1 files changed, 164 insertions, 105 deletions

diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index f31bd61c9466..3f2b4bde0f9c 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -54,6 +54,7 @@
 #include <linux/proc_ns.h>
 #include <linux/nsproxy.h>
 #include <linux/file.h>
+#include <linux/fs_parser.h>
 #include <linux/sched/cputime.h>
 #include <linux/psi.h>
 #include <net/sock.h>
@@ -197,7 +198,7 @@ static u64 css_serial_nr_next = 1;
  */
 static u16 have_fork_callback __read_mostly;
 static u16 have_exit_callback __read_mostly;
-static u16 have_free_callback __read_mostly;
+static u16 have_release_callback __read_mostly;
 static u16 have_canfork_callback __read_mostly;
 
 /* cgroup namespace for init task */
@@ -1772,26 +1773,37 @@ int cgroup_show_path(struct seq_file *sf, struct kernfs_node *kf_node,
 	return len;
 }
 
-static int parse_cgroup_root_flags(char *data, unsigned int *root_flags)
-{
-	char *token;
+enum cgroup2_param {
+	Opt_nsdelegate,
+	nr__cgroup2_params
+};
 
-	*root_flags = 0;
+static const struct fs_parameter_spec cgroup2_param_specs[] = {
+	fsparam_flag  ("nsdelegate",		Opt_nsdelegate),
+	{}
+};
 
-	if (!data || *data == '\0')
-		return 0;
+static const struct fs_parameter_description cgroup2_fs_parameters = {
+	.name		= "cgroup2",
+	.specs		= cgroup2_param_specs,
+};
 
-	while ((token = strsep(&data, ",")) != NULL) {
-		if (!strcmp(token, "nsdelegate")) {
-			*root_flags |= CGRP_ROOT_NS_DELEGATE;
-			continue;
-		}
+static int cgroup2_parse_param(struct fs_context *fc, struct fs_parameter *param)
+{
+	struct cgroup_fs_context *ctx = cgroup_fc2context(fc);
+	struct fs_parse_result result;
+	int opt;
 
-		pr_err("cgroup2: unknown option \"%s\"\n", token);
-		return -EINVAL;
-	}
+	opt = fs_parse(fc, &cgroup2_fs_parameters, param, &result);
+	if (opt < 0)
+		return opt;
 
-	return 0;
+	switch (opt) {
+	case Opt_nsdelegate:
+		ctx->flags |= CGRP_ROOT_NS_DELEGATE;
+		return 0;
+	}
+	return -EINVAL;
 }
 
 static void apply_cgroup_root_flags(unsigned int root_flags)
@@ -1811,16 +1823,11 @@ static int cgroup_show_options(struct seq_file *seq, struct kernfs_root *kf_root
 	return 0;
 }
 
-static int cgroup_remount(struct kernfs_root *kf_root, int *flags, char *data)
+static int cgroup_reconfigure(struct fs_context *fc)
 {
-	unsigned int root_flags;
-	int ret;
-
-	ret = parse_cgroup_root_flags(data, &root_flags);
-	if (ret)
-		return ret;
+	struct cgroup_fs_context *ctx = cgroup_fc2context(fc);
 
-	apply_cgroup_root_flags(root_flags);
+	apply_cgroup_root_flags(ctx->flags);
 	return 0;
 }
 
@@ -1908,8 +1915,9 @@ static void init_cgroup_housekeeping(struct cgroup *cgrp)
 	INIT_WORK(&cgrp->release_agent_work, cgroup1_release_agent);
 }
 
-void init_cgroup_root(struct cgroup_root *root, struct cgroup_sb_opts *opts)
+void init_cgroup_root(struct cgroup_fs_context *ctx)
 {
+	struct cgroup_root *root = ctx->root;
 	struct cgroup *cgrp = &root->cgrp;
 
 	INIT_LIST_HEAD(&root->root_list);
@@ -1918,16 +1926,16 @@ void init_cgroup_root(struct cgroup_root *root, struct cgroup_sb_opts *opts)
 	init_cgroup_housekeeping(cgrp);
 	idr_init(&root->cgroup_idr);
 
-	root->flags = opts->flags;
-	if (opts->release_agent)
-		strscpy(root->release_agent_path, opts->release_agent, PATH_MAX);
-	if (opts->name)
-		strscpy(root->name, opts->name, MAX_CGROUP_ROOT_NAMELEN);
-	if (opts->cpuset_clone_children)
+	root->flags = ctx->flags;
+	if (ctx->release_agent)
+		strscpy(root->release_agent_path, ctx->release_agent, PATH_MAX);
+	if (ctx->name)
+		strscpy(root->name, ctx->name, MAX_CGROUP_ROOT_NAMELEN);
+	if (ctx->cpuset_clone_children)
 		set_bit(CGRP_CPUSET_CLONE_CHILDREN, &root->cgrp.flags);
 }
 
-int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask, int ref_flags)
+int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask)
 {
 	LIST_HEAD(tmp_links);
 	struct cgroup *root_cgrp = &root->cgrp;
@@ -1944,7 +1952,7 @@ int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask, int ref_flags)
 	root_cgrp->ancestor_ids[0] = ret;
 
 	ret = percpu_ref_init(&root_cgrp->self.refcnt, css_release,
-			      ref_flags, GFP_KERNEL);
+			      0, GFP_KERNEL);
 	if (ret)
 		goto out;
 
@@ -2028,57 +2036,104 @@ out:
 	return ret;
 }
 
-struct dentry *cgroup_do_mount(struct file_system_type *fs_type, int flags,
-			       struct cgroup_root *root, unsigned long magic,
-			       struct cgroup_namespace *ns)
+int cgroup_do_get_tree(struct fs_context *fc)
 {
-	struct dentry *dentry;
-	bool new_sb;
+	struct cgroup_fs_context *ctx = cgroup_fc2context(fc);
+	int ret;
 
-	dentry = kernfs_mount(fs_type, flags, root->kf_root, magic, &new_sb);
+	ctx->kfc.root = ctx->root->kf_root;
+	if (fc->fs_type == &cgroup2_fs_type)
+		ctx->kfc.magic = CGROUP2_SUPER_MAGIC;
+	else
+		ctx->kfc.magic = CGROUP_SUPER_MAGIC;
+	ret = kernfs_get_tree(fc);
 
 	/*
 	 * In non-init cgroup namespace, instead of root cgroup's dentry,
 	 * we return the dentry corresponding to the cgroupns->root_cgrp.
 	 */
-	if (!IS_ERR(dentry) && ns != &init_cgroup_ns) {
+	if (!ret && ctx->ns != &init_cgroup_ns) {
 		struct dentry *nsdentry;
+		struct super_block *sb = fc->root->d_sb;
 		struct cgroup *cgrp;
 
 		mutex_lock(&cgroup_mutex);
 		spin_lock_irq(&css_set_lock);
 
-		cgrp = cset_cgroup_from_root(ns->root_cset, root);
+		cgrp = cset_cgroup_from_root(ctx->ns->root_cset, ctx->root);
 
 		spin_unlock_irq(&css_set_lock);
 		mutex_unlock(&cgroup_mutex);
 
-		nsdentry = kernfs_node_dentry(cgrp->kn, dentry->d_sb);
-		dput(dentry);
-		dentry = nsdentry;
+		nsdentry = kernfs_node_dentry(cgrp->kn, sb);
+		dput(fc->root);
+		fc->root = nsdentry;
+		if (IS_ERR(nsdentry)) {
+			ret = PTR_ERR(nsdentry);
+			deactivate_locked_super(sb);
+		}
 	}
 
-	if (IS_ERR(dentry) || !new_sb)
-		cgroup_put(&root->cgrp);
+	if (!ctx->kfc.new_sb_created)
+		cgroup_put(&ctx->root->cgrp);
 
-	return dentry;
+	return ret;
 }
 
-static struct dentry *cgroup_mount(struct file_system_type *fs_type,
-			 int flags, const char *unused_dev_name,
-			 void *data)
+/*
+ * Destroy a cgroup filesystem context.
+ */
+static void cgroup_fs_context_free(struct fs_context *fc)
 {
-	struct cgroup_namespace *ns = current->nsproxy->cgroup_ns;
-	struct dentry *dentry;
+	struct cgroup_fs_context *ctx = cgroup_fc2context(fc);
+
+	kfree(ctx->name);
+	kfree(ctx->release_agent);
+	put_cgroup_ns(ctx->ns);
+	kernfs_free_fs_context(fc);
+	kfree(ctx);
+}
+
+static int cgroup_get_tree(struct fs_context *fc)
+{
+	struct cgroup_fs_context *ctx = cgroup_fc2context(fc);
 	int ret;
 
-	get_cgroup_ns(ns);
+	cgrp_dfl_visible = true;
+	cgroup_get_live(&cgrp_dfl_root.cgrp);
+	ctx->root = &cgrp_dfl_root;
 
-	/* 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);
-	}
+	ret = cgroup_do_get_tree(fc);
+	if (!ret)
+		apply_cgroup_root_flags(ctx->flags);
+	return ret;
+}
+
+static const struct fs_context_operations cgroup_fs_context_ops = {
+	.free		= cgroup_fs_context_free,
+	.parse_param	= cgroup2_parse_param,
+	.get_tree	= cgroup_get_tree,
+	.reconfigure	= cgroup_reconfigure,
+};
+
+static const struct fs_context_operations cgroup1_fs_context_ops = {
+	.free		= cgroup_fs_context_free,
+	.parse_param	= cgroup1_parse_param,
+	.get_tree	= cgroup1_get_tree,
+	.reconfigure	= cgroup1_reconfigure,
+};
+
+/*
+ * Initialise the cgroup filesystem creation/reconfiguration context.  Notably,
+ * we select the namespace we're going to use.
+ */
+static int cgroup_init_fs_context(struct fs_context *fc)
+{
+	struct cgroup_fs_context *ctx;
+
+	ctx = kzalloc(sizeof(struct cgroup_fs_context), GFP_KERNEL);
+	if (!ctx)
+		return -ENOMEM;
 
 	/*
 	 * The first time anyone tries to mount a cgroup, enable the list
@@ -2087,29 +2142,18 @@ static struct dentry *cgroup_mount(struct file_system_type *fs_type,
 	if (!use_task_css_set_links)
 		cgroup_enable_task_cg_lists();
 
-	if (fs_type == &cgroup2_fs_type) {
-		unsigned int root_flags;
-
-		ret = parse_cgroup_root_flags(data, &root_flags);
-		if (ret) {
-			put_cgroup_ns(ns);
-			return ERR_PTR(ret);
-		}
-
-		cgrp_dfl_visible = true;
-		cgroup_get_live(&cgrp_dfl_root.cgrp);
-
-		dentry = cgroup_do_mount(&cgroup2_fs_type, flags, &cgrp_dfl_root,
-					 CGROUP2_SUPER_MAGIC, ns);
-		if (!IS_ERR(dentry))
-			apply_cgroup_root_flags(root_flags);
-	} else {
-		dentry = cgroup1_mount(&cgroup_fs_type, flags, data,
-				       CGROUP_SUPER_MAGIC, ns);
-	}
-
-	put_cgroup_ns(ns);
-	return dentry;
+	ctx->ns = current->nsproxy->cgroup_ns;
+	get_cgroup_ns(ctx->ns);
+	fc->fs_private = &ctx->kfc;
+	if (fc->fs_type == &cgroup2_fs_type)
+		fc->ops = &cgroup_fs_context_ops;
+	else
+		fc->ops = &cgroup1_fs_context_ops;
+	if (fc->user_ns)
+		put_user_ns(fc->user_ns);
+	fc->user_ns = get_user_ns(ctx->ns->user_ns);
+	fc->global = true;
+	return 0;
 }
 
 static void cgroup_kill_sb(struct super_block *sb)
@@ -2118,33 +2162,33 @@ static void cgroup_kill_sb(struct super_block *sb)
 	struct cgroup_root *root = cgroup_root_from_kf(kf_root);
 
 	/*
-	 * If @root doesn't have any mounts or children, start killing it.
+	 * If @root doesn't have any children, start killing it.
 	 * This prevents new mounts by disabling percpu_ref_tryget_live().
 	 * cgroup_mount() may wait for @root's release.
 	 *
 	 * And don't kill the default root.
 	 */
-	if (!list_empty(&root->cgrp.self.children) ||
-	    root == &cgrp_dfl_root)
-		cgroup_put(&root->cgrp);
-	else
+	if (list_empty(&root->cgrp.self.children) && root != &cgrp_dfl_root &&
+	    !percpu_ref_is_dying(&root->cgrp.self.refcnt))
 		percpu_ref_kill(&root->cgrp.self.refcnt);
-
+	cgroup_put(&root->cgrp);
 	kernfs_kill_sb(sb);
 }
 
 struct file_system_type cgroup_fs_type = {
-	.name = "cgroup",
-	.mount = cgroup_mount,
-	.kill_sb = cgroup_kill_sb,
-	.fs_flags = FS_USERNS_MOUNT,
+	.name			= "cgroup",
+	.init_fs_context	= cgroup_init_fs_context,
+	.parameters		= &cgroup1_fs_parameters,
+	.kill_sb		= cgroup_kill_sb,
+	.fs_flags		= FS_USERNS_MOUNT,
 };
 
 static struct file_system_type cgroup2_fs_type = {
-	.name = "cgroup2",
-	.mount = cgroup_mount,
-	.kill_sb = cgroup_kill_sb,
-	.fs_flags = FS_USERNS_MOUNT,
+	.name			= "cgroup2",
+	.init_fs_context	= cgroup_init_fs_context,
+	.parameters		= &cgroup2_fs_parameters,
+	.kill_sb		= cgroup_kill_sb,
+	.fs_flags		= FS_USERNS_MOUNT,
 };
 
 int cgroup_path_ns_locked(struct cgroup *cgrp, char *buf, size_t buflen,
@@ -3533,6 +3577,16 @@ static ssize_t cgroup_file_write(struct kernfs_open_file *of, char *buf,
 	return ret ?: nbytes;
 }
 
+static __poll_t cgroup_file_poll(struct kernfs_open_file *of, poll_table *pt)
+{
+	struct cftype *cft = of->kn->priv;
+
+	if (cft->poll)
+		return cft->poll(of, pt);
+
+	return kernfs_generic_poll(of, pt);
+}
+
 static void *cgroup_seqfile_start(struct seq_file *seq, loff_t *ppos)
 {
 	return seq_cft(seq)->seq_start(seq, ppos);
@@ -3571,6 +3625,7 @@ static struct kernfs_ops cgroup_kf_single_ops = {
 	.open			= cgroup_file_open,
 	.release		= cgroup_file_release,
 	.write			= cgroup_file_write,
+	.poll			= cgroup_file_poll,
 	.seq_show		= cgroup_seqfile_show,
 };
 
@@ -3579,6 +3634,7 @@ static struct kernfs_ops cgroup_kf_ops = {
 	.open			= cgroup_file_open,
 	.release		= cgroup_file_release,
 	.write			= cgroup_file_write,
+	.poll			= cgroup_file_poll,
 	.seq_start		= cgroup_seqfile_start,
 	.seq_next		= cgroup_seqfile_next,
 	.seq_stop		= cgroup_seqfile_stop,
@@ -5267,7 +5323,6 @@ int cgroup_rmdir(struct kernfs_node *kn)
 
 static struct kernfs_syscall_ops cgroup_kf_syscall_ops = {
 	.show_options		= cgroup_show_options,
-	.remount_fs		= cgroup_remount,
 	.mkdir			= cgroup_mkdir,
 	.rmdir			= cgroup_rmdir,
 	.show_path		= cgroup_show_path,
@@ -5313,7 +5368,7 @@ static void __init cgroup_init_subsys(struct cgroup_subsys *ss, bool early)
 
 	have_fork_callback |= (bool)ss->fork << ss->id;
 	have_exit_callback |= (bool)ss->exit << ss->id;
-	have_free_callback |= (bool)ss->free << ss->id;
+	have_release_callback |= (bool)ss->release << ss->id;
 	have_canfork_callback |= (bool)ss->can_fork << ss->id;
 
 	/* At system boot, before all subsystems have been
@@ -5334,11 +5389,12 @@ static void __init cgroup_init_subsys(struct cgroup_subsys *ss, bool early)
  */
 int __init cgroup_init_early(void)
 {
-	static struct cgroup_sb_opts __initdata opts;
+	static struct cgroup_fs_context __initdata ctx;
 	struct cgroup_subsys *ss;
 	int i;
 
-	init_cgroup_root(&cgrp_dfl_root, &opts);
+	ctx.root = &cgrp_dfl_root;
+	init_cgroup_root(&ctx);
 	cgrp_dfl_root.cgrp.self.flags |= CSS_NO_REF;
 
 	RCU_INIT_POINTER(init_task.cgroups, &init_css_set);
@@ -5399,7 +5455,7 @@ int __init cgroup_init(void)
 	hash_add(css_set_table, &init_css_set.hlist,
 		 css_set_hash(init_css_set.subsys));
 
-	BUG_ON(cgroup_setup_root(&cgrp_dfl_root, 0, 0));
+	BUG_ON(cgroup_setup_root(&cgrp_dfl_root, 0));
 
 	mutex_unlock(&cgroup_mutex);
 
@@ -5749,16 +5805,19 @@ void cgroup_exit(struct task_struct *tsk)
 	} while_each_subsys_mask();
 }
 
-void cgroup_free(struct task_struct *task)
+void cgroup_release(struct task_struct *task)
 {
-	struct css_set *cset = task_css_set(task);
 	struct cgroup_subsys *ss;
 	int ssid;
 
-	do_each_subsys_mask(ss, ssid, have_free_callback) {
-		ss->free(task);
+	do_each_subsys_mask(ss, ssid, have_release_callback) {
+		ss->release(task);
 	} while_each_subsys_mask();
+}
 
+void cgroup_free(struct task_struct *task)
+{
+	struct css_set *cset = task_css_set(task);
 	put_css_set(cset);
 }
 
@@ -5996,7 +6055,7 @@ int cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog,
 	int ret;
 
 	mutex_lock(&cgroup_mutex);
-	ret = __cgroup_bpf_detach(cgrp, prog, type, flags);
+	ret = __cgroup_bpf_detach(cgrp, prog, type);
 	mutex_unlock(&cgroup_mutex);
 	return ret;
 }