Merging upstream version 6.8.11.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

3 files changed, 125 insertions, 19 deletions

diff --git a/fs/tracefs/event_inode.c b/fs/tracefs/event_inode.c
index 110e8a2721..56d1741fe0 100644
--- a/fs/tracefs/event_inode.c
+++ b/fs/tracefs/event_inode.c
@@ -164,21 +164,7 @@ static int eventfs_set_attr(struct mnt_idmap *idmap, struct dentry *dentry,
 	 * determined by the parent directory.
 	 */
 	if (dentry->d_inode->i_mode & S_IFDIR) {
-		/*
-		 * The events directory dentry is never freed, unless its
-		 * part of an instance that is deleted. It's attr is the
-		 * default for its child files and directories.
-		 * Do not update it. It's not used for its own mode or ownership.
-		 */
-		if (ei->is_events) {
-			/* But it still needs to know if it was modified */
-			if (iattr->ia_valid & ATTR_UID)
-				ei->attr.mode |= EVENTFS_SAVE_UID;
-			if (iattr->ia_valid & ATTR_GID)
-				ei->attr.mode |= EVENTFS_SAVE_GID;
-		} else {
-			update_attr(&ei->attr, iattr);
-		}
+		update_attr(&ei->attr, iattr);
 
 	} else {
 		name = dentry->d_name.name;
@@ -265,6 +251,35 @@ 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)
+{
+	struct eventfs_inode *ei = ti->private;
+
+	if (!ei)
+		return;
+
+	if (update_uid)
+		ei->attr.mode &= ~EVENTFS_SAVE_UID;
+
+	if (update_gid)
+		ei->attr.mode &= ~EVENTFS_SAVE_GID;
+
+	if (!ei->entry_attrs)
+		return;
+
+	for (int i = 0; i < ei->nr_entries; i++) {
+		if (update_uid)
+			ei->entry_attrs[i].mode &= ~EVENTFS_SAVE_UID;
+		if (update_gid)
+			ei->entry_attrs[i].mode &= ~EVENTFS_SAVE_GID;
+	}
+}
+
 /* Return the evenfs_inode of the "events" directory */
 static struct eventfs_inode *eventfs_find_events(struct dentry *dentry)
 {
diff --git a/fs/tracefs/inode.c b/fs/tracefs/inode.c
index d65ffad4c3..e30b74228e 100644
--- a/fs/tracefs/inode.c
+++ b/fs/tracefs/inode.c
@@ -30,20 +30,47 @@ static struct vfsmount *tracefs_mount;
 static int tracefs_mount_count;
 static bool tracefs_registered;
 
+/*
+ * Keep track of all tracefs_inodes in order to update their
+ * flags if necessary on a remount.
+ */
+static DEFINE_SPINLOCK(tracefs_inode_lock);
+static LIST_HEAD(tracefs_inodes);
+
 static struct inode *tracefs_alloc_inode(struct super_block *sb)
 {
 	struct tracefs_inode *ti;
+	unsigned long flags;
 
 	ti = kmem_cache_alloc(tracefs_inode_cachep, GFP_KERNEL);
 	if (!ti)
 		return NULL;
 
+	spin_lock_irqsave(&tracefs_inode_lock, flags);
+	list_add_rcu(&ti->list, &tracefs_inodes);
+	spin_unlock_irqrestore(&tracefs_inode_lock, flags);
+
 	return &ti->vfs_inode;
 }
 
+static void tracefs_free_inode_rcu(struct rcu_head *rcu)
+{
+	struct tracefs_inode *ti;
+
+	ti = container_of(rcu, struct tracefs_inode, rcu);
+	kmem_cache_free(tracefs_inode_cachep, ti);
+}
+
 static void tracefs_free_inode(struct inode *inode)
 {
-	kmem_cache_free(tracefs_inode_cachep, get_tracefs(inode));
+	struct tracefs_inode *ti = get_tracefs(inode);
+	unsigned long flags;
+
+	spin_lock_irqsave(&tracefs_inode_lock, flags);
+	list_del_rcu(&ti->list);
+	spin_unlock_irqrestore(&tracefs_inode_lock, flags);
+
+	call_rcu(&ti->rcu, tracefs_free_inode_rcu);
 }
 
 static ssize_t default_read_file(struct file *file, char __user *buf,
@@ -153,16 +180,39 @@ static void set_tracefs_inode_owner(struct inode *inode)
 {
 	struct tracefs_inode *ti = get_tracefs(inode);
 	struct inode *root_inode = ti->private;
+	kuid_t uid;
+	kgid_t gid;
+
+	uid = root_inode->i_uid;
+	gid = root_inode->i_gid;
+
+	/*
+	 * If the root is not the mount point, then check the root's
+	 * permissions. If it was never set, then default to the
+	 * mount point.
+	 */
+	if (root_inode != d_inode(root_inode->i_sb->s_root)) {
+		struct tracefs_inode *rti;
+
+		rti = get_tracefs(root_inode);
+		root_inode = d_inode(root_inode->i_sb->s_root);
+
+		if (!(rti->flags & TRACEFS_UID_PERM_SET))
+			uid = root_inode->i_uid;
+
+		if (!(rti->flags & TRACEFS_GID_PERM_SET))
+			gid = root_inode->i_gid;
+	}
 
 	/*
 	 * If this inode has never been referenced, then update
 	 * the permissions to the superblock.
 	 */
 	if (!(ti->flags & TRACEFS_UID_PERM_SET))
-		inode->i_uid = root_inode->i_uid;
+		inode->i_uid = uid;
 
 	if (!(ti->flags & TRACEFS_GID_PERM_SET))
-		inode->i_gid = root_inode->i_gid;
+		inode->i_gid = gid;
 }
 
 static int tracefs_permission(struct mnt_idmap *idmap,
@@ -313,6 +363,8 @@ static int tracefs_apply_options(struct super_block *sb, bool remount)
 	struct tracefs_fs_info *fsi = sb->s_fs_info;
 	struct inode *inode = d_inode(sb->s_root);
 	struct tracefs_mount_opts *opts = &fsi->mount_opts;
+	struct tracefs_inode *ti;
+	bool update_uid, update_gid;
 	umode_t tmp_mode;
 
 	/*
@@ -332,6 +384,25 @@ static int tracefs_apply_options(struct super_block *sb, bool remount)
 	if (!remount || opts->opts & BIT(Opt_gid))
 		inode->i_gid = opts->gid;
 
+	if (remount && (opts->opts & BIT(Opt_uid) || opts->opts & BIT(Opt_gid))) {
+
+		update_uid = opts->opts & BIT(Opt_uid);
+		update_gid = opts->opts & BIT(Opt_gid);
+
+		rcu_read_lock();
+		list_for_each_entry_rcu(ti, &tracefs_inodes, list) {
+			if (update_uid)
+				ti->flags &= ~TRACEFS_UID_PERM_SET;
+
+			if (update_gid)
+				ti->flags &= ~TRACEFS_GID_PERM_SET;
+
+			if (ti->flags & TRACEFS_EVENT_INODE)
+				eventfs_remount(ti, update_uid, update_gid);
+		}
+		rcu_read_unlock();
+	}
+
 	return 0;
 }
 
@@ -398,7 +469,22 @@ 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,
 };
diff --git a/fs/tracefs/internal.h b/fs/tracefs/internal.h
index beb3dcd0e4..824cbe8367 100644
--- a/fs/tracefs/internal.h
+++ b/fs/tracefs/internal.h
@@ -11,8 +11,12 @@ enum {
 };
 
 struct tracefs_inode {
-	struct inode            vfs_inode;
+	union {
+		struct inode            vfs_inode;
+		struct rcu_head		rcu;
+	};
 	/* The below gets initialized with memset_after(ti, 0, vfs_inode) */
+	struct list_head	list;
 	unsigned long           flags;
 	void                    *private;
 };
@@ -75,6 +79,7 @@ struct dentry *tracefs_end_creating(struct dentry *dentry);
 struct dentry *tracefs_failed_creating(struct dentry *dentry);
 struct inode *tracefs_get_inode(struct super_block *sb);
 
+void eventfs_remount(struct tracefs_inode *ti, bool update_uid, bool update_gid);
 void eventfs_d_release(struct dentry *dentry);
 
 #endif /* _TRACEFS_INTERNAL_H */