This is a note to let you know that I've just added the patch titled
writeback, cgroup: keep list of inodes attached to bdi_writeback
to the 5.10-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary
The filename of the patch is:
writeback-cgroup-keep-list-of-inodes-attached-to-bdi.patch
and it can be found in the queue-5.10 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable@xxxxxxxxxxxxxxx> know about it.
commit 6ebfdd72f515b6ccb3f7f3900a4f12c715dd8290
Author: Roman Gushchin <roman.gushchin@xxxxxxxxx>
Date: Mon Jun 28 19:35:53 2021 -0700
writeback, cgroup: keep list of inodes attached to bdi_writeback
[ Upstream commit f3b6a6df38aa514d97e8c6fcc748be1d4142bec9 ]
Currently there is no way to iterate over inodes attached to a specific
cgwb structure. It limits the ability to efficiently reclaim the
writeback structure itself and associated memory and block cgroup
structures without scanning all inodes belonging to a sb, which can be
prohibitively expensive.
While dirty/in-active-writeback an inode belongs to one of the
bdi_writeback's io lists: b_dirty, b_io, b_more_io and b_dirty_time. Once
cleaned up, it's removed from all io lists. So the inode->i_io_list can
be reused to maintain the list of inodes, attached to a bdi_writeback
structure.
This patch introduces a new wb->b_attached list, which contains all inodes
which were dirty at least once and are attached to the given cgwb. Inodes
attached to the root bdi_writeback structures are never placed on such
list. The following patch will use this list to try to release cgwbs
structures more efficiently.
Link: https://lkml.kernel.org/r/20210608230225.2078447-6-guro@xxxxxx
Signed-off-by: Roman Gushchin <guro@xxxxxx>
Suggested-by: Jan Kara <jack@xxxxxxx>
Reviewed-by: Jan Kara <jack@xxxxxxx>
Acked-by: Tejun Heo <tj@xxxxxxxxxx>
Acked-by: Dennis Zhou <dennis@xxxxxxxxxx>
Cc: Alexander Viro <viro@xxxxxxxxxxxxxxxxxx>
Cc: Dave Chinner <dchinner@xxxxxxxxxx>
Cc: Jan Kara <jack@xxxxxxxx>
Cc: Jens Axboe <axboe@xxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Signed-off-by: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Stable-dep-of: cbfecb927f42 ("fs: record I_DIRTY_TIME even if inode already has I_DIRTY_INODE")
Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx>
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 71043e847e7c..489514bcd7e1 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -131,25 +131,6 @@ static bool inode_io_list_move_locked(struct inode *inode,
return false;
}
-/**
- * inode_io_list_del_locked - remove an inode from its bdi_writeback IO list
- * @inode: inode to be removed
- * @wb: bdi_writeback @inode is being removed from
- *
- * Remove @inode which may be on one of @wb->b_{dirty|io|more_io} lists and
- * clear %WB_has_dirty_io if all are empty afterwards.
- */
-static void inode_io_list_del_locked(struct inode *inode,
- struct bdi_writeback *wb)
-{
- assert_spin_locked(&wb->list_lock);
- assert_spin_locked(&inode->i_lock);
-
- inode->i_state &= ~I_SYNC_QUEUED;
- list_del_init(&inode->i_io_list);
- wb_io_lists_depopulated(wb);
-}
-
static void wb_wakeup(struct bdi_writeback *wb)
{
spin_lock_bh(&wb->work_lock);
@@ -278,6 +259,28 @@ void __inode_attach_wb(struct inode *inode, struct page *page)
}
EXPORT_SYMBOL_GPL(__inode_attach_wb);
+/**
+ * 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)
+{
+ assert_spin_locked(&wb->list_lock);
+ assert_spin_locked(&inode->i_lock);
+
+ inode->i_state &= ~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
@@ -419,21 +422,28 @@ static void inode_switch_wbs_work_fn(struct work_struct *work)
wb_get(new_wb);
/*
- * Transfer to @new_wb's IO list if necessary. 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.
+ * 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 (!list_empty(&inode->i_io_list)) {
- struct inode *pos;
-
- inode_io_list_del_locked(inode, old_wb);
inode->i_wb = new_wb;
- list_for_each_entry(pos, &new_wb->b_dirty, i_io_list)
- if (time_after_eq(inode->dirtied_when,
- pos->dirtied_when))
- break;
- inode_io_list_move_locked(inode, new_wb, pos->i_io_list.prev);
+
+ 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;
+ inode_io_list_move_locked(inode, new_wb,
+ pos->i_io_list.prev);
+ } else {
+ inode_cgwb_move_to_attached(inode, new_wb);
+ }
} else {
inode->i_wb = new_wb;
}
@@ -1030,6 +1040,17 @@ fs_initcall(cgroup_writeback_init);
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);
+
+ inode->i_state &= ~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)
@@ -1130,7 +1151,11 @@ void inode_io_list_del(struct inode *inode)
wb = inode_to_wb_and_lock_list(inode);
spin_lock(&inode->i_lock);
- inode_io_list_del_locked(inode, wb);
+
+ inode->i_state &= ~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);
}
@@ -1443,7 +1468,7 @@ static void requeue_inode(struct inode *inode, struct bdi_writeback *wb,
inode->i_state &= ~I_SYNC_QUEUED;
} else {
/* The inode is clean. Remove from writeback lists. */
- inode_io_list_del_locked(inode, wb);
+ inode_cgwb_move_to_attached(inode, wb);
}
}
@@ -1586,7 +1611,7 @@ static int writeback_single_inode(struct inode *inode,
* touch it. See comment above for explanation.
*/
if (!(inode->i_state & I_DIRTY_ALL))
- inode_io_list_del_locked(inode, wb);
+ inode_cgwb_move_to_attached(inode, wb);
spin_unlock(&wb->list_lock);
inode_sync_complete(inode);
out:
diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h
index fff9367a6348..e5dc238ebe4f 100644
--- a/include/linux/backing-dev-defs.h
+++ b/include/linux/backing-dev-defs.h
@@ -154,6 +154,7 @@ struct bdi_writeback {
struct cgroup_subsys_state *blkcg_css; /* and blkcg */
struct list_head memcg_node; /* anchored at memcg->cgwb_list */
struct list_head blkcg_node; /* anchored at blkcg->cgwb_list */
+ struct list_head b_attached; /* attached inodes, protected by list_lock */
union {
struct work_struct release_work;
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index ca770a783a9f..1c1b44fcaf7d 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -397,6 +397,7 @@ static void cgwb_release_workfn(struct work_struct *work)
fprop_local_destroy_percpu(&wb->memcg_completions);
percpu_ref_exit(&wb->refcnt);
wb_exit(wb);
+ WARN_ON_ONCE(!list_empty(&wb->b_attached));
kfree_rcu(wb, rcu);
}
@@ -473,6 +474,7 @@ static int cgwb_create(struct backing_dev_info *bdi,
wb->memcg_css = memcg_css;
wb->blkcg_css = blkcg_css;
+ INIT_LIST_HEAD(&wb->b_attached);
INIT_WORK(&wb->release_work, cgwb_release_workfn);
set_bit(WB_registered, &wb->state);
