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 [thread overview]
Message-ID: <20230622085335.77010-22-zhengqi.arch@bytedance.com> (raw)
In-Reply-To: <20230622085335.77010-1-zhengqi.arch@bytedance.com>
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
next prev parent reply other threads:[~2023-06-22 8:56 UTC|newest]
Thread overview: 56+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-06-22 8:53 [PATCH 00/29] use refcount+RCU method to implement lockless slab shrink Qi Zheng
2023-06-22 8:53 ` [PATCH 01/29] mm: shrinker: add shrinker::private_data field Qi Zheng
2023-06-22 14:47 ` Vlastimil Babka
2023-06-23 12:50 ` [External] " Qi Zheng
2023-06-22 8:53 ` [PATCH 02/29] mm: vmscan: introduce some helpers for dynamically allocating shrinker Qi Zheng
2023-06-23 6:12 ` Dave Chinner
2023-06-23 12:49 ` Qi Zheng
2023-06-22 8:53 ` [PATCH 03/29] drm/i915: dynamically allocate the i915_gem_mm shrinker Qi Zheng
2023-06-22 8:53 ` [PATCH 04/29] drm/msm: dynamically allocate the drm-msm_gem shrinker Qi Zheng
2023-06-22 8:53 ` [PATCH 05/29] drm/panfrost: dynamically allocate the drm-panfrost shrinker Qi Zheng
2023-06-23 13:33 ` Qi Zheng
2023-06-23 14:18 ` Bobs_Email
2023-06-22 8:53 ` [PATCH 06/29] dm: dynamically allocate the dm-bufio shrinker Qi Zheng
2023-06-22 8:53 ` [PATCH 07/29] dm zoned: dynamically allocate the dm-zoned-meta shrinker Qi Zheng
2023-06-22 8:53 ` [PATCH 08/29] md/raid5: dynamically allocate the md-raid5 shrinker Qi Zheng
2023-06-22 8:53 ` [PATCH 09/29] bcache: dynamically allocate the md-bcache shrinker Qi Zheng
2023-06-22 8:53 ` [PATCH 10/29] vmw_balloon: dynamically allocate the vmw-balloon shrinker Qi Zheng
2023-06-22 8:53 ` [PATCH 11/29] virtio_balloon: dynamically allocate the virtio-balloon shrinker Qi Zheng
2023-06-22 8:53 ` [PATCH 12/29] mbcache: dynamically allocate the mbcache shrinker Qi Zheng
2023-06-22 8:53 ` [PATCH 13/29] ext4: dynamically allocate the ext4-es shrinker Qi Zheng
2023-06-22 8:53 ` [PATCH 14/29] jbd2,ext4: dynamically allocate the jbd2-journal shrinker Qi Zheng
2023-06-22 8:53 ` [PATCH 15/29] NFSD: dynamically allocate the nfsd-client shrinker Qi Zheng
2023-06-23 21:49 ` Chuck Lever
2023-06-24 11:17 ` Qi Zheng
2023-06-22 8:53 ` [PATCH 16/29] NFSD: dynamically allocate the nfsd-reply shrinker Qi Zheng
2023-06-22 8:53 ` [PATCH 17/29] xfs: dynamically allocate the xfs-buf shrinker Qi Zheng
2023-06-22 8:53 ` [PATCH 18/29] xfs: dynamically allocate the xfs-inodegc shrinker Qi Zheng
2023-06-22 8:53 ` [PATCH 19/29] xfs: dynamically allocate the xfs-qm shrinker Qi Zheng
2023-06-22 8:53 ` [PATCH 20/29] zsmalloc: dynamically allocate the mm-zspool shrinker Qi Zheng
2023-06-22 8:53 ` Qi Zheng [this message]
2023-06-22 8:53 ` [PATCH 22/29] drm/ttm: introduce pool_shrink_rwsem Qi Zheng
2023-06-22 8:53 ` [PATCH 23/29] mm: shrinker: add refcount and completion_wait fields Qi Zheng
2023-06-22 8:53 ` [PATCH 24/29] mm: vmscan: make global slab shrink lockless Qi Zheng
2023-06-22 15:12 ` Vlastimil Babka
2023-06-22 16:42 ` Qi Zheng
2023-06-22 17:41 ` Alan Huang
2023-06-22 18:18 ` Qi Zheng
2023-06-23 6:29 ` Dave Chinner
2023-06-23 13:10 ` Qi Zheng
2023-06-23 22:19 ` Dave Chinner
2023-06-24 11:08 ` Qi Zheng
2023-06-25 3:15 ` Qi Zheng
2023-07-04 4:20 ` Qi Zheng
2023-07-03 16:39 ` Paul E. McKenney
2023-07-04 3:45 ` Qi Zheng
2023-07-05 3:27 ` Qi Zheng
2023-06-22 8:53 ` [PATCH 25/29] mm: vmscan: make memcg " Qi Zheng
2023-06-22 8:53 ` [PATCH 26/29] mm: shrinker: make count and scan in shrinker debugfs lockless Qi Zheng
2023-06-22 8:53 ` [PATCH 27/29] mm: vmscan: hold write lock to reparent shrinker nr_deferred Qi Zheng
2023-06-22 8:53 ` [PATCH 28/29] mm: shrinkers: convert shrinker_rwsem to mutex Qi Zheng
2023-06-22 8:53 ` [PATCH 29/29] mm: shrinker: move shrinker-related code into a separate file Qi Zheng
2023-06-22 14:53 ` Vlastimil Babka
2023-06-23 13:12 ` Qi Zheng
2023-06-23 5:25 ` Sergey Senozhatsky
2023-06-23 13:24 ` Qi Zheng
2023-06-22 9:02 ` [PATCH 00/29] use refcount+RCU method to implement lockless slab shrink Qi Zheng
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20230622085335.77010-22-zhengqi.arch@bytedance.com \
--to=zhengqi.arch@bytedance.com \
--cc=akpm@linux-foundation.org \
--cc=brauner@kernel.org \
--cc=david@fromorbit.com \
--cc=djwong@kernel.org \
--cc=dm-devel@redhat.com \
--cc=dri-devel@lists.freedesktop.org \
--cc=intel-gfx@lists.freedesktop.org \
--cc=linux-arm-msm@vger.kernel.org \
--cc=linux-bcache@vger.kernel.org \
--cc=linux-btrfs@vger.kernel.org \
--cc=linux-ext4@vger.kernel.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=linux-nfs@vger.kernel.org \
--cc=linux-raid@vger.kernel.org \
--cc=linux-xfs@vger.kernel.org \
--cc=paulmck@kernel.org \
--cc=roman.gushchin@linux.dev \
--cc=tkhai@ya.ru \
--cc=tytso@mit.edu \
--cc=vbabka@suse.cz \
--cc=virtualization@lists.linux-foundation.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox