cgroup: reorganize cgroup source files

index 8a916dc..3c02404 100644
@@ -148,14 +148,18 @@ struct cgroup_subsys_state {
  * set for a task.
  */
 struct css_set {
-	/* Reference count */
-	atomic_t refcount;
-
 	/*
-	 * List running through all cgroup groups in the same hash
-	 * slot. Protected by css_set_lock
+	 * Set of subsystem states, one for each subsystem. This array is
+	 * immutable after creation apart from the init_css_set during
+	 * subsystem registration (at boot time).
 	 */
-	struct hlist_node hlist;
+	struct cgroup_subsys_state *subsys[CGROUP_SUBSYS_COUNT];
+
+	/* reference count */
+	atomic_t refcount;
+
+	/* the default cgroup associated with this css_set */
+	struct cgroup *dfl_cgrp;
 
 	/*
 	 * Lists running through all tasks using this cgroup group.

@@ -167,21 +171,29 @@ struct css_set {
 	struct list_head tasks;
 	struct list_head mg_tasks;
 
+	/* all css_task_iters currently walking this cset */
+	struct list_head task_iters;
+
 	/*
-	 * List of cgrp_cset_links pointing at cgroups referenced from this
-	 * css_set.  Protected by css_set_lock.
+	 * On the default hierarhcy, ->subsys[ssid] may point to a css
+	 * attached to an ancestor instead of the cgroup this css_set is
+	 * associated with.  The following node is anchored at
+	 * ->subsys[ssid]->cgroup->e_csets[ssid] and provides a way to
+	 * iterate through all css's attached to a given cgroup.
 	 */
-	struct list_head cgrp_links;
+	struct list_head e_cset_node[CGROUP_SUBSYS_COUNT];
 
-	/* the default cgroup associated with this css_set */
-	struct cgroup *dfl_cgrp;
+	/*
+	 * List running through all cgroup groups in the same hash
+	 * slot. Protected by css_set_lock
+	 */
+	struct hlist_node hlist;
 
 	/*
-	 * Set of subsystem states, one for each subsystem. This array is
-	 * immutable after creation apart from the init_css_set during
-	 * subsystem registration (at boot time).
+	 * List of cgrp_cset_links pointing at cgroups referenced from this
+	 * css_set.  Protected by css_set_lock.
 	 */
-	struct cgroup_subsys_state *subsys[CGROUP_SUBSYS_COUNT];
+	struct list_head cgrp_links;
 
 	/*
 	 * List of csets participating in the on-going migration either as

@@ -201,18 +213,6 @@ struct css_set {
 	struct cgroup *mg_dst_cgrp;
 	struct css_set *mg_dst_cset;
 
-	/*
-	 * On the default hierarhcy, ->subsys[ssid] may point to a css
-	 * attached to an ancestor instead of the cgroup this css_set is
-	 * associated with.  The following node is anchored at
-	 * ->subsys[ssid]->cgroup->e_csets[ssid] and provides a way to
-	 * iterate through all css's attached to a given cgroup.
-	 */
-	struct list_head e_cset_node[CGROUP_SUBSYS_COUNT];
-
-	/* all css_task_iters currently walking this cset */
-	struct list_head task_iters;
-
 	/* dead and being drained, ignore for migration */
 	bool dead;
 

index b9e2d85..1a815f2 100644
@@ -647,12 +647,12 @@ struct cgrp_cset_link {
  */
 struct css_set init_css_set = {
 	.refcount		= ATOMIC_INIT(1),
-	.cgrp_links		= LIST_HEAD_INIT(init_css_set.cgrp_links),
 	.tasks			= LIST_HEAD_INIT(init_css_set.tasks),
 	.mg_tasks		= LIST_HEAD_INIT(init_css_set.mg_tasks),
+	.task_iters		= LIST_HEAD_INIT(init_css_set.task_iters),
+	.cgrp_links		= LIST_HEAD_INIT(init_css_set.cgrp_links),
 	.mg_preload_node	= LIST_HEAD_INIT(init_css_set.mg_preload_node),
 	.mg_node		= LIST_HEAD_INIT(init_css_set.mg_node),
-	.task_iters		= LIST_HEAD_INIT(init_css_set.task_iters),
 };
 
 static int css_set_count	= 1;	/* 1 for init_css_set */

@@ -1095,13 +1095,13 @@ static struct css_set *find_css_set(struct css_set *old_cset,
 	}
 
 	atomic_set(&cset->refcount, 1);
-	INIT_LIST_HEAD(&cset->cgrp_links);
 	INIT_LIST_HEAD(&cset->tasks);
 	INIT_LIST_HEAD(&cset->mg_tasks);
-	INIT_LIST_HEAD(&cset->mg_preload_node);
-	INIT_LIST_HEAD(&cset->mg_node);
 	INIT_LIST_HEAD(&cset->task_iters);
 	INIT_HLIST_NODE(&cset->hlist);
+	INIT_LIST_HEAD(&cset->cgrp_links);
+	INIT_LIST_HEAD(&cset->mg_preload_node);
+	INIT_LIST_HEAD(&cset->mg_node);
 
 	/* Copy the set of subsystem state objects generated in
 	 * find_existing_css_set() */

@@ -4384,6 +4384,9 @@ int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from)
 	struct task_struct *task;
 	int ret;
 
+	if (cgroup_on_dfl(to))
+		return -EINVAL;
+
 	if (!cgroup_may_migrate_to(to))
 		return -EBUSY;
 

similarity index 100%
rename from kernel/cgroup.c
rename to kernel/cgroup/cgroup.c

similarity index 100%
rename from kernel/cpuset.c
rename to kernel/cgroup/cpuset.c

similarity index 100%
rename from kernel/cgroup_freezer.c
rename to kernel/cgroup/freezer.c

similarity index 100%
rename from kernel/cgroup_pids.c
rename to kernel/cgroup/pids.c

101 lines not on this page · raw message

1,027 lines not on this page · raw message

1,410 lines not on this page · raw message

103 lines not on this page · raw message

1,027 lines not on this page · raw message

1,426 lines not on this page · raw message

index cb0d29e..6225c4b 100644
@@ -1991,48 +1991,55 @@ static int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask)
 	return ret;
 }
 
-static struct dentry *cgroup_mount(struct file_system_type *fs_type,
-			 int flags, const char *unused_dev_name,
-			 void *data)
+static struct dentry *cgroup_do_mount(struct file_system_type *fs_type,
+				      int flags, struct cgroup_root *root,
+				      unsigned long magic,
+				      struct cgroup_namespace *ns)
 {
-	bool is_v2 = fs_type == &cgroup2_fs_type;
-	struct super_block *pinned_sb = NULL;
-	struct cgroup_namespace *ns = current->nsproxy->cgroup_ns;
-	struct cgroup_subsys *ss;
-	struct cgroup_root *root;
-	struct cgroup_sb_opts opts;
 	struct dentry *dentry;
-	int ret;
-	int i;
 	bool new_sb;
 
-	get_cgroup_ns(ns);
-
-	/* Check if the caller has permission to mount. */
-	if (!ns_capable(ns->user_ns, CAP_SYS_ADMIN)) {
-		put_cgroup_ns(ns);
-		return ERR_PTR(-EPERM);
-	}
+	dentry = kernfs_mount(fs_type, flags, root->kf_root, magic, &new_sb);
 
 	/*
-	 * The first time anyone tries to mount a cgroup, enable the list
-	 * linking each css_set to its tasks and fix up all existing tasks.
+	 * In non-init cgroup namespace, instead of root cgroup's dentry,
+	 * we return the dentry corresponding to the cgroupns->root_cgrp.
 	 */
-	if (!use_task_css_set_links)
-		cgroup_enable_task_cg_lists();
+	if (!IS_ERR(dentry) && ns != &init_cgroup_ns) {
+		struct dentry *nsdentry;
+		struct cgroup *cgrp;
 
-	if (is_v2) {
-		if (data) {
-			pr_err("cgroup2: unknown option \"%s\"\n", (char *)data);
-			put_cgroup_ns(ns);
-			return ERR_PTR(-EINVAL);
-		}
-		cgrp_dfl_visible = true;
-		root = &cgrp_dfl_root;
-		cgroup_get(&root->cgrp);
-		goto out_mount;
+		mutex_lock(&cgroup_mutex);
+		spin_lock_irq(&css_set_lock);
+
+		cgrp = cset_cgroup_from_root(ns->root_cset, root);
+
+		spin_unlock_irq(&css_set_lock);
+		mutex_unlock(&cgroup_mutex);
+
+		nsdentry = kernfs_node_dentry(cgrp->kn, dentry->d_sb);
+		dput(dentry);
+		dentry = nsdentry;
 	}
 
+	if (IS_ERR(dentry) || !new_sb)
+		cgroup_put(&root->cgrp);
+
+	return dentry;
+}
+
+static struct dentry *cgroup1_mount(struct file_system_type *fs_type,
+				    int flags, void *data,
+				    unsigned long magic,
+				    struct cgroup_namespace *ns)
+{
+	struct super_block *pinned_sb = NULL;
+	struct cgroup_sb_opts opts;
+	struct cgroup_root *root;
+	struct cgroup_subsys *ss;
+	struct dentry *dentry;
+	int i, ret;
+
 	cgroup_lock_and_drain_offline(&cgrp_dfl_root.cgrp);
 
 	/* First find the desired set of subsystems */

@@ -2154,47 +2161,58 @@ static struct dentry *cgroup_mount(struct file_system_type *fs_type,
 	kfree(opts.release_agent);
 	kfree(opts.name);
 
-	if (ret) {
-		put_cgroup_ns(ns);
+	if (ret)
 		return ERR_PTR(ret);
-	}
-out_mount:
-	dentry = kernfs_mount(fs_type, flags, root->kf_root,
-			      is_v2 ? CGROUP2_SUPER_MAGIC : CGROUP_SUPER_MAGIC,
-			      &new_sb);
+
+	dentry = cgroup_do_mount(&cgroup_fs_type, flags, root,
+				 CGROUP_SUPER_MAGIC, ns);
 
 	/*
-	 * In non-init cgroup namespace, instead of root cgroup's
-	 * dentry, we return the dentry corresponding to the
-	 * cgroupns->root_cgrp.
+	 * If @pinned_sb, we're reusing an existing root and holding an
+	 * extra ref on its sb.  Mount is complete.  Put the extra ref.
 	 */
-	if (!IS_ERR(dentry) && ns != &init_cgroup_ns) {
-		struct dentry *nsdentry;
-		struct cgroup *cgrp;
+	if (pinned_sb)
+		deactivate_super(pinned_sb);
 
-		mutex_lock(&cgroup_mutex);
-		spin_lock_irq(&css_set_lock);
+	return dentry;
+}
 
-		cgrp = cset_cgroup_from_root(ns->root_cset, root);
+static struct dentry *cgroup_mount(struct file_system_type *fs_type,
+			 int flags, const char *unused_dev_name,
+			 void *data)
+{
+	struct cgroup_namespace *ns = current->nsproxy->cgroup_ns;
+	struct dentry *dentry;
 
-		spin_unlock_irq(&css_set_lock);
-		mutex_unlock(&cgroup_mutex);
+	get_cgroup_ns(ns);
 
-		nsdentry = kernfs_node_dentry(cgrp->kn, dentry->d_sb);
-		dput(dentry);
-		dentry = nsdentry;
+	/* Check if the caller has permission to mount. */
+	if (!ns_capable(ns->user_ns, CAP_SYS_ADMIN)) {
+		put_cgroup_ns(ns);
+		return ERR_PTR(-EPERM);
 	}
 
-	if (IS_ERR(dentry) || !new_sb)
-		cgroup_put(&root->cgrp);
-
 	/*
-	 * If @pinned_sb, we're reusing an existing root and holding an
-	 * extra ref on its sb.  Mount is complete.  Put the extra ref.
+	 * The first time anyone tries to mount a cgroup, enable the list
+	 * linking each css_set to its tasks and fix up all existing tasks.
 	 */
-	if (pinned_sb) {
-		WARN_ON(new_sb);
-		deactivate_super(pinned_sb);
+	if (!use_task_css_set_links)
+		cgroup_enable_task_cg_lists();
+
+	if (fs_type == &cgroup2_fs_type) {
+		if (data) {
+			pr_err("cgroup2: unknown option \"%s\"\n", (char *)data);
+			put_cgroup_ns(ns);
+			return ERR_PTR(-EINVAL);
+		}
+		cgrp_dfl_visible = true;
+		cgroup_get(&cgrp_dfl_root.cgrp);
+
+		dentry = cgroup_do_mount(&cgroup2_fs_type, flags, &cgrp_dfl_root,
+					 CGROUP2_SUPER_MAGIC, ns);
+	} else {
+		dentry = cgroup1_mount(&cgroup_fs_type, flags, data,
+				       CGROUP_SUPER_MAGIC, ns);
 	}
 
 	put_cgroup_ns(ns);

index d86fbbc..7b8182e 100644
@@ -93,8 +93,8 @@ extern const struct file_operations proc_cgroupstats_operations;
 
 bool cgroup_ssid_no_v1(int ssid);
 void cgroup_pidlist_destroy_all(struct cgroup *cgrp);
-int cgroup_rename(struct kernfs_node *kn, struct kernfs_node *new_parent,
-		  const char *new_name_str);
+int cgroup1_rename(struct kernfs_node *kn, struct kernfs_node *new_parent,
+		   const char *new_name_str);
 void cgroup_release_agent(struct work_struct *work);
 void check_for_release(struct cgroup *cgrp);
 

index 7af745a..0b2c24f 100644
@@ -800,8 +800,8 @@ void cgroup_release_agent(struct work_struct *work)
 /*
  * cgroup_rename - Only allow simple rename of directories in place.
  */
-int cgroup_rename(struct kernfs_node *kn, struct kernfs_node *new_parent,
-		  const char *new_name_str)
+int cgroup1_rename(struct kernfs_node *kn, struct kernfs_node *new_parent,
+		   const char *new_name_str)
 {
 	struct cgroup *cgrp = kn->priv;
 	int ret;

@@ -812,13 +812,6 @@ int cgroup_rename(struct kernfs_node *kn, struct kernfs_node *new_parent,
 		return -EIO;
 
 	/*
-	 * This isn't a proper migration and its usefulness is very
-	 * limited.  Disallow on the default hierarchy.
-	 */
-	if (cgroup_on_dfl(cgrp))
-		return -EPERM;
-
-	/*
 	 * We're gonna grab cgroup_mutex which nests outside kernfs
 	 * active_ref.  kernfs_rename() doesn't require active_ref
 	 * protection.  Break them before grabbing cgroup_mutex.

index 6225c4b..f1b71fb 100644
@@ -1234,6 +1234,7 @@ struct cgroup *task_cgroup_from_root(struct task_struct *task,
  * update of a tasks cgroup pointer by cgroup_attach_task()
  */
 
+static struct kernfs_syscall_ops cgroup1_kf_syscall_ops;
 static struct kernfs_syscall_ops cgroup_kf_syscall_ops;
 
 static char *cgroup_file_name(struct cgroup *cgrp, const struct cftype *cft,

@@ -1568,16 +1569,15 @@ static int cgroup_show_path(struct seq_file *sf, struct kernfs_node *kf_node,
 	return len;
 }
 
-static int cgroup_show_options(struct seq_file *seq, struct kernfs_root *kf_root)
+static int cgroup1_show_options(struct seq_file *seq, struct kernfs_root *kf_root)
 {
 	struct cgroup_root *root = cgroup_root_from_kf(kf_root);
 	struct cgroup_subsys *ss;
 	int ssid;
 
-	if (root != &cgrp_dfl_root)
-		for_each_subsys(ss, ssid)
-			if (root->subsys_mask & (1 << ssid))
-				seq_show_option(seq, ss->legacy_name, NULL);
+	for_each_subsys(ss, ssid)
+		if (root->subsys_mask & (1 << ssid))
+			seq_show_option(seq, ss->legacy_name, NULL);
 	if (root->flags & CGRP_ROOT_NOPREFIX)
 		seq_puts(seq, ",noprefix");
 	if (root->flags & CGRP_ROOT_XATTR)

@@ -1738,18 +1738,13 @@ static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts)
 	return 0;
 }
 
-static int cgroup_remount(struct kernfs_root *kf_root, int *flags, char *data)
+static int cgroup1_remount(struct kernfs_root *kf_root, int *flags, char *data)
 {
 	int ret = 0;
 	struct cgroup_root *root = cgroup_root_from_kf(kf_root);
 	struct cgroup_sb_opts opts;
 	u16 added_mask, removed_mask;
 
-	if (root == &cgrp_dfl_root) {
-		pr_err("remount is not allowed\n");
-		return -EINVAL;
-	}
-
 	cgroup_lock_and_drain_offline(&cgrp_dfl_root.cgrp);
 
 	/* See what subsystems are wanted */

@@ -1800,6 +1795,12 @@ static int cgroup_remount(struct kernfs_root *kf_root, int *flags, char *data)
 	return ret;
 }
 
+static int cgroup_remount(struct kernfs_root *kf_root, int *flags, char *data)
+{
+	pr_err("remount is not allowed\n");
+	return -EINVAL;
+}
+
 /*
  * To reduce the fork() overhead for systems that are not actually using
  * their cgroups capability, we don't maintain the lists running through

@@ -1902,6 +1903,7 @@ static int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask)
 {
 	LIST_HEAD(tmp_links);
 	struct cgroup *root_cgrp = &root->cgrp;
+	struct kernfs_syscall_ops *kf_sops;
 	struct css_set *cset;
 	int i, ret;
 

@@ -1933,7 +1935,10 @@ static int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask)
 	if (ret)
 		goto cancel_ref;
 
-	root->kf_root = kernfs_create_root(&cgroup_kf_syscall_ops,
+	kf_sops = root == &cgrp_dfl_root ?
+		&cgroup_kf_syscall_ops : &cgroup1_kf_syscall_ops;
+
+	root->kf_root = kernfs_create_root(kf_sops,
 					   KERNFS_ROOT_CREATE_DEACTIVATED,
 					   root_cgrp);
 	if (IS_ERR(root->kf_root)) {

@@ -4815,12 +4820,19 @@ static int cgroup_rmdir(struct kernfs_node *kn)
 	return ret;
 }
 
+static struct kernfs_syscall_ops cgroup1_kf_syscall_ops = {
+	.remount_fs		= cgroup1_remount,
+	.show_options		= cgroup1_show_options,
+	.rename			= cgroup1_rename,
+	.mkdir			= cgroup_mkdir,
+	.rmdir			= cgroup_rmdir,
+	.show_path		= cgroup_show_path,
+};
+
 static struct kernfs_syscall_ops cgroup_kf_syscall_ops = {
 	.remount_fs		= cgroup_remount,
-	.show_options		= cgroup_show_options,
 	.mkdir			= cgroup_mkdir,
 	.rmdir			= cgroup_rmdir,
-	.rename			= cgroup_rename,
 	.show_path		= cgroup_show_path,
 };
 

index 7b8182e..3d431b6 100644
@@ -26,6 +26,16 @@ struct cgrp_cset_link {
 	struct list_head	cgrp_link;
 };
 
+struct cgroup_sb_opts {
+	u16 subsys_mask;
+	unsigned int flags;
+	char *release_agent;
+	bool cpuset_clone_children;
+	char *name;
+	/* User explicitly requested empty subsystem */
+	bool none;
+};
+
 extern struct cgroup_subsys *cgroup_subsys[];
 extern struct list_head cgroup_roots;
 extern struct file_system_type cgroup_fs_type;

@@ -64,7 +74,13 @@ void cgroup_kn_unlock(struct kernfs_node *kn);
 int cgroup_path_ns_locked(struct cgroup *cgrp, char *buf, size_t buflen,
 			  struct cgroup_namespace *ns);
 
+void cgroup_free_root(struct cgroup_root *root);
+void init_cgroup_root(struct cgroup_root *root, struct cgroup_sb_opts *opts);
+int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask);
 int rebind_subsystems(struct cgroup_root *dst_root, u16 ss_mask);
+struct dentry *cgroup_do_mount(struct file_system_type *fs_type, int flags,
+			       struct cgroup_root *root, unsigned long magic,
+			       struct cgroup_namespace *ns);
 
 bool cgroup_may_migrate_to(struct cgroup *dst_cgrp);
 void cgroup_migrate_finish(struct list_head *preloaded_csets);

@@ -84,18 +100,24 @@ ssize_t cgroup_procs_write(struct kernfs_open_file *of, char *buf, size_t nbytes
 
 void cgroup_lock_and_drain_offline(struct cgroup *cgrp);
 
+int cgroup_mkdir(struct kernfs_node *parent_kn, const char *name, umode_t mode);
+int cgroup_rmdir(struct kernfs_node *kn);
+int cgroup_show_path(struct seq_file *sf, struct kernfs_node *kf_node,
+		     struct kernfs_root *kf_root);
+
 /*
  * cgroup-v1.c
  */
-extern spinlock_t release_agent_path_lock;
 extern struct cftype cgroup_legacy_base_files[];
 extern const struct file_operations proc_cgroupstats_operations;
+extern struct kernfs_syscall_ops cgroup1_kf_syscall_ops;
 
 bool cgroup_ssid_no_v1(int ssid);
 void cgroup_pidlist_destroy_all(struct cgroup *cgrp);
-int cgroup1_rename(struct kernfs_node *kn, struct kernfs_node *new_parent,
-		   const char *new_name_str);
 void cgroup_release_agent(struct work_struct *work);
 void check_for_release(struct cgroup *cgrp);
+struct dentry *cgroup1_mount(struct file_system_type *fs_type, int flags,
+			     void *data, unsigned long magic,
+			     struct cgroup_namespace *ns);
 
 #endif /* __CGROUP_INTERNAL_H */

406 lines not on this page · raw message

488 lines not on this page · raw message

index 3d431b6..2020d8d 100644
@@ -108,14 +108,14 @@ int cgroup_show_path(struct seq_file *sf, struct kernfs_node *kf_node,
 /*
  * cgroup-v1.c
  */
-extern struct cftype cgroup_legacy_base_files[];
+extern struct cftype cgroup1_base_files[];
 extern const struct file_operations proc_cgroupstats_operations;
 extern struct kernfs_syscall_ops cgroup1_kf_syscall_ops;
 
-bool cgroup_ssid_no_v1(int ssid);
-void cgroup_pidlist_destroy_all(struct cgroup *cgrp);
-void cgroup_release_agent(struct work_struct *work);
-void check_for_release(struct cgroup *cgrp);
+bool cgroup1_ssid_disabled(int ssid);
+void cgroup1_pidlist_destroy_all(struct cgroup *cgrp);
+void cgroup1_release_agent(struct work_struct *work);
+void cgroup1_check_for_release(struct cgroup *cgrp);
 struct dentry *cgroup1_mount(struct file_system_type *fs_type, int flags,
 			     void *data, unsigned long magic,
 			     struct cgroup_namespace *ns);

index ae240c0..37be09e 100644
@@ -36,7 +36,7 @@ static struct workqueue_struct *cgroup_pidlist_destroy_wq;
  */
 static DEFINE_SPINLOCK(release_agent_path_lock);
 
-bool cgroup_ssid_no_v1(int ssid)
+bool cgroup1_ssid_disabled(int ssid)
 {
 	return cgroup_no_v1_mask & (1 << ssid);
 }

@@ -201,7 +201,7 @@ static void pidlist_free(void *p)
  * Used to destroy all pidlists lingering waiting for destroy timer.  None
  * should be left afterwards.
  */
-void cgroup_pidlist_destroy_all(struct cgroup *cgrp)
+void cgroup1_pidlist_destroy_all(struct cgroup *cgrp)
 {
 	struct cgroup_pidlist *l, *tmp_l;
 

@@ -585,7 +585,7 @@ static int cgroup_clone_children_write(struct cgroup_subsys_state *css,
 }
 
 /* cgroup core interface files for the legacy hierarchies */
-struct cftype cgroup_legacy_base_files[] = {
+struct cftype cgroup1_base_files[] = {
 	{
 		.name = "cgroup.procs",
 		.seq_start = cgroup_pidlist_start,

@@ -729,7 +729,7 @@ int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry)
 	return 0;
 }
 
-void check_for_release(struct cgroup *cgrp)
+void cgroup1_check_for_release(struct cgroup *cgrp)
 {
 	if (notify_on_release(cgrp) && !cgroup_is_populated(cgrp) &&
 	    !css_has_online_children(&cgrp->self) && !cgroup_is_dead(cgrp))

@@ -759,7 +759,7 @@ void check_for_release(struct cgroup *cgrp)
  * this routine has no use for the exit status of the release agent
  * task, so no sense holding our caller up for that.
  */
-void cgroup_release_agent(struct work_struct *work)
+void cgroup1_release_agent(struct work_struct *work)
 {
 	struct cgroup *cgrp =
 		container_of(work, struct cgroup, release_agent_work);

@@ -946,7 +946,7 @@ static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts)
 				continue;
 			if (!cgroup_ssid_enabled(i))
 				continue;
-			if (cgroup_ssid_no_v1(i))
+			if (cgroup1_ssid_disabled(i))
 				continue;
 
 			/* Mutually exclusive option 'all' + subsystem name */

@@ -968,7 +968,7 @@ static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts)
 	 */
 	if (all_ss || (!one_ss && !opts->none && !opts->name))
 		for_each_subsys(ss, i)
-			if (cgroup_ssid_enabled(i) && !cgroup_ssid_no_v1(i))
+			if (cgroup_ssid_enabled(i) && !cgroup1_ssid_disabled(i))
 				opts->subsys_mask |= (1 << i);
 
 	/*

index ae25f14..dcfbeb6 100644
@@ -201,7 +201,7 @@ struct cgroup_namespace init_cgroup_ns = {
 static u16 have_canfork_callback __read_mostly;
 
 static struct file_system_type cgroup2_fs_type;
-static struct cftype cgroup_dfl_base_files[];
+static struct cftype cgroup_base_files[];
 
 static int cgroup_apply_control(struct cgroup *cgrp);
 static void cgroup_finalize_control(struct cgroup *cgrp, int ret);

@@ -611,7 +611,7 @@ static void cgroup_update_populated(struct cgroup *cgrp, bool populated)
 		if (!trigger)
 			break;
 
-		check_for_release(cgrp);
+		cgroup1_check_for_release(cgrp);
 		cgroup_file_notify(&cgrp->events_file);
 
 		cgrp = cgroup_parent(cgrp);

@@ -1442,9 +1442,9 @@ static int css_populate_dir(struct cgroup_subsys_state *css)
 
 	if (!css->ss) {
 		if (cgroup_on_dfl(cgrp))
-			cfts = cgroup_dfl_base_files;
+			cfts = cgroup_base_files;
 		else
-			cfts = cgroup_legacy_base_files;
+			cfts = cgroup1_base_files;
 
 		return cgroup_addrm_files(&cgrp->self, cgrp, cfts, true);
 	}

@@ -1647,7 +1647,7 @@ static void init_cgroup_housekeeping(struct cgroup *cgrp)
 		INIT_LIST_HEAD(&cgrp->e_csets[ssid]);
 
 	init_waitqueue_head(&cgrp->offline_waitq);
-	INIT_WORK(&cgrp->release_agent_work, cgroup_release_agent);
+	INIT_WORK(&cgrp->release_agent_work, cgroup1_release_agent);
 }
 
 void init_cgroup_root(struct cgroup_root *root, struct cgroup_sb_opts *opts)

@@ -3838,7 +3838,7 @@ static int cgroup_procs_show(struct seq_file *s, void *v)
 }
 
 /* cgroup core interface files for the default hierarchy */
-static struct cftype cgroup_dfl_base_files[] = {
+static struct cftype cgroup_base_files[] = {
 	{
 		.name = "cgroup.procs",
 		.file_offset = offsetof(struct cgroup, procs_file),

@@ -3911,7 +3911,7 @@ static void css_free_work_fn(struct work_struct *work)
 	} else {
 		/* cgroup free path */
 		atomic_dec(&cgrp->root->nr_cgrps);
-		cgroup_pidlist_destroy_all(cgrp);
+		cgroup1_pidlist_destroy_all(cgrp);
 		cancel_work_sync(&cgrp->release_agent_work);
 
 		if (cgroup_parent(cgrp)) {

@@ -4413,7 +4413,7 @@ static int cgroup_destroy_locked(struct cgroup *cgrp)
 	 */
 	kernfs_remove(cgrp->kn);
 
-	check_for_release(cgroup_parent(cgrp));
+	cgroup1_check_for_release(cgroup_parent(cgrp));
 
 	/* put the base reference */
 	percpu_ref_kill(&cgrp->self.refcnt);

@@ -4550,8 +4550,8 @@ int __init cgroup_init(void)
 
 	BUILD_BUG_ON(CGROUP_SUBSYS_COUNT > 16);
 	BUG_ON(percpu_init_rwsem(&cgroup_threadgroup_rwsem));
-	BUG_ON(cgroup_init_cftypes(NULL, cgroup_dfl_base_files));
-	BUG_ON(cgroup_init_cftypes(NULL, cgroup_legacy_base_files));
+	BUG_ON(cgroup_init_cftypes(NULL, cgroup_base_files));
+	BUG_ON(cgroup_init_cftypes(NULL, cgroup1_base_files));
 
 	/*
 	 * The latency of the synchronize_sched() is too high for cgroups,

@@ -4601,7 +4601,7 @@ int __init cgroup_init(void)
 			continue;
 		}
 
-		if (cgroup_ssid_no_v1(ssid))
+		if (cgroup1_ssid_disabled(ssid))
 			printk(KERN_INFO "Disabling %s control group subsystem in v1 mounts\n",
 			       ss->name);
 

index 2020d8d..690fa5d 100644
@@ -63,6 +63,33 @@ static inline bool notify_on_release(const struct cgroup *cgrp)
 	return test_bit(CGRP_NOTIFY_ON_RELEASE, &cgrp->flags);
 }
 
+void put_css_set_locked(struct css_set *cset);
+
+static inline void put_css_set(struct css_set *cset)
+{
+	unsigned long flags;
+
+	/*
+	 * Ensure that the refcount doesn't hit zero while any readers
+	 * can see it. Similar to atomic_dec_and_lock(), but for an
+	 * rwlock
+	 */
+	if (atomic_add_unless(&cset->refcount, -1, 1))
+		return;
+
+	spin_lock_irqsave(&css_set_lock, flags);
+	put_css_set_locked(cset);
+	spin_unlock_irqrestore(&css_set_lock, flags);
+}
+
+/*
+ * refcounted get/put for css_set objects
+ */
+static inline void get_css_set(struct css_set *cset)
+{
+	atomic_inc(&cset->refcount);
+}
+
 bool cgroup_ssid_enabled(int ssid);
 bool cgroup_on_dfl(const struct cgroup *cgrp);
 

@@ -106,6 +133,11 @@ int cgroup_show_path(struct seq_file *sf, struct kernfs_node *kf_node,
 		     struct kernfs_root *kf_root);
 
 /*
+ * namespace.c
+ */
+extern const struct proc_ns_operations cgroupns_operations;
+
+/*
  * cgroup-v1.c
  */
 extern struct cftype cgroup1_base_files[];

193 lines not on this page · raw message

155 lines not on this page · raw message

index 37be09e..465b101 100644
@@ -694,7 +694,7 @@ int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry)
 	 * @kn->priv is RCU safe.  Let's do the RCU dancing.
 	 */
 	rcu_read_lock();
-	cgrp = rcu_dereference(kn->priv);
+	cgrp = rcu_dereference(*(void __rcu __force **)&kn->priv);
 	if (!cgrp || cgroup_is_dead(cgrp)) {
 		rcu_read_unlock();
 		mutex_unlock(&cgroup_mutex);

index b6b9068..d9d82e9 100644
@@ -4932,7 +4932,7 @@ struct cgroup_subsys_state *css_tryget_online_from_dir(struct dentry *dentry,
 	 * have been or be removed at any point.  @kn->priv is RCU
 	 * protected for this access.  See css_release_work_fn() for details.
 	 */
-	cgrp = rcu_dereference(kn->priv);
+	cgrp = rcu_dereference(*(void __rcu __force **)&kn->priv);
 	if (cgrp)
 		css = cgroup_css(cgrp, ss);