cgroup: CSS ID support

Patch for Per-CSS(Cgroup Subsys State) ID and private hierarchy code.

This patch attaches unique ID to each css and provides following.

 - css_lookup(subsys, id)
   returns pointer to struct cgroup_subysys_state of id.
 - css_get_next(subsys, id, rootid, depth, foundid)
   returns the next css under "root" by scanning

When cgroup_subsys->use_id is set, an id for css is maintained.

The cgroup framework only parepares
	- css_id of root css for subsys
	- id is automatically attached at creation of css.
	- id is *not* freed automatically. Because the cgroup framework
	  don't know lifetime of cgroup_subsys_state.
	  free_css_id() function is provided. This must be called by subsys.

There are several reasons to develop this.
	- Saving space .... For example, memcg's swap_cgroup is array of
	  pointers to cgroup. But it is not necessary to be very fast.
	  By replacing pointers(8bytes per ent) to ID (2byes per ent), we can
	  reduce much amount of memory usage.

	- Scanning without lock.
	  CSS_ID provides "scan id under this ROOT" function. By this, scanning
	  css under root can be written without locks.
	  ex)
	  do {
		rcu_read_lock();
		next = cgroup_get_next(subsys, id, root, &found);
		/* check sanity of next here */
		css_tryget();
		rcu_read_unlock();
		id = found + 1
	 } while(...)

Characteristics:
	- Each css has unique ID under subsys.
	- Lifetime of ID is controlled by subsys.
	- css ID contains "ID" and "Depth in hierarchy" and stack of hierarchy
	- Allowed ID is 1-65535, ID 0 is UNUSED ID.

Design Choices:
	- scan-by-ID v.s. scan-by-tree-walk.
	  As /proc's pid scan does, scan-by-ID is robust when scanning is done
	  by following kind of routine.
	  scan -> rest a while(release a lock) -> conitunue from interrupted
	  memcg's hierarchical reclaim does this.

	- When subsys->use_id is set, # of css in the system is limited to
	  65535.

[bharata@linux.vnet.ibm.com: remove rcu_read_lock() from css_get_next()]
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Acked-by: Paul Menage <menage@google.com>
Cc: Li Zefan <lizf@cn.fujitsu.com>
Cc: Balbir Singh <balbir@in.ibm.com>
Cc: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
Signed-off-by: Bharata B Rao <bharata@linux.vnet.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 50 insertions, 0 deletions

diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 788c4964c14..9a23bb09820 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; }