diff mbox series

[3/8] fs: move list_lru_destroy() to destroy_super_work()

Message ID 20230531095742.2480623-4-qi.zheng@linux.dev (mailing list archive)
State Under Review
Headers show
Series make unregistration of super_block shrinker more faster | expand

Commit Message

Qi Zheng May 31, 2023, 9:57 a.m. UTC
From: Kirill Tkhai <tkhai@ya.ru>

The patch makes s_dentry_lru and s_inode_lru be destroyed
later from the workqueue. This is preparation to split
unregister_shrinker(super_block::s_shrink) in two stages,
and to call finalize stage from destroy_super_work().

Note, that generic filesystem shrinker unregistration
is safe to be split in two stages right after this
patch, since super_cache_count() and super_cache_scan()
have a deal with s_dentry_lru and s_inode_lru only.

But there are two exceptions: XFS and SHMEM, which
define .nr_cached_objects() and .free_cached_objects()
callbacks. These two do not allow us to do the splitting
right after this patch. They touch fs-specific data,
which is destroyed earlier, than destroy_super_work().
So, we can't call unregister_shrinker_delayed_finalize()
from destroy_super_work() because of them, and next
patches make preparations to make this possible.

Signed-off-by: Kirill Tkhai <tkhai@ya.ru>
Signed-off-by: Qi Zheng <zhengqi.arch@bytedance.com>
---
 fs/super.c | 17 +++++------------
 1 file changed, 5 insertions(+), 12 deletions(-)

Comments

Dave Chinner May 31, 2023, 11 p.m. UTC | #1
On Wed, May 31, 2023 at 09:57:37AM +0000, Qi Zheng wrote:
> From: Kirill Tkhai <tkhai@ya.ru>
> 
> The patch makes s_dentry_lru and s_inode_lru be destroyed
> later from the workqueue. This is preparation to split
> unregister_shrinker(super_block::s_shrink) in two stages,
> and to call finalize stage from destroy_super_work().
> 
> Note, that generic filesystem shrinker unregistration
> is safe to be split in two stages right after this
> patch, since super_cache_count() and super_cache_scan()
> have a deal with s_dentry_lru and s_inode_lru only.
> 
> But there are two exceptions: XFS and SHMEM, which
> define .nr_cached_objects() and .free_cached_objects()
> callbacks. These two do not allow us to do the splitting
> right after this patch. They touch fs-specific data,
> which is destroyed earlier, than destroy_super_work().
> So, we can't call unregister_shrinker_delayed_finalize()
> from destroy_super_work() because of them, and next
> patches make preparations to make this possible.
> 
> Signed-off-by: Kirill Tkhai <tkhai@ya.ru>
> Signed-off-by: Qi Zheng <zhengqi.arch@bytedance.com>
> ---
>  fs/super.c | 17 +++++------------
>  1 file changed, 5 insertions(+), 12 deletions(-)
> 
> diff --git a/fs/super.c b/fs/super.c
> index 8d8d68799b34..2ce4c72720f3 100644
> --- a/fs/super.c
> +++ b/fs/super.c
> @@ -159,6 +159,11 @@ static void destroy_super_work(struct work_struct *work)
>  							destroy_work);
>  	int i;
>  
> +	WARN_ON(list_lru_count(&s->s_dentry_lru));
> +	WARN_ON(list_lru_count(&s->s_inode_lru));
> +	list_lru_destroy(&s->s_dentry_lru);
> +	list_lru_destroy(&s->s_inode_lru);
> +
>  	for (i = 0; i < SB_FREEZE_LEVELS; i++)
>  		percpu_free_rwsem(&s->s_writers.rw_sem[i]);
>  	kfree(s);
> @@ -177,8 +182,6 @@ static void destroy_unused_super(struct super_block *s)
>  	if (!s)
>  		return;
>  	up_write(&s->s_umount);
> -	list_lru_destroy(&s->s_dentry_lru);
> -	list_lru_destroy(&s->s_inode_lru);
>  	security_sb_free(s);
>  	put_user_ns(s->s_user_ns);
>  	kfree(s->s_subtype);
> @@ -287,8 +290,6 @@ static void __put_super(struct super_block *s)
>  {
>  	if (!--s->s_count) {
>  		list_del_init(&s->s_list);
> -		WARN_ON(s->s_dentry_lru.node);
> -		WARN_ON(s->s_inode_lru.node);

Why are you removing the wanrings from here? Regardless of where
we tear down the lru lists, they *must* be empty here otherwise we
have a memory leak. Hence I don't think these warnings should be
moved at all.

Cheers,

Dave.
diff mbox series

Patch

diff --git a/fs/super.c b/fs/super.c
index 8d8d68799b34..2ce4c72720f3 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -159,6 +159,11 @@  static void destroy_super_work(struct work_struct *work)
 							destroy_work);
 	int i;
 
+	WARN_ON(list_lru_count(&s->s_dentry_lru));
+	WARN_ON(list_lru_count(&s->s_inode_lru));
+	list_lru_destroy(&s->s_dentry_lru);
+	list_lru_destroy(&s->s_inode_lru);
+
 	for (i = 0; i < SB_FREEZE_LEVELS; i++)
 		percpu_free_rwsem(&s->s_writers.rw_sem[i]);
 	kfree(s);
@@ -177,8 +182,6 @@  static void destroy_unused_super(struct super_block *s)
 	if (!s)
 		return;
 	up_write(&s->s_umount);
-	list_lru_destroy(&s->s_dentry_lru);
-	list_lru_destroy(&s->s_inode_lru);
 	security_sb_free(s);
 	put_user_ns(s->s_user_ns);
 	kfree(s->s_subtype);
@@ -287,8 +290,6 @@  static void __put_super(struct super_block *s)
 {
 	if (!--s->s_count) {
 		list_del_init(&s->s_list);
-		WARN_ON(s->s_dentry_lru.node);
-		WARN_ON(s->s_inode_lru.node);
 		WARN_ON(!list_empty(&s->s_mounts));
 		security_sb_free(s);
 		put_user_ns(s->s_user_ns);
@@ -330,14 +331,6 @@  void deactivate_locked_super(struct super_block *s)
 		unregister_shrinker(&s->s_shrink);
 		fs->kill_sb(s);
 
-		/*
-		 * Since list_lru_destroy() may sleep, we cannot call it from
-		 * put_super(), where we hold the sb_lock. Therefore we destroy
-		 * the lru lists right now.
-		 */
-		list_lru_destroy(&s->s_dentry_lru);
-		list_lru_destroy(&s->s_inode_lru);
-
 		put_filesystem(fs);
 		put_super(s);
 	} else {