODE | I_DIRTY_TIME)); trace_writeback_dirty_inode(inode, flags); + + /* I_DIRTY_INODE supersedes I_DIRTY_TIME. */ + flags &= ~I_DIRTY_TIME; + } else { + /* + * Else it's either I_DIRTY_PAGES, I_DIRTY_TIME, or nothing. + * (We don't support setting both I_DIRTY_PAGES and I_DIRTY_TIME + * in one call to __mark_inode_dirty().) + */ + dirtytime = flags & I_DIRTY_TIME; + WARN_ON_ONCE(dirtytime && flags != I_DIRTY_TIME); } /* - * make sure that changes are seen by all cpus before we test i_state - * -- mikulas + * Paired with smp_mb() in __writeback_single_inode() for the + * following lockless i_state test. See there for details. */ smp_mb(); - /* avoid the locking if we can */ - if ((inode->i_state & flags) == flags) + if ((inode_state_read_once(inode) & flags) == flags) return; - if (unlikely(block_dump)) - block_dump___mark_inode_dirty(inode); - spin_lock(&inode->i_lock); - if ((inode->i_state & flags) != flags) { - const int was_dirty = inode->i_state & I_DIRTY; + if ((inode_state_read(inode) & flags) != flags) { + const int was_dirty = inode_state_read(inode) & I_DIRTY; + + inode_attach_wb(inode, NULL); - inode->i_state |= flags; + inode_state_set(inode, flags); /* - * If the inode is being synced, just update its dirty state. - * The unlocker will place the inode on the appropriate - * superblock list, based upon its state. + * Grab inode's wb early because it requires dropping i_lock and we + * need to make sure following checks happen atomically with dirty + * list handling so that we don't move inodes under flush worker's + * hands. */ - if (inode->i_state & I_SYNC) - goto out_unlock_inode; + if (!was_dirty) { + wb = locked_inode_to_wb_and_lock_list(inode); + spin_lock(&inode->i_lock); + } + + /* + * If the inode is queued for writeback by flush worker, just + * update its dirty state. Once the flush worker is done with + * the inode it will place it on the appropriate superblock + * list, based upon its state. + */ + if (inode_state_read(inode) & I_SYNC_QUEUED) + goto out_unlock; /* * Only add valid (hashed) inodes to the superblock's @@ -1160,53 +2643,67 @@ void __mark_inode_dirty(struct inode *inode, int flags) */ if (!S_ISBLK(inode->i_mode)) { if (inode_unhashed(inode)) - goto out_unlock_inode; + goto out_unlock; } - if (inode->i_state & I_FREEING) - goto out_unlock_inode; + if (inode_state_read(inode) & I_FREEING) + goto out_unlock; /* * If the inode was already on b_dirty/b_io/b_more_io, don't * reposition it (that would break b_dirty time-ordering). */ if (!was_dirty) { + struct list_head *dirty_list; bool wakeup_bdi = false; - bdi = inode_to_bdi(inode); - if (bdi_cap_writeback_dirty(bdi)) { - WARN(!test_bit(BDI_registered, &bdi->state), - "bdi-%s not registered\n", bdi->name); + inode->dirtied_when = jiffies; + if (dirtytime) + inode->dirtied_time_when = jiffies; + + if (inode_state_read(inode) & I_DIRTY) + dirty_list = &wb->b_dirty; + else + dirty_list = &wb->b_dirty_time; - /* - * If this is the first dirty inode for this - * bdi, we have to wake-up the corresponding - * bdi thread to make sure background - * write-back happens later. - */ - if (!wb_has_dirty_io(&bdi->wb)) - wakeup_bdi = true; - } + wakeup_bdi = inode_io_list_move_locked(inode, wb, + dirty_list); + + /* + * If this is the first dirty inode for this bdi, + * we have to wake-up the corresponding bdi thread + * to make sure background write-back happens + * later. + */ + if (wakeup_bdi && + (wb->bdi->capabilities & BDI_CAP_WRITEBACK)) + wb_wakeup_delayed(wb); + spin_unlock(&wb->list_lock); spin_unlock(&inode->i_lock); - spin_lock(&bdi->wb.list_lock); - inode->dirtied_when = jiffies; - list_move(&inode->i_wb_list, &bdi->wb.b_dirty); - spin_unlock(&bdi->wb.list_lock); + trace_writeback_dirty_inode_enqueue(inode); - if (wakeup_bdi) - bdi_wakeup_thread_delayed(bdi); return; } } -out_unlock_inode: +out_unlock: + if (wb) + spin_unlock(&wb->list_lock); spin_unlock(&inode->i_lock); - } EXPORT_SYMBOL(__mark_inode_dirty); +/* + * The @s_sync_lock is used to serialise concurrent sync operations + * to avoid lock contention problems with concurrent wait_sb_inodes() calls. + * Concurrent callers will block on the s_sync_lock rather than doing contending + * walks. The queueing maintains sync(2) required behaviour as all the IO that + * has been issued up to the time this function is enter is guaranteed to be + * completed by the time we have gained the lock and waited for all IO that is + * in progress regardless of the order callers are granted the lock. + */ static void wait_sb_inodes(struct super_block *sb) { - struct inode *inode, *old_inode = NULL; + LIST_HEAD(sync_list); /* * We need to be protected against the filesystem going from @@ -1214,47 +2711,101 @@ static void wait_sb_inodes(struct super_block *sb) */ WARN_ON(!rwsem_is_locked(&sb->s_umount)); - spin_lock(&inode_sb_list_lock); + mutex_lock(&sb->s_sync_lock); /* - * Data integrity sync. Must wait for all pages under writeback, - * because there may have been pages dirtied before our sync - * call, but which had writeout started before we write it out. - * In which case, the inode may not be on the dirty list, but - * we still have to wait for that writeout. + * Splice the writeback list onto a temporary list to avoid waiting on + * inodes that have started writeback after this point. + * + * Use rcu_read_lock() to keep the inodes around until we have a + * reference. s_inode_wblist_lock protects sb->s_inodes_wb as well as + * the local list because inodes can be dropped from either by writeback + * completion. + */ + rcu_read_lock(); + spin_lock_irq(&sb->s_inode_wblist_lock); + list_splice_init(&sb->s_inodes_wb, &sync_list); + + /* + * Data integrity sync. Must wait for all pages under writeback, because + * there may have been pages dirtied before our sync call, but which had + * writeout started before we write it out. In which case, the inode + * may not be on the dirty list, but we still have to wait for that + * writeout. */ - list_for_each_entry(inode, &sb->s_inodes, i_sb_list) { + while (!list_empty(&sync_list)) { + struct inode *inode = list_first_entry(&sync_list, struct inode, + i_wb_list); struct address_space *mapping = inode->i_mapping; + /* + * Move each inode back to the wb list before we drop the lock + * to preserve consistency between i_wb_list and the mapping + * writeback tag. Writeback completion is responsible to remove + * the inode from either list once the writeback tag is cleared. + */ + list_move_tail(&inode->i_wb_list, &sb->s_inodes_wb); + + /* + * The mapping can appear untagged while still on-list since we + * do not have the mapping lock. Skip it here, wb completion + * will remove it. + */ + if (!mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK)) + continue; + + spin_unlock_irq(&sb->s_inode_wblist_lock); + spin_lock(&inode->i_lock); - if ((inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW)) || - (mapping->nrpages == 0)) { + if (inode_state_read(inode) & (I_FREEING | I_WILL_FREE | I_NEW)) { spin_unlock(&inode->i_lock); + + spin_lock_irq(&sb->s_inode_wblist_lock); continue; } __iget(inode); spin_unlock(&inode->i_lock); - spin_unlock(&inode_sb_list_lock); + rcu_read_unlock(); /* - * We hold a reference to 'inode' so it couldn't have been - * removed from s_inodes list while we dropped the - * inode_sb_list_lock. We cannot iput the inode now as we can - * be holding the last reference and we cannot iput it under - * inode_sb_list_lock. So we keep the reference and iput it - * later. + * We keep the error status of individual mapping so that + * applications can catch the writeback error using fsync(2). + * See filemap_fdatawait_keep_errors() for details. */ - iput(old_inode); - old_inode = inode; - - filemap_fdatawait(mapping); + filemap_fdatawait_keep_errors(mapping); cond_resched(); - spin_lock(&inode_sb_list_lock); + iput(inode); + + rcu_read_lock(); + spin_lock_irq(&sb->s_inode_wblist_lock); } - spin_unlock(&inode_sb_list_lock); - iput(old_inode); + spin_unlock_irq(&sb->s_inode_wblist_lock); + rcu_read_unlock(); + mutex_unlock(&sb->s_sync_lock); +} + +static void __writeback_inodes_sb_nr(struct super_block *sb, unsigned long nr, + enum wb_reason reason, bool skip_if_busy) +{ + struct backing_dev_info *bdi = sb->s_bdi; + DEFINE_WB_COMPLETION(done, bdi); + struct wb_writeback_work work = { + .sb = sb, + .sync_mode = WB_SYNC_NONE, + .tagged_writepages = 1, + .done = &done, + .nr_pages = nr, + .reason = reason, + }; + + if (!bdi_has_dirty_io(bdi) || bdi == &noop_backing_dev_info) + return; + WARN_ON(!rwsem_is_locked(&sb->s_umount)); + + bdi_split_work_to_wbs(sb->s_bdi, &work, skip_if_busy); + wb_wait_for_completion(&done); } /** @@ -1271,21 +2822,7 @@ void writeback_inodes_sb_nr(struct super_block *sb, unsigned long nr, enum wb_reason reason) { - DECLARE_COMPLETION_ONSTACK(done); - struct wb_writeback_work work = { - .sb = sb, - .sync_mode = WB_SYNC_NONE, - .tagged_writepages = 1, - .done = &done, - .nr_pages = nr, - .reason = reason, - }; - - if (sb->s_bdi == &noop_backing_dev_info) - return; - WARN_ON(!rwsem_is_locked(&sb->s_umount)); - bdi_queue_work(sb->s_bdi, &work); - wait_for_completion(&done); + __writeback_inodes_sb_nr(sb, nr, reason, false); } EXPORT_SYMBOL(writeback_inodes_sb_nr); @@ -1300,46 +2837,24 @@ EXPORT_SYMBOL(writeback_inodes_sb_nr); */ void writeback_inodes_sb(struct super_block *sb, enum wb_reason reason) { - return writeback_inodes_sb_nr(sb, get_nr_dirty_pages(), reason); + writeback_inodes_sb_nr(sb, get_nr_dirty_pages(), reason); } EXPORT_SYMBOL(writeback_inodes_sb); /** - * try_to_writeback_inodes_sb_nr - try to start writeback if none underway + * try_to_writeback_inodes_sb - try to start writeback if none underway * @sb: the superblock - * @nr: the number of pages to write - * @reason: the reason of writeback + * @reason: reason why some writeback work was initiated * - * Invoke writeback_inodes_sb_nr if no writeback is currently underway. - * Returns 1 if writeback was started, 0 if not. + * Invoke __writeback_inodes_sb_nr if no writeback is currently underway. */ -int try_to_writeback_inodes_sb_nr(struct super_block *sb, - unsigned long nr, - enum wb_reason reason) +void try_to_writeback_inodes_sb(struct super_block *sb, enum wb_reason reason) { - if (writeback_in_progress(sb->s_bdi)) - return 1; - if (!down_read_trylock(&sb->s_umount)) - return 0; + return; - writeback_inodes_sb_nr(sb, nr, reason); + __writeback_inodes_sb_nr(sb, get_nr_dirty_pages(), reason, true); up_read(&sb->s_umount); - return 1; -} -EXPORT_SYMBOL(try_to_writeback_inodes_sb_nr); - -/** - * try_to_writeback_inodes_sb - try to start writeback if none underway - * @sb: the superblock - * @reason: reason why some writeback work was initiated - * - * Implement by try_to_writeback_inodes_sb_nr() - * Returns 1 if writeback was started, 0 if not. - */ -int try_to_writeback_inodes_sb(struct super_block *sb, enum wb_reason reason) -{ - return try_to_writeback_inodes_sb_nr(sb, get_nr_dirty_pages(), reason); } EXPORT_SYMBOL(try_to_writeback_inodes_sb); @@ -1352,7 +2867,8 @@ EXPORT_SYMBOL(try_to_writeback_inodes_sb); */ void sync_inodes_sb(struct super_block *sb) { - DECLARE_COMPLETION_ONSTACK(done); + struct backing_dev_info *bdi = sb->s_bdi; + DEFINE_WB_COMPLETION(done, bdi); struct wb_writeback_work work = { .sb = sb, .sync_mode = WB_SYNC_ALL, @@ -1363,13 +2879,20 @@ void sync_inodes_sb(struct super_block *sb) .for_sync = 1, }; - /* Nothing to do? */ - if (sb->s_bdi == &noop_backing_dev_info) + /* + * Can't skip on !bdi_has_dirty() because we should wait for !dirty + * inodes under writeback and I_DIRTY_TIME inodes ignored by + * bdi_has_dirty() need to be written out too. + */ + if (bdi == &noop_backing_dev_info) return; WARN_ON(!rwsem_is_locked(&sb->s_umount)); - bdi_queue_work(sb->s_bdi, &work); - wait_for_completion(&done); + /* protect against inode wb switch, see inode_switch_wbs_work_fn() */ + bdi_down_write_wb_switch_rwsem(bdi); + bdi_split_work_to_wbs(bdi, &work, false); + wb_wait_for_completion(&done); + bdi_up_write_wb_switch_rwsem(bdi); wait_sb_inodes(sb); } @@ -1387,7 +2910,6 @@ EXPORT_SYMBOL(sync_inodes_sb); */ int write_inode_now(struct inode *inode, int sync) { - struct bdi_writeback *wb = &inode_to_bdi(inode)->wb; struct writeback_control wbc = { .nr_to_write = LONG_MAX, .sync_mode = sync ? WB_SYNC_ALL : WB_SYNC_NONE, @@ -1395,32 +2917,15 @@ int write_inode_now(struct inode *inode, int sync) .range_end = LLONG_MAX, }; - if (!mapping_cap_writeback_dirty(inode->i_mapping)) + if (!mapping_can_writeback(inode->i_mapping)) wbc.nr_to_write = 0; might_sleep(); - return writeback_single_inode(inode, wb, &wbc); + return writeback_single_inode(inode, &wbc); } EXPORT_SYMBOL(write_inode_now); /** - * sync_inode - write an inode and its pages to disk. - * @inode: the inode to sync - * @wbc: controls the writeback mode - * - * sync_inode() will write an inode and its pages to disk. It will also - * correctly update the inode on its superblock's dirty inode lists and will - * update inode->i_state. - * - * The caller must have a ref on the inode. - */ -int sync_inode(struct inode *inode, struct writeback_control *wbc) -{ - return writeback_single_inode(inode, &inode_to_bdi(inode)->wb, wbc); -} -EXPORT_SYMBOL(sync_inode); - -/** * sync_inode_metadata - write an inode to disk * @inode: the inode to sync * @wait: wait for I/O to complete. @@ -1436,6 +2941,6 @@ int sync_inode_metadata(struct inode *inode, int wait) .nr_to_write = 0, /* metadata-only */ }; - return sync_inode(inode, &wbc); + return writeback_single_inode(inode, &wbc); } EXPORT_SYMBOL(sync_inode_metadata); |