Task Control Groups: make cpusets a client of cgroups

Remove the filesystem support logic from the cpusets system and makes cpusets
a cgroup subsystem

The "cpuset" filesystem becomes a dummy filesystem; attempts to mount it get
passed through to the cgroup filesystem with the appropriate options to
emulate the old cpuset filesystem behaviour.

Signed-off-by: Paul Menage <menage@google.com>
Cc: Serge E. Hallyn <serue@us.ibm.com>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Dave Hansen <haveblue@us.ibm.com>
Cc: Balbir Singh <balbir@in.ibm.com>
Cc: Paul Jackson <pj@sgi.com>
Cc: Kirill Korotaev <dev@openvz.org>
Cc: Herbert Poetzl <herbert@13thfloor.at>
Cc: Srivatsa Vaddagiri <vatsa@in.ibm.com>
Cc: Cedric Le Goater <clg@fr.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

11 files changed, 277 insertions, 1055 deletions

diff --git a/Documentation/cpusets.txt b/Documentation/cpusets.txt
index ec9de6917f0..85eeab5e7e3 100644
--- a/Documentation/cpusets.txt
+++ b/Documentation/cpusets.txt
@@ -7,6 +7,7 @@ Written by Simon.Derr@bull.net
 Portions Copyright (c) 2004-2006 Silicon Graphics, Inc.
 Modified by Paul Jackson <pj@sgi.com>
 Modified by Christoph Lameter <clameter@sgi.com>
+Modified by Paul Menage <menage@google.com>
 
 CONTENTS:
 =========
@@ -16,10 +17,9 @@ CONTENTS:
   1.2 Why are cpusets needed ?
   1.3 How are cpusets implemented ?
   1.4 What are exclusive cpusets ?
-  1.5 What does notify_on_release do ?
-  1.6 What is memory_pressure ?
-  1.7 What is memory spread ?
-  1.8 How do I use cpusets ?
+  1.5 What is memory_pressure ?
+  1.6 What is memory spread ?
+  1.7 How do I use cpusets ?
 2. Usage Examples and Syntax
   2.1 Basic Usage
   2.2 Adding/removing cpus
@@ -44,18 +44,19 @@ hierarchy visible in a virtual file system.  These are the essential
 hooks, beyond what is already present, required to manage dynamic
 job placement on large systems.
 
-Each task has a pointer to a cpuset.  Multiple tasks may reference
-the same cpuset.  Requests by a task, using the sched_setaffinity(2)
-system call to include CPUs in its CPU affinity mask, and using the
-mbind(2) and set_mempolicy(2) system calls to include Memory Nodes
-in its memory policy, are both filtered through that tasks cpuset,
-filtering out any CPUs or Memory Nodes not in that cpuset.  The
-scheduler will not schedule a task on a CPU that is not allowed in
-its cpus_allowed vector, and the kernel page allocator will not
-allocate a page on a node that is not allowed in the requesting tasks
-mems_allowed vector.
-
-User level code may create and destroy cpusets by name in the cpuset
+Cpusets use the generic cgroup subsystem described in
+Documentation/cgroup.txt.
+
+Requests by a task, using the sched_setaffinity(2) system call to
+include CPUs in its CPU affinity mask, and using the mbind(2) and
+set_mempolicy(2) system calls to include Memory Nodes in its memory
+policy, are both filtered through that tasks cpuset, filtering out any
+CPUs or Memory Nodes not in that cpuset.  The scheduler will not
+schedule a task on a CPU that is not allowed in its cpus_allowed
+vector, and the kernel page allocator will not allocate a page on a
+node that is not allowed in the requesting tasks mems_allowed vector.
+
+User level code may create and destroy cpusets by name in the cgroup
 virtual file system, manage the attributes and permissions of these
 cpusets and which CPUs and Memory Nodes are assigned to each cpuset,
 specify and query to which cpuset a task is assigned, and list the
@@ -115,7 +116,7 @@ Cpusets extends these two mechanisms as follows:
  - Cpusets are sets of allowed CPUs and Memory Nodes, known to the
    kernel.
  - Each task in the system is attached to a cpuset, via a pointer
-   in the task structure to a reference counted cpuset structure.
+   in the task structure to a reference counted cgroup structure.
  - Calls to sched_setaffinity are filtered to just those CPUs
    allowed in that tasks cpuset.
  - Calls to mbind and set_mempolicy are filtered to just
@@ -145,15 +146,10 @@ into the rest of the kernel, none in performance critical paths:
  - in page_alloc.c, to restrict memory to allowed nodes.
  - in vmscan.c, to restrict page recovery to the current cpuset.
 
-In addition a new file system, of type "cpuset" may be mounted,
-typically at /dev/cpuset, to enable browsing and modifying the cpusets
-presently known to the kernel.  No new system calls are added for
-cpusets - all support for querying and modifying cpusets is via
-this cpuset file system.
-
-Each task under /proc has an added file named 'cpuset', displaying
-the cpuset name, as the path relative to the root of the cpuset file
-system.
+You should mount the "cgroup" filesystem type in order to enable
+browsing and modifying the cpusets presently known to the kernel.  No
+new system calls are added for cpusets - all support for querying and
+modifying cpusets is via this cpuset file system.
 
 The /proc/<pid>/status file for each task has two added lines,
 displaying the tasks cpus_allowed (on which CPUs it may be scheduled)
@@ -163,16 +159,15 @@ in the format seen in the following example:
   Cpus_allowed:   ffffffff,ffffffff,ffffffff,ffffffff
   Mems_allowed:   ffffffff,ffffffff
 
-Each cpuset is represented by a directory in the cpuset file system
-containing the following files describing that cpuset:
+Each cpuset is represented by a directory in the cgroup file system
+containing (on top of the standard cgroup files) the following
+files describing that cpuset:
 
  - cpus: list of CPUs in that cpuset
  - mems: list of Memory Nodes in that cpuset
  - memory_migrate flag: if set, move pages to cpusets nodes
  - cpu_exclusive flag: is cpu placement exclusive?
  - mem_exclusive flag: is memory placement exclusive?
- - tasks: list of tasks (by pid) attached to that cpuset
- - notify_on_release flag: run /sbin/cpuset_release_agent on exit?
  - memory_pressure: measure of how much paging pressure in cpuset
 
 In addition, the root cpuset only has the following file:
@@ -237,21 +232,7 @@ such as requests from interrupt handlers, is allowed to be taken
 outside even a mem_exclusive cpuset.
 
 
-1.5 What does notify_on_release do ?
-------------------------------------
-
-If the notify_on_release flag is enabled (1) in a cpuset, then whenever
-the last task in the cpuset leaves (exits or attaches to some other
-cpuset) and the last child cpuset of that cpuset is removed, then
-the kernel runs the command /sbin/cpuset_release_agent, supplying the
-pathname (relative to the mount point of the cpuset file system) of the
-abandoned cpuset.  This enables automatic removal of abandoned cpusets.
-The default value of notify_on_release in the root cpuset at system
-boot is disabled (0).  The default value of other cpusets at creation
-is the current value of their parents notify_on_release setting.
-
-
-1.6 What is memory_pressure ?
+1.5 What is memory_pressure ?
 -----------------------------
 The memory_pressure of a cpuset provides a simple per-cpuset metric
 of the rate that the tasks in a cpuset are attempting to free up in
@@ -308,7 +289,7 @@ the tasks in the cpuset, in units of reclaims attempted per second,
 times 1000.
 
 
-1.7 What is memory spread ?
+1.6 What is memory spread ?
 ---------------------------
 There are two boolean flag files per cpuset that control where the
 kernel allocates pages for the file system buffers and related in
@@ -379,7 +360,7 @@ data set, the memory allocation across the nodes in the jobs cpuset
 can become very uneven.
 
 
-1.8 How do I use cpusets ?
+1.7 How do I use cpusets ?
 --------------------------
 
 In order to minimize the impact of cpusets on critical kernel
@@ -469,7 +450,7 @@ than stress the kernel.
 To start a new job that is to be contained within a cpuset, the steps are:
 
  1) mkdir /dev/cpuset
- 2) mount -t cpuset none /dev/cpuset
+ 2) mount -t cgroup -ocpuset cpuset /dev/cpuset
  3) Create the new cpuset by doing mkdir's and write's (or echo's) in
     the /dev/cpuset virtual file system.
  4) Start a task that will be the "founding father" of the new job.
@@ -481,7 +462,7 @@ For example, the following sequence of commands will setup a cpuset
 named "Charlie", containing just CPUs 2 and 3, and Memory Node 1,
 and then start a subshell 'sh' in that cpuset:
 
-  mount -t cpuset none /dev/cpuset
+  mount -t cgroup -ocpuset cpuset /dev/cpuset
   cd /dev/cpuset
   mkdir Charlie
   cd Charlie
@@ -513,7 +494,7 @@ Creating, modifying, using the cpusets can be done through the cpuset
 virtual filesystem.
 
 To mount it, type:
-# mount -t cpuset none /dev/cpuset
+# mount -t cgroup -o cpuset cpuset /dev/cpuset
 
 Then under /dev/cpuset you can find a tree that corresponds to the
 tree of the cpusets in the system. For instance, /dev/cpuset
@@ -556,6 +537,18 @@ To remove a cpuset, just use rmdir:
 This will fail if the cpuset is in use (has cpusets inside, or has
 processes attached).
 
+Note that for legacy reasons, the "cpuset" filesystem exists as a
+wrapper around the cgroup filesystem.
+
+The command
+
+mount -t cpuset X /dev/cpuset
+
+is equivalent to
+
+mount -t cgroup -ocpuset X /dev/cpuset
+echo "/sbin/cpuset_release_agent" > /dev/cpuset/release_agent
+
 2.2 Adding/removing cpus
 ------------------------
 
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 0e9a9aa9df6..fbff900fd5a 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -2131,7 +2131,7 @@ static const struct pid_entry tgid_base_stuff[] = {
 #ifdef CONFIG_SCHEDSTATS
 	INF("schedstat",  S_IRUGO, pid_schedstat),
 #endif
-#ifdef CONFIG_CPUSETS
+#ifdef CONFIG_PROC_PID_CPUSET
 	REG("cpuset",     S_IRUGO, cpuset),
 #endif
 #ifdef CONFIG_CGROUPS
@@ -2420,7 +2420,7 @@ static const struct pid_entry tid_base_stuff[] = {
 #ifdef CONFIG_SCHEDSTATS
 	INF("schedstat", S_IRUGO, pid_schedstat),
 #endif
-#ifdef CONFIG_CPUSETS
+#ifdef CONFIG_PROC_PID_CPUSET
 	REG("cpuset",    S_IRUGO, cpuset),
 #endif
 #ifdef CONFIG_CGROUPS
diff --git a/include/linux/cgroup_subsys.h b/include/linux/cgroup_subsys.h
index f8eddbbcad9..b152b51a436 100644
--- a/include/linux/cgroup_subsys.h
+++ b/include/linux/cgroup_subsys.h
@@ -7,4 +7,10 @@
 
 /* */
 
+#ifdef CONFIG_CPUSETS
+SUBSYS(cpuset)
+#endif
+
+/* */
+
 /* */
diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h
index ea44d2e768a..31adfde1c95 100644
--- a/include/linux/cpuset.h
+++ b/include/linux/cpuset.h
@@ -11,6 +11,7 @@
 #include <linux/sched.h>
 #include <linux/cpumask.h>
 #include <linux/nodemask.h>
+#include <linux/cgroup.h>
 
 #ifdef CONFIG_CPUSETS
 
@@ -19,8 +20,6 @@ extern int number_of_cpusets;	/* How many cpusets are defined in system? */
 extern int cpuset_init_early(void);
 extern int cpuset_init(void);
 extern void cpuset_init_smp(void);
-extern void cpuset_fork(struct task_struct *p);
-extern void cpuset_exit(struct task_struct *p);
 extern cpumask_t cpuset_cpus_allowed(struct task_struct *p);
 extern nodemask_t cpuset_mems_allowed(struct task_struct *p);
 #define cpuset_current_mems_allowed (current->mems_allowed)
@@ -76,13 +75,13 @@ static inline int cpuset_do_slab_mem_spread(void)
 
 extern void cpuset_track_online_nodes(void);
 
+extern int current_cpuset_is_being_rebound(void);
+
 #else /* !CONFIG_CPUSETS */
 
 static inline int cpuset_init_early(void) { return 0; }
 static inline int cpuset_init(void) { return 0; }
 static inline void cpuset_init_smp(void) {}
-static inline void cpuset_fork(struct task_struct *p) {}
-static inline void cpuset_exit(struct task_struct *p) {}
 
 static inline cpumask_t cpuset_cpus_allowed(struct task_struct *p)
 {
@@ -148,6 +147,11 @@ static inline int cpuset_do_slab_mem_spread(void)
 
 static inline void cpuset_track_online_nodes(void) {}
 
+static inline int current_cpuset_is_being_rebound(void)
+{
+	return 0;
+}
+
 #endif /* !CONFIG_CPUSETS */
 
 #endif /* _LINUX_CPUSET_H */
diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h
index 38c04d61ee0..59c4865bc85 100644
--- a/include/linux/mempolicy.h
+++ b/include/linux/mempolicy.h
@@ -148,14 +148,6 @@ extern void mpol_rebind_task(struct task_struct *tsk,
 					const nodemask_t *new);
 extern void mpol_rebind_mm(struct mm_struct *mm, nodemask_t *new);
 extern void mpol_fix_fork_child_flag(struct task_struct *p);
-#define set_cpuset_being_rebound(x) (cpuset_being_rebound = (x))
-
-#ifdef CONFIG_CPUSETS
-#define current_cpuset_is_being_rebound() \
-				(cpuset_being_rebound == current->cpuset)
-#else
-#define current_cpuset_is_being_rebound() 0
-#endif
 
 extern struct mempolicy default_policy;
 extern struct zonelist *huge_zonelist(struct vm_area_struct *vma,
@@ -173,8 +165,6 @@ static inline void check_highest_zone(enum zone_type k)
 int do_migrate_pages(struct mm_struct *mm,
 	const nodemask_t *from_nodes, const nodemask_t *to_nodes, int flags);
 
-extern void *cpuset_being_rebound;	/* Trigger mpol_copy vma rebind */
-
 #else
 
 struct mempolicy {};
@@ -248,8 +238,6 @@ static inline void mpol_fix_fork_child_flag(struct task_struct *p)
 {
 }
 
-#define set_cpuset_being_rebound(x) do {} while (0)
-
 static inline struct zonelist *huge_zonelist(struct vm_area_struct *vma,
  		unsigned long addr, gfp_t gfp_flags, struct mempolicy **mpol)
 {
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 1aa1cfa63b3..93a55f2e5ef 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -756,8 +756,6 @@ static inline int above_background_load(void)
 }
 
 struct io_context;			/* See blkdev.h */
-struct cpuset;
-
 #define NGROUPS_SMALL		32
 #define NGROUPS_PER_BLOCK	((int)(PAGE_SIZE / sizeof(gid_t)))
 struct group_info {
@@ -1125,7 +1123,6 @@ struct task_struct {
 	short il_next;
 #endif
 #ifdef CONFIG_CPUSETS
-	struct cpuset *cpuset;
 	nodemask_t mems_allowed;
 	int cpuset_mems_generation;
 	int cpuset_mem_spread_rotor;
diff --git a/init/Kconfig b/init/Kconfig
index 51b3d14f44f..18b1abc677d 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -280,7 +280,7 @@ config CGROUPS
 
 config CPUSETS
 	bool "Cpuset support"
-	depends on SMP
+	depends on SMP && CGROUPS
 	help
 	  This option will let you create and manage CPUSETs which
 	  allow dynamically partitioning a system into sets of CPUs and
@@ -330,6 +330,11 @@ config SYSFS_DEPRECATED
 	  If you are using a distro that was released in 2006 or later,
 	  it should be safe to say N here.
 
+config PROC_PID_CPUSET
+	bool "Include legacy /proc/<pid>/cpuset file"
+	depends on CPUSETS
+	default y
+
 config RELAY
 	bool "Kernel->user space relay support (formerly relayfs)"
 	help
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index a40a2c4384b..1133062395e 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -5,6 +5,7 @@
  *
  *  Copyright (C) 2003 BULL SA.
  *  Copyright (C) 2004-2006 Silicon Graphics, Inc.
+ *  Copyright (C) 2006 Google, Inc
  *
  *  Portions derived from Patrick Mochel's sysfs code.
  *  sysfs is Copyright (c) 2001-3 Patrick Mochel
@@ -12,6 +13,7 @@
  *  2003-10-10 Written by Simon Derr.
  *  2003-10-22 Updates by Stephen Hemminger.
  *  2004 May-July Rework by Paul Jackson.
+ *  2006 Rework by Paul Menage to use generic cgroups
  *
  *  This file is subject to the terms and conditions of the GNU General Public
  *  License.  See the file COPYING in the main directory of the Linux
@@ -53,8 +55,6 @@
 #include <asm/atomic.h>
 #include <linux/mutex.h>
 
-#define CPUSET_SUPER_MAGIC		0x27e0eb
-
 /*
  * Tracks how many cpusets are currently defined in system.
  * When there is only one cpuset (the root cpuset) we can
@@ -62,6 +62,10 @@
  */
 int number_of_cpusets __read_mostly;
 
+/* Retrieve the cpuset from a cgroup */
+struct cgroup_subsys cpuset_subsys;
+struct cpuset;
+
 /* See "Frequency meter" comments, below. */
 
 struct fmeter {
@@ -72,24 +76,13 @@ struct fmeter {
 };
 
 struct cpuset {
+	struct cgroup_subsys_state css;
+
 	unsigned long flags;		/* "unsigned long" so bitops work */
 	cpumask_t cpus_allowed;		/* CPUs allowed to tasks in cpuset */
 	nodemask_t mems_allowed;	/* Memory Nodes allowed to tasks */
 
-	/*
-	 * Count is atomic so can incr (fork) or decr (exit) without a lock.
-	 */
-	atomic_t count;			/* count tasks using this cpuset */
-
-	/*
-	 * We link our 'sibling' struct into our parents 'children'.
-	 * Our children link their 'sibling' into our 'children'.
-	 */
-	struct list_head sibling;	/* my parents children */
-	struct list_head children;	/* my children */
-
 	struct cpuset *parent;		/* my parent */
-	struct dentry *dentry;		/* cpuset fs entry */
 
 	/*
 	 * Copy of global cpuset_mems_generation as of the most
@@ -100,13 +93,26 @@ struct cpuset {
 	struct fmeter fmeter;		/* memory_pressure filter */
 };
 
+/* Retrieve the cpuset for a cgroup */
+static inline struct cpuset *cgroup_cs(struct cgroup *cont)
+{
+	return container_of(cgroup_subsys_state(cont, cpuset_subsys_id),
+			    struct cpuset, css);
+}
+
+/* Retrieve the cpuset for a task */
+static inline struct cpuset *task_cs(struct task_struct *task)
+{
+	return container_of(task_subsys_state(task, cpuset_subsys_id),
+			    struct cpuset, css);
+}
+
+
 /* bits in struct cpuset flags field */
 typedef enum {
 	CS_CPU_EXCLUSIVE,
 	CS_MEM_EXCLUSIVE,
 	CS_MEMORY_MIGRATE,
-	CS_REMOVED,
-	CS_NOTIFY_ON_RELEASE,
 	CS_SPREAD_PAGE,
 	CS_SPREAD_SLAB,
 } cpuset_flagbits_t;
@@ -122,16 +128,6 @@ static inline int is_mem_exclusive(const struct cpuset *cs)
 	return test_bit(CS_MEM_EXCLUSIVE, &cs->flags);
 }
 
-static inline int is_removed(const struct cpuset *cs)
-{
-	return test_bit(CS_REMOVED, &cs->flags);
-}
-
-static inline int notify_on_release(const struct cpuset *cs)
-{
-	return test_bit(CS_NOTIFY_ON_RELEASE, &cs->flags);
-}
-
 static inline int is_memory_migrate(const struct cpuset *cs)
 {
 	return test_bit(CS_MEMORY_MIGRATE, &cs->flags);
@@ -172,14 +168,8 @@ static struct cpuset top_cpuset = {
 	.flags = ((1 << CS_CPU_EXCLUSIVE) | (1 << CS_MEM_EXCLUSIVE)),
 	.cpus_allowed = CPU_MASK_ALL,
 	.mems_allowed = NODE_MASK_ALL,
-	.count = ATOMIC_INIT(0),
-	.sibling = LIST_HEAD_INIT(top_cpuset.sibling),
-	.children = LIST_HEAD_INIT(top_cpuset.children),
 };
 
-static struct vfsmount *cpuset_mount;
-static struct super_block *cpuset_sb;
-
 /*
  * We have two global cpuset mutexes below.  They can nest.
  * It is ok to first take manage_mutex, then nest callback_mutex.  We also
@@ -263,297 +253,33 @@ static struct super_block *cpuset_sb;
  * the routine cpuset_update_task_memory_state().
  */
 
-static DEFINE_MUTEX(manage_mutex);
 static DEFINE_MUTEX(callback_mutex);
 
-/*
- * A couple of forward declarations required, due to cyclic reference loop:
- *  cpuset_mkdir -> cpuset_create -> cpuset_populate_dir -> cpuset_add_file
- *  -> cpuset_create_file -> cpuset_dir_inode_operations -> cpuset_mkdir.
- */
-
-static int cpuset_mkdir(struct inode *dir, struct dentry *dentry, int mode);
-static int cpuset_rmdir(struct inode *unused_dir, struct dentry *dentry);
-
-static struct backing_dev_info cpuset_backing_dev_info = {
-	.ra_pages = 0,		/* No readahead */
-	.capabilities	= BDI_CAP_NO_ACCT_DIRTY | BDI_CAP_NO_WRITEBACK,
-};
-
-static struct inode *cpuset_new_inode(mode_t mode)
-{
-	struct inode *inode = new_inode(cpuset_sb);
-
-	if (inode) {
-		inode->i_mode = mode;
-		inode->i_uid = current->fsuid;
-		inode->i_gid = current->fsgid;
-		inode->i_blocks = 0;
-		inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
-		inode->i_mapping->backing_dev_info = &cpuset_backing_dev_info;
-	}
-	return inode;
-}
-
-static void cpuset_diput(struct dentry *dentry, struct inode *inode)
-{
-	/* is dentry a directory ? if so, kfree() associated cpuset */
-	if (S_ISDIR(inode->i_mode)) {
-		struct cpuset *cs = dentry->d_fsdata;
-		BUG_ON(!(is_removed(cs)));
-		kfree(cs);
-	}
-	iput(inode);
-}
-
-static struct dentry_operations cpuset_dops = {
-	.d_iput = cpuset_diput,
-};
-
-static struct dentry *cpuset_get_dentry(struct dentry *parent, const char *name)
-{
-	struct dentry *d = lookup_one_len(name, parent, strlen(name));
-	if (!IS_ERR(d))
-		d->d_op = &cpuset_dops;
-	return d;
-}
-
-static void remove_dir(struct dentry *d)
-{
-	struct dentry *parent = dget(d->d_parent);
-
-	d_delete(d);
-	simple_rmdir(parent->d_inode, d);
-	dput(parent);
-}
-
-/*
- * NOTE : the dentry must have been dget()'ed
- */
-static void cpuset_d_remove_dir(struct dentry *dentry)
-{
-	struct list_head *node;
-
-	spin_lock(&dcache_lock);
-	node = dentry->d_subdirs.next;
-	while (node != &dentry->d_subdirs) {
-		struct dentry *d = list_entry(node, struct dentry, d_u.d_child);
-		list_del_init(node);
-		if (d->d_inode) {
-			d = dget_locked(d);
-			spin_unlock(&dcache_lock);
-			d_delete(d);
-			simple_unlink(dentry->d_inode, d);
-			dput(d);
-			spin_lock(&dcache_lock);
-		}
-		node = dentry->d_subdirs.next;
-	}
-	list_del_init(&dentry->d_u.d_child);
-	spin_unlock(&dcache_lock);
-	remove_dir(dentry);
-}
-
-static struct super_operations cpuset_ops = {
-	.statfs = simple_statfs,
-	.drop_inode = generic_delete_inode,
-};
-
-static int cpuset_fill_super(struct super_block *sb, void *unused_data,
-							int unused_silent)
-{
-	struct inode *inode;
-	struct dentry *root;
-
-	sb->s_blocksize = PAGE_CACHE_SIZE;
-	sb->s_blocksize_bits = PAGE_CACHE_SHIFT;
-	sb->s_magic = CPUSET_SUPER_MAGIC;
-	sb->s_op = &cpuset_ops;
-	cpuset_sb = sb;
-
-	inode = cpuset_new_inode(S_IFDIR | S_IRUGO | S_IXUGO | S_IWUSR);
-	if (inode) {
-		inode->i_op = &simple_dir_inode_operations;
-		inode->i_fop = &simple_dir_operations;
-		/* directories start off with i_nlink == 2 (for "." entry) */
-		inc_nlink(inode);
-	} else {
-		return -ENOMEM;
-	}
-
-	root = d_alloc_root(inode);
-	if (!root) {
-		iput(inode);
-		return -ENOMEM;
-	}
-	sb->s_root = root;
-	return 0;
-}
-
+/* This is ugly, but preserves the userspace API for existing cpuset
+ * users. If someone tries to mount the "cpuset" filesystem, we
+ * silently switch it to mount "cgroup" instead */
 static int cpuset_get_sb(struct file_system_type *fs_type,
 			 int flags, const char *unused_dev_name,
 			 void *data, struct vfsmount *mnt)
 {
-	return get_sb_single(fs_type, flags, data, cpuset_fill_super, mnt);
+	struct file_system_type *cgroup_fs = get_fs_type("cgroup");
+	int ret = -ENODEV;
+	if (cgroup_fs) {
+		char mountopts[] =
+			"cpuset,noprefix,"
+			"release_agent=/sbin/cpuset_release_agent";
+		ret = cgroup_fs->get_sb(cgroup_fs, flags,
+					   unused_dev_name, mountopts, mnt);
+		put_filesystem(cgroup_fs);
+	}
+	return ret;
 }
 
 static struct file_system_type cpuset_fs_type = {
 	.name = "cpuset",
 	.get_sb = cpuset_get_sb,
-	.kill_sb = kill_litter_super,
 };
 
-/* struct cftype:
- *
- * The files in the cpuset filesystem mostly have a very simple read/write
- * handling, some common function will take care of it. Nevertheless some cases
- * (read tasks) are special and therefore I define this structure for every
- * kind of file.
- *
- *
- * When reading/writing to a file:
- *	- the cpuset to use in file->f_path.dentry->d_parent->d_fsdata
- *	- the 'cftype' of the file is file->f_path.dentry->d_fsdata
- */
-
-struct cftype {
-	char *name;
-	int private;
-	int (*open) (struct inode *inode, struct file *file);
-	ssize_t (*read) (struct file *file, char __user *buf, size_t nbytes,
-							loff_t *ppos);
-	int (*write) (struct file *file, const char __user *buf, size_t nbytes,
-							loff_t *ppos);
-	int (*release) (struct inode *inode, struct file *file);
-};
-
-static inline struct cpuset *__d_cs(struct dentry *dentry)
-{
-	return dentry->d_fsdata;
-}
-
-static inline struct cftype *__d_cft(struct dentry *dentry)
-{
-	return dentry->d_fsdata;
-}
-
-/*
- * Call with manage_mutex held.  Writes path of cpuset into buf.
- * Returns 0 on success, -errno on error.
- */
-
-static int cpuset_path(const struct cpuset *cs, char *buf, int buflen)
-{
-	char *start;
-
-	start = buf + buflen;
-
-	*--start = '\0';
-	for (;;) {
-		int len = cs->dentry->d_name.len;
-		if ((start -= len) < buf)
-			return -ENAMETOOLONG;
-		memcpy(start, cs->dentry->d_name.name, len);
-		cs = cs->parent;
-		if (!cs)
-			break;
-		if (!cs->parent)
-			continue;
-		if (--start < buf)
-			return -ENAMETOOLONG;
-		*start = '/';
-	}
-	memmove(buf, start, buf + buflen - start);
-	return 0;
-}
-
-/*
- * Notify userspace when a cpuset is released, by running
- * /sbin/cpuset_release_agent with the name of the cpuset (path
- * relative to the root of cpuset file system) as the argument.
- *
- * Most likely, this user command will try to rmdir this cpuset.
- *
- * This races with the possibility that some other task will be
- * attached to this cpuset before it is removed, or that some other
- * user task will 'mkdir' a child cpuset of this cpuset.  That's ok.
- * The presumed 'rmdir' will fail quietly if this cpuset is no longer
- * unused, and this cpuset will be reprieved from its death sentence,
- * to continue to serve a useful existence.  Next time it's released,
- * we will get notified again, if it still has 'notify_on_release' set.
- *
- * The final arg to call_usermodehelper() is 0, which means don't
- * wait.  The separate /sbin/cpuset_release_agent task is forked by
- * call_usermodehelper(), then control in this thread returns here,
- * without waiting for the release agent task.  We don't bother to
- * wait because the caller of this routine has no use for the exit
- * status of the /sbin/cpuset_release_agent task, so no sense holding
- * our caller up for that.
- *
- * When we had only one cpuset mutex, we had to call this
- * without holding it, to avoid deadlock when call_usermodehelper()
- * allocated memory.  With two locks, we could now call this while
- * holding manage_mutex, but we still don't, so as to minimize
- * the time manage_mutex is held.
- */
-
-static void cpuset_release_agent(const char *pathbuf)
-{
-	char *argv[3], *envp[3];
-	int i;
-
-	if (!pathbuf)
-		return;
-
-	i = 0;
-	argv[i++] = "/sbin/cpuset_release_agent";
-	argv[i++] = (char *)pathbuf;
-	argv[i] = NULL;
-
-	i = 0;
-	/* minimal command environment */
-	envp[i++] = "HOME=/";
-	envp[i++] = "PATH=/sbin:/bin:/usr/sbin:/usr/bin";
-	envp[i] = NULL;
-
-	call_usermodehelper(argv[0], argv, envp, UMH_WAIT_EXEC);
-	kfree(pathbuf);
-}
-
-/*
- * Either cs->count of using tasks transitioned to zero, or the
- * cs->children list of child cpusets just became empty.  If this
- * cs is notify_on_release() and now both the user count is zero and
- * the list of children is empty, prepare cpuset path in a kmalloc'd
- * buffer, to be returned via ppathbuf, so that the caller can invoke
- * cpuset_release_agent() with it later on, once manage_mutex is dropped.
- * Call here with manage_mutex held.
- *
- * This check_for_release() routine is responsible for kmalloc'ing
- * pathbuf.  The above cpuset_release_agent() is responsible for
- * kfree'ing pathbuf.  The caller of these routines is responsible
- * for providing a pathbuf pointer, initialized to NULL, then
- * calling check_for_release() with manage_mutex held and the address
- * of the pathbuf pointer, then dropping manage_mutex, then calling
- * cpuset_release_agent() with pathbuf, as set by check_for_release().
- */
-
-static void check_for_release(struct cpuset *cs, char **ppathbuf)
-{
-	if (notify_on_release(cs) && atomic_read(&cs->count) == 0 &&
-	    list_empty(&cs->children)) {
-		char *buf;
-
-		buf = kmalloc(PAGE_SIZE, GFP_KERNEL);
-		if (!buf)
-			return;
-		if (cpuset_path(cs, buf, PAGE_SIZE) < 0)
-			kfree(buf);
-		else
-			*ppathbuf = buf;
-	}
-}
-
 /*
  * Return in *pmask the portion of a cpusets's cpus_allowed that
  * are online.  If none are online, walk up the cpuset hierarchy
@@ -653,20 +379,19 @@ void cpuset_update_task_memory_state(void)
 	struct task_struct *tsk = current;
 	struct cpuset *cs;
 
-	if (tsk->cpuset == &top_cpuset) {
+	if (task_cs(tsk) == &top_cpuset) {
 		/* Don't need rcu for top_cpuset.  It's never freed. */
 		my_cpusets_mem_gen = top_cpuset.mems_generation;
 	} else {
 		rcu_read_lock();
-		cs = rcu_dereference(tsk->cpuset);
-		my_cpusets_mem_gen = cs->mems_generation;
+		my_cpusets_mem_gen = task_cs(current)->mems_generation;
 		rcu_read_unlock();
 	}
 
 	if (my_cpusets_mem_gen != tsk->cpuset_mems_generation) {
 		mutex_lock(&callback_mutex);
 		task_lock(tsk);
-		cs = tsk->cpuset;	/* Maybe changed when task not locked */
+		cs = task_cs(tsk); /* Maybe changed when task not locked */
 		guarantee_online_mems(cs, &tsk->mems_allowed);
 		tsk->cpuset_mems_generation = cs->mems_generation;
 		if (is_spread_page(cs))
@@ -721,11 +446,12 @@ static int is_cpuset_subset(const struct cpuset *p, const struct cpuset *q)
 
 static int validate_change(const struct cpuset *cur, const struct cpuset *trial)
 {
+	struct cgroup *cont;
 	struct cpuset *c, *par;
 
 	/* Each of our child cpusets must be a subset of us */
-	list_for_each_entry(c, &cur->children, sibling) {
-		if (!is_cpuset_subset(c, trial))
+	list_for_each_entry(cont, &cur->css.cgroup->children, sibling) {
+		if (!is_cpuset_subset(cgroup_cs(cont), trial))
 			return -EBUSY;
 	}
 
@@ -740,7 +466,8 @@ static int validate_change(const struct cpuset *cur, const struct cpuset *trial)
 		return -EACCES;
 
 	/* If either I or some sibling (!= me) is exclusive, we can't overlap */
-	list_for_each_entry(c, &par->children, sibling) {
+	list_for_each_entry(cont, &par->css.cgroup->children, sibling) {
+		c = cgroup_cs(cont);
 		if ((is_cpu_exclusive(trial) || is_cpu_exclusive(c)) &&
 		    c != cur &&
 		    cpus_intersects(trial->cpus_allowed, c->cpus_allowed))
@@ -783,7 +510,8 @@ static int update_cpumask(struct cpuset *cs, char *buf)
 	}
 	cpus_and(trialcs.cpus_allowed, trialcs.cpus_allowed, cpu_online_map);
 	/* cpus_allowed cannot be empty for a cpuset with attached tasks. */
-	if (atomic_read(&cs->count) && cpus_empty(trialcs.cpus_allowed))
+	if (cgroup_task_count(cs->css.cgroup) &&
+	    cpus_empty(trialcs.cpus_allowed))
 		return -ENOSPC;
 	retval = validate_change(cs, &trialcs);
 	if (retval < 0)
@@ -839,7 +567,7 @@ static void cpuset_migrate_mm(struct mm_struct *mm, const nodemask_t *from,
 	do_migrate_pages(mm, from, to, MPOL_MF_MOVE_ALL);
 
 	mutex_lock(&callback_mutex);
-	guarantee_online_mems(tsk->cpuset, &tsk->mems_allowed);
+	guarantee_online_mems(task_cs(tsk),&tsk->mems_allowed);
 	mutex_unlock(&callback_mutex);
 }
 
@@ -857,16 +585,19 @@ static void cpuset_migrate_mm(struct mm_struct *mm, const nodemask_t *from,
  * their mempolicies to the cpusets new mems_allowed.
  */
 
+static void *cpuset_being_rebound;
+
 static int update_nodemask(struct cpuset *cs, char *buf)
 {
 	struct cpuset trialcs;
 	nodemask_t oldmem;
-	struct task_struct *g, *p;
+	struct task_struct *p;
 	struct mm_struct **mmarray;
 	int i, n, ntasks;
 	int migrate;
 	int fudge;
 	int retval;
+	struct cgroup_iter it;
 
 	/*
 	 * top_cpuset.mems_allowed tracks node_stats[N_HIGH_MEMORY];
@@ -909,7 +640,8 @@ static int update_nodemask(struct cpuset *cs, char *buf)
 		goto done;
 	}
 	/* mems_allowed cannot be empty for a cpuset with attached tasks. */
-	if (atomic_read(&cs->count) && nodes_empty(trialcs.mems_allowed)) {
+	if (cgroup_task_count(cs->css.cgroup) &&
+	    nodes_empty(trialcs.mems_allowed)) {
 		retval = -ENOSPC;
 		goto done;
 	}
@@ -922,7 +654,7 @@ static int update_nodemask(struct cpuset *cs, char *buf)
 	cs->mems_generation = cpuset_mems_generation++;
 	mutex_unlock(&callback_mutex);
 
-	set_cpuset_being_rebound(cs);		/* causes mpol_copy() rebind */
+	cpuset_being_rebound = cs;		/* causes mpol_copy() rebind */
 
 	fudge = 10;				/* spare mmarray[] slots */
 	fudge += cpus_weight(cs->cpus_allowed);	/* imagine one fork-bomb/cpu */
@@ -936,13 +668,13 @@ static int update_nodemask(struct cpuset *cs, char *buf)
 	 * enough mmarray[] w/o using GFP_ATOMIC.
 	 */
 	while (1) {
-		ntasks = atomic_read(&cs->count);	/* guess */
+		ntasks = cgroup_task_count(cs->css.cgroup);  /* guess */
 		ntasks += fudge;
 		mmarray = kmalloc(ntasks * sizeof(*mmarray), GFP_KERNEL);
 		if (!mmarray)
 			goto done;
 		read_lock(&tasklist_lock);		/* block fork */
-		if (atomic_read(&cs->count) <= ntasks)
+		if (cgroup_task_count(cs->css.cgroup) <= ntasks)
 			break;				/* got enough */
 		read_unlock(&tasklist_lock);		/* try again */
 		kfree(mmarray);
@@ -951,21 +683,21 @@ static int update_nodemask(struct cpuset *cs, char *buf)
 	n = 0;
 
 	/* Load up mmarray[] with mm reference for each task in cpuset. */
-	do_each_thread(g, p) {
+	cgroup_iter_start(cs->css.cgroup, &it);
+	while ((p = cgroup_iter_next(cs->css.cgroup, &it))) {
 		struct mm_struct *mm;
 
 		if (n >= ntasks) {
 			printk(KERN_WARNING
 				"Cpuset mempolicy rebind incomplete.\n");
-			continue;
+			break;
 		}
-		if (p->cpuset != cs)
-			continue;
 		mm = get_task_mm(p);
 		if (!mm)
 			continue;
 		mmarray[n++] = mm;
-	} while_each_thread(g, p);
+	}
+	cgroup_iter_end(cs->css.cgroup, &it);
 	read_unlock(&tasklist_lock);
 
 	/*