cgroups: implement device whitelist

Implement a cgroup to track and enforce open and mknod restrictions on device
files.  A device cgroup associates a device access whitelist with each cgroup.
 A whitelist entry has 4 fields.  'type' is a (all), c (char), or b (block).
'all' means it applies to all types and all major and minor numbers.  Major
and minor are either an integer or * for all.  Access is a composition of r
(read), w (write), and m (mknod).

The root device cgroup starts with rwm to 'all'.  A child devcg gets a copy of
the parent.  Admins can then remove devices from the whitelist or add new
entries.  A child cgroup can never receive a device access which is denied its
parent.  However when a device access is removed from a parent it will not
also be removed from the child(ren).

An entry is added using devices.allow, and removed using
devices.deny.  For instance

	echo 'c 1:3 mr' > /cgroups/1/devices.allow

allows cgroup 1 to read and mknod the device usually known as
/dev/null.  Doing

	echo a > /cgroups/1/devices.deny

will remove the default 'a *:* mrw' entry.

CAP_SYS_ADMIN is needed to change permissions or move another task to a new
cgroup.  A cgroup may not be granted more permissions than the cgroup's parent
has.  Any task can move itself between cgroups.  This won't be sufficient, but
we can decide the best way to adequately restrict movement later.

[akpm@linux-foundation.org: coding-style fixes]
[akpm@linux-foundation.org: fix may-be-used-uninitialized warning]
Signed-off-by: Serge E. Hallyn <serue@us.ibm.com>
Acked-by: James Morris <jmorris@namei.org>
Looks-good-to: Pavel Emelyanov <xemul@openvz.org>
Cc: Daniel Hokka Zakrisson <daniel@hozac.com>
Cc: Li Zefan <lizf@cn.fujitsu.com>
Cc: Paul Menage <menage@google.com>
Cc: Balbir Singh <balbir@in.ibm.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

Documentation/controllers/devices.txt

+Device Whitelist Controller
+
+1. Description:
+
+Implement a cgroup to track and enforce open and mknod restrictions
+on device files.  A device cgroup associates a device access
+whitelist with each cgroup.  A whitelist entry has 4 fields.
+'type' is a (all), c (char), or b (block).  'all' means it applies
+to all types and all major and minor numbers.  Major and minor are
+either an integer or * for all.  Access is a composition of r
+(read), w (write), and m (mknod).
+
+The root device cgroup starts with rwm to 'all'.  A child device
+cgroup gets a copy of the parent.  Administrators can then remove
+devices from the whitelist or add new entries.  A child cgroup can
+never receive a device access which is denied its parent.  However
+when a device access is removed from a parent it will not also be
+removed from the child(ren).
+
+2. User Interface
+
+An entry is added using devices.allow, and removed using
+devices.deny.  For instance
+
+	echo 'c 1:3 mr' > /cgroups/1/devices.allow
+
+allows cgroup 1 to read and mknod the device usually known as
+/dev/null.  Doing
+
+	echo a > /cgroups/1/devices.deny
+
+will remove the default 'a *:* mrw' entry.
+
+3. Security
+
+Any task can move itself between cgroups.  This clearly won't
+suffice, but we can decide the best way to adequately restrict
+movement as people get some experience with this.  We may just want
+to require CAP_SYS_ADMIN, which at least is a separate bit from
+CAP_MKNOD.  We may want to just refuse moving to a cgroup which
+isn't a descendent of the current one.  Or we may want to use
+CAP_MAC_ADMIN, since we really are trying to lock down root.
+
+CAP_SYS_ADMIN is needed to modify the whitelist or move another
+task to a new cgroup.  (Again we'll probably want to change that).
+
+A cgroup may not be granted more permissions than the cgroup's
+parent has.

fs/namei.c

@@ -30,6 +30,7 @@
 #include <linux/capability.h>
 #include <linux/file.h>
 #include <linux/fcntl.h>
+#include <linux/device_cgroup.h>
 #include <asm/namei.h>
 #include <asm/uaccess.h>
 
@@ -281,6 +282,10 @@ int permission(struct inode *inode, int mask, struct nameidata *nd)
 	if (retval)
 		return retval;
 
+	retval = devcgroup_inode_permission(inode, mask);
+	if (retval)
+		return retval;
+
 	return security_inode_permission(inode, mask, nd);
 }
 
@@ -2028,6 +2033,10 @@ int vfs_mknod(struct inode *dir, struct dentry *dentry, int mode, dev_t dev)
 	if (!dir->i_op || !dir->i_op->mknod)
 		return -EPERM;
 
+	error = devcgroup_inode_mknod(mode, dev);
+	if (error)
+		return error;
+
 	error = security_inode_mknod(dir, dentry, mode, dev);
 	if (error)
 		return error;

include/linux/cgroup_subsys.h

@@ -42,3 +42,9 @@ SUBSYS(mem_cgroup)
 #endif
 
 /* */
+
+#ifdef CONFIG_CGROUP_DEVICE
+SUBSYS(devices)
+#endif
+
+/* */

include/linux/device_cgroup.h

+#include <linux/module.h>
+#include <linux/fs.h>
+
+#ifdef CONFIG_CGROUP_DEVICE
+extern int devcgroup_inode_permission(struct inode *inode, int mask);
+extern int devcgroup_inode_mknod(int mode, dev_t dev);
+#else
+static inline int devcgroup_inode_permission(struct inode *inode, int mask)
+{ return 0; }
+static inline int devcgroup_inode_mknod(int mode, dev_t dev)
+{ return 0; }
+#endif

init/Kconfig

@@ -298,6 +298,13 @@ config CGROUP_NS
           for instance virtual servers and checkpoint/restart
           jobs.
 
+config CGROUP_DEVICE
+	bool "Device controller for cgroups"
+	depends on CGROUPS && EXPERIMENTAL
+	help
+	  Provides a cgroup implementing whitelists for devices which
+	  a process in the cgroup can mknod or open.
+
 config CPUSETS
 	bool "Cpuset support"
 	depends on SMP && CGROUPS

security/Makefile

@@ -18,3 +18,4 @@ obj-$(CONFIG_SECURITY_SELINUX)		+= selinux/built-in.o
 obj-$(CONFIG_SECURITY_SMACK)		+= commoncap.o smack/built-in.o
 obj-$(CONFIG_SECURITY_CAPABILITIES)	+= commoncap.o capability.o
 obj-$(CONFIG_SECURITY_ROOTPLUG)		+= commoncap.o root_plug.o
+obj-$(CONFIG_CGROUP_DEVICE)		+= device_cgroup.o