1 files changed, 248 insertions, 112 deletions

diff --git a/fs/kernfs/mount.c b/fs/kernfs/mount.c
index d5b149a45be1..3ac52e141766 100644
--- a/fs/kernfs/mount.c
+++ b/fs/kernfs/mount.c
@@ -1,11 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * fs/kernfs/mount.c - kernfs mount implementation
  *
  * Copyright (c) 2001-3 Patrick Mochel
  * Copyright (c) 2007 SUSE Linux Products GmbH
  * Copyright (c) 2007, 2013 Tejun Heo <tj@kernel.org>
- *
- * This file is released under the GPLv2.
  */
 
 #include <linux/fs.h>
@@ -16,24 +15,19 @@
 #include <linux/pagemap.h>
 #include <linux/namei.h>
 #include <linux/seq_file.h>
+#include <linux/exportfs.h>
+#include <linux/uuid.h>
+#include <linux/statfs.h>
 
 #include "kernfs-internal.h"
 
-struct kmem_cache *kernfs_node_cache;
-
-static int kernfs_sop_remount_fs(struct super_block *sb, int *flags, char *data)
-{
-	struct kernfs_root *root = kernfs_info(sb)->root;
-	struct kernfs_syscall_ops *scops = root->syscall_ops;
-
-	if (scops && scops->remount_fs)
-		return scops->remount_fs(root, flags, data);
-	return 0;
-}
+struct kmem_cache *kernfs_node_cache __ro_after_init;
+struct kmem_cache *kernfs_iattrs_cache __ro_after_init;
+struct kernfs_global_locks *kernfs_locks __ro_after_init;
 
 static int kernfs_sop_show_options(struct seq_file *sf, struct dentry *dentry)
 {
-	struct kernfs_root *root = kernfs_root(dentry->d_fsdata);
+	struct kernfs_root *root = kernfs_root(kernfs_dentry_node(dentry));
 	struct kernfs_syscall_ops *scops = root->syscall_ops;
 
 	if (scops && scops->show_options)
@@ -43,7 +37,7 @@ static int kernfs_sop_show_options(struct seq_file *sf, struct dentry *dentry)
 
 static int kernfs_sop_show_path(struct seq_file *sf, struct dentry *dentry)
 {
-	struct kernfs_node *node = dentry->d_fsdata;
+	struct kernfs_node *node = kernfs_dentry_node(dentry);
 	struct kernfs_root *root = kernfs_root(node);
 	struct kernfs_syscall_ops *scops = root->syscall_ops;
 
@@ -54,21 +48,136 @@ static int kernfs_sop_show_path(struct seq_file *sf, struct dentry *dentry)
 	return 0;
 }
 
+static int kernfs_statfs(struct dentry *dentry, struct kstatfs *buf)
+{
+	simple_statfs(dentry, buf);
+	buf->f_fsid = uuid_to_fsid(dentry->d_sb->s_uuid.b);
+	return 0;
+}
+
 const struct super_operations kernfs_sops = {
-	.statfs		= simple_statfs,
-	.drop_inode	= generic_delete_inode,
+	.statfs		= kernfs_statfs,
+	.drop_inode	= inode_just_drop,
 	.evict_inode	= kernfs_evict_inode,
 
-	.remount_fs	= kernfs_sop_remount_fs,
 	.show_options	= kernfs_sop_show_options,
 	.show_path	= kernfs_sop_show_path,
+
+	/*
+	 * sysfs is built on top of kernfs and sysfs provides the power
+	 * management infrastructure to support suspend/hibernate by
+	 * writing to various files in /sys/power/. As filesystems may
+	 * be automatically frozen during suspend/hibernate implementing
+	 * freeze/thaw support for kernfs generically will cause
+	 * deadlocks as the suspending/hibernation initiating task will
+	 * hold a VFS lock that it will then wait upon to be released.
+	 * If freeze/thaw for kernfs is needed talk to the VFS.
+	 */
+	.freeze_fs	= NULL,
+	.unfreeze_fs	= NULL,
+	.freeze_super	= NULL,
+	.thaw_super	= NULL,
+};
+
+static int kernfs_encode_fh(struct inode *inode, __u32 *fh, int *max_len,
+			    struct inode *parent)
+{
+	struct kernfs_node *kn = inode->i_private;
+
+	if (*max_len < 2) {
+		*max_len = 2;
+		return FILEID_INVALID;
+	}
+
+	*max_len = 2;
+	*(u64 *)fh = kn->id;
+	return FILEID_KERNFS;
+}
+
+static struct dentry *__kernfs_fh_to_dentry(struct super_block *sb,
+					    struct fid *fid, int fh_len,
+					    int fh_type, bool get_parent)
+{
+	struct kernfs_super_info *info = kernfs_info(sb);
+	struct kernfs_node *kn;
+	struct inode *inode;
+	u64 id;
+
+	if (fh_len < 2)
+		return NULL;
+
+	switch (fh_type) {
+	case FILEID_KERNFS:
+		id = *(u64 *)fid;
+		break;
+	case FILEID_INO32_GEN:
+	case FILEID_INO32_GEN_PARENT:
+		/*
+		 * blk_log_action() exposes "LOW32,HIGH32" pair without
+		 * type and userland can call us with generic fid
+		 * constructed from them.  Combine it back to ID.  See
+		 * blk_log_action().
+		 */
+		id = ((u64)fid->i32.gen << 32) | fid->i32.ino;
+		break;
+	default:
+		return NULL;
+	}
+
+	kn = kernfs_find_and_get_node_by_id(info->root, id);
+	if (!kn)
+		return ERR_PTR(-ESTALE);
+
+	if (get_parent) {
+		struct kernfs_node *parent;
+
+		parent = kernfs_get_parent(kn);
+		kernfs_put(kn);
+		kn = parent;
+		if (!kn)
+			return ERR_PTR(-ESTALE);
+	}
+
+	inode = kernfs_get_inode(sb, kn);
+	kernfs_put(kn);
+	return d_obtain_alias(inode);
+}
+
+static struct dentry *kernfs_fh_to_dentry(struct super_block *sb,
+					  struct fid *fid, int fh_len,
+					  int fh_type)
+{
+	return __kernfs_fh_to_dentry(sb, fid, fh_len, fh_type, false);
+}
+
+static struct dentry *kernfs_fh_to_parent(struct super_block *sb,
+					  struct fid *fid, int fh_len,
+					  int fh_type)
+{
+	return __kernfs_fh_to_dentry(sb, fid, fh_len, fh_type, true);
+}
+
+static struct dentry *kernfs_get_parent_dentry(struct dentry *child)
+{
+	struct kernfs_node *kn = kernfs_dentry_node(child);
+	struct kernfs_root *root = kernfs_root(kn);
+
+	guard(rwsem_read)(&root->kernfs_rwsem);
+	return d_obtain_alias(kernfs_get_inode(child->d_sb, kernfs_parent(kn)));
+}
+
+static const struct export_operations kernfs_export_ops = {
+	.encode_fh	= kernfs_encode_fh,
+	.fh_to_dentry	= kernfs_fh_to_dentry,
+	.fh_to_parent	= kernfs_fh_to_parent,
+	.get_parent	= kernfs_get_parent_dentry,
 };
 
 /**
  * kernfs_root_from_sb - determine kernfs_root associated with a super_block
  * @sb: the super_block in question
  *
- * Return the kernfs_root associated with @sb.  If @sb is not a kernfs one,
+ * Return: the kernfs_root associated with @sb.  If @sb is not a kernfs one,
  * %NULL is returned.
  */
 struct kernfs_root *kernfs_root_from_sb(struct super_block *sb)
@@ -82,7 +191,7 @@ struct kernfs_root *kernfs_root_from_sb(struct super_block *sb)
  * find the next ancestor in the path down to @child, where @parent was the
  * ancestor whose descendant we want to find.
  *
- * Say the path is /a/b/c/d.  @child is d, @parent is NULL.  We return the root
+ * Say the path is /a/b/c/d.  @child is d, @parent is %NULL.  We return the root
  * node.  If @parent is b, then we return the node for c.
  * Passing in d as @parent is not ok.
  */
@@ -94,10 +203,10 @@ static struct kernfs_node *find_next_ancestor(struct kernfs_node *child,
 		return NULL;
 	}
 
-	while (child->parent != parent) {
-		if (!child->parent)
+	while (kernfs_parent(child) != parent) {
+		child = kernfs_parent(child);
+		if (!child)
 			return NULL;
-		child = child->parent;
 	}
 
 	return child;
@@ -107,37 +216,63 @@ static struct kernfs_node *find_next_ancestor(struct kernfs_node *child,
  * kernfs_node_dentry - get a dentry for the given kernfs_node
  * @kn: kernfs_node for which a dentry is needed
  * @sb: the kernfs super_block
+ *
+ * Return: the dentry pointer
  */
 struct dentry *kernfs_node_dentry(struct kernfs_node *kn,
 				  struct super_block *sb)
 {
 	struct dentry *dentry;
-	struct kernfs_node *knparent = NULL;
+	struct kernfs_node *knparent;
+	struct kernfs_root *root;
 
 	BUG_ON(sb->s_op != &kernfs_sops);
 
 	dentry = dget(sb->s_root);
 
 	/* Check if this is the root kernfs_node */
-	if (!kn->parent)
+	if (!rcu_access_pointer(kn->__parent))
 		return dentry;
 
-	knparent = find_next_ancestor(kn, NULL);
-	if (WARN_ON(!knparent))
+	root = kernfs_root(kn);
+	/*
+	 * As long as kn is valid, its parent can not vanish. This is cgroup's
+	 * kn so it can't have its parent replaced. Therefore it is safe to use
+	 * the ancestor node outside of the RCU or locked section.
+	 */
+	if (WARN_ON_ONCE(!(root->flags & KERNFS_ROOT_INVARIANT_PARENT)))
+		return ERR_PTR(-EINVAL);
+	scoped_guard(rcu) {
+		knparent = find_next_ancestor(kn, NULL);
+	}
+	if (WARN_ON(!knparent)) {
+		dput(dentry);
 		return ERR_PTR(-EINVAL);
+	}
 
 	do {
 		struct dentry *dtmp;
 		struct kernfs_node *kntmp;
+		const char *name;
 
 		if (kn == knparent)
 			return dentry;
-		kntmp = find_next_ancestor(kn, knparent);
-		if (WARN_ON(!kntmp))
-			return ERR_PTR(-EINVAL);
-		dtmp = lookup_one_len_unlocked(kntmp->name, dentry,
-					       strlen(kntmp->name));
+
+		scoped_guard(rwsem_read, &root->kernfs_rwsem) {
+			kntmp = find_next_ancestor(kn, knparent);
+			if (WARN_ON(!kntmp)) {
+				dput(dentry);
+				return ERR_PTR(-EINVAL);
+			}
+			name = kstrdup(kernfs_rcu_name(kntmp), GFP_KERNEL);
+		}
+		if (!name) {
+			dput(dentry);
+			return ERR_PTR(-ENOMEM);
+		}
+		dtmp = lookup_noperm_positive_unlocked(&QSTR(name), dentry);
 		dput(dentry);
+		kfree(name);
 		if (IS_ERR(dtmp))
 			return dtmp;
 		knparent = kntmp;
@@ -145,9 +280,10 @@ struct dentry *kernfs_node_dentry(struct kernfs_node *kn,
 	} while (true);
 }
 
-static int kernfs_fill_super(struct super_block *sb, unsigned long magic)
+static int kernfs_fill_super(struct super_block *sb, struct kernfs_fs_context *kfc)
 {
 	struct kernfs_super_info *info = kernfs_info(sb);
+	struct kernfs_root *kf_root = kfc->root;
 	struct inode *inode;
 	struct dentry *root;
 
@@ -156,15 +292,21 @@ static int kernfs_fill_super(struct super_block *sb, unsigned long magic)
 	sb->s_iflags |= SB_I_NOEXEC | SB_I_NODEV;
 	sb->s_blocksize = PAGE_SIZE;
 	sb->s_blocksize_bits = PAGE_SHIFT;
-	sb->s_magic = magic;
+	sb->s_magic = kfc->magic;
 	sb->s_op = &kernfs_sops;
 	sb->s_xattr = kernfs_xattr_handlers;
+	if (info->root->flags & KERNFS_ROOT_SUPPORT_EXPORTOP)
+		sb->s_export_op = &kernfs_export_ops;
 	sb->s_time_gran = 1;
+	sb->s_maxbytes  = MAX_LFS_FILESIZE;
+
+	/* sysfs dentries and inodes don't require IO to create */
+	sb->s_shrink->seeks = 0;
 
 	/* get root inode, initialize and unlock it */
-	mutex_lock(&kernfs_mutex);
+	down_read(&kf_root->kernfs_rwsem);
 	inode = kernfs_get_inode(sb, info->root->kn);
-	mutex_unlock(&kernfs_mutex);
+	up_read(&kf_root->kernfs_rwsem);
 	if (!inode) {
 		pr_debug("kernfs: could not get root inode\n");
 		return -ENOMEM;
@@ -176,35 +318,32 @@ static int kernfs_fill_super(struct super_block *sb, unsigned long magic)
 		pr_debug("%s: could not get root dentry!\n", __func__);
 		return -ENOMEM;
 	}
-	kernfs_get(info->root->kn);
-	root->d_fsdata = info->root->kn;
 	sb->s_root = root;
-	sb->s_d_op = &kernfs_dops;
+	set_default_d_op(sb, &kernfs_dops);
 	return 0;
 }
 
-static int kernfs_test_super(struct super_block *sb, void *data)
+static int kernfs_test_super(struct super_block *sb, struct fs_context *fc)
 {
 	struct kernfs_super_info *sb_info = kernfs_info(sb);
-	struct kernfs_super_info *info = data;
+	struct kernfs_super_info *info = fc->s_fs_info;
 
 	return sb_info->root == info->root && sb_info->ns == info->ns;
 }
 
-static int kernfs_set_super(struct super_block *sb, void *data)
+static int kernfs_set_super(struct super_block *sb, struct fs_context *fc)
 {
-	int error;
-	error = set_anon_super(sb, data);
-	if (!error)
-		sb->s_fs_info = data;
-	return error;
+	struct kernfs_fs_context *kfc = fc->fs_private;
+
+	kfc->ns_tag = NULL;
+	return set_anon_super_fc(sb, fc);
 }
 
 /**
  * kernfs_super_ns - determine the namespace tag of a kernfs super_block
  * @sb: super_block of interest
  *
- * Return the namespace tag associated with kernfs super_block @sb.
+ * Return: the namespace tag associated with kernfs super_block @sb.
  */
 const void *kernfs_super_ns(struct super_block *sb)
 {
@@ -214,62 +353,67 @@ const void *kernfs_super_ns(struct super_block *sb)
 }
 
 /**
- * kernfs_mount_ns - kernfs mount helper
- * @fs_type: file_system_type of the fs being mounted
- * @flags: mount flags specified for the mount
- * @root: kernfs_root of the hierarchy being mounted
- * @magic: file system specific magic number
- * @new_sb_created: tell the caller if we allocated a new superblock
- * @ns: optional namespace tag of the mount
+ * kernfs_get_tree - kernfs filesystem access/retrieval helper
+ * @fc: The filesystem context.
  *
- * This is to be called from each kernfs user's file_system_type->mount()
- * implementation, which should pass through the specified @fs_type and
- * @flags, and specify the hierarchy and namespace tag to mount via @root
- * and @ns, respectively.
+ * This is to be called from each kernfs user's fs_context->ops->get_tree()
+ * implementation, which should set the specified ->@fs_type and ->@flags, and
+ * specify the hierarchy and namespace tag to mount via ->@root and ->@ns,
+ * respectively.
  *
- * The return value can be passed to the vfs layer verbatim.
+ * Return: %0 on success, -errno on failure.
  */
-struct dentry *kernfs_mount_ns(struct file_system_type *fs_type, int flags,
-				struct kernfs_root *root, unsigned long magic,
-				bool *new_sb_created, const void *ns)
+int kernfs_get_tree(struct fs_context *fc)
 {
+	struct kernfs_fs_context *kfc = fc->fs_private;
 	struct super_block *sb;
 	struct kernfs_super_info *info;
 	int error;
 
 	info = kzalloc(sizeof(*info), GFP_KERNEL);
 	if (!info)
-		return ERR_PTR(-ENOMEM);
+		return -ENOMEM;
 
-	info->root = root;
-	info->ns = ns;
+	info->root = kfc->root;
+	info->ns = kfc->ns_tag;
+	INIT_LIST_HEAD(&info->node);
 
-	sb = sget_userns(fs_type, kernfs_test_super, kernfs_set_super, flags,
-			 &init_user_ns, info);
-	if (IS_ERR(sb) || sb->s_fs_info != info)
-		kfree(info);
+	fc->s_fs_info = info;
+	sb = sget_fc(fc, kernfs_test_super, kernfs_set_super);
 	if (IS_ERR(sb))
-		return ERR_CAST(sb);
-
-	if (new_sb_created)
-		*new_sb_created = !sb->s_root;
+		return PTR_ERR(sb);
 
 	if (!sb->s_root) {
 		struct kernfs_super_info *info = kernfs_info(sb);
+		struct kernfs_root *root = kfc->root;
+
+		kfc->new_sb_created = true;
 
-		error = kernfs_fill_super(sb, magic);
+		error = kernfs_fill_super(sb, kfc);
 		if (error) {
 			deactivate_locked_super(sb);
-			return ERR_PTR(error);
+			return error;
 		}
-		sb->s_flags |= MS_ACTIVE;
+		sb->s_flags |= SB_ACTIVE;
 
-		mutex_lock(&kernfs_mutex);
-		list_add(&info->node, &root->supers);
-		mutex_unlock(&kernfs_mutex);
+		uuid_t uuid;
+		uuid_gen(&uuid);
+		super_set_uuid(sb, uuid.b, sizeof(uuid));
+
+		down_write(&root->kernfs_supers_rwsem);
+		list_add(&info->node, &info->root->supers);
+		up_write(&root->kernfs_supers_rwsem);
 	}
 
-	return dget(sb->s_root);
+	fc->root = dget(sb->s_root);
+	return 0;
+}
+
+void kernfs_free_fs_context(struct fs_context *fc)
+{
+	/* Note that we don't deal with kfc->ns_tag here. */
+	kfree(fc->s_fs_info);
+	fc->s_fs_info = NULL;
 }
 
 /**
@@ -283,11 +427,11 @@ struct dentry *kernfs_mount_ns(struct file_system_type *fs_type, int flags,
 void kernfs_kill_sb(struct super_block *sb)
 {
 	struct kernfs_super_info *info = kernfs_info(sb);
-	struct kernfs_node *root_kn = sb->s_root->d_fsdata;
+	struct kernfs_root *root = info->root;
 
-	mutex_lock(&kernfs_mutex);
+	down_write(&root->kernfs_supers_rwsem);
 	list_del(&info->node);
-	mutex_unlock(&kernfs_mutex);
+	up_write(&root->kernfs_supers_rwsem);
 
 	/*
 	 * Remove the superblock from fs_supers/s_instances
@@ -295,37 +439,22 @@ void kernfs_kill_sb(struct super_block *sb)
 	 */
 	kill_anon_super(sb);
 	kfree(info);
-	kernfs_put(root_kn);
 }
 
-/**
- * kernfs_pin_sb: try to pin the superblock associated with a kernfs_root
- * @kernfs_root: the kernfs_root in question
- * @ns: the namespace tag
- *
- * Pin the superblock so the superblock won't be destroyed in subsequent
- * operations.  This can be used to block ->kill_sb() which may be useful
- * for kernfs users which dynamically manage superblocks.
- *
- * Returns NULL if there's no superblock associated to this kernfs_root, or
- * -EINVAL if the superblock is being freed.
- */
-struct super_block *kernfs_pin_sb(struct kernfs_root *root, const void *ns)
+static void __init kernfs_mutex_init(void)
 {
-	struct kernfs_super_info *info;
-	struct super_block *sb = NULL;
-
-	mutex_lock(&kernfs_mutex);
-	list_for_each_entry(info, &root->supers, node) {
-		if (info->ns == ns) {
-			sb = info->sb;
-			if (!atomic_inc_not_zero(&info->sb->s_active))
-				sb = ERR_PTR(-EINVAL);
-			break;
-		}
-	}
-	mutex_unlock(&kernfs_mutex);
-	return sb;
+	int count;
+
+	for (count = 0; count < NR_KERNFS_LOCKS; count++)
+		mutex_init(&kernfs_locks->open_file_mutex[count]);
+}
+
+static void __init kernfs_lock_init(void)
+{
+	kernfs_locks = kmalloc(sizeof(struct kernfs_global_locks), GFP_KERNEL);
+	WARN_ON(!kernfs_locks);
+
+	kernfs_mutex_init();
 }
 
 void __init kernfs_init(void)
@@ -333,4 +462,11 @@ void __init kernfs_init(void)
 	kernfs_node_cache = kmem_cache_create("kernfs_node_cache",
 					      sizeof(struct kernfs_node),
 					      0, SLAB_PANIC, NULL);
+
+	/* Creates slab cache for kernfs inode attributes */
+	kernfs_iattrs_cache  = kmem_cache_create("kernfs_iattrs_cache",
+					      sizeof(struct kernfs_iattrs),
+					      0, SLAB_PANIC, NULL);
+
+	kernfs_lock_init();
 }