diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 788c4964c142373b43dac281d77278ccdb20b8d0..9a23bb0982057ba3798b013bf975d82a6d30a5b7 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -15,6 +15,7 @@
#include <linux/cgroupstats.h>
#include <linux/prio_heap.h>
#include <linux/rwsem.h>
+#include <linux/idr.h>
#ifdef CONFIG_CGROUPS
@@ -22,6 +23,7 @@ struct cgroupfs_root;
struct cgroup_subsys;
struct inode;
struct cgroup;
+struct css_id;
extern int cgroup_init_early(void);
extern int cgroup_init(void);
@@ -63,6 +65,8 @@ struct cgroup_subsys_state {
atomic_t refcnt;
unsigned long flags;
+ /* ID for this css, if possible */
+ struct css_id *id;
};
/* bits in struct cgroup_subsys_state flags field */
@@ -373,6 +377,11 @@ struct cgroup_subsys {
int active;
int disabled;
int early_init;
+ /*
+ * True if this subsys uses ID. ID is not available before cgroup_init()
+ * (not available in early_init time.)
+ */
+ bool use_id;
#define MAX_CGROUP_TYPE_NAMELEN 32
const char *name;
@@ -395,6 +404,9 @@ struct cgroup_subsys {
*/
struct cgroupfs_root *root;
struct list_head sibling;
+ /* used when use_id == true */
+ struct idr idr;
+ spinlock_t id_lock;
};
#define SUBSYS(_x) extern struct cgroup_subsys _x ## _subsys;
@@ -450,6 +462,44 @@ void cgroup_iter_end(struct cgroup *cgrp, struct cgroup_iter *it);
int cgroup_scan_tasks(struct cgroup_scanner *scan);
int cgroup_attach_task(struct cgroup *, struct task_struct *);
+/*
+ * CSS ID is ID for cgroup_subsys_state structs under subsys. This only works
+ * if cgroup_subsys.use_id == true. It can be used for looking up and scanning.
+ * CSS ID is assigned at cgroup allocation (create) automatically
+ * and removed when subsys calls free_css_id() function. This is because
+ * the lifetime of cgroup_subsys_state is subsys's matter.
+ *
+ * Looking up and scanning function should be called under rcu_read_lock().
+ * Taking cgroup_mutex()/hierarchy_mutex() is not necessary for following calls.
+ * But the css returned by this routine can be "not populated yet" or "being
+ * destroyed". The caller should check css and cgroup's status.
+ */
+
+/*
+ * Typically Called at ->destroy(), or somewhere the subsys frees
+ * cgroup_subsys_state.
+ */
+void free_css_id(struct cgroup_subsys *ss, struct cgroup_subsys_state *css);
+
+/* Find a cgroup_subsys_state which has given ID */
+
+struct cgroup_subsys_state *css_lookup(struct cgroup_subsys *ss, int id);
+
+/*
+ * Get a cgroup whose id is greater than or equal to id under tree of root.
+ * Returning a cgroup_subsys_state or NULL.
+ */
+struct cgroup_subsys_state *css_get_next(struct cgroup_subsys *ss, int id,
+ struct cgroup_subsys_state *root, int *foundid);
+
+/* Returns true if root is ancestor of cg */
+bool css_is_ancestor(struct cgroup_subsys_state *cg,
+ struct cgroup_subsys_state *root);
+
+/* Get id and depth of css */
+unsigned short css_id(struct cgroup_subsys_state *css);
+unsigned short css_depth(struct cgroup_subsys_state *css);
+
#else /* !CONFIG_CGROUPS */
static inline int cgroup_init_early(void) { return 0; }
diff --git a/include/linux/idr.h b/include/linux/idr.h
index dd846df8cd32182f6740ea59f6451079deb3060d..e968db71e33a94548160cb38c216289ab1577c30 100644
--- a/include/linux/idr.h
+++ b/include/linux/idr.h
@@ -106,6 +106,7 @@ int idr_get_new(struct idr *idp, void *ptr, int *id);
int idr_get_new_above(struct idr *idp, void *ptr, int starting_id, int *id);
int idr_for_each(struct idr *idp,
int (*fn)(int id, void *p, void *data), void *data);
+void *idr_get_next(struct idr *idp, int *nextid);
void *idr_replace(struct idr *idp, void *ptr, int id);
void idr_remove(struct idr *idp, int id);
void idr_remove_all(struct idr *idp);
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 27792bcb07581830c0d1968bef35207995a86f2d..d3c521137425fbc10225ec6025458166c2df6d35 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -94,7 +94,6 @@ struct cgroupfs_root {
char release_agent_path[PATH_MAX];
};
-
/*
* The "rootnode" hierarchy is the "dummy hierarchy", reserved for the
* subsystems that are otherwise unattached - it never has more than a
@@ -102,6 +101,39 @@ struct cgroupfs_root {
*/
static struct cgroupfs_root rootnode;
+/*
+ * CSS ID -- ID per subsys's Cgroup Subsys State(CSS). used only when
+ * cgroup_subsys->use_id != 0.
+ */
+#define CSS_ID_MAX (65535)
+struct css_id {
+ /*
+ * The css to which this ID points. This pointer is set to valid value
+ * after cgroup is populated. If cgroup is removed, this will be NULL.
+ * This pointer is expected to be RCU-safe because destroy()
+ * is called after synchronize_rcu(). But for safe use, css_is_removed()
+ * css_tryget() should be used for avoiding race.
+ */
+ struct cgroup_subsys_state *css;
+ /*
+ * ID of this css.
+ */
+ unsigned short id;
+ /*
+ * Depth in hierarchy which this ID belongs to.
+ */
+ unsigned short depth;
+ /*
+ * ID is freed by RCU. (and lookup routine is RCU safe.)
+ */
+ struct rcu_head rcu_head;
+ /*
+ * Hierarchy of CSS ID belongs to.
+ */
+ unsigned short stack[0]; /* Array of Length (depth+1) */
+};
+
+
/* The list of hierarchy roots */
static LIST_HEAD(roots);
@@ -185,6 +217,8 @@ struct cg_cgroup_link {
static struct css_set init_css_set;
static struct cg_cgroup_link init_css_set_link;
+static int cgroup_subsys_init_idr(struct cgroup_subsys *ss);
+
/* css_set_lock protects the list of css_set objects, and the
* chain of tasks off each css_set. Nests outside task->alloc_lock
* due to cgroup_iter_start() */
@@ -567,6 +601,9 @@ static struct backing_dev_info cgroup_backing_dev_info = {
.capabilities = BDI_CAP_NO_ACCT_AND_WRITEBACK,
};
+static int alloc_css_id(struct cgroup_subsys *ss,
+ struct cgroup *parent, struct cgroup *child);
+
static struct inode *cgroup_new_inode(mode_t mode, struct super_block *sb)
{
struct inode *inode = new_inode(sb);
@@ -2327,6 +2364,17 @@ static int cgroup_populate_dir(struct cgroup *cgrp)
if (ss->populate && (err = ss->populate(ss, cgrp)) < 0)
return err;
}
+ /* This cgroup is ready now */
+ for_each_subsys(cgrp->root, ss) {
+ struct cgroup_subsys_state *css = cgrp->subsys[ss->subsys_id];
+ /*
+ * Update id->css pointer and make this css visible from
+ * CSS ID functions. This pointer will be dereferened
+ * from RCU-read-side without locks.
+ */
+ if (css->id)
+ rcu_assign_pointer(css->id->css, css);
+ }
return 0;
}
@@ -2338,6 +2386,7 @@ static void init_cgroup_css(struct cgroup_subsys_state *css,
css->cgroup = cgrp;
atomic_set(&css->refcnt, 1);
css->flags = 0;
+ css->id = NULL;
if (cgrp == dummytop)
set_bit(CSS_ROOT, &css->flags);
BUG_ON(cgrp->subsys[ss->subsys_id]);
@@ -2413,6 +2462,10 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
goto err_destroy;
}
init_cgroup_css(css, ss, cgrp);
+ if (ss->use_id)
+ if (alloc_css_id(ss, parent, cgrp))
+ goto err_destroy;
+ /* At error, ->destroy() callback has to free assigned ID. */
}
cgroup_lock_hierarchy(root);
@@ -2708,6 +2761,8 @@ int __init cgroup_init(void)
struct cgroup_subsys *ss = subsys[i];
if (!ss->early_init)
cgroup_init_subsys(ss);
+ if (ss->use_id)
+ cgroup_subsys_init_idr(ss);
}
/* Add init_css_set to the hash table */
@@ -3242,3 +3297,232 @@ static int __init cgroup_disable(char *str)
return 1;
}
__setup("cgroup_disable=", cgroup_disable);
+
+/*
+ * Functons for CSS ID.
+ */
+
+/*
+ *To get ID other than 0, this should be called when !cgroup_is_removed().
+ */
+unsigned short css_id(struct cgroup_subsys_state *css)
+{
+ struct css_id *cssid = rcu_dereference(css->id);
+
+ if (cssid)
+ return cssid->id;
+ return 0;
+}
+
+unsigned short css_depth(struct cgroup_subsys_state *css)
+{
+ struct css_id *cssid = rcu_dereference(css->id);
+
+ if (cssid)
+ return cssid->depth;
+ return 0;
+}
+
+bool css_is_ancestor(struct cgroup_subsys_state *child,
+ struct cgroup_subsys_state *root)
+{
+ struct css_id *child_id = rcu_dereference(child->id);
+ struct css_id *root_id = rcu_dereference(root->id);
+
+ if (!child_id || !root_id || (child_id->depth < root_id->depth))
+ return false;
+ return child_id->stack[root_id->depth] == root_id->id;
+}
+
+static void __free_css_id_cb(struct rcu_head *head)
+{
+ struct css_id *id;
+
+ id = container_of(head, struct css_id, rcu_head);
+ kfree(id);
+}
+
+void free_css_id(struct cgroup_subsys *ss, struct cgroup_subsys_state *css)
+{
+ struct css_id *id = css->id;
+ /* When this is called before css_id initialization, id can be NULL */
+ if (!id)
+ return;
+
+ BUG_ON(!ss->use_id);
+
+ rcu_assign_pointer(id->css, NULL);
+ rcu_assign_pointer(css->id, NULL);
+ spin_lock(&ss->id_lock);
+ idr_remove(&ss->idr, id->id);
+ spin_unlock(&ss->id_lock);
+ call_rcu(&id->rcu_head, __free_css_id_cb);
+}
+
+/*
+ * This is called by init or create(). Then, calls to this function are
+ * always serialized (By cgroup_mutex() at create()).
+ */
+
+static struct css_id *get_new_cssid(struct cgroup_subsys *ss, int depth)
+{
+ struct css_id *newid;
+ int myid, error, size;
+
+ BUG_ON(!ss->use_id);
+
+ size = sizeof(*newid) + sizeof(unsigned short) * (depth + 1);
+ newid = kzalloc(size, GFP_KERNEL);
+ if (!newid)
+ return ERR_PTR(-ENOMEM);
+ /* get id */
+ if (unlikely(!idr_pre_get(&ss->idr, GFP_KERNEL))) {
+ error = -ENOMEM;
+ goto err_out;
+ }
+ spin_lock(&ss->id_lock);
+ /* Don't use 0. allocates an ID of 1-65535 */
+ error = idr_get_new_above(&ss->idr, newid, 1, &myid);
+ spin_unlock(&ss->id_lock);
+
+ /* Returns error when there are no free spaces for new ID.*/
+ if (error) {
+ error = -ENOSPC;
+ goto err_out;
+ }
+ if (myid > CSS_ID_MAX)
+ goto remove_idr;
+
+ newid->id = myid;
+ newid->depth = depth;
+ return newid;
+remove_idr:
+ error = -ENOSPC;
+ spin_lock(&ss->id_lock);
+ idr_remove(&ss->idr, myid);
+ spin_unlock(&ss->id_lock);
+err_out:
+ kfree(newid);
+ return ERR_PTR(error);
+
+}
+
+static int __init cgroup_subsys_init_idr(struct cgroup_subsys *ss)
+{
+ struct css_id *newid;
+ struct cgroup_subsys_state *rootcss;
+
+ spin_lock_init(&ss->id_lock);
+ idr_init(&ss->idr);
+
+ rootcss = init_css_set.subsys[ss->subsys_id];
+ newid = get_new_cssid(ss, 0);
+ if (IS_ERR(newid))
+ return PTR_ERR(newid);
+
+ newid->stack[0] = newid->id;
+ newid->css = rootcss;
+ rootcss->id = newid;
+ return 0;
+}
+
+static int alloc_css_id(struct cgroup_subsys *ss, struct cgroup *parent,
+ struct cgroup *child)
+{
+ int subsys_id, i, depth = 0;
+ struct cgroup_subsys_state *parent_css, *child_css;
+ struct css_id *child_id, *parent_id = NULL;
+
+ subsys_id = ss->subsys_id;
+ parent_css = parent->subsys[subsys_id];
+ child_css = child->subsys[subsys_id];
+ depth = css_depth(parent_css) + 1;
+ parent_id = parent_css->id;
+
+ child_id = get_new_cssid(ss, depth);
+ if (IS_ERR(child_id))
+ return PTR_ERR(child_id);
+
+ for (i = 0; i < depth; i++)
+ child_id->stack[i] = parent_id->stack[i];
+ child_id->stack[depth] = child_id->id;
+ /*
+ * child_id->css pointer will be set after this cgroup is available
+ * see cgroup_populate_dir()
+ */
+ rcu_assign_pointer(child_css->id, child_id);
+
+ return 0;
+}
+
+/**
+ * css_lookup - lookup css by id
+ * @ss: cgroup subsys to be looked into.
+ * @id: the id
+ *
+ * Returns pointer to cgroup_subsys_state if there is valid one with id.
+ * NULL if not. Should be called under rcu_read_lock()
+ */
+struct cgroup_subsys_state *css_lookup(struct cgroup_subsys *ss, int id)
+{
+ struct css_id *cssid = NULL;
+
+ BUG_ON(!ss->use_id);
+ cssid = idr_find(&ss->idr, id);
+
+ if (unlikely(!cssid))
+ return NULL;
+
+ return rcu_dereference(cssid->css);
+}
+
+/**
+ * css_get_next - lookup next cgroup under specified hierarchy.
+ * @ss: pointer to subsystem
+ * @id: current position of iteration.
+ * @root: pointer to css. search tree under this.
+ * @foundid: position of found object.
+ *
+ * Search next css under the specified hierarchy of rootid. Calling under
+ * rcu_read_lock() is necessary. Returns NULL if it reaches the end.
+ */
+struct cgroup_subsys_state *
+css_get_next(struct cgroup_subsys *ss, int id,
+ struct cgroup_subsys_state *root, int *foundid)
+{
+ struct cgroup_subsys_state *ret = NULL;
+ struct css_id *tmp;
+ int tmpid;
+ int rootid = css_id(root);
+ int depth = css_depth(root);
+
+ if (!rootid)
+ return NULL;
+
+ BUG_ON(!ss->use_id);
+ /* fill start point for scan */
+ tmpid = id;
+ while (1) {
+ /*
+ * scan next entry from bitmap(tree), tmpid is updated after
+ * idr_get_next().
+ */
+ spin_lock(&ss->id_lock);
+ tmp = idr_get_next(&ss->idr, &tmpid);
+ spin_unlock(&ss->id_lock);
+
+ if (!tmp)
+ break;
+ if (tmp->depth >= depth && tmp->stack[depth] == rootid) {
+ ret = rcu_dereference(tmp->css);
+ if (ret) {
+ *foundid = tmpid;
+ break;
+ }
+ }
+ /* continue to scan from next id */
+ tmpid = tmpid + 1;
+ }
+ return ret;
+}
+
diff --git a/lib/idr.c b/lib/idr.c
index dab4bca86f5d1981027c0be5104a69ce7d05fbe9..80ca9aca038be447573b8130cbc22c1133f34867 100644
--- a/lib/idr.c
+++ b/lib/idr.c
@@ -578,6 +578,52 @@ int idr_for_each(struct idr *idp,
}
EXPORT_SYMBOL(idr_for_each);
+/**
+ * idr_get_next - lookup next object of id to given id.
+ * @idp: idr handle
+ * @id: pointer to lookup key
+ *
+ * Returns pointer to registered object with id, which is next number to
+ * given id.
+ */
+
+void *idr_get_next(struct idr *idp, int *nextidp)
+{
+ struct idr_layer *p, *pa[MAX_LEVEL];
+ struct idr_layer **paa = &pa[0];
+ int id = *nextidp;
+ int n, max;
+
+ /* find first ent */
+ n = idp->layers * IDR_BITS;
+ max = 1 << n;
+ p = rcu_dereference(idp->top);
+ if (!p)
+ return NULL;
+
+ while (id < max) {
+ while (n > 0 && p) {
+ n -= IDR_BITS;
+ *paa++ = p;
+ p = rcu_dereference(p->ary[(id >> n) & IDR_MASK]);
+ }
+
+ if (p) {
+ *nextidp = id;
+ return p;
+ }
+
+ id += 1 << n;
+ while (n < fls(id)) {
+ n += IDR_BITS;
+ p = *--paa;
+ }
+ }
+ return NULL;
+}
+
+
+
/**
* idr_replace - replace pointer for given id
* @idp: idr handle