3 files changed, 196 insertions, 86 deletions

diff --git a/fs/tracefs/event_inode.c b/fs/tracefs/event_inode.c
index 56d1741fe0..129d0f54ba 100644
--- a/fs/tracefs/event_inode.c
+++ b/fs/tracefs/event_inode.c
@@ -35,11 +35,27 @@ static DEFINE_MUTEX(eventfs_mutex);
 /* Choose something "unique" ;-) */
 #define EVENTFS_FILE_INODE_INO		0x12c4e37
 
+struct eventfs_root_inode {
+	struct eventfs_inode		ei;
+	struct inode			*parent_inode;
+	struct dentry			*events_dir;
+};
+
+static struct eventfs_root_inode *get_root_inode(struct eventfs_inode *ei)
+{
+	WARN_ON_ONCE(!ei->is_events);
+	return container_of(ei, struct eventfs_root_inode, ei);
+}
+
 /* Just try to make something consistent and unique */
 static int eventfs_dir_ino(struct eventfs_inode *ei)
 {
-	if (!ei->ino)
+	if (!ei->ino) {
 		ei->ino = get_next_ino();
+		/* Must not have the file inode number */
+		if (ei->ino == EVENTFS_FILE_INODE_INO)
+			ei->ino = get_next_ino();
+	}
 
 	return ei->ino;
 }
@@ -57,11 +73,25 @@ enum {
 	EVENTFS_SAVE_MODE	= BIT(16),
 	EVENTFS_SAVE_UID	= BIT(17),
 	EVENTFS_SAVE_GID	= BIT(18),
-	EVENTFS_TOPLEVEL	= BIT(19),
 };
 
 #define EVENTFS_MODE_MASK	(EVENTFS_SAVE_MODE - 1)
 
+static void free_ei_rcu(struct rcu_head *rcu)
+{
+	struct eventfs_inode *ei = container_of(rcu, struct eventfs_inode, rcu);
+	struct eventfs_root_inode *rei;
+
+	kfree(ei->entry_attrs);
+	kfree_const(ei->name);
+	if (ei->is_events) {
+		rei = get_root_inode(ei);
+		kfree(rei);
+	} else {
+		kfree(ei);
+	}
+}
+
 /*
  * eventfs_inode reference count management.
  *
@@ -73,12 +103,17 @@ enum {
 static void release_ei(struct kref *ref)
 {
 	struct eventfs_inode *ei = container_of(ref, struct eventfs_inode, kref);
+	const struct eventfs_entry *entry;
 
 	WARN_ON_ONCE(!ei->is_freed);
 
-	kfree(ei->entry_attrs);
-	kfree_const(ei->name);
-	kfree_rcu(ei, rcu);
+	for (int i = 0; i < ei->nr_entries; i++) {
+		entry = &ei->entries[i];
+		if (entry->release)
+			entry->release(entry->name, ei->data);
+	}
+
+	call_rcu(&ei->rcu, free_ei_rcu);
 }
 
 static inline void put_ei(struct eventfs_inode *ei)
@@ -95,6 +130,18 @@ static inline void free_ei(struct eventfs_inode *ei)
 	}
 }
 
+/*
+ * Called when creation of an ei fails, do not call release() functions.
+ */
+static inline void cleanup_ei(struct eventfs_inode *ei)
+{
+	if (ei) {
+		/* Set nr_entries to 0 to prevent release() function being called */
+		ei->nr_entries = 0;
+		free_ei(ei);
+	}
+}
+
 static inline struct eventfs_inode *get_ei(struct eventfs_inode *ei)
 {
 	if (ei)
@@ -182,18 +229,25 @@ static int eventfs_set_attr(struct mnt_idmap *idmap, struct dentry *dentry,
 	return ret;
 }
 
-static void update_top_events_attr(struct eventfs_inode *ei, struct super_block *sb)
+static void update_events_attr(struct eventfs_inode *ei, struct super_block *sb)
 {
-	struct inode *root;
+	struct eventfs_root_inode *rei;
+	struct inode *parent;
 
-	/* Only update if the "events" was on the top level */
-	if (!ei || !(ei->attr.mode & EVENTFS_TOPLEVEL))
-		return;
+	rei = get_root_inode(ei);
+
+	/* Use the parent inode permissions unless root set its permissions */
+	parent = rei->parent_inode;
+
+	if (rei->ei.attr.mode & EVENTFS_SAVE_UID)
+		ei->attr.uid = rei->ei.attr.uid;
+	else
+		ei->attr.uid = parent->i_uid;
 
-	/* Get the tracefs root inode. */
-	root = d_inode(sb->s_root);
-	ei->attr.uid = root->i_uid;
-	ei->attr.gid = root->i_gid;
+	if (rei->ei.attr.mode & EVENTFS_SAVE_GID)
+		ei->attr.gid = rei->ei.attr.gid;
+	else
+		ei->attr.gid = parent->i_gid;
 }
 
 static void set_top_events_ownership(struct inode *inode)
@@ -202,10 +256,10 @@ static void set_top_events_ownership(struct inode *inode)
 	struct eventfs_inode *ei = ti->private;
 
 	/* The top events directory doesn't get automatically updated */
-	if (!ei || !ei->is_events || !(ei->attr.mode & EVENTFS_TOPLEVEL))
+	if (!ei || !ei->is_events)
 		return;
 
-	update_top_events_attr(ei, inode->i_sb);
+	update_events_attr(ei, inode->i_sb);
 
 	if (!(ei->attr.mode & EVENTFS_SAVE_UID))
 		inode->i_uid = ei->attr.uid;
@@ -234,7 +288,7 @@ static int eventfs_permission(struct mnt_idmap *idmap,
 	return generic_permission(idmap, inode, mask);
 }
 
-static const struct inode_operations eventfs_root_dir_inode_operations = {
+static const struct inode_operations eventfs_dir_inode_operations = {
 	.lookup		= eventfs_root_lookup,
 	.setattr	= eventfs_set_attr,
 	.getattr	= eventfs_get_attr,
@@ -251,33 +305,60 @@ static const struct file_operations eventfs_file_operations = {
 	.llseek		= generic_file_llseek,
 };
 
-/*
- * On a remount of tracefs, if UID or GID options are set, then
- * the mount point inode permissions should be used.
- * Reset the saved permission flags appropriately.
- */
-void eventfs_remount(struct tracefs_inode *ti, bool update_uid, bool update_gid)
+static void eventfs_set_attrs(struct eventfs_inode *ei, bool update_uid, kuid_t uid,
+			      bool update_gid, kgid_t gid, int level)
 {
-	struct eventfs_inode *ei = ti->private;
+	struct eventfs_inode *ei_child;
 
-	if (!ei)
+	/* Update events/<system>/<event> */
+	if (WARN_ON_ONCE(level > 3))
 		return;
 
-	if (update_uid)
+	if (update_uid) {
 		ei->attr.mode &= ~EVENTFS_SAVE_UID;
+		ei->attr.uid = uid;
+	}
 
-	if (update_gid)
+	if (update_gid) {
 		ei->attr.mode &= ~EVENTFS_SAVE_GID;
+		ei->attr.gid = gid;
+	}
+
+	list_for_each_entry(ei_child, &ei->children, list) {
+		eventfs_set_attrs(ei_child, update_uid, uid, update_gid, gid, level + 1);
+	}
 
 	if (!ei->entry_attrs)
 		return;
 
 	for (int i = 0; i < ei->nr_entries; i++) {
-		if (update_uid)
+		if (update_uid) {
 			ei->entry_attrs[i].mode &= ~EVENTFS_SAVE_UID;
-		if (update_gid)
+			ei->entry_attrs[i].uid = uid;
+		}
+		if (update_gid) {
 			ei->entry_attrs[i].mode &= ~EVENTFS_SAVE_GID;
+			ei->entry_attrs[i].gid = gid;
+		}
 	}
+
+}
+
+/*
+ * On a remount of tracefs, if UID or GID options are set, then
+ * the mount point inode permissions should be used.
+ * Reset the saved permission flags appropriately.
+ */
+void eventfs_remount(struct tracefs_inode *ti, bool update_uid, bool update_gid)
+{
+	struct eventfs_inode *ei = ti->private;
+
+	/* Only the events directory does the updates */
+	if (!ei || !ei->is_events || ei->is_freed)
+		return;
+
+	eventfs_set_attrs(ei, update_uid, ti->vfs_inode.i_uid,
+			  update_gid, ti->vfs_inode.i_gid, 0);
 }
 
 /* Return the evenfs_inode of the "events" directory */
@@ -295,14 +376,13 @@ static struct eventfs_inode *eventfs_find_events(struct dentry *dentry)
 		 * If the ei is being freed, the ownership of the children
 		 * doesn't matter.
 		 */
-		if (ei->is_freed) {
-			ei = NULL;
-			break;
-		}
+		if (ei->is_freed)
+			return NULL;
+
 		// Walk upwards until you find the events inode
 	} while (!ei->is_events);
 
-	update_top_events_attr(ei, dentry->d_sb);
+	update_events_attr(ei, dentry->d_sb);
 
 	return ei;
 }
@@ -334,6 +414,7 @@ static void update_inode_attr(struct dentry *dentry, struct inode *inode,
 
 /**
  * lookup_file - look up a file in the tracefs filesystem
+ * @parent_ei: Pointer to the eventfs_inode that represents parent of the file
  * @dentry: the dentry to look up
  * @mode: the permission that the file should have.
  * @attr: saved attributes changed by user
@@ -387,6 +468,7 @@ static struct dentry *lookup_file(struct eventfs_inode *parent_ei,
 /**
  * lookup_dir_entry - look up a dir in the tracefs filesystem
  * @dentry: the directory to look up
+ * @pei: Pointer to the parent eventfs_inode if available
  * @ei: the eventfs_inode that represents the directory to create
  *
  * This function will look up a dentry for a directory represented by
@@ -406,7 +488,7 @@ static struct dentry *lookup_dir_entry(struct dentry *dentry,
 	update_inode_attr(dentry, inode, &ei->attr,
 			  S_IFDIR | S_IRWXU | S_IRUGO | S_IXUGO);
 
-	inode->i_op = &eventfs_root_dir_inode_operations;
+	inode->i_op = &eventfs_dir_inode_operations;
 	inode->i_fop = &eventfs_file_operations;
 
 	/* All directories will have the same inode number */
@@ -423,19 +505,43 @@ static struct dentry *lookup_dir_entry(struct dentry *dentry,
 	return NULL;
 }
 
+static inline struct eventfs_inode *init_ei(struct eventfs_inode *ei, const char *name)
+{
+	ei->name = kstrdup_const(name, GFP_KERNEL);
+	if (!ei->name)
+		return NULL;
+	kref_init(&ei->kref);
+	return ei;
+}
+
 static inline struct eventfs_inode *alloc_ei(const char *name)
 {
 	struct eventfs_inode *ei = kzalloc(sizeof(*ei), GFP_KERNEL);
+	struct eventfs_inode *result;
 
 	if (!ei)
 		return NULL;
 
-	ei->name = kstrdup_const(name, GFP_KERNEL);
-	if (!ei->name) {
+	result = init_ei(ei, name);
+	if (!result)
 		kfree(ei);
+
+	return result;
+}
+
+static inline struct eventfs_inode *alloc_root_ei(const char *name)
+{
+	struct eventfs_root_inode *rei = kzalloc(sizeof(*rei), GFP_KERNEL);
+	struct eventfs_inode *ei;
+
+	if (!rei)
 		return NULL;
-	}
-	kref_init(&ei->kref);
+
+	rei->ei.is_events = 1;
+	ei = init_ei(&rei->ei, name);
+	if (!ei)
+		kfree(rei);
+
 	return ei;
 }
 
@@ -452,16 +558,20 @@ void eventfs_d_release(struct dentry *dentry)
 
 /**
  * lookup_file_dentry - create a dentry for a file of an eventfs_inode
+ * @dentry: The parent dentry under which the new file's dentry will be created
  * @ei: the eventfs_inode that the file will be created under
  * @idx: the index into the entry_attrs[] of the @ei
- * @parent: The parent dentry of the created file.
- * @name: The name of the file to create
  * @mode: The mode of the file.
  * @data: The data to use to set the inode of the file with on open()
  * @fops: The fops of the file to be created.
  *
- * Create a dentry for a file of an eventfs_inode @ei and place it into the
- * address located at @e_dentry.
+ * This function creates a dentry for a file associated with an
+ * eventfs_inode @ei. It uses the entry attributes specified by @idx,
+ * if available. The file will have the specified @mode and its inode will be
+ * set up with @data upon open. The file operations will be set to @fops.
+ *
+ * Return: Returns a pointer to the newly created file's dentry or an error
+ * pointer.
  */
 static struct dentry *
 lookup_file_dentry(struct dentry *dentry,
@@ -498,7 +608,7 @@ static struct dentry *eventfs_root_lookup(struct inode *dir,
 	struct dentry *result = NULL;
 
 	ti = get_tracefs(dir);
-	if (!(ti->flags & TRACEFS_EVENT_INODE))
+	if (WARN_ON_ONCE(!(ti->flags & TRACEFS_EVENT_INODE)))
 		return ERR_PTR(-EIO);
 
 	mutex_lock(&eventfs_mutex);
@@ -510,7 +620,8 @@ static struct dentry *eventfs_root_lookup(struct inode *dir,
 	list_for_each_entry(ei_child, &ei->children, list) {
 		if (strcmp(ei_child->name, name) != 0)
 			continue;
-		if (ei_child->is_freed)
+		/* A child is freed and removed from the list at the same time */
+		if (WARN_ON_ONCE(ei_child->is_freed))
 			goto out;
 		result = lookup_dir_entry(dentry, ei, ei_child);
 		goto out;
@@ -701,7 +812,7 @@ struct eventfs_inode *eventfs_create_dir(const char *name, struct eventfs_inode
 
 	/* Was the parent freed? */
 	if (list_empty(&ei->list)) {
-		free_ei(ei);
+		cleanup_ei(ei);
 		ei = NULL;
 	}
 	return ei;
@@ -724,6 +835,7 @@ struct eventfs_inode *eventfs_create_events_dir(const char *name, struct dentry
 						int size, void *data)
 {
 	struct dentry *dentry = tracefs_start_creating(name, parent);
+	struct eventfs_root_inode *rei;
 	struct eventfs_inode *ei;
 	struct tracefs_inode *ti;
 	struct inode *inode;
@@ -736,7 +848,7 @@ struct eventfs_inode *eventfs_create_events_dir(const char *name, struct dentry
 	if (IS_ERR(dentry))
 		return ERR_CAST(dentry);
 
-	ei = alloc_ei(name);
+	ei = alloc_root_ei(name);
 	if (!ei)
 		goto fail;
 
@@ -745,39 +857,38 @@ struct eventfs_inode *eventfs_create_events_dir(const char *name, struct dentry
 		goto fail;
 
 	// Note: we have a ref to the dentry from tracefs_start_creating()
-	ei->events_dir = dentry;
+	rei = get_root_inode(ei);
+	rei->events_dir = dentry;
+	rei->parent_inode = d_inode(dentry->d_sb->s_root);
+
 	ei->entries = entries;
 	ei->nr_entries = size;
-	ei->is_events = 1;
 	ei->data = data;
 
 	/* Save the ownership of this directory */
 	uid = d_inode(dentry->d_parent)->i_uid;
 	gid = d_inode(dentry->d_parent)->i_gid;
 
-	/*
-	 * If the events directory is of the top instance, then parent
-	 * is NULL. Set the attr.mode to reflect this and its permissions will
-	 * default to the tracefs root dentry.
-	 */
-	if (!parent)
-		ei->attr.mode = EVENTFS_TOPLEVEL;
-
-	/* This is used as the default ownership of the files and directories */
 	ei->attr.uid = uid;
 	ei->attr.gid = gid;
 
+	/*
+	 * When the "events" directory is created, it takes on the
+	 * permissions of its parent. But can be reset on remount.
+	 */
+	ei->attr.mode |= EVENTFS_SAVE_UID | EVENTFS_SAVE_GID;
+
 	INIT_LIST_HEAD(&ei->children);
 	INIT_LIST_HEAD(&ei->list);
 
 	ti = get_tracefs(inode);
-	ti->flags |= TRACEFS_EVENT_INODE | TRACEFS_EVENT_TOP_INODE;
+	ti->flags |= TRACEFS_EVENT_INODE;
 	ti->private = ei;
 
 	inode->i_mode = S_IFDIR | S_IRWXU | S_IRUGO | S_IXUGO;
 	inode->i_uid = uid;
 	inode->i_gid = gid;
-	inode->i_op = &eventfs_root_dir_inode_operations;
+	inode->i_op = &eventfs_dir_inode_operations;
 	inode->i_fop = &eventfs_file_operations;
 
 	dentry->d_fsdata = get_ei(ei);
@@ -800,7 +911,7 @@ struct eventfs_inode *eventfs_create_events_dir(const char *name, struct dentry
 	return ei;
 
  fail:
-	free_ei(ei);
+	cleanup_ei(ei);
 	tracefs_failed_creating(dentry);
 	return ERR_PTR(-ENOMEM);
 }
@@ -859,13 +970,15 @@ void eventfs_remove_dir(struct eventfs_inode *ei)
  */
 void eventfs_remove_events_dir(struct eventfs_inode *ei)
 {
+	struct eventfs_root_inode *rei;
 	struct dentry *dentry;
 
-	dentry = ei->events_dir;
+	rei = get_root_inode(ei);
+	dentry = rei->events_dir;
 	if (!dentry)
 		return;
 
-	ei->events_dir = NULL;
+	rei->events_dir = NULL;
 	eventfs_remove_dir(ei);
 
 	/*
diff --git a/fs/tracefs/inode.c b/fs/tracefs/inode.c
index e30b74228e..d8c60c2b76 100644
--- a/fs/tracefs/inode.c
+++ b/fs/tracefs/inode.c
@@ -439,10 +439,26 @@ static int tracefs_show_options(struct seq_file *m, struct dentry *root)
 	return 0;
 }
 
+static int tracefs_drop_inode(struct inode *inode)
+{
+	struct tracefs_inode *ti = get_tracefs(inode);
+
+	/*
+	 * This inode is being freed and cannot be used for
+	 * eventfs. Clear the flag so that it doesn't call into
+	 * eventfs during the remount flag updates. The eventfs_inode
+	 * gets freed after an RCU cycle, so the content will still
+	 * be safe if the iteration is going on now.
+	 */
+	ti->flags &= ~TRACEFS_EVENT_INODE;
+
+	return 1;
+}
+
 static const struct super_operations tracefs_super_operations = {
 	.alloc_inode    = tracefs_alloc_inode,
 	.free_inode     = tracefs_free_inode,
-	.drop_inode     = generic_delete_inode,
+	.drop_inode     = tracefs_drop_inode,
 	.statfs		= simple_statfs,
 	.remount_fs	= tracefs_remount,
 	.show_options	= tracefs_show_options,
@@ -469,22 +485,7 @@ static int tracefs_d_revalidate(struct dentry *dentry, unsigned int flags)
 	return !(ei && ei->is_freed);
 }
 
-static void tracefs_d_iput(struct dentry *dentry, struct inode *inode)
-{
-	struct tracefs_inode *ti = get_tracefs(inode);
-
-	/*
-	 * This inode is being freed and cannot be used for
-	 * eventfs. Clear the flag so that it doesn't call into
-	 * eventfs during the remount flag updates. The eventfs_inode
-	 * gets freed after an RCU cycle, so the content will still
-	 * be safe if the iteration is going on now.
-	 */
-	ti->flags &= ~TRACEFS_EVENT_INODE;
-}
-
 static const struct dentry_operations tracefs_dentry_operations = {
-	.d_iput = tracefs_d_iput,
 	.d_revalidate = tracefs_d_revalidate,
 	.d_release = tracefs_d_release,
 };
@@ -817,7 +818,6 @@ static int __init tracefs_init(void)
 	tracefs_inode_cachep = kmem_cache_create("tracefs_inode_cache",
 						 sizeof(struct tracefs_inode),
 						 0, (SLAB_RECLAIM_ACCOUNT|
-						     SLAB_MEM_SPREAD|
 						     SLAB_ACCOUNT),
 						 init_once);
 	if (!tracefs_inode_cachep)
diff --git a/fs/tracefs/internal.h b/fs/tracefs/internal.h
index 824cbe8367..f704d83483 100644
--- a/fs/tracefs/internal.h
+++ b/fs/tracefs/internal.h
@@ -4,10 +4,9 @@
 
 enum {
 	TRACEFS_EVENT_INODE		= BIT(1),
-	TRACEFS_EVENT_TOP_INODE		= BIT(2),
-	TRACEFS_GID_PERM_SET		= BIT(3),
-	TRACEFS_UID_PERM_SET		= BIT(4),
-	TRACEFS_INSTANCE_INODE		= BIT(5),
+	TRACEFS_GID_PERM_SET		= BIT(2),
+	TRACEFS_UID_PERM_SET		= BIT(3),
+	TRACEFS_INSTANCE_INODE		= BIT(4),
 };
 
 struct tracefs_inode {
@@ -40,7 +39,6 @@ struct eventfs_attr {
  * @children:	link list into the child eventfs_inode
  * @entries:	the array of entries representing the files in the directory
  * @name:	the name of the directory to create
- * @events_dir: the dentry of the events directory
  * @entry_attrs: Saved mode and ownership of the @d_children
  * @data:	The private data to pass to the callbacks
  * @attr:	Saved mode and ownership of eventfs_inode itself
@@ -58,7 +56,6 @@ struct eventfs_inode {
 	struct list_head		children;
 	const struct eventfs_entry	*entries;
 	const char			*name;
-	struct dentry			*events_dir;
 	struct eventfs_attr		*entry_attrs;
 	void				*data;
 	struct eventfs_attr		attr;