diff options
Diffstat (limited to 'fs/fs-writeback.c')
| -rw-r--r-- | fs/fs-writeback.c | 367 |
1 files changed, 220 insertions, 147 deletions
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 3cd99e2dc6ac..6800886c4d10 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -14,6 +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> @@ -32,11 +33,6 @@ #include "internal.h" /* - * 4MB minimal write chunk size - */ -#define MIN_WRITEBACK_PAGES (4096UL >> (PAGE_SHIFT - 10)) - -/* * Passed into wb_writeback(), essentially a subset of writeback_control */ struct wb_writeback_work { @@ -65,7 +61,7 @@ struct wb_writeback_work { * timestamps written to disk after 12 hours, but in the worst case a * few inodes might not their timestamps updated for 24 hours. */ -unsigned int dirtytime_expire_interval = 12 * 60 * 60; +static unsigned int dirtytime_expire_interval = 12 * 60 * 60; static inline struct inode *wb_inode(struct list_head *head) { @@ -121,7 +117,7 @@ static bool inode_io_list_move_locked(struct inode *inode, { assert_spin_locked(&wb->list_lock); assert_spin_locked(&inode->i_lock); - WARN_ON_ONCE(inode->i_state & I_FREEING); + WARN_ON_ONCE(inode_state_read(inode) & I_FREEING); list_move(&inode->i_io_list, head); @@ -200,6 +196,19 @@ static void wb_queue_work(struct bdi_writeback *wb, 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 @@ -212,8 +221,9 @@ static void wb_queue_work(struct bdi_writeback *wb, */ 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, !atomic_read(&done->cnt)); + wait_event(*done->waitq, wb_wait_for_completion_cb(done)); } #ifdef CONFIG_CGROUP_WRITEBACK @@ -304,9 +314,9 @@ static void inode_cgwb_move_to_attached(struct inode *inode, { assert_spin_locked(&wb->list_lock); assert_spin_locked(&inode->i_lock); - WARN_ON_ONCE(inode->i_state & I_FREEING); + WARN_ON_ONCE(inode_state_read(inode) & I_FREEING); - inode->i_state &= ~I_SYNC_QUEUED; + inode_state_clear(inode, I_SYNC_QUEUED); if (wb != &wb->bdi->wb) list_move(&inode->i_io_list, &wb->b_attached); else @@ -368,7 +378,8 @@ static struct bdi_writeback *inode_to_wb_and_lock_list(struct inode *inode) } struct inode_switch_wbs_context { - struct rcu_work work; + /* List of queued switching contexts for the wb */ + struct llist_node list; /* * Multiple inodes can be switched at once. The switching procedure @@ -378,7 +389,6 @@ struct inode_switch_wbs_context { * array embedded into struct inode_switch_wbs_context. Otherwise * an inode could be left in a non-consistent state. */ - struct bdi_writeback *new_wb; struct inode *inodes[]; }; @@ -408,7 +418,7 @@ static bool inode_do_switch_wbs(struct inode *inode, * 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->i_state & (I_FREEING | I_WILL_FREE))) + if (unlikely(inode_state_read(inode) & (I_FREEING | I_WILL_FREE))) goto skip_switch; trace_inode_switch_wbs(inode, old_wb, new_wb); @@ -445,22 +455,23 @@ static bool inode_do_switch_wbs(struct inode *inode, * 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. - * The transfer preserves @inode->dirtied_when ordering. 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 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->i_state & I_DIRTY_ALL) { - struct inode *pos; - - list_for_each_entry(pos, &new_wb->b_dirty, i_io_list) - if (time_after_eq(inode->dirtied_when, - pos->dirtied_when)) - break; + 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, - pos->i_io_list.prev); + &new_wb->b_dirty); } else { inode_cgwb_move_to_attached(inode, new_wb); } @@ -475,10 +486,11 @@ static bool inode_do_switch_wbs(struct inode *inode, switched = true; skip_switch: /* - * Paired with load_acquire in unlocked_inode_to_wb_begin() and + * 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_store_release(&inode->i_state, inode->i_state & ~I_WB_SWITCH); + smp_wmb(); + inode_state_clear(inode, I_WB_SWITCH); xa_unlock_irq(&mapping->i_pages); spin_unlock(&inode->i_lock); @@ -486,13 +498,11 @@ skip_switch: return switched; } -static void inode_switch_wbs_work_fn(struct work_struct *work) +static void process_inode_switch_wbs(struct bdi_writeback *new_wb, + struct inode_switch_wbs_context *isw) { - struct inode_switch_wbs_context *isw = - container_of(to_rcu_work(work), struct inode_switch_wbs_context, work); struct backing_dev_info *bdi = inode_to_bdi(isw->inodes[0]); struct bdi_writeback *old_wb = isw->inodes[0]->i_wb; - struct bdi_writeback *new_wb = isw->new_wb; unsigned long nr_switched = 0; struct inode **inodep; @@ -502,6 +512,7 @@ static void inode_switch_wbs_work_fn(struct work_struct *work) */ 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 @@ -512,6 +523,7 @@ static void inode_switch_wbs_work_fn(struct work_struct *work) * 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); @@ -520,10 +532,17 @@ static void inode_switch_wbs_work_fn(struct work_struct *work) spin_lock_nested(&old_wb->list_lock, SINGLE_DEPTH_NESTING); } - for (inodep = isw->inodes; *inodep; inodep++) { + 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); @@ -543,6 +562,38 @@ static void inode_switch_wbs_work_fn(struct work_struct *work) 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) { @@ -560,18 +611,25 @@ static bool inode_prepare_wbs_switch(struct inode *inode, /* 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->i_state & (I_WB_SWITCH | I_FREEING | I_WILL_FREE) || + 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->i_state |= I_WB_SWITCH; + 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 @@ -585,9 +643,10 @@ 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->i_state & I_WB_SWITCH) + if (inode_state_read_once(inode) & I_WB_SWITCH) return; /* avoid queueing a new switch if too many are already in flight */ @@ -609,40 +668,35 @@ static void inode_switch_wbs(struct inode *inode, int new_wb_id) if (!memcg_css) goto out_free; - isw->new_wb = wb_get_create(bdi, memcg_css, GFP_ATOMIC); + new_wb = wb_get_create(bdi, memcg_css, GFP_ATOMIC); css_put(memcg_css); - if (!isw->new_wb) + if (!new_wb) goto out_free; - if (!inode_prepare_wbs_switch(inode, isw->new_wb)) + if (!inode_prepare_wbs_switch(inode, new_wb)) goto out_free; isw->inodes[0] = inode; - /* - * 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. - */ - INIT_RCU_WORK(&isw->work, inode_switch_wbs_work_fn); - queue_rcu_work(isw_wq, &isw->work); + 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 (isw->new_wb) - wb_put(isw->new_wb); + if (new_wb) + wb_put(new_wb); kfree(isw); } -static bool isw_prepare_wbs_switch(struct inode_switch_wbs_context *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, isw->new_wb)) + if (!inode_prepare_wbs_switch(inode, new_wb)) continue; isw->inodes[*nr] = inode; @@ -666,6 +720,7 @@ 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; @@ -678,12 +733,12 @@ bool cleanup_offline_cgwb(struct bdi_writeback *wb) for (memcg_css = wb->memcg_css->parent; memcg_css; memcg_css = memcg_css->parent) { - isw->new_wb = wb_get_create(wb->bdi, memcg_css, GFP_KERNEL); - if (isw->new_wb) + new_wb = wb_get_create(wb->bdi, memcg_css, GFP_KERNEL); + if (new_wb) break; } - if (unlikely(!isw->new_wb)) - isw->new_wb = &wb->bdi->wb; /* wb_get() is noop for bdi's wb */ + if (unlikely(!new_wb)) + new_wb = &wb->bdi->wb; /* wb_get() is noop for bdi's wb */ nr = 0; spin_lock(&wb->list_lock); @@ -695,27 +750,22 @@ bool cleanup_offline_cgwb(struct bdi_writeback *wb) * bandwidth restrictions, as writeback of inode metadata is not * accounted for. */ - restart = isw_prepare_wbs_switch(isw, &wb->b_attached, &nr); + restart = isw_prepare_wbs_switch(new_wb, isw, &wb->b_attached, &nr); if (!restart) - restart = isw_prepare_wbs_switch(isw, &wb->b_dirty_time, &nr); + 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(isw->new_wb); + wb_put(new_wb); kfree(isw); return restart; } - /* - * 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. - */ - INIT_RCU_WORK(&isw->work, inode_switch_wbs_work_fn); - queue_rcu_work(isw_wq, &isw->work); + trace_inode_switch_wbs_queue(wb, new_wb, nr); + wb_queue_isw(new_wb, isw); return restart; } @@ -768,9 +818,9 @@ static void wbc_attach_and_unlock_inode(struct writeback_control *wbc, * @wbc: writeback_control of interest * @inode: target inode * - * This function is to be used by __filemap_fdatawrite_range(), which is an - * alternative entry point into writeback code, and first ensures @inode is - * associated with a bdi_writeback and attaches it to @wbc. + * 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) @@ -1123,7 +1173,7 @@ int cgroup_writeback_by_id(u64 bdi_id, int memcg_id, dirty = dirty * 10 / 8; /* issue the writeback work */ - work = kzalloc(sizeof(*work), GFP_NOWAIT | __GFP_NOWARN); + work = kzalloc(sizeof(*work), GFP_NOWAIT); if (work) { work->nr_pages = dirty; work->sync_mode = WB_SYNC_NONE; @@ -1180,7 +1230,7 @@ void cgroup_writeback_umount(struct super_block *sb) static int __init cgroup_writeback_init(void) { - isw_wq = alloc_workqueue("inode_switch_wbs", 0, 0); + isw_wq = alloc_workqueue("inode_switch_wbs", WQ_PERCPU, 0); if (!isw_wq) return -ENOMEM; return 0; @@ -1197,9 +1247,9 @@ static void inode_cgwb_move_to_attached(struct inode *inode, { assert_spin_locked(&wb->list_lock); assert_spin_locked(&inode->i_lock); - WARN_ON_ONCE(inode->i_state & I_FREEING); + WARN_ON_ONCE(inode_state_read(inode) & I_FREEING); - inode->i_state &= ~I_SYNC_QUEUED; + inode_state_clear(inode, I_SYNC_QUEUED); list_del_init(&inode->i_io_list); wb_io_lists_depopulated(wb); } @@ -1309,10 +1359,17 @@ void inode_io_list_del(struct inode *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->i_state &= ~I_SYNC_QUEUED; + inode_state_clear(inode, I_SYNC_QUEUED); list_del_init(&inode->i_io_list); wb_io_lists_depopulated(wb); @@ -1370,13 +1427,13 @@ static void redirty_tail_locked(struct inode *inode, struct bdi_writeback *wb) { assert_spin_locked(&inode->i_lock); - inode->i_state &= ~I_SYNC_QUEUED; + 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->i_state & I_FREEING) { + if (inode_state_read(inode) & I_FREEING) { list_del_init(&inode->i_io_list); wb_io_lists_depopulated(wb); return; @@ -1410,9 +1467,9 @@ static void inode_sync_complete(struct inode *inode) { assert_spin_locked(&inode->i_lock); - inode->i_state &= ~I_SYNC; + inode_state_clear(inode, I_SYNC); /* If inode is clean an unused, put it into LRU now... */ - inode_add_lru(inode); + inode_lru_list_add(inode); /* Called with inode->i_lock which ensures memory ordering. */ inode_wake_up_bit(inode, __I_SYNC); } @@ -1454,7 +1511,7 @@ static int move_expired_inodes(struct list_head *delaying_queue, spin_lock(&inode->i_lock); list_move(&inode->i_io_list, &tmp); moved++; - inode->i_state |= I_SYNC_QUEUED; + inode_state_set(inode, I_SYNC_QUEUED); spin_unlock(&inode->i_lock); if (sb_is_blkdev_sb(inode->i_sb)) continue; @@ -1540,14 +1597,14 @@ void inode_wait_for_writeback(struct inode *inode) assert_spin_locked(&inode->i_lock); - if (!(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->i_state & I_SYNC)) + if (!(inode_state_read(inode) & I_SYNC)) break; spin_unlock(&inode->i_lock); schedule(); @@ -1573,7 +1630,7 @@ static void inode_sleep_on_writeback(struct inode *inode) 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->i_state & I_SYNC); + sleep = !!(inode_state_read(inode) & I_SYNC); spin_unlock(&inode->i_lock); if (sleep) schedule(); @@ -1592,7 +1649,7 @@ static void requeue_inode(struct inode *inode, struct bdi_writeback *wb, struct writeback_control *wbc, unsigned long dirtied_before) { - if (inode->i_state & I_FREEING) + if (inode_state_read(inode) & I_FREEING) return; /* @@ -1600,7 +1657,7 @@ 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; @@ -1611,7 +1668,7 @@ static void requeue_inode(struct inode *inode, struct bdi_writeback *wb, * is odd for clean inodes, it can happen for some * filesystems so handle that gracefully. */ - if (inode->i_state & I_DIRTY_ALL) + if (inode_state_read(inode) & I_DIRTY_ALL) redirty_tail_locked(inode, wb); else inode_cgwb_move_to_attached(inode, wb); @@ -1637,17 +1694,17 @@ static void requeue_inode(struct inode *inode, struct bdi_writeback *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_locked(inode, wb); - } else if (inode->i_state & I_DIRTY_TIME) { + } 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->i_state &= ~I_SYNC_QUEUED; + inode_state_clear(inode, I_SYNC_QUEUED); } else { /* The inode is clean. Remove from writeback lists. */ inode_cgwb_move_to_attached(inode, wb); @@ -1673,7 +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); @@ -1697,7 +1754,7 @@ __writeback_single_inode(struct inode *inode, struct writeback_control *wbc) * mark_inode_dirty_sync() to notify the filesystem about it and to * change I_DIRTY_TIME into I_DIRTY_SYNC. */ - if ((inode->i_state & I_DIRTY_TIME) && + 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))) { @@ -1712,8 +1769,8 @@ __writeback_single_inode(struct inode *inode, struct writeback_control *wbc) * after handling timestamp expiration, as that may dirty the inode too. */ spin_lock(&inode->i_lock); - dirty = inode->i_state & I_DIRTY; - inode->i_state &= ~dirty; + dirty = inode_state_read(inode) & I_DIRTY; + inode_state_clear(inode, dirty); /* * Paired with smp_mb() in __mark_inode_dirty(). This allows @@ -1729,10 +1786,10 @@ __writeback_single_inode(struct inode *inode, struct writeback_control *wbc) smp_mb(); if (mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) - inode->i_state |= I_DIRTY_PAGES; - else if (unlikely(inode->i_state & I_PINNING_NETFS_WB)) { - if (!(inode->i_state & I_DIRTY_PAGES)) { - inode->i_state &= ~I_PINNING_NETFS_WB; + 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 */ } @@ -1767,12 +1824,12 @@ static int writeback_single_inode(struct inode *inode, 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 (inode_state_read(inode) & I_SYNC) { /* * Writeback is already running on the inode. For WB_SYNC_NONE, * that's enough and we can just return. For WB_SYNC_ALL, we @@ -1783,7 +1840,7 @@ static int writeback_single_inode(struct inode *inode, goto out; inode_wait_for_writeback(inode); } - WARN_ON(inode->i_state & I_SYNC); + WARN_ON(inode_state_read(inode) & I_SYNC); /* * If the inode is already fully clean, then there's nothing to do. * @@ -1791,11 +1848,11 @@ static int writeback_single_inode(struct inode *inode, * 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_ALL) && + 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; + inode_state_set(inode, I_SYNC); wbc_attach_and_unlock_inode(wbc, inode); ret = __writeback_single_inode(inode, wbc); @@ -1808,18 +1865,18 @@ static int writeback_single_inode(struct inode *inode, * 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_FREEING)) { + 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->i_state & I_DIRTY_ALL)) + if (!(inode_state_read(inode) & I_DIRTY_ALL)) inode_cgwb_move_to_attached(inode, wb); - else if (!(inode->i_state & I_SYNC_QUEUED)) { - if ((inode->i_state & I_DIRTY)) + else if (!(inode_state_read(inode) & I_SYNC_QUEUED)) { + if ((inode_state_read(inode) & I_DIRTY)) redirty_tail_locked(inode, wb); - else if (inode->i_state & I_DIRTY_TIME) { + else if (inode_state_read(inode) & I_DIRTY_TIME) { inode->dirtied_when = jiffies; inode_io_list_move_locked(inode, wb, @@ -1835,8 +1892,8 @@ out: return ret; } -static long writeback_chunk_size(struct bdi_writeback *wb, - 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; @@ -1854,16 +1911,13 @@ static long writeback_chunk_size(struct bdi_writeback *wb, * (maybe slowly) sync all tagged pages */ if (work->sync_mode == WB_SYNC_ALL || work->tagged_writepages) - pages = LONG_MAX; - else { - pages = min(wb->avg_write_bandwidth / 2, - global_wb_domain.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); } /* @@ -1928,12 +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); 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 @@ -1955,17 +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; + inode_state_set(inode, I_SYNC); wbc_attach_and_unlock_inode(&wbc, inode); - write_chunk = writeback_chunk_size(wb, work); + write_chunk = writeback_chunk_size(inode->i_sb, wb, work); wbc.nr_to_write = write_chunk; wbc.pages_skipped = 0; @@ -1975,6 +2029,12 @@ 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 - wbc.pages_skipped; @@ -2000,7 +2060,7 @@ static long writeback_sb_inodes(struct super_block *sb, */ tmp_wb = inode_to_wb_and_lock_list(inode); spin_lock(&inode->i_lock); - if (!(inode->i_state & I_DIRTY_ALL)) + if (!(inode_state_read(inode) & I_DIRTY_ALL)) total_wrote++; requeue_inode(inode, tmp_wb, &wbc, dirtied_before); inode_sync_complete(inode); @@ -2435,24 +2495,36 @@ static void wakeup_dirtytime_writeback(struct work_struct *w) schedule_delayed_work(&dirtytime_work, dirtytime_expire_interval * HZ); } -static int __init start_dirtytime_writeback(void) -{ - schedule_delayed_work(&dirtytime_work, dirtytime_expire_interval * HZ); - return 0; -} -__initcall(start_dirtytime_writeback); - -int dirtytime_interval_handler(const struct ctl_table *table, int write, +static int dirtytime_interval_handler(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int ret; ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); if (ret == 0 && write) - mod_delayed_work(system_wq, &dirtytime_work, 0); + 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 to mark an inode dirty * @@ -2494,10 +2566,10 @@ void __mark_inode_dirty(struct inode *inode, int flags) * We tell ->dirty_inode callback that timestamps need to * be updated by setting I_DIRTY_TIME in flags. */ - if (inode->i_state & I_DIRTY_TIME) { + if (inode_state_read_once(inode) & I_DIRTY_TIME) { spin_lock(&inode->i_lock); - if (inode->i_state & I_DIRTY_TIME) { - inode->i_state &= ~I_DIRTY_TIME; + if (inode_state_read(inode) & I_DIRTY_TIME) { + inode_state_clear(inode, I_DIRTY_TIME); flags |= I_DIRTY_TIME; } spin_unlock(&inode->i_lock); @@ -2534,16 +2606,16 @@ void __mark_inode_dirty(struct inode *inode, int flags) */ smp_mb(); - if ((inode->i_state & flags) == flags) + if ((inode_state_read_once(inode) & flags) == flags) return; 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); /* * Grab inode's wb early because it requires dropping i_lock and we @@ -2562,7 +2634,7 @@ void __mark_inode_dirty(struct inode *inode, int flags) * the inode it will place it on the appropriate superblock * list, based upon its state. */ - if (inode->i_state & I_SYNC_QUEUED) + if (inode_state_read(inode) & I_SYNC_QUEUED) goto out_unlock; /* @@ -2573,7 +2645,7 @@ void __mark_inode_dirty(struct inode *inode, int flags) if (inode_unhashed(inode)) goto out_unlock; } - if (inode->i_state & I_FREEING) + if (inode_state_read(inode) & I_FREEING) goto out_unlock; /* @@ -2588,7 +2660,7 @@ void __mark_inode_dirty(struct inode *inode, int flags) if (dirtytime) inode->dirtied_time_when = jiffies; - if (inode->i_state & I_DIRTY) + if (inode_state_read(inode) & I_DIRTY) dirty_list = &wb->b_dirty; else dirty_list = &wb->b_dirty_time; @@ -2596,10 +2668,6 @@ void __mark_inode_dirty(struct inode *inode, int flags) wakeup_bdi = inode_io_list_move_locked(inode, wb, dirty_list); - spin_unlock(&wb->list_lock); - spin_unlock(&inode->i_lock); - trace_writeback_dirty_inode_enqueue(inode); - /* * If this is the first dirty inode for this bdi, * we have to wake-up the corresponding bdi thread @@ -2609,6 +2677,11 @@ void __mark_inode_dirty(struct inode *inode, int flags) if (wakeup_bdi && (wb->bdi->capabilities & BDI_CAP_WRITEBACK)) wb_wakeup_delayed(wb); + + spin_unlock(&wb->list_lock); + spin_unlock(&inode->i_lock); + trace_writeback_dirty_inode_enqueue(inode); + return; } } @@ -2684,7 +2757,7 @@ static void wait_sb_inodes(struct super_block *sb) spin_unlock_irq(&sb->s_inode_wblist_lock); spin_lock(&inode->i_lock); - if (inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW)) { + 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); |