Received-SPF: pass (google.com: domain of linux-nfs-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
From:   Qi Zheng <zhengqi.arch@bytedance.com>
To:     akpm@linux-foundation.org, david@fromorbit.com, tkhai@ya.ru,
        vbabka@suse.cz, roman.gushchin@linux.dev, djwong@kernel.org,
        brauner@kernel.org, paulmck@kernel.org, tytso@mit.edu
Cc:     linux-kernel@vger.kernel.org, linux-mm@kvack.org,
        intel-gfx@lists.freedesktop.org, dri-devel@lists.freedesktop.org,
        linux-arm-msm@vger.kernel.org, dm-devel@redhat.com,
        linux-raid@vger.kernel.org, linux-bcache@vger.kernel.org,
        virtualization@lists.linux-foundation.org,
        linux-fsdevel@vger.kernel.org, linux-ext4@vger.kernel.org,
        linux-nfs@vger.kernel.org, linux-xfs@vger.kernel.org,
        linux-btrfs@vger.kernel.org, Qi Zheng <zhengqi.arch@bytedance.com>
Subject: [PATCH 21/29] fs: super: dynamically allocate the s_shrink
Date:   Thu, 22 Jun 2023 16:53:27 +0800
Message-Id: <20230622085335.77010-22-zhengqi.arch@bytedance.com>
In-Reply-To: <20230622085335.77010-1-zhengqi.arch@bytedance.com>
References: <20230622085335.77010-1-zhengqi.arch@bytedance.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

In preparation for implementing lockless slab shrink,
we need to dynamically allocate the s_shrink, so that
it can be freed asynchronously using kfree_rcu(). Then
it doesn't need to wait for RCU read-side critical
section when releasing the struct super_block.

Signed-off-by: Qi Zheng <zhengqi.arch@bytedance.com>
---
 fs/btrfs/super.c   |  2 +-
 fs/kernfs/mount.c  |  2 +-
 fs/proc/root.c     |  2 +-
 fs/super.c         | 38 ++++++++++++++++++++++----------------
 include/linux/fs.h |  2 +-
 5 files changed, 26 insertions(+), 20 deletions(-)

diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index f1dd172d8d5b..fad4ded26c80 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -1513,7 +1513,7 @@ static struct dentry *btrfs_mount_root(struct file_system_type *fs_type,
 			error = -EBUSY;
 	} else {
 		snprintf(s->s_id, sizeof(s->s_id), "%pg", bdev);
-		shrinker_debugfs_rename(&s->s_shrink, "sb-%s:%s", fs_type->name,
+		shrinker_debugfs_rename(s->s_shrink, "sb-%s:%s", fs_type->name,
 					s->s_id);
 		btrfs_sb(s)->bdev_holder = fs_type;
 		error = btrfs_fill_super(s, fs_devices, data);
diff --git a/fs/kernfs/mount.c b/fs/kernfs/mount.c
index d49606accb07..2657ff1181f1 100644
--- a/fs/kernfs/mount.c
+++ b/fs/kernfs/mount.c
@@ -256,7 +256,7 @@ static int kernfs_fill_super(struct super_block *sb, struct kernfs_fs_context *k
 	sb->s_time_gran = 1;
 
 	/* sysfs dentries and inodes don't require IO to create */
-	sb->s_shrink.seeks = 0;
+	sb->s_shrink->seeks = 0;
 
 	/* get root inode, initialize and unlock it */
 	down_read(&kf_root->kernfs_rwsem);
diff --git a/fs/proc/root.c b/fs/proc/root.c
index a86e65a608da..22b78b28b477 100644
--- a/fs/proc/root.c
+++ b/fs/proc/root.c
@@ -188,7 +188,7 @@ static int proc_fill_super(struct super_block *s, struct fs_context *fc)
 	s->s_stack_depth = FILESYSTEM_MAX_STACK_DEPTH;
 
 	/* procfs dentries and inodes don't require IO to create */
-	s->s_shrink.seeks = 0;
+	s->s_shrink->seeks = 0;
 
 	pde_get(&proc_root);
 	root_inode = proc_get_inode(s, &proc_root);
diff --git a/fs/super.c b/fs/super.c
index 2e83c8cd435b..791342bb8ac9 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -67,7 +67,7 @@ static unsigned long super_cache_scan(struct shrinker *shrink,
 	long	dentries;
 	long	inodes;
 
-	sb = container_of(shrink, struct super_block, s_shrink);
+	sb = shrink->private_data;
 
 	/*
 	 * Deadlock avoidance.  We may hold various FS locks, and we don't want
@@ -120,7 +120,7 @@ static unsigned long super_cache_count(struct shrinker *shrink,
 	struct super_block *sb;
 	long	total_objects = 0;
 
-	sb = container_of(shrink, struct super_block, s_shrink);
+	sb = shrink->private_data;
 
 	/*
 	 * We don't call trylock_super() here as it is a scalability bottleneck,
@@ -182,7 +182,10 @@ static void destroy_unused_super(struct super_block *s)
 	security_sb_free(s);
 	put_user_ns(s->s_user_ns);
 	kfree(s->s_subtype);
-	free_prealloced_shrinker(&s->s_shrink);
+	if (s->s_shrink) {
+		free_prealloced_shrinker(s->s_shrink);
+		shrinker_free(s->s_shrink);
+	}
 	/* no delays needed */
 	destroy_super_work(&s->destroy_work);
 }
@@ -259,16 +262,19 @@ static struct super_block *alloc_super(struct file_system_type *type, int flags,
 	s->s_time_min = TIME64_MIN;
 	s->s_time_max = TIME64_MAX;
 
-	s->s_shrink.seeks = DEFAULT_SEEKS;
-	s->s_shrink.scan_objects = super_cache_scan;
-	s->s_shrink.count_objects = super_cache_count;
-	s->s_shrink.batch = 1024;
-	s->s_shrink.flags = SHRINKER_NUMA_AWARE | SHRINKER_MEMCG_AWARE;
-	if (prealloc_shrinker(&s->s_shrink, "sb-%s", type->name))
+	s->s_shrink = shrinker_alloc_and_init(super_cache_count,
+					      super_cache_scan, 1024,
+					      DEFAULT_SEEKS,
+					      SHRINKER_NUMA_AWARE | SHRINKER_MEMCG_AWARE,
+					      s);
+	if (!s->s_shrink)
+		goto fail;
+
+	if (prealloc_shrinker(s->s_shrink, "sb-%s", type->name))
 		goto fail;
-	if (list_lru_init_memcg(&s->s_dentry_lru, &s->s_shrink))
+	if (list_lru_init_memcg(&s->s_dentry_lru, s->s_shrink))
 		goto fail;
-	if (list_lru_init_memcg(&s->s_inode_lru, &s->s_shrink))
+	if (list_lru_init_memcg(&s->s_inode_lru, s->s_shrink))
 		goto fail;
 	return s;
 
@@ -326,7 +332,7 @@ void deactivate_locked_super(struct super_block *s)
 {
 	struct file_system_type *fs = s->s_type;
 	if (atomic_dec_and_test(&s->s_active)) {
-		unregister_shrinker(&s->s_shrink);
+		unregister_and_free_shrinker(s->s_shrink);
 		fs->kill_sb(s);
 
 		/*
@@ -599,7 +605,7 @@ struct super_block *sget_fc(struct fs_context *fc,
 	hlist_add_head(&s->s_instances, &s->s_type->fs_supers);
 	spin_unlock(&sb_lock);
 	get_filesystem(s->s_type);
-	register_shrinker_prepared(&s->s_shrink);
+	register_shrinker_prepared(s->s_shrink);
 	return s;
 
 share_extant_sb:
@@ -678,7 +684,7 @@ struct super_block *sget(struct file_system_type *type,
 	hlist_add_head(&s->s_instances, &type->fs_supers);
 	spin_unlock(&sb_lock);
 	get_filesystem(type);
-	register_shrinker_prepared(&s->s_shrink);
+	register_shrinker_prepared(s->s_shrink);
 	return s;
 }
 EXPORT_SYMBOL(sget);
@@ -1308,7 +1314,7 @@ int get_tree_bdev(struct fs_context *fc,
 		down_write(&s->s_umount);
 	} else {
 		snprintf(s->s_id, sizeof(s->s_id), "%pg", bdev);
-		shrinker_debugfs_rename(&s->s_shrink, "sb-%s:%s",
+		shrinker_debugfs_rename(s->s_shrink, "sb-%s:%s",
 					fc->fs_type->name, s->s_id);
 		sb_set_blocksize(s, block_size(bdev));
 		error = fill_super(s, fc);
@@ -1381,7 +1387,7 @@ struct dentry *mount_bdev(struct file_system_type *fs_type,
 		down_write(&s->s_umount);
 	} else {
 		snprintf(s->s_id, sizeof(s->s_id), "%pg", bdev);
-		shrinker_debugfs_rename(&s->s_shrink, "sb-%s:%s",
+		shrinker_debugfs_rename(s->s_shrink, "sb-%s:%s",
 					fs_type->name, s->s_id);
 		sb_set_blocksize(s, block_size(bdev));
 		error = fill_super(s, data, flags & SB_SILENT ? 1 : 0);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 53e0b5e98046..dd6f8ce28385 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1228,7 +1228,7 @@ struct super_block {
 
 	const struct dentry_operations *s_d_op; /* default d_op for dentries */
 
-	struct shrinker s_shrink;	/* per-sb shrinker handle */
+	struct shrinker *s_shrink;	/* per-sb shrinker handle */
 
 	/* Number of inodes with nlink == 0 but still referenced */
 	atomic_long_t s_remove_count;
-- 
2.30.2