Quoting Daniel Hokka Zakrisson (daniel@hozac.com):
> Hi Serge,
> 
> Some minor nits in the patch.
> 
> Serge E. Hallyn wrote:
> > This version differs from v4 only in that it addresses Li Zefan's comments
> > on
> > v4.
> >
> > 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.
> >
> > Changelog:
> > 	Mar 18 2008: Address comments by Li Zefan.
> > 	Mar 17 2008: Place specific device cgroup hooks next to
> > 		security_inode_{mknod,permission} rather than using
> > 		the security hooks.
> > 		Also remove most of the controls over tasks moving
> > 		between cgroups and playing with the allow and deny
> > 		permissions.
> > 	Mar 13 2008: move the dev_cgroup support into
> > 		capability hooks instead of having it
> > 		as a separate security module.
> > 		Support root_plug with devcg.
> > 		Note that due to this change, devcg will
> > 		not be enforcing if the dummy module is
> > 		loaded, or if selinux is loaded without
> > 		capabilities.
> > 	Mar 12 2008: allow dev_cgroup lsm to be used when
> > 		SECURITY=n, and allow stacking with SELinux
> > 		and Smack.  Don't work too hard in Kconfig
> > 		to prevent a warning when smack+devcg are
> > 		both compiled in, worry about that later.
> >
> > 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>
> > :)
> > ---
> >  fs/namei.c                    |    9 +
> >  include/linux/cgroup_subsys.h |    6 +
> >  include/linux/device_cgroup.h |   12 +
> >  init/Kconfig                  |    7 +
> >  security/Makefile             |    1 +
> >  security/device_cgroup.c      |  598
> > +++++++++++++++++++++++++++++++++++++++++
> >  6 files changed, 633 insertions(+), 0 deletions(-)
> >  create mode 100644 include/linux/device_cgroup.h
> >  create mode 100644 security/device_cgroup.c
> >
> > diff --git a/fs/namei.c b/fs/namei.c
> > index dfb3cb8..6caed32 100644
> > --- a/fs/namei.c
> > +++ b/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;
> > diff --git a/include/linux/cgroup_subsys.h b/include/linux/cgroup_subsys.h
> > index 1ddebfc..e287745 100644
> > --- a/include/linux/cgroup_subsys.h
> > +++ b/include/linux/cgroup_subsys.h
> > @@ -42,3 +42,9 @@ SUBSYS(mem_cgroup)
> >  #endif
> >
> >  /* */
> > +
> > +#ifdef CONFIG_CGROUP_DEVICE
> > +SUBSYS(devices)
> > +#endif
> > +
> > +/* */
> > diff --git a/include/linux/device_cgroup.h b/include/linux/device_cgroup.h
> > new file mode 100644
> > index 0000000..0b0d9c3
> > --- /dev/null
> > +++ b/include/linux/device_cgroup.h
> > @@ -0,0 +1,12 @@
> > +#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
> > diff --git a/init/Kconfig b/init/Kconfig
> > index 009f2d8..30868cd 100644
> > --- a/init/Kconfig
> > +++ b/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
> > diff --git a/security/Makefile b/security/Makefile
> > index 9e8b025..7ef1107 100644
> > --- a/security/Makefile
> > +++ b/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
> > diff --git a/security/device_cgroup.c b/security/device_cgroup.c
> > new file mode 100644
> > index 0000000..63d9099
> > --- /dev/null
> > +++ b/security/device_cgroup.c
> > @@ -0,0 +1,598 @@
> > +/*
> > + * dev_cgroup.c - device cgroup subsystem
> > + *
> > + * Copyright 2007 IBM Corp
> > + */
> > +
> > +#include <linux/device_cgroup.h>
> > +#include <linux/cgroup.h>
> > +#include <linux/ctype.h>
> > +#include <linux/list.h>
> > +#include <asm/uaccess.h>
> > +
> > +#define ACC_MKNOD 1
> > +#define ACC_READ  2
> > +#define ACC_WRITE 4
> > +#define ACC_MASK (ACC_MKNOD | ACC_READ | ACC_WRITE)
> > +
> > +#define DEV_BLOCK 1
> > +#define DEV_CHAR  2
> > +#define DEV_ALL   4  /* this represents all devices */
> > +
> > +/*
> > + * whitelist locking rules:
> > + * cgroup_lock() cannot be taken under dev_cgroup->lock.
> > + * dev_cgroup->lock can be taken with or without cgroup_lock().
> > + *
> > + * modifications always require cgroup_lock
> > + * modifications to a list which is visible require the
> > + *   dev_cgroup->lock *and* cgroup_lock()
> > + * walking the list requires dev_cgroup->lock or cgroup_lock().
> > + *
> > + * reasoning: dev_whitelist_copy() needs to kmalloc, so needs
> > + *   a mutex, which the cgroup_lock() is.  Since modifying
> > + *   a visible list requires both locks, either lock can be
> > + *   taken for walking the list.
> > + */
> > +
> > +struct dev_whitelist_item {
> > +	u32 major, minor;
> > +	short type;
> > +	short access;
> > +	struct list_head list;
> > +};
> > +
> > +struct dev_cgroup {
> > +	struct cgroup_subsys_state css;
> > +	struct list_head whitelist;
> > +	spinlock_t lock;
> > +};
> > +
> > +static inline struct dev_cgroup *cgroup_to_devcgroup(
> > +		struct cgroup *cgroup)
> > +{
> > +	return container_of(cgroup_subsys_state(cgroup, devices_subsys_id),
> > +			    struct dev_cgroup, css);
> > +}
> > +
> > +
> > +struct cgroup_subsys devices_subsys;
> > +
> > +static int devcgroup_can_attach(struct cgroup_subsys *ss,
> > +		struct cgroup *new_cgroup, struct task_struct