1 files changed, 48 insertions, 17 deletions

diff --git a/fs/inode.c b/fs/inode.c
index 524ee91f74a6..b608528efd3a 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -192,8 +192,6 @@ int inode_init_always(struct super_block *sb, struct inode *inode)
 	inode->i_wb_frn_history = 0;
 #endif
 
-	if (security_inode_alloc(inode))
-		goto out;
 	spin_lock_init(&inode->i_lock);
 	lockdep_set_class(&inode->i_lock, &sb->s_type->i_lock_key);
 
@@ -228,11 +226,12 @@ int inode_init_always(struct super_block *sb, struct inode *inode)
 	inode->i_fsnotify_mask = 0;
 #endif
 	inode->i_flctx = NULL;
+
+	if (unlikely(security_inode_alloc(inode)))
+		return -ENOMEM;
 	this_cpu_inc(nr_inodes);
 
 	return 0;
-out:
-	return -ENOMEM;
 }
 EXPORT_SYMBOL(inode_init_always);
 
@@ -422,6 +421,7 @@ void inode_init_once(struct inode *inode)
 	INIT_LIST_HEAD(&inode->i_io_list);
 	INIT_LIST_HEAD(&inode->i_wb_list);
 	INIT_LIST_HEAD(&inode->i_lru);
+	INIT_LIST_HEAD(&inode->i_sb_list);
 	__address_space_init_once(&inode->i_data);
 	i_size_ordered_init(inode);
 }
@@ -1021,7 +1021,6 @@ struct inode *new_inode_pseudo(struct super_block *sb)
 		spin_lock(&inode->i_lock);
 		inode->i_state = 0;
 		spin_unlock(&inode->i_lock);
-		INIT_LIST_HEAD(&inode->i_sb_list);
 	}
 	return inode;
 }
@@ -1165,7 +1164,6 @@ struct inode *inode_insert5(struct inode *inode, unsigned long hashval,
 {
 	struct hlist_head *head = inode_hashtable + hash(inode->i_sb, hashval);
 	struct inode *old;
-	bool creating = inode->i_state & I_CREATING;
 
 again:
 	spin_lock(&inode_hash_lock);
@@ -1199,7 +1197,12 @@ again:
 	inode->i_state |= I_NEW;
 	hlist_add_head_rcu(&inode->i_hash, head);
 	spin_unlock(&inode->i_lock);
-	if (!creating)
+
+	/*
+	 * Add inode to the sb list if it's not already. It has I_NEW at this
+	 * point, so it should be safe to test i_sb_list locklessly.
+	 */
+	if (list_empty(&inode->i_sb_list))
 		inode_sb_list_add(inode);
 unlock:
 	spin_unlock(&inode_hash_lock);
@@ -2014,23 +2017,25 @@ static int __file_remove_privs(struct file *file, unsigned int flags)
 {
 	struct dentry *dentry = file_dentry(file);
 	struct inode *inode = file_inode(file);
-	int error;
+	int error = 0;
 	int kill;
 
 	if (IS_NOSEC(inode) || !S_ISREG(inode->i_mode))
 		return 0;
 
 	kill = dentry_needs_remove_privs(dentry);
-	if (kill <= 0)
+	if (kill < 0)
 		return kill;
 
-	if (flags & IOCB_NOWAIT)
-		return -EAGAIN;
+	if (kill) {
+		if (flags & IOCB_NOWAIT)
+			return -EAGAIN;
+
+		error = __remove_privs(file_mnt_user_ns(file), dentry, kill);
+	}
 
-	error = __remove_privs(file_mnt_user_ns(file), dentry, kill);
 	if (!error)
 		inode_has_no_xattr(inode);
-
 	return error;
 }
 
@@ -2326,10 +2331,6 @@ void inode_init_owner(struct user_namespace *mnt_userns, struct inode *inode,
 		/* Directories are special, and always inherit S_ISGID */
 		if (S_ISDIR(mode))
 			mode |= S_ISGID;
-		else if ((mode & (S_ISGID | S_IXGRP)) == (S_ISGID | S_IXGRP) &&
-			 !in_group_p(i_gid_into_mnt(mnt_userns, dir)) &&
-			 !capable_wrt_inode_uidgid(mnt_userns, dir, CAP_FSETID))
-			mode &= ~S_ISGID;
 	} else
 		inode_fsgid_set(inode, mnt_userns);
 	inode->i_mode = mode;
@@ -2485,3 +2486,33 @@ struct timespec64 current_time(struct inode *inode)
 	return timestamp_truncate(now, inode);
 }
 EXPORT_SYMBOL(current_time);
+
+/**
+ * mode_strip_sgid - handle the sgid bit for non-directories
+ * @mnt_userns: User namespace of the mount the inode was created from
+ * @dir: parent directory inode
+ * @mode: mode of the file to be created in @dir
+ *
+ * If the @mode of the new file has both the S_ISGID and S_IXGRP bit
+ * raised and @dir has the S_ISGID bit raised ensure that the caller is
+ * either in the group of the parent directory or they have CAP_FSETID
+ * in their user namespace and are privileged over the parent directory.
+ * In all other cases, strip the S_ISGID bit from @mode.
+ *
+ * Return: the new mode to use for the file
+ */
+umode_t mode_strip_sgid(struct user_namespace *mnt_userns,
+			const struct inode *dir, umode_t mode)
+{
+	if ((mode & (S_ISGID | S_IXGRP)) != (S_ISGID | S_IXGRP))
+		return mode;
+	if (S_ISDIR(mode) || !dir || !(dir->i_mode & S_ISGID))
+		return mode;
+	if (in_group_p(i_gid_into_mnt(mnt_userns, dir)))
+		return mode;
+	if (capable_wrt_inode_uidgid(mnt_userns, dir, CAP_FSETID))
+		return mode;
+
+	return mode & ~S_ISGID;
+}
+EXPORT_SYMBOL(mode_strip_sgid);