namei: make permission helpers idmapped mount aware

The two helpers inode_permission() and generic_permission() are used by
the vfs to perform basic permission checking by verifying that the
caller is privileged over an inode. In order to handle idmapped mounts
we extend the two helpers with an additional user namespace argument.
On idmapped mounts the two helpers will make sure to map the inode
according to the mount's user namespace and then peform identical
permission checks to inode_permission() and generic_permission(). If the
initial user namespace is passed nothing changes so non-idmapped mounts
will see identical behavior as before.

Link: https://lore.kernel.org/r/20210121131959.646623-6-christian.brauner@ubuntu.com
Cc: Christoph Hellwig <hch@lst.de>
Cc: David Howells <dhowells@redhat.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: linux-fsdevel@vger.kernel.org
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: James Morris <jamorris@linux.microsoft.com>
Acked-by: Serge Hallyn <serge@hallyn.com>
Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com>

1 files changed, 86 insertions, 35 deletions

diff --git a/fs/namei.c b/fs/namei.c
index fd4724bce4f5..d78d74f5f5af 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -259,7 +259,24 @@ void putname(struct filename *name)
 		__putname(name);
 }
 
-static int check_acl(struct inode *inode, int mask)
+/**
+ * check_acl - perform ACL permission checking
+ * @mnt_userns:	user namespace of the mount the inode was found from
+ * @inode:	inode to check permissions on
+ * @mask:	right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC ...)
+ *
+ * This function performs the ACL permission checking. Since this function
+ * retrieve POSIX acls it needs to know whether it is called from a blocking or
+ * non-blocking context and thus cares about the MAY_NOT_BLOCK bit.
+ *
+ * If the inode has been found through an idmapped mount the user namespace of
+ * the vfsmount must be passed through @mnt_userns. This function will then take
+ * care to map the inode according to @mnt_userns before checking permissions.
+ * On non-idmapped mounts or if permission checking is to be performed on the
+ * raw inode simply passs init_user_ns.
+ */
+static int check_acl(struct user_namespace *mnt_userns,
+		     struct inode *inode, int mask)
 {
 #ifdef CONFIG_FS_POSIX_ACL
 	struct posix_acl *acl;
@@ -271,14 +288,14 @@ static int check_acl(struct inode *inode, int mask)
 		/* no ->get_acl() calls in RCU mode... */
 		if (is_uncached_acl(acl))
 			return -ECHILD;
-	        return posix_acl_permission(inode, acl, mask);
+	        return posix_acl_permission(mnt_userns, inode, acl, mask);
 	}
 
 	acl = get_acl(inode, ACL_TYPE_ACCESS);
 	if (IS_ERR(acl))
 		return PTR_ERR(acl);
 	if (acl) {
-	        int error = posix_acl_permission(inode, acl, mask);
+	        int error = posix_acl_permission(mnt_userns, inode, acl, mask);
 	        posix_acl_release(acl);
 	        return error;
 	}
@@ -287,18 +304,31 @@ static int check_acl(struct inode *inode, int mask)
 	return -EAGAIN;
 }
 
-/*
- * This does the basic UNIX permission checking.
+/**
+ * acl_permission_check - perform basic UNIX permission checking
+ * @mnt_userns:	user namespace of the mount the inode was found from
+ * @inode:	inode to check permissions on
+ * @mask:	right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC ...)
+ *
+ * This function performs the basic UNIX permission checking. Since this
+ * function may retrieve POSIX acls it needs to know whether it is called from a
+ * blocking or non-blocking context and thus cares about the MAY_NOT_BLOCK bit.
  *
- * Note that the POSIX ACL check cares about the MAY_NOT_BLOCK bit,
- * for RCU walking.
+ * If the inode has been found through an idmapped mount the user namespace of
+ * the vfsmount must be passed through @mnt_userns. This function will then take
+ * care to map the inode according to @mnt_userns before checking permissions.
+ * On non-idmapped mounts or if permission checking is to be performed on the
+ * raw inode simply passs init_user_ns.
  */
-static int acl_permission_check(struct inode *inode, int mask)
+static int acl_permission_check(struct user_namespace *mnt_userns,
+				struct inode *inode, int mask)
 {
 	unsigned int mode = inode->i_mode;
+	kuid_t i_uid;
 
 	/* Are we the owner? If so, ACL's don't matter */
-	if (likely(uid_eq(current_fsuid(), inode->i_uid))) {
+	i_uid = i_uid_into_mnt(mnt_userns, inode);
+	if (likely(uid_eq(current_fsuid(), i_uid))) {
 		mask &= 7;
 		mode >>= 6;
 		return (mask & ~mode) ? -EACCES : 0;
@@ -306,7 +336,7 @@ static int acl_permission_check(struct inode *inode, int mask)
 
 	/* Do we have ACL's? */
 	if (IS_POSIXACL(inode) && (mode & S_IRWXG)) {
-		int error = check_acl(inode, mask);
+		int error = check_acl(mnt_userns, inode, mask);
 		if (error != -EAGAIN)
 			return error;
 	}
@@ -320,7 +350,8 @@ static int acl_permission_check(struct inode *inode, int mask)
 	 * about? Need to check group ownership if so.
 	 */
 	if (mask & (mode ^ (mode >> 3))) {
-		if (in_group_p(inode->i_gid))
+		kgid_t kgid = i_gid_into_mnt(mnt_userns, inode);
+		if (in_group_p(kgid))
 			mode >>= 3;
 	}
 
@@ -330,6 +361,7 @@ static int acl_permission_check(struct inode *inode, int mask)
 
 /**
  * generic_permission -  check for access rights on a Posix-like filesystem
+ * @mnt_userns:	user namespace of the mount the inode was found from
  * @inode:	inode to check access rights for
  * @mask:	right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC,
  *		%MAY_NOT_BLOCK ...)
@@ -342,25 +374,32 @@ static int acl_permission_check(struct inode *inode, int mask)
  * generic_permission is rcu-walk aware. It returns -ECHILD in case an rcu-walk
  * request cannot be satisfied (eg. requires blocking or too much complexity).
  * It would then be called again in ref-walk mode.
+ *
+ * If the inode has been found through an idmapped mount the user namespace of
+ * the vfsmount must be passed through @mnt_userns. This function will then take
+ * care to map the inode according to @mnt_userns before checking permissions.
+ * On non-idmapped mounts or if permission checking is to be performed on the
+ * raw inode simply passs init_user_ns.
  */
-int generic_permission(struct inode *inode, int mask)
+int generic_permission(struct user_namespace *mnt_userns, struct inode *inode,
+		       int mask)
 {
 	int ret;
 
 	/*
 	 * Do the basic permission checks.
 	 */
-	ret = acl_permission_check(inode, mask);
+	ret = acl_permission_check(mnt_userns, inode, mask);
 	if (ret != -EACCES)
 		return ret;
 
 	if (S_ISDIR(inode->i_mode)) {
 		/* DACs are overridable for directories */
 		if (!(mask & MAY_WRITE))
-			if (capable_wrt_inode_uidgid(&init_user_ns, inode,
+			if (capable_wrt_inode_uidgid(mnt_userns, inode,
 						     CAP_DAC_READ_SEARCH))
 				return 0;
-		if (capable_wrt_inode_uidgid(&init_user_ns, inode,
+		if (capable_wrt_inode_uidgid(mnt_userns, inode,
 					     CAP_DAC_OVERRIDE))
 			return 0;
 		return -EACCES;
@@ -371,7 +410,7 @@ int generic_permission(struct inode *inode, int mask)
 	 */
 	mask &= MAY_READ | MAY_WRITE | MAY_EXEC;
 	if (mask == MAY_READ)
-		if (capable_wrt_inode_uidgid(&init_user_ns, inode,
+		if (capable_wrt_inode_uidgid(mnt_userns, inode,
 					     CAP_DAC_READ_SEARCH))
 			return 0;
 	/*
@@ -380,7 +419,7 @@ int generic_permission(struct inode *inode, int mask)
 	 * at least one exec bit set.
 	 */
 	if (!(mask & MAY_EXEC) || (inode->i_mode & S_IXUGO))
-		if (capable_wrt_inode_uidgid(&init_user_ns, inode,
+		if (capable_wrt_inode_uidgid(mnt_userns, inode,
 					     CAP_DAC_OVERRIDE))
 			return 0;
 
@@ -388,13 +427,19 @@ int generic_permission(struct inode *inode, int mask)
 }
 EXPORT_SYMBOL(generic_permission);
 
-/*
+/**
+ * do_inode_permission - UNIX permission checking
+ * @mnt_userns:	user namespace of the mount the inode was found from
+ * @inode:	inode to check permissions on
+ * @mask:	right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC ...)
+ *
  * We _really_ want to just do "generic_permission()" without
  * even looking at the inode->i_op values. So we keep a cache
  * flag in inode->i_opflags, that says "this has not special
  * permission function, use the fast case".
  */
-static inline int do_inode_permission(struct inode *inode, int mask)
+static inline int do_inode_permission(struct user_namespace *mnt_userns,
+				      struct inode *inode, int mask)
 {
 	if (unlikely(!(inode->i_opflags & IOP_FASTPERM))) {
 		if (likely(inode->i_op->permission))
@@ -405,7 +450,7 @@ static inline int do_inode_permission(struct inode *inode, int mask)
 		inode->i_opflags |= IOP_FASTPERM;
 		spin_unlock(&inode->i_lock);
 	}
-	return generic_permission(inode, mask);
+	return generic_permission(mnt_userns, inode, mask);
 }
 
 /**
@@ -430,8 +475,9 @@ static int sb_permission(struct super_block *sb, struct inode *inode, int mask)
 
 /**
  * inode_permission - Check for access rights to a given inode
- * @inode: Inode to check permission on
- * @mask: Right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC)
+ * @mnt_userns:	User namespace of the mount the inode was found from
+ * @inode:	Inode to check permission on
+ * @mask:	Right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC)
  *
  * Check for read/write/execute permissions on an inode.  We use fs[ug]id for
  * this, letting us set arbitrary permissions for filesystem access without
@@ -439,7 +485,8 @@ static int sb_permission(struct super_block *sb, struct inode *inode, int mask)
  *
  * When checking for MAY_APPEND, MAY_WRITE must also be set in @mask.
  */
-int inode_permission(struct inode *inode, int mask)
+int inode_permission(struct user_namespace *mnt_userns,
+		     struct inode *inode, int mask)
 {
 	int retval;
 
@@ -463,7 +510,7 @@ int inode_permission(struct inode *inode, int mask)
 			return -EACCES;
 	}
 
-	retval = do_inode_permission(inode, mask);
+	retval = do_inode_permission(mnt_userns, inode, mask);
 	if (retval)
 		return retval;
 
@@ -1009,7 +1056,7 @@ static bool safe_hardlink_source(struct inode *inode)
 		return false;
 
 	/* Hardlinking to unreadable or unwritable sources is dangerous. */
-	if (inode_permission(inode, MAY_READ | MAY_WRITE))
+	if (inode_permission(&init_user_ns, inode, MAY_READ | MAY_WRITE))
 		return false;
 
 	return true;
@@ -1569,13 +1616,14 @@ static struct dentry *lookup_slow(const struct qstr *name,
 static inline int may_lookup(struct nameidata *nd)
 {
 	if (nd->flags & LOOKUP_RCU) {
-		int err = inode_permission(nd->inode, MAY_EXEC|MAY_NOT_BLOCK);
+		int err = inode_permission(&init_user_ns, nd->inode,
+					   MAY_EXEC | MAY_NOT_BLOCK);
 		if (err != -ECHILD)
 			return err;
 		if (unlazy_walk(nd))
 			return -ECHILD;
 	}
-	return inode_permission(nd->inode, MAY_EXEC);
+	return inode_permission(&init_user_ns, nd->inode, MAY_EXEC);
 }
 
 static int reserve_stack(struct nameidata *nd, struct path *link, unsigned seq)
@@ -2509,7 +2557,7 @@ static int lookup_one_len_common(const char *name, struct dentry *base,
 			return err;
 	}
 
-	return inode_permission(base->d_inode, MAY_EXEC);
+	return inode_permission(&init_user_ns, base->d_inode, MAY_EXEC);
 }
 
 /**
@@ -2703,7 +2751,7 @@ static int may_delete(struct inode *dir, struct dentry *victim, bool isdir)
 
 	audit_inode_child(dir, victim, AUDIT_TYPE_CHILD_DELETE);
 
-	error = inode_permission(dir, MAY_WRITE | MAY_EXEC);
+	error = inode_permission(&init_user_ns, dir, MAY_WRITE | MAY_EXEC);
 	if (error)
 		return error;
 	if (IS_APPEND(dir))
@@ -2747,7 +2795,7 @@ static inline int may_create(struct inode *dir, struct dentry *child)
 	if (!kuid_has_mapping(s_user_ns, current_fsuid()) ||
 	    !kgid_has_mapping(s_user_ns, current_fsgid()))
 		return -EOVERFLOW;
-	return inode_permission(dir, MAY_WRITE | MAY_EXEC);
+	return inode_permission(&init_user_ns, dir, MAY_WRITE | MAY_EXEC);
 }
 
 /*
@@ -2877,7 +2925,7 @@ static int may_open(const struct path *path, int acc_mode, int flag)
 		break;
 	}
 
-	error = inode_permission(inode, MAY_OPEN | acc_mode);
+	error = inode_permission(&init_user_ns, inode, MAY_OPEN | acc_mode);
 	if (error)
 		return error;
 
@@ -2939,7 +2987,8 @@ static int may_o_create(const struct path *dir, struct dentry *dentry, umode_t m
 	    !kgid_has_mapping(s_user_ns, current_fsgid()))
 		return -EOVERFLOW;
 
-	error = inode_permission(dir->dentry->d_inode, MAY_WRITE | MAY_EXEC);
+	error = inode_permission(&init_user_ns, dir->dentry->d_inode,
+				 MAY_WRITE | MAY_EXEC);
 	if (error)
 		return error;
 
@@ -3276,7 +3325,7 @@ struct dentry *vfs_tmpfile(struct dentry *dentry, umode_t mode, int open_flag)
 	int error;
 
 	/* we want directory to be writable */
-	error = inode_permission(dir, MAY_WRITE | MAY_EXEC);
+	error = inode_permission(&init_user_ns, dir, MAY_WRITE | MAY_EXEC);
 	if (error)
 		goto out_err;
 	error = -EOPNOTSUPP;
@@ -4267,12 +4316,14 @@ int vfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	 */
 	if (new_dir != old_dir) {
 		if (is_dir) {
-			error = inode_permission(source, MAY_WRITE);
+			error = inode_permission(&init_user_ns, source,
+						 MAY_WRITE);
 			if (error)
 				return error;
 		}
 		if ((flags & RENAME_EXCHANGE) && new_is_dir) {
-			error = inode_permission(target, MAY_WRITE);
+			error = inode_permission(&init_user_ns, target,
+						 MAY_WRITE);
 			if (error)
 				return error;
 		}