landlock: Add syscall implementations

These 3 system calls are designed to be used by unprivileged processes
to sandbox themselves:
* landlock_create_ruleset(2): Creates a ruleset and returns its file
  descriptor.
* landlock_add_rule(2): Adds a rule (e.g. file hierarchy access) to a
  ruleset, identified by the dedicated file descriptor.
* landlock_restrict_self(2): Enforces a ruleset on the calling thread
  and its future children (similar to seccomp).  This syscall has the
  same usage restrictions as seccomp(2): the caller must have the
  no_new_privs attribute set or have CAP_SYS_ADMIN in the current user
  namespace.

All these syscalls have a "flags" argument (not currently used) to
enable extensibility.

Here are the motivations for these new syscalls:
* A sandboxed process may not have access to file systems, including
  /dev, /sys or /proc, but it should still be able to add more
  restrictions to itself.
* Neither prctl(2) nor seccomp(2) (which was used in a previous version)
  fit well with the current definition of a Landlock security policy.

All passed structs (attributes) are checked at build time to ensure that
they don't contain holes and that they are aligned the same way for each
architecture.

See the user and kernel documentation for more details (provided by a
following commit):
* Documentation/userspace-api/landlock.rst
* Documentation/security/landlock.rst

Cc: Arnd Bergmann <arnd@arndb.de>
Cc: James Morris <jmorris@namei.org>
Cc: Jann Horn <jannh@google.com>
Cc: Kees Cook <keescook@chromium.org>
Signed-off-by: Mickaël Salaün <mic@linux.microsoft.com>
Acked-by: Serge Hallyn <serge@hallyn.com>
Link: https://lore.kernel.org/r/20210422154123.13086-9-mic@digikod.net
Signed-off-by: James Morris <jamorris@linux.microsoft.com>

2 files changed, 60 insertions, 0 deletions

diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 2839dc9a7c01..fa3971012e1c 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -69,6 +69,8 @@ struct io_uring_params;
 struct clone_args;
 struct open_how;
 struct mount_attr;
+struct landlock_ruleset_attr;
+enum landlock_rule_type;
 
 #include <linux/types.h>
 #include <linux/aio_abi.h>
@@ -1041,6 +1043,11 @@ asmlinkage long sys_pidfd_send_signal(int pidfd, int sig,
 				       siginfo_t __user *info,
 				       unsigned int flags);
 asmlinkage long sys_pidfd_getfd(int pidfd, int fd, unsigned int flags);
+asmlinkage long sys_landlock_create_ruleset(const struct landlock_ruleset_attr __user *attr,
+		size_t size, __u32 flags);
+asmlinkage long sys_landlock_add_rule(int ruleset_fd, enum landlock_rule_type rule_type,
+		const void __user *rule_attr, __u32 flags);
+asmlinkage long sys_landlock_restrict_self(int ruleset_fd, __u32 flags);
 
 /*
  * Architecture-specific system calls
diff --git a/include/uapi/linux/landlock.h b/include/uapi/linux/landlock.h
index b1a81b5a8b86..ba946a1e40b2 100644
--- a/include/uapi/linux/landlock.h
+++ b/include/uapi/linux/landlock.h
@@ -9,6 +9,59 @@
 #ifndef _UAPI_LINUX_LANDLOCK_H
 #define _UAPI_LINUX_LANDLOCK_H
 
+#include <linux/types.h>
+
+/**
+ * struct landlock_ruleset_attr - Ruleset definition
+ *
+ * Argument of sys_landlock_create_ruleset().  This structure can grow in
+ * future versions.
+ */
+struct landlock_ruleset_attr {
+	/**
+	 * @handled_access_fs: Bitmask of actions (cf. `Filesystem flags`_)
+	 * that is handled by this ruleset and should then be forbidden if no
+	 * rule explicitly allow them.  This is needed for backward
+	 * compatibility reasons.
+	 */
+	__u64 handled_access_fs;
+};
+
+/**
+ * enum landlock_rule_type - Landlock rule type
+ *
+ * Argument of sys_landlock_add_rule().
+ */
+enum landlock_rule_type {
+	/**
+	 * @LANDLOCK_RULE_PATH_BENEATH: Type of a &struct
+	 * landlock_path_beneath_attr .
+	 */
+	LANDLOCK_RULE_PATH_BENEATH = 1,
+};
+
+/**
+ * struct landlock_path_beneath_attr - Path hierarchy definition
+ *
+ * Argument of sys_landlock_add_rule().
+ */
+struct landlock_path_beneath_attr {
+	/**
+	 * @allowed_access: Bitmask of allowed actions for this file hierarchy
+	 * (cf. `Filesystem flags`_).
+	 */
+	__u64 allowed_access;
+	/**
+	 * @parent_fd: File descriptor, open with ``O_PATH``, which identifies
+	 * the parent directory of a file hierarchy, or just a file.
+	 */
+	__s32 parent_fd;
+	/*
+	 * This struct is packed to avoid trailing reserved members.
+	 * Cf. security/landlock/syscalls.c:build_check_abi()
+	 */
+} __attribute__((packed));
+
 /**
  * DOC: fs_access
  *