Home » Mailing lists » Devel » [PATCH 0/6] containers: Generic Process Containers (V6)
| [PATCH 3/6] containers: Add generic multi-subsystem API to containers [message #9246 is a reply to message #9240] |
Fri, 22 December 2006 14:14   |
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 | 273 ++++++++++---
Documentation/cpusets.txt | 20
include/linux/container.h | 137 ++++++
include/linux/cpuset.h | 16
include/linux/mempolicy.h | 12
include/linux/sched.h | 4
init/Kconfig | 12
kernel/container.c | 903 +++++++++++++++++++++++++++++++++----------
kernel/cpuset.c | 173 +++++---
mm/mempolicy.c | 2
10 files changed, 1215 insertions(+), 337 deletions(-)
Index: container-2.6.20-rc1/include/linux/container.h
============================================================ =======
--- container-2.6.20-rc1.orig/include/linux/container.h
+++ container-2.6.20-rc1/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 */
+
+ /* Private pointers for each registered subsystem */
+ struct container_subsys_state *subsys[CONFIG_MAX_CONTAINER_SUBSYS];
+
+ int hierarchy;
-#ifdef CONFIG_CPUSETS
- struct cpuset *cpuset;
-#endif
+ struct containerfs_root *root;
+ struct container *top_container;
};
/* struct cftype:
@@ -67,8 +131,11 @@ struct container {
*/
struct inode;
+#define MAX_CFTYPE_NAME 64
struct cftype {
- char *name;
+ /* By convention, the name should begin with the name of the
+ * subsystem, followed by a period */
+ char name[MAX_CFTYPE_NAME];
int private;
int (*open) (struct inode *inode, struct file *file);
ssize_t (*read) (struct container *cont, struct cftype *cft,
@@ -83,7 +150,61 @@ 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);
+
+/* 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);
+void container_set_release_agent_path(struct container_subsys *ss,
+ const char *path);
+
+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);
Index: container-2.6.20-rc1/include/linux/cpuset.h
============================================================ =======
--- container-2.6.20-rc1.orig/include/linux/cpuset.h
+++ container-2.6.20-rc1/include/linux/cpuset.h
@@ -70,16 +70,7 @@ 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 */
@@ -147,6 +138,11 @@ 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-2.6.20-rc1/kernel/container.c
============================================================ =======
--- container-2.6.20-rc1.orig/kernel/container.c
+++ container-2.6.20-rc1/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 +62,58 @@
#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;
+
+/* A containerfs_root represents the root of a container hierarchy,
+ * and may be associated with a superblock to form an active
+ * hierarchy */
+struct containerfs_root {
+ struct super_block *sb;
+
+ /* The bitmask of subsystems attached to this hierarchy */
+ unsigned long subsys_bits;
+
+ /* A list running through the attached subsystems */
+ struct list_head subsys_list;
+
+ /* The root container for this hierarchy */
+ struct container top_container;
+
+ /* Tracks how many containers are currently defined in hierarchy.*/
+ int number_of_containers;
+
+ /* 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. We ensure that it's always a valid
+ * NUL-terminated string */
+ char release_agent_path[PATH_MAX];
+};
+
+/* 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
...
|
|
|
|
Current Time: Fri Nov 01 07:00:36 GMT 2024
Total time taken to generate the page: 0.03465 seconds
|
OpenVZ Forum
Members
Search
Help
Register
Login
Home
