From 1720f5dd8d3af34d6023fb9e8c35e5e60e8b6643 Mon Sep 17 00:00:00 2001 From: Qi Zheng Date: Mon, 11 Sep 2023 17:44:37 +0800 Subject: fs: super: dynamically allocate the s_shrink In preparation for implementing lockless slab shrink, use new APIs to dynamically allocate the s_shrink, so that it can be freed asynchronously via RCU. Then it doesn't need to wait for RCU read-side critical section when releasing the struct super_block. Link: https://lkml.kernel.org/r/20230911094444.68966-39-zhengqi.arch@bytedance.com Signed-off-by: Qi Zheng Reviewed-by: Muchun Song Acked-by: David Sterba Cc: Chris Mason Cc: Josef Bacik Cc: Alexander Viro Cc: Christian Brauner Cc: Abhinav Kumar Cc: Alasdair Kergon Cc: Alyssa Rosenzweig Cc: Andreas Dilger Cc: Andreas Gruenbacher Cc: Anna Schumaker Cc: Arnd Bergmann Cc: Bob Peterson Cc: Borislav Petkov Cc: Carlos Llamas Cc: Chandan Babu R Cc: Chao Yu Cc: Christian Koenig Cc: Chuck Lever Cc: Coly Li Cc: Dai Ngo Cc: Daniel Vetter Cc: Daniel Vetter Cc: "Darrick J. Wong" Cc: Dave Chinner Cc: Dave Hansen Cc: David Airlie Cc: David Hildenbrand Cc: Dmitry Baryshkov Cc: Gao Xiang Cc: Greg Kroah-Hartman Cc: Huang Rui Cc: Ingo Molnar Cc: Jaegeuk Kim Cc: Jani Nikula Cc: Jan Kara Cc: Jason Wang Cc: Jeff Layton Cc: Jeffle Xu Cc: Joel Fernandes (Google) Cc: Joonas Lahtinen Cc: Juergen Gross Cc: Kent Overstreet Cc: Kirill Tkhai Cc: Marijn Suijten Cc: "Michael S. Tsirkin" Cc: Mike Snitzer Cc: Minchan Kim Cc: Muchun Song Cc: Nadav Amit Cc: Neil Brown Cc: Oleksandr Tyshchenko Cc: Olga Kornievskaia Cc: Paul E. McKenney Cc: Richard Weinberger Cc: Rob Clark Cc: Rob Herring Cc: Rodrigo Vivi Cc: Roman Gushchin Cc: Sean Paul Cc: Sergey Senozhatsky Cc: Song Liu Cc: Stefano Stabellini Cc: Steven Price Cc: "Theodore Ts'o" Cc: Thomas Gleixner Cc: Tomeu Vizoso Cc: Tom Talpey Cc: Trond Myklebust Cc: Tvrtko Ursulin Cc: Vlastimil Babka Cc: Xuan Zhuo Cc: Yue Hu Signed-off-by: Andrew Morton --- fs/super.c | 33 ++++++++++++++++++--------------- 1 file changed, 18 insertions(+), 15 deletions(-) (limited to 'fs/super.c') diff --git a/fs/super.c b/fs/super.c index 2d762ce67f6e6c..adadf6689611e9 100644 --- a/fs/super.c +++ b/fs/super.c @@ -191,7 +191,7 @@ 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 @@ -244,7 +244,7 @@ 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 super_trylock_shared() here as it is a scalability @@ -306,7 +306,7 @@ 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); + shrinker_free(s->s_shrink); /* no delays needed */ destroy_super_work(&s->destroy_work); } @@ -383,16 +383,19 @@ 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(SHRINKER_NUMA_AWARE | SHRINKER_MEMCG_AWARE, + "sb-%s", type->name); + if (!s->s_shrink) goto fail; - if (list_lru_init_memcg(&s->s_dentry_lru, &s->s_shrink)) + + s->s_shrink->scan_objects = super_cache_scan; + s->s_shrink->count_objects = super_cache_count; + s->s_shrink->batch = 1024; + s->s_shrink->private_data = s; + + 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; @@ -477,7 +480,7 @@ 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); + shrinker_free(s->s_shrink); fs->kill_sb(s); kill_super_notify(s); @@ -818,7 +821,7 @@ 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); + shrinker_register(s->s_shrink); return s; share_extant_sb: @@ -901,7 +904,7 @@ 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); + shrinker_register(s->s_shrink); return s; } EXPORT_SYMBOL(sget); @@ -1522,7 +1525,7 @@ int setup_bdev_super(struct super_block *sb, int sb_flags, mutex_unlock(&bdev->bd_fsfreeze_mutex); snprintf(sb->s_id, sizeof(sb->s_id), "%pg", bdev); - shrinker_debugfs_rename(&sb->s_shrink, "sb-%s:%s", sb->s_type->name, + shrinker_debugfs_rename(sb->s_shrink, "sb-%s:%s", sb->s_type->name, sb->s_id); sb_set_blocksize(sb, block_size(bdev)); return 0; -- cgit 1.2.3-korg From 8a0e8bb112af28362514624fc46e20426b4bdf1f Mon Sep 17 00:00:00 2001 From: Qi Zheng Date: Mon, 11 Sep 2023 17:44:44 +0800 Subject: mm: shrinker: convert shrinker_rwsem to mutex Now there are no readers of shrinker_rwsem, so we can simply replace it with mutex lock. [akpm@linux-foundation.org: update the fix to alloc_shrinker_info()] Link: https://lkml.kernel.org/r/20230911094444.68966-46-zhengqi.arch@bytedance.com Signed-off-by: Qi Zheng Reviewed-by: Muchun Song Cc: Abhinav Kumar Cc: Alasdair Kergon Cc: Alexander Viro Cc: Alyssa Rosenzweig Cc: Andreas Dilger Cc: Andreas Gruenbacher Cc: Anna Schumaker Cc: Arnd Bergmann Cc: Bob Peterson Cc: Borislav Petkov Cc: Carlos Llamas Cc: Chandan Babu R Cc: Chao Yu Cc: Chris Mason Cc: Christian Brauner Cc: Christian Koenig Cc: Chuck Lever Cc: Coly Li Cc: Dai Ngo Cc: Daniel Vetter Cc: Daniel Vetter Cc: "Darrick J. Wong" Cc: Dave Chinner Cc: Dave Hansen Cc: David Airlie Cc: David Hildenbrand Cc: David Sterba Cc: Dmitry Baryshkov Cc: Gao Xiang Cc: Greg Kroah-Hartman Cc: Huang Rui Cc: Ingo Molnar Cc: Jaegeuk Kim Cc: Jani Nikula Cc: Jan Kara Cc: Jason Wang Cc: Jeff Layton Cc: Jeffle Xu Cc: Joel Fernandes (Google) Cc: Joonas Lahtinen Cc: Josef Bacik Cc: Juergen Gross Cc: Kent Overstreet Cc: Kirill Tkhai Cc: Marijn Suijten Cc: "Michael S. Tsirkin" Cc: Mike Snitzer Cc: Minchan Kim Cc: Nadav Amit Cc: Neil Brown Cc: Oleksandr Tyshchenko Cc: Olga Kornievskaia Cc: Paul E. McKenney Cc: Richard Weinberger Cc: Rob Clark Cc: Rob Herring Cc: Rodrigo Vivi Cc: Roman Gushchin Cc: Sean Paul Cc: Sergey Senozhatsky Cc: Song Liu Cc: Stefano Stabellini Cc: Steven Price Cc: "Theodore Ts'o" Cc: Thomas Gleixner Cc: Tomeu Vizoso Cc: Tom Talpey Cc: Trond Myklebust Cc: Tvrtko Ursulin Cc: Vlastimil Babka Cc: Xuan Zhuo Cc: Yue Hu Signed-off-by: Andrew Morton --- drivers/md/dm-cache-metadata.c | 2 +- fs/super.c | 2 +- mm/shrinker.c | 30 +++++++++++++++--------------- mm/shrinker_debug.c | 14 +++++++------- 4 files changed, 24 insertions(+), 24 deletions(-) (limited to 'fs/super.c') diff --git a/drivers/md/dm-cache-metadata.c b/drivers/md/dm-cache-metadata.c index acffed750e3edc..9e0c6995858720 100644 --- a/drivers/md/dm-cache-metadata.c +++ b/drivers/md/dm-cache-metadata.c @@ -1828,7 +1828,7 @@ int dm_cache_metadata_abort(struct dm_cache_metadata *cmd) * Replacement block manager (new_bm) is created and old_bm destroyed outside of * cmd root_lock to avoid ABBA deadlock that would result (due to life-cycle of * shrinker associated with the block manager's bufio client vs cmd root_lock). - * - must take shrinker_rwsem without holding cmd->root_lock + * - must take shrinker_mutex without holding cmd->root_lock */ new_bm = dm_block_manager_create(cmd->bdev, DM_CACHE_METADATA_BLOCK_SIZE << SECTOR_SHIFT, CACHE_MAX_CONCURRENT_LOCKS); diff --git a/fs/super.c b/fs/super.c index adadf6689611e9..816a22a5cad1be 100644 --- a/fs/super.c +++ b/fs/super.c @@ -178,7 +178,7 @@ static void super_wake(struct super_block *sb, unsigned int flag) * One thing we have to be careful of with a per-sb shrinker is that we don't * drop the last active reference to the superblock from within the shrinker. * If that happens we could trigger unregistering the shrinker from within the - * shrinker path and that leads to deadlock on the shrinker_rwsem. Hence we + * shrinker path and that leads to deadlock on the shrinker_mutex. Hence we * take a passive reference to the superblock to avoid this from occurring. */ static unsigned long super_cache_scan(struct shrinker *shrink, diff --git a/mm/shrinker.c b/mm/shrinker.c index ef22f20a97cbd9..dd91eab43ed301 100644 --- a/mm/shrinker.c +++ b/mm/shrinker.c @@ -8,7 +8,7 @@ #include "internal.h" LIST_HEAD(shrinker_list); -DECLARE_RWSEM(shrinker_rwsem); +DEFINE_MUTEX(shrinker_mutex); #ifdef CONFIG_MEMCG static int shrinker_nr_max; @@ -80,7 +80,7 @@ int alloc_shrinker_info(struct mem_cgroup *memcg) int nid, ret = 0; int array_size = 0; - down_write(&shrinker_rwsem); + mutex_lock(&shrinker_mutex); array_size = shrinker_unit_size(shrinker_nr_max); for_each_node(nid) { info = kvzalloc_node(sizeof(*info) + array_size, GFP_KERNEL, nid); @@ -91,12 +91,12 @@ int alloc_shrinker_info(struct mem_cgroup *memcg) goto err; rcu_assign_pointer(memcg->nodeinfo[nid]->shrinker_info, info); } - up_write(&shrinker_rwsem); + mutex_unlock(&shrinker_mutex); return ret; err: - up_write(&shrinker_rwsem); + mutex_unlock(&shrinker_mutex); free_shrinker_info(memcg); return -ENOMEM; } @@ -105,7 +105,7 @@ static struct shrinker_info *shrinker_info_protected(struct mem_cgroup *memcg, int nid) { return rcu_dereference_protected(memcg->nodeinfo[nid]->shrinker_info, - lockdep_is_held(&shrinker_rwsem)); + lockdep_is_held(&shrinker_mutex)); } static int expand_one_shrinker_info(struct mem_cgroup *memcg, int new_size, @@ -155,7 +155,7 @@ static int expand_shrinker_info(int new_id) if (!root_mem_cgroup) goto out; - lockdep_assert_held(&shrinker_rwsem); + lockdep_assert_held(&shrinker_mutex); new_size = shrinker_unit_size(new_nr_max); old_size = shrinker_unit_size(shrinker_nr_max); @@ -218,7 +218,7 @@ static int shrinker_memcg_alloc(struct shrinker *shrinker) if (mem_cgroup_disabled()) return -ENOSYS; - down_write(&shrinker_rwsem); + mutex_lock(&shrinker_mutex); id = idr_alloc(&shrinker_idr, shrinker, 0, 0, GFP_KERNEL); if (id < 0) goto unlock; @@ -232,7 +232,7 @@ static int shrinker_memcg_alloc(struct shrinker *shrinker) shrinker->id = id; ret = 0; unlock: - up_write(&shrinker_rwsem); + mutex_unlock(&shrinker_mutex); return ret; } @@ -242,7 +242,7 @@ static void shrinker_memcg_remove(struct shrinker *shrinker) BUG_ON(id < 0); - lockdep_assert_held(&shrinker_rwsem); + lockdep_assert_held(&shrinker_mutex); idr_remove(&shrinker_idr, id); } @@ -293,7 +293,7 @@ void reparent_shrinker_deferred(struct mem_cgroup *memcg) parent = root_mem_cgroup; /* Prevent from concurrent shrinker_info expand */ - down_write(&shrinker_rwsem); + mutex_lock(&shrinker_mutex); for_each_node(nid) { child_info = shrinker_info_protected(memcg, nid); parent_info = shrinker_info_protected(parent, nid); @@ -306,7 +306,7 @@ void reparent_shrinker_deferred(struct mem_cgroup *memcg) } } } - up_write(&shrinker_rwsem); + mutex_unlock(&shrinker_mutex); } #else static int shrinker_memcg_alloc(struct shrinker *shrinker) @@ -740,11 +740,11 @@ void shrinker_register(struct shrinker *shrinker) return; } - down_write(&shrinker_rwsem); + mutex_lock(&shrinker_mutex); list_add_tail_rcu(&shrinker->list, &shrinker_list); shrinker->flags |= SHRINKER_REGISTERED; shrinker_debugfs_add(shrinker); - up_write(&shrinker_rwsem); + mutex_unlock(&shrinker_mutex); init_completion(&shrinker->done); /* @@ -784,7 +784,7 @@ void shrinker_free(struct shrinker *shrinker) wait_for_completion(&shrinker->done); } - down_write(&shrinker_rwsem); + mutex_lock(&shrinker_mutex); if (shrinker->flags & SHRINKER_REGISTERED) { /* * Now we can safely remove it from the shrinker_list and then @@ -799,7 +799,7 @@ void shrinker_free(struct shrinker *shrinker) if (shrinker->flags & SHRINKER_MEMCG_AWARE) shrinker_memcg_remove(shrinker); - up_write(&shrinker_rwsem); + mutex_unlock(&shrinker_mutex); if (debugfs_entry) shrinker_debugfs_remove(debugfs_entry, debugfs_id); diff --git a/mm/shrinker_debug.c b/mm/shrinker_debug.c index 24aebe7c24cc51..12ea5486a3e959 100644 --- a/mm/shrinker_debug.c +++ b/mm/shrinker_debug.c @@ -9,7 +9,7 @@ #include "internal.h" /* defined in vmscan.c */ -extern struct rw_semaphore shrinker_rwsem; +extern struct mutex shrinker_mutex; extern struct list_head shrinker_list; static DEFINE_IDA(shrinker_debugfs_ida); @@ -165,7 +165,7 @@ int shrinker_debugfs_add(struct shrinker *shrinker) char buf[128]; int id; - lockdep_assert_held(&shrinker_rwsem); + lockdep_assert_held(&shrinker_mutex); /* debugfs isn't initialized yet, add debugfs entries later. */ if (!shrinker_debugfs_root) @@ -208,7 +208,7 @@ int shrinker_debugfs_rename(struct shrinker *shrinker, const char *fmt, ...) if (!new) return -ENOMEM; - down_write(&shrinker_rwsem); + mutex_lock(&shrinker_mutex); old = shrinker->name; shrinker->name = new; @@ -226,7 +226,7 @@ int shrinker_debugfs_rename(struct shrinker *shrinker, const char *fmt, ...) shrinker->debugfs_entry = entry; } - up_write(&shrinker_rwsem); + mutex_unlock(&shrinker_mutex); kfree_const(old); @@ -239,7 +239,7 @@ struct dentry *shrinker_debugfs_detach(struct shrinker *shrinker, { struct dentry *entry = shrinker->debugfs_entry; - lockdep_assert_held(&shrinker_rwsem); + lockdep_assert_held(&shrinker_mutex); *debugfs_id = entry ? shrinker->debugfs_id : -1; shrinker->debugfs_entry = NULL; @@ -265,14 +265,14 @@ static int __init shrinker_debugfs_init(void) shrinker_debugfs_root = dentry; /* Create debugfs entries for shrinkers registered at boot */ - down_write(&shrinker_rwsem); + mutex_lock(&shrinker_mutex); list_for_each_entry(shrinker, &shrinker_list, list) if (!shrinker->debugfs_entry) { ret = shrinker_debugfs_add(shrinker); if (ret) break; } - up_write(&shrinker_rwsem); + mutex_unlock(&shrinker_mutex); return ret; } -- cgit 1.2.3-korg