diff --git a/fs/9p/v9fs.h b/fs/9p/v9fs.h
index a462bcbfc7da..2ac863dc8446 100644
--- a/fs/9p/v9fs.h
+++ b/fs/9p/v9fs.h
@@ -137,6 +137,7 @@ struct v9fs_session_info {
 	struct list_head slist; /* list of sessions registered with v9fs */
 	struct rw_semaphore rename_sem;
 	long session_lock_timeout; /* retry interval for blocking locks */
+	struct rcu_head rcu;	/* v9fs_vfs_get_link_dotl() reads ->cache in rcu pathwalk */
 };
 
 #define NDENTRY_TIMEOUT_NEVER (-1U)
diff --git a/fs/9p/vfs_super.c b/fs/9p/vfs_super.c
index 94d6b02c221b..79526044685c 100644
--- a/fs/9p/vfs_super.c
+++ b/fs/9p/vfs_super.c
@@ -173,8 +173,8 @@ static void v9fs_kill_super(struct super_block *s)
 
 	v9fs_session_cancel(v9ses);
 	v9fs_session_close(v9ses);
-	kfree(v9ses);
-	s->s_fs_info = NULL;
+	/* v9fs_vfs_get_link_dotl() may still read ->cache in rcu pathwalk */
+	kfree_rcu(v9ses, rcu);
 	p9_debug(P9_DEBUG_VFS, "exiting kill_super\n");
 }
 
diff --git a/fs/afs/internal.h b/fs/afs/internal.h
index 330654ed16ec..3282d5d6e1c0 100644
--- a/fs/afs/internal.h
+++ b/fs/afs/internal.h
@@ -251,6 +251,8 @@ struct afs_super_info {
 	struct afs_volume	*volume;	/* volume record */
 	enum afs_flock_mode	flock_mode:8;	/* File locking emulation mode */
 	bool			dyn_root;	/* True if dynamic root */
+	/* afs_atcell_get_link() reads ->net_ns in rcu pathwalk */
+	struct rcu_head		rcu;
 };
 
 static inline struct afs_super_info *AFS_FS_S(struct super_block *sb)
diff --git a/fs/afs/super.c b/fs/afs/super.c
index 82bb713825a0..33b195821e36 100644
--- a/fs/afs/super.c
+++ b/fs/afs/super.c
@@ -523,7 +523,7 @@ static void afs_destroy_sbi(struct afs_super_info *as)
 		afs_put_volume(as->volume, afs_volume_trace_put_destroy_sbi);
 		afs_unuse_cell(as->cell, afs_cell_trace_unuse_sbi);
 		put_net(as->net_ns);
-		kfree(as);
+		kfree_rcu(as, rcu);
 	}
 }
 
diff --git a/fs/autofs/waitq.c b/fs/autofs/waitq.c
index d46241342dfc..92c0bbbf452b 100644
--- a/fs/autofs/waitq.c
+++ b/fs/autofs/waitq.c
@@ -12,15 +12,13 @@
  */
 static autofs_wqt_t autofs_next_wait_queue = 1;
 
-void autofs_catatonic_mode(struct autofs_sb_info *sbi)
+static void autofs_catatonic_mode_locked(struct autofs_sb_info *sbi)
 {
 	struct autofs_wait_queue *wq, *nwq;
 
-	mutex_lock(&sbi->wq_mutex);
-	if (sbi->flags & AUTOFS_SBI_CATATONIC) {
-		mutex_unlock(&sbi->wq_mutex);
+	lockdep_assert_held(&sbi->wq_mutex);
+	if (sbi->flags & AUTOFS_SBI_CATATONIC)
 		return;
-	}
 
 	pr_debug("entering catatonic mode\n");
 
@@ -40,6 +38,21 @@ void autofs_catatonic_mode(struct autofs_sb_info *sbi)
 	fput(sbi->pipe);	/* Close the pipe */
 	sbi->pipe = NULL;
 	sbi->pipefd = -1;
+}
+
+void autofs_catatonic_mode(struct autofs_sb_info *sbi)
+{
+	mutex_lock(&sbi->wq_mutex);
+	autofs_catatonic_mode_locked(sbi);
+	mutex_unlock(&sbi->wq_mutex);
+}
+
+static void autofs_catatonic_mode_for_pipe(struct autofs_sb_info *sbi,
+					   struct file *pipe)
+{
+	mutex_lock(&sbi->wq_mutex);
+	if (sbi->pipe == pipe)
+		autofs_catatonic_mode_locked(sbi);
 	mutex_unlock(&sbi->wq_mutex);
 }
 
@@ -170,7 +183,7 @@ static void autofs_notify_daemon(struct autofs_sb_info *sbi,
 		autofs_wait_release(sbi, wq->wait_queue_token, ret);
 		break;
 	default:
-		autofs_catatonic_mode(sbi);
+		autofs_catatonic_mode_for_pipe(sbi, pipe);
 		break;
 	}
 	fput(pipe);
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 724a27e8be61..af70bb26bb54 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -1774,6 +1774,8 @@ struct ext4_sb_info {
 	struct list_head s_es_list;	/* List of inodes with reclaimable extents */
 	long s_es_nr_inode;
 	struct ext4_es_stats s_es_stats;
+	/* ext4_get_link() reads the sbi in rcu pathwalk */
+	struct rcu_head s_rcu;
 	struct mb_cache *s_ea_block_cache;
 	struct mb_cache *s_ea_inode_cache;
 
diff --git a/fs/ext4/extents-test.c b/fs/ext4/extents-test.c
index c3836ecb89f9..2e997f228330 100644
--- a/fs/ext4/extents-test.c
+++ b/fs/ext4/extents-test.c
@@ -151,6 +151,7 @@ static void extents_kunit_exit(struct kunit *test)
 
 	sbi = k_ctx.k_ei->vfs_inode.i_sb->s_fs_info;
 	ext4_es_unregister_shrinker(sbi);
+	ext4_es_destroy_stats(sbi);
 	deactivate_super(sbi->s_sb);
 	kfree(sbi);
 	kfree(k_ctx.k_ei);
@@ -340,6 +341,7 @@ out:
 	k_ctx.k_data = NULL;
 
 	ext4_es_unregister_shrinker(sbi);
+	ext4_es_destroy_stats(sbi);
 out_deactivate:
 	deactivate_locked_super(sb);
 	kfree(sbi);
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 76038b6c3655..3bf0a6cdbec2 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -6409,6 +6409,7 @@ EXPORT_SYMBOL_FOR_EXT4_TEST(__ext4_ext_dirty);
 EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_ext_zeroout);
 EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_es_register_shrinker);
 EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_es_unregister_shrinker);
+EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_es_destroy_stats);
 EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_map_create_blocks);
 EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_es_init_tree);
 EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_es_lookup_extent);
diff --git a/fs/ext4/extents_status.c b/fs/ext4/extents_status.c
index 6e4a191e8219..018b6146b9d8 100644
--- a/fs/ext4/extents_status.c
+++ b/fs/ext4/extents_status.c
@@ -1881,12 +1881,17 @@ err1:
 }
 
 void ext4_es_unregister_shrinker(struct ext4_sb_info *sbi)
+{
+	shrinker_free(sbi->s_es_shrinker);
+}
+
+/* ext4_get_link() bumps the hit and miss counters in rcu pathwalk */
+void ext4_es_destroy_stats(struct ext4_sb_info *sbi)
 {
 	percpu_counter_destroy(&sbi->s_es_stats.es_stats_cache_hits);
 	percpu_counter_destroy(&sbi->s_es_stats.es_stats_cache_misses);
 	percpu_counter_destroy(&sbi->s_es_stats.es_stats_all_cnt);
 	percpu_counter_destroy(&sbi->s_es_stats.es_stats_shk_cnt);
-	shrinker_free(sbi->s_es_shrinker);
 }
 
 /*
diff --git a/fs/ext4/extents_status.h b/fs/ext4/extents_status.h
index f3396cf32b44..01cddcaaa68e 100644
--- a/fs/ext4/extents_status.h
+++ b/fs/ext4/extents_status.h
@@ -238,6 +238,7 @@ static inline void ext4_es_store_pblock_status(struct extent_status *es,
 
 extern int ext4_es_register_shrinker(struct ext4_sb_info *sbi);
 extern void ext4_es_unregister_shrinker(struct ext4_sb_info *sbi);
+extern void ext4_es_destroy_stats(struct ext4_sb_info *sbi);
 
 extern int ext4_seq_es_shrinker_info_show(struct seq_file *seq, void *v);
 
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index d636b89090a2..3ace06b4f9e3 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -1279,6 +1279,14 @@ static void ext4_flex_groups_free(struct ext4_sb_info *sbi)
 	}
 }
 
+static void ext4_put_sbi_rcu(struct rcu_head *head)
+{
+	struct ext4_sb_info *sbi = container_of(head, struct ext4_sb_info, s_rcu);
+
+	ext4_es_destroy_stats(sbi);
+	kfree(sbi);
+}
+
 static void ext4_put_super(struct super_block *sb)
 {
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
@@ -1374,7 +1382,6 @@ static void ext4_put_super(struct super_block *sb)
 	ext4_stop_mmpd(sbi);
 
 	brelse(sbi->s_sbh);
-	sb->s_fs_info = NULL;
 	/*
 	 * Now that we are completely done shutting down the
 	 * superblock, we need to actually destroy the kobject.
@@ -1387,7 +1394,8 @@ static void ext4_put_super(struct super_block *sb)
 #if IS_ENABLED(CONFIG_UNICODE)
 	utf8_unload(sb->s_encoding);
 #endif
-	kfree(sbi);
+	/* ext4_get_link() reads the sbi and the counters in rcu pathwalk */
+	call_rcu(&sbi->s_rcu, ext4_put_sbi_rcu);
 }
 
 static struct kmem_cache *ext4_inode_cachep;
@@ -5806,6 +5814,7 @@ failed_mount3a:
 	/* Drain deferred EA inode iputs from journal replay */
 	flush_delayed_work(&sbi->s_ea_inode_work);
 	ext4_es_unregister_shrinker(sbi);
+	ext4_es_destroy_stats(sbi);
 failed_mount3:
 	/* flush s_sb_upd_work before sbi destroy */
 	flush_work(&sbi->s_sb_upd_work);
diff --git a/fs/namei.c b/fs/namei.c
index c87c14ee1a25..e45e30603215 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -2086,33 +2086,6 @@ all_done: // pure jump
 	return NULL;
 }
 
-/*
- * Be careful in case the dentry is unlinked or renamed. Any mounts
- * stacked on top of it are going away. We need to make sure that we
- * don't reveal the underyling dentry during refwalk. In rcuwalk we
- * catch this via d_seq and another lookup for the name. Give the same
- * guarantee in refwalk.
- */
-static bool unlink_may_reveal(struct nameidata *nd, int flags,
-			      struct path *path, struct dentry *dentry)
-{
-	/* ".." and LOOKUP_DOWN may land on an unhashed directory */
-	if (flags & WALK_NOFOLLOW)
-		return false;
-	if (nd->flags & LOOKUP_REVAL)
-		return false;
-	/* We crossed onto a mount and the name led us here while it still existed */
-	if (path->mnt != nd->path.mnt)
-		return false;
-	/* only a name on its way out is flagged */
-	if (likely(!cant_mount(dentry)))
-		return false;
-	if (!d_unlinked(dentry))
-		return false;
-	dput(no_free_ptr(path->dentry));
-	return true;
-}
-
 /*
  * Do we need to follow links? We _really_ want to be able
  * to do this check without having to look at inode->i_op,
@@ -2142,8 +2115,6 @@ static noinline const char *step_into_slowpath(struct nameidata *nd, int flags,
 			if (unlikely(!inode))
 				return ERR_PTR(-ENOENT);
 		} else {
-			if (unlikely(unlink_may_reveal(nd, flags, &path, dentry)))
-				return ERR_PTR(-ESTALE);
 			dput(nd->path.dentry);
 			if (nd->path.mnt != path.mnt)
 				mntput(nd->path.mnt);
@@ -4750,8 +4721,7 @@ static struct dentry *lookup_fast_for_open(struct nameidata *nd, int open_flag)
 		return dentry;
 
 	if (open_flag & O_CREAT) {
-		/* Discard negative dentries. Need inode_lock to do the create */
-		if (!dentry->d_inode) {
+		if (d_is_negative(dentry)) {
 			if (!(nd->flags & LOOKUP_RCU))
 				dput(dentry);
 			dentry = NULL;
diff --git a/fs/namespace.c b/fs/namespace.c
index 3ed3766f3a18..c30f063742f4 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -297,7 +297,11 @@ int mnt_get_count(struct mount *mnt)
 	/* puts first, so a put counted here has its get counted below */
 	for_each_possible_cpu(cpu)
 		puts += per_cpu_ptr(mnt->mnt_pcp, cpu)->mnt_puts;
-	smp_mb();	/* pairs with the smp_wmb() in mntput_no_expire() */
+	/*
+	 * Pairs with the smp_wmb() in mntput_no_expire() and with the
+	 * smp_mb() in __legitimize_mnt().
+	 */
+	smp_mb();
 	for_each_possible_cpu(cpu)
 		gets += per_cpu_ptr(mnt->mnt_pcp, cpu)->mnt_gets;
 
@@ -782,7 +786,7 @@ int __legitimize_mnt(struct vfsmount *bastard, unsigned seq)
 		return 0;
 	mnt = real_mount(bastard);
 	mnt_inc_count(mnt);
-	smp_mb();	/* see mntput_no_expire_slowpath() and do_umount() */
+	smp_mb();	/* pairs with the smp_mb() in mnt_get_count() */
 	if (likely(!read_seqretry(&mount_lock, seq)))
 		return 0;
 	lock_mount_hash();
@@ -1419,11 +1423,6 @@ static void noinline mntput_no_expire_slowpath(struct mount *mnt)
 
 	VFS_BUG_ON(mnt->mnt_ns);
 	lock_mount_hash();
-	/*
-	 * make sure that if __legitimize_mnt() has not seen us grab
-	 * mount_lock, we'll see their refcount increment here.
-	 */
-	smp_mb();
 	mnt_dec_count(mnt);
 	count = mnt_get_count(mnt);
 	if (count != 0) {
@@ -2006,7 +2005,6 @@ static int do_umount(struct mount *mnt, int flags)
 		umount_tree(mnt, UMOUNT_PROPAGATE);
 		retval = 0;
 	} else {
-		smp_mb(); // paired with __legitimize_mnt()
 		shrink_submounts(mnt);
 		retval = -EBUSY;
 		if (!propagate_mount_busy(mnt, 2)) {
@@ -2254,6 +2252,11 @@ struct mount *copy_tree(struct mount *src_root, struct dentry *dentry,
 			}
 			if (!(flag & CL_COPY_MNT_NS_FILE) &&
 			    is_mnt_ns_file(src_mnt->mnt.mnt_root)) {
+				if (src_mnt->mnt.mnt_flags & MNT_LOCKED) {
+					/* Both a mount namespace file and locked. */
+					dst_mnt = ERR_PTR(-EPERM);
+					goto out;
+				}
 				src_mnt = skip_mnt_tree(src_mnt);
 				continue;
 			}
@@ -3649,8 +3652,9 @@ static bool mount_is_ancestor(const struct mount *p1, const struct mount *p2)
  * @mnt_to:   mount under which to mount
  * @mp:   mountpoint of @mnt_to
  *
- * - Make sure that the caller can unmount the topmost mount ensuring
- *   that the caller could reveal the underlying mountpoint.
+ * - Make sure that @mnt_from can take over the lock of @mnt_to. A
+ *   mount of a mount namespace file is left out of a copy of the tree
+ *   and can't.
  * - Ensure that nothing has been mounted on top of @mnt_from before we
  *   grabbed @namespace_sem to avoid creating pointless shadow mounts.
  * - Prevent mounting beneath a mount if the propagation relationship
@@ -3666,6 +3670,15 @@ static int can_move_mount_beneath(const struct mount *mnt_from,
 {
 	struct mount *parent_mnt_to = mnt_to->mnt_parent;
 
+	/*
+	 * @mnt_from takes over the lock of @mnt_to. copy_tree() leaves a
+	 * mount of a mount namespace file out of every copy made without
+	 * CL_COPY_MNT_NS_FILE, together with what is mounted on it, so it
+	 * can't keep anything hidden.
+	 */
+	if (IS_MNT_LOCKED(mnt_to) && is_mnt_ns_file(mnt_from->mnt.mnt_root))
+		return -EINVAL;
+
 	/* Avoid creating shadow mounts during mount propagation. */
 	if (mnt_from->overmount)
 		return -EINVAL;
diff --git a/fs/notify/mark.c b/fs/notify/mark.c
index d17628580a57..cb07f42d3422 100644
--- a/fs/notify/mark.c
+++ b/fs/notify/mark.c
@@ -929,6 +929,11 @@ restart:
 		goto restart;
 	}
 
+	if (conn->flags & FSNOTIFY_CONN_FLAG_DESTROYING) {
+		err = -ENOENT;
+		goto out_err;
+	}
+
 	/* is mark the first mark? */
 	if (hlist_empty(&conn->list)) {
 		hlist_add_head_rcu(&mark->obj_list, &conn->list);
@@ -1116,6 +1121,12 @@ void fsnotify_destroy_marks(fsnotify_connp_t *connp)
 	conn = fsnotify_grab_connector(connp);
 	if (!conn)
 		return;
+	/*
+	 * New marks could be inserted before our cursor and survive the final
+	 * detachment of the connector from the object. Prevent additions to
+	 * this connector before dropping its lock.
+	 */
+	conn->flags |= FSNOTIFY_CONN_FLAG_DESTROYING;
 	/*
 	 * We have to be careful since we can race with e.g.
 	 * fsnotify_clear_marks_by_group() and once we drop the conn->lock, the
diff --git a/fs/ntfs3/dir.c b/fs/ntfs3/dir.c
index eb9152e9fa22..14ca54e54578 100644
--- a/fs/ntfs3/dir.c
+++ b/fs/ntfs3/dir.c
@@ -186,11 +186,20 @@ int ntfs_nls_to_utf16(struct ntfs_sb_info *sbi, const u8 *name, u32 name_len,
 {
 	int ret, slen, i;
 	const u8 *end;
-	struct nls_table *nls = sbi->options->nls;
+	struct ntfs_mount_options *opts;
+	struct nls_table *nls;
+	bool ads;
 	u16 *uname = uni->name;
 
 	static_assert(sizeof(wchar_t) == sizeof(u16));
 
+	/* ntfs_fs_reconfigure() may replace the options, but not ->nls */
+	rcu_read_lock();
+	opts = READ_ONCE(sbi->options);
+	nls = opts->nls;
+	ads = opts->ads;
+	rcu_read_unlock();
+
 	if (!nls) {
 		/* utf8 -> utf16 */
 		ret = _utf8s_to_utf16s(name, name_len, endian, uname, max_ulen);
@@ -230,7 +239,7 @@ int ntfs_nls_to_utf16(struct ntfs_sb_info *sbi, const u8 *name, u32 name_len,
 
 	uni->len = ret;
 	uni->ads_len = 0;
-	if (ret > 0 && sbi->options->ads) {
+	if (ret > 0 && ads) {
 		uname = uni->name;
 		/* Find delimiter in range [1 : ret-2). */
 		for (i = 1; i + 1 < ret; i++) {
diff --git a/fs/ntfs3/ntfs_fs.h b/fs/ntfs3/ntfs_fs.h
index 5811d89d67b3..44d59b444648 100644
--- a/fs/ntfs3/ntfs_fs.h
+++ b/fs/ntfs3/ntfs_fs.h
@@ -91,6 +91,8 @@ enum utf16_endian;
 struct ntfs_mount_options {
 	char *nls_name;
 	struct nls_table *nls;
+	/* ->d_hash() and ->d_compare() read the options in rcu pathwalk */
+	struct rcu_head rcu;
 
 	kuid_t fs_uid;
 	kgid_t fs_gid;
@@ -211,6 +213,7 @@ struct ntfs_index {
 /* Ntfs file system in-core superblock data. */
 struct ntfs_sb_info {
 	struct super_block *sb;
+	struct rcu_head rcu;
 
 	u32 discard_granularity;
 	u64 discard_granularity_mask_inv; // ~(discard_granularity_mask_inv-1)
diff --git a/fs/ntfs3/super.c b/fs/ntfs3/super.c
index f4a42a0c73a4..58ef6be3286b 100644
--- a/fs/ntfs3/super.c
+++ b/fs/ntfs3/super.c
@@ -196,7 +196,7 @@ void *ntfs_set_shared(void *ptr, u32 bytes)
 	void *ret = NULL;
 	int i, j = -1;
 
-	spin_lock(&s_shared_lock);
+	spin_lock_bh(&s_shared_lock);
 	for (i = 0; i < ARRAY_SIZE(s_shared); i++) {
 		if (!s_shared[i].cnt) {
 			j = i;
@@ -214,7 +214,7 @@ void *ntfs_set_shared(void *ptr, u32 bytes)
 		s_shared[j].cnt = 1;
 		ret = ptr;
 	}
-	spin_unlock(&s_shared_lock);
+	spin_unlock_bh(&s_shared_lock);
 
 	return ret;
 }
@@ -231,7 +231,7 @@ void *ntfs_put_shared(void *ptr)
 	void *ret = ptr;
 	int i;
 
-	spin_lock(&s_shared_lock);
+	spin_lock_bh(&s_shared_lock);
 	for (i = 0; i < ARRAY_SIZE(s_shared); i++) {
 		if (s_shared[i].cnt && s_shared[i].ptr == ptr) {
 			if (--s_shared[i].cnt)
@@ -239,7 +239,7 @@ void *ntfs_put_shared(void *ptr)
 			break;
 		}
 	}
-	spin_unlock(&s_shared_lock);
+	spin_unlock_bh(&s_shared_lock);
 
 	return ret;
 }
@@ -251,6 +251,11 @@ static inline void put_mount_options(struct ntfs_mount_options *options)
 	kfree(options);
 }
 
+static void put_mount_options_rcu(struct rcu_head *head)
+{
+	put_mount_options(container_of(head, struct ntfs_mount_options, rcu));
+}
+
 enum Opt {
 	Opt_uid,
 	Opt_gid,
@@ -444,6 +449,7 @@ static int ntfs_fs_reconfigure(struct fs_context *fc)
 	struct super_block *sb = fc->root->d_sb;
 	struct ntfs_sb_info *sbi = sb->s_fs_info;
 	struct ntfs_mount_options *new_opts = fc->fs_private;
+	struct ntfs_mount_options *old_opts;
 	int ro_rw;
 
 	ro_rw = sb_rdonly(sb) && !(fc->sb_flags & SB_RDONLY);
@@ -473,7 +479,15 @@ static int ntfs_fs_reconfigure(struct fs_context *fc)
 	}
 
 	sync_filesystem(sb);
-	swap(sbi->options, fc->fs_private);
+	old_opts = sbi->options;
+	/* pairs with the READ_ONCE() in ntfs_nls_to_utf16() */
+	smp_store_release(&sbi->options, new_opts);
+	fc->fs_private = NULL;
+	/*
+	 * ntfs_d_hash() and ntfs_d_compare() of a pathwalk in rcu mode may
+	 * still read the old options through the sbi.
+	 */
+	call_rcu(&old_opts->rcu, put_mount_options_rcu);
 
 	return 0;
 }
@@ -708,6 +722,8 @@ static noinline void ntfs3_put_sbi(struct ntfs_sb_info *sbi)
 
 static void ntfs3_free_sbi(struct ntfs_sb_info *sbi)
 {
+	if (sbi->options)
+		put_mount_options(sbi->options);
 	kfree(sbi->new_rec);
 	kvfree(ntfs_put_shared(sbi->upcase));
 	kvfree(sbi->def_table);
@@ -719,6 +735,11 @@ static void ntfs3_free_sbi(struct ntfs_sb_info *sbi)
 	kfree(sbi);
 }
 
+static void ntfs3_free_sbi_rcu(struct rcu_head *head)
+{
+	ntfs3_free_sbi(container_of(head, struct ntfs_sb_info, rcu));
+}
+
 static void ntfs_put_super(struct super_block *sb)
 {
 	struct ntfs_sb_info *sbi = sb->s_fs_info;
@@ -728,11 +749,11 @@ static void ntfs_put_super(struct super_block *sb)
 	/* Mark rw ntfs as clear, if possible. */
 	ntfs_set_state(sbi, NTFS_DIRTY_CLEAR);
 
-	if (sbi->options) {
-		put_mount_options(sbi->options);
-		sbi->options = NULL;
-	}
-
+	/*
+	 * The mount options stay until the sbi is freed: ->d_hash() and
+	 * ->d_compare() of a pathwalk in rcu mode read the nls table through
+	 * them.
+	 */
 	ntfs3_put_sbi(sbi);
 }
 
@@ -1939,9 +1960,11 @@ static void ntfs3_kill_sb(struct super_block *sb)
 
 	kill_block_super(sb);
 
-	if (sbi->options)
-		put_mount_options(sbi->options);
-	ntfs3_free_sbi(sbi);
+	/*
+	 * A pathwalk in rcu mode may still be in ->d_hash() or ->d_compare()
+	 * and read the upcase table and the nls table through the sbi.
+	 */
+	call_rcu(&sbi->rcu, ntfs3_free_sbi_rcu);
 }
 
 // clang-format off
diff --git a/fs/ocfs2/dlm/dlmcommon.h b/fs/ocfs2/dlm/dlmcommon.h
index 20f790a47484..58b28dfa8d34 100644
--- a/fs/ocfs2/dlm/dlmcommon.h
+++ b/fs/ocfs2/dlm/dlmcommon.h
@@ -435,6 +435,8 @@ enum {
 	DLM_DEREF_LOCKRES_DONE		= 522,
 };
 
+extern spinlock_t dlm_reco_state_lock;
+
 struct dlm_reco_node_data
 {
 	int state;
diff --git a/fs/ocfs2/dlm/dlmdebug.c b/fs/ocfs2/dlm/dlmdebug.c
index ce6d301cb942..a91f167ed683 100644
--- a/fs/ocfs2/dlm/dlmdebug.c
+++ b/fs/ocfs2/dlm/dlmdebug.c
@@ -736,8 +736,11 @@ static int debug_state_print(struct dlm_ctxt *dlm, char *buf, int len)
 				 buf + out, len - out);
 	out += scnprintf(buf + out, len - out, "\n");
 
+	spin_unlock(&dlm->spinlock);
+
 	/* Recovery Node State: */
 	out += scnprintf(buf + out, len - out, "Recovery Node State:\n");
+	spin_lock(&dlm_reco_state_lock);
 	list_for_each_entry(node, &dlm->reco.node_data, list) {
 		switch (node->state) {
 		case DLM_RECO_NODE_DATA_INIT:
@@ -769,7 +772,7 @@ static int debug_state_print(struct dlm_ctxt *dlm, char *buf, int len)
 				node->node_num, state);
 	}
 
-	spin_unlock(&dlm->spinlock);
+	spin_unlock(&dlm_reco_state_lock);
 
 	return out;
 }
diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c
index 9d4a2695b959..7d519e31fcf1 100644
--- a/fs/ocfs2/dlm/dlmrecovery.c
+++ b/fs/ocfs2/dlm/dlmrecovery.c
@@ -80,7 +80,7 @@ static int dlm_lockres_master_requery(struct dlm_ctxt *dlm,
 
 static u64 dlm_get_next_mig_cookie(void);
 
-static DEFINE_SPINLOCK(dlm_reco_state_lock);
+DEFINE_SPINLOCK(dlm_reco_state_lock);
 static DEFINE_SPINLOCK(dlm_mig_cookie_lock);
 static u64 dlm_mig_cookie = 1;
 
diff --git a/fs/overlayfs/params.c b/fs/overlayfs/params.c
index c93fcaa45d4a..5a15e5478a6b 100644
--- a/fs/overlayfs/params.c
+++ b/fs/overlayfs/params.c
@@ -216,6 +216,9 @@ static ssize_t ovl_parse_param_split_lowerdirs(char *str)
 		if (*s == '\\') {
 			/* keep esc chars in split lowerdir */
 			*d++ = *s++;
+			/* A trailing backslash escapes nothing. */
+			if (!*s)
+				return -EINVAL;
 		} else if (*s == ':') {
 			bool next_colon = (*(s + 1) == ':');
 
diff --git a/fs/pipe.c b/fs/pipe.c
index 292425a834dd..61806a013fde 100644
--- a/fs/pipe.c
+++ b/fs/pipe.c
@@ -838,9 +838,11 @@ pipe_fasync(int fd, struct file *filp, int on)
 	if (filp->f_mode & FMODE_READ)
 		retval = fasync_helper(fd, filp, on, &pipe->fasync_readers);
 	if ((filp->f_mode & FMODE_WRITE) && retval >= 0) {
+		int read_ret = retval;
+
 		retval = fasync_helper(fd, filp, on, &pipe->fasync_writers);
-		if (retval < 0 && (filp->f_mode & FMODE_READ))
-			/* this can happen only if on == T */
+		/* Undo only a reader entry added by this call. */
+		if (retval < 0 && read_ret > 0)
 			fasync_helper(-1, filp, 0, &pipe->fasync_readers);
 	}
 	mutex_unlock(&pipe->mutex);
diff --git a/fs/tracefs/event_inode.c b/fs/tracefs/event_inode.c
index 6e3513b13cfa..090aca946717 100644
--- a/fs/tracefs/event_inode.c
+++ b/fs/tracefs/event_inode.c
@@ -91,6 +91,14 @@ static void free_ei_rcu(struct rcu_head *rcu)
 	}
 }
 
+/* read under eventfs_srcu and, by tracefs_d_revalidate(), in rcu pathwalk */
+static void free_ei_srcu(struct rcu_head *rcu)
+{
+	struct eventfs_inode *ei = container_of(rcu, struct eventfs_inode, rcu);
+
+	call_rcu(&ei->rcu, free_ei_rcu);
+}
+
 /*
  * eventfs_inode reference count management.
  *
@@ -112,7 +120,7 @@ static void release_ei(struct kref *ref)
 			entry->release(entry->name, ei->data);
 	}
 
-	call_srcu(&eventfs_srcu, &ei->rcu, free_ei_rcu);
+	call_srcu(&eventfs_srcu, &ei->rcu, free_ei_srcu);
 }
 
 static inline void put_ei(struct eventfs_inode *ei)
diff --git a/fs/unicode/utf8-core.c b/fs/unicode/utf8-core.c
index f313532f5e80..74a74a48dd8b 100644
--- a/fs/unicode/utf8-core.c
+++ b/fs/unicode/utf8-core.c
@@ -3,6 +3,7 @@
 #include <linux/kernel.h>
 #include <linux/string.h>
 #include <linux/slab.h>
+#include <linux/rcupdate.h>
 #include <linux/parser.h>
 #include <linux/errno.h>
 #include <linux/stringhash.h>
@@ -183,12 +184,24 @@ out_free_um:
 }
 EXPORT_SYMBOL(utf8_load);
 
+static void utf8_unload_rcu(struct rcu_head *head)
+{
+	struct unicode_map *um = container_of(head, struct unicode_map, rcu);
+
+	symbol_put(utf8_data_table);
+	kfree(um);
+}
+
+/*
+ * A pathwalk in rcu mode may still be in ->d_hash() or ->d_compare() of a
+ * filesystem that is being torn down and read the map through its
+ * superblock, so the map and the tables it points to have to outlive the
+ * grace period.
+ */
 void utf8_unload(struct unicode_map *um)
 {
-	if (um) {
-		symbol_put(utf8_data_table);
-		kfree(um);
-	}
+	if (um)
+		call_rcu(&um->rcu, utf8_unload_rcu);
 }
 EXPORT_SYMBOL(utf8_unload);
 
diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h
index 618eed4d6d72..a6d5c1a89cff 100644
--- a/include/linux/fsnotify_backend.h
+++ b/include/linux/fsnotify_backend.h
@@ -566,6 +566,7 @@ struct fsnotify_mark_connector {
 	unsigned char prio;	/* Highest priority group */
 #define FSNOTIFY_CONN_FLAG_IS_WATCHED	0x01
 #define FSNOTIFY_CONN_FLAG_HAS_IREF	0x02
+#define FSNOTIFY_CONN_FLAG_DESTROYING	0x04
 	unsigned short flags;	/* flags [lock] */
 	union {
 		/* Object pointer [lock] */
diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h
index d45a5476b97d..efa1e2d6c7a6 100644
--- a/include/linux/sched/signal.h
+++ b/include/linux/sched/signal.h
@@ -130,8 +130,8 @@ struct signal_struct {
 	 * process will inherit a flag if they should look for a
 	 * child_subreaper process at exit.
 	 */
-	unsigned int		is_child_subreaper:1;
-	unsigned int		has_child_subreaper:1;
+	bool			is_child_subreaper;
+	bool			has_child_subreaper;
 	unsigned int		autoreap:1;
 
 #ifdef CONFIG_POSIX_TIMERS
diff --git a/include/linux/unicode.h b/include/linux/unicode.h
index 64fa44fe180c..3a8cb603eb93 100644
--- a/include/linux/unicode.h
+++ b/include/linux/unicode.h
@@ -53,6 +53,7 @@ struct unicode_map {
 	unsigned int version;
 	const struct utf8data *ntab[UTF8_NMAX];
 	const struct utf8data_table *tables;
+	struct rcu_head rcu;
 };
 
 int utf8_validate(const struct unicode_map *um, const struct qstr *str);
diff --git a/ipc/namespace.c b/ipc/namespace.c
index 1e71353bdb4a..75aa7b469348 100644
--- a/ipc/namespace.c
+++ b/ipc/namespace.c
@@ -96,7 +96,7 @@ fail_ipc:
 fail_mq_sysctls:
 	retire_mq_sysctls(ns);
 fail_mq_mount:
-	mntput(ns->mq_mnt);
+	kern_unmount(ns->mq_mnt);
 fail_put:
 	put_user_ns(ns->user_ns);
 	ns_common_free(ns);
diff --git a/kernel/exit.c b/kernel/exit.c
index 282328d2b4cf..ba1469bea8fb 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -1729,7 +1729,7 @@ static long do_wait(struct wait_opts *wo)
 	add_wait_queue(&current->signal->wait_chldexit, &wo->child_wait);
 
 	do {
-		set_current_state(TASK_INTERRUPTIBLE);
+		set_current_state(TASK_INTERRUPTIBLE | TASK_FREEZABLE);
 		retval = __do_wait(wo);
 		if (retval != -ERESTARTSYS)
 			break;
diff --git a/kernel/fork.c b/kernel/fork.c
index eb198c8dfdc7..33760ece3bb3 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1619,7 +1619,13 @@ static int copy_exec_state(u64 clone_flags, struct task_struct *tsk)
 	return task_exec_state_copy(tsk);
 }
 
-static int copy_fs(u64 clone_flags, struct task_struct *tsk, bool umh)
+enum copy_fs_flags_t {
+	COPY_FS_UMH	= (1 << 0),
+	COPY_FS_IDLE	= (1 << 1),
+};
+
+static int copy_fs(u64 clone_flags, struct task_struct *tsk,
+		   enum copy_fs_flags_t flags)
 {
 	struct fs_struct *fs;
 
@@ -1629,19 +1635,20 @@ static int copy_fs(u64 clone_flags, struct task_struct *tsk, bool umh)
 	 * filesystem state, or be started from a non-initial mount
 	 * namespace.
 	 */
-	if (umh) {
+	if (flags & COPY_FS_UMH) {
 		if (clone_flags & (CLONE_NEWNS | CLONE_FS))
 			return -EINVAL;
 		if (current->nsproxy->mnt_ns != &init_mnt_ns)
 			return -EINVAL;
 		fs = userspace_init_fs;
+	} else if (flags & COPY_FS_IDLE) {
+		fs = &init_fs;
 	} else {
 		fs = current->fs;
 		VFS_WARN_ON_ONCE(current->fs != current->real_fs);
 	}
 
 	if (clone_flags & CLONE_FS) {
-		/* tsk->fs is already what we want */
 		read_seqlock_excl(&fs->seq);
 		/* "users" and "in_exec" locked for check_unsafe_exec() */
 		if (fs->in_exec) {
@@ -1650,6 +1657,7 @@ static int copy_fs(u64 clone_flags, struct task_struct *tsk, bool umh)
 		}
 		fs->users++;
 		read_sequnlock_excl(&fs->seq);
+		tsk->real_fs = tsk->fs = fs;
 		return 0;
 	}
 	tsk->real_fs = tsk->fs = copy_fs_struct(fs);
@@ -2299,7 +2307,9 @@ __latent_entropy struct task_struct *copy_process(
 	retval = copy_files(clone_flags, p, args->no_files);
 	if (retval)
 		goto bad_fork_cleanup_semundo;
-	retval = copy_fs(clone_flags, p, args->umh);
+	retval = copy_fs(clone_flags, p,
+			 (args->umh ? COPY_FS_UMH : 0) |
+			 (args->idle ? COPY_FS_IDLE : 0));
 	if (retval)
 		goto bad_fork_cleanup_files;
 	retval = copy_sighand(clone_flags, p);
@@ -2671,7 +2681,7 @@ struct task_struct * __init fork_idle(int cpu)
 {
 	struct task_struct *task;
 	struct kernel_clone_args args = {
-		.flags		= CLONE_VM,
+		.flags		= CLONE_VM | CLONE_FS,
 		.fn		= &idle_dummy,
 		.fn_arg		= NULL,
 		.kthread	= 1,
diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c
index d36afc58ee1d..4ade0f37ed54 100644
--- a/kernel/pid_namespace.c
+++ b/kernel/pid_namespace.c
@@ -268,7 +268,7 @@ void zap_pid_ns_processes(struct pid_namespace *pid_ns)
 	 * free_pid() will awaken this task.
 	 */
 	for (;;) {
-		set_current_state(TASK_INTERRUPTIBLE);
+		set_current_state(TASK_IDLE | TASK_FREEZABLE);
 		if (pid_ns->pid_allocated == init_pids)
 			break;
 		schedule();
diff --git a/kernel/watch_queue.c b/kernel/watch_queue.c
index 538520861e8b..932a88ac1f39 100644
--- a/kernel/watch_queue.c
+++ b/kernel/watch_queue.c
@@ -101,7 +101,7 @@ static bool post_one_notification(struct watch_queue *wqueue,
 	struct pipe_inode_info *pipe = wqueue->pipe;
 	struct pipe_buffer *buf;
 	struct page *page;
-	unsigned int head, tail, note, offset, len;
+	unsigned int head, tail, note, offset, len, nr_notes;
 	bool done = false;
 
 	spin_lock_irq(&pipe->rd_wait.lock);
@@ -111,8 +111,10 @@ static bool post_one_notification(struct watch_queue *wqueue,
 	if (pipe_full(head, tail, pipe->ring_size))
 		goto lost;
 
-	note = find_first_bit(wqueue->notes_bitmap, wqueue->nr_notes);
-	if (note >= wqueue->nr_notes)
+	/* Pairs with the smp_store_release() in watch_queue_set_size(). */
+	nr_notes = smp_load_acquire(&wqueue->nr_notes);
+	note = find_first_bit(wqueue->notes_bitmap, nr_notes);
+	if (note >= nr_notes)
 		goto lost;
 
 	page = wqueue->notes[note / WATCH_QUEUE_NOTES_PER_PAGE];
@@ -297,7 +299,8 @@ long watch_queue_set_size(struct pipe_inode_info *pipe, unsigned int nr_notes)
 	wqueue->notes = pages;
 	wqueue->notes_bitmap = bitmap;
 	wqueue->nr_pages = nr_pages;
-	wqueue->nr_notes = nr_notes;
+	/* Pairs with the smp_load_acquire() in post_one_notification(). */
+	smp_store_release(&wqueue->nr_notes, nr_notes);
 	return 0;
 
 error_p:
diff --git a/samples/pidfd/Makefile b/samples/pidfd/Makefile
index 9754e2d81f70..d82409f7061f 100644
--- a/samples/pidfd/Makefile
+++ b/samples/pidfd/Makefile
@@ -1,4 +1,4 @@
 # SPDX-License-Identifier: GPL-2.0
-usertprogs-always-y += pidfd-metadata
+userprogs-always-y += pidfd-metadata
 
 userccflags += -I usr/include
diff --git a/tools/testing/selftests/filesystems/umount_propagation/locked_mount_test.c b/tools/testing/selftests/filesystems/umount_propagation/locked_mount_test.c
index 0799b2ba545d..e9b2b874dd16 100644
--- a/tools/testing/selftests/filesystems/umount_propagation/locked_mount_test.c
+++ b/tools/testing/selftests/filesystems/umount_propagation/locked_mount_test.c
@@ -9,6 +9,8 @@
 #include <errno.h>
 #include <fcntl.h>
 #include <sched.h>
+#include <stdbool.h>
+#include <signal.h>
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
@@ -27,6 +29,12 @@
 #ifndef MOVE_MOUNT_BENEATH
 #define MOVE_MOUNT_BENEATH	0x00000200
 #endif
+#ifndef OPEN_TREE_CLONE
+#define OPEN_TREE_CLONE		1
+#endif
+#ifndef OPEN_TREE_CLOEXEC
+#define OPEN_TREE_CLOEXEC	O_CLOEXEC
+#endif
 
 #define DIR_LEN		64
 #define PATH_LEN	192
@@ -120,6 +128,35 @@ static bool covered(const char *path)
 	return fd < 0;
 }
 
+/* What @path reads, "" if it can't be read. */
+static int read_word(const char *path, char *buf, size_t len)
+{
+	ssize_t n = 0;
+	int fd;
+
+	fd = open(path, O_RDONLY | O_CLOEXEC);
+	if (fd >= 0) {
+		n = read(fd, buf, len - 1);
+		close(fd);
+	}
+	buf[n > 0 ? n : 0] = 0;
+	return fd < 0 ? -1 : 0;
+}
+
+/* Put a clone of the mount at @src beneath the top mount at @where. */
+static int move_beneath(const char *src, const char *where)
+{
+	int fd, ret;
+
+	fd = syscall(__NR_open_tree, AT_FDCWD, src, OPEN_TREE_CLONE | OPEN_TREE_CLOEXEC);
+	if (fd < 0)
+		return -1;
+	ret = syscall(__NR_move_mount, fd, "", AT_FDCWD, where,
+		      MOVE_MOUNT_F_EMPTY_PATH | MOVE_MOUNT_BENEATH);
+	close(fd);
+	return ret;
+}
+
 FIXTURE(locked_mount) {
 	char base[DIR_LEN];
 	bool tracing;		/* debugfs with the tracefs automount is there */
@@ -429,4 +466,89 @@ TEST_F(locked_mount, propagated_copy_keeps_the_cover_locked)
 	EXPECT_EQ(ret, CHILD_OK);
 }
 
+/*
+ * A mount of a mount namespace file is left out of the copy that
+ * unshare(CLONE_NEWNS) makes, together with everything mounted on it, so
+ * it can't take over the lock of a cover it is moved beneath. The child
+ * tries just that with the namespace file of a grandchild and gets EINVAL.
+ * A bind of an ordinary file takes the lock over, and the file is still
+ * covered in the next copy of the mount namespace.
+ */
+static int ns_file_child(const char *base)
+{
+	char secret[PATH_LEN], mine[PATH_LEN], nsfile[PATH_LEN], buf[32];
+	int ret = CHILD_OK, pfd[2];
+	pid_t pid;
+
+	snprintf(secret, sizeof(secret), "%s/P/secret", base);
+	snprintf(mine, sizeof(mine), "%s/mine", base);
+
+	if (enter_userns() || pipe(pfd))
+		return CHILD_SETUP;
+	/* the cover is locked */
+	if (!umount2(secret, 0) || errno != EINVAL)
+		return CHILD_STEP1;
+
+	/* a mount namespace newer than our own, so that a bind of it is allowed */
+	pid = fork();
+	if (pid < 0)
+		return CHILD_SETUP;
+	if (pid == 0) {
+		if (unshare(CLONE_NEWNS) || send_byte(pfd[1]))
+			_exit(1);
+		pause();
+		_exit(0);
+	}
+	if (wait_byte(pfd[0]))
+		return CHILD_SETUP;
+	snprintf(nsfile, sizeof(nsfile), "/proc/%d/ns/mnt", pid);
+	if (!move_beneath(nsfile, secret) || errno != EINVAL)
+		ret = CHILD_STEP2;
+	kill(pid, SIGKILL);
+	waitpid(pid, NULL, 0);
+	if (ret)
+		return ret;
+
+	/* an ordinary file beneath the cover takes the lock over */
+	if (move_beneath(mine, secret))
+		return CHILD_STEP3;
+	if (umount2(secret, 0))
+		return CHILD_STEP3;
+	if (!umount2(secret, 0) || errno != EINVAL)
+		return CHILD_STEP3;
+	/* and it is in the next copy of the namespace */
+	if (unshare(CLONE_NEWNS))
+		return CHILD_SETUP;
+	if (read_word(secret, buf, sizeof(buf)) || strcmp(buf, "mine"))
+		return CHILD_STEP4;
+	return CHILD_OK;
+}
+
+TEST_F(locked_mount, mount_namespace_file_cant_take_the_lock)
+{
+	char p[PATH_LEN], q[PATH_LEN];
+	pid_t pid;
+	int ret;
+
+	snprintf(p, sizeof(p), "%s/P", self->base);
+	ASSERT_EQ(mkdir(p, 0755), 0);
+	ASSERT_EQ(mount("tmpfs", p, "tmpfs", 0, "mode=0755"), 0);
+	snprintf(p, sizeof(p), "%s/P/secret", self->base);
+	ASSERT_EQ(create_file(p, "covered-by-root\n"), 0);
+	snprintf(q, sizeof(q), "%s/P/empty", self->base);
+	ASSERT_EQ(create_file(q, ""), 0);
+	/* the cover: an empty file over the secret */
+	ASSERT_EQ(mount(q, p, NULL, MS_BIND, NULL), 0);
+	snprintf(q, sizeof(q), "%s/mine", self->base);
+	ASSERT_EQ(create_file(q, "mine"), 0);
+
+	pid = fork();
+	ASSERT_GE(pid, 0);
+	if (pid == 0)
+		_exit(ns_file_child(self->base));
+	ret = wait_child(pid);
+	TH_LOG("child exit code %d", ret);
+	EXPECT_EQ(ret, CHILD_OK);
+}
+
 TEST_HARNESS_MAIN