Merge branch 'for-3.13' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup

Pull cgroup changes from Tejun Heo:
 "Not too much activity this time around.  css_id is finally killed and
  a minor update to device_cgroup"

* 'for-3.13' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup:
  device_cgroup: remove can_attach
  cgroup: kill css_id
  memcg: stop using css id
  memcg: fail to create cgroup if the cgroup id is too big
  memcg: convert to use cgroup id
  memcg: convert to use cgroup_is_descendant()

include/linux/cgroup.h

@@ -612,11 +612,6 @@ struct cgroup_subsys {
 	int subsys_id;
 	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;
 
 	/*
 	 * If %false, this subsystem is properly hierarchical -
@@ -642,9 +637,6 @@ struct cgroup_subsys {
 	 */
 	struct cgroupfs_root *root;
 	struct list_head sibling;
-	/* used when use_id == true */
-	struct idr idr;
-	spinlock_t id_lock;
 
 	/* list of cftype_sets */
 	struct list_head cftsets;
@@ -875,35 +867,6 @@ int css_scan_tasks(struct cgroup_subsys_state *css,
 int cgroup_attach_task_all(struct task_struct *from, struct task_struct *);
 int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from);
 
-/*
- * 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 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);
-
-/* Returns true if root is ancestor of cg */
-bool css_is_ancestor(struct cgroup_subsys_state *cg,
-		     const struct cgroup_subsys_state *root);
-
-/* Get id and depth of css */
-unsigned short css_id(struct cgroup_subsys_state *css);
 struct cgroup_subsys_state *css_from_dir(struct dentry *dentry,
 					 struct cgroup_subsys *ss);
 

kernel/cgroup.c

@@ -124,38 +124,6 @@ struct cfent {
 	struct simple_xattrs		xattrs;
 };
 
-/*
- * 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_tryget()
-	 * should be used for avoiding race.
-	 */
-	struct cgroup_subsys_state __rcu *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) */
-};
-
 /*
  * cgroup_event represents events which userspace want to receive.
  */
@@ -387,9 +355,6 @@ struct cgrp_cset_link {
 static struct css_set init_css_set;
 static struct cgrp_cset_link init_cgrp_cset_link;
 
-static int cgroup_init_idr(struct cgroup_subsys *ss,
-			   struct cgroup_subsys_state *css);
-
 /*
  * 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
@@ -841,8 +806,6 @@ static struct backing_dev_info cgroup_backing_dev_info = {
 	.capabilities	= BDI_CAP_NO_ACCT_AND_WRITEBACK,
 };
 
-static int alloc_css_id(struct cgroup_subsys_state *child_css);
-
 static struct inode *cgroup_new_inode(umode_t mode, struct super_block *sb)
 {
 	struct inode *inode = new_inode(sb);
@@ -4240,21 +4203,6 @@ static int cgroup_populate_dir(struct cgroup *cgrp, unsigned long subsys_mask)
 				goto err;
 		}
 	}
-
-	/* This cgroup is ready now */
-	for_each_root_subsys(cgrp->root, ss) {
-		struct cgroup_subsys_state *css = cgroup_css(cgrp, ss);
-		struct css_id *id = rcu_dereference_protected(css->id, true);
-
-		/*
-		 * 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 (id)
-			rcu_assign_pointer(id->css, css);
-	}
-
 	return 0;
 err:
 	cgroup_clear_dir(cgrp, subsys_mask);
@@ -4323,7 +4271,6 @@ static void init_css(struct cgroup_subsys_state *css, struct cgroup_subsys *ss,
 	css->cgroup = cgrp;
 	css->ss = ss;
 	css->flags = 0;
-	css->id = NULL;
 
 	if (cgrp->parent)
 		css->parent = cgroup_css(cgrp->parent, ss);
@@ -4455,12 +4402,6 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
 			goto err_free_all;
 
 		init_css(css, ss, cgrp);
-
-		if (ss->use_id) {
-			err = alloc_css_id(css);
-			if (err)
-				goto err_free_all;
-		}
 	}
 
 	/*
@@ -4925,12 +4866,6 @@ int __init_or_module cgroup_load_subsys(struct cgroup_subsys *ss)
 
 	/* our new subsystem will be attached to the dummy hierarchy. */
 	init_css(css, ss, cgroup_dummy_top);
-	/* init_idr must be after init_css() because it sets css->id. */
-	if (ss->use_id) {
-		ret = cgroup_init_idr(ss, css);
-		if (ret)
-			goto err_unload;
-	}
 
 	/*
 	 * Now we need to entangle the css into the existing css_sets. unlike
@@ -4996,9 +4931,6 @@ void cgroup_unload_subsys(struct cgroup_subsys *ss)
 
 	offline_css(cgroup_css(cgroup_dummy_top, ss));
 
-	if (ss->use_id)
-		idr_destroy(&ss->idr);
-
 	/* deassign the subsys_id */
 	cgroup_subsys[ss->subsys_id] = NULL;
 
@@ -5025,8 +4957,7 @@ void cgroup_unload_subsys(struct cgroup_subsys *ss)
 	/*
 	 * remove subsystem's css from the cgroup_dummy_top and free it -
 	 * need to free before marking as null because ss->css_free needs
-	 * the cgrp->subsys pointer to find their state. note that this
+	 * the cgrp->subsys pointer to find their state.
-	 * also takes care of freeing the css_id.
 	 */
 	ss->css_free(cgroup_css(cgroup_dummy_top, ss));
 	RCU_INIT_POINTER(cgroup_dummy_top->subsys[ss->subsys_id], NULL);
@@ -5097,8 +5028,6 @@ int __init cgroup_init(void)
 	for_each_builtin_subsys(ss, i) {
 		if (!ss->early_init)
 			cgroup_init_subsys(ss);
-		if (ss->use_id)
-			cgroup_init_idr(ss, init_css_set.subsys[ss->subsys_id]);
 	}
 
 	/* allocate id for the dummy hierarchy */
@@ -5518,181 +5447,6 @@ static int __init cgroup_disable(char *str)
 }
 __setup("cgroup_disable=", cgroup_disable);
 
-/*
- * Functons for CSS ID.
- */
-
-/* to get ID other than 0, this should be called when !cgroup_is_dead() */
-unsigned short css_id(struct cgroup_subsys_state *css)
-{
-	struct css_id *cssid;
-
-	/*
-	 * This css_id() can return correct value when somone has refcnt
-	 * on this or this is under rcu_read_lock(). Once css->id is allocated,
-	 * it's unchanged until freed.
-	 */
-	cssid = rcu_dereference_raw(css->id);
-
-	if (cssid)
-		return cssid->id;
-	return 0;
-}
-EXPORT_SYMBOL_GPL(css_id);
-
-/**
- *  css_is_ancestor - test "root" css is an ancestor of "child"
- * @child: the css to be tested.
- * @root: the css supporsed to be an ancestor of the child.
- *
- * Returns true if "root" is an ancestor of "child" in its hierarchy. Because
- * this function reads css->id, the caller must hold rcu_read_lock().
- * But, considering usual usage, the csses should be valid objects after test.
- * Assuming that the caller will do some action to the child if this returns
- * returns true, the caller must take "child";s reference count.
- * If "child" is valid object and this returns true, "root" is valid, too.
- */
-
-bool css_is_ancestor(struct cgroup_subsys_state *child,
-		    const struct cgroup_subsys_state *root)
-{
-	struct css_id *child_id;
-	struct css_id *root_id;
-
-	child_id  = rcu_dereference(child->id);
-	if (!child_id)
-		return false;
-	root_id = rcu_dereference(root->id);
-	if (!root_id)
-		return false;
-	if (child_id->depth < root_id->depth)
-		return false;
-	if (child_id->stack[root_id->depth] != root_id->id)
-		return false;
-	return true;
-}
-
-void free_css_id(struct cgroup_subsys *ss, struct cgroup_subsys_state *css)
-{
-	struct css_id *id = rcu_dereference_protected(css->id, true);
-
-	/* 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);
-	kfree_rcu(id, rcu_head);
-}
-EXPORT_SYMBOL_GPL(free_css_id);
-
-/*
- * 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 ret, 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);
-
-	idr_preload(GFP_KERNEL);
-	spin_lock(&ss->id_lock);
-	/* Don't use 0. allocates an ID of 1-65535 */
-	ret = idr_alloc(&ss->idr, newid, 1, CSS_ID_MAX + 1, GFP_NOWAIT);
-	spin_unlock(&ss->id_lock);
-	idr_preload_end();
-
-	/* Returns error when there are no free spaces for new ID.*/
-	if (ret < 0)
-		goto err_out;
-
-	newid->id = ret;
-	newid->depth = depth;
-	return newid;
-err_out:
-	kfree(newid);
-	return ERR_PTR(ret);
-
-}
-
-static int __init_or_module cgroup_init_idr(struct cgroup_subsys *ss,
-					    struct cgroup_subsys_state *rootcss)
-{
-	struct css_id *newid;
-
-	spin_lock_init(&ss->id_lock);
-	idr_init(&ss->idr);
-
-	newid = get_new_cssid(ss, 0);
-	if (IS_ERR(newid))
-		return PTR_ERR(newid);
-
-	newid->stack[0] = newid->id;
-	RCU_INIT_POINTER(newid->css, rootcss);
-	RCU_INIT_POINTER(rootcss->id, newid);
-	return 0;
-}
-
-static int alloc_css_id(struct cgroup_subsys_state *child_css)
-{
-	struct cgroup_subsys_state *parent_css = css_parent(child_css);
-	struct css_id *child_id, *parent_id;
-	int i, depth;
-
-	parent_id = rcu_dereference_protected(parent_css->id, true);
-	depth = parent_id->depth + 1;
-
-	child_id = get_new_cssid(child_css->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);
-}
-EXPORT_SYMBOL_GPL(css_lookup);
-
 /**
  * css_from_dir - get corresponding css from the dentry of a cgroup dir
  * @dentry: directory dentry of interest

mm/memcontrol.c

@@ -499,6 +499,29 @@ static inline bool mem_cgroup_is_root(struct mem_cgroup *memcg)
 	return (memcg == root_mem_cgroup);
 }
 
+/*
+ * We restrict the id in the range of [1, 65535], so it can fit into
+ * an unsigned short.
+ */
+#define MEM_CGROUP_ID_MAX	USHRT_MAX
+
+static inline unsigned short mem_cgroup_id(struct mem_cgroup *memcg)
+{
+	/*
+	 * The ID of the root cgroup is 0, but memcg treat 0 as an
+	 * invalid ID, so we return (cgroup_id + 1).
+	 */
+	return memcg->css.cgroup->id + 1;
+}
+
+static inline struct mem_cgroup *mem_cgroup_from_id(unsigned short id)
+{
+	struct cgroup_subsys_state *css;
+
+	css = css_from_id(id - 1, &mem_cgroup_subsys);
+	return mem_cgroup_from_css(css);
+}
+
 /* Writing them here to avoid exposing memcg's inner layout */
 #if defined(CONFIG_INET) && defined(CONFIG_MEMCG_KMEM)
 
@@ -570,16 +593,11 @@ static void disarm_sock_keys(struct mem_cgroup *memcg)
 #ifdef CONFIG_MEMCG_KMEM
 /*
  * This will be the memcg's index in each cache's ->memcg_params->memcg_caches.
- * There are two main reasons for not using the css_id for this:
+ * The main reason for not using cgroup id for this:
- *  1) this works better in sparse environments, where we have a lot of memcgs,
+ *  this works better in sparse environments, where we have a lot of memcgs,
- *     but only a few kmem-limited. Or also, if we have, for instance, 200
+ *  but only a few kmem-limited. Or also, if we have, for instance, 200
- *     memcgs, and none but the 200th is kmem-limited, we'd have to have a
+ *  memcgs, and none but the 200th is kmem-limited, we'd have to have a
- *     200 entry array for that.
+ *  200 entry array for that.
- *
- *  2) In order not to violate the cgroup API, we would like to do all memory
- *     allocation in ->create(). At that point, we haven't yet allocated the
- *     css_id. Having a separate index prevents us from messing with the cgroup
- *     core for this
  *
  * The current size of the caches array is stored in
  * memcg_limited_groups_array_size.  It will double each time we have to
@@ -594,14 +612,14 @@ int memcg_limited_groups_array_size;
  * cgroups is a reasonable guess. In the future, it could be a parameter or
  * tunable, but that is strictly not necessary.
  *
- * MAX_SIZE should be as large as the number of css_ids. Ideally, we could get
+ * MAX_SIZE should be as large as the number of cgrp_ids. Ideally, we could get
  * this constant directly from cgroup, but it is understandable that this is
  * better kept as an internal representation in cgroup.c. In any case, the
- * css_id space is not getting any smaller, and we don't have to necessarily
+ * cgrp_id space is not getting any smaller, and we don't have to necessarily
  * increase ours as well if it increases.
  */
 #define MEMCG_CACHES_MIN_SIZE 4
-#define MEMCG_CACHES_MAX_SIZE 65535
+#define MEMCG_CACHES_MAX_SIZE MEM_CGROUP_ID_MAX
 
 /*
  * A lot of the calls to the cache allocation functions are expected to be
@@ -1408,7 +1426,7 @@ bool __mem_cgroup_same_or_subtree(const struct mem_cgroup *root_memcg,
 		return true;
 	if (!root_memcg->use_hierarchy || !memcg)
 		return false;
-	return css_is_ancestor(&memcg->css, &root_memcg->css);
+	return cgroup_is_descendant(memcg->css.cgroup, root_memcg->css.cgroup);
 }
 
 static bool mem_cgroup_same_or_subtree(const struct mem_cgroup *root_memcg,
@@ -2826,15 +2844,10 @@ static void __mem_cgroup_cancel_local_charge(struct mem_cgroup *memcg,
  */
 static struct mem_cgroup *mem_cgroup_lookup(unsigned short id)
 {
-	struct cgroup_subsys_state *css;
-
 	/* ID 0 is unused ID */
 	if (!id)
 		return NULL;
-	css = css_lookup(&mem_cgroup_subsys, id);
+	return mem_cgroup_from_id(id);
-	if (!css)
-		return NULL;
-	return mem_cgroup_from_css(css);
 }
 
 struct mem_cgroup *try_get_mem_cgroup_from_page(struct page *page)
@@ -4350,7 +4363,7 @@ mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent, bool swapout)
 	 * css_get() was called in uncharge().
 	 */
 	if (do_swap_account && swapout && memcg)
-		swap_cgroup_record(ent, css_id(&memcg->css));
+		swap_cgroup_record(ent, mem_cgroup_id(memcg));
 }
 #endif
 
@@ -4402,8 +4415,8 @@ static int mem_cgroup_move_swap_account(swp_entry_t entry,
 {
 	unsigned short old_id, new_id;
 
-	old_id = css_id(&from->css);
+	old_id = mem_cgroup_id(from);
-	new_id = css_id(&to->css);
+	new_id = mem_cgroup_id(to);
 
 	if (swap_cgroup_cmpxchg(entry, old_id, new_id) == old_id) {
 		mem_cgroup_swap_statistics(from, false);
@@ -6166,7 +6179,6 @@ static void __mem_cgroup_free(struct mem_cgroup *memcg)
 	size_t size = memcg_size();
 
 	mem_cgroup_remove_from_trees(memcg);
-	free_css_id(&mem_cgroup_subsys, &memcg->css);
 
 	for_each_node(node)
 		free_mem_cgroup_per_zone_info(memcg, node);
@@ -6269,6 +6281,9 @@ mem_cgroup_css_online(struct cgroup_subsys_state *css)
 	struct mem_cgroup *parent = mem_cgroup_from_css(css_parent(css));
 	int error = 0;
 
+	if (css->cgroup->id > MEM_CGROUP_ID_MAX)
+		return -ENOSPC;
+
 	if (!parent)
 		return 0;
 
@@ -6540,7 +6555,7 @@ static enum mc_target_type get_mctgt_type(struct vm_area_struct *vma,
 	}
 	/* There is a swap entry and a page doesn't exist or isn't charged */
 	if (ent.val && !ret &&
-			css_id(&mc.from->css) == lookup_swap_cgroup_id(ent)) {
+	    mem_cgroup_id(mc.from) == lookup_swap_cgroup_id(ent)) {
 		ret = MC_TARGET_SWAP;
 		if (target)
 			target->ent = ent;
@@ -6960,7 +6975,6 @@ struct cgroup_subsys mem_cgroup_subsys = {
 	.bind = mem_cgroup_bind,
 	.base_cftypes = mem_cgroup_files,
 	.early_init = 0,
-	.use_id = 1,
 };
 
 #ifdef CONFIG_MEMCG_SWAP

security/device_cgroup.c

@@ -63,16 +63,6 @@ static inline struct dev_cgroup *task_devcgroup(struct task_struct *task)
 
 struct cgroup_subsys devices_subsys;
 
-static int devcgroup_can_attach(struct cgroup_subsys_state *new_css,
-				struct cgroup_taskset *set)
-{
-	struct task_struct *task = cgroup_taskset_first(set);
-
-	if (current != task && !capable(CAP_SYS_ADMIN))
-		return -EPERM;
-	return 0;
-}
-
 /*
  * called under devcgroup_mutex
  */
@@ -697,7 +687,6 @@ static struct cftype dev_cgroup_files[] = {
 
 struct cgroup_subsys devices_subsys = {
 	.name = "devices",
-	.can_attach = devcgroup_can_attach,
 	.css_alloc = devcgroup_css_alloc,
 	.css_free = devcgroup_css_free,
 	.css_online = devcgroup_online,