Task Control Groups: basic task cgroup framework

Generic Process Control Groups
--------------------------

There have recently been various proposals floating around for
resource management/accounting and other task grouping subsystems in
the kernel, including ResGroups, User BeanCounters, NSProxy
cgroups, and others.  These all need the basic abstraction of being
able to group together multiple processes in an aggregate, in order to
track/limit the resources permitted to those processes, or control
other behaviour of the processes, and all implement this grouping in
different ways.

This patchset provides a framework for tracking and grouping processes
into arbitrary "cgroups" and assigning arbitrary state to those
groupings, in order to control the behaviour of the cgroup as an
aggregate.

The intention is that the various resource management and
virtualization/cgroup efforts can also become task cgroup
clients, with the result that:

- the userspace APIs are (somewhat) normalised

- it's easier to test e.g. the ResGroups CPU controller in
 conjunction with the BeanCounters memory controller, or use either of
them as the resource-control portion of a virtual server system.

- the additional kernel footprint of any of the competing resource
 management systems is substantially reduced, since it doesn't need
 to provide process grouping/containment, hence improving their
 chances of getting into the kernel

This patch:

Add the main task cgroups framework - the cgroup filesystem, and the
basic structures for tracking membership and associating subsystem state
objects to tasks.
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>

include/linux/cgroup.h

+#ifndef _LINUX_CGROUP_H
+#define _LINUX_CGROUP_H
+/*
+ *  cgroup interface
+ *
+ *  Copyright (C) 2003 BULL SA
+ *  Copyright (C) 2004-2006 Silicon Graphics, Inc.
+ *
+ */
+
+#include <linux/sched.h>
+#include <linux/kref.h>
+#include <linux/cpumask.h>
+#include <linux/nodemask.h>
+#include <linux/rcupdate.h>
+
+#ifdef CONFIG_CGROUPS
+
+struct cgroupfs_root;
+struct cgroup_subsys;
+struct inode;
+
+extern int cgroup_init_early(void);
+extern int cgroup_init(void);
+extern void cgroup_init_smp(void);
+extern void cgroup_lock(void);
+extern void cgroup_unlock(void);
+
+/* Per-subsystem/per-cgroup state maintained by the system. */
+struct cgroup_subsys_state {
+	/* The cgroup that this subsystem is attached to. Useful
+	 * for subsystems that want to know about the cgroup
+	 * hierarchy structure */
+	struct cgroup *cgroup;
+
+	/* State maintained by the cgroup system to allow
+	 * subsystems to be "busy". Should be accessed via css_get()
+	 * and css_put() */
+
+	atomic_t refcnt;
+
+	unsigned long flags;
+};
+
+/* bits in struct cgroup_subsys_state flags field */
+enum {
+	CSS_ROOT, /* This CSS is the root of the subsystem */
+};
+
+/*
+ * Call css_get() to hold a reference on the cgroup;
+ *
+ */
+
+static inline void css_get(struct cgroup_subsys_state *css)
+{
+	/* We don't need to reference count the root state */
+	if (!test_bit(CSS_ROOT, &css->flags))
+		atomic_inc(&css->refcnt);
+}
+/*
+ * css_put() should be called to release a reference taken by
+ * css_get()
+ */
+
+static inline void css_put(struct cgroup_subsys_state *css)
+{
+	if (!test_bit(CSS_ROOT, &css->flags))
+		atomic_dec(&css->refcnt);
+}
+
+struct cgroup {
+	unsigned long flags;		/* "unsigned long" so bitops work */
+
+	/* count users of this cgroup. >0 means busy, but doesn't
+	 * necessarily indicate the number of tasks in the
+	 * cgroup */
+	atomic_t count;
+
+	/*
+	 * We link our 'sibling' struct into our parent's 'children'.
+	 * Our children link their 'sibling' into our 'children'.
+	 */
+	struct list_head sibling;	/* my parent's children */
+	struct list_head children;	/* my children */
+
+	struct cgroup *parent;	/* my parent */
+	struct dentry *dentry;	  	/* cgroup fs entry */
+
+	/* Private pointers for each registered subsystem */
+	struct cgroup_subsys_state *subsys[CGROUP_SUBSYS_COUNT];
+
+	struct cgroupfs_root *root;
+	struct cgroup *top_cgroup;
+};
+
+/* struct cftype:
+ *
+ * The files in the cgroup 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 cgroup to use in file->f_dentry->d_parent->d_fsdata
+ *	- the 'cftype' of the file is file->f_dentry->d_fsdata
+ */
+
+#define MAX_CFTYPE_NAME 64
+struct cftype {
+	/* By convention, the name should begin with the name of the
+	 * subsystem, followed by a period */
+	char name[MAX_CFTYPE_NAME];
+	int private;
+	int (*open) (struct inode *inode, struct file *file);
+	ssize_t (*read) (struct cgroup *cont, struct cftype *cft,
+			 struct file *file,
+			 char __user *buf, size_t nbytes, loff_t *ppos);
+	/*
+	 * read_uint() is a shortcut for the common case of returning a
+	 * single integer. Use it in place of read()
+	 */
+	u64 (*read_uint) (struct cgroup *cont, struct cftype *cft);
+	ssize_t (*write) (struct cgroup *cont, struct cftype *cft,
+			  struct file *file,
+			  const char __user *buf, size_t nbytes, loff_t *ppos);
+	int (*release) (struct inode *inode, struct file *file);
+};
+
+/* Add a new file to the given cgroup directory. Should only be
+ * called by subsystems from within a populate() method */
+int cgroup_add_file(struct cgroup *cont, struct cgroup_subsys *subsys,
+		       const struct cftype *cft);
+
+/* Add a set of new files to the given cgroup directory. Should
+ * only be called by subsystems from within a populate() method */
+int cgroup_add_files(struct cgroup *cont,
+			struct cgroup_subsys *subsys,
+			const struct cftype cft[],
+			int count);
+
+int cgroup_is_removed(const struct cgroup *cont);
+
+int cgroup_path(const struct cgroup *cont, char *buf, int buflen);
+
+/* Return true if the cgroup is a descendant of the current cgroup */
+int cgroup_is_descendant(const struct cgroup *cont);
+
+/* Control Group subsystem type. See Documentation/cgroups.txt for details */
+
+struct cgroup_subsys {
+	struct cgroup_subsys_state *(*create)(struct cgroup_subsys *ss,
+						  struct cgroup *cont);
+	void (*destroy)(struct cgroup_subsys *ss, struct cgroup *cont);
+	int (*can_attach)(struct cgroup_subsys *ss,
+			  struct cgroup *cont, struct task_struct *tsk);
+	void (*attach)(struct cgroup_subsys *ss, struct cgroup *cont,
+			struct cgroup *old_cont, struct task_struct *tsk);
+	void (*fork)(struct cgroup_subsys *ss, struct task_struct *task);
+	void (*exit)(struct cgroup_subsys *ss, struct task_struct *task);
+	int (*populate)(struct cgroup_subsys *ss,
+			struct cgroup *cont);
+	void (*bind)(struct cgroup_subsys *ss, struct cgroup *root);
+	int subsys_id;
+	int active;
+	int early_init;
+#define MAX_CGROUP_TYPE_NAMELEN 32
+	const char *name;
+
+	/* Protected by RCU */
+	struct cgroupfs_root *root;
+
+	struct list_head sibling;
+
+	void *private;
+};
+
+#define SUBSYS(_x) extern struct cgroup_subsys _x ## _subsys;
+#include <linux/cgroup_subsys.h>
+#undef SUBSYS
+
+static inline struct cgroup_subsys_state *cgroup_subsys_state(
+	struct cgroup *cont, int subsys_id)
+{
+	return cont->subsys[subsys_id];
+}
+
+static inline struct cgroup_subsys_state *task_subsys_state(
+	struct task_struct *task, int subsys_id)
+{
+	return rcu_dereference(task->cgroups.subsys[subsys_id]);
+}
+
+static inline struct cgroup* task_cgroup(struct task_struct *task,
+					       int subsys_id)
+{
+	return task_subsys_state(task, subsys_id)->cgroup;
+}
+
+int cgroup_path(const struct cgroup *cont, char *buf, int buflen);
+
+#else /* !CONFIG_CGROUPS */
+
+static inline int cgroup_init_early(void) { return 0; }
+static inline int cgroup_init(void) { return 0; }
+static inline void cgroup_init_smp(void) {}
+
+static inline void cgroup_lock(void) {}
+static inline void cgroup_unlock(void) {}
+
+#endif /* !CONFIG_CGROUPS */
+
+#endif /* _LINUX_CGROUP_H */

include/linux/cgroup_subsys.h

+/* Add subsystem definitions of the form SUBSYS(<name>) in this
+ * file. Surround each one by a line of comment markers so that
+ * patches don't collide
+ */
+
+/* */
+
+/* */
+
+/* */

include/linux/magic.h

@@ -37,6 +37,7 @@
 
 #define SMB_SUPER_MAGIC		0x517B
 #define USBDEVICE_SUPER_MAGIC	0x9fa2
+#define CGROUP_SUPER_MAGIC	0x27e0eb
 
 #define FUTEXFS_SUPER_MAGIC	0xBAD1DEA
 #define INOTIFYFS_SUPER_MAGIC	0x2BAD1DEA

include/linux/sched.h

@@ -894,6 +894,34 @@ struct sched_entity {
 #endif
 };
 
+#ifdef CONFIG_CGROUPS
+
+#define SUBSYS(_x) _x ## _subsys_id,
+enum cgroup_subsys_id {
+#include <linux/cgroup_subsys.h>
+	CGROUP_SUBSYS_COUNT
+};
+#undef SUBSYS
+
+/* A css_set is a structure holding pointers to a set of
+ * cgroup_subsys_state objects.
+ */
+
+struct css_set {
+
+	/* Set of subsystem states, one for each subsystem. NULL for
+	 * subsystems that aren't part of this hierarchy. These
+	 * pointers reduce the number of dereferences required to get
+	 * from a task to its state for a given cgroup, but result
+	 * in increased space usage if tasks are in wildly different
+	 * groupings across different hierarchies. This array is
+	 * immutable after creation */
+	struct cgroup_subsys_state *subsys[CGROUP_SUBSYS_COUNT];
+
+};
+
+#endif /* CONFIG_CGROUPS */
+
 struct task_struct {
 	volatile long state;	/* -1 unrunnable, 0 runnable, >0 stopped */
 	void *stack;
@@ -1130,6 +1158,9 @@ struct task_struct {
 	int cpuset_mems_generation;
 	int cpuset_mem_spread_rotor;
 #endif
+#ifdef CONFIG_CGROUPS
+	struct css_set cgroups;
+#endif
 #ifdef CONFIG_FUTEX
 	struct robust_list_head __user *robust_list;
 #ifdef CONFIG_COMPAT
@@ -1625,7 +1656,8 @@ static inline int thread_group_empty(struct task_struct *p)
 /*
  * Protects ->fs, ->files, ->mm, ->group_info, ->comm, keyring
  * subscriptions and synchronises with wait4().  Also used in procfs.  Also
- * pins the final release of task.io_context.  Also protects ->cpuset.
+ * pins the final release of task.io_context.  Also protects ->cpuset and
+ * ->cgroup.subsys[].
  *
  * Nests both inside and outside of read_lock(&tasklist_lock).
  * It must not be nested with write_lock_irq(&tasklist_lock),

init/Kconfig

@@ -270,6 +270,14 @@ config LOG_BUF_SHIFT
 		     13 =>  8 KB
 		     12 =>  4 KB
 
+config CGROUPS
+	bool "Control Group support"
+	help
+	  This option will let you use process cgroup subsystems
+	  such as Cpusets
+
+	  Say N if unsure.
+
 config CPUSETS
 	bool "Cpuset support"
 	depends on SMP

init/main.c

@@ -39,6 +39,7 @@
 #include <linux/writeback.h>
 #include <linux/cpu.h>
 #include <linux/cpuset.h>
+#include <linux/cgroup.h>
 #include <linux/efi.h>
 #include <linux/tick.h>
 #include <linux/interrupt.h>
@@ -523,6 +524,7 @@ asmlinkage void __init start_kernel(void)
 	 */
 	unwind_init();
 	lockdep_init();
+	cgroup_init_early();
 
 	local_irq_disable();
 	early_boot_irqs_off();
@@ -640,6 +642,7 @@ asmlinkage void __init start_kernel(void)
 #ifdef CONFIG_PROC_FS
 	proc_root_init();
 #endif
+	cgroup_init();
 	cpuset_init();
 	taskstats_init_early();
 	delayacct_init();

kernel/Makefile

@@ -36,6 +36,7 @@ obj-$(CONFIG_PM) += power/
 obj-$(CONFIG_BSD_PROCESS_ACCT) += acct.o
 obj-$(CONFIG_KEXEC) += kexec.o
 obj-$(CONFIG_COMPAT) += compat.o
+obj-$(CONFIG_CGROUPS) += cgroup.o
 obj-$(CONFIG_CPUSETS) += cpuset.o
 obj-$(CONFIG_IKCONFIG) += configs.o
 obj-$(CONFIG_STOP_MACHINE) += stop_machine.o