Merge tag 'v5.1' into next

Sync up with mainline to bring in the latest APIs.

8 files changed, 1426 insertions, 478 deletions

diff --git a/kernel/cgroup/cgroup-internal.h b/kernel/cgroup/cgroup-internal.h
index 75568fcf2180..30e39f3932ad 100644
--- a/kernel/cgroup/cgroup-internal.h
+++ b/kernel/cgroup/cgroup-internal.h
@@ -7,10 +7,13 @@
 #include <linux/workqueue.h>
 #include <linux/list.h>
 #include <linux/refcount.h>
+#include <linux/fs_context.h>
 
 #define TRACE_CGROUP_PATH_LEN 1024
 extern spinlock_t trace_cgroup_path_lock;
 extern char trace_cgroup_path[TRACE_CGROUP_PATH_LEN];
+extern bool cgroup_debug;
+extern void __init enable_debug_cgroup(void);
 
 /*
  * cgroup_path() takes a spin lock. It is good practice not to take
@@ -35,6 +38,31 @@ extern char trace_cgroup_path[TRACE_CGROUP_PATH_LEN];
 	} while (0)
 
 /*
+ * The cgroup filesystem superblock creation/mount context.
+ */
+struct cgroup_fs_context {
+	struct kernfs_fs_context kfc;
+	struct cgroup_root	*root;
+	struct cgroup_namespace	*ns;
+	unsigned int	flags;			/* CGRP_ROOT_* flags */
+
+	/* cgroup1 bits */
+	bool		cpuset_clone_children;
+	bool		none;			/* User explicitly requested empty subsystem */
+	bool		all_ss;			/* Seen 'all' option */
+	u16		subsys_mask;		/* Selected subsystems */
+	char		*name;			/* Hierarchy name */
+	char		*release_agent;		/* Path for release notifications */
+};
+
+static inline struct cgroup_fs_context *cgroup_fc2context(struct fs_context *fc)
+{
+	struct kernfs_fs_context *kfc = fc->fs_private;
+
+	return container_of(kfc, struct cgroup_fs_context, kfc);
+}
+
+/*
  * A cgroup can be associated with multiple css_sets as different tasks may
  * belong to different cgroups on different hierarchies.  In the other
  * direction, a css_set is naturally associated with multiple cgroups.
@@ -115,16 +143,6 @@ struct cgroup_mgctx {
 #define DEFINE_CGROUP_MGCTX(name)						\
 	struct cgroup_mgctx name = CGROUP_MGCTX_INIT(name)
 
-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 mutex cgroup_mutex;
 extern spinlock_t css_set_lock;
 extern struct cgroup_subsys *cgroup_subsys[];
@@ -195,12 +213,10 @@ 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 ref_flags);
+void init_cgroup_root(struct cgroup_fs_context *ctx);
+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);
+int cgroup_do_get_tree(struct fs_context *fc);
 
 int cgroup_migrate_vet_dst(struct cgroup *dst_cgrp);
 void cgroup_migrate_finish(struct cgroup_mgctx *mgctx);
@@ -244,14 +260,15 @@ extern const struct proc_ns_operations cgroupns_operations;
  */
 extern struct cftype cgroup1_base_files[];
 extern struct kernfs_syscall_ops cgroup1_kf_syscall_ops;
+extern const struct fs_parameter_description cgroup1_fs_parameters;
 
 int proc_cgroupstats_show(struct seq_file *m, void *v);
 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);
+int cgroup1_parse_param(struct fs_context *fc, struct fs_parameter *param);
+int cgroup1_get_tree(struct fs_context *fc);
+int cgroup1_reconfigure(struct fs_context *ctx);
 
 #endif /* __CGROUP_INTERNAL_H */
diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c
index 51063e7a93c2..c126b34fd4ff 100644
--- a/kernel/cgroup/cgroup-v1.c
+++ b/kernel/cgroup/cgroup-v1.c
@@ -13,9 +13,12 @@
 #include <linux/delayacct.h>
 #include <linux/pid_namespace.h>
 #include <linux/cgroupstats.h>
+#include <linux/fs_parser.h>
 
 #include <trace/events/cgroup.h>
 
+#define cg_invalf(fc, fmt, ...) invalf(fc, fmt, ## __VA_ARGS__)
+
 /*
  * pidlists linger the following amount before being destroyed.  The goal
  * is avoiding frequent destruction in the middle of consecutive read calls
@@ -27,6 +30,9 @@
 /* Controllers blocked by the commandline in v1 */
 static u16 cgroup_no_v1_mask;
 
+/* disable named v1 mounts */
+static bool cgroup_no_v1_named;
+
 /*
  * pidlist destructions need to be flushed on cgroup destruction.  Use a
  * separate workqueue as flush domain.
@@ -903,168 +909,195 @@ static int cgroup1_show_options(struct seq_file *seq, struct kernfs_root *kf_roo
 	return 0;
 }
 
-static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts)
-{
-	char *token, *o = data;
-	bool all_ss = false, one_ss = false;
-	u16 mask = U16_MAX;
-	struct cgroup_subsys *ss;
-	int nr_opts = 0;
-	int i;
-
-#ifdef CONFIG_CPUSETS
-	mask = ~((u16)1 << cpuset_cgrp_id);
-#endif
-
-	memset(opts, 0, sizeof(*opts));
+enum cgroup1_param {
+	Opt_all,
+	Opt_clone_children,
+	Opt_cpuset_v2_mode,
+	Opt_name,
+	Opt_none,
+	Opt_noprefix,
+	Opt_release_agent,
+	Opt_xattr,
+};
 
-	while ((token = strsep(&o, ",")) != NULL) {
-		nr_opts++;
+static const struct fs_parameter_spec cgroup1_param_specs[] = {
+	fsparam_flag  ("all",		Opt_all),
+	fsparam_flag  ("clone_children", Opt_clone_children),
+	fsparam_flag  ("cpuset_v2_mode", Opt_cpuset_v2_mode),
+	fsparam_string("name",		Opt_name),
+	fsparam_flag  ("none",		Opt_none),
+	fsparam_flag  ("noprefix",	Opt_noprefix),
+	fsparam_string("release_agent",	Opt_release_agent),
+	fsparam_flag  ("xattr",		Opt_xattr),
+	{}
+};
 
-		if (!*token)
-			return -EINVAL;
-		if (!strcmp(token, "none")) {
-			/* Explicitly have no subsystems */
-			opts->none = true;
-			continue;
-		}
-		if (!strcmp(token, "all")) {
-			/* Mutually exclusive option 'all' + subsystem name */
-			if (one_ss)
-				return -EINVAL;
-			all_ss = true;
-			continue;
-		}
-		if (!strcmp(token, "noprefix")) {
-			opts->flags |= CGRP_ROOT_NOPREFIX;
-			continue;
-		}
-		if (!strcmp(token, "clone_children")) {
-			opts->cpuset_clone_children = true;
-			continue;
-		}
-		if (!strcmp(token, "cpuset_v2_mode")) {
-			opts->flags |= CGRP_ROOT_CPUSET_V2_MODE;
-			continue;
-		}
-		if (!strcmp(token, "xattr")) {
-			opts->flags |= CGRP_ROOT_XATTR;
-			continue;
-		}
-		if (!strncmp(token, "release_agent=", 14)) {
-			/* Specifying two release agents is forbidden */
-			if (opts->release_agent)
-				return -EINVAL;
-			opts->release_agent =
-				kstrndup(token + 14, PATH_MAX - 1, GFP_KERNEL);
-			if (!opts->release_agent)
-				return -ENOMEM;
-			continue;
-		}
-		if (!strncmp(token, "name=", 5)) {
-			const char *name = token + 5;
-			/* Can't specify an empty name */
-			if (!strlen(name))
-				return -EINVAL;
-			/* Must match [\w.-]+ */
-			for (i = 0; i < strlen(name); i++) {
-				char c = name[i];
-				if (isalnum(c))
-					continue;
-				if ((c == '.') || (c == '-') || (c == '_'))
-					continue;
-				return -EINVAL;
-			}
-			/* Specifying two names is forbidden */
-			if (opts->name)
-				return -EINVAL;
-			opts->name = kstrndup(name,
-					      MAX_CGROUP_ROOT_NAMELEN - 1,
-					      GFP_KERNEL);
-			if (!opts->name)
-				return -ENOMEM;
+const struct fs_parameter_description cgroup1_fs_parameters = {
+	.name		= "cgroup1",
+	.specs		= cgroup1_param_specs,
+};
 
-			continue;
+int cgroup1_parse_param(struct fs_context *fc, struct fs_parameter *param)
+{
+	struct cgroup_fs_context *ctx = cgroup_fc2context(fc);
+	struct cgroup_subsys *ss;
+	struct fs_parse_result result;
+	int opt, i;
+
+	opt = fs_parse(fc, &cgroup1_fs_parameters, param, &result);
+	if (opt == -ENOPARAM) {
+		if (strcmp(param->key, "source") == 0) {
+			fc->source = param->string;
+			param->string = NULL;
+			return 0;
 		}
-
 		for_each_subsys(ss, i) {
-			if (strcmp(token, ss->legacy_name))
+			if (strcmp(param->key, ss->legacy_name))
 				continue;
-			if (!cgroup_ssid_enabled(i))
+			ctx->subsys_mask |= (1 << i);
+			return 0;
+		}
+		return cg_invalf(fc, "cgroup1: Unknown subsys name '%s'", param->key);
+	}
+	if (opt < 0)
+		return opt;
+
+	switch (opt) {
+	case Opt_none:
+		/* Explicitly have no subsystems */
+		ctx->none = true;
+		break;
+	case Opt_all:
+		ctx->all_ss = true;
+		break;
+	case Opt_noprefix:
+		ctx->flags |= CGRP_ROOT_NOPREFIX;
+		break;
+	case Opt_clone_children:
+		ctx->cpuset_clone_children = true;
+		break;
+	case Opt_cpuset_v2_mode:
+		ctx->flags |= CGRP_ROOT_CPUSET_V2_MODE;
+		break;
+	case Opt_xattr:
+		ctx->flags |= CGRP_ROOT_XATTR;
+		break;
+	case Opt_release_agent:
+		/* Specifying two release agents is forbidden */
+		if (ctx->release_agent)
+			return cg_invalf(fc, "cgroup1: release_agent respecified");
+		ctx->release_agent = param->string;
+		param->string = NULL;
+		break;
+	case Opt_name:
+		/* blocked by boot param? */
+		if (cgroup_no_v1_named)
+			return -ENOENT;
+		/* Can't specify an empty name */
+		if (!param->size)
+			return cg_invalf(fc, "cgroup1: Empty name");
+		if (param->size > MAX_CGROUP_ROOT_NAMELEN - 1)
+			return cg_invalf(fc, "cgroup1: Name too long");
+		/* Must match [\w.-]+ */
+		for (i = 0; i < param->size; i++) {
+			char c = param->string[i];
+			if (isalnum(c))
 				continue;
-			if (cgroup1_ssid_disabled(i))
+			if ((c == '.') || (c == '-') || (c == '_'))
 				continue;
-
-			/* Mutually exclusive option 'all' + subsystem name */
-			if (all_ss)
-				return -EINVAL;
-			opts->subsys_mask |= (1 << i);
-			one_ss = true;
-
-			break;
+			return cg_invalf(fc, "cgroup1: Invalid name");
 		}
-		if (i == CGROUP_SUBSYS_COUNT)
-			return -ENOENT;
+		/* Specifying two names is forbidden */
+		if (ctx->name)
+			return cg_invalf(fc, "cgroup1: name respecified");
+		ctx->name = param->string;
+		param->string = NULL;
+		break;
 	}
+	return 0;
+}
+
+static int check_cgroupfs_options(struct fs_context *fc)
+{
+	struct cgroup_fs_context *ctx = cgroup_fc2context(fc);
+	u16 mask = U16_MAX;
+	u16 enabled = 0;
+	struct cgroup_subsys *ss;
+	int i;
+
+#ifdef CONFIG_CPUSETS
+	mask = ~((u16)1 << cpuset_cgrp_id);
+#endif
+	for_each_subsys(ss, i)
+		if (cgroup_ssid_enabled(i) && !cgroup1_ssid_disabled(i))
+			enabled |= 1 << i;
+
+	ctx->subsys_mask &= enabled;
 
 	/*
-	 * If the 'all' option was specified select all the subsystems,
-	 * otherwise if 'none', 'name=' and a subsystem name options were
-	 * not specified, let's default to 'all'
+	 * In absense of 'none', 'name=' or subsystem name options,
+	 * let's default to 'all'.
 	 */
-	if (all_ss || (!one_ss && !opts->none && !opts->name))
-		for_each_subsys(ss, i)
-			if (cgroup_ssid_enabled(i) && !cgroup1_ssid_disabled(i))
-				opts->subsys_mask |= (1 << i);
+	if (!ctx->subsys_mask && !ctx->none && !ctx->name)
+		ctx->all_ss = true;
+
+	if (ctx->all_ss) {
+		/* Mutually exclusive option 'all' + subsystem name */
+		if (ctx->subsys_mask)
+			return cg_invalf(fc, "cgroup1: subsys name conflicts with all");
+		/* 'all' => select all the subsystems */
+		ctx->subsys_mask = enabled;
+	}
 
 	/*
 	 * We either have to specify by name or by subsystems. (So all
 	 * empty hierarchies must have a name).
 	 */
-	if (!opts->subsys_mask && !opts->name)
-		return -EINVAL;
+	if (!ctx->subsys_mask && !ctx->name)
+		return cg_invalf(fc, "cgroup1: Need name or subsystem set");
 
 	/*
 	 * Option noprefix was introduced just for backward compatibility
 	 * with the old cpuset, so we allow noprefix only if mounting just
 	 * the cpuset subsystem.
 	 */
-	if ((opts->flags & CGRP_ROOT_NOPREFIX) && (opts->subsys_mask & mask))
-		return -EINVAL;
+	if ((ctx->flags & CGRP_ROOT_NOPREFIX) && (ctx->subsys_mask & mask))
+		return cg_invalf(fc, "cgroup1: noprefix used incorrectly");
 
 	/* Can't specify "none" and some subsystems */
-	if (opts->subsys_mask && opts->none)
-		return -EINVAL;
+	if (ctx->subsys_mask && ctx->none)
+		return cg_invalf(fc, "cgroup1: none used incorrectly");
 
 	return 0;
 }
 
-static int cgroup1_remount(struct kernfs_root *kf_root, int *flags, char *data)
+int cgroup1_reconfigure(struct fs_context *fc)
 {
-	int ret = 0;
+	struct cgroup_fs_context *ctx = cgroup_fc2context(fc);
+	struct kernfs_root *kf_root = kernfs_root_from_sb(fc->root->d_sb);
 	struct cgroup_root *root = cgroup_root_from_kf(kf_root);
-	struct cgroup_sb_opts opts;
+	int ret = 0;
 	u16 added_mask, removed_mask;
 
 	cgroup_lock_and_drain_offline(&cgrp_dfl_root.cgrp);
 
 	/* See what subsystems are wanted */
-	ret = parse_cgroupfs_options(data, &opts);
+	ret = check_cgroupfs_options(fc);
 	if (ret)
 		goto out_unlock;
 
-	if (opts.subsys_mask != root->subsys_mask || opts.release_agent)
+	if (ctx->subsys_mask != root->subsys_mask || ctx->release_agent)
 		pr_warn("option changes via remount are deprecated (pid=%d comm=%s)\n",
 			task_tgid_nr(current), current->comm);
 
-	added_mask = opts.subsys_mask & ~root->subsys_mask;
-	removed_mask = root->subsys_mask & ~opts.subsys_mask;
+	added_mask = ctx->subsys_mask & ~root->subsys_mask;
+	removed_mask = root->subsys_mask & ~ctx->subsys_mask;
 
 	/* Don't allow flags or name to change at remount */
-	if ((opts.flags ^ root->flags) ||
-	    (opts.name && strcmp(opts.name, root->name))) {
-		pr_err("option or name mismatch, new: 0x%x \"%s\", old: 0x%x \"%s\"\n",
-		       opts.flags, opts.name ?: "", root->flags, root->name);
+	if ((ctx->flags ^ root->flags) ||
+	    (ctx->name && strcmp(ctx->name, root->name))) {
+		cg_invalf(fc, "option or name mismatch, new: 0x%x \"%s\", old: 0x%x \"%s\"",
+		       ctx->flags, ctx->name ?: "", root->flags, root->name);
 		ret = -EINVAL;
 		goto out_unlock;
 	}
@@ -1081,17 +1114,15 @@ static int cgroup1_remount(struct kernfs_root *kf_root, int *flags, char *data)
 
 	WARN_ON(rebind_subsystems(&cgrp_dfl_root, removed_mask));
 
-	if (opts.release_agent) {
+	if (ctx->release_agent) {
 		spin_lock(&release_agent_path_lock);
-		strcpy(root->release_agent_path, opts.release_agent);
+		strcpy(root->release_agent_path, ctx->release_agent);
 		spin_unlock(&release_agent_path_lock);
 	}
 
 	trace_cgroup_remount(root);
 
  out_unlock:
-	kfree(opts.release_agent);
-	kfree(opts.name);
 	mutex_unlock(&cgroup_mutex);
 	return ret;
 }
@@ -1099,30 +1130,30 @@ static int cgroup1_remount(struct kernfs_root *kf_root, int *flags, char *data)
 struct kernfs_syscall_ops cgroup1_kf_syscall_ops = {
 	.rename			= cgroup1_rename,
 	.show_options		= cgroup1_show_options,
-	.remount_fs		= cgroup1_remount,
 	.mkdir			= cgroup_mkdir,
 	.rmdir			= cgroup_rmdir,
 	.show_path		= cgroup_show_path,
 };
 
-struct dentry *cgroup1_mount(struct file_system_type *fs_type, int flags,
-			     void *data, unsigned long magic,
-			     struct cgroup_namespace *ns)
+/*
+ * The guts of cgroup1 mount - find or create cgroup_root to use.
+ * Called with cgroup_mutex held; returns 0 on success, -E... on
+ * error and positive - in case when the candidate is busy dying.
+ * On success it stashes a reference to cgroup_root into given
+ * cgroup_fs_context; that reference is *NOT* counting towards the
+ * cgroup_root refcount.
+ */
+static int cgroup1_root_to_use(struct fs_context *fc)
 {
-	struct super_block *pinned_sb = NULL;
-	struct cgroup_sb_opts opts;
+	struct cgroup_fs_context *ctx = cgroup_fc2context(fc);
 	struct cgroup_root *root;
 	struct cgroup_subsys *ss;
-	struct dentry *dentry;
 	int i, ret;
-	bool new_root = false;
-
-	cgroup_lock_and_drain_offline(&cgrp_dfl_root.cgrp);
 
 	/* First find the desired set of subsystems */
-	ret = parse_cgroupfs_options(data, &opts);
+	ret = check_cgroupfs_options(fc);
 	if (ret)
-		goto out_unlock;
+		return ret;
 
 	/*
 	 * Destruction of cgroup root is asynchronous, so subsystems may
@@ -1132,16 +1163,12 @@ struct dentry *cgroup1_mount(struct file_system_type *fs_type, int flags,
 	 * starting.  Testing ref liveliness is good enough.
 	 */
 	for_each_subsys(ss, i) {
-		if (!(opts.subsys_mask & (1 << i)) ||
+		if (!(ctx->subsys_mask & (1 << i)) ||
 		    ss->root == &cgrp_dfl_root)
 			continue;
 
-		if (!percpu_ref_tryget_live(&ss->root->cgrp.self.refcnt)) {
-			mutex_unlock(&cgroup_mutex);
-			msleep(10);
-			ret = restart_syscall();
-			goto out_free;
-		}
+		if (!percpu_ref_tryget_live(&ss->root->cgrp.self.refcnt))
+			return 1;	/* restart */
 		cgroup_put(&ss->root->cgrp);
 	}
 
@@ -1156,8 +1183,8 @@ struct dentry *cgroup1_mount(struct file_system_type *fs_type, int flags,
 		 * name matches but sybsys_mask doesn't, we should fail.
 		 * Remember whether name matched.
 		 */
-		if (opts.name) {
-			if (strcmp(opts.name, root->name))
+		if (ctx->name) {
+			if (strcmp(ctx->name, root->name))
 				continue;
 			name_match = true;
 		}
@@ -1166,42 +1193,18 @@ struct dentry *cgroup1_mount(struct file_system_type *fs_type, int flags,
 		 * If we asked for subsystems (or explicitly for no
 		 * subsystems) then they must match.
 		 */
-		if ((opts.subsys_mask || opts.none) &&
-		    (opts.subsys_mask != root->subsys_mask)) {
+		if ((ctx->subsys_mask || ctx->none) &&
+		    (ctx->subsys_mask != root->subsys_mask)) {
 			if (!name_match)
 				continue;
-			ret = -EBUSY;
-			goto out_unlock;
+			return -EBUSY;
 		}
 
-		if (root->flags ^ opts.flags)
+		if (root->flags ^ ctx->flags)
 			pr_warn("new mount options do not match the existing superblock, will be ignored\n");
 
-		/*
-		 * We want to reuse @root whose lifetime is governed by its
-		 * ->cgrp.  Let's check whether @root is alive and keep it
-		 * that way.  As cgroup_kill_sb() can happen anytime, we
-		 * want to block it by pinning the sb so that @root doesn't
-		 * get killed before mount is complete.
-		 *
-		 * With the sb pinned, tryget_live can reliably indicate
-		 * whether @root can be reused.  If it's being killed,
-		 * drain it.  We can use wait_queue for the wait but this
-		 * path is super cold.  Let's just sleep a bit and retry.
-		 */
-		pinned_sb = kernfs_pin_sb(root->kf_root, NULL);
-		if (IS_ERR(pinned_sb) ||
-		    !percpu_ref_tryget_live(&root->cgrp.self.refcnt)) {
-			mutex_unlock(&cgroup_mutex);
-			if (!IS_ERR_OR_NULL(pinned_sb))
-				deactivate_super(pinned_sb);
-			msleep(10);
-			ret = restart_syscall();
-			goto out_free;
-		}
-
-		ret = 0;
-		goto out_unlock;
+		ctx->root = root;
+		return 0;
 	}
 
 	/*
@@ -1209,62 +1212,58 @@ struct dentry *cgroup1_mount(struct file_system_type *fs_type, int flags,
 	 * specification is allowed for already existing hierarchies but we
 	 * can't create new one without subsys specification.
 	 */
-	if (!opts.subsys_mask && !opts.none) {
-		ret = -EINVAL;
-		goto out_unlock;
-	}
+	if (!ctx->subsys_mask && !ctx->none)
+		return cg_invalf(fc, "cgroup1: No subsys list or none specified");
 
 	/* Hierarchies may only be created in the initial cgroup namespace. */
-	if (ns != &init_cgroup_ns) {
-		ret = -EPERM;
-		goto out_unlock;
-	}
+	if (ctx->ns != &init_cgroup_ns)
+		return -EPERM;
 
 	root = kzalloc(sizeof(*root), GFP_KERNEL);
-	if (!root) {
-		ret = -ENOMEM;
-		goto out_unlock;
-	}
-	new_root = true;
+	if (!root)
+		return -ENOMEM;
 
-	init_cgroup_root(root, &opts);
+	ctx->root = root;
+	init_cgroup_root(ctx);
 
-	ret = cgroup_setup_root(root, opts.subsys_mask, PERCPU_REF_INIT_DEAD);
+	ret = cgroup_setup_root(root, ctx->subsys_mask);
 	if (ret)
 		cgroup_free_root(root);
+	return ret;
+}
 
-out_unlock:
-	mutex_unlock(&cgroup_mutex);
-out_free:
-	kfree(opts.release_agent);
-	kfree(opts.name);
+int cgroup1_get_tree(struct fs_context *fc)
+{
+	struct cgroup_fs_context *ctx = cgroup_fc2context(fc);
+	int ret;
 
-	if (ret)
-		return ERR_PTR(ret);
+	/* Check if the caller has permission to mount. */
+	if (!ns_capable(ctx->ns->user_ns, CAP_SYS_ADMIN))
+		return -EPERM;
 
-	dentry = cgroup_do_mount(&cgroup_fs_type, flags, root,
-				 CGROUP_SUPER_MAGIC, ns);
+	cgroup_lock_and_drain_offline(&cgrp_dfl_root.cgrp);
 
-	/*
-	 * There's a race window after we release cgroup_mutex and before
-	 * allocating a superblock. Make sure a concurrent process won't
-	 * be able to re-use the root during this window by delaying the
-	 * initialization of root refcnt.
-	 */
-	if (new_root) {
-		mutex_lock(&cgroup_mutex);
-		percpu_ref_reinit(&root->cgrp.self.refcnt);
-		mutex_unlock(&cgroup_mutex);
-	}
+	ret = cgroup1_root_to_use(fc);
+	if (!ret && !percpu_ref_tryget_live(&ctx->root->cgrp.self.refcnt))
+		ret = 1;	/* restart */
 
-	/*
-	 * 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 (pinned_sb)
-		deactivate_super(pinned_sb);
+	mutex_unlock(&cgroup_mutex);
+
+	if (!ret)
+		ret = cgroup_do_get_tree(fc);
 
-	return dentry;
+	if (!ret && percpu_ref_is_dying(&ctx->root->cgrp.self.refcnt)) {
+		struct super_block *sb = fc->root->d_sb;
+		dput(fc->root);
+		deactivate_locked_super(sb);
+		ret = 1;
+	}
+
+	if (unlikely(ret > 0)) {
+		msleep(10);
+		return restart_syscall();
+	}
+	return ret;
 }
 
 static int __init cgroup1_wq_init(void)
@@ -1292,7 +1291,12 @@ static int __init cgroup_no_v1(char *str)
 
 		if (!strcmp(token, "all")) {
 			cgroup_no_v1_mask = U16_MAX;
-			break;
+			continue;
+		}
+
+		if (!strcmp(token, "named")) {
+			cgroup_no_v1_named = true;
+			continue;
 		}
 
 		for_each_subsys(ss, i) {
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 6aaf5dd5383b..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>
@@ -86,6 +87,7 @@ EXPORT_SYMBOL_GPL(css_set_lock);
 
 DEFINE_SPINLOCK(trace_cgroup_path_lock);
 char trace_cgroup_path[TRACE_CGROUP_PATH_LEN];
+bool cgroup_debug __read_mostly;
 
 /*
  * Protects cgroup_idr and css_idr so that IDs can be released without
@@ -196,7 +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 */
@@ -493,7 +495,7 @@ static struct cgroup_subsys_state *cgroup_tryget_css(struct cgroup *cgrp,
 }
 
 /**
- * cgroup_e_css - obtain a cgroup's effective css for the specified subsystem
+ * cgroup_e_css_by_mask - obtain a cgroup's effective css for the specified ss
  * @cgrp: the cgroup of interest
  * @ss: the subsystem of interest (%NULL returns @cgrp->self)
  *
@@ -502,8 +504,8 @@ static struct cgroup_subsys_state *cgroup_tryget_css(struct cgroup *cgrp,
  * enabled.  If @ss is associated with the hierarchy @cgrp is on, this
  * function is guaranteed to return non-NULL css.
  */
-static struct cgroup_subsys_state *cgroup_e_css(struct cgroup *cgrp,
-						struct cgroup_subsys *ss)
+static struct cgroup_subsys_state *cgroup_e_css_by_mask(struct cgroup *cgrp,
+							struct cgroup_subsys *ss)
 {
 	lockdep_assert_held(&cgroup_mutex);
 
@@ -524,6 +526,35 @@ static struct cgroup_subsys_state *cgroup_e_css(struct cgroup *cgrp,
 }
 
 /**
+ * cgroup_e_css - obtain a cgroup's effective css for the specified subsystem
+ * @cgrp: the cgroup of interest
+ * @ss: the subsystem of interest
+ *
+ * Find and get the effective css of @cgrp for @ss.  The effective css is
+ * defined as the matching css of the nearest ancestor including self which
+ * has @ss enabled.  If @ss is not mounted on the hierarchy @cgrp is on,
+ * the root css is returned, so this function always returns a valid css.
+ *
+ * The returned css is not guaranteed to be online, and therefore it is the
+ * callers responsiblity to tryget a reference for it.
+ */
+struct cgroup_subsys_state *cgroup_e_css(struct cgroup *cgrp,
+					 struct cgroup_subsys *ss)
+{
+	struct cgroup_subsys_state *css;
+
+	do {
+		css = cgroup_css(cgrp, ss);
+
+		if (css)
+			return css;
+		cgrp = cgroup_parent(cgrp);
+	} while (cgrp);
+
+	return init_css_set.subsys[ss->id];
+}
+
+/**
  * cgroup_get_e_css - get a cgroup's effective css for the specified subsystem
  * @cgrp: the cgroup of interest
  * @ss: the subsystem of interest
@@ -605,10 +636,11 @@ EXPORT_SYMBOL_GPL(of_css);
  *
  * Should be called under cgroup_[tree_]mutex.
  */
-#define for_each_e_css(css, ssid, cgrp)					\
-	for ((ssid) = 0; (ssid) < CGROUP_SUBSYS_COUNT; (ssid)++)	\
-		if (!((css) = cgroup_e_css(cgrp, cgroup_subsys[(ssid)]))) \
-			;						\
+#define for_each_e_css(css, ssid, cgrp)					    \
+	for ((ssid) = 0; (ssid) < CGROUP_SUBSYS_COUNT; (ssid)++)	    \
+		if (!((css) = cgroup_e_css_by_mask(cgrp,		    \
+						   cgroup_subsys[(ssid)]))) \
+			;						    \
 		else
 
 /**
@@ -1007,7 +1039,7 @@ static struct css_set *find_existing_css_set(struct css_set *old_cset,
 			 * @ss is in this hierarchy, so we want the
 			 * effective css from @cgrp.
 			 */
-			template[i] = cgroup_e_css(cgrp, ss);
+			template[i] = cgroup_e_css_by_mask(cgrp, ss);
 		} else {
 			/*
 			 * @ss is not in this hierarchy, so we don't want
@@ -1399,12 +1431,15 @@ static char *cgroup_file_name(struct cgroup *cgrp, const struct cftype *cft,
 	struct cgroup_subsys *ss = cft->ss;
 
 	if (cft->ss && !(cft->flags & CFTYPE_NO_PREFIX) &&
-	    !(cgrp->root->flags & CGRP_ROOT_NOPREFIX))
-		snprintf(buf, CGROUP_FILE_NAME_MAX, "%s.%s",
-			 cgroup_on_dfl(cgrp) ? ss->name : ss->legacy_name,
+	    !(cgrp->root->flags & CGRP_ROOT_NOPREFIX)) {
+		const char *dbg = (cft->flags & CFTYPE_DEBUG) ? ".__DEBUG__." : "";
+
+		snprintf(buf, CGROUP_FILE_NAME_MAX, "%s%s.%s",
+			 dbg, cgroup_on_dfl(cgrp) ? ss->name : ss->legacy_name,
 			 cft->name);
-	else
+	} else {
 		strscpy(buf, cft->name, CGROUP_FILE_NAME_MAX);
+	}
 	return buf;
 }
 
@@ -1738,26 +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)
-		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)
@@ -1777,16 +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;
 }
 
@@ -1874,8 +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);
@@ -1884,16 +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;
@@ -1910,7 +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;
 
@@ -1994,57 +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
@@ -2053,29 +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)
@@ -2084,33 +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,
@@ -3024,7 +3102,7 @@ static int cgroup_apply_control(struct cgroup *cgrp)
 		return ret;
 
 	/*
-	 * At this point, cgroup_e_css() results reflect the new csses
+	 * At this point, cgroup_e_css_by_mask() results reflect the new csses
 	 * making the following cgroup_update_dfl_csses() properly update
 	 * css associations of all tasks in the subtree.
 	 */
@@ -3499,6 +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);
@@ -3537,6 +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,
 };
 
@@ -3545,6 +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,
@@ -3639,7 +3729,8 @@ restart:
 			continue;
 		if ((cft->flags & CFTYPE_ONLY_ON_ROOT) && cgroup_parent(cgrp))
 			continue;
-
+		if ((cft->flags & CFTYPE_DEBUG) && !cgroup_debug)
+			continue;
 		if (is_add) {
 			ret = cgroup_add_file(css, cgrp, cft);
 			if (ret) {
@@ -4202,20 +4293,25 @@ static void css_task_iter_advance(struct css_task_iter *it)
 
 	lockdep_assert_held(&css_set_lock);
 repeat:
-	/*
-	 * Advance iterator to find next entry.  cset->tasks is consumed
-	 * first and then ->mg_tasks.  After ->mg_tasks, we move onto the
-	 * next cset.
-	 */
-	next = it->task_pos->next;
+	if (it->task_pos) {
+		/*
+		 * Advance iterator to find next entry.  cset->tasks is
+		 * consumed first and then ->mg_tasks.  After ->mg_tasks,
+		 * we move onto the next cset.
+		 */
+		next = it->task_pos->next;
 
-	if (next == it->tasks_head)
-		next = it->mg_tasks_head->next;
+		if (next == it->tasks_head)
+			next = it->mg_tasks_head->next;
 
-	if (next == it->mg_tasks_head)
+		if (next == it->mg_tasks_head)
+			css_task_iter_advance_css_set(it);
+		else
+			it->task_pos = next;
+	} else {
+		/* called from start, proceed to the first cset */
 		css_task_iter_advance_css_set(it);
-	else
-		it->task_pos = next;
+	}
 
 	/* if PROCS, skip over tasks which aren't group leaders */
 	if ((it->flags & CSS_TASK_ITER_PROCS) && it->task_pos &&
@@ -4255,7 +4351,7 @@ void css_task_iter_start(struct cgroup_subsys_state *css, unsigned int flags,
 
 	it->cset_head = it->cset_pos;
 
-	css_task_iter_advance_css_set(it);
+	css_task_iter_advance(it);
 
 	spin_unlock_irq(&css_set_lock);
 }
@@ -5227,7 +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,
@@ -5273,7 +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
@@ -5294,11 +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);
@@ -5343,7 +5439,7 @@ int __init cgroup_init(void)
 	cgroup_rstat_boot();
 
 	/*
-	 * The latency of the synchronize_sched() is too high for cgroups,
+	 * The latency of the synchronize_rcu() is too high for cgroups,
 	 * avoid it at the cost of forcing all readers into the slow path.
 	 */
 	rcu_sync_enter_start(&cgroup_threadgroup_rwsem.rss);
@@ -5359,7 +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);
 
@@ -5709,16 +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);
 }
 
@@ -5743,6 +5842,16 @@ static int __init cgroup_disable(char *str)
 }
 __setup("cgroup_disable=", cgroup_disable);
 
+void __init __weak enable_debug_cgroup(void) { }
+
+static int __init enable_cgroup_debug(char *str)
+{
+	cgroup_debug = true;
+	enable_debug_cgroup();
+	return 1;
+}
+__setup("cgroup_debug", enable_cgroup_debug);
+
 /**
  * css_tryget_online_from_dir - get corresponding css from a cgroup dentry
  * @dentry: directory dentry of interest
@@ -5946,7 +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;
 }
@@ -5978,10 +6087,8 @@ static ssize_t show_delegatable_files(struct cftype *files, char *buf,
 
 		ret += snprintf(buf + ret, size - ret, "%s\n", cft->name);
 
-		if (unlikely(ret >= size)) {
-			WARN_ON(1);
+		if (WARN_ON(ret >= size))
 			break;
-		}
 	}
 
 	return ret;
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index 266f10cb7222..4834c4214e9c 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -39,6 +39,7 @@
 #include <linux/memory.h>
 #include <linux/export.h>
 #include <linux/mount.h>
+#include <linux/fs_context.h>
 #include <linux/namei.h>
 #include <linux/pagemap.h>
 #include <linux/proc_fs.h>
@@ -110,6 +111,16 @@ struct cpuset {
 	nodemask_t effective_mems;
 
 	/*
+	 * CPUs allocated to child sub-partitions (default hierarchy only)
+	 * - CPUs granted by the parent = effective_cpus U subparts_cpus
+	 * - effective_cpus and subparts_cpus are mutually exclusive.
+	 *
+	 * effective_cpus contains only onlined CPUs, but subparts_cpus
+	 * may have offlined ones.
+	 */
+	cpumask_var_t subparts_cpus;
+
+	/*
 	 * This is old Memory Nodes tasks took on.
 	 *
 	 * - top_cpuset.old_mems_allowed is initialized to mems_allowed.
@@ -134,6 +145,47 @@ struct cpuset {
 
 	/* for custom sched domain */
 	int relax_domain_level;
+
+	/* number of CPUs in subparts_cpus */
+	int nr_subparts_cpus;
+
+	/* partition root state */
+	int partition_root_state;
+
+	/*
+	 * Default hierarchy only:
+	 * use_parent_ecpus - set if using parent's effective_cpus
+	 * child_ecpus_count - # of children with use_parent_ecpus set
+	 */
+	int use_parent_ecpus;
+	int child_ecpus_count;
+};
+
+/*
+ * Partition root states:
+ *
+ *   0 - not a partition root
+ *
+ *   1 - partition root
+ *
+ *  -1 - invalid partition root
+ *       None of the cpus in cpus_allowed can be put into the parent's
+ *       subparts_cpus. In this case, the cpuset is not a real partition
+ *       root anymore.  However, the CPU_EXCLUSIVE bit will still be set
+ *       and the cpuset can be restored back to a partition root if the
+ *       parent cpuset can give more CPUs back to this child cpuset.
+ */
+#define PRS_DISABLED		0
+#define PRS_ENABLED		1
+#define PRS_ERROR		-1
+
+/*
+ * Temporary cpumasks for working with partitions that are passed among
+ * functions to avoid memory allocation in inner functions.
+ */
+struct tmpmasks {
+	cpumask_var_t addmask, delmask;	/* For partition root */
+	cpumask_var_t new_cpus;		/* For update_cpumasks_hier() */
 };
 
 static inline struct cpuset *css_cs(struct cgroup_subsys_state *css)
@@ -152,19 +204,6 @@ static inline struct cpuset *parent_cs(struct cpuset *cs)
 	return css_cs(cs->css.parent);
 }
 
-#ifdef CONFIG_NUMA
-static inline bool task_has_mempolicy(struct task_struct *task)
-{
-	return task->mempolicy;
-}
-#else
-static inline bool task_has_mempolicy(struct task_struct *task)
-{
-	return false;
-}
-#endif
-
-
 /* bits in struct cpuset flags field */
 typedef enum {
 	CS_ONLINE,
@@ -218,9 +257,15 @@ static inline int is_spread_slab(const struct cpuset *cs)
 	return test_bit(CS_SPREAD_SLAB, &cs->flags);
 }
 
+static inline int is_partition_root(const struct cpuset *cs)
+{
+	return cs->partition_root_state > 0;
+}
+
 static struct cpuset top_cpuset = {
 	.flags = ((1 << CS_ONLINE) | (1 << CS_CPU_EXCLUSIVE) |
 		  (1 << CS_MEM_EXCLUSIVE)),
+	.partition_root_state = PRS_ENABLED,
 };
 
 /**
@@ -315,25 +360,52 @@ static inline bool is_in_v2_mode(void)
  * users. If someone tries to mount the "cpuset" filesystem, we
  * silently switch it to mount "cgroup" instead
  */
-static struct dentry *cpuset_mount(struct file_system_type *fs_type,
-			 int flags, const char *unused_dev_name, void *data)
-{
-	struct file_system_type *cgroup_fs = get_fs_type("cgroup");
-	struct dentry *ret = ERR_PTR(-ENODEV);
-	if (cgroup_fs) {
-		char mountopts[] =
-			"cpuset,noprefix,"
-			"release_agent=/sbin/cpuset_release_agent";
-		ret = cgroup_fs->mount(cgroup_fs, flags,
-					   unused_dev_name, mountopts);
-		put_filesystem(cgroup_fs);
+static int cpuset_get_tree(struct fs_context *fc)
+{
+	struct file_system_type *cgroup_fs;
+	struct fs_context *new_fc;
+	int ret;
+
+	cgroup_fs = get_fs_type("cgroup");
+	if (!cgroup_fs)
+		return -ENODEV;
+
+	new_fc = fs_context_for_mount(cgroup_fs, fc->sb_flags);
+	if (IS_ERR(new_fc)) {
+		ret = PTR_ERR(new_fc);
+	} else {
+		static const char agent_path[] = "/sbin/cpuset_release_agent";
+		ret = vfs_parse_fs_string(new_fc, "cpuset", NULL, 0);
+		if (!ret)
+			ret = vfs_parse_fs_string(new_fc, "noprefix", NULL, 0);
+		if (!ret)
+			ret = vfs_parse_fs_string(new_fc, "release_agent",
+					agent_path, sizeof(agent_path) - 1);
+		if (!ret)
+			ret = vfs_get_tree(new_fc);
+		if (!ret) {	/* steal the result */
+			fc->root = new_fc->root;
+			new_fc->root = NULL;
+		}
+		put_fs_context(new_fc);
 	}
+	put_filesystem(cgroup_fs);
 	return ret;
 }
 
+static const struct fs_context_operations cpuset_fs_context_ops = {
+	.get_tree	= cpuset_get_tree,
+};
+
+static int cpuset_init_fs_context(struct fs_context *fc)
+{
+	fc->ops = &cpuset_fs_context_ops;
+	return 0;
+}
+
 static struct file_system_type cpuset_fs_type = {
-	.name = "cpuset",
-	.mount = cpuset_mount,
+	.name			= "cpuset",
+	.init_fs_context	= cpuset_init_fs_context,
 };
 
 /*
@@ -419,6 +491,65 @@ static int is_cpuset_subset(const struct cpuset *p, const struct cpuset *q)
 }
 
 /**
+ * alloc_cpumasks - allocate three cpumasks for cpuset
+ * @cs:  the cpuset that have cpumasks to be allocated.
+ * @tmp: the tmpmasks structure pointer
+ * Return: 0 if successful, -ENOMEM otherwise.
+ *
+ * Only one of the two input arguments should be non-NULL.
+ */
+static inline int alloc_cpumasks(struct cpuset *cs, struct tmpmasks *tmp)
+{
+	cpumask_var_t *pmask1, *pmask2, *pmask3;
+
+	if (cs) {
+		pmask1 = &cs->cpus_allowed;
+		pmask2 = &cs->effective_cpus;
+		pmask3 = &cs->subparts_cpus;
+	} else {
+		pmask1 = &tmp->new_cpus;
+		pmask2 = &tmp->addmask;
+		pmask3 = &tmp->delmask;
+	}
+
+	if (!zalloc_cpumask_var(pmask1, GFP_KERNEL))
+		return -ENOMEM;
+
+	if (!zalloc_cpumask_var(pmask2, GFP_KERNEL))
+		goto free_one;
+
+	if (!zalloc_cpumask_var(pmask3, GFP_KERNEL))
+		goto free_two;
+
+	return 0;
+
+free_two:
+	free_cpumask_var(*pmask2);
+free_one:
+	free_cpumask_var(*pmask1);
+	return -ENOMEM;
+}
+
+/**
+ * free_cpumasks - free cpumasks in a tmpmasks structure
+ * @cs:  the cpuset that have cpumasks to be free.
+ * @tmp: the tmpmasks structure pointer
+ */
+static inline void free_cpumasks(struct cpuset *cs, struct tmpmasks *tmp)
+{
+	if (cs) {
+		free_cpumask_var(cs->cpus_allowed);
+		free_cpumask_var(cs->effective_cpus);
+		free_cpumask_var(cs->subparts_cpus);
+	}
+	if (tmp) {
+		free_cpumask_var(tmp->new_cpus);
+		free_cpumask_var(tmp->addmask);
+		free_cpumask_var(tmp->delmask);
+	}
+}
+
+/**
  * alloc_trial_cpuset - allocate a trial cpuset
  * @cs: the cpuset that the trial cpuset duplicates
  */
@@ -430,31 +561,24 @@ static struct cpuset *alloc_trial_cpuset(struct cpuset *cs)
 	if (!trial)
 		return NULL;
 
-	if (!alloc_cpumask_var(&trial->cpus_allowed, GFP_KERNEL))
-		goto free_cs;
-	if (!alloc_cpumask_var(&trial->effective_cpus, GFP_KERNEL))
-		goto free_cpus;
+	if (alloc_cpumasks(trial, NULL)) {
+		kfree(trial);
+		return NULL;
+	}
 
 	cpumask_copy(trial->cpus_allowed, cs->cpus_allowed);
 	cpumask_copy(trial->effective_cpus, cs->effective_cpus);
 	return trial;
-
-free_cpus:
-	free_cpumask_var(trial->cpus_allowed);
-free_cs:
-	kfree(trial);
-	return NULL;
 }
 
 /**
- * free_trial_cpuset - free the trial cpuset
- * @trial: the trial cpuset to be freed
+ * free_cpuset - free the cpuset
+ * @cs: the cpuset to be freed
  */
-static void free_trial_cpuset(struct cpuset *trial)
+static inline void free_cpuset(struct cpuset *cs)
 {
-	free_cpumask_var(trial->effective_cpus);
-	free_cpumask_var(trial->cpus_allowed);
-	kfree(trial);
+	free_cpumasks(cs, NULL);
+	kfree(cs);
 }
 
 /*
@@ -660,13 +784,14 @@ static int generate_sched_domains(cpumask_var_t **domains,
 	int ndoms = 0;		/* number of sched domains in result */
 	int nslot;		/* next empty doms[] struct cpumask slot */
 	struct cgroup_subsys_state *pos_css;
+	bool root_load_balance = is_sched_load_balance(&top_cpuset);
 
 	doms = NULL;
 	dattr = NULL;
 	csa = NULL;
 
 	/* Special case for the 99% of systems with one, full, sched domain */
-	if (is_sched_load_balance(&top_cpuset)) {
+	if (root_load_balance && !top_cpuset.nr_subparts_cpus) {
 		ndoms = 1;
 		doms = alloc_sched_domains(ndoms);
 		if (!doms)
@@ -689,6 +814,8 @@ static int generate_sched_domains(cpumask_var_t **domains,
 	csn = 0;
 
 	rcu_read_lock();
+	if (root_load_balance)
+		csa[csn++] = &top_cpuset;
 	cpuset_for_each_descendant_pre(cp, pos_css, &top_cpuset) {
 		if (cp == &top_cpuset)
 			continue;
@@ -699,6 +826,9 @@ static int generate_sched_domains(cpumask_var_t **domains,
 		 * parent's cpus, so just skip them, and then we call
 		 * update_domain_attr_tree() to calc relax_domain_level of
 		 * the corresponding sched domain.
+		 *
+		 * If root is load-balancing, we can skip @cp if it
+		 * is a subset of the root's effective_cpus.
 		 */
 		if (!cpumask_empty(cp->cpus_allowed) &&
 		    !(is_sched_load_balance(cp) &&
@@ -706,11 +836,16 @@ static int generate_sched_domains(cpumask_var_t **domains,
 					 housekeeping_cpumask(HK_FLAG_DOMAIN))))
 			continue;
 
+		if (root_load_balance &&
+		    cpumask_subset(cp->cpus_allowed, top_cpuset.effective_cpus))
+			continue;
+
 		if (is_sched_load_balance(cp))
 			csa[csn++] = cp;
 
-		/* skip @cp's subtree */
-		pos_css = css_rightmost_descendant(pos_css);
+		/* skip @cp's subtree if not a partition root */
+		if (!is_partition_root(cp))
+			pos_css = css_rightmost_descendant(pos_css);
 	}
 	rcu_read_unlock();
 
@@ -838,7 +973,12 @@ static void rebuild_sched_domains_locked(void)
 	 * passing doms with offlined cpu to partition_sched_domains().
 	 * Anyways, hotplug work item will rebuild sched domains.
 	 */
-	if (!cpumask_equal(top_cpuset.effective_cpus, cpu_active_mask))
+	if (!top_cpuset.nr_subparts_cpus &&
+	    !cpumask_equal(top_cpuset.effective_cpus, cpu_active_mask))
+		goto out;
+
+	if (top_cpuset.nr_subparts_cpus &&
+	   !cpumask_subset(top_cpuset.effective_cpus, cpu_active_mask))
 		goto out;
 
 	/* Generate domain masks and attrs */
@@ -881,10 +1021,248 @@ static void update_tasks_cpumask(struct cpuset *cs)
 	css_task_iter_end(&it);
 }
 
+/**
+ * compute_effective_cpumask - Compute the effective cpumask of the cpuset
+ * @new_cpus: the temp variable for the new effective_cpus mask
+ * @cs: the cpuset the need to recompute the new effective_cpus mask
+ * @parent: the parent cpuset
+ *
+ * If the parent has subpartition CPUs, include them in the list of
+ * allowable CPUs in computing the new effective_cpus mask. Since offlined
+ * CPUs are not removed from subparts_cpus, we have to use cpu_active_mask
+ * to mask those out.
+ */
+static void compute_effective_cpumask(struct cpumask *new_cpus,
+				      struct cpuset *cs, struct cpuset *parent)
+{
+	if (parent->nr_subparts_cpus) {
+		cpumask_or(new_cpus, parent->effective_cpus,
+			   parent->subparts_cpus);
+		cpumask_and(new_cpus, new_cpus, cs->cpus_allowed);
+		cpumask_and(new_cpus, new_cpus, cpu_active_mask);
+	} else {
+		cpumask_and(new_cpus, cs->cpus_allowed, parent->effective_cpus);
+	}
+}
+
+/*
+ * Commands for update_parent_subparts_cpumask
+ */
+enum subparts_cmd {
+	partcmd_enable,		/* Enable partition root	 */
+	partcmd_disable,	/* Disable partition root	 */
+	partcmd_update,		/* Update parent's subparts_cpus */
+};
+
+/**
+ * update_parent_subparts_cpumask - update subparts_cpus mask of parent cpuset
+ * @cpuset:  The cpuset that requests change in partition root state
+ * @cmd:     Partition root state change command
+ * @newmask: Optional new cpumask for partcmd_update
+ * @tmp:     Temporary addmask and delmask
+ * Return:   0, 1 or an error code
+ *
+ * For partcmd_enable, the cpuset is being transformed from a non-partition
+ * root to a partition root. The cpus_allowed mask of the given cpuset will
+ * be put into parent's subparts_cpus and taken away from parent's
+ * effective_cpus. The function will return 0 if all the CPUs listed in
+ * cpus_allowed can be granted or an error code will be returned.
+ *
+ * For partcmd_disable, the cpuset is being transofrmed from a partition
+ * root back to a non-partition root. any CPUs in cpus_allowed that are in
+ * parent's subparts_cpus will be taken away from that cpumask and put back
+ * into parent's effective_cpus. 0 should always be returned.
+ *
+ * For partcmd_update, if the optional newmask is specified, the cpu
+ * list is to be changed from cpus_allowed to newmask. Otherwise,
+ * cpus_allowed is assumed to remain the same. The cpuset should either
+ * be a partition root or an invalid partition root. The partition root
+ * state may change if newmask is NULL and none of the requested CPUs can
+ * be granted by the parent. The function will return 1 if changes to
+ * parent's subparts_cpus and effective_cpus happen or 0 otherwise.
+ * Error code should only be returned when newmask is non-NULL.
+ *
+ * The partcmd_enable and partcmd_disable commands are used by
+ * update_prstate(). The partcmd_update command is used by
+ * update_cpumasks_hier() with newmask NULL and update_cpumask() with
+ * newmask set.
+ *
+ * The checking is more strict when enabling partition root than the
+ * other two commands.
+ *
+ * Because of the implicit cpu exclusive nature of a partition root,
+ * cpumask changes that violates the cpu exclusivity rule will not be
+ * permitted when checked by validate_change(). The validate_change()
+ * function will also prevent any changes to the cpu list if it is not
+ * a superset of children's cpu lists.
+ */
+static int update_parent_subparts_cpumask(struct cpuset *cpuset, int cmd,
+					  struct cpumask *newmask,
+					  struct tmpmasks *tmp)
+{
+	struct cpuset *parent = parent_cs(cpuset);
+	int adding;	/* Moving cpus from effective_cpus to subparts_cpus */
+	int deleting;	/* Moving cpus from subparts_cpus to effective_cpus */
+	bool part_error = false;	/* Partition error? */
+
+	lockdep_assert_held(&cpuset_mutex);
+
+	/*
+	 * The parent must be a partition root.
+	 * The new cpumask, if present, or the current cpus_allowed must
+	 * not be empty.
+	 */
+	if (!is_partition_root(parent) ||
+	   (newmask && cpumask_empty(newmask)) ||
+	   (!newmask && cpumask_empty(cpuset->cpus_allowed)))
+		return -EINVAL;
+
+	/*
+	 * Enabling/disabling partition root is not allowed if there are
+	 * online children.
+	 */
+	if ((cmd != partcmd_update) && css_has_online_children(&cpuset->css))
+		return -EBUSY;
+
+	/*
+	 * Enabling partition root is not allowed if not all the CPUs
+	 * can be granted from parent's effective_cpus or at least one
+	 * CPU will be left after that.
+	 */
+	if ((cmd == partcmd_enable) &&
+	   (!cpumask_subset(cpuset->cpus_allowed, parent->effective_cpus) ||
+	     cpumask_equal(cpuset->cpus_allowed, parent->effective_cpus)))
+		return -EINVAL;
+
+	/*
+	 * A cpumask update cannot make parent's effective_cpus become empty.
+	 */
+	adding = deleting = false;
+	if (cmd == partcmd_enable) {
+		cpumask_copy(tmp->addmask, cpuset->cpus_allowed);
+		adding = true;
+	} else if (cmd == partcmd_disable) {
+		deleting = cpumask_and(tmp->delmask, cpuset->cpus_allowed,
+				       parent->subparts_cpus);
+	} else if (newmask) {
+		/*
+		 * partcmd_update with newmask:
+		 *
+		 * delmask = cpus_allowed & ~newmask & parent->subparts_cpus
+		 * addmask = newmask & parent->effective_cpus
+		 *		     & ~parent->subparts_cpus
+		 */
+		cpumask_andnot(tmp->delmask, cpuset->cpus_allowed, newmask);
+		deleting = cpumask_and(tmp->delmask, tmp->delmask,
+				       parent->subparts_cpus);
+
+		cpumask_and(tmp->addmask, newmask, parent->effective_cpus);
+		adding = cpumask_andnot(tmp->addmask, tmp->addmask,
+					parent->subparts_cpus);
+		/*
+		 * Return error if the new effective_cpus could become empty.
+		 */
+		if (adding &&
+		    cpumask_equal(parent->effective_cpus, tmp->addmask)) {
+			if (!deleting)
+				return -EINVAL;
+			/*
+			 * As some of the CPUs in subparts_cpus might have
+			 * been offlined, we need to compute the real delmask
+			 * to confirm that.
+			 */
+			if (!cpumask_and(tmp->addmask, tmp->delmask,
+					 cpu_active_mask))
+				return -EINVAL;
+			cpumask_copy(tmp->addmask, parent->effective_cpus);
+		}
+	} else {
+		/*
+		 * partcmd_update w/o newmask:
+		 *
+		 * addmask = cpus_allowed & parent->effectiveb_cpus
+		 *
+		 * Note that parent's subparts_cpus may have been
+		 * pre-shrunk in case there is a change in the cpu list.
+		 * So no deletion is needed.
+		 */
+		adding = cpumask_and(tmp->addmask, cpuset->cpus_allowed,
+				     parent->effective_cpus);
+		part_error = cpumask_equal(tmp->addmask,
+					   parent->effective_cpus);
+	}
+
+	if (cmd == partcmd_update) {
+		int prev_prs = cpuset->partition_root_state;
+
+		/*
+		 * Check for possible transition between PRS_ENABLED
+		 * and PRS_ERROR.
+		 */
+		switch (cpuset->partition_root_state) {
+		case PRS_ENABLED:
+			if (part_error)
+				cpuset->partition_root_state = PRS_ERROR;
+			break;
+		case PRS_ERROR:
+			if (!part_error)
+				cpuset->partition_root_state = PRS_ENABLED;
+			break;
+		}
+		/*
+		 * Set part_error if previously in invalid state.
+		 */
+		part_error = (prev_prs == PRS_ERROR);
+	}
+
+	if (!part_error && (cpuset->partition_root_state == PRS_ERROR))
+		return 0;	/* Nothing need to be done */
+
+	if (cpuset->partition_root_state == PRS_ERROR) {
+		/*
+		 * Remove all its cpus from parent's subparts_cpus.
+		 */
+		adding = false;
+		deleting = cpumask_and(tmp->delmask, cpuset->cpus_allowed,
+				       parent->subparts_cpus);
+	}
+
+	if (!adding && !deleting)
+		return 0;
+
+	/*
+	 * Change the parent's subparts_cpus.
+	 * Newly added CPUs will be removed from effective_cpus and
+	 * newly deleted ones will be added back to effective_cpus.
+	 */
+	spin_lock_irq(&callback_lock);
+	if (adding) {
+		cpumask_or(parent->subparts_cpus,
+			   parent->subparts_cpus, tmp->addmask);
+		cpumask_andnot(parent->effective_cpus,
+			       parent->effective_cpus, tmp->addmask);
+	}
+	if (deleting) {
+		cpumask_andnot(parent->subparts_cpus,
+			       parent->subparts_cpus, tmp->delmask);
+		/*
+		 * Some of the CPUs in subparts_cpus might have been offlined.
+		 */
+		cpumask_and(tmp->delmask, tmp->delmask, cpu_active_mask);
+		cpumask_or(parent->effective_cpus,
+			   parent->effective_cpus, tmp->delmask);
+	}
+
+	parent->nr_subparts_cpus = cpumask_weight(parent->subparts_cpus);
+	spin_unlock_irq(&callback_lock);
+
+	return cmd == partcmd_update;
+}
+
 /*
  * update_cpumasks_hier - Update effective cpumasks and tasks in the subtree
- * @cs: the cpuset to consider
- * @new_cpus: temp variable for calculating new effective_cpus
+ * @cs:  the cpuset to consider
+ * @tmp: temp variables for calculating effective_cpus & partition setup
  *
  * When congifured cpumask is changed, the effective cpumasks of this cpuset
  * and all its descendants need to be updated.
@@ -893,7 +1271,7 @@ static void update_tasks_cpumask(struct cpuset *cs)
  *
  * Called with cpuset_mutex held
  */
-static void update_cpumasks_hier(struct cpuset *cs, struct cpumask *new_cpus)
+static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp)
 {
 	struct cpuset *cp;
 	struct cgroup_subsys_state *pos_css;
@@ -903,27 +1281,115 @@ static void update_cpumasks_hier(struct cpuset *cs, struct cpumask *new_cpus)
 	cpuset_for_each_descendant_pre(cp, pos_css, cs) {
 		struct cpuset *parent = parent_cs(cp);
 
-		cpumask_and(new_cpus, cp->cpus_allowed, parent->effective_cpus);
+		compute_effective_cpumask(tmp->new_cpus, cp, parent);
 
 		/*
 		 * If it becomes empty, inherit the effective mask of the
 		 * parent, which is guaranteed to have some CPUs.
 		 */
-		if (is_in_v2_mode() && cpumask_empty(new_cpus))
-			cpumask_copy(new_cpus, parent->effective_cpus);
+		if (is_in_v2_mode() && cpumask_empty(tmp->new_cpus)) {
+			cpumask_copy(tmp->new_cpus, parent->effective_cpus);
+			if (!cp->use_parent_ecpus) {
+				cp->use_parent_ecpus = true;
+				parent->child_ecpus_count++;
+			}
+		} else if (cp->use_parent_ecpus) {
+			cp->use_parent_ecpus = false;
+			WARN_ON_ONCE(!parent->child_ecpus_count);
+			parent->child_ecpus_count--;
+		}
 
-		/* Skip the whole subtree if the cpumask remains the same. */
-		if (cpumask_equal(new_cpus, cp->effective_cpus)) {
+		/*
+		 * Skip the whole subtree if the cpumask remains the same
+		 * and has no partition root state.
+		 */
+		if (!cp->partition_root_state &&
+		    cpumask_equal(tmp->new_cpus, cp->effective_cpus)) {
 			pos_css = css_rightmost_descendant(pos_css);
 			continue;
 		}
 
+		/*
+		 * update_parent_subparts_cpumask() should have been called
+		 * for cs already in update_cpumask(). We should also call
+		 * update_tasks_cpumask() again for tasks in the parent
+		 * cpuset if the parent's subparts_cpus changes.
+		 */
+		if ((cp != cs) && cp->partition_root_state) {
+			switch (parent->partition_root_state) {
+			case PRS_DISABLED:
+				/*
+				 * If parent is not a partition root or an
+				 * invalid partition root, clear the state
+				 * state and the CS_CPU_EXCLUSIVE flag.
+				 */
+				WARN_ON_ONCE(cp->partition_root_state
+					     != PRS_ERROR);
+				cp->partition_root_state = 0;
+
+				/*
+				 * clear_bit() is an atomic operation and
+				 * readers aren't interested in the state
+				 * of CS_CPU_EXCLUSIVE anyway. So we can
+				 * just update the flag without holding
+				 * the callback_lock.
+				 */
+				clear_bit(CS_CPU_EXCLUSIVE, &cp->flags);
+				break;
+
+			case PRS_ENABLED:
+				if (update_parent_subparts_cpumask(cp, partcmd_update, NULL, tmp))
+					update_tasks_cpumask(parent);
+				break;
+
+			case PRS_ERROR:
+				/*
+				 * When parent is invalid, it has to be too.
+				 */
+				cp->partition_root_state = PRS_ERROR;
+				if (cp->nr_subparts_cpus) {
+					cp->nr_subparts_cpus = 0;
+					cpumask_clear(cp->subparts_cpus);
+				}
+				break;
+			}
+		}
+
 		if (!css_tryget_online(&cp->css))
 			continue;
 		rcu_read_unlock();
 
 		spin_lock_irq(&callback_lock);
-		cpumask_copy(cp->effective_cpus, new_cpus);
+
+		cpumask_copy(cp->effective_cpus, tmp->new_cpus);
+		if (cp->nr_subparts_cpus &&
+		   (cp->partition_root_state != PRS_ENABLED)) {
+			cp->nr_subparts_cpus = 0;
+			cpumask_clear(cp->subparts_cpus);
+		} else if (cp->nr_subparts_cpus) {
+			/*
+			 * Make sure that effective_cpus & subparts_cpus
+			 * are mutually exclusive.
+			 *
+			 * In the unlikely event that effective_cpus
+			 * becomes empty. we clear cp->nr_subparts_cpus and
+			 * let its child partition roots to compete for
+			 * CPUs again.
+			 */
+			cpumask_andnot(cp->effective_cpus, cp->effective_cpus,
+				       cp->subparts_cpus);
+			if (cpumask_empty(cp->effective_cpus)) {
+				cpumask_copy(cp->effective_cpus, tmp->new_cpus);
+				cpumask_clear(cp->subparts_cpus);
+				cp->nr_subparts_cpus = 0;
+			} else if (!cpumask_subset(cp->subparts_cpus,
+						   tmp->new_cpus)) {
+				cpumask_andnot(cp->subparts_cpus,
+					cp->subparts_cpus, tmp->new_cpus);
+				cp->nr_subparts_cpus
+					= cpumask_weight(cp->subparts_cpus);
+			}
+		}
 		spin_unlock_irq(&callback_lock);
 
 		WARN_ON(!is_in_v2_mode() &&
@@ -932,11 +1398,15 @@ static void update_cpumasks_hier(struct cpuset *cs, struct cpumask *new_cpus)
 		update_tasks_cpumask(cp);
 
 		/*
-		 * If the effective cpumask of any non-empty cpuset is changed,
-		 * we need to rebuild sched domains.
+		 * On legacy hierarchy, if the effective cpumask of any non-
+		 * empty cpuset is changed, we need to rebuild sched domains.
+		 * On default hierarchy, the cpuset needs to be a partition
+		 * root as well.
 		 */
 		if (!cpumask_empty(cp->cpus_allowed) &&
-		    is_sched_load_balance(cp))
+		    is_sched_load_balance(cp) &&
+		   (!cgroup_subsys_on_dfl(cpuset_cgrp_subsys) ||
+		    is_partition_root(cp)))
 			need_rebuild_sched_domains = true;
 
 		rcu_read_lock();
@@ -949,6 +1419,35 @@ static void update_cpumasks_hier(struct cpuset *cs, struct cpumask *new_cpus)
 }
 
 /**
+ * update_sibling_cpumasks - Update siblings cpumasks
+ * @parent:  Parent cpuset
+ * @cs:      Current cpuset
+ * @tmp:     Temp variables
+ */
+static void update_sibling_cpumasks(struct cpuset *parent, struct cpuset *cs,
+				    struct tmpmasks *tmp)
+{
+	struct cpuset *sibling;
+	struct cgroup_subsys_state *pos_css;
+
+	/*
+	 * Check all its siblings and call update_cpumasks_hier()
+	 * if their use_parent_ecpus flag is set in order for them
+	 * to use the right effective_cpus value.
+	 */
+	rcu_read_lock();
+	cpuset_for_each_child(sibling, pos_css, parent) {
+		if (sibling == cs)
+			continue;
+		if (!sibling->use_parent_ecpus)
+			continue;
+
+		update_cpumasks_hier(sibling, tmp);
+	}
+	rcu_read_unlock();
+}
+
+/**
  * update_cpumask - update the cpus_allowed mask of a cpuset and all tasks in it
  * @cs: the cpuset to consider
  * @trialcs: trial cpuset
@@ -958,6 +1457,7 @@ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs,
 			  const char *buf)
 {
 	int retval;
+	struct tmpmasks tmp;
 
 	/* top_cpuset.cpus_allowed tracks cpu_online_mask; it's read-only */
 	if (cs == &top_cpuset)
@@ -989,12 +1489,50 @@ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs,
 	if (retval < 0)
 		return retval;
 
+#ifdef CONFIG_CPUMASK_OFFSTACK
+	/*
+	 * Use the cpumasks in trialcs for tmpmasks when they are pointers
+	 * to allocated cpumasks.
+	 */
+	tmp.addmask  = trialcs->subparts_cpus;
+	tmp.delmask  = trialcs->effective_cpus;
+	tmp.new_cpus = trialcs->cpus_allowed;
+#endif
+
+	if (cs->partition_root_state) {
+		/* Cpumask of a partition root cannot be empty */
+		if (cpumask_empty(trialcs->cpus_allowed))
+			return -EINVAL;
+		if (update_parent_subparts_cpumask(cs, partcmd_update,
+					trialcs->cpus_allowed, &tmp) < 0)
+			return -EINVAL;
+	}
+
 	spin_lock_irq(&callback_lock);
 	cpumask_copy(cs->cpus_allowed, trialcs->cpus_allowed);
+
+	/*
+	 * Make sure that subparts_cpus is a subset of cpus_allowed.
+	 */
+	if (cs->nr_subparts_cpus) {
+		cpumask_andnot(cs->subparts_cpus, cs->subparts_cpus,
+			       cs->cpus_allowed);
+		cs->nr_subparts_cpus = cpumask_weight(cs->subparts_cpus);
+	}
 	spin_unlock_irq(&callback_lock);
 
-	/* use trialcs->cpus_allowed as a temp variable */
-	update_cpumasks_hier(cs, trialcs->cpus_allowed);
+	update_cpumasks_hier(cs, &tmp);
+
+	if (cs->partition_root_state) {
+		struct cpuset *parent = parent_cs(cs);
+
+		/*
+		 * For partition root, update the cpumasks of sibling
+		 * cpusets if they use parent's effective_cpus.
+		 */
+		if (parent->child_ecpus_count)
+			update_sibling_cpumasks(parent, cs, &tmp);
+	}
 	return 0;
 }
 
@@ -1348,7 +1886,95 @@ static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs,
 	if (spread_flag_changed)
 		update_tasks_flags(cs);
 out:
-	free_trial_cpuset(trialcs);
+	free_cpuset(trialcs);
+	return err;
+}
+
+/*
+ * update_prstate - update partititon_root_state
+ * cs:	the cpuset to update
+ * val: 0 - disabled, 1 - enabled
+ *
+ * Call with cpuset_mutex held.
+ */
+static int update_prstate(struct cpuset *cs, int val)
+{
+	int err;
+	struct cpuset *parent = parent_cs(cs);
+	struct tmpmasks tmp;
+
+	if ((val != 0) && (val != 1))
+		return -EINVAL;
+	if (val == cs->partition_root_state)
+		return 0;
+
+	/*
+	 * Cannot force a partial or invalid partition root to a full
+	 * partition root.
+	 */
+	if (val && cs->partition_root_state)
+		return -EINVAL;
+
+	if (alloc_cpumasks(NULL, &tmp))
+		return -ENOMEM;
+
+	err = -EINVAL;
+	if (!cs->partition_root_state) {
+		/*
+		 * Turning on partition root requires setting the
+		 * CS_CPU_EXCLUSIVE bit implicitly as well and cpus_allowed
+		 * cannot be NULL.
+		 */
+		if (cpumask_empty(cs->cpus_allowed))
+			goto out;
+
+		err = update_flag(CS_CPU_EXCLUSIVE, cs, 1);
+		if (err)
+			goto out;
+
+		err = update_parent_subparts_cpumask(cs, partcmd_enable,
+						     NULL, &tmp);
+		if (err) {
+			update_flag(CS_CPU_EXCLUSIVE, cs, 0);
+			goto out;
+		}
+		cs->partition_root_state = PRS_ENABLED;
+	} else {
+		/*
+		 * Turning off partition root will clear the
+		 * CS_CPU_EXCLUSIVE bit.
+		 */
+		if (cs->partition_root_state == PRS_ERROR) {
+			cs->partition_root_state = 0;
+			update_flag(CS_CPU_EXCLUSIVE, cs, 0);
+			err = 0;
+			goto out;
+		}
+
+		err = update_parent_subparts_cpumask(cs, partcmd_disable,
+						     NULL, &tmp);
+		if (err)
+			goto out;
+
+		cs->partition_root_state = 0;
+
+		/* Turning off CS_CPU_EXCLUSIVE will not return error */
+		update_flag(CS_CPU_EXCLUSIVE, cs, 0);
+	}
+
+	/*
+	 * Update cpumask of parent's tasks except when it is the top
+	 * cpuset as some system daemons cannot be mapped to other CPUs.
+	 */
+	if (parent != &top_cpuset)
+		update_tasks_cpumask(parent);
+
+	if (parent->child_ecpus_count)
+		update_sibling_cpumasks(parent, cs, &tmp);
+
+	rebuild_sched_domains_locked();
+out:
+	free_cpumasks(NULL, &tmp);
 	return err;
 }
 
@@ -1498,10 +2124,8 @@ out_unlock:
 static void cpuset_cancel_attach(struct cgroup_taskset *tset)
 {
 	struct cgroup_subsys_state *css;
-	struct cpuset *cs;
 
 	cgroup_taskset_first(tset, &css);
-	cs = css_cs(css);
 
 	mutex_lock(&cpuset_mutex);
 	css_cs(css)->attach_in_progress--;
@@ -1593,10 +2217,12 @@ typedef enum {
 	FILE_MEMLIST,
 	FILE_EFFECTIVE_CPULIST,
 	FILE_EFFECTIVE_MEMLIST,
+	FILE_SUBPARTS_CPULIST,
 	FILE_CPU_EXCLUSIVE,
 	FILE_MEM_EXCLUSIVE,
 	FILE_MEM_HARDWALL,
 	FILE_SCHED_LOAD_BALANCE,
+	FILE_PARTITION_ROOT,
 	FILE_SCHED_RELAX_DOMAIN_LEVEL,
 	FILE_MEMORY_PRESSURE_ENABLED,
 	FILE_MEMORY_PRESSURE,
@@ -1732,7 +2358,7 @@ static ssize_t cpuset_write_resmask(struct kernfs_open_file *of,
 		break;
 	}
 
-	free_trial_cpuset(trialcs);
+	free_cpuset(trialcs);
 out_unlock:
 	mutex_unlock(&cpuset_mutex);
 	kernfs_unbreak_active_protection(of->kn);
@@ -1770,6 +2396,9 @@ static int cpuset_common_seq_show(struct seq_file *sf, void *v)
 	case FILE_EFFECTIVE_MEMLIST:
 		seq_printf(sf, "%*pbl\n", nodemask_pr_args(&cs->effective_mems));
 		break;
+	case FILE_SUBPARTS_CPULIST:
+		seq_printf(sf, "%*pbl\n", cpumask_pr_args(cs->subparts_cpus));
+		break;
 	default:
 		ret = -EINVAL;
 	}
@@ -1824,12 +2453,60 @@ static s64 cpuset_read_s64(struct cgroup_subsys_state *css, struct cftype *cft)
 	return 0;
 }
 
+static int sched_partition_show(struct seq_file *seq, void *v)
+{
+	struct cpuset *cs = css_cs(seq_css(seq));
+
+	switch (cs->partition_root_state) {
+	case PRS_ENABLED:
+		seq_puts(seq, "root\n");
+		break;
+	case PRS_DISABLED:
+		seq_puts(seq, "member\n");
+		break;
+	case PRS_ERROR:
+		seq_puts(seq, "root invalid\n");
+		break;
+	}
+	return 0;
+}
+
+static ssize_t sched_partition_write(struct kernfs_open_file *of, char *buf,
+				     size_t nbytes, loff_t off)
+{
+	struct cpuset *cs = css_cs(of_css(of));
+	int val;
+	int retval = -ENODEV;
+
+	buf = strstrip(buf);
+
+	/*
+	 * Convert "root" to ENABLED, and convert "member" to DISABLED.
+	 */
+	if (!strcmp(buf, "root"))
+		val = PRS_ENABLED;
+	else if (!strcmp(buf, "member"))
+		val = PRS_DISABLED;
+	else
+		return -EINVAL;
+
+	css_get(&cs->css);
+	mutex_lock(&cpuset_mutex);
+	if (!is_cpuset_online(cs))
+		goto out_unlock;
+
+	retval = update_prstate(cs, val);
+out_unlock:
+	mutex_unlock(&cpuset_mutex);
+	css_put(&cs->css);
+	return retval ?: nbytes;
+}
 
 /*
  * for the common functions, 'private' gives the type of file
  */
 
-static struct cftype files[] = {
+static struct cftype legacy_files[] = {
 	{
 		.name = "cpus",
 		.seq_show = cpuset_common_seq_show,
@@ -1932,6 +2609,60 @@ static struct cftype files[] = {
 };
 
 /*
+ * This is currently a minimal set for the default hierarchy. It can be
+ * expanded later on by migrating more features and control files from v1.
+ */
+static struct cftype dfl_files[] = {
+	{
+		.name = "cpus",
+		.seq_show = cpuset_common_seq_show,
+		.write = cpuset_write_resmask,
+		.max_write_len = (100U + 6 * NR_CPUS),
+		.private = FILE_CPULIST,
+		.flags = CFTYPE_NOT_ON_ROOT,
+	},
+
+	{
+		.name = "mems",
+		.seq_show = cpuset_common_seq_show,
+		.write = cpuset_write_resmask,
+		.max_write_len = (100U + 6 * MAX_NUMNODES),
+		.private = FILE_MEMLIST,
+		.flags = CFTYPE_NOT_ON_ROOT,
+	},
+
+	{
+		.name = "cpus.effective",
+		.seq_show = cpuset_common_seq_show,
+		.private = FILE_EFFECTIVE_CPULIST,
+	},
+
+	{
+		.name = "mems.effective",
+		.seq_show = cpuset_common_seq_show,
+		.private = FILE_EFFECTIVE_MEMLIST,
+	},
+
+	{
+		.name = "cpus.partition",
+		.seq_show = sched_partition_show,
+		.write = sched_partition_write,
+		.private = FILE_PARTITION_ROOT,
+		.flags = CFTYPE_NOT_ON_ROOT,
+	},
+
+	{
+		.name = "cpus.subpartitions",
+		.seq_show = cpuset_common_seq_show,
+		.private = FILE_SUBPARTS_CPULIST,
+		.flags = CFTYPE_DEBUG,
+	},
+
+	{ }	/* terminate */
+};
+
+
+/*
  *	cpuset_css_alloc - allocate a cpuset css
  *	cgrp:	control group that the new cpuset will be part of
  */
@@ -1947,26 +2678,19 @@ cpuset_css_alloc(struct cgroup_subsys_state *parent_css)
 	cs = kzalloc(sizeof(*cs), GFP_KERNEL);
 	if (!cs)
 		return ERR_PTR(-ENOMEM);
-	if (!alloc_cpumask_var(&cs->cpus_allowed, GFP_KERNEL))
-		goto free_cs;
-	if (!alloc_cpumask_var(&cs->effective_cpus, GFP_KERNEL))
-		goto free_cpus;
+
+	if (alloc_cpumasks(cs, NULL)) {
+		kfree(cs);
+		return ERR_PTR(-ENOMEM);
+	}
 
 	set_bit(CS_SCHED_LOAD_BALANCE, &cs->flags);
-	cpumask_clear(cs->cpus_allowed);
 	nodes_clear(cs->mems_allowed);
-	cpumask_clear(cs->effective_cpus);
 	nodes_clear(cs->effective_mems);
 	fmeter_init(&cs->fmeter);
 	cs->relax_domain_level = -1;
 
 	return &cs->css;
-
-free_cpus:
-	free_cpumask_var(cs->cpus_allowed);
-free_cs:
-	kfree(cs);
-	return ERR_PTR(-ENOMEM);
 }
 
 static int cpuset_css_online(struct cgroup_subsys_state *css)
@@ -1993,6 +2717,8 @@ static int cpuset_css_online(struct cgroup_subsys_state *css)
 	if (is_in_v2_mode()) {
 		cpumask_copy(cs->effective_cpus, parent->effective_cpus);
 		cs->effective_mems = parent->effective_mems;
+		cs->use_parent_ecpus = true;
+		parent->child_ecpus_count++;
 	}
 	spin_unlock_irq(&callback_lock);
 
@@ -2035,7 +2761,12 @@ out_unlock:
 /*
  * If the cpuset being removed has its flag 'sched_load_balance'
  * enabled, then simulate turning sched_load_balance off, which
- * will call rebuild_sched_domains_locked().
+ * will call rebuild_sched_domains_locked(). That is not needed
+ * in the default hierarchy where only changes in partition
+ * will cause repartitioning.
+ *
+ * If the cpuset has the 'sched.partition' flag enabled, simulate
+ * turning 'sched.partition" off.
  */
 
 static void cpuset_css_offline(struct cgroup_subsys_state *css)
@@ -2044,9 +2775,20 @@ static void cpuset_css_offline(struct cgroup_subsys_state *css)
 
 	mutex_lock(&cpuset_mutex);
 
-	if (is_sched_load_balance(cs))
+	if (is_partition_root(cs))
+		update_prstate(cs, 0);
+
+	if (!cgroup_subsys_on_dfl(cpuset_cgrp_subsys) &&
+	    is_sched_load_balance(cs))
 		update_flag(CS_SCHED_LOAD_BALANCE, cs, 0);
 
+	if (cs->use_parent_ecpus) {
+		struct cpuset *parent = parent_cs(cs);
+
+		cs->use_parent_ecpus = false;
+		parent->child_ecpus_count--;
+	}
+
 	cpuset_dec();
 	clear_bit(CS_ONLINE, &cs->flags);
 
@@ -2057,9 +2799,7 @@ static void cpuset_css_free(struct cgroup_subsys_state *css)
 {
 	struct cpuset *cs = css_cs(css);
 
-	free_cpumask_var(cs->effective_cpus);
-	free_cpumask_var(cs->cpus_allowed);
-	kfree(cs);
+	free_cpuset(cs);
 }
 
 static void cpuset_bind(struct cgroup_subsys_state *root_css)
@@ -2105,8 +2845,10 @@ struct cgroup_subsys cpuset_cgrp_subsys = {
 	.post_attach	= cpuset_post_attach,
 	.bind		= cpuset_bind,
 	.fork		= cpuset_fork,
-	.legacy_cftypes	= files,
+	.legacy_cftypes	= legacy_files,
+	.dfl_cftypes	= dfl_files,
 	.early_init	= true,
+	.threaded	= true,
 };
 
 /**
@@ -2121,6 +2863,7 @@ int __init cpuset_init(void)
 
 	BUG_ON(!alloc_cpumask_var(&top_cpuset.cpus_allowed, GFP_KERNEL));
 	BUG_ON(!alloc_cpumask_var(&top_cpuset.effective_cpus, GFP_KERNEL));
+	BUG_ON(!zalloc_cpumask_var(&top_cpuset.subparts_cpus, GFP_KERNEL));
 
 	cpumask_setall(top_cpuset.cpus_allowed);
 	nodes_setall(top_cpuset.mems_allowed);
@@ -2227,20 +2970,29 @@ hotplug_update_tasks(struct cpuset *cs,
 		update_tasks_nodemask(cs);
 }
 
+static bool force_rebuild;
+
+void cpuset_force_rebuild(void)
+{
+	force_rebuild = true;
+}
+
 /**
  * cpuset_hotplug_update_tasks - update tasks in a cpuset for hotunplug
  * @cs: cpuset in interest
+ * @tmp: the tmpmasks structure pointer
  *
  * Compare @cs's cpu and mem masks against top_cpuset and if some have gone
  * offline, update @cs accordingly.  If @cs ends up with no CPU or memory,
  * all its tasks are moved to the nearest ancestor with both resources.
  */
-static void cpuset_hotplug_update_tasks(struct cpuset *cs)
+static void cpuset_hotplug_update_tasks(struct cpuset *cs, struct tmpmasks *tmp)
 {
 	static cpumask_t new_cpus;
 	static nodemask_t new_mems;
 	bool cpus_updated;
 	bool mems_updated;
+	struct cpuset *parent;
 retry:
 	wait_event(cpuset_attach_wq, cs->attach_in_progress == 0);
 
@@ -2255,9 +3007,60 @@ retry:
 		goto retry;
 	}
 
-	cpumask_and(&new_cpus, cs->cpus_allowed, parent_cs(cs)->effective_cpus);
-	nodes_and(new_mems, cs->mems_allowed, parent_cs(cs)->effective_mems);
+	parent =  parent_cs(cs);
+	compute_effective_cpumask(&new_cpus, cs, parent);
+	nodes_and(new_mems, cs->mems_allowed, parent->effective_mems);
+
+	if (cs->nr_subparts_cpus)
+		/*
+		 * Make sure that CPUs allocated to child partitions
+		 * do not show up in effective_cpus.
+		 */
+		cpumask_andnot(&new_cpus, &new_cpus, cs->subparts_cpus);
+
+	if (!tmp || !cs->partition_root_state)
+		goto update_tasks;
+
+	/*
+	 * In the unlikely event that a partition root has empty
+	 * effective_cpus or its parent becomes erroneous, we have to
+	 * transition it to the erroneous state.
+	 */
+	if (is_partition_root(cs) && (cpumask_empty(&new_cpus) ||
+	   (parent->partition_root_state == PRS_ERROR))) {
+		if (cs->nr_subparts_cpus) {
+			cs->nr_subparts_cpus = 0;
+			cpumask_clear(cs->subparts_cpus);
+			compute_effective_cpumask(&new_cpus, cs, parent);
+		}
+
+		/*
+		 * If the effective_cpus is empty because the child
+		 * partitions take away all the CPUs, we can keep
+		 * the current partition and let the child partitions
+		 * fight for available CPUs.
+		 */
+		if ((parent->partition_root_state == PRS_ERROR) ||
+		     cpumask_empty(&new_cpus)) {
+			update_parent_subparts_cpumask(cs, partcmd_disable,
+						       NULL, tmp);
+			cs->partition_root_state = PRS_ERROR;
+		}
+		cpuset_force_rebuild();
+	}
+
+	/*
+	 * On the other hand, an erroneous partition root may be transitioned
+	 * back to a regular one or a partition root with no CPU allocated
+	 * from the parent may change to erroneous.
+	 */
+	if (is_partition_root(parent) &&
+	   ((cs->partition_root_state == PRS_ERROR) ||
+	    !cpumask_intersects(&new_cpus, parent->subparts_cpus)) &&
+	     update_parent_subparts_cpumask(cs, partcmd_update, NULL, tmp))
+		cpuset_force_rebuild();
 
+update_tasks:
 	cpus_updated = !cpumask_equal(&new_cpus, cs->effective_cpus);
 	mems_updated = !nodes_equal(new_mems, cs->effective_mems);
 
@@ -2271,13 +3074,6 @@ retry:
 	mutex_unlock(&cpuset_mutex);
 }
 
-static bool force_rebuild;
-
-void cpuset_force_rebuild(void)
-{
-	force_rebuild = true;
-}
-
 /**
  * cpuset_hotplug_workfn - handle CPU/memory hotunplug for a cpuset
  *
@@ -2300,6 +3096,10 @@ static void cpuset_hotplug_workfn(struct work_struct *work)
 	static nodemask_t new_mems;
 	bool cpus_updated, mems_updated;
 	bool on_dfl = is_in_v2_mode();
+	struct tmpmasks tmp, *ptmp = NULL;
+
+	if (on_dfl && !alloc_cpumasks(NULL, &tmp))
+		ptmp = &tmp;
 
 	mutex_lock(&cpuset_mutex);
 
@@ -2307,6 +3107,11 @@ static void cpuset_hotplug_workfn(struct work_struct *work)
 	cpumask_copy(&new_cpus, cpu_active_mask);
 	new_mems = node_states[N_MEMORY];
 
+	/*
+	 * If subparts_cpus is populated, it is likely that the check below
+	 * will produce a false positive on cpus_updated when the cpu list
+	 * isn't changed. It is extra work, but it is better to be safe.
+	 */
 	cpus_updated = !cpumask_equal(top_cpuset.effective_cpus, &new_cpus);
 	mems_updated = !nodes_equal(top_cpuset.effective_mems, new_mems);
 
@@ -2315,6 +3120,22 @@ static void cpuset_hotplug_workfn(struct work_struct *work)
 		spin_lock_irq(&callback_lock);
 		if (!on_dfl)
 			cpumask_copy(top_cpuset.cpus_allowed, &new_cpus);
+		/*
+		 * Make sure that CPUs allocated to child partitions
+		 * do not show up in effective_cpus. If no CPU is left,
+		 * we clear the subparts_cpus & let the child partitions
+		 * fight for the CPUs again.
+		 */
+		if (top_cpuset.nr_subparts_cpus) {
+			if (cpumask_subset(&new_cpus,
+					   top_cpuset.subparts_cpus)) {
+				top_cpuset.nr_subparts_cpus = 0;
+				cpumask_clear(top_cpuset.subparts_cpus);
+			} else {
+				cpumask_andnot(&new_cpus, &new_cpus,
+					       top_cpuset.subparts_cpus);
+			}
+		}
 		cpumask_copy(top_cpuset.effective_cpus, &new_cpus);
 		spin_unlock_irq(&callback_lock);
 		/* we don't mess with cpumasks of tasks in top_cpuset */
@@ -2343,7 +3164,7 @@ static void cpuset_hotplug_workfn(struct work_struct *work)
 				continue;
 			rcu_read_unlock();
 
-			cpuset_hotplug_update_tasks(cs);
+			cpuset_hotplug_update_tasks(cs, ptmp);
 
 			rcu_read_lock();
 			css_put(&cs->css);
@@ -2356,6 +3177,8 @@ static void cpuset_hotplug_workfn(struct work_struct *work)
 		force_rebuild = false;
 		rebuild_sched_domains();
 	}
+
+	free_cpumasks(NULL, ptmp);
 }
 
 void cpuset_update_active_cpus(void)
@@ -2666,9 +3489,9 @@ void cpuset_print_current_mems_allowed(void)
 	rcu_read_lock();
 
 	cgrp = task_cs(current)->css.cgroup;
-	pr_info("%s cpuset=", current->comm);
+	pr_cont(",cpuset=");
 	pr_cont_cgroup_name(cgrp);
-	pr_cont(" mems_allowed=%*pbl\n",
+	pr_cont(",mems_allowed=%*pbl",
 		nodemask_pr_args(&current->mems_allowed));
 
 	rcu_read_unlock();
diff --git a/kernel/cgroup/debug.c b/kernel/cgroup/debug.c
index 9caeda610249..5f1b87330bee 100644
--- a/kernel/cgroup/debug.c
+++ b/kernel/cgroup/debug.c
@@ -373,11 +373,9 @@ struct cgroup_subsys debug_cgrp_subsys = {
  * On v2, debug is an implicit controller enabled by "cgroup_debug" boot
  * parameter.
  */
-static int __init enable_cgroup_debug(char *str)
+void __init enable_debug_cgroup(void)
 {
 	debug_cgrp_subsys.dfl_cftypes = debug_files;
 	debug_cgrp_subsys.implicit_on_dfl = true;
 	debug_cgrp_subsys.threaded = true;
-	return 1;
 }
-__setup("cgroup_debug", enable_cgroup_debug);
diff --git a/kernel/cgroup/pids.c b/kernel/cgroup/pids.c
index 9829c67ebc0a..c9960baaa14f 100644
--- a/kernel/cgroup/pids.c
+++ b/kernel/cgroup/pids.c
@@ -247,7 +247,7 @@ static void pids_cancel_fork(struct task_struct *task)
 	pids_uncharge(pids, 1);
 }
 
-static void pids_free(struct task_struct *task)
+static void pids_release(struct task_struct *task)
 {
 	struct pids_cgroup *pids = css_pids(task_css(task, pids_cgrp_id));
 
@@ -342,7 +342,7 @@ struct cgroup_subsys pids_cgrp_subsys = {
 	.cancel_attach 	= pids_cancel_attach,
 	.can_fork	= pids_can_fork,
 	.cancel_fork	= pids_cancel_fork,
-	.free		= pids_free,
+	.release	= pids_release,
 	.legacy_cftypes	= pids_files,
 	.dfl_cftypes	= pids_files,
 	.threaded	= true,
diff --git a/kernel/cgroup/rdma.c b/kernel/cgroup/rdma.c
index d3bbb757ee49..1d75ae7f1cb7 100644
--- a/kernel/cgroup/rdma.c
+++ b/kernel/cgroup/rdma.c
@@ -313,10 +313,8 @@ EXPORT_SYMBOL(rdmacg_try_charge);
  * If IB stack wish a device to participate in rdma cgroup resource
  * tracking, it must invoke this API to register with rdma cgroup before
  * any user space application can start using the RDMA resources.
- * Returns 0 on success or EINVAL when table length given is beyond
- * supported size.
  */
-int rdmacg_register_device(struct rdmacg_device *device)
+void rdmacg_register_device(struct rdmacg_device *device)
 {
 	INIT_LIST_HEAD(&device->dev_node);
 	INIT_LIST_HEAD(&device->rpools);
@@ -324,7 +322,6 @@ int rdmacg_register_device(struct rdmacg_device *device)
 	mutex_lock(&rdmacg_mutex);
 	list_add_tail(&device->dev_node, &rdmacg_devices);
 	mutex_unlock(&rdmacg_mutex);
-	return 0;
 }
 EXPORT_SYMBOL(rdmacg_register_device);
 
diff --git a/kernel/cgroup/rstat.c b/kernel/cgroup/rstat.c
index d503d1a9007c..bb95a35e8c2d 100644
--- a/kernel/cgroup/rstat.c
+++ b/kernel/cgroup/rstat.c
@@ -87,7 +87,6 @@ static struct cgroup *cgroup_rstat_cpu_pop_updated(struct cgroup *pos,
 						   struct cgroup *root, int cpu)
 {
 	struct cgroup_rstat_cpu *rstatc;
-	struct cgroup *parent;
 
 	if (pos == root)
 		return NULL;
@@ -115,8 +114,8 @@ static struct cgroup *cgroup_rstat_cpu_pop_updated(struct cgroup *pos,
 	 * However, due to the way we traverse, @pos will be the first
 	 * child in most cases. The only exception is @root.
 	 */
-	parent = cgroup_parent(pos);
-	if (parent && rstatc->updated_next) {
+	if (rstatc->updated_next) {
+		struct cgroup *parent = cgroup_parent(pos);
 		struct cgroup_rstat_cpu *prstatc = cgroup_rstat_cpu(parent, cpu);
 		struct cgroup_rstat_cpu *nrstatc;
 		struct cgroup **nextp;
@@ -140,9 +139,12 @@ static struct cgroup *cgroup_rstat_cpu_pop_updated(struct cgroup *pos,
 		 * updated stat.
 		 */
 		smp_mb();
+
+		return pos;
 	}
 
-	return pos;
+	/* only happens for @root */
+	return NULL;
 }
 
 /* see cgroup_rstat_flush() */