{
assert_spin_locked(&wb->list_lock);
assert_spin_locked(&inode->i_lock);
+ WARN_ON_ONCE(inode->i_state & I_FREEING);
list_move(&inode->i_io_list, head);
static void wb_wakeup(struct bdi_writeback *wb)
{
- spin_lock_bh(&wb->work_lock);
+ spin_lock_irq(&wb->work_lock);
if (test_bit(WB_registered, &wb->state))
mod_delayed_work(bdi_wq, &wb->dwork, 0);
- spin_unlock_bh(&wb->work_lock);
+ spin_unlock_irq(&wb->work_lock);
+}
+
+/*
+ * 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;
+
+ 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 void finish_writeback_work(struct bdi_writeback *wb,
if (work->done)
atomic_inc(&work->done->cnt);
- spin_lock_bh(&wb->work_lock);
+ spin_lock_irq(&wb->work_lock);
if (test_bit(WB_registered, &wb->state)) {
list_add_tail(&work->list, &wb->work_list);
} else
finish_writeback_work(wb, work);
- spin_unlock_bh(&wb->work_lock);
+ spin_unlock_irq(&wb->work_lock);
}
/**
static atomic_t isw_nr_in_flight = ATOMIC_INIT(0);
static struct workqueue_struct *isw_wq;
-void __inode_attach_wb(struct inode *inode, struct page *page)
+void __inode_attach_wb(struct inode *inode, struct folio *folio)
{
struct backing_dev_info *bdi = inode_to_bdi(inode);
struct bdi_writeback *wb = NULL;
if (inode_cgwb_enabled(inode)) {
struct cgroup_subsys_state *memcg_css;
- if (page) {
- memcg_css = mem_cgroup_css_from_page(page);
+ 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() */
{
assert_spin_locked(&wb->list_lock);
assert_spin_locked(&inode->i_lock);
+ WARN_ON_ONCE(inode->i_state & I_FREEING);
inode->i_state &= ~I_SYNC_QUEUED;
if (wb != &wb->bdi->wb)
kfree(isw);
}
+static bool isw_prepare_wbs_switch(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))
+ continue;
+
+ isw->inodes[*nr] = inode;
+ (*nr)++;
+
+ if (*nr >= WB_MAX_INODES_PER_ISW - 1)
+ return true;
+ }
+ return false;
+}
+
/**
* cleanup_offline_cgwb - detach associated inodes
* @wb: target wb
{
struct cgroup_subsys_state *memcg_css;
struct inode_switch_wbs_context *isw;
- struct inode *inode;
int nr;
bool restart = false;
nr = 0;
spin_lock(&wb->list_lock);
- list_for_each_entry(inode, &wb->b_attached, i_io_list) {
- if (!inode_prepare_wbs_switch(inode, isw->new_wb))
- continue;
-
- isw->inodes[nr++] = inode;
-
- if (nr >= WB_MAX_INODES_PER_ISW - 1) {
- restart = true;
- break;
- }
- }
+ /*
+ * 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(isw, &wb->b_attached, &nr);
+ if (!restart)
+ restart = isw_prepare_wbs_switch(isw, &wb->b_dirty_time, &nr);
spin_unlock(&wb->list_lock);
/* no attached inodes? bail out */
* is okay. The main goal is avoiding keeping an inode on
* the wrong wb for an extended period of time.
*/
- if (hweight32(history) > WB_FRN_HIST_THR_SLOTS)
+ if (hweight16(history) > WB_FRN_HIST_THR_SLOTS)
inode_switch_wbs(inode, max_id);
}
void wbc_account_cgroup_owner(struct writeback_control *wbc, struct page *page,
size_t bytes)
{
+ struct folio *folio;
struct cgroup_subsys_state *css;
int id;
if (!wbc->wb || wbc->no_cgroup_owner)
return;
- css = mem_cgroup_css_from_page(page);
+ folio = page_folio(page);
+ css = mem_cgroup_css_from_folio(folio);
/* dead cgroups shouldn't contribute to inode ownership arbitration */
if (!(css->flags & CSS_ONLINE))
return;
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->done = &fallback_work_done;
wb_queue_work(wb, work);
-
- /*
- * Pin @wb so that it stays on @bdi->wb_list. This allows
- * continuing iteration from @wb after dropping and
- * regrabbing rcu read lock.
- */
- wb_get(wb);
last_wb = wb;
rcu_read_unlock();
{
assert_spin_locked(&wb->list_lock);
assert_spin_locked(&inode->i_lock);
+ WARN_ON_ONCE(inode->i_state & I_FREEING);
inode->i_state &= ~I_SYNC_QUEUED;
list_del_init(&inode->i_io_list);
{
assert_spin_locked(&inode->i_lock);
+ inode->i_state &= ~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) {
+ list_del_init(&inode->i_io_list);
+ wb_io_lists_depopulated(wb);
+ return;
+ }
if (!list_empty(&wb->b_dirty)) {
struct inode *tail;
inode->dirtied_when = jiffies;
}
inode_io_list_move_locked(inode, wb, &wb->b_dirty);
- inode->i_state &= ~I_SYNC_QUEUED;
}
static void redirty_tail(struct inode *inode, struct bdi_writeback *wb)
return ret;
}
-#define EXPIRE_DIRTY_ATIME 0x0001
-
/*
* Move expired (dirtied before dirtied_before) dirty inodes from
* @delaying_queue to @dispatch_queue.
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_locked(inode, wb);
+ if (inode->i_state & I_DIRTY_ALL)
+ redirty_tail_locked(inode, wb);
+ else
+ inode_cgwb_move_to_attached(inode, wb);
return;
}
if (mapping_tagged(mapping, PAGECACHE_TAG_DIRTY))
inode->i_state |= I_DIRTY_PAGES;
- else if (unlikely(inode->i_state & I_PINNING_FSCACHE_WB)) {
+ else if (unlikely(inode->i_state & I_PINNING_NETFS_WB)) {
if (!(inode->i_state & I_DIRTY_PAGES)) {
- inode->i_state &= ~I_PINNING_FSCACHE_WB;
- wbc->unpinned_fscache_wb = true;
- dirty |= I_PINNING_FSCACHE_WB; /* Cause write_inode */
+ inode->i_state &= ~I_PINNING_NETFS_WB;
+ wbc->unpinned_netfs_wb = true;
+ dirty |= I_PINNING_NETFS_WB; /* Cause write_inode */
}
}
if (ret == 0)
ret = err;
}
- wbc->unpinned_fscache_wb = false;
+ wbc->unpinned_netfs_wb = false;
trace_writeback_single_inode(inode, wbc, nr_to_write);
return ret;
}
wb = inode_to_wb_and_lock_list(inode);
spin_lock(&inode->i_lock);
/*
- * 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 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_ALL))
- inode_cgwb_move_to_attached(inode, wb);
- else if (!(inode->i_state & I_SYNC_QUEUED) &&
- (inode->i_state & I_DIRTY))
- redirty_tail_locked(inode, wb);
+ if (!(inode->i_state & 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))
+ inode_cgwb_move_to_attached(inode, wb);
+ else if (!(inode->i_state & I_SYNC_QUEUED)) {
+ if ((inode->i_state & I_DIRTY))
+ redirty_tail_locked(inode, wb);
+ else if (inode->i_state & 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);
struct inode *inode = wb_inode(wb->b_io.prev);
struct super_block *sb = inode->i_sb;
- if (!trylock_super(sb)) {
+ if (!super_trylock_shared(sb)) {
/*
- * trylock_super() 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.
*/
struct blk_plug plug;
blk_start_plug(&plug);
- spin_lock(&wb->list_lock);
for (;;) {
/*
* Stop writeback when nr_pages has been consumed
if (work->for_background && !wb_over_bg_thresh(wb))
break;
+
+ spin_lock(&wb->list_lock);
+
/*
* Kupdate and background works are special and we want to
* include all inodes that need writing. Livelock avoidance is
* 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) {
+ 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
spin_unlock(&wb->list_lock);
/* This function drops i_lock... */
inode_sleep_on_writeback(inode);
- spin_lock(&wb->list_lock);
}
- spin_unlock(&wb->list_lock);
blk_finish_plug(&plug);
return nr_pages - work->nr_pages;
{
struct wb_writeback_work *work = NULL;
- spin_lock_bh(&wb->work_lock);
+ 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(&wb->work_lock);
+ spin_unlock_irq(&wb->work_lock);
return work;
}
trace_writeback_mark_inode_dirty(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->i_state & I_DIRTY_TIME) {
+ spin_lock(&inode->i_lock);
+ if (inode->i_state & I_DIRTY_TIME) {
+ inode->i_state &= ~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
*/
trace_writeback_dirty_inode_start(inode, flags);
if (sb->s_op->dirty_inode)
- sb->s_op->dirty_inode(inode, flags & I_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. */
*/
smp_mb();
- if (((inode->i_state & flags) == flags) ||
- (dirtytime && (inode->i_state & I_DIRTY_INODE)))
+ if ((inode->i_state & flags) == flags)
return;
spin_lock(&inode->i_lock);
- if (dirtytime && (inode->i_state & I_DIRTY_INODE))
- goto out_unlock_inode;
if ((inode->i_state & flags) != flags) {
const int was_dirty = inode->i_state & I_DIRTY;
inode_attach_wb(inode, NULL);
- /* I_DIRTY_INODE supersedes I_DIRTY_TIME. */
- if (flags & I_DIRTY_INODE)
- inode->i_state &= ~I_DIRTY_TIME;
inode->i_state |= flags;
/*
out_unlock:
if (wb)
spin_unlock(&wb->list_lock);
-out_unlock_inode:
spin_unlock(&inode->i_lock);
}
EXPORT_SYMBOL(__mark_inode_dirty);