Merge branch 'for-4.5-ancestor-test' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup

Preparatory changes for some new socket cgroup infrastructure
and netfilter targets.
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

fs/kernfs/dir.c

@@ -694,6 +694,29 @@ static struct kernfs_node *kernfs_find_ns(struct kernfs_node *parent,
 	return NULL;
 }
 
+static struct kernfs_node *kernfs_walk_ns(struct kernfs_node *parent,
+					  const unsigned char *path,
+					  const void *ns)
+{
+	static char path_buf[PATH_MAX];	/* protected by kernfs_mutex */
+	size_t len = strlcpy(path_buf, path, PATH_MAX);
+	char *p = path_buf;
+	char *name;
+
+	lockdep_assert_held(&kernfs_mutex);
+
+	if (len >= PATH_MAX)
+		return NULL;
+
+	while ((name = strsep(&p, "/")) && parent) {
+		if (*name == '\0')
+			continue;
+		parent = kernfs_find_ns(parent, name, ns);
+	}
+
+	return parent;
+}
+
 /**
  * kernfs_find_and_get_ns - find and get kernfs_node with the given name
  * @parent: kernfs_node to search under
@@ -718,6 +741,29 @@ struct kernfs_node *kernfs_find_and_get_ns(struct kernfs_node *parent,
 }
 EXPORT_SYMBOL_GPL(kernfs_find_and_get_ns);
 
+/**
+ * kernfs_walk_and_get_ns - find and get kernfs_node with the given path
+ * @parent: kernfs_node to search under
+ * @path: path to look for
+ * @ns: the namespace tag to use
+ *
+ * Look for kernfs_node with path @path under @parent and get a reference
+ * if found.  This function may sleep and returns pointer to the found
+ * kernfs_node on success, %NULL on failure.
+ */
+struct kernfs_node *kernfs_walk_and_get_ns(struct kernfs_node *parent,
+					   const char *path, const void *ns)
+{
+	struct kernfs_node *kn;
+
+	mutex_lock(&kernfs_mutex);
+	kn = kernfs_walk_ns(parent, path, ns);
+	kernfs_get(kn);
+	mutex_unlock(&kernfs_mutex);
+
+	return kn;
+}
+
 /**
  * kernfs_create_root - create a new kernfs hierarchy
  * @scops: optional syscall operations for the hierarchy

include/linux/cgroup-defs.h

@@ -234,6 +234,14 @@ struct cgroup {
 	 */
 	int id;
 
+	/*
+	 * The depth this cgroup is at.  The root is at depth zero and each
+	 * step down the hierarchy increments the level.  This along with
+	 * ancestor_ids[] can determine whether a given cgroup is a
+	 * descendant of another without traversing the hierarchy.
+	 */
+	int level;
+
 	/*
 	 * Each non-empty css_set associated with this cgroup contributes
 	 * one to populated_cnt.  All children with non-zero popuplated_cnt
@@ -289,6 +297,9 @@ struct cgroup {
 
 	/* used to schedule release agent */
 	struct work_struct release_agent_work;
+
+	/* ids of the ancestors at each level including self */
+	int ancestor_ids[];
 };
 
 /*
@@ -308,6 +319,9 @@ struct cgroup_root {
 	/* The root cgroup.  Root is destroyed on its release. */
 	struct cgroup cgrp;
 
+	/* for cgrp->ancestor_ids[0] */
+	int cgrp_ancestor_id_storage;
+
 	/* Number of cgroups in the hierarchy, used only for /proc/cgroups */
 	atomic_t nr_cgrps;
 

include/linux/cgroup.h

@@ -81,7 +81,8 @@ struct cgroup_subsys_state *cgroup_get_e_css(struct cgroup *cgroup,
 struct cgroup_subsys_state *css_tryget_online_from_dir(struct dentry *dentry,
 						       struct cgroup_subsys *ss);
 
-bool cgroup_is_descendant(struct cgroup *cgrp, struct cgroup *ancestor);
+struct cgroup *cgroup_get_from_path(const char *path);
+
 int cgroup_attach_task_all(struct task_struct *from, struct task_struct *);
 int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from);
 
@@ -352,6 +353,11 @@ static inline void css_put_many(struct cgroup_subsys_state *css, unsigned int n)
 		percpu_ref_put_many(&css->refcnt, n);
 }
 
+static inline void cgroup_put(struct cgroup *cgrp)
+{
+	css_put(&cgrp->self);
+}
+
 /**
  * task_css_set_check - obtain a task's css_set with extra access conditions
  * @task: the task to obtain css_set for
@@ -459,6 +465,23 @@ static inline struct cgroup *task_cgroup(struct task_struct *task,
 	return task_css(task, subsys_id)->cgroup;
 }
 
+/**
+ * cgroup_is_descendant - test ancestry
+ * @cgrp: the cgroup to be tested
+ * @ancestor: possible ancestor of @cgrp
+ *
+ * Test whether @cgrp is a descendant of @ancestor.  It also returns %true
+ * if @cgrp == @ancestor.  This function is safe to call as long as @cgrp
+ * and @ancestor are accessible.
+ */
+static inline bool cgroup_is_descendant(struct cgroup *cgrp,
+					struct cgroup *ancestor)
+{
+	if (cgrp->root != ancestor->root || cgrp->level < ancestor->level)
+		return false;
+	return cgrp->ancestor_ids[ancestor->level] == ancestor->id;
+}
+
 /* no synchronization, the result can only be used as a hint */
 static inline bool cgroup_is_populated(struct cgroup *cgrp)
 {

include/linux/kernfs.h

@@ -274,6 +274,8 @@ void pr_cont_kernfs_path(struct kernfs_node *kn);
 struct kernfs_node *kernfs_get_parent(struct kernfs_node *kn);
 struct kernfs_node *kernfs_find_and_get_ns(struct kernfs_node *parent,
 					   const char *name, const void *ns);
+struct kernfs_node *kernfs_walk_and_get_ns(struct kernfs_node *parent,
+					   const char *path, const void *ns);
 void kernfs_get(struct kernfs_node *kn);
 void kernfs_put(struct kernfs_node *kn);
 
@@ -350,6 +352,10 @@ static inline struct kernfs_node *
 kernfs_find_and_get_ns(struct kernfs_node *parent, const char *name,
 		       const void *ns)
 { return NULL; }
+static inline struct kernfs_node *
+kernfs_walk_and_get_ns(struct kernfs_node *parent, const char *path,
+		       const void *ns)
+{ return NULL; }
 
 static inline void kernfs_get(struct kernfs_node *kn) { }
 static inline void kernfs_put(struct kernfs_node *kn) { }
@@ -430,6 +436,12 @@ kernfs_find_and_get(struct kernfs_node *kn, const char *name)
 	return kernfs_find_and_get_ns(kn, name, NULL);
 }
 
+static inline struct kernfs_node *
+kernfs_walk_and_get(struct kernfs_node *kn, const char *path)
+{
+	return kernfs_walk_and_get_ns(kn, path, NULL);
+}
+
 static inline struct kernfs_node *
 kernfs_create_dir(struct kernfs_node *parent, const char *name, umode_t mode,
 		  void *priv)

kernel/cgroup.c

@@ -434,11 +434,6 @@ static bool cgroup_tryget(struct cgroup *cgrp)
 	return css_tryget(&cgrp->self);
 }
 
-static void cgroup_put(struct cgroup *cgrp)
-{
-	css_put(&cgrp->self);
-}
-
 struct cgroup_subsys_state *of_css(struct kernfs_open_file *of)
 {
 	struct cgroup *cgrp = of->kn->parent->priv;
@@ -459,25 +454,6 @@ struct cgroup_subsys_state *of_css(struct kernfs_open_file *of)
 }
 EXPORT_SYMBOL_GPL(of_css);
 
-/**
- * cgroup_is_descendant - test ancestry
- * @cgrp: the cgroup to be tested
- * @ancestor: possible ancestor of @cgrp
- *
- * Test whether @cgrp is a descendant of @ancestor.  It also returns %true
- * if @cgrp == @ancestor.  This function is safe to call as long as @cgrp
- * and @ancestor are accessible.
- */
-bool cgroup_is_descendant(struct cgroup *cgrp, struct cgroup *ancestor)
-{
-	while (cgrp) {
-		if (cgrp == ancestor)
-			return true;
-		cgrp = cgroup_parent(cgrp);
-	}
-	return false;
-}
-
 static int notify_on_release(const struct cgroup *cgrp)
 {
 	return test_bit(CGRP_NOTIFY_ON_RELEASE, &cgrp->flags);
@@ -1903,6 +1879,7 @@ static int cgroup_setup_root(struct cgroup_root *root, unsigned long ss_mask)
 	if (ret < 0)
 		goto out;
 	root_cgrp->id = ret;
+	root_cgrp->ancestor_ids[0] = ret;
 
 	ret = percpu_ref_init(&root_cgrp->self.refcnt, css_release, 0,
 			      GFP_KERNEL);
@@ -4846,11 +4823,11 @@ static int create_css(struct cgroup *cgrp, struct cgroup_subsys *ss,
 static int cgroup_mkdir(struct kernfs_node *parent_kn, const char *name,
 			umode_t mode)
 {
-	struct cgroup *parent, *cgrp;
+	struct cgroup *parent, *cgrp, *tcgrp;
 	struct cgroup_root *root;
 	struct cgroup_subsys *ss;
 	struct kernfs_node *kn;
-	int ssid, ret;
+	int level, ssid, ret;
 
 	/* Do not accept '\n' to prevent making /proc/<pid>/cgroup unparsable.
 	 */
@@ -4861,9 +4838,11 @@ static int cgroup_mkdir(struct kernfs_node *parent_kn, const char *name,
 	if (!parent)
 		return -ENODEV;
 	root = parent->root;
+	level = parent->level + 1;
 
 	/* allocate the cgroup and its ID, 0 is reserved for the root */
-	cgrp = kzalloc(sizeof(*cgrp), GFP_KERNEL);
+	cgrp = kzalloc(sizeof(*cgrp) +
+		       sizeof(cgrp->ancestor_ids[0]) * (level + 1), GFP_KERNEL);
 	if (!cgrp) {
 		ret = -ENOMEM;
 		goto out_unlock;
@@ -4887,6 +4866,10 @@ static int cgroup_mkdir(struct kernfs_node *parent_kn, const char *name,
 
 	cgrp->self.parent = &parent->self;
 	cgrp->root = root;
+	cgrp->level = level;
+
+	for (tcgrp = cgrp; tcgrp; tcgrp = cgroup_parent(tcgrp))
+		cgrp->ancestor_ids[tcgrp->level] = tcgrp->id;
 
 	if (notify_on_release(parent))
 		set_bit(CGRP_NOTIFY_ON_RELEASE, &cgrp->flags);
@@ -5765,6 +5748,40 @@ struct cgroup_subsys_state *css_from_id(int id, struct cgroup_subsys *ss)
 	return id > 0 ? idr_find(&ss->css_idr, id) : NULL;
 }
 
+/**
+ * cgroup_get_from_path - lookup and get a cgroup from its default hierarchy path
+ * @path: path on the default hierarchy
+ *
+ * Find the cgroup at @path on the default hierarchy, increment its
+ * reference count and return it.  Returns pointer to the found cgroup on
+ * success, ERR_PTR(-ENOENT) if @path doens't exist and ERR_PTR(-ENOTDIR)
+ * if @path points to a non-directory.
+ */
+struct cgroup *cgroup_get_from_path(const char *path)
+{
+	struct kernfs_node *kn;
+	struct cgroup *cgrp;
+
+	mutex_lock(&cgroup_mutex);
+
+	kn = kernfs_walk_and_get(cgrp_dfl_root.cgrp.kn, path);
+	if (kn) {
+		if (kernfs_type(kn) == KERNFS_DIR) {
+			cgrp = kn->priv;
+			cgroup_get(cgrp);
+		} else {
+			cgrp = ERR_PTR(-ENOTDIR);
+		}
+		kernfs_put(kn);
+	} else {
+		cgrp = ERR_PTR(-ENOENT);
+	}
+
+	mutex_unlock(&cgroup_mutex);
+	return cgrp;
+}
+EXPORT_SYMBOL_GPL(cgroup_get_from_path);
+
 #ifdef CONFIG_CGROUP_DEBUG
 static struct cgroup_subsys_state *
 debug_css_alloc(struct cgroup_subsys_state *parent_css)