landlock: Support filesystem access-control

Using Landlock objects and ruleset, it is possible to tag inodes
according to a process's domain.  To enable an unprivileged process to
express a file hierarchy, it first needs to open a directory (or a file)
and pass this file descriptor to the kernel through
landlock_add_rule(2).  When checking if a file access request is
allowed, we walk from the requested dentry to the real root, following
the different mount layers.  The access to each "tagged" inodes are
collected according to their rule layer level, and ANDed to create
access to the requested file hierarchy.  This makes possible to identify
a lot of files without tagging every inodes nor modifying the
filesystem, while still following the view and understanding the user
has from the filesystem.

Add a new ARCH_EPHEMERAL_INODES for UML because it currently does not
keep the same struct inodes for the same inodes whereas these inodes are
in use.

This commit adds a minimal set of supported filesystem access-control
which doesn't enable to restrict all file-related actions.  This is the
result of multiple discussions to minimize the code of Landlock to ease
review.  Thanks to the Landlock design, extending this access-control
without breaking user space will not be a problem.  Moreover, seccomp
filters can be used to restrict the use of syscall families which may
not be currently handled by Landlock.

Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Anton Ivanov <anton.ivanov@cambridgegreys.com>
Cc: James Morris <jmorris@namei.org>
Cc: Jann Horn <jannh@google.com>
Cc: Jeff Dike <jdike@addtoit.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: Richard Weinberger <richard@nod.at>
Cc: Serge E. Hallyn <serge@hallyn.com>
Signed-off-by: Mickaël Salaün <mic@linux.microsoft.com>
Link: https://lore.kernel.org/r/20210422154123.13086-8-mic@digikod.net
Signed-off-by: James Morris <jamorris@linux.microsoft.com>

MAINTAINERS

@@ -10003,6 +10003,7 @@ L:	linux-security-module@vger.kernel.org
 S:	Supported
 W:	https://landlock.io
 T:	git https://github.com/landlock-lsm/linux.git
+F:	include/uapi/linux/landlock.h
 F:	security/landlock/
 K:	landlock
 K:	LANDLOCK

arch/Kconfig

@@ -1013,6 +1013,13 @@ config COMPAT_32BIT_TIME
 config ARCH_NO_PREEMPT
 	bool
 
+config ARCH_EPHEMERAL_INODES
+	def_bool n
+	help
+	  An arch should select this symbol if it doesn't keep track of inode
+	  instances on its own, but instead relies on something else (e.g. the
+	  host kernel for an UML kernel).
+
 config ARCH_SUPPORTS_RT
 	bool
 

arch/um/Kconfig

@@ -5,6 +5,7 @@ menu "UML-specific options"
 config UML
 	bool
 	default y
+	select ARCH_EPHEMERAL_INODES
 	select ARCH_HAS_KCOV
 	select ARCH_NO_PREEMPT
 	select HAVE_ARCH_AUDITSYSCALL

include/uapi/linux/landlock.h

@@ -0,0 +1,76 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * Landlock - User space API
+ *
+ * Copyright © 2017-2020 Mickaël Salaün <mic@digikod.net>
+ * Copyright © 2018-2020 ANSSI
+ */
+
+#ifndef _UAPI_LINUX_LANDLOCK_H
+#define _UAPI_LINUX_LANDLOCK_H
+
+/**
+ * DOC: fs_access
+ *
+ * A set of actions on kernel objects may be defined by an attribute (e.g.
+ * &struct landlock_path_beneath_attr) including a bitmask of access.
+ *
+ * Filesystem flags
+ * ~~~~~~~~~~~~~~~~
+ *
+ * These flags enable to restrict a sandboxed process to a set of actions on
+ * files and directories.  Files or directories opened before the sandboxing
+ * are not subject to these restrictions.
+ *
+ * A file can only receive these access rights:
+ *
+ * - %LANDLOCK_ACCESS_FS_EXECUTE: Execute a file.
+ * - %LANDLOCK_ACCESS_FS_WRITE_FILE: Open a file with write access.
+ * - %LANDLOCK_ACCESS_FS_READ_FILE: Open a file with read access.
+ *
+ * A directory can receive access rights related to files or directories.  The
+ * following access right is applied to the directory itself, and the
+ * directories beneath it:
+ *
+ * - %LANDLOCK_ACCESS_FS_READ_DIR: Open a directory or list its content.
+ *
+ * However, the following access rights only apply to the content of a
+ * directory, not the directory itself:
+ *
+ * - %LANDLOCK_ACCESS_FS_REMOVE_DIR: Remove an empty directory or rename one.
+ * - %LANDLOCK_ACCESS_FS_REMOVE_FILE: Unlink (or rename) a file.
+ * - %LANDLOCK_ACCESS_FS_MAKE_CHAR: Create (or rename or link) a character
+ *   device.
+ * - %LANDLOCK_ACCESS_FS_MAKE_DIR: Create (or rename) a directory.
+ * - %LANDLOCK_ACCESS_FS_MAKE_REG: Create (or rename or link) a regular file.
+ * - %LANDLOCK_ACCESS_FS_MAKE_SOCK: Create (or rename or link) a UNIX domain
+ *   socket.
+ * - %LANDLOCK_ACCESS_FS_MAKE_FIFO: Create (or rename or link) a named pipe.
+ * - %LANDLOCK_ACCESS_FS_MAKE_BLOCK: Create (or rename or link) a block device.
+ * - %LANDLOCK_ACCESS_FS_MAKE_SYM: Create (or rename or link) a symbolic link.
+ *
+ * .. warning::
+ *
+ *   It is currently not possible to restrict some file-related actions
+ *   accessible through these syscall families: :manpage:`chdir(2)`,
+ *   :manpage:`truncate(2)`, :manpage:`stat(2)`, :manpage:`flock(2)`,
+ *   :manpage:`chmod(2)`, :manpage:`chown(2)`, :manpage:`setxattr(2)`,
+ *   :manpage:`utime(2)`, :manpage:`ioctl(2)`, :manpage:`fcntl(2)`,
+ *   :manpage:`access(2)`.
+ *   Future Landlock evolutions will enable to restrict them.
+ */
+#define LANDLOCK_ACCESS_FS_EXECUTE			(1ULL << 0)
+#define LANDLOCK_ACCESS_FS_WRITE_FILE			(1ULL << 1)
+#define LANDLOCK_ACCESS_FS_READ_FILE			(1ULL << 2)
+#define LANDLOCK_ACCESS_FS_READ_DIR			(1ULL << 3)
+#define LANDLOCK_ACCESS_FS_REMOVE_DIR			(1ULL << 4)
+#define LANDLOCK_ACCESS_FS_REMOVE_FILE			(1ULL << 5)
+#define LANDLOCK_ACCESS_FS_MAKE_CHAR			(1ULL << 6)
+#define LANDLOCK_ACCESS_FS_MAKE_DIR			(1ULL << 7)
+#define LANDLOCK_ACCESS_FS_MAKE_REG			(1ULL << 8)
+#define LANDLOCK_ACCESS_FS_MAKE_SOCK			(1ULL << 9)
+#define LANDLOCK_ACCESS_FS_MAKE_FIFO			(1ULL << 10)
+#define LANDLOCK_ACCESS_FS_MAKE_BLOCK			(1ULL << 11)
+#define LANDLOCK_ACCESS_FS_MAKE_SYM			(1ULL << 12)
+
+#endif /* _UAPI_LINUX_LANDLOCK_H */

security/landlock/Kconfig

@@ -2,7 +2,7 @@
 
 config SECURITY_LANDLOCK
 	bool "Landlock support"
-	depends on SECURITY
+	depends on SECURITY && !ARCH_EPHEMERAL_INODES
 	select SECURITY_PATH
 	help
 	  Landlock is a sandboxing mechanism that enables processes to restrict

security/landlock/Makefile

@@ -1,4 +1,4 @@
 obj-$(CONFIG_SECURITY_LANDLOCK) := landlock.o
 
 landlock-y := setup.o object.o ruleset.o \
-	cred.o ptrace.o
+	cred.o ptrace.o fs.o

security/landlock/fs.h

@@ -0,0 +1,70 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Landlock LSM - Filesystem management and hooks
+ *
+ * Copyright © 2017-2020 Mickaël Salaün <mic@digikod.net>
+ * Copyright © 2018-2020 ANSSI
+ */
+
+#ifndef _SECURITY_LANDLOCK_FS_H
+#define _SECURITY_LANDLOCK_FS_H
+
+#include <linux/fs.h>
+#include <linux/init.h>
+#include <linux/rcupdate.h>
+
+#include "ruleset.h"
+#include "setup.h"
+
+/**
+ * struct landlock_inode_security - Inode security blob
+ *
+ * Enable to reference a &struct landlock_object tied to an inode (i.e.
+ * underlying object).
+ */
+struct landlock_inode_security {
+	/**
+	 * @object: Weak pointer to an allocated object.  All assignments of a
+	 * new object are protected by the underlying inode->i_lock.  However,
+	 * atomically disassociating @object from the inode is only protected
+	 * by @object->lock, from the time @object's usage refcount drops to
+	 * zero to the time this pointer is nulled out (cf. release_inode() and
+	 * hook_sb_delete()).  Indeed, such disassociation doesn't require
+	 * inode->i_lock thanks to the careful rcu_access_pointer() check
+	 * performed by get_inode_object().
+	 */
+	struct landlock_object __rcu *object;
+};
+
+/**
+ * struct landlock_superblock_security - Superblock security blob
+ *
+ * Enable hook_sb_delete() to wait for concurrent calls to release_inode().
+ */
+struct landlock_superblock_security {
+	/**
+	 * @inode_refs: Number of pending inodes (from this superblock) that
+	 * are being released by release_inode().
+	 * Cf. struct super_block->s_fsnotify_inode_refs .
+	 */
+	atomic_long_t inode_refs;
+};
+
+static inline struct landlock_inode_security *landlock_inode(
+		const struct inode *const inode)
+{
+	return inode->i_security + landlock_blob_sizes.lbs_inode;
+}
+
+static inline struct landlock_superblock_security *landlock_superblock(
+		const struct super_block *const superblock)
+{
+	return superblock->s_security + landlock_blob_sizes.lbs_superblock;
+}
+
+__init void landlock_add_fs_hooks(void);
+
+int landlock_append_fs_rule(struct landlock_ruleset *const ruleset,
+		const struct path *const path, u32 access_hierarchy);
+
+#endif /* _SECURITY_LANDLOCK_FS_H */

security/landlock/limits.h

@@ -10,8 +10,12 @@
 #define _SECURITY_LANDLOCK_LIMITS_H
 
 #include <linux/limits.h>
+#include <uapi/linux/landlock.h>
 
 #define LANDLOCK_MAX_NUM_LAYERS		64
 #define LANDLOCK_MAX_NUM_RULES		U32_MAX
 
+#define LANDLOCK_LAST_ACCESS_FS		LANDLOCK_ACCESS_FS_MAKE_SYM
+#define LANDLOCK_MASK_ACCESS_FS		((LANDLOCK_LAST_ACCESS_FS << 1) - 1)
+
 #endif /* _SECURITY_LANDLOCK_LIMITS_H */

security/landlock/ruleset.c

@@ -116,9 +116,11 @@ static void build_check_ruleset(void)
 		.num_rules = ~0,
 		.num_layers = ~0,
 	};
+	typeof(ruleset.fs_access_masks[0]) fs_access_mask = ~0;
 
 	BUILD_BUG_ON(ruleset.num_rules < LANDLOCK_MAX_NUM_RULES);
 	BUILD_BUG_ON(ruleset.num_layers < LANDLOCK_MAX_NUM_LAYERS);
+	BUILD_BUG_ON(fs_access_mask < LANDLOCK_MASK_ACCESS_FS);
 }
 
 /**
@@ -217,9 +219,11 @@ static void build_check_layer(void)
 {
 	const struct landlock_layer layer = {
 		.level = ~0,
+		.access = ~0,
 	};
 
 	BUILD_BUG_ON(layer.level < LANDLOCK_MAX_NUM_LAYERS);
+	BUILD_BUG_ON(layer.access < LANDLOCK_MASK_ACCESS_FS);
 }
 
 /* @ruleset must be locked by the caller. */

security/landlock/setup.c

@@ -11,17 +11,24 @@
 
 #include "common.h"
 #include "cred.h"
+#include "fs.h"
 #include "ptrace.h"
 #include "setup.h"
 
+bool landlock_initialized __lsm_ro_after_init = false;
+
 struct lsm_blob_sizes landlock_blob_sizes __lsm_ro_after_init = {
 	.lbs_cred = sizeof(struct landlock_cred_security),
+	.lbs_inode = sizeof(struct landlock_inode_security),
+	.lbs_superblock = sizeof(struct landlock_superblock_security),
 };
 
 static int __init landlock_init(void)
 {
 	landlock_add_cred_hooks();
 	landlock_add_ptrace_hooks();
+	landlock_add_fs_hooks();
+	landlock_initialized = true;
 	pr_info("Up and running.\n");
 	return 0;
 }

security/landlock/setup.h

@@ -11,6 +11,8 @@
 
 #include <linux/lsm_hooks.h>
 
+extern bool landlock_initialized;
+
 extern struct lsm_blob_sizes landlock_blob_sizes;
 
 #endif /* _SECURITY_LANDLOCK_SETUP_H */