netfilter, cgroup: implement xt_cgroup2 match

index 60d44b2..504d859 100644
@@ -235,6 +235,14 @@ 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
 	 * of their own contribute one.  The count is zero iff there's no

@@ -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;
 

index 22e3754..b5ee2c4 100644
@@ -81,7 +81,6 @@ 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);
 int cgroup_attach_task_all(struct task_struct *from, struct task_struct *);
 int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from);
 

@@ -459,6 +458,23 @@ 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)
 {

index f1603c1..3190040 100644
@@ -459,25 +459,6 @@ 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 +1884,7 @@ 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 +4828,11 @@ 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 +4843,11 @@ 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 +4871,10 @@ 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);

index 91e0045..95dc415 100644
@@ -694,6 +694,31 @@ 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 */
+	int len = strlen(path);
+	char *p, *name;
+
+	lockdep_assert_held(&kernfs_mutex);
+
+	if (len >= PATH_MAX)
+		return NULL;
+
+	memcpy(path_buf, path, len + 1);
+	p = path_buf;
+
+	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

@@ -719,6 +744,29 @@ 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
  * @flags: KERNFS_ROOT_* flags

index 5d4e9c4..af51df3 100644
@@ -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) { }

@@ -431,6 +437,12 @@ kernfs_find_and_get(struct kernfs_node *kn, const char *name)
 }
 
 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)
 {

index b5ee2c4..4c3ffab 100644
@@ -81,6 +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);
 
+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);
 

@@ -351,6 +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

index 3190040..49947c1 100644
@@ -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;

@@ -5753,6 +5748,39 @@ 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;
+}
+
 #ifdef CONFIG_CGROUP_DEBUG
 static struct cgroup_subsys_state *
 debug_css_alloc(struct cgroup_subsys_state *parent_css)

index 4c3ffab..2a6d7c4 100644
@@ -20,6 +20,8 @@
 
 #include <linux/cgroup-defs.h>
 
+struct sock;
+
 #ifdef CONFIG_CGROUPS
 
 /*

@@ -108,6 +110,9 @@ void cgroup_free(struct task_struct *p);
 int cgroup_init_early(void);
 int cgroup_init(void);
 
+void cgroup_sk_alloc(struct sock *sk);
+void cgroup_sk_free(struct sock *sk);
+
 /*
  * Iteration helpers and macros.
  */

@@ -576,6 +581,9 @@ static inline void cgroup_free(struct task_struct *p) {}
 static inline int cgroup_init_early(void) { return 0; }
 static inline int cgroup_init(void) { return 0; }
 
+static inline void cgroup_sk_alloc(struct sock *sk) {}
+static inline void cgroup_sk_free(struct sock *sk) {}
+
 #endif /* !CONFIG_CGROUPS */
 
 #endif /* _LINUX_CGROUP_H */

index bbf7c2c..6c5d195 100644
@@ -310,6 +310,7 @@ struct cg_proto;
   *	@sk_security: used by security modules
   *	@sk_mark: generic packet mark
   *	@sk_classid: this socket's cgroup classid
+  *	@sk_cgroup: the v2 cgroup this socket is associated with
   *	@sk_cgrp: this socket's cgroup-specific proto data
   *	@sk_write_pending: a write to stream socket waits to start
   *	@sk_state_change: callback to indicate change in the state of the sock

@@ -447,6 +448,9 @@ struct sock {
 #ifdef CONFIG_CGROUP_NET_CLASSID
 	u32			sk_classid;
 #endif
+#ifdef CONFIG_CGROUPS
+	struct cgroup		*sk_cgroup;
+#endif
 	struct cg_proto		*sk_cgrp;
 	void			(*sk_state_change)(struct sock *sk);
 	void			(*sk_data_ready)(struct sock *sk);

index 49947c1..f26533b 100644
@@ -57,8 +57,8 @@
 #include <linux/vmalloc.h> /* TODO: replace with more sophisticated array */
 #include <linux/kthread.h>
 #include <linux/delay.h>
-
 #include <linux/atomic.h>
+#include <net/sock.h>
 
 /*
  * pidlists linger the following amount before being destroyed.  The goal

@@ -5781,6 +5781,29 @@ struct cgroup *cgroup_get_from_path(const char *path)
 	return cgrp;
 }
 
+void cgroup_sk_alloc(struct sock *sk)
+{
+	rcu_read_lock();
+
+	while (true) {
+		struct css_set *cset;
+
+		cset = task_css_set(current);
+		if (likely(cgroup_tryget(cset->dfl_cgrp))) {
+			sk->sk_cgroup = cset->dfl_cgrp;
+			break;
+		}
+		cpu_relax();
+	}
+
+	rcu_read_unlock();
+}
+
+void cgroup_sk_free(struct sock *sk)
+{
+	cgroup_put(sk->sk_cgroup);
+}
+
 #ifdef CONFIG_CGROUP_DEBUG
 static struct cgroup_subsys_state *
 debug_css_alloc(struct cgroup_subsys_state *parent_css)

index 1e4dd54..7c34bba 100644
@@ -1363,6 +1363,7 @@ static struct sock *sk_prot_alloc(struct proto *prot, gfp_t priority,
 		if (!try_module_get(prot->owner))
 			goto out_free_sec;
 		sk_tx_queue_clear(sk);
+		cgroup_sk_alloc(sk);
 	}
 
 	return sk;

@@ -1385,6 +1386,7 @@ static void sk_prot_free(struct proto *prot, struct sock *sk)
 	owner = prot->owner;
 	slab = prot->slab;
 
+	cgroup_sk_free(sk);
 	security_sk_free(sk);
 	if (slab != NULL)
 		kmem_cache_free(slab, sk);

new file mode 100644
index 0000000..8726d31
@@ -0,0 +1,14 @@
+#ifndef _XT_CGROUP2_H
+#define _XT_CGROUP2_H
+
+#include <linux/types.h>
+
+struct xt_cgroup2_info {
+	char				path[PATH_MAX];
+	__u8				invert;
+
+	/* kernel internal data */
+	void				*priv;
+};
+
+#endif /* _XT_CGROUP2_H */

75 lines not on this page · raw message

@@ -0,0 +1,70 @@
+#include <stdio.h>
+#include <mntent.h>
+#include <xtables.h>
+#include <linux/netfilter/xt_cgroup2.h>
+#include <linux/limits.h>
+
+enum {
+	O_CGROUP2_PATH,
+};
+
+static void cgroup2_help(void)
+{
+	printf(
+"cgroup2 match options:\n"
+"[!] --path path                 path relative to cgroup2 root, recursive match\n");
+}
+
+static const struct xt_option_entry cgroup2_opts[] = {
+	{
+		.name = "path",
+		.id = O_CGROUP2_PATH,
+		.type = XTTYPE_STRING,
+		.flags = XTOPT_INVERT | XTOPT_MAND | XTOPT_PUT,
+		XTOPT_POINTER(struct xt_cgroup2_info, path)
+	},
+	XTOPT_TABLEEND,
+};
+
+static void cgroup2_parse(struct xt_option_call *cb)
+{
+	struct xt_cgroup2_info *info = cb->data;
+
+	xtables_option_parse(cb);
+
+	if (cb->invert)
+		info->invert = true;
+}
+
+static void cgroup2_print(const void *ip, const struct xt_entry_match *match,
+			  int numeric)
+{
+	const struct xt_cgroup2_info *info = (void *)match->data;
+
+	printf(" cgroup2 %s%s", info->invert ? "! ":"", info->path);
+}
+
+static void cgroup2_save(const void *ip, const struct xt_entry_match *match)
+{
+	const struct xt_cgroup2_info *info = (void *)match->data;
+
+	printf("%s --path %s", info->invert ? " !" : "", info->path);
+}
+
+static struct xtables_match cgroup2_match = {
+	.family		= NFPROTO_UNSPEC,
+	.name		= "cgroup2",
+	.version	= XTABLES_VERSION,
+	.size		= XT_ALIGN(sizeof(struct xt_cgroup2_info)),
+	.userspacesize	= XT_ALIGN(sizeof(struct xt_cgroup2_info)),
+	.help		= cgroup2_help,
+	.print		= cgroup2_print,
+	.save		= cgroup2_save,
+	.x6_parse	= cgroup2_parse,
+	.x6_options	= cgroup2_opts,
+};
+
+void _init(void)
+{
+	xtables_register_match(&cgroup2_match);
+}

@@ -0,0 +1,14 @@
+#ifndef _XT_CGROUP2_H
+#define _XT_CGROUP2_H
+
+#include <linux/types.h>
+
+struct xt_cgroup2_info {
+	char				path[PATH_MAX];
+	__u8				invert;
+
+	/* kernel internal data */
+	void				*priv;
+};
+
+#endif /* _XT_CGROUP2_H */