kernel: conditionally support non-root users, groups and capabilities

There are a lot of embedded systems that run most or all of their
functionality in init, running as root:root.  For these systems,
supporting multiple users is not necessary.

This patch adds a new symbol, CONFIG_MULTIUSER, that makes support for
non-root users, non-root groups, and capabilities optional.  It is enabled
under CONFIG_EXPERT menu.

When this symbol is not defined, UID and GID are zero in any possible case
and processes always have all capabilities.

The following syscalls are compiled out: setuid, setregid, setgid,
setreuid, setresuid, getresuid, setresgid, getresgid, setgroups,
getgroups, setfsuid, setfsgid, capget, capset.

Also, groups.c is compiled out completely.

In kernel/capability.c, capable function was moved in order to avoid
adding two ifdef blocks.

This change saves about 25 KB on a defconfig build.  The most minimal
kernels have total text sizes in the high hundreds of kB rather than
low MB.  (The 25k goes down a bit with allnoconfig, but not that much.

The kernel was booted in Qemu.  All the common functionalities work.
Adding users/groups is not possible, failing with -ENOSYS.

Bloat-o-meter output:
add/remove: 7/87 grow/shrink: 19/397 up/down: 1675/-26325 (-24650)

[akpm@linux-foundation.org: coding-style fixes]
Signed-off-by: Iulia Manda <iulia.manda21@gmail.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
Acked-by: Geert Uytterhoeven <geert@linux-m68k.org>
Tested-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

6 files changed, 41 insertions, 20 deletions

diff --git a/kernel/Makefile b/kernel/Makefile
index 1408b33..0f8f8b0 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -9,7 +9,9 @@ obj-y     = fork.o exec_domain.o panic.o \
 	    extable.o params.o \
 	    kthread.o sys_ni.o nsproxy.o \
 	    notifier.o ksysfs.o cred.o reboot.o \
-	    async.o range.o groups.o smpboot.o
+	    async.o range.o smpboot.o
+
+obj-$(CONFIG_MULTIUSER) += groups.o
 
 ifdef CONFIG_FUNCTION_TRACER
 # Do not trace debug files and internal ftrace files
diff --git a/kernel/capability.c b/kernel/capability.c
index 989f5bf..45432b5 100644
--- a/kernel/capability.c
+++ b/kernel/capability.c
@@ -35,6 +35,7 @@ static int __init file_caps_disable(char *str)
 }
 __setup("no_file_caps", file_caps_disable);
 
+#ifdef CONFIG_MULTIUSER
 /*
  * More recent versions of libcap are available from:
  *
@@ -386,6 +387,24 @@ bool ns_capable(struct user_namespace *ns, int cap)
 }
 EXPORT_SYMBOL(ns_capable);
 
+
+/**
+ * capable - Determine if the current task has a superior capability in effect
+ * @cap: The capability to be tested for
+ *
+ * Return true if the current task has the given superior capability currently
+ * available for use, false if not.
+ *
+ * This sets PF_SUPERPRIV on the task if the capability is available on the
+ * assumption that it's about to be used.
+ */
+bool capable(int cap)
+{
+	return ns_capable(&init_user_ns, cap);
+}
+EXPORT_SYMBOL(capable);
+#endif /* CONFIG_MULTIUSER */
+
 /**
  * file_ns_capable - Determine if the file's opener had a capability in effect
  * @file:  The file we want to check
@@ -412,22 +431,6 @@ bool file_ns_capable(const struct file *file, struct user_namespace *ns,
 EXPORT_SYMBOL(file_ns_capable);
 
 /**
- * capable - Determine if the current task has a superior capability in effect
- * @cap: The capability to be tested for
- *
- * Return true if the current task has the given superior capability currently
- * available for use, false if not.
- *
- * This sets PF_SUPERPRIV on the task if the capability is available on the
- * assumption that it's about to be used.
- */
-bool capable(int cap)
-{
-	return ns_capable(&init_user_ns, cap);
-}
-EXPORT_SYMBOL(capable);
-
-/**
  * capable_wrt_inode_uidgid - Check nsown_capable and uid and gid mapped
  * @inode: The inode in question
  * @cap: The capability in question
diff --git a/kernel/cred.c b/kernel/cred.c
index e0573a4..ec1c076 100644
--- a/kernel/cred.c
+++ b/kernel/cred.c
@@ -29,6 +29,9 @@
 
 static struct kmem_cache *cred_jar;
 
+/* init to 2 - one for init_task, one to ensure it is never freed */
+struct group_info init_groups = { .usage = ATOMIC_INIT(2) };
+
 /*
  * The initial credentials for the initial task
  */
diff --git a/kernel/groups.c b/kernel/groups.c
index 664411f..74d431d 100644
--- a/kernel/groups.c
+++ b/kernel/groups.c
@@ -9,9 +9,6 @@
 #include <linux/user_namespace.h>
 #include <asm/uaccess.h>
 
-/* init to 2 - one for init_task, one to ensure it is never freed */
-struct group_info init_groups = { .usage = ATOMIC_INIT(2) };
-
 struct group_info *groups_alloc(int gidsetsize)
 {
 	struct group_info *group_info;
diff --git a/kernel/sys.c b/kernel/sys.c
index a03d9cd..3be3449 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -325,6 +325,7 @@ out_unlock:
  * SMP: There are not races, the GIDs are checked only by filesystem
  *      operations (as far as semantic preservation is concerned).
  */
+#ifdef CONFIG_MULTIUSER
 SYSCALL_DEFINE2(setregid, gid_t, rgid, gid_t, egid)
 {
 	struct user_namespace *ns = current_user_ns();
@@ -815,6 +816,7 @@ change_okay:
 	commit_creds(new);
 	return old_fsgid;
 }
+#endif /* CONFIG_MULTIUSER */
 
 /**
  * sys_getpid - return the thread group id of the current process
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index 5adcb0a..7995ef5 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -159,6 +159,20 @@ cond_syscall(sys_uselib);
 cond_syscall(sys_fadvise64);
 cond_syscall(sys_fadvise64_64);
 cond_syscall(sys_madvise);
+cond_syscall(sys_setuid);
+cond_syscall(sys_setregid);
+cond_syscall(sys_setgid);
+cond_syscall(sys_setreuid);
+cond_syscall(sys_setresuid);
+cond_syscall(sys_getresuid);
+cond_syscall(sys_setresgid);
+cond_syscall(sys_getresgid);
+cond_syscall(sys_setgroups);
+cond_syscall(sys_getgroups);
+cond_syscall(sys_setfsuid);
+cond_syscall(sys_setfsgid);
+cond_syscall(sys_capget);
+cond_syscall(sys_capset);
 
 /* arch-specific weak syscall entries */
 cond_syscall(sys_pciconfig_read);