OpenVZ Forum


Home » Mailing lists » Devel » [PATCH 0/7] Generic Process Containers (+ ResGroups/BeanCounters)
[PATCH 0/7] Generic Process Containers (+ ResGroups/BeanCounters) [message #8540] Thu, 23 November 2006 12:08 Go to next message
Paul Menage is currently offline  Paul Menage
Messages: 642
Registered: September 2006
Senior Member
This is an update to my multi-hierarchy generic containers patch (against
2.6.19-rc6). Changes include:

- an example patch implementing the BeanCounters core and numfiles
counters over generic containers. The addition of the
BeanCounters code unifies the three main process grouping
abstractions (Cpusets, ResGroups and BeanCounters).

- a patch splitting Cpusets into two independently groupable
subsystems, Cpusets and Memsets.

- support for a subsystem to keep a container alive via refcounts
(e.g. the BeanCounters numfiles counter has a reference to the
beancounter object from each file charged to that beancounter, so
needs to be able to keep the beancounter alive until the file is
destroyed)

-------------------------------------

There have recently been various proposals floating around for
resource management/accounting subsystems in the kernel, including
Res Groups, User BeanCounters 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, and all implement this grouping in different ways.

Already existing in the kernel is the cpuset subsystem; this has a
process grouping mechanism that is mature, tested, and well documented
(particularly with regards to synchronization rules).

This patchset extracts the process grouping code from cpusets into a
generic container system, and makes the cpusets code a client of
the container system.

It also provides several example clients of the container system,
including ResGroups and BeanCounters

The change is implemented in five stages plus two additional example patches:

1) extract the process grouping code from cpusets into a standalone system

2) remove the process grouping code from cpusets and hook into the
container system

3) convert the container system to present a generic multi-hierarchy
API, and make cpusets a client of that API

4) add a simple CPU accounting container subsystem as an example

5) example of implementing ResGroups and its numtasks controller over
generic containers - not intended to be applied with this patch set

6) split cpusets into two subsystems, cpusets and memsets

7) example of implementing BeanCounters and its numfiles counter over
generic containers - not intended to be applied with this patch set


The intention is that the various resource management efforts can also
become container clients, with the result that:

- the userspace APIs are (somewhat) normalised

- it's easier to test out e.g. the ResGroups CPU controller in
conjunction with the BeanCounters memory controller

- 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

Signed-off-by: Paul Menage <menage@google.com>

--
[PATCH 3/7] Add generic multi-subsystem API to containers [message #8541 is a reply to message #8540] Thu, 23 November 2006 12:08 Go to previous messageGo to next message
Paul Menage is currently offline  Paul Menage
Messages: 642
Registered: September 2006
Senior Member
This patch removes all cpuset-specific knowlege from the container
system, replacing it with a generic API that can be used by multiple
subsystems. Cpusets is adapted to be a container subsystem.

Signed-off-by: Paul Menage <menage@google.com>

---
Documentation/containers.txt | 233 ++++++++++++-
include/linux/container.h | 132 +++++++
include/linux/cpuset.h | 16
include/linux/mempolicy.h | 12
include/linux/sched.h | 4
kernel/container.c | 716 +++++++++++++++++++++++++++++++++++--------
kernel/cpuset.c | 165 ++++++---
mm/mempolicy.c | 2
8 files changed, 1048 insertions(+), 232 deletions(-)

Index: container-2.6.19-rc6/include/linux/container.h
============================================================ =======
--- container-2.6.19-rc6.orig/include/linux/container.h
+++ container-2.6.19-rc6/include/linux/container.h
@@ -14,8 +14,6 @@

#ifdef CONFIG_CONTAINERS

-extern int number_of_containers; /* How many containers are defined in system? */
-
extern int container_init_early(void);
extern int container_init(void);
extern void container_init_smp(void);
@@ -30,6 +28,68 @@ extern void container_unlock(void);
extern void container_manage_lock(void);
extern void container_manage_unlock(void);

+struct containerfs_root;
+
+/* Per-subsystem/per-container state maintained by the system. */
+struct container_subsys_state {
+ /* The container that this subsystem is attached to. Useful
+ * for subsystems that want to know about the container
+ * hierarchy structure */
+ struct container *container;
+
+ /* State maintained by the container system to allow
+ * subsystems to be "busy". Should be accessed via css_get()
+ * and css_put() */
+ spinlock_t refcnt_lock;
+ atomic_t refcnt;
+};
+
+/*
+ * Call css_get() to hold a reference on the container; following a
+ * return of 0, this container subsystem state object is guaranteed
+ * not to be destroyed until css_put() is called on it. A non-zero
+ * return code indicates that a reference could not be taken.
+ *
+ */
+
+static inline int css_get(struct container_subsys_state *css)
+{
+ int retval = 0;
+ unsigned long flags;
+ /* Synchronize with container_rmdir() */
+ spin_lock_irqsave(&css->refcnt_lock, flags);
+ if (atomic_read(&css->refcnt) >= 0) {
+ /* Container is still alive */
+ atomic_inc(&css->refcnt);
+ } else {
+ /* Container removal is in progress */
+ retval = -EINVAL;
+ }
+ spin_unlock_irqrestore(&css->refcnt_lock, flags);
+ return retval;
+}
+
+/*
+ * If you are holding current->alloc_lock then it's impossible for you
+ * to be moved out of your container, and hence it's impossible for
+ * your container to be destroyed. Therefore doing a simple
+ * atomic_inc() on a css is safe.
+ */
+
+static inline void css_get_current(struct container_subsys_state *css)
+{
+ atomic_inc(&css->refcnt);
+}
+
+/*
+ * css_put() should be called to release a reference taken by
+ * css_get() or css_get_current()
+ */
+
+static inline void css_put(struct container_subsys_state *css) {
+ atomic_dec(&css->refcnt);
+}
+
struct container {
unsigned long flags; /* "unsigned long" so bitops work */

@@ -46,11 +106,15 @@ struct container {
struct list_head children; /* my children */

struct container *parent; /* my parent */
- struct dentry *dentry; /* container fs entry */
+ struct dentry *dentry; /* container fs entry */

-#ifdef CONFIG_CPUSETS
- struct cpuset *cpuset;
-#endif
+ /* Private pointers for each registered subsystem */
+ struct container_subsys_state *subsys[CONFIG_MAX_CONTAINER_SUBSYS];
+
+ int hierarchy;
+
+ struct containerfs_root *root;
+ struct container *top_container;
};

/* struct cftype:
@@ -67,8 +131,9 @@ struct container {
*/

struct inode;
+#define MAX_CFTYPE_NAME 64
struct cftype {
- char *name;
+ char name[MAX_CFTYPE_NAME];
int private;
int (*open) (struct inode *inode, struct file *file);
ssize_t (*read) (struct container *cont, struct cftype *cft,
@@ -87,6 +152,59 @@ void container_set_release_agent_path(co

int container_path(const struct container *cont, char *buf, int buflen);

+/* Container subsystem type. See Documentation/containers.txt for details */
+
+struct container_subsys {
+ int (*create)(struct container_subsys *ss,
+ struct container *cont);
+ void (*destroy)(struct container_subsys *ss, struct container *cont);
+ int (*can_attach)(struct container_subsys *ss,
+ struct container *cont, struct task_struct *tsk);
+ void (*attach)(struct container_subsys *ss, struct container *cont,
+ struct container *old_cont, struct task_struct *tsk);
+ void (*post_attach)(struct container_subsys *ss,
+ struct container *cont,
+ struct container *old_cont,
+ struct task_struct *tsk);
+ void (*fork)(struct container_subsys *ss, struct task_struct *task);
+ void (*exit)(struct container_subsys *ss, struct task_struct *task);
+ int (*populate)(struct container_subsys *ss,
+ struct container *cont);
+
+ int subsys_id;
+#define MAX_CONTAINER_TYPE_NAMELEN 32
+ const char *name;
+
+ /* Protected by RCU */
+ int hierarchy;
+
+ struct list_head sibling;
+};
+
+int container_register_subsys(struct container_subsys *subsys);
+
+static inline struct container_subsys_state *container_subsys_state(
+ struct container *cont,
+ struct container_subsys *ss)
+{
+ return cont->subsys[ss->subsys_id];
+}
+
+static inline struct container* task_container(struct task_struct *task,
+ struct container_subsys *ss)
+{
+ return rcu_dereference(task->container[ss->hierarchy]);
+}
+
+static inline struct container_subsys_state *task_subsys_state(
+ struct task_struct *task,
+ struct container_subsys *ss)
+{
+ return container_subsys_state(task_container(task, ss), ss);
+}
+
+int container_path(const struct container *cont, char *buf, int buflen);
+
#else /* !CONFIG_CONTAINERS */

static inline int container_init_early(void) { return 0; }
Index: container-2.6.19-rc6/include/linux/cpuset.h
============================================================ =======
--- container-2.6.19-rc6.orig/include/linux/cpuset.h
+++ container-2.6.19-rc6/include/linux/cpuset.h
@@ -60,16 +60,7 @@ static inline int cpuset_do_slab_mem_spr

extern void cpuset_track_online_nodes(void);

-extern int cpuset_can_attach_task(struct container *cont,
- struct task_struct *tsk);
-extern void cpuset_attach_task(struct container *cont,
- struct task_struct *tsk);
-extern void cpuset_post_attach_task(struct container *cont,
- struct container *oldcont,
- struct task_struct *tsk);
-extern int cpuset_populate_dir(struct container *cont);
-extern int cpuset_create(struct container *cont);
-extern void cpuset_destroy(struct container *cont);
+extern int current_cpuset_is_being_rebound(void);

#else /* !CONFIG_CPUSETS */

@@ -131,6 +122,11 @@ static inline int cpuset_do_slab_mem_spr

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 */
Index: container-2.6.19-rc6/kernel/container.c
============================================================ =======
--- container-2.6.19-rc6.orig/kernel/container.c
+++ container-2.6.19-rc6/kernel/container.c
@@ -55,7 +55,6 @@
#include <linux/time.h>
#include <linux/backing-dev.h>
#include <linux/sort.h>
-#include <linux/cpuset.h>

#include <asm/uaccess.h>
#include <asm/atomic.h>
@@ -63,12 +62,47 @@

#define CONTAINER_SUPER_MAGIC 0x27e0eb

-/*
- * Tracks how many containers are currently defined in system.
- * When there is only one container (the root container) we can
- * short circuit some hooks.
+static struct container_subsys *subsys[CONFIG_MAX_CONTAINER_SUBSYS];
+static int subsys_count = 0;
+
+struct containerfs_root {
+ struct super_block *sb;
+ unsigned long subsys_bits;
+ struct list_head subsys_list;
+ struct container top_container;
+ /*
+ * Tracks how many containers are currently defined in system.
+ * When there is only one container (the root container) we can
+ * short circuit some hooks.
+ */
+ int number_of_containers;
+ struct vfsmount *pin_mount;
+};
+
+/* The set of hierarchies in use. Hierarchy 0 is the "dummy
+ * container", reserved for the subsystems that are otherwise
+ * unattached - it never has more than a single container, and all
+ * tasks are part of that container. */
+
+static struct containerfs_root rootnode[CONFIG_MAX_CONTAINER_HIERARCHIES];
+
+/* dummytop is a shorthand for the dummy hierarchy's top container */
+#define dummytop (&rootnode[0].top_container)
+
+/* This flag indicates whether tasks in the fork and exit paths should
+ * take callback_mutex and check for fork/exit handlers to call. This
+ * avoids us having to take locks in the fork/exit path if none of the
+ * subsystems need to be called.
+ *
+ * It is protected via RCU, with the invariant that a process in an
+ * rcu_read_lock() section will never see this as 0 if there are
+ * actually registered subsystems with a fork or exit
+ * handler. (Sometimes it may be 1 without there being any registered
+ * subsystems with such a handler, but such periods are safe and of
+ * short duration).
*/
-int number_of_containers __read_mostly;
+
+static int need_forkexit_callback = 0;

/* bits in struct container flags field */
typedef enum {
@@ -87,11 +121,8 @@ static inline int notify_on_release(cons
return test_bit(CONT_NOTIFY_ON_RELEASE, &cont->flags);
}

-static struct container top_container = {
- .count = ATOMIC_INIT(0),
- .sibling = LIST_HEAD_INIT(top_container.sibling),
- .children = LIST_HEAD_INIT(top_container.children),
-};
+#define for_each_subsys(_hierarchy, _ss) list_for_each_entry(_ss, &rootnode[_hierarchy].subsys_list, sibling)
+

/* The path to use for release notificatio
...

[PATCH 7/7] BeanCounters over generic process containers [message #8542 is a reply to message #8540] Thu, 23 November 2006 12:08 Go to previous messageGo to next message
Paul Menage is currently offline  Paul Menage
Messages: 642
Registered: September 2006
Senior Member
This patch implements the BeanCounter resource control abstraction
over generic process containers. It contains the beancounter core
code, plus the numfiles resource counter. It doesn't currently contain
any of the memory tracking code or the code for switching beancounter
context in interrupts.

Currently all the beancounters resource counters are lumped into a
single hierarchy; ideally it would be possible for each resource
counter to be a separate container subsystem, allowing them to be
connected to different hierarchies.

---
fs/file_table.c | 11 +
include/bc/beancounter.h | 192 ++++++++++++++++++++++++
include/bc/misc.h | 27 +++
include/linux/fs.h | 3
init/Kconfig | 4
init/main.c | 3
kernel/Makefile | 1
kernel/bc/Kconfig | 17 ++
kernel/bc/Makefile | 7
kernel/bc/beancounter.c | 371 +++++++++++++++++++++++++++++++++++++++++++++++
kernel/bc/misc.c | 56 +++++++
11 files changed, 691 insertions(+), 1 deletion(-)

Index: container-2.6.19-rc6/init/Kconfig
============================================================ =======
--- container-2.6.19-rc6.orig/init/Kconfig
+++ container-2.6.19-rc6/init/Kconfig
@@ -601,6 +601,10 @@ config STOP_MACHINE
Need stop_machine() primitive.
endmenu

+menu "Beancounters"
+source "kernel/bc/Kconfig"
+endmenu
+
menu "Block layer"
source "block/Kconfig"
endmenu
Index: container-2.6.19-rc6/kernel/Makefile
============================================================ =======
--- container-2.6.19-rc6.orig/kernel/Makefile
+++ container-2.6.19-rc6/kernel/Makefile
@@ -12,6 +12,7 @@ obj-y = sched.o fork.o exec_domain.o

obj-$(CONFIG_STACKTRACE) += stacktrace.o
obj-y += time/
+obj-$(CONFIG_BEANCOUNTERS) += bc/
obj-$(CONFIG_DEBUG_MUTEXES) += mutex-debug.o
obj-$(CONFIG_LOCKDEP) += lockdep.o
ifeq ($(CONFIG_PROC_FS),y)
Index: container-2.6.19-rc6/kernel/bc/Kconfig
============================================================ =======
--- /dev/null
+++ container-2.6.19-rc6/kernel/bc/Kconfig
@@ -0,0 +1,17 @@
+config BEANCOUNTERS
+ bool "Enable resource accounting/control"
+ default n
+ select CONTAINERS
+ help
+ When Y this option provides accounting and allows configuring
+ limits for user's consumption of exhaustible system resources.
+ The most important resource controlled by this patch is unswappable
+ memory (either mlock'ed or used by internal kernel structures and
+ buffers). The main goal of this patch is to protect processes
+ from running short of important resources because of accidental
+ misbehavior of processes or malicious activity aiming to ``kill''
+ the system. It's worth mentioning that resource limits configured
+ by setrlimit(2) do not give an acceptable level of protection
+ because they cover only a small fraction of resources and work on a
+ per-process basis. Per-process accounting doesn't prevent malicious
+ users from spawning a lot of resource-consuming processes.
Index: container-2.6.19-rc6/kernel/bc/Makefile
============================================================ =======
--- /dev/null
+++ container-2.6.19-rc6/kernel/bc/Makefile
@@ -0,0 +1,7 @@
+#
+# kernel/bc/Makefile
+#
+# Copyright (C) 2006 OpenVZ SWsoft Inc.
+#
+
+obj-y = beancounter.o misc.o
Index: container-2.6.19-rc6/include/bc/beancounter.h
============================================================ =======
--- /dev/null
+++ container-2.6.19-rc6/include/bc/beancounter.h
@@ -0,0 +1,192 @@
+/*
+ * include/bc/beancounter.h
+ *
+ * Copyright (C) 2006 OpenVZ SWsoft Inc
+ *
+ */
+
+#ifndef __BEANCOUNTER_H__
+#define __BEANCOUNTER_H__
+
+#include <linux/container.h>
+
+enum {
+ BC_KMEMSIZE,
+ BC_PRIVVMPAGES,
+ BC_PHYSPAGES,
+ BC_NUMTASKS,
+ BC_NUMFILES,
+
+ BC_RESOURCES
+};
+
+struct bc_resource_parm {
+ unsigned long barrier;
+ unsigned long limit;
+ unsigned long held;
+ unsigned long minheld;
+ unsigned long maxheld;
+ unsigned long failcnt;
+
+};
+
+#ifdef __KERNEL__
+
+#include <linux/list.h>
+#include <linux/spinlock.h>
+#include <linux/init.h>
+#include <linux/configfs.h>
+#include <asm/atomic.h>
+
+#define BC_MAXVALUE ((unsigned long)LONG_MAX)
+
+enum bc_severity {
+ BC_BARRIER,
+ BC_LIMIT,
+ BC_FORCE,
+};
+
+struct beancounter;
+
+#ifdef CONFIG_BEANCOUNTERS
+
+enum bc_attr_index {
+ BC_RES_HELD,
+ BC_RES_MAXHELD,
+ BC_RES_MINHELD,
+ BC_RES_BARRIER,
+ BC_RES_LIMIT,
+ BC_RES_FAILCNT,
+
+ BC_ATTRS
+};
+
+struct bc_resource {
+ char *bcr_name;
+ int res_id;
+
+ int (*bcr_init)(struct beancounter *bc, int res);
+ int (*bcr_change)(struct beancounter *bc,
+ unsigned long new_bar, unsigned long new_lim);
+ void (*bcr_barrier_hit)(struct beancounter *bc);
+ int (*bcr_limit_hit)(struct beancounter *bc, unsigned long val,
+ unsigned long flags);
+ void (*bcr_fini)(struct beancounter *bc);
+
+ /* container file handlers */
+ struct cftype cft_attrs[BC_ATTRS];
+};
+
+extern struct bc_resource *bc_resources[];
+extern struct container_subsys bc_subsys;
+
+struct beancounter {
+ struct container_subsys_state css;
+ spinlock_t bc_lock;
+
+ struct bc_resource_parm bc_parms[BC_RESOURCES];
+};
+
+/* Update the beancounter for a container */
+static inline void set_container_bc(struct container *cont,
+ struct beancounter *bc)
+{
+ cont->subsys[bc_subsys.subsys_id] = &bc->css;
+}
+
+/* Retrieve the beancounter for a container */
+static inline struct beancounter *container_bc(struct container *cont)
+{
+ return container_of(container_subsys_state(cont, &bc_subsys),
+ struct beancounter, css);
+}
+
+/* Retrieve the beancounter for a task */
+static inline struct beancounter *task_bc(struct task_struct *task)
+{
+ return container_bc(task_container(task, &bc_subsys));
+}
+
+static inline void bc_adjust_maxheld(struct bc_resource_parm *parm)
+{
+ if (parm->maxheld < parm->held)
+ parm->maxheld = parm->held;
+}
+
+static inline void bc_adjust_minheld(struct bc_resource_parm *parm)
+{
+ if (parm->minheld > parm->held)
+ parm->minheld = parm->held;
+}
+
+static inline void bc_init_resource(struct bc_resource_parm *parm,
+ unsigned long bar, unsigned long lim)
+{
+ parm->barrier = bar;
+ parm->limit = lim;
+ parm->held = 0;
+ parm->minheld = 0;
+ parm->maxheld = 0;
+ parm->failcnt = 0;
+}
+
+int bc_change_param(struct beancounter *bc, int res,
+ unsigned long bar, unsigned long lim);
+
+int __must_check bc_charge_locked(struct beancounter *bc, int res_id,
+ unsigned long val, int strict, unsigned long flags);
+static inline int __must_check bc_charge(struct beancounter *bc, int res_id,
+ unsigned long val, int strict)
+{
+ int ret;
+ unsigned long flags;
+
+ spin_lock_irqsave(&bc->bc_lock, flags);
+ ret = bc_charge_locked(bc, res_id, val, strict, flags);
+ spin_unlock_irqrestore(&bc->bc_lock, flags);
+ return ret;
+}
+
+void __must_check bc_uncharge_locked(struct beancounter *bc, int res_id,
+ unsigned long val);
+static inline void bc_uncharge(struct beancounter *bc, int res_id,
+ unsigned long val)
+{
+ unsigned long flags;
+
+ spin_lock_irqsave(&bc->bc_lock, flags);
+ bc_uncharge_locked(bc, res_id, val);
+ spin_unlock_irqrestore(&bc->bc_lock, flags);
+}
+
+void __init bc_register_resource(int res_id, struct bc_resource *br);
+void __init bc_init_early(void);
+#else /* CONFIG_BEANCOUNTERS */
+static inline int __must_check bc_charge_locked(struct beancounter *bc, int res,
+ unsigned long val, int strict, unsigned long flags)
+{
+ return 0;
+}
+
+static inline int __must_check bc_charge(struct beancounter *bc, int res,
+ unsigned long val, int strict)
+{
+ return 0;
+}
+
+static inline void bc_uncharge_locked(struct beancounter *bc, int res,
+ unsigned long val)
+{
+}
+
+static inline void bc_uncharge(struct beancounter *bc, int res,
+ unsigned long val)
+{
+}
+
+static inline void bc_init_early(void)
+{
+}
+#endif /* CONFIG_BEANCOUNTERS */
+#endif /* __KERNEL__ */
+#endif
Index: container-2.6.19-rc6/init/main.c
============================================================ =======
--- container-2.6.19-rc6.orig/init/main.c
+++ container-2.6.19-rc6/init/main.c
@@ -52,6 +52,8 @@
#include <linux/debug_locks.h>
#include <linux/lockdep.h>

+#include <bc/beancounter.h>
+
#include <asm/io.h>
#include <asm/bugs.h>
#include <asm/setup.h>
@@ -482,6 +484,7 @@ asmlinkage void __init start_kernel(void
char * command_line;
extern struct kernel_param __start___param[], __stop___param[];

+ bc_init_early();
smp_setup_processor_id();

/*
Index: container-2.6.19-rc6/kernel/bc/beancounter.c
============================================================ =======
--- /dev/null
+++ container-2.6.19-rc6/kernel/bc/beancounter.c
@@ -0,0 +1,371 @@
+/*
+ * kernel/bc/beancounter.c
+ *
+ * Copyright (C) 2006 OpenVZ SWsoft Inc
+ *
+ */
+
+#include <linux/sched.h>
+#include <linux/list.h>
+#include <linux/hash.h>
+#include <linux/gfp.h>
+#include <linux/slab.h>
+#include <linux/module.h>
+#include <linux/fs.h>
+#include <linux/uaccess.h>
+
+#include <bc/beancounter.h>
+
+#define BC_HASH_BITS (8)
+#define BC_HASH_SIZE (1 << BC_HASH_BITS)
+
+static int bc_dummy_init(struct beancounter *bc, int i)
+{
+ bc_init_resource(&bc->bc_parms[i], BC_MAXVALUE, BC_MAXVALUE);
+ return 0;
+}
+
+static struct bc_resource bc_dummy_res = {
+ .bcr_name = "dummy",
+ .bcr_init = bc_dummy_init,
+};
+
+struct bc_resource *bc_resources[BC_RESOURCES] = {
+ [0 ... BC_RESOURCES - 1] = &bc_dummy_res,
+};
+
+struct beancounter init_bc;
+static kmem_cache_t *bc_cache;
+
+static int bc_create(struct container_subsys *ss,
+ struct container *cont)
+{
+ int i;
+ struct beancounter *new_bc;
+
+ if (!cont->parent) {
+ /* Early initialization for top container */
+ set_container_b
...

[PATCH 5/7] Resource Groups over generic containers [message #8543 is a reply to message #8540] Thu, 23 November 2006 12:08 Go to previous messageGo to next message
Paul Menage is currently offline  Paul Menage
Messages: 642
Registered: September 2006
Senior Member
This patch provides the RG core and numtasks controller as container
subsystems, intended as an example of how to implement a more complex
resource control system over generic process containers. The changes
to the core involve primarily removing the group management, task
membership and configfs support and adding interface layers to talk to
the generic container layer instead.

Each resource controller becomes an independent container subsystem;
the RG core is essentially a library that the resource controllers can
use to provide the RG API to userspace. Rather than a single shares
and stats file in each group, there's a <controller>_shares and
a <controller>_stats file, each linked to the appropriate resource
controller.

include/linux/moduleparam.h | 12 -
include/linux/numtasks.h | 28 ++
include/linux/res_group.h | 87 ++++++++
include/linux/res_group_rc.h | 97 ++++++++
init/Kconfig | 22 ++
kernel/Makefile | 1
kernel/fork.c | 7
kernel/res_group/Makefile | 2
kernel/res_group/local.h | 38 +++
kernel/res_group/numtasks.c | 467 +++++++++++++++++++++++++++++++++++++++++++
kernel/res_group/res_group.c | 160 ++++++++++++++
kernel/res_group/rgcs.c | 302 +++++++++++++++++++++++++++
kernel/res_group/shares.c | 228 ++++++++++++++++++++
13 files changed, 1447 insertions(+), 4 deletions(-)

Index: container-2.6.19-rc6/include/linux/moduleparam.h
============================================================ =======
--- container-2.6.19-rc6.orig/include/linux/moduleparam.h
+++ container-2.6.19-rc6/include/linux/moduleparam.h
@@ -75,11 +75,17 @@ struct kparam_array
/* Helper functions: type is byte, short, ushort, int, uint, long,
ulong, charp, bool or invbool, or XXX if you define param_get_XXX,
param_set_XXX and param_check_XXX. */
-#define module_param_named(name, value, type, perm) \
- param_check_##type(name, &(value)); \
- module_param_call(name, param_set_##type, param_get_##type, &value, perm); \
+#define module_param_named_call(name, value, type, set, perm) \
+ param_check_##type(name, &(value)); \
+ module_param_call(name, set, param_get_##type, &(value), perm); \
__MODULE_PARM_TYPE(name, #type)

+#define module_param_named(name, value, type, perm) \
+ module_param_named_call(name, value, type, param_set_##type, perm)
+
+#define module_param_set_call(name, type, setfn, perm) \
+ module_param_named_call(name, name, type, setfn, perm)
+
#define module_param(name, type, perm) \
module_param_named(name, name, type, perm)

Index: container-2.6.19-rc6/include/linux/numtasks.h
============================================================ =======
--- /dev/null
+++ container-2.6.19-rc6/include/linux/numtasks.h
@@ -0,0 +1,28 @@
+/* numtasks.h - No. of tasks resource controller for Resource Groups
+ *
+ * Copyright (C) Chandra Seetharaman, IBM Corp. 2003, 2004, 2005
+ *
+ * Provides No. of tasks resource controller for Resource Groups
+ *
+ * Latest version, more details at http://ckrm.sf.net
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ */
+#ifndef _LINUX_NUMTASKS_H
+#define _LINUX_NUMTASKS_H
+
+#ifdef CONFIG_RES_GROUPS_NUMTASKS
+#include <linux/res_group_rc.h>
+
+extern int numtasks_allow_fork(struct task_struct *);
+
+#else /* CONFIG_RES_GROUPS_NUMTASKS */
+
+#define numtasks_allow_fork(task) (0)
+
+#endif /* CONFIG_RES_GROUPS_NUMTASKS */
+#endif /* _LINUX_NUMTASKS_H */
Index: container-2.6.19-rc6/include/linux/res_group.h
============================================================ =======
--- /dev/null
+++ container-2.6.19-rc6/include/linux/res_group.h
@@ -0,0 +1,87 @@
+/*
+ * res_group.h - Header file to be used by Resource Groups
+ *
+ * Copyright (C) Hubertus Franke, IBM Corp. 2003, 2004
+ * (C) Shailabh Nagar, IBM Corp. 2003, 2004
+ * (C) Chandra Seetharaman, IBM Corp. 2003, 2004, 2005
+ *
+ * Provides data structures, macros and kernel APIs
+ *
+ * More details at http://ckrm.sf.net
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ */
+
+#ifndef _LINUX_RES_GROUP_H
+#define _LINUX_RES_GROUP_H
+
+#ifdef CONFIG_RES_GROUPS
+#include <linux/spinlock.h>
+#include <linux/list.h>
+#include <linux/kref.h>
+#include <linux/container.h>
+
+#define SHARE_UNCHANGED (-1) /* implicitly specified by userspace,
+ * never stored in a resource group'
+ * shares struct; never displayed */
+#define SHARE_UNSUPPORTED (-2) /* If the resource controller doesn't
+ * support user changing a shares value
+ * it sets the corresponding share
+ * value to UNSUPPORTED when it returns
+ * the newly allocated shares data
+ * structure */
+#define SHARE_DONT_CARE (-3)
+
+#define SHARE_DEFAULT_DIVISOR (100)
+
+#define MAX_RES_CTLRS CONFIG_MAX_CONTAINER_SUBSYS /* max # of resource controllers */
+#define MAX_DEPTH 5 /* max depth of hierarchy supported */
+
+#define NO_RES_GROUP NULL
+#define NO_SHARE NULL
+#define NO_RES_ID MAX_RES_CTLRS /* Invalid ID */
+
+/*
+ * Share quantities are a child's fraction of the parent's resource
+ * specified by a divisor in the parent and a dividend in the child.
+ *
+ * Shares are represented as a relative quantity between parent and child
+ * to simplify locking when propagating modifications to the shares of a
+ * resource group. Only the parent and the children of the modified
+ * resource group need to be locked.
+*/
+struct res_shares {
+ /* shares only set by userspace */
+ int min_shares; /* minimun fraction of parent's resources allowed */
+ int max_shares; /* maximum fraction of parent's resources allowed */
+ int child_shares_divisor; /* >= 1, may not be DONT_CARE */
+
+ /*
+ * share values invisible to userspace. adjusted when userspace
+ * sets shares
+ */
+ int unused_min_shares;
+ /* 0 <= unused_min_shares <= (child_shares_divisor -
+ * Sum of min_shares of children)
+ */
+ int cur_max_shares; /* max(children's max_shares). need better name */
+
+ /* State maintained by container system - only relevant when
+ * this shares struct is the actual shares struct for a
+ * container */
+ struct container_subsys_state css;
+};
+
+/*
+ * Class is the grouping of tasks with shares of each resource that has
+ * registered a resource controller (see include/linux/res_group_rc.h).
+ */
+
+#define resource_group container
+
+#endif /* CONFIG_RES_GROUPS */
+#endif /* _LINUX_RES_GROUP_H */
Index: container-2.6.19-rc6/include/linux/res_group_rc.h
============================================================ =======
--- /dev/null
+++ container-2.6.19-rc6/include/linux/res_group_rc.h
@@ -0,0 +1,97 @@
+/*
+ * res_group_rc.h - Header file to be used by Resource controllers of
+ * Resource Groups
+ *
+ * Copyright (C) Hubertus Franke, IBM Corp. 2003
+ * (C) Shailabh Nagar, IBM Corp. 2003
+ * (C) Chandra Seetharaman, IBM Corp. 2003, 2004, 2005
+ * (C) Vivek Kashyap , IBM Corp. 2004
+ *
+ * Provides data structures, macros and kernel API of Resource Groups for
+ * resource controllers.
+ *
+ * More details at http://ckrm.sf.net
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ */
+
+#ifndef _LINUX_RES_GROUP_RC_H
+#define _LINUX_RES_GROUP_RC_H
+
+#include <linux/res_group.h>
+#include <linux/container.h>
+
+struct res_group_cft {
+ struct cftype cft;
+ struct res_controller *ctlr;
+};
+
+struct res_controller {
+ struct container_subsys subsys;
+ struct res_group_cft shares_cft;
+ struct res_group_cft stats_cft;
+
+ const char *name;
+ unsigned int ctlr_id;
+
+ /*
+ * Keeps number of references to this controller structure. kref
+ * does not work as we want to be able to allow removal of a
+ * controller even when some resource group are still defined.
+ */
+ atomic_t count;
+
+ /*
+ * Allocate a new shares struct for this resource controller.
+ * Called when registering a resource controller with pre-existing
+ * resource groups and when new resource group is created by the user.
+ */
+ struct res_shares *(*alloc_shares_struct)(struct container *);
+ /* Corresponding free of shares struct for this resource controller */
+ void (*free_shares_struct)(struct res_shares *);
+
+ /* Notifies the controller when the shares are changed */
+ void (*shares_changed)(struct res_shares *);
+
+ /* resource statistics */
+ ssize_t (*show_stats)(struct res_shares *, char *, size_t);
+ int (*reset_stats)(struct res_shares *, const char *);
+
+ /*
+ * move_task is called when a task moves from one resource group to
+ * another. First parameter is the task that is moving, the second
+ * is the resource specific shares of the resource group the task
+ * was in, and the third is the shares of the resource group the
+ * task has moved to.
+ */
+ void (*move_task)(struct task_struct *, struct res_shares *,
+ struct res_shares *);
+};
+
+extern int register_controller(struct res_controller *);
+extern int unregister_controller(struct res_controller *);
+extern struct resource_group default_res_group;
+static inline int is_res_group_root(const struct resource_group *rgroup)
+{
+ return (rgroup->parent == NULL);
+}
+
+#define for_each_child(child, parent) \
+ list_for_each_entry(child, &parent->children, sibling)
+
+/* Get controller specific shares structure for the given resource group *
...

[PATCH 2/7] Cpusets hooked into containers [message #8544 is a reply to message #8540] Thu, 23 November 2006 12:08 Go to previous messageGo to next message
Paul Menage is currently offline  Paul Menage
Messages: 642
Registered: September 2006
Senior Member
This patch removes the process grouping code from the cpusets code,
instead hooking it into the generic container system. This temporarily
adds cpuset-specific code in kernel/container.c, which is removed by
the next patch in the series.

Signed-off-by: Paul Menage <menage@google.com>

---
Documentation/cpusets.txt | 81 +-
fs/super.c | 5
include/linux/container.h | 7
include/linux/cpuset.h | 25
include/linux/fs.h | 2
include/linux/mempolicy.h | 2
include/linux/sched.h | 4
init/Kconfig | 23
kernel/container.c | 107 +++
kernel/cpuset.c | 1273 +++++-----------------------------------------
kernel/exit.c | 2
kernel/fork.c | 7
mm/oom_kill.c | 6
13 files changed, 330 insertions(+), 1214 deletions(-)

Index: container-2.6.19-rc5/include/linux/container.h
============================================================ =======
--- container-2.6.19-rc5.orig/include/linux/container.h
+++ container-2.6.19-rc5/include/linux/container.h
@@ -47,6 +47,10 @@ struct container {

struct container *parent; /* my parent */
struct dentry *dentry; /* container fs entry */
+
+#ifdef CONFIG_CPUSETS
+ struct cpuset *cpuset;
+#endif
};

/* struct cftype:
@@ -79,6 +83,9 @@ struct cftype {
int container_add_file(struct container *cont, const struct cftype *cft);

int container_is_removed(const struct container *cont);
+void container_set_release_agent_path(const char *path);
+
+int container_path(const struct container *cont, char *buf, int buflen);

#else /* !CONFIG_CONTAINERS */

Index: container-2.6.19-rc5/include/linux/cpuset.h
============================================================ =======
--- container-2.6.19-rc5.orig/include/linux/cpuset.h
+++ container-2.6.19-rc5/include/linux/cpuset.h
@@ -11,16 +11,15 @@
#include <linux/sched.h>
#include <linux/cpumask.h>
#include <linux/nodemask.h>
+#include <linux/container.h>

#ifdef CONFIG_CPUSETS

-extern int number_of_cpusets; /* How many cpusets are defined in system? */
+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);
void cpuset_init_current_mems_allowed(void);
@@ -47,10 +46,6 @@ extern void __cpuset_memory_pressure_bum

extern struct file_operations proc_cpuset_operations;
extern char *cpuset_task_status_allowed(struct task_struct *task, char *buffer);
-
-extern void cpuset_lock(void);
-extern void cpuset_unlock(void);
-
extern int cpuset_mem_spread_node(void);

static inline int cpuset_do_page_mem_spread(void)
@@ -65,13 +60,22 @@ static inline int cpuset_do_slab_mem_spr

extern void cpuset_track_online_nodes(void);

+extern int cpuset_can_attach_task(struct container *cont,
+ struct task_struct *tsk);
+extern void cpuset_attach_task(struct container *cont,
+ struct task_struct *tsk);
+extern void cpuset_post_attach_task(struct container *cont,
+ struct container *oldcont,
+ struct task_struct *tsk);
+extern int cpuset_populate_dir(struct container *cont);
+extern int cpuset_create(struct container *cont);
+extern void cpuset_destroy(struct container *cont);
+
#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)
{
@@ -110,9 +114,6 @@ static inline char *cpuset_task_status_a
return buffer;
}

-static inline void cpuset_lock(void) {}
-static inline void cpuset_unlock(void) {}
-
static inline int cpuset_mem_spread_node(void)
{
return 0;
Index: container-2.6.19-rc5/kernel/exit.c
============================================================ =======
--- container-2.6.19-rc5.orig/kernel/exit.c
+++ container-2.6.19-rc5/kernel/exit.c
@@ -29,7 +29,6 @@
#include <linux/mempolicy.h>
#include <linux/taskstats_kern.h>
#include <linux/delayacct.h>
-#include <linux/cpuset.h>
#include <linux/container.h>
#include <linux/syscalls.h>
#include <linux/signal.h>
@@ -923,7 +922,6 @@ fastcall NORET_TYPE void do_exit(long co
__exit_files(tsk);
__exit_fs(tsk);
exit_thread();
- cpuset_exit(tsk);
container_exit(tsk);
exit_keys(tsk);

Index: container-2.6.19-rc5/kernel/fork.c
============================================================ =======
--- container-2.6.19-rc5.orig/kernel/fork.c
+++ container-2.6.19-rc5/kernel/fork.c
@@ -30,7 +30,6 @@
#include <linux/nsproxy.h>
#include <linux/capability.h>
#include <linux/cpu.h>
-#include <linux/cpuset.h>
#include <linux/container.h>
#include <linux/security.h>
#include <linux/swap.h>
@@ -1056,13 +1055,12 @@ static struct task_struct *copy_process(
p->io_wait = NULL;
p->audit_context = NULL;
container_fork(p);
- cpuset_fork(p);
#ifdef CONFIG_NUMA
p->mempolicy = mpol_copy(p->mempolicy);
if (IS_ERR(p->mempolicy)) {
retval = PTR_ERR(p->mempolicy);
p->mempolicy = NULL;
- goto bad_fork_cleanup_cpuset;
+ goto bad_fork_cleanup_container;
}
mpol_fix_fork_child_flag(p);
#endif
@@ -1286,9 +1284,8 @@ bad_fork_cleanup_security:
bad_fork_cleanup_policy:
#ifdef CONFIG_NUMA
mpol_free(p->mempolicy);
-bad_fork_cleanup_cpuset:
+bad_fork_cleanup_container:
#endif
- cpuset_exit(p);
container_exit(p);
bad_fork_cleanup_delays_binfmt:
delayacct_tsk_free(p);
Index: container-2.6.19-rc5/kernel/container.c
============================================================ =======
--- container-2.6.19-rc5.orig/kernel/container.c
+++ container-2.6.19-rc5/kernel/container.c
@@ -55,6 +55,7 @@
#include <linux/time.h>
#include <linux/backing-dev.h>
#include <linux/sort.h>
+#include <linux/cpuset.h>

#include <asm/uaccess.h>
#include <asm/atomic.h>
@@ -92,6 +93,18 @@ static struct container top_container =
.children = LIST_HEAD_INIT(top_container.children),
};

+/* The path to use for release notifications. No locking between
+ * setting and use - so if userspace updates this while subcontainers
+ * exist, you could miss a notification */
+static char release_agent_path[PATH_MAX] = "/sbin/container_release_agent";
+
+void container_set_release_agent_path(const char *path)
+{
+ container_manage_lock();
+ strcpy(release_agent_path, path);
+ container_manage_unlock();
+}
+
static struct vfsmount *container_mount;
static struct super_block *container_sb;

@@ -333,7 +346,7 @@ static inline struct cftype *__d_cft(str
* Returns 0 on success, -errno on error.
*/

-static int container_path(const struct container *cont, char *buf, int buflen)
+int container_path(const struct container *cont, char *buf, int buflen)
{
char *start;

@@ -397,7 +410,7 @@ static void container_release_agent(cons
return;

i = 0;
- argv[i++] = "/sbin/container_release_agent";
+ argv[i++] = release_agent_path;
argv[i++] = (char *)pathbuf;
argv[i] = NULL;

@@ -438,6 +451,7 @@ static void check_for_release(struct con
buf = kmalloc(PAGE_SIZE, GFP_KERNEL);
if (!buf)
return;
+
if (container_path(cont, buf, PAGE_SIZE) < 0)
kfree(buf);
else
@@ -486,7 +500,7 @@ static int attach_task(struct container
pid_t pid;
struct task_struct *tsk;
struct container *oldcont;
- int retval;
+ int retval = 0;

if (sscanf(pidbuf, "%d", &pid) != 1)
return -EIO;
@@ -513,7 +527,9 @@ static int attach_task(struct container
get_task_struct(tsk);
}

- retval = security_task_setscheduler(tsk, 0, NULL);
+#ifdef CONFIG_CPUSETS
+ retval = cpuset_can_attach_task(cont, tsk);
+#endif
if (retval) {
put_task_struct(tsk);
return retval;
@@ -533,8 +549,16 @@ static int attach_task(struct container
rcu_assign_pointer(tsk->container, cont);
task_unlock(tsk);

+#ifdef CONFIG_CPUSETS
+ cpuset_attach_task(cont, tsk);
+#endif
+
mutex_unlock(&callback_mutex);

+#ifdef CONFIG_CPUSETS
+ cpuset_post_attach_task(cont, oldcont, tsk);
+#endif
+
put_task_struct(tsk);
synchronize_rcu();
if (atomic_dec_and_test(&oldcont->count))
@@ -549,6 +573,7 @@ typedef enum {
FILE_DIR,
FILE_NOTIFY_ON_RELEASE,
FILE_TASKLIST,
+ FILE_RELEASE_AGENT,
} container_filetype_t;

static ssize_t container_common_file_write(struct container *cont,
@@ -562,8 +587,7 @@ static ssize_t container_common_file_wri
char *pathbuf = NULL;
int retval = 0;

- /* Crude upper limit on largest legitimate cpulist user might write. */
- if (nbytes > 100 + 6 * NR_CPUS)
+ if (nbytes >= PATH_MAX)
return -E2BIG;

/* +1 for nul-terminator */
@@ -590,6 +614,20 @@ static ssize_t container_common_file_wri
case FILE_TASKLIST:
retval = attach_task(cont, buffer, &pathbuf);
break;
+ case FILE_RELEASE_AGENT:
+ {
+ if (nbytes < sizeof(release_agent_path)) {
+ /* We never write anything other than '\0'
+ * into the last char of release_agent_path,
+ * so it always remains a NUL-terminated
+ * string */
+ strncpy(release_agent_path, buffer, nbytes);
+ release_agent_path[nbytes] = 0;
+ } else {
+ retval = -ENOSPC;
+ }
+ break;
+ }
default:
retval = -EINVAL;
goto out2;
@@ -643,6 +681,17 @@ static ssize_t container_common_file_rea
case FILE_NOTIFY_ON_RELEASE:
*s++ = notify_on_release(cont) ? '1' : '0';
break;
+ case FILE_RELEASE_AGENT:
+ {
+ size_t n;
+ container_manage_lock();
+ n = strnlen(release_agent_path, sizeof(release_agent_path));
+ n = min(n, (size_t) PAGE_SIZE);
+ strncpy(s, release_agent_path, n);
+ container_manage_unlock();
+ s += n;
+ break;
+ }
default:
retval = -EINVAL;
goto out;
@@ -978,6 +1027,13 @@ static struct cftype cft_notify_on_relea
.private = FILE_NOTIFY_ON_RELEASE,
};

+static struct cftype cft_release_agent = {
+ .name = "release_agent",
+ .read = container_common_file_read,
+ .write = container_common_file_write,
+ .private = FILE_RELEASE_AGENT,
+};
+
static int container_populate_dir(struct container *cont)
{
int err;
@@ -986,6 +1042,13 @@ static int container_populate_dir(struct
return err;
if ((err = container_add_file(cont, &cft_tasks)) < 0)
return err;
+ if ((cont == &top_container) &&
+ (err = container_add_file(cont, &cft_release_agent)) < 0)
+ return err;
+#ifdef CONFIG_CPUSETS
+ if ((err = cpuset_populate_dir(cont)) < 0)
+ return err;
+#endif
return 0;
}

@@ -1017,6 +1080,12 @@ static long container_create(struct cont

cont->parent = parent;

+#ifdef CONFIG_CPUSETS
+ err = cpuset_create(cont);
+ if (err)
+ goto err_unlock_free;
+#endif
+
mutex_lock(&callback_mutex);
list_add(&cont->sibling, &cont->parent->children);
number_of_containers++;
@@ -1038,11 +1107,14 @@ static long container_create(struct cont
return 0;

err_remove:
+#ifdef CONFIG_CPUSETS
+ cpuset_destroy(cont);
+#endif
mutex_lock(&callback_mutex);
list_del(&cont->sibling);
number_of_containers--;
mutex_unlock(&callback_mutex);
-
+ err_unlock_free:
mutex_unlock(&manage_mutex);
kfree(cont);
return err;
@@ -1097,6 +1169,9 @@ static int container_rmdir(struct inode
dput(d);
number_of_containers--;
mutex_unlock(&callback_mutex);
+#ifdef CONFIG_CPUSETS
+ cpuset_destroy(cont);
+#endif
if (list_empty(&parent->children))
check_for_release(parent, &pathbuf);
mutex_unlock(&manage_mutex);
@@ -1283,6 +1358,24 @@ void container_unlock(void)
mutex_unlock(&callback_mutex);
}

+void container_manage_lock(void)
+{
+ mutex_lock(&manage_mutex);
+}
+
+/**
+ * container_manage_unlock - release lock on container changes
+ *
+ * Undo the lock taken in a previous container_manage_lock() call.
+ */
+
+void container_manage_unlock(void)
+{
+ mutex_unlock(&manage_mutex);
+}
+
+
+
/*
* proc_container_show()
* - Print tasks container path into seq_file.
Index: container-2.6.19-rc5/kernel/cpuset.c
============================================================ =======
--- container-2.6.19-rc5.orig/kernel/cpuset.c
+++ container-2.6.19-rc5/kernel/cpuset.c
@@ -54,8 +54,6 @@
#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
@@ -77,20 +75,8 @@ struct cpuset {
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 container *container; /* Task container */
struct cpuset *parent; /* my parent */
- struct dentry *dentry; /* cpuset fs entry */

/*
* Copy of global cpuset_mems_generation as of the most
@@ -106,8 +92,6 @@ 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;
@@ -123,16 +107,6 @@ static inline int is_mem_exclusive(const
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);
@@ -173,388 +147,32 @@ 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
- * require taking task_lock() when dereferencing a tasks cpuset pointer.
- * See "The task_lock() exception", at the end of this comment.
- *
- * A task must hold both mutexes to modify cpusets. If a task
- * holds manage_mutex, then it blocks others wanting that mutex,
- * ensuring that it is the only task able to also acquire callback_mutex
- * and be able to modify cpusets. It can perform various checks on
- * the cpuset structure first, knowing nothing will change. It can
- * also allocate memory while just holding manage_mutex. While it is
- * performing these checks, various callback routines can briefly
- * acquire callback_mutex to query cpusets. Once it is ready to make
- * the changes, it takes callback_mutex, blocking everyone else.
- *
- * Calls to the kernel memory allocator can not be made while holding
- * callback_mutex, as that would risk double tripping on callback_mutex
- * from one of the callbacks into the cpuset code from within
- * __alloc_pages().
- *
- * If a task is only holding callback_mutex, then it has read-only
- * access to cpusets.
- *
- * The task_struct fields mems_allowed and mems_generation may only
- * be accessed in the context of that task, so require no locks.
- *
- * Any task can increment and decrement the count field without lock.
- * So in general, code holding manage_mutex or callback_mutex can't rely
- * on the count field not changing. However, if the count goes to
- * zero, then only attach_task(), which holds both mutexes, can
- * increment it again. Because a count of zero means that no tasks
- * are currently attached, therefore there is no way a task attached
- * to that cpuset can fork (the other way to increment the count).
- * So code holding manage_mutex or callback_mutex can safely assume that
- * if the count is zero, it will stay zero. Similarly, if a task
- * holds manage_mutex or callback_mutex on a cpuset with zero count, it
- * knows that the cpuset won't be removed, as cpuset_rmdir() needs
- * both of those mutexes.
- *
- * The cpuset_common_file_write handler for operations that modify
- * the cpuset hierarchy holds manage_mutex across the entire operation,
- * single threading all such cpuset modifications across the system.
- *
- * The cpuset_common_file_read() handlers only hold callback_mutex across
- * small pieces of code, such as when reading out possibly multi-word
- * cpumasks and nodemasks.
- *
- * The fork and exit callbacks cpuset_fork() and cpuset_exit(), don't
- * (usually) take either mutex. These are the two most performance
- * critical pieces of code here. The exception occurs on cpuset_exit(),
- * when a task in a notify_on_release cpuset exits. Then manage_mutex
- * is taken, and if the cpuset count is zero, a usermode call made
- * to /sbin/cpuset_release_agent with the name of the cpuset (path
- * relative to the root of cpuset file system) as the argument.
- *
- * A cpuset can only be deleted if both its 'count' of using tasks
- * is zero, and its list of 'children' cpusets is empty. Since all
- * tasks in the system use _some_ cpuset, and since there is always at
- * least one task in the system (init), therefore, top_cpuset
- * always has either children cpusets and/or using tasks. So we don't
- * need a special hack to ensure that top_cpuset cannot be deleted.
- *
- * The above "Tale of Two Semaphores" would be complete, but for:
- *
- * The task_lock() exception
- *
- * The need for this exception arises from the action of attach_task(),
- * which overwrites one tasks cpuset pointer with another. It does
- * so using both mutexes, however there are several performance
- * critical places that need to reference task->cpuset without the
- * expense of grabbing a system global mutex. Therefore except as
- * noted below, when dereferencing or, as in attach_task(), modifying
- * a tasks cpuset pointer we use task_lock(), which acts on a spinlock
- * (task->alloc_lock) already in the task_struct routinely used for
- * such matters.
- *
- * P.S. One more locking exception. RCU is used to guard the
- * update of a tasks cpuset pointer by attach_task() and the
- * access of task->cpuset->mems_generation via that pointer in
- * 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 "container" 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 *container_fs = get_fs_type("container");
+ int ret = -ENODEV;
+ container_set_release_agent_path("/sbin/cpuset_release_agent ");
+ if (container_fs) {
+ ret = container_fs->get_sb(container_fs, flags,
+ unused_dev_name,
+ data, mnt);
+ put_filesystem(container_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_dentry->d_parent->d_fsdata
- * - the 'cftype' of the file is file->f_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, 0);
- 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
@@ -652,20 +270,20 @@ void cpuset_update_task_memory_state(voi
struct task_struct *tsk = current;
struct cpuset *cs;

- if (tsk->cpuset == &top_cpuset) {
+ if (tsk->container->cpuset == &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);
+ cs = rcu_dereference(tsk->container->cpuset);
my_cpusets_mem_gen = cs->mems_generation;
rcu_read_unlock();
}

if (my_cpusets_mem_gen != tsk->cpuset_mems_generation) {
- mutex_lock(&callback_mutex);
+ container_lock();
task_lock(tsk);
- cs = tsk->cpuset; /* Maybe changed when task not locked */
+ cs = tsk->container->cpuset; /* 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))
@@ -677,7 +295,7 @@ void cpuset_update_task_memory_state(voi
else
tsk->flags &= ~PF_SPREAD_SLAB;
task_unlock(tsk);
- mutex_unlock(&callback_mutex);
+ container_unlock();
mpol_rebind_task(tsk, &tsk->mems_allowed);
}
}
@@ -720,10 +338,12 @@ static int is_cpuset_subset(const struct

static int validate_change(const struct cpuset *cur, const struct cpuset *trial)
{
+ struct container *cont;
struct cpuset *c, *par;

/* Each of our child cpusets must be a subset of us */
- list_for_each_entry(c, &cur->children, sibling) {
+ list_for_each_entry(cont, &cur->container->children, sibling) {
+ c = cont->cpuset;
if (!is_cpuset_subset(c, trial))
return -EBUSY;
}
@@ -737,7 +357,8 @@ static int validate_change(const struct
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->container->children, sibling) {
+ c = cont->cpuset;
if ((is_cpu_exclusive(trial) || is_cpu_exclusive(c)) &&
c != cur &&
cpus_intersects(trial->cpus_allowed, c->cpus_allowed))
@@ -767,6 +388,7 @@ static int validate_change(const struct

static void update_cpu_domains(struct cpuset *cur)
{
+ struct container *cont;
struct cpuset *c, *par = cur->parent;
cpumask_t pspan, cspan;

@@ -778,7 +400,8 @@ static void update_cpu_domains(struct cp
* children
*/
pspan = par->cpus_allowed;
- list_for_each_entry(c, &par->children, sibling) {
+ list_for_each_entry(cont, &par->container->children, sibling) {
+ c = cont->cpuset;
if (is_cpu_exclusive(c))
cpus_andnot(pspan, pspan, c->cpus_allowed);
}
@@ -795,7 +418,8 @@ static void update_cpu_domains(struct cp
* Get all cpus from current cpuset's cpus_allowed not part
* of exclusive children
*/
- list_for_each_entry(c, &cur->children, sibling) {
+ list_for_each_entry(cont, &cur->container->children, sibling) {
+ c = cont->cpuset;
if (is_cpu_exclusive(c))
cpus_andnot(cspan, cspan, c->cpus_allowed);
}
@@ -830,9 +454,9 @@ static int update_cpumask(struct cpuset
if (retval < 0)
return retval;
cpus_unchanged = cpus_equal(cs->cpus_allowed, trialcs.cpus_allowed);
- mutex_lock(&callback_mutex);
+ container_lock();
cs->cpus_allowed = trialcs.cpus_allowed;
- mutex_unlock(&callback_mutex);
+ container_unlock();
if (is_cpu_exclusive(cs) && !cpus_unchanged)
update_cpu_domains(cs);
return 0;
@@ -876,15 +500,15 @@ static void cpuset_migrate_mm(struct mm_

cpuset_update_task_memory_state();

- mutex_lock(&callback_mutex);
+ container_lock();
tsk->mems_allowed = *to;
- mutex_unlock(&callback_mutex);
+ container_unlock();

do_migrate_pages(mm, from, to, MPOL_MF_MOVE_ALL);

- mutex_lock(&callback_mutex);
- guarantee_online_mems(tsk->cpuset, &tsk->mems_allowed);
- mutex_unlock(&callback_mutex);
+ container_lock();
+ guarantee_online_mems(tsk->container->cpuset, &tsk->mems_allowed);
+ container_unlock();
}

/*
@@ -911,12 +535,14 @@ static int update_nodemask(struct cpuset
int migrate;
int fudge;
int retval;
+ struct container *cont;

/* top_cpuset.mems_allowed tracks node_online_map; it's read-only */
if (cs == &top_cpuset)
return -EACCES;

trialcs = *cs;
+ cont = cs->container;
retval = nodelist_parse(buf, trialcs.mems_allowed);
if (retval < 0)
goto done;
@@ -934,10 +560,10 @@ static int update_nodemask(struct cpuset
if (retval < 0)
goto done;

- mutex_lock(&callback_mutex);
+ container_lock();
cs->mems_allowed = trialcs.mems_allowed;
cs->mems_generation = cpuset_mems_generation++;
- mutex_unlock(&callback_mutex);
+ container_unlock();

set_cpuset_being_rebound(cs); /* causes mpol_copy() rebind */

@@ -953,13 +579,13 @@ static int update_nodemask(struct cpuset
* enough mmarray[] w/o using GFP_ATOMIC.
*/
while (1) {
- ntasks = atomic_read(&cs->count); /* guess */
+ ntasks = atomic_read(&cs->container->count); /* guess */
ntasks += fudge;
mmarray = kmalloc(ntasks * sizeof(*mmarray), GFP_KERNEL);
if (!mmarray)
goto done;
write_lock_irq(&tasklist_lock); /* block fork */
- if (atomic_read(&cs->count) <= ntasks)
+ if (atomic_read(&cs->container->count) <= ntasks)
break; /* got enough */
write_unlock_irq(&tasklist_lock); /* try again */
kfree(mmarray);
@@ -976,7 +602,7 @@ static int update_nodemask(struct cpuset
"Cpuset mempolicy rebind incomplete.\n");
continue;
}
- if (p->cpuset != cs)
+ if (p->container != cont)
continue;
mm = get_task_mm(p);
if (!mm)
@@ -1059,15 +685,15 @@ static int update_flag(cpuset_flagbits_t
return err;
cpu_exclusive_changed =
(is_cpu_exclusive(cs) != is_cpu_exclusive(&trialcs));
- mutex_lock(&callback_mutex);
+ container_lock();
if (turning_on)
set_bit(bit, &cs->flags);
else
clear_bit(bit, &cs->flags);
- mutex_unlock(&callback_mutex);
+ container_unlock();

if (cpu_exclusive_changed)
- update_cpu_domains(cs);
+ update_cpu_domains(cs);
return 0;
}

@@ -1169,85 +795,35 @@ static int fmeter_getrate(struct fmeter
return val;
}

-/*
- * Attack task specified by pid in 'pidbuf' to cpuset 'cs', possibly
- * writing the path of the old cpuset in 'ppathbuf' if it needs to be
- * notified on release.
- *
- * Call holding manage_mutex. May take callback_mutex and task_lock of
- * the task 'pid' during call.
- */
-
-static int attach_task(struct cpuset *cs, char *pidbuf, char **ppathbuf)
+int cpuset_can_attach_task(struct container *cont, struct task_struct *tsk)
{
- pid_t pid;
- struct task_struct *tsk;
- struct cpuset *oldcs;
- cpumask_t cpus;
- nodemask_t from, to;
- struct mm_struct *mm;
- int retval;
+ struct cpuset *cs = cont->cpuset;

- if (sscanf(pidbuf, "%d", &pid) != 1)
- return -EIO;
if (cpus_empty(cs->cpus_allowed) || nodes_empty(cs->mems_allowed))
return -ENOSPC;

- if (pid) {
- read_lock(&tasklist_lock);
-
- tsk = find_task_by_pid(pid);
- if (!tsk || tsk->flags & PF_EXITING) {
- read_unlock(&tasklist_lock);
- return -ESRCH;
- }
-
- get_task_struct(tsk);
- read_unlock(&tasklist_lock);
-
- if ((current->euid) && (current->euid != tsk->uid)
- && (current->euid != tsk->suid)) {
- put_task_struct(tsk);
- return -EACCES;
- }
- } else {
- tsk = current;
- get_task_struct(tsk);
- }
-
- retval = security_task_setscheduler(tsk, 0, NULL);
- if (retval) {
- put_task_struct(tsk);
- return retval;
- }
-
- mutex_lock(&callback_mutex);
-
- task_lock(tsk);
- oldcs = tsk->cpuset;
- /*
- * After getting 'oldcs' cpuset ptr, be sure still not exiting.
- * If 'oldcs' might be the top_cpuset due to the_top_cpuset_hack
- * then fail this attach_task(), to avoid breaking top_cpuset.count.
- */
- if (tsk->flags & PF_EXITING) {
- task_unlock(tsk);
- mutex_unlock(&callback_mutex);
- put_task_struct(tsk);
- return -ESRCH;
- }
- atomic_inc(&cs->count);
- rcu_assign_pointer(tsk->cpuset, cs);
- task_unlock(tsk);
+ return security_task_setscheduler(tsk, 0, NULL);
+}

+void cpuset_attach_task(struct container *cont, struct task_struct *tsk)
+{
+ cpumask_t cpus;
+ struct cpuset *cs = cont->cpuset;
guarantee_online_cpus(cs, &cpus);
set_cpus_allowed(tsk, cpus);
+}
+
+void cpuset_post_attach_task(struct container *cont,
+ struct container *oldcont,
+ struct task_struct *tsk)
+{
+ nodemask_t from, to;
+ struct mm_struct *mm;
+ struct cpuset *cs = cont->cpuset;
+ struct cpuset *oldcs = oldcont->cpuset;

from = oldcs->mems_allowed;
to = cs->mems_allowed;
-
- mutex_unlock(&callback_mutex);
-
mm = get_task_mm(tsk);
if (mm) {
mpol_rebind_mm(mm, &to);
@@ -1256,43 +832,35 @@ static int attach_task(struct cpuset *cs
mmput(mm);
}

- put_task_struct(tsk);
- synchronize_rcu();
- if (atomic_dec_and_test(&oldcs->count))
- check_for_release(oldcs, ppathbuf);
- return 0;
}

/* The various types of files and directories in a cpuset file system */

typedef enum {
- FILE_ROOT,
- FILE_DIR,
FILE_MEMORY_MIGRATE,
FILE_CPULIST,
FILE_MEMLIST,
FILE_CPU_EXCLUSIVE,
FILE_MEM_EXCLUSIVE,
- FILE_NOTIFY_ON_RELEASE,
FILE_MEMORY_PRESSURE_ENABLED,
FILE_MEMORY_PRESSURE,
FILE_SPREAD_PAGE,
FILE_SPREAD_SLAB,
- FILE_TASKLIST,
} cpuset_filetype_t;

-static ssize_t cpuset_common_file_write(struct file *file, const char __user *userbuf,
+static ssize_t cpuset_common_file_write(struct container *cont,
+ struct cftype *cft,
+ struct file *file,
+ const char __user *userbuf,
size_t nbytes, loff_t *unused_ppos)
{
- struct cpuset *cs = __d_cs(file->f_dentry->d_parent);
- struct cftype *cft = __d_cft(file->f_dentry);
+ struct cpuset *cs = cont->cpuset;
cpuset_filetype_t type = cft->private;
char *buffer;
- char *pathbuf = NULL;
int retval = 0;

- /* Crude upper limit on largest legitimate cpulist user might write. */
- if (nbytes > 100 + 6 * NR_CPUS)
+ /* Crude upper limit on largest legitimate list user might write. */
+ if (nbytes > 100 + 6 * max(NR_CPUS, MAX_NUMNODES))
return -E2BIG;

/* +1 for nul-terminator */
@@ -1305,9 +873,9 @@ static ssize_t cpuset_common_file_write(
}
buffer[nbytes] = 0; /* nul-terminate */

- mutex_lock(&manage_mutex);
+ container_manage_lock();

- if (is_removed(cs)) {
+ if (container_is_removed(cont)) {
retval = -ENODEV;
goto out2;
}
@@ -1325,9 +893,6 @@ static ssize_t cpuset_common_file_write(
case FILE_MEM_EXCLUSIVE:
retval = update_flag(CS_MEM_EXCLUSIVE, cs, buffer);
break;
- case FILE_NOTIFY_ON_RELEASE:
- retval = update_flag(CS_NOTIFY_ON_RELEASE, cs, buffer);
- break;
case FILE_MEMORY_MIGRATE:
retval = update_flag(CS_MEMORY_MIGRATE, cs, buffer);
break;
@@ -1345,9 +910,6 @@ static ssize_t cpuset_common_file_write(
retval = update_flag(CS_SPREAD_SLAB, cs, buffer);
cs->mems_generation = cpuset_mems_generation++;
break;
- case FILE_TASKLIST:
- retval = attach_task(cs, buffer, &pathbuf);
- break;
default:
retval = -EINVAL;
goto out2;
@@ -1356,30 +918,12 @@ static ssize_t cpuset_common_file_write(
if (retval == 0)
retval = nbytes;
out2:
- mutex_unlock(&manage_mutex);
- cpuset_release_agent(pathbuf);
+ container_manage_unlock();
out1:
kfree(buffer);
return retval;
}

-static ssize_t cpuset_file_write(struct file *file, const char __user *buf,
- size_t nbytes, loff_t *ppos)
-{
- ssize_t retval = 0;
- struct cftype *cft = __d_cft(file->f_dentry);
- if (!cft)
- return -ENODEV;
-
- /* special function ? */
- if (cft->write)
- retval = cft->write(file, buf, nbytes, ppos);
- else
- retval = cpuset_common_file_write(file, buf, nbytes, ppos);
-
- return retval;
-}
-
/*
* These ascii lists should be read in a single call, by using a user
* buffer large enough to hold the entire map. If read in smaller
@@ -1396,9 +940,9 @@ static int cpuset_sprintf_cpulist(char *
{
cpumask_t mask;

- mutex_lock(&callback_mutex);
+ container_lock();
mask = cs->cpus_allowed;
- mutex_unlock(&callback_mutex);
+ container_unlock();

return cpulist_scnprintf(page, PAGE_SIZE, mask);
}
@@ -1407,18 +951,20 @@ static int cpuset_sprintf_memlist(char *
{
nodemask_t mask;

- mutex_lock(&callback_mutex);
+ container_lock();
mask = cs->mems_allowed;
- mutex_unlock(&callback_mutex);
+ container_unlock();

return nodelist_scnprintf(page, PAGE_SIZE, mask);
}

-static ssize_t cpuset_common_file_read(struct file *file, char __user *buf,
- size_t nbytes, loff_t *ppos)
+static ssize_t cpuset_common_file_read(struct container *cont,
+ struct cftype *cft,
+ struct file *file,
+ char __user *buf,
+ size_t nbytes, loff_t *ppos)
{
- struct cftype *cft = __d_cft(file->f_dentry);
- struct cpuset *cs = __d_cs(file->f_dentry->d_parent);
+ struct cpuset *cs = cont->cpuset;
cpuset_filetype_t type = cft->private;
char *page;
ssize_t retval = 0;
@@ -1442,9 +988,6 @@ static ssize_t cpuset_common_file_read(s
case FILE_MEM_EXCLUSIVE:
*s++ = is_mem_exclusive(cs) ? '1' : '0';
break;
- case FILE_NOTIFY_ON_RELEASE:
- *s++ = notify_on_release(cs) ? '1' : '0';
- break;
case FILE_MEMORY_MIGRATE:
*s++ = is_memory_migrate(cs) ? '1' : '0';
break;
@@ -1472,391 +1015,97 @@ out:
return retval;
}

-static ssize_t cpuset_file_read(struct file *file, char __user *buf, size_t nbytes,
- loff_t *ppos)
-{
- ssize_t retval = 0;
- struct cftype *cft = __d_cft(file->f_dentry);
- if (!cft)
- return -ENODEV;
-
- /* special function ? */
- if (cft->read)
- retval = cft->read(file, buf, nbytes, ppos);
- else
- retval = cpuset_common_file_read(file, buf, nbytes, ppos);
-
- return retval;
-}
-
-static int cpuset_file_open(struct inode *inode, struct file *file)
-{
- int err;
- struct cftype *cft;
-
- err = generic_file_open(inode, file);
- if (err)
- return err;
-
- cft = __d_cft(file->f_dentry);
- if (!cft)
- return -ENODEV;
- if (cft->open)
- err = cft->open(inode, file);
- else
- err = 0;
-
- return err;
-}
-
-static int cpuset_file_release(struct inode *inode, struct file *file)
-{
- struct cftype *cft = __d_cft(file->f_dentry);
- if (cft->release)
- return cft->release(inode, file);
- return 0;
-}
-
-/*
- * cpuset_rename - Only allow simple rename of directories in place.
- */
-static int cpuset_rename(struct inode *old_dir, struct dentry *old_dentry,
- struct inode *new_dir, struct dentry *new_dentry)
-{
- if (!S_ISDIR(old_dentry->d_inode->i_mode))
- return -ENOTDIR;
- if (new_dentry->d_inode)
- return -EEXIST;
- if (old_dir != new_dir)
- return -EIO;
- return simple_rename(old_dir, old_dentry, new_dir, new_dentry);
-}
-
-static struct file_operations cpuset_file_operations = {
- .read = cpuset_file_read,
- .write = cpuset_file_write,
- .llseek = generic_file_llseek,
- .open = cpuset_file_open,
- .release = cpuset_file_release,
-};
-
-static struct inode_operations cpuset_dir_inode_operations = {
- .lookup = simple_lookup,
- .mkdir = cpuset_mkdir,
- .rmdir = cpuset_rmdir,
- .rename = cpuset_rename,
-};
-
-static int cpuset_create_file(struct dentry *dentry, int mode)
-{
- struct inode *inode;
-
- if (!dentry)
- return -ENOENT;
- if (dentry->d_inode)
- return -EEXIST;
-
- inode = cpuset_new_inode(mode);
- if (!inode)
- return -ENOMEM;
-
- if (S_ISDIR(mode)) {
- inode->i_op = &cpuset_dir_inode_operations;
- inode->i_fop = &simple_dir_operations;
-
- /* start off with i_nlink == 2 (for "." entry) */
- inc_nlink(inode);
- } else if (S_ISREG(mode)) {
- inode->i_size = 0;
- inode->i_fop = &cpuset_file_operations;
- }
-
- d_instantiate(dentry, inode);
- dget(dentry); /* Extra count - pin the dentry in core */
- return 0;
-}
-
-/*
- * cpuset_create_dir - create a directory for an object.
- * cs: the cpuset we create the directory for.
- * It must have a valid ->parent field
- * And we are going to fill its ->dentry field.
- * name: The name to give to the cpuset directory. Will be copied.
- * mode: mode to set on new directory.
- */
-
-static int cpuset_create_dir(struct cpuset *cs, const char *name, int mode)
-{
- struct dentry *dentry = NULL;
- struct dentry *parent;
- int error = 0;
-
- parent = cs->parent->dentry;
- dentry = cpuset_get_dentry(parent, name);
- if (IS_ERR(dentry))
- return PTR_ERR(dentry);
- error = cpuset_create_file(dentry, S_IFDIR | mode);
- if (!error) {
- dentry->d_fsdata = cs;
- inc_nlink(parent->d_inode);
- cs->dentry = dentry;
- }
- dput(dentry);
-
- return error;
-}
-
-static int cpuset_add_file(struct dentry *dir, const struct cftype *cft)
-{
- struct dentry *dentry;
- int error;
-
- mutex_lock(&dir->d_inode->i_mutex);
- dentry = cpuset_get_dentry(dir, cft->name);
- if (!IS_ERR(dentry)) {
- error = cpuset_create_file(dentry, 0644 | S_IFREG);
- if (!error)
- dentry->d_fsdata = (void *)cft;
- dput(dentry);
- } else
- error = PTR_ERR(dentry);
- mutex_unlock(&dir->d_inode->i_mutex);
- return error;
-}
-
-/*
- * Stuff for reading the 'tasks' file.
- *
- * Reading this file can return large amounts of data if a cpuset has
- * *lots* of attached tasks. So it may need several calls to read(),
- * but we cannot guarantee that the information we produce is correct
- * unless we produce it entirely atomically.
- *
- * Upon tasks file open(), a struct ctr_struct is allocated, that
- * will have a pointer to an array (also allocated here). The struct
- * ctr_struct * is stored in file->private_data. Its resources will
- * be freed by release() when the file is closed. The array is used
- * to sprintf the PIDs and then used by read().
- */
-
-/* cpusets_tasks_read array */
-
-struct ctr_struct {
- char *buf;
- int bufsz;
-};
-
-/*
- * Load into 'pidarray' up to 'npids' of the tasks using cpuset 'cs'.
- * Return actual number of pids loaded. No need to task_lock(p)
- * when reading out p->cpuset, as we don't really care if it changes
- * on the next cycle, and we are not going to try to dereference it.
- */
-static int pid_array_load(pid_t *pidarray, int npids, struct cpuset *cs)
-{
- int n = 0;
- struct task_struct *g, *p;
-
- read_lock(&tasklist_lock);
-
- do_each_thread(g, p) {
- if (p->cpuset == cs) {
- pidarray[n++] = p->pid;
- if (unlikely(n == npids))
- goto array_full;
- }
- } while_each_thread(g, p);
-
-array_full:
- read_unlock(&tasklist_lock);
- return n;
-}
-
-static int cmppid(const void *a, const void *b)
-{
- return *(pid_t *)a - *(pid_t *)b;
-}
-
-/*
- * Convert array 'a' of 'npids' pid_t's to a string of newline separated
- * decimal pids in 'buf'. Don't write more than 'sz' chars, but return
- * count 'cnt' of how many chars would be written if buf were large enough.
- */
-static int pid_array_to_buf(char *buf, int sz, pid_t *a, int npids)
-{
- int cnt = 0;
- int i;
-
- for (i = 0; i < npids; i++)
- cnt += snprintf(buf + cnt, max(sz - cnt, 0), "%d\n", a[i]);
- return cnt;
-}
-
-/*
- * Handle an open on 'tasks' file. Prepare a buffer listing the
- * process id's of tasks currently attached to the cpuset being opened.
- *
- * Does not require any specific cpuset mutexes, and does not take any.
- */
-static int cpuset_tasks_open(struct inode *unused, struct file *file)
-{
- struct cpuset *cs = __d_cs(file->f_dentry->d_parent);
- struct ctr_struct *ctr;
- pid_t *pidarray;
- int npids;
- char c;
-
- if (!(file->f_mode & FMODE_READ))
- return 0;
-
- ctr = kmalloc(sizeof(*ctr), GFP_KERNEL);
- if (!ctr)
- goto err0;
-
- /*
- * If cpuset gets more users after we read count, we won't have
- * enough space - tough. This race is indistinguishable to the
- * caller from the case that the additional cpuset users didn't
- * show up until sometime later on.
- */
- npids = atomic_read(&cs->count);
- pidarray = kmalloc(npids * sizeof(pid_t), GFP_KERNEL);
- if (!pidarray)
- goto err1;
-
- npids = pid_array_load(pidarray, npids, cs);
- sort(pidarray, npids, sizeof(pid_t), cmppid, NULL);
-
- /* Call pid_array_to_buf() twice, first just to get bufsz */
- ctr->bufsz = pid_array_to_buf(&c, sizeof(c), pidarray, npids) + 1;
- ctr->buf = kmalloc(ctr->bufsz, GFP_KERNEL);
- if (!ctr->buf)
- goto err2;
- ctr->bufsz = pid_array_to_buf(ctr->buf, ctr->bufsz, pidarray, npids);
-
- kfree(pidarray);
- file->private_data = ctr;
- return 0;
-
-err2:
- kfree(pidarray);
-err1:
- kfree(ctr);
-err0:
- return -ENOMEM;
-}
-
-static ssize_t cpuset_tasks_read(struct file *file, char __user *buf,
- size_t nbytes, loff_t *ppos)
-{
- struct ctr_struct *ctr = file->private_data;
-
- if (*ppos + nbytes > ctr->bufsz)
- nbytes = ctr->bufsz - *ppos;
- if (copy_to_user(buf, ctr->buf + *ppos, nbytes))
- return -EFAULT;
- *ppos += nbytes;
- return nbytes;
-}
-
-static int cpuset_tasks_release(struct inode *unused_inode, struct file *file)
-{
- struct ctr_struct *ctr;
-
- if (file->f_mode & FMODE_READ) {
- ctr = file->private_data;
- kfree(ctr->buf);
- kfree(ctr);
- }
- return 0;
-}

/*
* for the common functions, 'private' gives the type of file
*/

-static struct cftype cft_tasks = {
- .name = "tasks",
- .open = cpuset_tasks_open,
- .read = cpuset_tasks_read,
- .release = cpuset_tasks_release,
- .private = FILE_TASKLIST,
-};
-
static struct cftype cft_cpus = {
.name = "cpus",
+ .read = cpuset_common_file_read,
+ .write = cpuset_common_file_write,
.private = FILE_CPULIST,
};

static struct cftype cft_mems = {
.name = "mems",
+ .read = cpuset_common_file_read,
+ .write = cpuset_common_file_write,
.private = FILE_MEMLIST,
};

static struct cftype cft_cpu_exclusive = {
.name = "cpu_exclusive",
+ .read = cpuset_common_file_read,
+ .write = cpuset_common_file_write,
.private = FILE_CPU_EXCLUSIVE,
};

static struct cftype cft_mem_exclusive = {
.name = "mem_exclusive",
+ .read = cpuset_common_file_read,
+ .write = cpuset_common_file_write,
.private = FILE_MEM_EXCLUSIVE,
};

-static struct cftype cft_notify_on_release = {
- .name = "notify_on_release",
- .private = FILE_NOTIFY_ON_RELEASE,
-};
-
static struct cftype cft_memory_migrate = {
.name = "memory_migrate",
+ .read = cpuset_common_file_read,
+ .write = cpuset_common_file_write,
.private = FILE_MEMORY_MIGRATE,
};

static struct cftype cft_memory_pressure_enabled = {
.name = "memory_pressure_enabled",
+ .read = cpuset_common_file_read,
+ .write = cpuset_common_file_write,
.private = FILE_MEMORY_PRESSURE_ENABLED,
};

static struct cftype cft_memory_pressure = {
.name = "memory_pressure",
+ .read = cpuset_common_file_read,
+ .write = cpuset_common_file_write,
.private = FILE_MEMORY_PRESSURE,
};

static struct cftype cft_spread_page = {
.name = "memory_spread_page",
+ .read = cpuset_common_file_read,
+ .write = cpuset_common_file_write,
.private = FILE_SPREAD_PAGE,
};

static struct cftype cft_spread_slab = {
.name = "memory_spread_slab",
+ .read = cpuset_common_file_read,
+ .write = cpuset_common_file_write,
.private = FILE_SPREAD_SLAB,
};

-static int cpuset_populate_dir(struct dentry *cs_dentry)
+int cpuset_populate_dir(struct container *cont)
{
int err;

- if ((err = cpuset_add_file(cs_dentry, &cft_cpus)) < 0)
- return err;
- if ((err = cpuset_add_file(cs_dentry, &cft_mems)) < 0)
+ if ((err = container_add_file(cont, &cft_cpus)) < 0)
return err;
- if ((err = cpuset_add_file(cs_dentry, &cft_cpu_exclusive)) < 0)
+ if ((err = container_add_file(cont, &cft_mems)) < 0)
return err;
- if ((err = cpuset_add_file(cs_dentry, &cft_mem_exclusive)) < 0)
+ if ((err = container_add_file(cont, &cft_cpu_exclusive)) < 0)
return err;
- if ((err = cpuset_add_file(cs_dentry, &cft_notify_on_release)) < 0)
+ if ((err = container_add_file(cont, &cft_mem_exclusive)) < 0)
return err;
- if ((err = cpuset_add_file(cs_dentry, &cft_memory_migrate)) < 0)
+ if ((err = container_add_file(cont, &cft_memory_migrate)) < 0)
return err;
- if ((err = cpuset_add_file(cs_dentry, &cft_memory_pressure)) < 0)
+ if ((err = container_add_file(cont, &cft_memory_pressure)) < 0)
return err;
- if ((err = cpuset_add_file(cs_dentry, &cft_spread_page)) < 0)
+ if ((err = container_add_file(cont, &cft_spread_page)) < 0)
return err;
- if ((err = cpuset_add_file(cs_dentry, &cft_spread_slab)) < 0)
- return err;
- if ((err = cpuset_add_file(cs_dentry, &cft_tasks)) < 0)
+ if ((err = container_add_file(cont, &cft_spread_slab)) < 0)
return err;
+ /* memory_pressure_enabled is in root cpuset only */
+ if (err == 0 && !cont->parent)
+ err = container_add_file(cont, &cft_memory_pressure_enabled);
return 0;
}

@@ -1869,66 +1118,31 @@ static int cpuset_populate_dir(struct de
* Must be called with the mutex on the parent inode held
*/

-static long cpuset_create(struct cpuset *parent, const char *name, int mode)
+int cpuset_create(struct container *cont)
{
struct cpuset *cs;
- int err;
+ struct cpuset *parent = cont->parent->cpuset;

cs = kmalloc(sizeof(*cs), GFP_KERNEL);
if (!cs)
return -ENOMEM;

- mutex_lock(&manage_mutex);
cpuset_update_task_memory_state();
cs->flags = 0;
- if (notify_on_release(parent))
- set_bit(CS_NOTIFY_ON_RELEASE, &cs->flags);
if (is_spread_page(parent))
set_bit(CS_SPREAD_PAGE, &cs->flags);
if (is_spread_slab(parent))
set_bit(CS_SPREAD_SLAB, &cs->flags);
cs->cpus_allowed = CPU_MASK_NONE;
cs->mems_allowed = NODE_MASK_NONE;
- atomic_set(&cs->count, 0);
- INIT_LIST_HEAD(&cs->sibling);
- INIT_LIST_HEAD(&cs->children);
cs->mems_generation = cpuset_mems_generation++;
fmeter_init(&cs->fmeter);

cs->parent = parent;
-
- mutex_lock(&callback_mutex);
- list_add(&cs->sibling, &cs->parent->children);
+ cont->cpuset = cs;
+ cs->container = cont;
number_of_cpusets++;
- mutex_unlock(&callback_mutex);
-
- err = cpuset_create_dir(cs, name, mode);
- if (err < 0)
- goto err;
-
- /*
- * Release manage_mutex before cpuset_populate_dir() because it
- * will down() this new directory's i_mutex and if we race with
- * another mkdir, we might deadlock.
- */
- mutex_unlock(&manage_mutex);
-
- err = cpuset_populate_dir(cs->dentry);
- /* If err < 0, we have a half-filled directory - oh well ;) */
return 0;
-err:
- list_del(&cs->sibling);
- mutex_unlock(&manage_mutex);
- kfree(cs);
- return err;
-}
-
-static int cpuset_mkdir(struct inode *dir, struct dentry *dentry, int mode)
-{
- struct cpuset *c_parent = dentry->d_parent->d_fsdata;
-
- /* the vfs holds inode->i_mutex already */
- return cpuset_create(c_parent, dentry->d_name.name, mode | S_IFDIR);
}

/*
@@ -1942,49 +1156,16 @@ static int cpuset_mkdir(struct inode *di
* nesting would risk an ABBA deadlock.
*/

-static int cpuset_rmdir(struct inode *unused_dir, struct dentry *dentry)
+void cpuset_destroy(struct container *cont)
{
- struct cpuset *cs = dentry->d_fsdata;
- struct dentry *d;
- struct cpuset *parent;
- char *pathbuf = NULL;
-
- /* the vfs holds both inode->i_mutex already */
+ struct cpuset *cs = cont->cpuset;

- mutex_lock(&manage_mutex);
cpuset_update_task_memory_state();
- if (atomic_read(&cs->count) > 0) {
- mutex_unlock(&manage_mutex);
- return -EBUSY;
- }
- if (!list_empty(&cs->children)) {
- mutex_unlock(&manage_mutex);
- return -EBUSY;
- }
if (is_cpu_exclusive(cs)) {
int retval = update_flag(CS_CPU_EXCLUSIVE, cs, "0");
- if (retval < 0) {
- mutex_unlock(&manage_mutex);
- return retval;
- }
+ BUG_ON(retval);
}
- parent = cs->parent;
- mutex_lock(&callback_mutex);
- set_bit(CS_REMOVED, &cs->flags);
- list_del(&cs->sibling); /* delete my sibling from parent->children */
- spin_lock(&cs->dentry->d_lock);
- d = dget(cs->dentry);
- cs->dentry = NULL;
- spin_unlock(&d->d_lock);
- cpuset_d_remove_dir(d);
- dput(d);
number_of_cpusets--;
- mutex_unlock(&callback_mutex);
- if (list_empty(&parent->children))
- check_for_release(parent, &pathbuf);
- mutex_unlock(&manage_mutex);
- cpuset_release_agent(pathbuf);
- return 0;
}

/*
@@ -1995,10 +1176,10 @@ static int cpuset_rmdir(struct inode *un

int __init cpuset_init_early(void)
{
- struct task_struct *tsk = current;
-
- tsk->cpuset = &top_cpuset;
- tsk->cpuset->mems_generation = cpuset_mems_generation++;
+ struct container *cont = current->container;
+ cont->cpuset = &top_cpuset;
+ top_cpuset.container = cont;
+ cont->cpuset->mems_generation = cpuset_mems_generation++;
return 0;
}

@@ -2010,39 +1191,19 @@ int __init cpuset_init_early(void)

int __init cpuset_init(void)
{
- struct dentry *root;
- int err;
-
+ int err = 0;
top_cpuset.cpus_allowed = CPU_MASK_ALL;
top_cpuset.mems_allowed = NODE_MASK_ALL;

fmeter_init(&top_cpuset.fmeter);
top_cpuset.mems_generation = cpuset_mems_generation++;

- init_task.cpuset = &top_cpuset;
-
err = register_filesystem(&cpuset_fs_type);
if (err < 0)
- goto out;
- cpuset_mount = kern_mount(&cpuset_fs_type);
- if (IS_ERR(cpuset_mount)) {
- printk(KERN_ERR "cpuset: could not mount!\n");
- err = PTR_ERR(cpuset_mount);
- cpuset_mount = NULL;
- goto out;
- }
- root = cpuset_mount->mnt_sb->s_root;
- root->d_fsdata = &top_cpuset;
- inc_nlink(root->d_inode);
- top_cpuset.dentry = root;
- root->d_inode->i_op = &cpuset_dir_inode_operations;
+ return err;
+
number_of_cpusets = 1;
- err = cpuset_populate_dir(root);
- /* memory_pressure_enabled is in root cpuset only */
- if (err == 0)
- err = cpuset_add_file(root, &cft_memory_pressure_enabled);
-out:
- return err;
+ return 0;
}

#if defined(CONFIG_HOTPLUG_CPU) || defined(CONFIG_MEMORY_HOTPLUG)
@@ -2069,10 +1230,12 @@ out:

static void guarantee_online_cpus_mems_in_subtree(const struct cpuset *cur)
{
+ struct container *cont;
struct cpuset *c;

/* Each of our child cpusets mems must be online */
- list_for_each_entry(c, &cur->children, sibling) {
+ list_for_each_entry(c, &cur->container->children, sibling) {
+ c = container_cs(cont);
guarantee_online_cpus_mems_in_subtree(c);
if (!cpus_empty(c->cpus_allowed))
guarantee_online_cpus(c, &c->cpus_allowed);
@@ -2099,15 +1262,15 @@ static void guarantee_online_cpus_mems_i

static void common_cpu_mem_hotplug_unplug(void)
{
- mutex_lock(&manage_mutex);
- mutex_lock(&callback_mutex);
+ container_manage_lock();
+ container_lock();

guarantee_online_cpus_mems_in_subtree(&top_cpuset);
top_cpuset.cpus_allowed = cpu_online_map;
top_cpuset.mems_allowed = node_online_map;

- mutex_unlock(&callback_mutex);
- mutex_unlock(&manage_mutex);
+ container_unlock();
+ container_manage_unlock();
}
#endif

@@ -2158,111 +1321,6 @@ void __init cpuset_init_smp(void)
}

/**
- * cpuset_fork - attach newly forked task to its parents cpuset.
- * @tsk: pointer to task_struct of forking parent process.
- *
- * Description: A task inherits its parent's cpuset at fork().
- *
- * A pointer to the shared cpuset was automatically copied in fork.c
- * by dup_task_struct(). However, we ignore that copy, since it was
- * not made under the protection of task_lock(), so might no longer be
- * a valid cpuset pointer. attach_task() might have already changed
- * current->cpuset, allowing the previously referenced cpuset to
- * be removed and freed. Instead, we task_lock(current) and copy
- * its present value of current->cpuset for our freshly forked child.
- *
- * At the point that cpuset_fork() is called, 'current' is the parent
- * task, and the passed argument 'child' points to the child task.
- **/
-
-void cpuset_fork(struct task_struct *child)
-{
- task_lock(current);
- child->cpuset = current->cpuset;
- atomic_inc(&child->cpuset->count);
- task_unlock(current);
-}
-
-/**
- * cpuset_exit - detach cpuset from exiting task
- * @tsk: pointer to task_struct of exiting process
- *
- * Description: Detach cpuset from @tsk and release it.
- *
- * Note that cpusets marked notify_on_release force every task in
- * them to take the global manage_mutex mutex when exiting.
- * This could impact scaling on very large systems. Be reluctant to
- * use notify_on_release cpusets where very high task exit scaling
- * is required on large systems.
- *
- * Don't even think about derefencing 'cs' after the cpuset use count
- * goes to zero, except inside a critical section guarded by manage_mutex
- * or callback_mutex. Otherwise a zero cpuset use count is a license to
- * any other task to nuke the cpuset immediately, via cpuset_rmdir().
- *
- * This routine has to take manage_mutex, not callback_mutex, because
- * it is holding that mutex while calling check_for_release(),
- * which calls kmalloc(), so can't be called holding callback_mutex().
- *
- * We don't need to task_lock() this reference to tsk->cpuset,
- * because tsk is already marked PF_EXITING, so attach_task() won't
- * mess with it, or task is a failed fork, never visible to attach_task.
- *
- * the_top_cpuset_hack:
- *
- * Set the exiting tasks cpuset to the root cpuset (top_cpuset).
- *
- * Don't leave a task unable to allocate memory, as that is an
- * accident waiting to happen should someone add a callout in
- * do_exit() after the cpuset_exit() call that might allocate.
- * If a task tries to allocate memory with an invalid cpuset,
- * it will oops in cpuset_update_task_memory_state().
- *
- * We call cpuset_exit() while the task is still competent to
- * handle notify_on_release(), then leave the task attached to
- * the root cpuset (top_cpuset) for the remainder of its exit.
- *
- * To do this properly, we would increment the reference count on
- * top_cpuset, and near the very end of the kernel/exit.c do_exit()
- * code we would add a second cpuset function call, to drop that
- * reference. This would just create an unnecessary hot spot on
- * the top_cpuset reference count, to no avail.
- *
- * Normally, holding a reference to a cpuset without bumping its
- * count is unsafe. The cpuset could go away, or someone could
- * attach us to a different cpuset, decrementing the count on
- * the first cpuset that we never incremented. But in this case,
- * top_cpuset isn't going away, and either task has PF_EXITING set,
- * which wards off any attach_task() attempts, or task is a failed
- * fork, never visible to attach_task.
- *
- * Another way to do this would be to set the cpuset pointer
- * to NULL here, and check in cpuset_update_task_memory_state()
- * for a NULL pointer. This hack avoids that NULL check, for no
- * cost (other than this way too long comment ;).
- **/
-
-void cpuset_exit(struct task_struct *tsk)
-{
- struct cpuset *cs;
-
- cs = tsk->cpuset;
- tsk->cpuset = &top_cpuset; /* the_top_cpuset_hack - see above */
-
- if (notify_on_release(cs)) {
- char *pathbuf = NULL;
-
- mutex_lock(&manage_mutex);
- if (atomic_dec_and_test(&cs->count))
- check_for_release(cs, &pathbuf);
- mutex_unlock(&manage_mutex);
- cpuset_release_agent(pathbuf);
- } else {
- atomic_dec(&cs->count);
- }
-}
-
-/**
* cpuset_cpus_allowed - return cpus_allowed mask from a tasks cpuset.
* @tsk: pointer to task_struct from which to obtain cpuset->cpus_allowed.
*
@@ -2276,11 +1334,11 @@ cpumask_t cpuset_cpus_allowed(struct tas
{
cpumask_t mask;

- mutex_lock(&callback_mutex);
+ container_lock();
task_lock(tsk);
- guarantee_online_cpus(tsk->cpuset, &mask);
+ guarantee_online_cpus(tsk->container->cpuset, &mask);
task_unlock(tsk);
- mutex_unlock(&callback_mutex);
+ container_unlock();

return mask;
}
@@ -2304,11 +1362,11 @@ nodemask_t cpuset_mems_allowed(struct ta
{
nodemask_t mask;

- mutex_lock(&callback_mutex);
+ container_lock();
task_lock(tsk);
- guarantee_online_mems(tsk->cpuset, &mask);
+ guarantee_online_mems(tsk->container->cpuset, &mask);
task_unlock(tsk);
- mutex_unlock(&callback_mutex);
+ container_unlock();

return mask;
}
@@ -2408,45 +1466,18 @@ int __cpuset_zone_allowed(struct zone *z
return 1;

/* Not hardwall and node outside mems_allowed: scan up cpusets */
- mutex_lock(&callback_mutex);
+ container_lock();

task_lock(current);
- cs = nearest_exclusive_ancestor(current->cpuset);
+ cs = nearest_exclusive_ancestor(current->container->cpuset);
task_unlock(current);

allowed = node_isset(node, cs->mems_allowed);
- mutex_unlock(&callback_mutex);
+ container_unlock();
return allowed;
}

/**
- * cpuset_lock - lock out any changes to cpuset structures
- *
- * The out of memory (oom) code needs to mutex_lock cpusets
- * from being changed while it scans the tasklist looking for a
- * task in an overlapping cpuset. Expose callback_mutex via this
- * cpuset_lock() routine, so the oom code can lock it, before
- * locking the task list. The tasklist_lock is a spinlock, so
- * must be taken inside callback_mutex.
- */
-
-void cpuset_lock(void)
-{
- mutex_lock(&callback_mutex);
-}
-
-/**
- * cpuset_unlock - release lock on cpuset changes
- *
- * Undo the lock taken in a previous cpuset_lock() call.
- */
-
-void cpuset_unlock(void)
-{
- mutex_unlock(&callback_mutex);
-}
-
-/**
* cpuset_mem_spread_node() - On which node to begin search for a page
*
* If a task is marked PF_SPREAD_PAGE or PF_SPREAD_SLAB (as for
@@ -2506,7 +1537,7 @@ int cpuset_excl_nodes_overlap(const stru
task_unlock(current);
goto done;
}
- cs1 = nearest_exclusive_ancestor(current->cpuset);
+ cs1 = nearest_exclusive_ancestor(current->container->cpuset);
task_unlock(current);

task_lock((struct task_struct *)p);
@@ -2514,7 +1545,7 @@ int cpuset_excl_nodes_overlap(const stru
task_unlock((struct task_struct *)p);
goto done;
}
- cs2 = nearest_exclusive_ancestor(p->cpuset);
+ cs2 = nearest_exclusive_ancestor(p->container->cpuset);
task_unlock((struct task_struct *)p);

overlap = nodes_intersects(cs1->mems_allowed, cs2->mems_allowed);
@@ -2553,11 +1584,12 @@ void __cpuset_memory_pressure_bump(void)
struct cpuset *cs;

task_lock(current);
- cs = current->cpuset;
+ cs = current->container->cpuset;
fmeter_markevent(&cs->fmeter);
task_unlock(current);
}

+#ifdef CONFIG_PROC_PID_CPUSET
/*
* proc_cpuset_show()
* - Print tasks cpuset path into seq_file.
@@ -2588,15 +1620,15 @@ static int proc_cpuset_show(struct seq_f
goto out_free;

retval = -EINVAL;
- mutex_lock(&manage_mutex);
+ container_manage_lock();

- retval = cpuset_path(tsk->cpuset, buf, PAGE_SIZE);
+ retval = container_path(tsk->container, buf, PAGE_SIZE);
if (retval < 0)
goto out_unlock;
seq_puts(m, buf);
seq_putc(m, '\n');
out_unlock:
- mutex_unlock(&manage_mutex);
+ container_manage_unlock();
put_task_struct(tsk);
out_free:
kfree(buf);
@@ -2616,6 +1648,7 @@ struct file_operations proc_cpuset_opera
.llseek = seq_lseek,
.release = single_release,
};
+#endif /* CONFIG_PROC_PID_CPUSET */

/* Display task cpus_allowed, mems_allowed in /proc/<pid>/status file. */
char *cpuset_task_status_allowed(struct task_struct *task, char *buffer)
Index: container-2.6.19-rc5/init/Kconfig
============================================================ =======
--- container-2.6.19-rc5.orig/init/Kconfig
+++ container-2.6.19-rc5/init/Kconfig
@@ -239,17 +239,24 @@ config IKCONFIG_PROC
through /proc/config.gz.

config CONTAINERS
- bool "Container support"
- help
- This option will let you create and manage process containers,
- which can be used to aggregate multiple processes, e.g. for
- the purposes of resource tracking.
+ bool

- Say N if unsure
+config MAX_CONTAINER_SUBSYS
+ int "Number of container subsystems to support"
+ depends on CONTAINERS
+ range 1 255
+ default 8
+
+config MAX_CONTAINER_HIERARCHIES
+ int "Number of container hierarchies to support"
+ depends on CONTAINERS
+ range 2 255
+ default 4

config CPUSETS
bool "Cpuset support"
depends on SMP
+ select CONTAINERS
help
This option will let you create and manage CPUSETs which
allow dynamically partitioning a system into sets of CPUs and
@@ -258,6 +265,10 @@ config CPUSETS

Say N if unsure.

+config PROC_PID_CPUSET
+ bool "Include legacy /proc/<pid>/cpuset file"
+ depends on CPUSETS
+
config RELAY
bool "Kernel->user space relay support (formerly relayfs)"
help
Index: container-2.6.19-rc5/mm/oom_kill.c
============================================================ =======
--- container-2.6.19-rc5.orig/mm/oom_kill.c
+++ container-2.6.19-rc5/mm/oom_kill.c
@@ -395,7 +395,7 @@ void out_of_memory(struct zonelist *zone
show_mem();
}

- cpuset_lock();
+ container_lock();
read_lock(&tasklist_lock);

/*
@@ -429,7 +429,7 @@ retry:
/* Found nothing?!?! Either we hang forever, or we panic. */
if (!p) {
read_unlock(&tasklist_lock);
- cpuset_unlock();
+ container_unlock();
panic("Out of memory and no killable processes...\n");
}

@@ -441,7 +441,7 @@ retry:

out:
read_unlock(&tasklist_lock);
- cpuset_unlock();
+ container_unlock();

/*
* Give "p" a good chance of killing itself before we
Index: container-2.6.19-rc5/include/linux/sched.h
============================================================ =======
--- container-2.6.19-rc5.orig/include/linux/sched.h
+++ container-2.6.19-rc5/include/linux/sched.h
@@ -720,7 +720,6 @@ extern unsigned int max_cache_size;

struct io_context; /* See blkdev.h */
struct container;
-struct cpuset;
#define NGROUPS_SMALL 32
#define NGROUPS_PER_BLOCK ((int)(PAGE_SIZE / sizeof(gid_t)))
struct group_info {
@@ -1001,7 +1000,6 @@ 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;
@@ -1432,7 +1430,7 @@ static inline int thread_group_empty(str
/*
* 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 ->container.
*
* Nests both inside and outside of read_lock(&tasklist_lock).
* It must not be nested with write_lock_irq(&tasklist_lock),
Index: container-2.6.19-rc5/Documentation/cpusets.txt
============================================================ =======
--- container-2.6.19-rc5.orig/Documentation/cpusets.txt
+++ container-2.6.19-rc5/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
@@ -43,18 +43,19 @@ hierarchy visible in a virtual file syst
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.
+Cpusets use the generic container subsystem described in
+Documentation/container.txt.

-User level code may create and destroy cpusets by name in the 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 container
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
@@ -117,7 +118,7 @@ Cpusets extends these two mechanisms as
- 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 container 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
@@ -152,15 +153,10 @@ into the rest of the kernel, none in per
- 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 "container" 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)
@@ -170,16 +166,15 @@ in the format seen in the following exam
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 container file system
+containing (on top of the standard container 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:
@@ -253,21 +248,7 @@ such as requests from interrupt handlers
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
@@ -324,7 +305,7 @@ the tasks in the cpuset, in units of rec
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
@@ -395,7 +376,7 @@ data set, the memory allocation across t
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
@@ -485,7 +466,7 @@ 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 container none /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.
@@ -497,7 +478,7 @@ For example, the following sequence of c
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 container none /dev/cpuset
cd /dev/cpuset
mkdir Charlie
cd Charlie
@@ -507,7 +488,7 @@ and then start a subshell 'sh' in that c
sh
# The subshell 'sh' is now running in cpuset Charlie
# The next line should display '/Charlie'
- cat /proc/self/cpuset
+ cat /proc/self/container

In the future, a C library interface to cpusets will likely be
available. For now, the only way to query or modify cpusets is
@@ -529,7 +510,7 @@ Creating, modifying, using the cpusets c
virtual filesystem.

To mount it, type:
-# mount -t cpuset none /dev/cpuset
+# mount -t container none /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
Index: container-2.6.19-rc5/fs/super.c
============================================================ =======
--- container-2.6.19-rc5.orig/fs/super.c
+++ container-2.6.19-rc5/fs/super.c
@@ -39,11 +39,6 @@
#include <linux/mutex.h>
#include <asm/uaccess.h>

-
-void get_filesystem(struct file_system_type *fs);
-void put_filesystem(struct file_system_type *fs);
-struct file_system_type *get_fs_type(const char *name);
-
LIST_HEAD(super_blocks);
DEFINE_SPINLOCK(sb_lock);

Index: container-2.6.19-rc5/include/linux/fs.h
============================================================ =======
--- container-2.6.19-rc5.orig/include/linux/fs.h
+++ container-2.6.19-rc5/include/linux/fs.h
@@ -1875,6 +1875,8 @@ extern int vfs_fstat(unsigned int, struc

extern int vfs_ioctl(struct file *, unsigned int, unsigned int, unsigned long);

+extern void get_filesystem(struct file_system_type *fs);
+extern void put_filesystem(struct file_system_type *fs);
extern struct file_system_type *get_fs_type(const char *name);
extern struct super_block *get_super(struct block_device *);
extern struct super_block *user_get_super(dev_t);
Index: container-2.6.19-rc5/include/linux/mempolicy.h
============================================================ =======
--- container-2.6.19-rc5.orig/include/linux/mempolicy.h
+++ container-2.6.19-rc5/include/linux/mempolicy.h
@@ -152,7 +152,7 @@ extern void mpol_fix_fork_child_flag(str

#ifdef CONFIG_CPUSETS
#define current_cpuset_is_being_rebound() \
- (cpuset_being_rebound == current->cpuset)
+ (cpuset_being_rebound == current->container->cpuset)
#else
#define current_cpuset_is_being_rebound() 0
#endif

--
[PATCH 1/7] Generic container system abstracted from cpusets code [message #8545 is a reply to message #8540] Thu, 23 November 2006 12:08 Go to previous messageGo to next message
Paul Menage is currently offline  Paul Menage
Messages: 642
Registered: September 2006
Senior Member
This patch creates a generic process container system based on (and
parallel top) the cpusets code. At a coarse level it was created by
copying kernel/cpuset.c, doing s/cpuset/container/g, and stripping out any
code that was cpuset-specific rather than applicable to any process
container subsystem.

Signed-off-by: Paul Menage <menage@google.com>

---
Documentation/containers.txt | 229 +++++++
fs/proc/base.c | 11
include/linux/container.h | 96 +++
include/linux/sched.h | 5
init/Kconfig | 9
init/main.c | 3
kernel/Makefile | 1
kernel/container.c | 1343 +++++++++++++++++++++++++++++++++++++++++++
kernel/exit.c | 2
kernel/fork.c | 3
10 files changed, 1699 insertions(+), 3 deletions(-)

Index: container-2.6.19-rc5/fs/proc/base.c
============================================================ =======
--- container-2.6.19-rc5.orig/fs/proc/base.c
+++ container-2.6.19-rc5/fs/proc/base.c
@@ -68,6 +68,7 @@
#include <linux/security.h>
#include <linux/ptrace.h>
#include <linux/seccomp.h>
+#include <linux/container.h>
#include <linux/cpuset.h>
#include <linux/audit.h>
#include <linux/poll.h>
@@ -1782,7 +1783,10 @@ static struct pid_entry tgid_base_stuff[
#ifdef CONFIG_SCHEDSTATS
INF("schedstat", S_IRUGO, pid_schedstat),
#endif
-#ifdef CONFIG_CPUSETS
+#ifdef CONFIG_CONTAINERS
+ REG("container", S_IRUGO, container),
+#endif
+#ifdef CONFIG_PROC_PID_CPUSET
REG("cpuset", S_IRUGO, cpuset),
#endif
INF("oom_score", S_IRUGO, oom_score),
@@ -2056,7 +2060,10 @@ static struct pid_entry tid_base_stuff[]
#ifdef CONFIG_SCHEDSTATS
INF("schedstat", S_IRUGO, pid_schedstat),
#endif
-#ifdef CONFIG_CPUSETS
+#ifdef CONFIG_CONTAINERS
+ REG("container", S_IRUGO, container),
+#endif
+#ifdef CONFIG_PROC_PID_CPUSET
REG("cpuset", S_IRUGO, cpuset),
#endif
INF("oom_score", S_IRUGO, oom_score),
Index: container-2.6.19-rc5/include/linux/container.h
============================================================ =======
--- /dev/null
+++ container-2.6.19-rc5/include/linux/container.h
@@ -0,0 +1,96 @@
+#ifndef _LINUX_CONTAINER_H
+#define _LINUX_CONTAINER_H
+/*
+ * container interface
+ *
+ * Copyright (C) 2003 BULL SA
+ * Copyright (C) 2004-2006 Silicon Graphics, Inc.
+ *
+ */
+
+#include <linux/sched.h>
+#include <linux/cpumask.h>
+#include <linux/nodemask.h>
+
+#ifdef CONFIG_CONTAINERS
+
+extern int number_of_containers; /* How many containers are defined in system? */
+
+extern int container_init_early(void);
+extern int container_init(void);
+extern void container_init_smp(void);
+extern void container_fork(struct task_struct *p);
+extern void container_exit(struct task_struct *p);
+
+extern struct file_operations proc_container_operations;
+
+extern void container_lock(void);
+extern void container_unlock(void);
+
+extern void container_manage_lock(void);
+extern void container_manage_unlock(void);
+
+struct container {
+ unsigned long flags; /* "unsigned long" so bitops work */
+
+ /*
+ * Count is atomic so can incr (fork) or decr (exit) without a lock.
+ */
+ atomic_t count; /* count tasks using this container */
+
+ /*
+ * 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 container *parent; /* my parent */
+ struct dentry *dentry; /* container fs entry */
+};
+
+/* struct cftype:
+ *
+ * The files in the container 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 container to use in file->f_dentry->d_parent->d_fsdata
+ * - the 'cftype' of the file is file->f_dentry->d_fsdata
+ */
+
+struct inode;
+struct cftype {
+ char *name;
+ int private;
+ int (*open) (struct inode *inode, struct file *file);
+ ssize_t (*read) (struct container *cont, struct cftype *cft,
+ struct file *file,
+ char __user *buf, size_t nbytes, loff_t *ppos);
+ ssize_t (*write) (struct container *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);
+};
+
+int container_add_file(struct container *cont, const struct cftype *cft);
+
+int container_is_removed(const struct container *cont);
+
+#else /* !CONFIG_CONTAINERS */
+
+static inline int container_init_early(void) { return 0; }
+static inline int container_init(void) { return 0; }
+static inline void container_init_smp(void) {}
+static inline void container_fork(struct task_struct *p) {}
+static inline void container_exit(struct task_struct *p) {}
+
+static inline void container_lock(void) {}
+static inline void container_unlock(void) {}
+
+#endif /* !CONFIG_CONTAINERS */
+
+#endif /* _LINUX_CONTAINER_H */
Index: container-2.6.19-rc5/include/linux/sched.h
============================================================ =======
--- container-2.6.19-rc5.orig/include/linux/sched.h
+++ container-2.6.19-rc5/include/linux/sched.h
@@ -719,8 +719,8 @@ extern unsigned int max_cache_size;


struct io_context; /* See blkdev.h */
+struct container;
struct cpuset;
-
#define NGROUPS_SMALL 32
#define NGROUPS_PER_BLOCK ((int)(PAGE_SIZE / sizeof(gid_t)))
struct group_info {
@@ -1006,6 +1006,9 @@ struct task_struct {
int cpuset_mems_generation;
int cpuset_mem_spread_rotor;
#endif
+#ifdef CONFIG_CONTAINERS
+ struct container *container;
+#endif
struct robust_list_head __user *robust_list;
#ifdef CONFIG_COMPAT
struct compat_robust_list_head __user *compat_robust_list;
Index: container-2.6.19-rc5/init/Kconfig
============================================================ =======
--- container-2.6.19-rc5.orig/init/Kconfig
+++ container-2.6.19-rc5/init/Kconfig
@@ -238,6 +238,15 @@ config IKCONFIG_PROC
This option enables access to the kernel configuration file
through /proc/config.gz.

+config CONTAINERS
+ bool "Container support"
+ help
+ This option will let you create and manage process containers,
+ which can be used to aggregate multiple processes, e.g. for
+ the purposes of resource tracking.
+
+ Say N if unsure
+
config CPUSETS
bool "Cpuset support"
depends on SMP
Index: container-2.6.19-rc5/init/main.c
============================================================ =======
--- container-2.6.19-rc5.orig/init/main.c
+++ container-2.6.19-rc5/init/main.c
@@ -38,6 +38,7 @@
#include <linux/writeback.h>
#include <linux/cpu.h>
#include <linux/cpuset.h>
+#include <linux/container.h>
#include <linux/efi.h>
#include <linux/taskstats_kern.h>
#include <linux/delayacct.h>
@@ -568,6 +569,7 @@ asmlinkage void __init start_kernel(void
}
#endif
vfs_caches_init_early();
+ container_init_early();
cpuset_init_early();
mem_init();
kmem_cache_init();
@@ -598,6 +600,7 @@ asmlinkage void __init start_kernel(void
#ifdef CONFIG_PROC_FS
proc_root_init();
#endif
+ container_init();
cpuset_init();
taskstats_init_early();
delayacct_init();
Index: container-2.6.19-rc5/kernel/container.c
============================================================ =======
--- /dev/null
+++ container-2.6.19-rc5/kernel/container.c
@@ -0,0 +1,1343 @@
+/*
+ * kernel/container.c
+ *
+ * Generic process-grouping system.
+ *
+ * Based originally on the cpuset system, extracted by Paul Menage
+ * Copyright (C) 2006 Google, Inc
+ *
+ * Copyright notices from the original cpuset code:
+ * --------------------------------------------------
+ * Copyright (C) 2003 BULL SA.
+ * Copyright (C) 2004-2006 Silicon Graphics, Inc.
+ *
+ * Portions derived from Patrick Mochel's sysfs code.
+ * sysfs is Copyright (c) 2001-3 Patrick Mochel
+ *
+ * 2003-10-10 Written by Simon Derr.
+ * 2003-10-22 Updates by Stephen Hemminger.
+ * 2004 May-July Rework by Paul Jackson.
+ * ---------------------------------------------------
+ *
+ * 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
+ * distribution for more details.
+ */
+
+#include <linux/cpu.h>
+#include <linux/cpumask.h>
+#include <linux/container.h>
+#include <linux/err.h>
+#include <linux/errno.h>
+#include <linux/file.h>
+#include <linux/fs.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/kernel.h>
+#include <linux/kmod.h>
+#include <linux/list.h>
+#include <linux/mempolicy.h>
+#include <linux/mm.h>
+#include <linux/module.h>
+#include <linux/mount.h>
+#include <linux/namei.h>
+#include <linux/pagemap.h>
+#include <linux/proc_fs.h>
+#include <linux/rcupdate.h>
+#include <linux/sched.h>
+#include <linux/seq_file.h>
+#include <linux/security.h>
+#include <linux/slab.h>
+#include <linux/smp_lock.h>
+#include <linux/spinlock.h>
+#include <linux/stat.h>
+#include <linux/string.h>
+#include <linux/time.h>
+#include <linux/backing-dev.h>
+#include <linux/sort.h>
+
+#include <asm/uaccess.h>
+#include <asm/atomic.h>
+#include <linux/mutex.h>
+
+#define CONTAINER_SUPER_MAGIC 0x27e0eb
+
+/*
+ * Tracks how many containers are currently defined in system.
+ * When there is only one container (the root container) we can
+ * short circuit some hooks.
+ */
+int number_of_containers __read_mostly;
+
+/* bits in struct container fla
...

Re: [PATCH 0/7] Generic Process Containers (+ ResGroups/BeanCounters) [message #8646 is a reply to message #8540] Thu, 30 November 2006 07:32 Go to previous messageGo to next message
Paul Jackson is currently offline  Paul Jackson
Messages: 157
Registered: February 2006
Senior Member
I got a chance to build and test this patch set, to see if it behaved
like I expected cpusets to behave, on an ia64 SN2 Altix system.

Two details - otherwise looked good. I continue to like this
approach.

The two details are (1) /proc/<pid>/cpuset not configured by
default if CPUSETS configured, and (2) a locking bug wedging
tasks trying to rmdir a cpuset off the notify_on_release hook.


1) I had to enable CONFIG_PROC_PID_CPUSET. I used the following
one line change to do this. I am willing to consider, in due
time, phasing out such legacy cpuset support. But so long as it
is small stuff that is not getting in anyone's way, I think we
should take our sweet time about doing so -- as in a year or two
after marking it deprecated or some such. No sense deciding that
matter now; keep the current cpuset API working throughout any
transitition to container based cpusets, then revisit the question
of whether to deprecate and eventually remove these kernel API
details, later on, after the major reconstruction dust settles.
In general, we try to avoid removing kernel API's, especially if
they are happily being used and working and not causing anyone
grief.

============================ begin ============================
--- 2.6.19-rc5.orig/init/Kconfig 2006-11-29 21:14:48.071114833 -0800
+++ 2.6.19-rc5/init/Kconfig 2006-11-29 22:19:02.015166048 -0800
@@ -268,6 +268,7 @@ config CPUSETS
config PROC_PID_CPUSET
bool "Include legacy /proc/<pid>/cpuset file"
depends on CPUSETS
+ default y if CPUSETS

config CONTAINER_CPUACCT
bool "Simple CPU accounting container subsystem"
============================= end =============================


2) I wedged the kernel on the container_lock, doing a removal of a cpuset
using notify_on_release.

Right now, that test system has the following two tasks, wedged:

============================ begin ============================
F S UID PID PPID C PRI NI ADDR SZ WCHAN STIME TTY TIME CMD
0 S root 4992 34 0 71 -5 - 380 wait 22:51 ? 00:00:00 /bin/sh /sbin/cpuset_release_agent /cpuset_test_tree
0 D root 4994 4992 0 72 -5 - 200 contai 22:51 ? 00:00:00 rmdir /dev/cpuset//cpuset_test_tree
============================= end =============================

I had a cpuset called /cpuset_test_tree, and some sub-cpusets
below it. I marked it 'notify_on_release' and then removed all
tasks from it, and then removed the child cpusets that it had.
Removing that last child cpuset presumably triggered the above
callout to /sbin/cpuset_release_agent, which called rmdir.

That wait address (from /proc/4994/stat) in hex is a0000001000f1060,
and my System.map has the two lines:

a0000001000f1040 T container_lock
a0000001000f1360 T container_manage_unlock

So it is wedged in container_lock.

I have subsequently also wedged an 'ls' command trying to scan this
/dev/cpuset directory, waiting in the kernel routine vfs_readdir
(not surprising, given that I'm in the middle of doing a rmdir on
that directory.)

If you don't immediately see the problem, I can go back and get a
kernel stack trace or whatever else you need.

This lockup occurred the first, and thus far only, time that I tried
to use notify_on_release to rmdir a cpuset. So I presume it is an
easy failure for me to reproduce.

--
I won't rest till it's the best ...
Programmer, Linux Scalability
Paul Jackson <pj@sgi.com> 1.925.600.0401
Re: [PATCH 0/7] Generic Process Containers (+ ResGroups/BeanCounters) [message #8648 is a reply to message #8646] Thu, 30 November 2006 08:01 Go to previous messageGo to next message
Paul Menage is currently offline  Paul Menage
Messages: 642
Registered: September 2006
Senior Member
On 11/29/06, Paul Jackson <pj@sgi.com> wrote:
> config PROC_PID_CPUSET
> bool "Include legacy /proc/<pid>/cpuset file"
> depends on CPUSETS
> + default y if CPUSETS
>

Sounds very reasonable.

> 2) I wedged the kernel on the container_lock, doing a removal of a cpuset
> using notify_on_release.
>

I guess I've not really tested doing interesting things from the
notify_on_release code, just checked that it successfully executed a
simple command. I'll look into it.

Thanks for the feedback.

Paul
Re: [PATCH 0/7] Generic Process Containers (+ ResGroups/BeanCounters) [message #8649 is a reply to message #8646] Thu, 30 November 2006 08:51 Go to previous messageGo to next message
Paul Menage is currently offline  Paul Menage
Messages: 642
Registered: September 2006
Senior Member
On 11/29/06, Paul Jackson <pj@sgi.com> wrote:
>
> 2) I wedged the kernel on the container_lock, doing a removal of a cpuset
> using notify_on_release.

I couldn't reproduce this, with a /sbin/cpuset_release_agent that does:

#!/bin/bash
logger cpuset_release_agent $1
rmdir /dev/cpuset/$1

and running the commands:

while true; do
mkdir -p /dev/cpuset/bar/foo
echo 1 > /dev/cpuset/bar/notify_on_release
rmdir /dev/cpuset/bar/foo
usleep 1000
done

Is it actually reproducible for you? If so, could you get a fuller backtrace?

Thanks,

Paul
[Patch 1/3] Miscellaneous container fixes [message #8682 is a reply to message #8544] Fri, 01 December 2006 16:46 Go to previous messageGo to next message
Srivatsa Vaddagiri is currently offline  Srivatsa Vaddagiri
Messages: 241
Registered: August 2006
Senior Member
This patches fixes various bugs I hit in the recently posted container
patches.

1. If a subsystem registers with fork/exit hook during bootup (much
before rcu is initialized), then the resulting synchronize_rcu() in
container_register_subsys() hangs. Avoid this by not calling
synchronize_rcu() if we arent fully booted yet.

2. If cpuset_create fails() for some reason, then the resulting
call to cpuset_destroy can trip. Avoid this by initializing
container->...->cpuset pointer to NULL in cpuset_create().

3. container_rmdir->cpuset_destroy->update_flag can deadlock on
container_lock(). Avoid this by introducing __update_flag, which
doesnt take container_lock().

(I have also hit some lockdep warnings. Will post them after some
review, to make sure that they are not introduced by my patches).

Signed-off-by : Srivatsa Vaddagiri <vatsa@in.ibm.com>


---

linux-2.6.19-rc6-vatsa/kernel/container.c | 4 ++-
linux-2.6.19-rc6-vatsa/kernel/cpuset.c | 35 ++++++++++++++++++++++++------
2 files changed, 31 insertions(+), 8 deletions(-)

diff -puN kernel/container.c~container_fixes kernel/container.c
--- linux-2.6.19-rc6/kernel/container.c~container_fixes 2006-12-01 16:19:41.000000000 +0530
+++ linux-2.6.19-rc6-vatsa/kernel/container.c 2006-12-01 16:20:20.000000000 +0530
@@ -1344,6 +1344,7 @@ static long container_create(struct cont
cont->parent = parent;
cont->root = parent->root;
cont->hierarchy = parent->hierarchy;
+ cont->top_container = parent->top_container;

for_each_subsys(cont->hierarchy, ss) {
err = ss->create(ss, cont);
@@ -1580,7 +1581,8 @@ int container_register_subsys(struct con
if (!need_forkexit_callback &&
(new_subsys->fork || new_subsys->exit)) {
need_forkexit_callback = 1;
- synchronize_rcu();
+ if (system_state == SYSTEM_RUNNING)
+ synchronize_rcu();
}

/* If this subsystem requested that it be notified with fork
diff -puN kernel/cpuset.c~container_fixes kernel/cpuset.c
--- linux-2.6.19-rc6/kernel/cpuset.c~container_fixes 2006-12-01 19:02:35.000000000 +0530
+++ linux-2.6.19-rc6-vatsa/kernel/cpuset.c 2006-12-01 20:43:52.000000000 +0530
@@ -97,14 +97,22 @@ struct cpuset {
/* Update the cpuset for a container */
static inline void set_container_cs(struct container *cont, struct cpuset *cs)
{
- cont->subsys[cpuset_subsys.subsys_id] = &cs->css;
+ if (cs)
+ cont->subsys[cpuset_subsys.subsys_id] = &cs->css;
+ else
+ cont->subsys[cpuset_subsys.subsys_id] = NULL;
}

/* Retrieve the cpuset for a container */
static inline struct cpuset *container_cs(struct container *cont)
{
- return container_of(container_subsys_state(cont, &cpuset_subsys),
- struct cpuset, css);
+ struct container_subsys_state *css;
+
+ css = container_subsys_state(cont, &cpuset_subsys);
+ if (css)
+ return container_of(css, struct cpuset, css);
+ else
+ return NULL;
}

/* Retrieve the cpuset for a task */
@@ -698,7 +706,7 @@ static int update_memory_pressure_enable
* Call with manage_mutex held.
*/

-static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs, char *buf)
+static int __update_flag(cpuset_flagbits_t bit, struct cpuset *cs, char *buf)
{
int turning_on;
struct cpuset trialcs;
@@ -717,18 +725,27 @@ static int update_flag(cpuset_flagbits_t
return err;
cpu_exclusive_changed =
(is_cpu_exclusive(cs) != is_cpu_exclusive(&trialcs));
- container_lock();
if (turning_on)
set_bit(bit, &cs->flags);
else
clear_bit(bit, &cs->flags);
- container_unlock();

if (cpu_exclusive_changed)
update_cpu_domains(cs);
return 0;
}

+static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs, char *buf)
+{
+ int err;
+
+ container_lock();
+ err = __update_flag(bit, cs, buf);
+ container_unlock();
+
+ return err;
+}
+
/*
* Frequency meter - How fast is some event occurring?
*
@@ -1165,6 +1182,7 @@ int cpuset_create(struct container_subsy
return 0;
}
parent = container_cs(cont->parent);
+ set_container_cs(cont, NULL);
cs = kmalloc(sizeof(*cs), GFP_KERNEL);
if (!cs)
return -ENOMEM;
@@ -1202,9 +1220,12 @@ void cpuset_destroy(struct container_sub
{
struct cpuset *cs = container_cs(cont);

+ if (!cs)
+ return;
+
cpuset_update_task_memory_state();
if (is_cpu_exclusive(cs)) {
- int retval = update_flag(CS_CPU_EXCLUSIVE, cs, "0");
+ int retval = __update_flag(CS_CPU_EXCLUSIVE, cs, "0");
BUG_ON(retval);
}
number_of_cpusets--;
_


--
Regards,
vatsa
[Patch 2/3] cpu controller (v3) - based on RTLIMIT_RT_CPU patch [message #8683 is a reply to message #8682] Fri, 01 December 2006 16:51 Go to previous message
Srivatsa Vaddagiri is currently offline  Srivatsa Vaddagiri
Messages: 241
Registered: August 2006
Senior Member
Nick/Ingo,

Here's another approach for a minimal cpu controller. Would greatly
appreciate any feedback as before.

This version is inspired by Ingo's RTLIMIT_RT_CPU patches found here:

http://kernel.org/pub/linux/kernel/people/akpm/patches/2.6/2 .6.11-rc2/2.6.11-rc2-mm2/broken-out/rlimit_rt_cpu.patch

This patch is also about 80% smaller than the patches I had posted earlier:

http://lkml.org/lkml/2006/9/28/236

Primary differences between Ingo's RT_LIMIT_CPU patch and this one:

- This patch handles starvation of lower priority tasks in a group.
- This patch uses tokens for accounting cpu consumption. I didnt
get good results with decaying avg approach used in the rtlimit patches.
- Task grouping based on cpuset/containers and not on rtlimit.

Other features:

- Retains one-runqueue-per-cpu, as is prevalent today
- scheduling no longer of O(1) complexity, similar to rtlimit patches.
This can be avoided if we use separate runqueues for different groups
(as was done in http://lkml.org/lkml/2006/9/28/236)
- Only limit supported (no guarantee)

Unsupported feature:

- SMP load balance aware of group limits. This can be handled using
smpnice later if required (http://lkml.org/lkml/2006/9/28/244)


Signed-off-by : Srivatsa Vaddagiri <vatsa@in.ibm.com>

---

linux-2.6.19-rc6-vatsa/include/linux/sched.h | 3
linux-2.6.19-rc6-vatsa/kernel/sched.c | 195 ++++++++++++++++++++++++++-
2 files changed, 195 insertions(+), 3 deletions(-)

diff -puN include/linux/sched.h~cpu_ctlr include/linux/sched.h
--- linux-2.6.19-rc6/include/linux/sched.h~cpu_ctlr 2006-12-01 20:45:08.000000000 +0530
+++ linux-2.6.19-rc6-vatsa/include/linux/sched.h 2006-12-01 20:45:08.000000000 +0530
@@ -1095,6 +1095,9 @@ static inline void put_task_struct(struc
/* Not implemented yet, only for 486*/
#define PF_STARTING 0x00000002 /* being created */
#define PF_EXITING 0x00000004 /* getting shut down */
+#ifdef CONFIG_CPUMETER
+#define PF_STARVING 0x00000010 /* Task starving for CPU */
+#endif
#define PF_FORKNOEXEC 0x00000040 /* forked but didn't exec */
#define PF_SUPERPRIV 0x00000100 /* used super-user privileges */
#define PF_DUMPCORE 0x00000200 /* dumped core */
diff -puN kernel/sched.c~cpu_ctlr kernel/sched.c
--- linux-2.6.19-rc6/kernel/sched.c~cpu_ctlr 2006-12-01 20:45:08.000000000 +0530
+++ linux-2.6.19-rc6-vatsa/kernel/sched.c 2006-12-01 20:45:08.000000000 +0530
@@ -264,10 +264,25 @@ struct rq {
unsigned long ttwu_local;
#endif
struct lock_class_key rq_lock_key;
+#ifdef CONFIG_CPUMETER
+ unsigned long last_update;
+ int need_recheck;
+#endif
};

static DEFINE_PER_CPU(struct rq, runqueues);

+struct cpu_usage {
+ long tokens;
+ unsigned long last_update;
+ int starve_count;
+};
+
+struct task_grp {
+ unsigned long limit;
+ struct cpu_usage *cpu_usage; /* per-cpu ptr */
+};
+
static inline int cpu_of(struct rq *rq)
{
#ifdef CONFIG_SMP
@@ -705,6 +720,137 @@ enqueue_task_head(struct task_struct *p,
p->array = array;
}

+#ifdef CONFIG_CPUMETER
+
+#define task_starving(p) (p->flags & PF_STARVING)
+
+static inline struct task_grp *task_grp(struct task_struct *p)
+{
+ return NULL;
+}
+
+/* Mark a task starving - either we shortcircuited its timeslice or we didnt
+ * pick it to run (because its group ran out of bandwidth limit).
+ */
+static inline void set_tsk_starving(struct task_struct *p, struct task_grp *grp)
+{
+ struct cpu_usage *grp_usage;
+
+ if (task_starving(p))
+ return;
+
+ BUG_ON(!grp);
+ grp_usage = per_cpu_ptr(grp->cpu_usage, task_cpu(p));
+ grp_usage->starve_count++;
+ p->flags |= PF_STARVING;
+}
+
+/* Clear a task's starving flag */
+static inline void clear_tsk_starving(struct task_struct *p,
+ struct task_grp *grp)
+{
+ struct cpu_usage *grp_usage;
+
+ if (!task_starving(p))
+ return;
+
+ BUG_ON(!grp);
+ grp_usage = per_cpu_ptr(grp->cpu_usage, task_cpu(p));
+ grp_usage->starve_count--;
+ p->flags &= ~PF_STARVING;
+}
+
+/* Does the task's group have starving tasks? */
+static inline int is_grp_starving(struct task_struct *p)
+{
+ struct task_grp *grp = task_grp(p);
+ struct cpu_usage *grp_usage;
+
+ if (!grp)
+ return 0;
+
+ grp_usage = per_cpu_ptr(grp->cpu_usage, task_cpu(p));
+ if (grp_usage->starve_count)
+ return 1;
+
+ return 0;
+}
+
+/* Are we past the 1-sec control window? If so, all groups get to renew their
+ * expired tokens.
+ */
+static inline void adjust_control_window(struct task_struct *p)
+{
+ struct rq *rq = task_rq(p);
+ unsigned long delta;
+
+ delta = jiffies - rq->last_update;
+ if (delta >= HZ) {
+ rq->last_update += (delta/HZ) * HZ;
+ rq->need_recheck = 1;
+ }
+}
+
+/* Account group's cpu usage */
+static inline void inc_cpu_usage(struct task_struct *p)
+{
+ struct task_grp *grp = task_grp(p);
+ struct cpu_usage *grp_usage;
+
+ adjust_control_window(p);
+
+ if (!grp || !grp->limit || rt_task(p))
+ return;
+
+ grp_usage = per_cpu_ptr(grp->cpu_usage, task_cpu(p));
+ grp_usage->tokens--;
+}
+
+static inline int task_over_cpu_limit(struct task_struct *p)
+{
+ struct rq *rq = task_rq(p);
+ struct task_grp *grp = task_grp(p);
+ struct cpu_usage *grp_usage;
+
+ adjust_control_window(p);
+
+ if (!grp || !grp->limit || !rq->need_recheck)
+ return 0;
+
+ grp_usage = per_cpu_ptr(grp->cpu_usage, task_cpu(p));
+ if (grp_usage->last_update != rq->last_update) {
+ /* Replenish tokens */
+ grp_usage->tokens = grp->limit * HZ / 100;
+ grp_usage->last_update = rq->last_update;
+ }
+
+ if (grp_usage->tokens <= 0)
+ return 1;
+
+ return 0;
+}
+
+static inline void rq_set_recheck(struct rq *rq, int check)
+{
+ rq->need_recheck = check;
+}
+
+#else
+
+#define task_starving(p) 0
+
+struct task_grp;
+
+static struct task_grp *task_grp(struct task_struct *p) { return NULL;}
+static void inc_cpu_usage(struct task_struct *p) { }
+static int task_over_cpu_limit(struct task_struct *p) { return 0; }
+static void set_tsk_starving(struct task_struct *p, struct task_grp *grp) { }
+static void clear_tsk_starving(struct task_struct *p, struct task_grp *grp) { }
+static int is_grp_starving(struct task_struct *p) { return 0;}
+static inline void rq_set_recheck(struct rq *rq, int check) { }
+
+#endif /* CONFIG_CPUMETER */
+
/*
* __normal_prio - return the priority that is based on the static
* priority but is modified by bonuses/penalties.
@@ -847,6 +993,7 @@ static void __activate_task(struct task_
target = rq->expired;
enqueue_task(p, target);
inc_nr_running(p, rq);
+ rq_set_recheck(rq, 1);
}

/*
@@ -1586,6 +1733,9 @@ void fastcall sched_fork(struct task_str
/* Want to start with kernel preemption disabled. */
task_thread_info(p)->preempt_count = 1;
#endif
+#ifdef CONFIG_CPUMETER
+ p->flags &= ~PF_STARVING;
+#endif
/*
* Share the timeslice between parent and child, thus the
* total amount of pending timeslices in the system doesn't change,
@@ -2047,6 +2197,8 @@ static void pull_task(struct rq *src_rq,
{
dequeue_task(p, src_array);
dec_nr_running(p, src_rq);
+ clear_tsk_starving(p, task_grp(p));
+ rq_set_recheck(this_rq, 1);
set_task_cpu(p, this_cpu);
inc_nr_running(p, this_rq);
enqueue_task(p, this_array);
@@ -3068,6 +3220,9 @@ void scheduler_tick(void)
goto out;
}
spin_lock(&rq->lock);
+
+ inc_cpu_usage(p);
+
/*
* The task was running during this tick - update the
* time slice counter. Note: we do not update a thread's
@@ -3094,17 +3249,18 @@ void scheduler_tick(void)
dequeue_task(p, rq->active);
set_tsk_need_resched(p);
p->prio = effective_prio(p);
- p->time_slice = task_timeslice(p);
p->first_time_slice = 0;

if (!rq->expired_timestamp)
rq->expired_timestamp = jiffies;
- if (!TASK_INTERACTIVE(p) || expired_starving(rq)) {
+ if (!TASK_INTERACTIVE(p) || expired_starving(rq)
+ || task_over_cpu_limit(p)) {
enqueue_task(p, rq->expired);
if (p->static_prio < rq->best_expired_prio)
rq->best_expired_prio = p->static_prio;
} else
enqueue_task(p, rq->active);
+ goto out_unlock;
} else {
/*
* Prevent a too long timeslice allowing a task to monopolize
@@ -3131,6 +3287,14 @@ void scheduler_tick(void)
set_tsk_need_resched(p);
}
}
+
+ if (task_over_cpu_limit(p)) {
+ dequeue_task(p, rq->active);
+ set_tsk_need_resched(p);
+ enqueue_task(p, rq->expired);
+ set_tsk_starving(p, task_grp(p));
+ }
+
out_unlock:
spin_unlock(&rq->lock);
out:
@@ -3320,7 +3484,7 @@ asmlinkage void __sched schedule(void)
struct list_head *queue;
unsigned long long now;
unsigned long run_time;
- int cpu, idx, new_prio;
+ int cpu, idx, new_prio, array_switch;
long *switch_count;
struct rq *rq;

@@ -3379,6 +3543,7 @@ need_resched_nonpreemptible:
else {
if (prev->state == TASK_UNINTERRUPTIBLE)
rq->nr_uninterruptible++;
+ clear_tsk_starving(prev, task_grp(prev));
deactivate_task(prev, rq);
}
}
@@ -3394,11 +3559,15 @@ need_resched_nonpreemptible:
}
}

+ array_switch = 0;
+
+pick_next_task:
array = rq->active;
if (unlikely(!array->nr_active)) {
/*
* Switch the active and expired arrays.
*/
+ array_switch++;
schedstat_inc(rq, sched_switch);
rq->active = rq->expired;
rq->expired = array;
@@ -3411,6 +3580,25 @@ need_resched_nonpreemptible:
queue = array->queue + idx;
next = list_entry(queue->next, struct task_struct, run_list);

+ /* If we have done an array switch twice, it means we cant find any
+ * task which isn't above its limit and hence we just run the
+ * first task on the active array.
+ */
+ if (array_switch < 2 && (task_over_cpu_limit(next) ||
+ (!task_starving(next) && is_grp_starving(next)))) {
+ dequeue_task(next, rq->active);
+ enqueue_task(next, rq->expired);
+ if (next->time_slice)
+ set_tsk_starving(next, task_grp(next));
+ goto pick_next_task;
+ }
+
+ if (task_over_c
...

[PATCH 6/7] Split Cpusets into Cpusets and Memsets [message #16760 is a reply to message #8540] Thu, 23 November 2006 12:08 Go to previous message
Paul Menage is currently offline  Paul Menage
Messages: 642
Registered: September 2006
Senior Member
This patch splits the Cpusets container subsystem into two independent
subsystems; currently CPUsets are the cpu and memory node control
functionality in Cpusets are pretty much disjoint and unrelated; now
that the common process container abstraction has been moved out,
there's no particular reason to keep them together in the same
subsystem.

Signed-off-by: Paul Menage <menage@google.com>

---

 fs/proc/array.c           |    2 
 include/linux/cpuset.h    |   75 --
 include/linux/mempolicy.h |    2 
 include/linux/memset.h    |  125 ++++
 include/linux/sched.h     |   10 
 init/Kconfig              |   14 
 init/main.c               |    3 
 kernel/Makefile           |    1 
 kernel/cpuset.c           |  994 +--------------------------------
 kernel/memset.c           | 1352 ++++++++++++++++++++++++++++++++++++++++++++++
 mm/filemap.c              |    6 
 mm/hugetlb.c              |    4 
 mm/memory_hotplug.c       |    4 
 mm/mempolicy.c            |   36 -
 mm/migrate.c              |    4 
 mm/oom_kill.c             |   14 
 mm/page_alloc.c           |   26 
 mm/slab.c                 |   12 
 mm/vmscan.c               |   10 
 19 files changed, 1593 insertions(+), 1101 deletions(-)

Index: container-2.6.19-rc6/include/linux/cpuset.h
===================================================================
--- container-2.6.19-rc6.orig/include/linux/cpuset.h
+++ container-2.6.19-rc6/include/linux/cpuset.h
@@ -10,58 +10,22 @@
 
 #include <linux/sched.h>
 #include <linux/cpumask.h>
-#include <linux/nodemask.h>
 #include <linux/container.h>
 
 #ifdef CONFIG_CPUSETS
 
-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 cpumask_t cpuset_cpus_allowed(struct task_struct *p);
-extern nodemask_t cpuset_mems_allowed(struct task_struct *p);
-void cpuset_init_current_mems_allowed(void);
-void cpuset_update_task_memory_state(void);
-#define cpuset_nodes_subset_current_mems_allowed(nodes) \
-		nodes_subset((nodes), current->mems_allowed)
-int cpuset_zonelist_valid_mems_allowed(struct zonelist *zl);
-
-extern int __cpuset_zone_allowed(struct zone *z, gfp_t gfp_mask);
-static int inline cpuset_zone_allowed(struct zone *z, gfp_t gfp_mask)
-{
-	return number_of_cpusets <= 1 || __cpuset_zone_allowed(z, gfp_mask);
-}
 
 extern int cpuset_excl_nodes_overlap(const struct task_struct *p);
 
-#define cpuset_memory_pressure_bump() 				\
-	do {							\
-		if (cpuset_memory_pressure_enabled)		\
-			__cpuset_memory_pressure_bump();	\
-	} while (0)
-extern int cpuset_memory_pressure_enabled;
-extern void __cpuset_memory_pressure_bump(void);
-
 extern struct file_operations proc_cpuset_operations;
 extern char *cpuset_task_status_allowed(struct task_struct *task, char *buffer);
-extern int cpuset_mem_spread_node(void);
-
-static inline int cpuset_do_page_mem_spread(void)
-{
-	return current->flags & PF_SPREAD_PAGE;
-}
-
-static inline int cpuset_do_slab_mem_spread(void)
-{
-	return current->flags & PF_SPREAD_SLAB;
-}
 
 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; }
@@ -73,60 +37,21 @@ static inline cpumask_t cpuset_cpus_allo
 	return cpu_possible_map;
 }
 
-static inline nodemask_t cpuset_mems_allowed(struct task_struct *p)
-{
-	return node_possible_map;
-}
-
-static inline void cpuset_init_current_mems_allowed(void) {}
-static inline void cpuset_update_task_memory_state(void) {}
-#define cpuset_nodes_subset_current_mems_allowed(nodes) (1)
-
-static inline int cpuset_zonelist_valid_mems_allowed(struct zonelist *zl)
-{
-	return 1;
-}
-
-static inline int cpuset_zone_allowed(struct zone *z, gfp_t gfp_mask)
-{
-	return 1;
-}
 
 static inline int cpuset_excl_nodes_overlap(const struct task_struct *p)
 {
 	return 1;
 }
 
-static inline void cpuset_memory_pressure_bump(void) {}
-
 static inline char *cpuset_task_status_allowed(struct task_struct *task,
 							char *buffer)
 {
 	return buffer;
 }
 
-static inline int cpuset_mem_spread_node(void)
-{
-	return 0;
-}
-
-static inline int cpuset_do_page_mem_spread(void)
-{
-	return 0;
-}
-
-static inline int cpuset_do_slab_mem_spread(void)
-{
-	return 0;
-}
 
 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 */
Index: container-2.6.19-rc6/include/linux/memset.h
===================================================================
--- /dev/null
+++ container-2.6.19-rc6/include/linux/memset.h
@@ -0,0 +1,125 @@
+#ifndef _LINUX_MEMSET_H
+#define _LINUX_MEMSET_H
+/*
+ *  memset interface
+ *
+ *  Copyright (C) 2003 BULL SA
+ *  Copyright (C) 2004-2006 Silicon Graphics, Inc.
+ *
+ */
+
+#include <linux/sched.h>
+#include <linux/nodemask.h>
+#include <linux/container.h>
+
+#ifdef CONFIG_MEMSETS
+
+extern int number_of_memsets;  /* How many memsets are defined in system? */
+
+extern int memset_init_early(void);
+extern int memset_init(void);
+extern void memset_init_smp(void);
+extern nodemask_t memset_mems_allowed(struct task_struct *p);
+void memset_init_current_mems_allowed(void);
+void memset_update_task_memory_state(void);
+#define memset_nodes_subset_current_mems_allowed(nodes) \
+		nodes_subset((nodes), current->mems_allowed)
+int memset_zonelist_valid_mems_allowed(struct zonelist *zl);
+
+extern int __memset_zone_allowed(struct zone *z, gfp_t gfp_mask);
+static int inline memset_zone_allowed(struct zone *z, gfp_t gfp_mask)
+{
+	return number_of_memsets <= 1 || __memset_zone_allowed(z, gfp_mask);
+}
+
+extern int memset_excl_nodes_overlap(const struct task_struct *p);
+
+#define memset_memory_pressure_bump() 				\
+	do {							\
+		if (memset_memory_pressure_enabled)		\
+			__memset_memory_pressure_bump();	\
+	} while (0)
+extern int memset_memory_pressure_enabled;
+extern void __memset_memory_pressure_bump(void);
+
+extern struct file_operations proc_memset_operations;
+extern char *memset_task_status_allowed(struct task_struct *task, char *buffer);
+extern int memset_mem_spread_node(void);
+
+static inline int memset_do_page_mem_spread(void)
+{
+	return current->flags & PF_SPREAD_PAGE;
+}
+
+static inline int memset_do_slab_mem_spread(void)
+{
+	return current->flags & PF_SPREAD_SLAB;
+}
+
+extern void memset_track_online_nodes(void);
+
+extern int current_memset_is_being_rebound(void);
+
+#else /* !CONFIG_MEMSETS */
+
+static inline int memset_init_early(void) { return 0; }
+static inline int memset_init(void) { return 0; }
+static inline void memset_init_smp(void) {}
+
+static inline nodemask_t memset_mems_allowed(struct task_struct *p)
+{
+	return node_possible_map;
+}
+
+static inline void memset_init_current_mems_allowed(void) {}
+static inline void memset_update_task_memory_state(void) {}
+#define memset_nodes_subset_current_mems_allowed(nodes) (1)
+
+static inline int memset_zonelist_valid_mems_allowed(struct zonelist *zl)
+{
+	return 1;
+}
+
+static inline int memset_zone_allowed(struct zone *z, gfp_t gfp_mask)
+{
+	return 1;
+}
+
+static inline int memset_excl_nodes_overlap(const struct task_struct *p)
+{
+	return 1;
+}
+
+static inline void memset_memory_pressure_bump(void) {}
+
+static inline char *memset_task_status_allowed(struct task_struct *task,
+							char *buffer)
+{
+	return buffer;
+}
+
+static inline int memset_mem_spread_node(void)
+{
+	return 0;
+}
+
+static inline int memset_do_page_mem_spread(void)
+{
+	return 0;
+}
+
+static inline int memset_do_slab_mem_spread(void)
+{
+	return 0;
+}
+
+static inline void memset_track_online_nodes(void) {}
+
+static inline int current_memset_is_being_rebound(void)
+{
+	return 0;
+}
+
+#endif /* !CONFIG_MEMSETS */
+
+#endif /* _LINUX_MEMSET_H */
Index: container-2.6.19-rc6/kernel/cpuset.c
===================================================================
--- container-2.6.19-rc6.orig/kernel/cpuset.c
+++ container-2.6.19-rc6/kernel/cpuset.c
@@ -32,7 +32,6 @@
 #include <linux/kernel.h>
 #include <linux/kmod.h>
 #include <linux/list.h>
-#include <linux/mempolicy.h>
 #include <linux/mm.h>
 #include <linux/module.h>
 #include <linux/mount.h>
@@ -56,42 +55,18 @@
 #include <asm/atomic.h>
 #include <linux/mutex.h>
 
-/*
- * Tracks how many cpusets are currently defined in system.
- * When there is only one cpuset (the root cpuset) we can
- * short circuit some hooks.
- */
-int number_of_cpusets __read_mostly;
-
 /* Retrieve the cpuset from a container */
 static struct container_subsys cpuset_subsys;
 struct cpuset;
 
-/* See "Frequency meter" comments, below. */
-
-struct fmeter {
-	int cnt;		/* unprocessed events count */
-	int val;		/* most recent output value */
-	time_t time;		/* clock (secs) when val computed */
-	spinlock_t lock;	/* guards read or write of above */
-};
-
 struct cpuset {
 	struct container_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 */
 
 	struct cpuset *parent;		/* my parent */
 
-	/*
-	 * Copy of global cpuset_mems_generation as of the most
-	 * recent time this cpuset changed its mems_allowed.
-	 */
-	int mems_generation;
-
-	struct fmeter fmeter;		/* memory_pressure filter */
 };
 
 /* Update the cpuset for a container */
@@ -117,10 +92,6 @@ static inline struct cpuset *task_cs(str
 /* bits in struct cpuset flags field */
 typedef enum {
 	CS_CPU_EXCLUSIVE,
-	CS_MEM_EXCLUSIVE,
-	CS_MEMORY_MIGRATE,
-	CS_SPREAD_PAGE,
-	CS_SPREAD_SLAB,
 } cpuset_flagbits_t;
 
 /* convenient tests for these bits */
@@ -129,51 +100,10 @@ static inline int is_cpu_exclusive(const
 	return test_bit(CS_CPU_EXC
...

Previous Topic: [PATCH] skip data conversion in compat_sys_mount when data_page is NULL
Next Topic: Linux 2.6.19 VServer 2.1.x
Goto Forum:
  


Current Time: Sun Jul 27 05:31:52 GMT 2025

Total time taken to generate the page: 0.44742 seconds