Merge branch 'for-5.7' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup

Pull cgroup updates from Tejun Heo:

 - Christian extended clone3 so that processes can be spawned into
   cgroups directly.

   This is not only neat in terms of semantics but also avoids grabbing
   the global cgroup_threadgroup_rwsem for migration.

 - Daniel added !root xattr support to cgroupfs.

   Userland already uses xattrs on cgroupfs for bookkeeping. This will
   allow delegated cgroups to support such usages.

 - Prateek tried to make cpuset hotplug handling synchronous but that
   led to possible deadlock scenarios. Reverted.

 - Other minor changes including release_agent_path handling cleanup.

* 'for-5.7' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup:
  docs: cgroup-v1: Document the cpuset_v2_mode mount option
  Revert "cpuset: Make cpuset hotplug synchronous"
  cgroupfs: Support user xattrs
  kernfs: Add option to enable user xattrs
  kernfs: Add removed_size out param for simple_xattr_set
  kernfs: kvmalloc xattr value instead of kmalloc
  cgroup: Restructure release_agent_path handling
  selftests/cgroup: add tests for cloning into cgroups
  clone3: allow spawning processes into cgroups
  cgroup: add cgroup_may_write() helper
  cgroup: refactor fork helpers
  cgroup: add cgroup_get_from_file() helper
  cgroup: unify attach permission checking
  cpuset: Make cpuset hotplug synchronous
  cgroup.c: Use built-in RCU list checking
  kselftest/cgroup: add cgroup destruction test
  cgroup: Clean up css_set task traversal

Documentation/admin-guide/cgroup-v1/cpusets.rst

@@ -223,6 +223,17 @@ cpu_online_mask using a CPU hotplug notifier, and the mems file
 automatically tracks the value of node_states[N_MEMORY]--i.e.,
 nodes with memory--using the cpuset_track_online_nodes() hook.
 
+The cpuset.effective_cpus and cpuset.effective_mems files are
+normally read-only copies of cpuset.cpus and cpuset.mems files
+respectively.  If the cpuset cgroup filesystem is mounted with the
+special "cpuset_v2_mode" option, the behavior of these files will become
+similar to the corresponding files in cpuset v2.  In other words, hotplug
+events will not change cpuset.cpus and cpuset.mems.  Those events will
+only affect cpuset.effective_cpus and cpuset.effective_mems which show
+the actual cpus and memory nodes that are currently used by this cpuset.
+See Documentation/admin-guide/cgroup-v2.rst for more information about
+cpuset v2 behavior.
+
 
 1.4 What are exclusive cpusets ?
 --------------------------------

fs/kernfs/inode.c

@@ -53,6 +53,8 @@ static struct kernfs_iattrs *__kernfs_iattrs(struct kernfs_node *kn, int alloc)
 	kn->iattr->ia_ctime = kn->iattr->ia_atime;
 
 	simple_xattrs_init(&kn->iattr->xattrs);
+	atomic_set(&kn->iattr->nr_user_xattrs, 0);
+	atomic_set(&kn->iattr->user_xattr_size, 0);
 out_unlock:
 	ret = kn->iattr;
 	mutex_unlock(&iattr_mutex);
@@ -303,7 +305,7 @@ int kernfs_xattr_set(struct kernfs_node *kn, const char *name,
 	if (!attrs)
 		return -ENOMEM;
 
-	return simple_xattr_set(&attrs->xattrs, name, value, size, flags);
+	return simple_xattr_set(&attrs->xattrs, name, value, size, flags, NULL);
 }
 
 static int kernfs_vfs_xattr_get(const struct xattr_handler *handler,
@@ -327,6 +329,86 @@ static int kernfs_vfs_xattr_set(const struct xattr_handler *handler,
 	return kernfs_xattr_set(kn, name, value, size, flags);
 }
 
+static int kernfs_vfs_user_xattr_add(struct kernfs_node *kn,
+				     const char *full_name,
+				     struct simple_xattrs *xattrs,
+				     const void *value, size_t size, int flags)
+{
+	atomic_t *sz = &kn->iattr->user_xattr_size;
+	atomic_t *nr = &kn->iattr->nr_user_xattrs;
+	ssize_t removed_size;
+	int ret;
+
+	if (atomic_inc_return(nr) > KERNFS_MAX_USER_XATTRS) {
+		ret = -ENOSPC;
+		goto dec_count_out;
+	}
+
+	if (atomic_add_return(size, sz) > KERNFS_USER_XATTR_SIZE_LIMIT) {
+		ret = -ENOSPC;
+		goto dec_size_out;
+	}
+
+	ret = simple_xattr_set(xattrs, full_name, value, size, flags,
+			       &removed_size);
+
+	if (!ret && removed_size >= 0)
+		size = removed_size;
+	else if (!ret)
+		return 0;
+dec_size_out:
+	atomic_sub(size, sz);
+dec_count_out:
+	atomic_dec(nr);
+	return ret;
+}
+
+static int kernfs_vfs_user_xattr_rm(struct kernfs_node *kn,
+				    const char *full_name,
+				    struct simple_xattrs *xattrs,
+				    const void *value, size_t size, int flags)
+{
+	atomic_t *sz = &kn->iattr->user_xattr_size;
+	atomic_t *nr = &kn->iattr->nr_user_xattrs;
+	ssize_t removed_size;
+	int ret;
+
+	ret = simple_xattr_set(xattrs, full_name, value, size, flags,
+			       &removed_size);
+
+	if (removed_size >= 0) {
+		atomic_sub(removed_size, sz);
+		atomic_dec(nr);
+	}
+
+	return ret;
+}
+
+static int kernfs_vfs_user_xattr_set(const struct xattr_handler *handler,
+				     struct dentry *unused, struct inode *inode,
+				     const char *suffix, const void *value,
+				     size_t size, int flags)
+{
+	const char *full_name = xattr_full_name(handler, suffix);
+	struct kernfs_node *kn = inode->i_private;
+	struct kernfs_iattrs *attrs;
+
+	if (!(kernfs_root(kn)->flags & KERNFS_ROOT_SUPPORT_USER_XATTR))
+		return -EOPNOTSUPP;
+
+	attrs = kernfs_iattrs(kn);
+	if (!attrs)
+		return -ENOMEM;
+
+	if (value)
+		return kernfs_vfs_user_xattr_add(kn, full_name, &attrs->xattrs,
+						 value, size, flags);
+	else
+		return kernfs_vfs_user_xattr_rm(kn, full_name, &attrs->xattrs,
+						value, size, flags);
+
+}
+
 static const struct xattr_handler kernfs_trusted_xattr_handler = {
 	.prefix = XATTR_TRUSTED_PREFIX,
 	.get = kernfs_vfs_xattr_get,
@@ -339,8 +421,15 @@ static const struct xattr_handler kernfs_security_xattr_handler = {
 	.set = kernfs_vfs_xattr_set,
 };
 
+static const struct xattr_handler kernfs_user_xattr_handler = {
+	.prefix = XATTR_USER_PREFIX,
+	.get = kernfs_vfs_xattr_get,
+	.set = kernfs_vfs_user_xattr_set,
+};
+
 const struct xattr_handler *kernfs_xattr_handlers[] = {
 	&kernfs_trusted_xattr_handler,
 	&kernfs_security_xattr_handler,
+	&kernfs_user_xattr_handler,
 	NULL
 };

fs/kernfs/kernfs-internal.h

@@ -26,6 +26,8 @@ struct kernfs_iattrs {
 	struct timespec64	ia_ctime;
 
 	struct simple_xattrs	xattrs;
+	atomic_t		nr_user_xattrs;
+	atomic_t		user_xattr_size;
 };
 
 /* +1 to avoid triggering overflow warning when negating it */

fs/xattr.c

@@ -817,7 +817,7 @@ struct simple_xattr *simple_xattr_alloc(const void *value, size_t size)
 	if (len < sizeof(*new_xattr))
 		return NULL;
 
-	new_xattr = kmalloc(len, GFP_KERNEL);
+	new_xattr = kvmalloc(len, GFP_KERNEL);
 	if (!new_xattr)
 		return NULL;
 
@@ -860,6 +860,7 @@ int simple_xattr_get(struct simple_xattrs *xattrs, const char *name,
  * @value: value of the xattr. If %NULL, will remove the attribute.
  * @size: size of the new xattr
  * @flags: %XATTR_{CREATE|REPLACE}
+ * @removed_size: returns size of the removed xattr, -1 if none removed
  *
  * %XATTR_CREATE is set, the xattr shouldn't exist already; otherwise fails
  * with -EEXIST.  If %XATTR_REPLACE is set, the xattr should exist;
@@ -868,7 +869,8 @@ int simple_xattr_get(struct simple_xattrs *xattrs, const char *name,
  * Returns 0 on success, -errno on failure.
  */
 int simple_xattr_set(struct simple_xattrs *xattrs, const char *name,
-		     const void *value, size_t size, int flags)
+		     const void *value, size_t size, int flags,
+		     ssize_t *removed_size)
 {
 	struct simple_xattr *xattr;
 	struct simple_xattr *new_xattr = NULL;
@@ -882,7 +884,7 @@ int simple_xattr_set(struct simple_xattrs *xattrs, const char *name,
 
 		new_xattr->name = kstrdup(name, GFP_KERNEL);
 		if (!new_xattr->name) {
-			kfree(new_xattr);
+			kvfree(new_xattr);
 			return -ENOMEM;
 		}
 	}
@@ -895,8 +897,12 @@ int simple_xattr_set(struct simple_xattrs *xattrs, const char *name,
 				err = -EEXIST;
 			} else if (new_xattr) {
 				list_replace(&xattr->list, &new_xattr->list);
+				if (removed_size)
+					*removed_size = xattr->size;
 			} else {
 				list_del(&xattr->list);
+				if (removed_size)
+					*removed_size = xattr->size;
 			}
 			goto out;
 		}
@@ -908,11 +914,14 @@ int simple_xattr_set(struct simple_xattrs *xattrs, const char *name,
 		list_add(&new_xattr->list, &xattrs->head);
 		xattr = NULL;
 	}
+
+	if (removed_size)
+		*removed_size = -1;
 out:
 	spin_unlock(&xattrs->lock);
 	if (xattr) {
 		kfree(xattr->name);
-		kfree(xattr);
+		kvfree(xattr);
 	}
 	return err;
 

include/linux/cgroup-defs.h

@@ -633,8 +633,9 @@ struct cgroup_subsys {
 	void (*cancel_attach)(struct cgroup_taskset *tset);
 	void (*attach)(struct cgroup_taskset *tset);
 	void (*post_attach)(void);
-	int (*can_fork)(struct task_struct *task);
-	void (*cancel_fork)(struct task_struct *task);
+	int (*can_fork)(struct task_struct *task,
+			struct css_set *cset);
+	void (*cancel_fork)(struct task_struct *task, struct css_set *cset);
 	void (*fork)(struct task_struct *task);
 	void (*exit)(struct task_struct *task);
 	void (*release)(struct task_struct *task);

include/linux/cgroup.h

@@ -27,6 +27,8 @@
 
 #include <linux/cgroup-defs.h>
 
+struct kernel_clone_args;
+
 #ifdef CONFIG_CGROUPS
 
 /*
@@ -58,9 +60,6 @@ struct css_task_iter {
 	struct list_head		*tcset_head;
 
 	struct list_head		*task_pos;
-	struct list_head		*tasks_head;
-	struct list_head		*mg_tasks_head;
-	struct list_head		*dying_tasks_head;
 
 	struct list_head		*cur_tasks_head;
 	struct css_set			*cur_cset;
@@ -122,9 +121,12 @@ int proc_cgroup_show(struct seq_file *m, struct pid_namespace *ns,
 		     struct pid *pid, struct task_struct *tsk);
 
 void cgroup_fork(struct task_struct *p);
-extern int cgroup_can_fork(struct task_struct *p);
-extern void cgroup_cancel_fork(struct task_struct *p);
-extern void cgroup_post_fork(struct task_struct *p);
+extern int cgroup_can_fork(struct task_struct *p,
+			   struct kernel_clone_args *kargs);
+extern void cgroup_cancel_fork(struct task_struct *p,
+			       struct kernel_clone_args *kargs);
+extern void cgroup_post_fork(struct task_struct *p,
+			     struct kernel_clone_args *kargs);
 void cgroup_exit(struct task_struct *p);
 void cgroup_release(struct task_struct *p);
 void cgroup_free(struct task_struct *p);
@@ -708,9 +710,12 @@ static inline int cgroupstats_build(struct cgroupstats *stats,
 				    struct dentry *dentry) { return -EINVAL; }
 
 static inline void cgroup_fork(struct task_struct *p) {}
-static inline int cgroup_can_fork(struct task_struct *p) { return 0; }
-static inline void cgroup_cancel_fork(struct task_struct *p) {}
-static inline void cgroup_post_fork(struct task_struct *p) {}
+static inline int cgroup_can_fork(struct task_struct *p,
+				  struct kernel_clone_args *kargs) { return 0; }
+static inline void cgroup_cancel_fork(struct task_struct *p,
+				      struct kernel_clone_args *kargs) {}
+static inline void cgroup_post_fork(struct task_struct *p,
+				    struct kernel_clone_args *kargs) {}
 static inline void cgroup_exit(struct task_struct *p) {}
 static inline void cgroup_release(struct task_struct *p) {}
 static inline void cgroup_free(struct task_struct *p) {}

include/linux/kernfs.h

@@ -37,8 +37,10 @@ enum kernfs_node_type {
 	KERNFS_LINK		= 0x0004,
 };
 
-#define KERNFS_TYPE_MASK	0x000f
-#define KERNFS_FLAG_MASK	~KERNFS_TYPE_MASK
+#define KERNFS_TYPE_MASK		0x000f
+#define KERNFS_FLAG_MASK		~KERNFS_TYPE_MASK
+#define KERNFS_MAX_USER_XATTRS		128
+#define KERNFS_USER_XATTR_SIZE_LIMIT	(128 << 10)
 
 enum kernfs_node_flag {
 	KERNFS_ACTIVATED	= 0x0010,
@@ -78,6 +80,11 @@ enum kernfs_root_flag {
 	 * fhandle to access nodes of the fs.
 	 */
 	KERNFS_ROOT_SUPPORT_EXPORTOP		= 0x0004,
+
+	/*
+	 * Support user xattrs to be written to nodes rooted at this root.
+	 */
+	KERNFS_ROOT_SUPPORT_USER_XATTR		= 0x0008,
 };
 
 /* type-specific structures for kernfs_node union members */

include/linux/sched/task.h

@@ -13,6 +13,7 @@
 struct task_struct;
 struct rusage;
 union thread_union;
+struct css_set;
 
 /* All the bits taken by the old clone syscall. */
 #define CLONE_LEGACY_FLAGS 0xffffffffULL
@@ -29,6 +30,9 @@ struct kernel_clone_args {
 	pid_t *set_tid;
 	/* Number of elements in *set_tid */
 	size_t set_tid_size;
+	int cgroup;
+	struct cgroup *cgrp;
+	struct css_set *cset;
 };
 
 /*

include/linux/xattr.h

@@ -102,7 +102,8 @@ struct simple_xattr *simple_xattr_alloc(const void *value, size_t size);
 int simple_xattr_get(struct simple_xattrs *xattrs, const char *name,
 		     void *buffer, size_t size);
 int simple_xattr_set(struct simple_xattrs *xattrs, const char *name,
-		     const void *value, size_t size, int flags);
+		     const void *value, size_t size, int flags,
+		     ssize_t *removed_size);
 ssize_t simple_xattr_list(struct inode *inode, struct simple_xattrs *xattrs, char *buffer,
 			  size_t size);
 void simple_xattr_list_add(struct simple_xattrs *xattrs,

include/uapi/linux/sched.h

@@ -35,6 +35,7 @@
 
 /* Flags for the clone3() syscall. */
 #define CLONE_CLEAR_SIGHAND 0x100000000ULL /* Clear any signal handler and reset to SIG_DFL. */
+#define CLONE_INTO_CGROUP 0x200000000ULL /* Clone into a specific cgroup given the right permissions. */
 
 /*
  * cloning flags intersect with CSIGNAL so can be used with unshare and clone3
@@ -81,6 +82,8 @@
  * @set_tid_size: This defines the size of the array referenced
  *                in @set_tid. This cannot be larger than the
  *                kernel's limit of nested PID namespaces.
+ * @cgroup:       If CLONE_INTO_CGROUP is specified set this to
+ *                a file descriptor for the cgroup.
  *
  * The structure is versioned by size and thus extensible.
  * New struct members must go at the end of the struct and
@@ -97,11 +100,13 @@ struct clone_args {
 	__aligned_u64 tls;
 	__aligned_u64 set_tid;
 	__aligned_u64 set_tid_size;
+	__aligned_u64 cgroup;
 };
 #endif
 
 #define CLONE_ARGS_SIZE_VER0 64 /* sizeof first published struct */
 #define CLONE_ARGS_SIZE_VER1 80 /* sizeof second published struct */
+#define CLONE_ARGS_SIZE_VER2 88 /* sizeof third published struct */
 
 /*
  * Scheduling policies

kernel/cgroup/cgroup-v1.c

@@ -38,10 +38,7 @@ static bool cgroup_no_v1_named;
  */
 static struct workqueue_struct *cgroup_pidlist_destroy_wq;
 
-/*
- * Protects cgroup_subsys->release_agent_path.  Modifying it also requires
- * cgroup_mutex.  Reading requires either cgroup_mutex or this spinlock.
- */
+/* protects cgroup_subsys->release_agent_path */
 static DEFINE_SPINLOCK(release_agent_path_lock);
 
 bool cgroup1_ssid_disabled(int ssid)
@@ -775,22 +772,29 @@ void cgroup1_release_agent(struct work_struct *work)
 {
 	struct cgroup *cgrp =
 		container_of(work, struct cgroup, release_agent_work);
-	char *pathbuf = NULL, *agentbuf = NULL;
+	char *pathbuf, *agentbuf;
 	char *argv[3], *envp[3];
 	int ret;
 
-	mutex_lock(&cgroup_mutex);
+	/* snoop agent path and exit early if empty */
+	if (!cgrp->root->release_agent_path[0])
+		return;
 
+	/* prepare argument buffers */
 	pathbuf = kmalloc(PATH_MAX, GFP_KERNEL);
-	agentbuf = kstrdup(cgrp->root->release_agent_path, GFP_KERNEL);
-	if (!pathbuf || !agentbuf || !strlen(agentbuf))
-		goto out;
+	agentbuf = kmalloc(PATH_MAX, GFP_KERNEL);
+	if (!pathbuf || !agentbuf)
+		goto out_free;
 
-	spin_lock_irq(&css_set_lock);
-	ret = cgroup_path_ns_locked(cgrp, pathbuf, PATH_MAX, &init_cgroup_ns);
-	spin_unlock_irq(&css_set_lock);
+	spin_lock(&release_agent_path_lock);
+	strlcpy(agentbuf, cgrp->root->release_agent_path, PATH_MAX);
+	spin_unlock(&release_agent_path_lock);
+	if (!agentbuf[0])
+		goto out_free;
+
+	ret = cgroup_path_ns(cgrp, pathbuf, PATH_MAX, &init_cgroup_ns);
 	if (ret < 0 || ret >= PATH_MAX)
-		goto out;
+		goto out_free;
 
 	argv[0] = agentbuf;
 	argv[1] = pathbuf;
@@ -801,11 +805,7 @@ void cgroup1_release_agent(struct work_struct *work)
 	envp[1] = "PATH=/sbin:/bin:/usr/sbin:/usr/bin";
 	envp[2] = NULL;
 
-	mutex_unlock(&cgroup_mutex);
 	call_usermodehelper(argv[0], argv, envp, UMH_WAIT_EXEC);
-	goto out_free;
-out:
-	mutex_unlock(&cgroup_mutex);
 out_free:
 	kfree(agentbuf);
 	kfree(pathbuf);

kernel/cgroup/cgroup.c

@@ -1966,7 +1966,8 @@ int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask)
 
 	root->kf_root = kernfs_create_root(kf_sops,
 					   KERNFS_ROOT_CREATE_DEACTIVATED |
-					   KERNFS_ROOT_SUPPORT_EXPORTOP,
+					   KERNFS_ROOT_SUPPORT_EXPORTOP |
+					   KERNFS_ROOT_SUPPORT_USER_XATTR,
 					   root_cgrp);
 	if (IS_ERR(root->kf_root)) {
 		ret = PTR_ERR(root->kf_root);
@@ -2726,11 +2727,7 @@ int cgroup_attach_task(struct cgroup *dst_cgrp, struct task_struct *leader,
 {
 	DEFINE_CGROUP_MGCTX(mgctx);
 	struct task_struct *task;
-	int ret;
-
-	ret = cgroup_migrate_vet_dst(dst_cgrp);
-	if (ret)
-		return ret;
+	int ret = 0;
 
 	/* look up all src csets */
 	spin_lock_irq(&css_set_lock);
@@ -4160,7 +4157,8 @@ struct cgroup_subsys_state *css_next_child(struct cgroup_subsys_state *pos,
 	} else if (likely(!(pos->flags & CSS_RELEASED))) {
 		next = list_entry_rcu(pos->sibling.next, struct cgroup_subsys_state, sibling);
 	} else {
-		list_for_each_entry_rcu(next, &parent->children, sibling)
+		list_for_each_entry_rcu(next, &parent->children, sibling,
+					lockdep_is_held(&cgroup_mutex))
 			if (next->serial_nr > pos->serial_nr)
 				break;
 	}
@@ -4403,29 +4401,24 @@ static void css_task_iter_advance_css_set(struct css_task_iter *it)
 
 	lockdep_assert_held(&css_set_lock);
 
-	/* Advance to the next non-empty css_set */
-	do {
-		cset = css_task_iter_next_css_set(it);
-		if (!cset) {
-			it->task_pos = NULL;
-			return;
+	/* Advance to the next non-empty css_set and find first non-empty tasks list*/
+	while ((cset = css_task_iter_next_css_set(it))) {
+		if (!list_empty(&cset->tasks)) {
+			it->cur_tasks_head = &cset->tasks;
+			break;
+		} else if (!list_empty(&cset->mg_tasks)) {
+			it->cur_tasks_head = &cset->mg_tasks;
+			break;
+		} else if (!list_empty(&cset->dying_tasks)) {
+			it->cur_tasks_head = &cset->dying_tasks;
+			break;
 		}
-	} while (!css_set_populated(cset) && list_empty(&cset->dying_tasks));
-
-	if (!list_empty(&cset->tasks)) {
-		it->task_pos = cset->tasks.next;
-		it->cur_tasks_head = &cset->tasks;
-	} else if (!list_empty(&cset->mg_tasks)) {
-		it->task_pos = cset->mg_tasks.next;
-		it->cur_tasks_head = &cset->mg_tasks;
-	} else {
-		it->task_pos = cset->dying_tasks.next;
-		it->cur_tasks_head = &cset->dying_tasks;
 	}
-
-	it->tasks_head = &cset->tasks;
-	it->mg_tasks_head = &cset->mg_tasks;
-	it->dying_tasks_head = &cset->dying_tasks;
+	if (!cset) {
+		it->task_pos = NULL;
+		return;
+	}
+	it->task_pos = it->cur_tasks_head->next;
 
 	/*
 	 * We don't keep css_sets locked across iteration steps and thus
@@ -4470,24 +4463,24 @@ static void css_task_iter_advance(struct css_task_iter *it)
 repeat:
 	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.
+		 * Advance iterator to find next entry. We go through cset
+		 * tasks, mg_tasks and dying_tasks, when consumed we move onto
+		 * the next cset.
 		 */
 		if (it->flags & CSS_TASK_ITER_SKIPPED)
 			it->flags &= ~CSS_TASK_ITER_SKIPPED;
 		else
 			it->task_pos = it->task_pos->next;
 
-		if (it->task_pos == it->tasks_head) {
-			it->task_pos = it->mg_tasks_head->next;
-			it->cur_tasks_head = it->mg_tasks_head;
+		if (it->task_pos == &it->cur_cset->tasks) {
+			it->cur_tasks_head = &it->cur_cset->mg_tasks;
+			it->task_pos = it->cur_tasks_head->next;
 		}
-		if (it->task_pos == it->mg_tasks_head) {
-			it->task_pos = it->dying_tasks_head->next;
-			it->cur_tasks_head = it->dying_tasks_head;
+		if (it->task_pos == &it->cur_cset->mg_tasks) {
+			it->cur_tasks_head = &it->cur_cset->dying_tasks;
+			it->task_pos = it->cur_tasks_head->next;
 		}
-		if (it->task_pos == it->dying_tasks_head)
+		if (it->task_pos == &it->cur_cset->dying_tasks)
 			css_task_iter_advance_css_set(it);
 	} else {
 		/* called from start, proceed to the first cset */
@@ -4505,12 +4498,12 @@ static void css_task_iter_advance(struct css_task_iter *it)
 			goto repeat;
 
 		/* and dying leaders w/o live member threads */
-		if (it->cur_tasks_head == it->dying_tasks_head &&
+		if (it->cur_tasks_head == &it->cur_cset->dying_tasks &&
 		    !atomic_read(&task->signal->live))
 			goto repeat;
 	} else {
 		/* skip all dying ones */
-		if (it->cur_tasks_head == it->dying_tasks_head)
+		if (it->cur_tasks_head == &it->cur_cset->dying_tasks)
 			goto repeat;
 	}
 }
@@ -4674,13 +4667,28 @@ static int cgroup_procs_show(struct seq_file *s, void *v)
 	return 0;
 }
 
+static int cgroup_may_write(const struct cgroup *cgrp, struct super_block *sb)
+{
+	int ret;
+	struct inode *inode;
+
+	lockdep_assert_held(&cgroup_mutex);
+
+	inode = kernfs_get_inode(sb, cgrp->procs_file.kn);
+	if (!inode)
+		return -ENOMEM;
+
+	ret = inode_permission(inode, MAY_WRITE);
+	iput(inode);
+	return ret;
+}
+
 static int cgroup_procs_write_permission(struct cgroup *src_cgrp,
 					 struct cgroup *dst_cgrp,
 					 struct super_block *sb)
 {
 	struct cgroup_namespace *ns = current->nsproxy->cgroup_ns;
 	struct cgroup *com_cgrp = src_cgrp;
-	struct inode *inode;
 	int ret;
 
 	lockdep_assert_held(&cgroup_mutex);
@@ -4690,12 +4698,7 @@ static int cgroup_procs_write_permission(struct cgroup *src_cgrp,
 		com_cgrp = cgroup_parent(com_cgrp);
 
 	/* %current should be authorized to migrate to the common ancestor */
-	inode = kernfs_get_inode(sb, com_cgrp->procs_file.kn);
-	if (!inode)
-		return -ENOMEM;
-
-	ret = inode_permission(inode, MAY_WRITE);
-	iput(inode);
+	ret = cgroup_may_write(com_cgrp, sb);
 	if (ret)
 		return ret;
 
@@ -4711,6 +4714,26 @@ static int cgroup_procs_write_permission(struct cgroup *src_cgrp,
 	return 0;
 }
 
+static int cgroup_attach_permissions(struct cgroup *src_cgrp,
+				     struct cgroup *dst_cgrp,
+				     struct super_block *sb, bool threadgroup)
+{
+	int ret = 0;
+
+	ret = cgroup_procs_write_permission(src_cgrp, dst_cgrp, sb);
+	if (ret)
+		return ret;
+
+	ret = cgroup_migrate_vet_dst(dst_cgrp);
+	if (ret)
+		return ret;
+
+	if (!threadgroup && (src_cgrp->dom_cgrp != dst_cgrp->dom_cgrp))
+		ret = -EOPNOTSUPP;
+
+	return ret;
+}
+
 static ssize_t cgroup_procs_write(struct kernfs_open_file *of,
 				  char *buf, size_t nbytes, loff_t off)
 {
@@ -4733,8 +4756,8 @@ static ssize_t cgroup_procs_write(struct kernfs_open_file *of,
 	src_cgrp = task_cgroup_from_root(task, &cgrp_dfl_root);
 	spin_unlock_irq(&css_set_lock);
 
-	ret = cgroup_procs_write_permission(src_cgrp, dst_cgrp,
-					    of->file->f_path.dentry->d_sb);
+	ret = cgroup_attach_permissions(src_cgrp, dst_cgrp,
+					of->file->f_path.dentry->d_sb, true);
 	if (ret)
 		goto out_finish;
 
@@ -4778,16 +4801,11 @@ static ssize_t cgroup_threads_write(struct kernfs_open_file *of,
 	spin_unlock_irq(&css_set_lock);
 
 	/* thread migrations follow the cgroup.procs delegation rule */
-	ret = cgroup_procs_write_permission(src_cgrp, dst_cgrp,
-					    of->file->f_path.dentry->d_sb);
+	ret = cgroup_attach_permissions(src_cgrp, dst_cgrp,
+					of->file->f_path.dentry->d_sb, false);
 	if (ret)
 		goto out_finish;
 
-	/* and must be contained in the same domain */
-	ret = -EOPNOTSUPP;
-	if (src_cgrp->dom_cgrp != dst_cgrp->dom_cgrp)
-		goto out_finish;
-
 	ret = cgroup_attach_task(dst_cgrp, task, false);
 
 out_finish:
@@ -5876,8 +5894,7 @@ int proc_cgroup_show(struct seq_file *m, struct pid_namespace *ns,
  * @child: pointer to task_struct of forking parent process.
  *
  * A task is associated with the init_css_set until cgroup_post_fork()
- * attaches it to the parent's css_set.  Empty cg_list indicates that
- * @child isn't holding reference to its css_set.
+ * attaches it to the target css_set.
  */
 void cgroup_fork(struct task_struct *child)
 {
@@ -5885,21 +5902,172 @@ void cgroup_fork(struct task_struct *child)
 	INIT_LIST_HEAD(&child->cg_list);
 }
 
+static struct cgroup *cgroup_get_from_file(struct file *f)
+{
+	struct cgroup_subsys_state *css;
+	struct cgroup *cgrp;
+
+	css = css_tryget_online_from_dir(f->f_path.dentry, NULL);
+	if (IS_ERR(css))
+		return ERR_CAST(css);
+
+	cgrp = css->cgroup;
+	if (!cgroup_on_dfl(cgrp)) {
+		cgroup_put(cgrp);
+		return ERR_PTR(-EBADF);
+	}
+
+	return cgrp;
+}
+
+/**
+ * cgroup_css_set_fork - find or create a css_set for a child process
+ * @kargs: the arguments passed to create the child process
+ *
+ * This functions finds or creates a new css_set which the child
+ * process will be attached to in cgroup_post_fork(). By default,
+ * the child process will be given the same css_set as its parent.
+ *
+ * If CLONE_INTO_CGROUP is specified this function will try to find an
+ * existing css_set which includes the requested cgroup and if not create
+ * a new css_set that the child will be attached to later. If this function
+ * succeeds it will hold cgroup_threadgroup_rwsem on return. If
+ * CLONE_INTO_CGROUP is requested this function will grab cgroup mutex
+ * before grabbing cgroup_threadgroup_rwsem and will hold a reference
+ * to the target cgroup.
+ */
+static int cgroup_css_set_fork(struct kernel_clone_args *kargs)
+	__acquires(&cgroup_mutex) __acquires(&cgroup_threadgroup_rwsem)
+{
+	int ret;
+	struct cgroup *dst_cgrp = NULL;
+	struct css_set *cset;
+	struct super_block *sb;
+	struct file *f;
+
+	if (kargs->flags & CLONE_INTO_CGROUP)
+		mutex_lock(&cgroup_mutex);
+
+	cgroup_threadgroup_change_begin(current);
+
+	spin_lock_irq(&css_set_lock);
+	cset = task_css_set(current);
+	get_css_set(cset);
+	spin_unlock_irq(&css_set_lock);
+
+	if (!(kargs->flags & CLONE_INTO_CGROUP)) {
+		kargs->cset = cset;
+		return 0;
+	}
+
+	f = fget_raw(kargs->cgroup);
+	if (!f) {
+		ret = -EBADF;
+		goto err;
+	}
+	sb = f->f_path.dentry->d_sb;
+
+	dst_cgrp = cgroup_get_from_file(f);
+	if (IS_ERR(dst_cgrp)) {
+		ret = PTR_ERR(dst_cgrp);
+		dst_cgrp = NULL;
+		goto err;
+	}
+
+	if (cgroup_is_dead(dst_cgrp)) {
+		ret = -ENODEV;
+		goto err;
+	}
+
+	/*
+	 * Verify that we the target cgroup is writable for us. This is
+	 * usually done by the vfs layer but since we're not going through
+	 * the vfs layer here we need to do it "manually".
+	 */
+	ret = cgroup_may_write(dst_cgrp, sb);
+	if (ret)
+		goto err;
+
+	ret = cgroup_attach_permissions(cset->dfl_cgrp, dst_cgrp, sb,
+					!(kargs->flags & CLONE_THREAD));
+	if (ret)
+		goto err;
+
+	kargs->cset = find_css_set(cset, dst_cgrp);
+	if (!kargs->cset) {
+		ret = -ENOMEM;
+		goto err;
+	}
+
+	put_css_set(cset);
+	fput(f);
+	kargs->cgrp = dst_cgrp;
+	return ret;
+
+err:
+	cgroup_threadgroup_change_end(current);
+	mutex_unlock(&cgroup_mutex);
+	if (f)
+		fput(f);
+	if (dst_cgrp)
+		cgroup_put(dst_cgrp);
+	put_css_set(cset);
+	if (kargs->cset)
+		put_css_set(kargs->cset);
+	return ret;
+}
+
+/**
+ * cgroup_css_set_put_fork - drop references we took during fork
+ * @kargs: the arguments passed to create the child process
+ *
+ * Drop references to the prepared css_set and target cgroup if
+ * CLONE_INTO_CGROUP was requested.
+ */
+static void cgroup_css_set_put_fork(struct kernel_clone_args *kargs)
+	__releases(&cgroup_threadgroup_rwsem) __releases(&cgroup_mutex)
+{
+	cgroup_threadgroup_change_end(current);
+
+	if (kargs->flags & CLONE_INTO_CGROUP) {
+		struct cgroup *cgrp = kargs->cgrp;
+		struct css_set *cset = kargs->cset;
+
+		mutex_unlock(&cgroup_mutex);
+
+		if (cset) {
+			put_css_set(cset);
+			kargs->cset = NULL;
+		}
+
+		if (cgrp) {
+			cgroup_put(cgrp);
+			kargs->cgrp = NULL;
+		}
+	}
+}
+
 /**
  * cgroup_can_fork - called on a new task before the process is exposed
- * @child: the task in question.
+ * @child: the child process
  *
- * This calls the subsystem can_fork() callbacks. If the can_fork() callback
- * returns an error, the fork aborts with that error code. This allows for
- * a cgroup subsystem to conditionally allow or deny new forks.
+ * This prepares a new css_set for the child process which the child will
+ * be attached to in cgroup_post_fork().
+ * This calls the subsystem can_fork() callbacks. If the cgroup_can_fork()
+ * callback returns an error, the fork aborts with that error code. This
+ * allows for a cgroup subsystem to conditionally allow or deny new forks.
  */
-int cgroup_can_fork(struct task_struct *child)
+int cgroup_can_fork(struct task_struct *child, struct kernel_clone_args *kargs)
 {
 	struct cgroup_subsys *ss;
 	int i, j, ret;
 
+	ret = cgroup_css_set_fork(kargs);
+	if (ret)
+		return ret;
+
 	do_each_subsys_mask(ss, i, have_canfork_callback) {
-		ret = ss->can_fork(child);
+		ret = ss->can_fork(child, kargs->cset);
 		if (ret)
 			goto out_revert;
 	} while_each_subsys_mask();
@@ -5911,54 +6079,64 @@ int cgroup_can_fork(struct task_struct *child)
 		if (j >= i)
 			break;
 		if (ss->cancel_fork)
-			ss->cancel_fork(child);
+			ss->cancel_fork(child, kargs->cset);
 	}
 
+	cgroup_css_set_put_fork(kargs);
+
 	return ret;
 }
 
 /**
  * cgroup_cancel_fork - called if a fork failed after cgroup_can_fork()
- * @child: the task in question
+ * @child: the child process
+ * @kargs: the arguments passed to create the child process
  *
  * This calls the cancel_fork() callbacks if a fork failed *after*
- * cgroup_can_fork() succeded.
+ * cgroup_can_fork() succeded and cleans up references we took to
+ * prepare a new css_set for the child process in cgroup_can_fork().
  */
-void cgroup_cancel_fork(struct task_struct *child)
+void cgroup_cancel_fork(struct task_struct *child,
+			struct kernel_clone_args *kargs)
 {
 	struct cgroup_subsys *ss;
 	int i;
 
 	for_each_subsys(ss, i)
 		if (ss->cancel_fork)
-			ss->cancel_fork(child);
+			ss->cancel_fork(child, kargs->cset);
+
+	cgroup_css_set_put_fork(kargs);
 }
 
 /**
- * cgroup_post_fork - called on a new task after adding it to the task list
- * @child: the task in question
- *
- * Adds the task to the list running through its css_set if necessary and
- * call the subsystem fork() callbacks.  Has to be after the task is
- * visible on the task list in case we race with the first call to
- * cgroup_task_iter_start() - to guarantee that the new task ends up on its
- * list.
+ * cgroup_post_fork - finalize cgroup setup for the child process
+ * @child: the child process
+ *
+ * Attach the child process to its css_set calling the subsystem fork()
+ * callbacks.
  */
-void cgroup_post_fork(struct task_struct *child)
+void cgroup_post_fork(struct task_struct *child,
+		      struct kernel_clone_args *kargs)
+	__releases(&cgroup_threadgroup_rwsem) __releases(&cgroup_mutex)
 {
 	struct cgroup_subsys *ss;
 	struct css_set *cset;
 	int i;
 
+	cset = kargs->cset;
+	kargs->cset = NULL;
+
 	spin_lock_irq(&css_set_lock);
 
 	/* init tasks are special, only link regular threads */
 	if (likely(child->pid)) {
 		WARN_ON_ONCE(!list_empty(&child->cg_list));
-		cset = task_css_set(current); /* current is @child's parent */
-		get_css_set(cset);
 		cset->nr_tasks++;
 		css_set_move_task(child, NULL, cset, false);
+	} else {
+		put_css_set(cset);
+		cset = NULL;
 	}
 
 	/*
@@ -5990,6 +6168,17 @@ void cgroup_post_fork(struct task_struct *child)
 	do_each_subsys_mask(ss, i, have_fork_callback) {
 		ss->fork(child);
 	} while_each_subsys_mask();
+
+	/* Make the new cset the root_cset of the new cgroup namespace. */
+	if (kargs->flags & CLONE_NEWCGROUP) {
+		struct css_set *rcset = child->nsproxy->cgroup_ns->root_cset;
+
+		get_css_set(cset);
+		child->nsproxy->cgroup_ns->root_cset = cset;
+		put_css_set(rcset);
+	}
+
+	cgroup_css_set_put_fork(kargs);
 }
 
 /**
@@ -6176,7 +6365,6 @@ EXPORT_SYMBOL_GPL(cgroup_get_from_path);
  */
 struct cgroup *cgroup_get_from_fd(int fd)
 {
-	struct cgroup_subsys_state *css;
 	struct cgroup *cgrp;
 	struct file *f;
 
@@ -6184,17 +6372,8 @@ struct cgroup *cgroup_get_from_fd(int fd)
 	if (!f)
 		return ERR_PTR(-EBADF);
 
-	css = css_tryget_online_from_dir(f->f_path.dentry, NULL);
+	cgrp = cgroup_get_from_file(f);
 	fput(f);
-	if (IS_ERR(css))
-		return ERR_CAST(css);
-
-	cgrp = css->cgroup;
-	if (!cgroup_on_dfl(cgrp)) {
-		cgroup_put(cgrp);
-		return ERR_PTR(-EBADF);
-	}
-
 	return cgrp;
 }
 EXPORT_SYMBOL_GPL(cgroup_get_from_fd);

kernel/cgroup/cpuset.c

@@ -358,8 +358,12 @@ static DECLARE_WORK(cpuset_hotplug_work, cpuset_hotplug_workfn);
 static DECLARE_WAIT_QUEUE_HEAD(cpuset_attach_wq);
 
 /*
- * Cgroup v2 behavior is used when on default hierarchy or the
- * cgroup_v2_mode flag is set.
+ * Cgroup v2 behavior is used on the "cpus" and "mems" control files when
+ * on default hierarchy or when the cpuset_v2_mode flag is set by mounting
+ * the v1 cpuset cgroup filesystem with the "cpuset_v2_mode" mount option.
+ * With v2 behavior, "cpus" and "mems" are always what the users have
+ * requested and won't be changed by hotplug events. Only the effective
+ * cpus or mems will be affected.
  */
 static inline bool is_in_v2_mode(void)
 {

kernel/cgroup/pids.c

@@ -33,6 +33,7 @@
 #include <linux/atomic.h>
 #include <linux/cgroup.h>
 #include <linux/slab.h>
+#include <linux/sched/task.h>
 
 #define PIDS_MAX (PID_MAX_LIMIT + 1ULL)
 #define PIDS_MAX_STR "max"
@@ -214,13 +215,16 @@ static void pids_cancel_attach(struct cgroup_taskset *tset)
  * task_css_check(true) in pids_can_fork() and pids_cancel_fork() relies
  * on cgroup_threadgroup_change_begin() held by the copy_process().
  */
-static int pids_can_fork(struct task_struct *task)
+static int pids_can_fork(struct task_struct *task, struct css_set *cset)
 {
 	struct cgroup_subsys_state *css;
 	struct pids_cgroup *pids;
 	int err;
 
-	css = task_css_check(current, pids_cgrp_id, true);
+	if (cset)
+		css = cset->subsys[pids_cgrp_id];
+	else
+		css = task_css_check(current, pids_cgrp_id, true);
 	pids = css_pids(css);
 	err = pids_try_charge(pids, 1);
 	if (err) {
@@ -235,12 +239,15 @@ static int pids_can_fork(struct task_struct *task)
 	return err;
 }
 
-static void pids_cancel_fork(struct task_struct *task)
+static void pids_cancel_fork(struct task_struct *task, struct css_set *cset)
 {
 	struct cgroup_subsys_state *css;
 	struct pids_cgroup *pids;
 
-	css = task_css_check(current, pids_cgrp_id, true);
+	if (cset)
+		css = cset->subsys[pids_cgrp_id];
+	else
+		css = task_css_check(current, pids_cgrp_id, true);
 	pids = css_pids(css);
 	pids_uncharge(pids, 1);
 }

kernel/fork.c

@@ -2176,16 +2176,15 @@ static __latent_entropy struct task_struct *copy_process(
 	INIT_LIST_HEAD(&p->thread_group);
 	p->task_works = NULL;
 
-	cgroup_threadgroup_change_begin(current);
 	/*
 	 * Ensure that the cgroup subsystem policies allow the new process to be
 	 * forked. It should be noted the the new process's css_set can be changed
 	 * between here and cgroup_post_fork() if an organisation operation is in
 	 * progress.
 	 */
-	retval = cgroup_can_fork(p);
+	retval = cgroup_can_fork(p, args);
 	if (retval)
-		goto bad_fork_cgroup_threadgroup_change_end;
+		goto bad_fork_put_pidfd;
 
 	/*
 	 * From this point on we must avoid any synchronous user-space
@@ -2290,8 +2289,7 @@ static __latent_entropy struct task_struct *copy_process(
 	write_unlock_irq(&tasklist_lock);
 
 	proc_fork_connector(p);
-	cgroup_post_fork(p);
-	cgroup_threadgroup_change_end(current);
+	cgroup_post_fork(p, args);
 	perf_event_fork(p);
 
 	trace_task_newtask(p, clone_flags);
@@ -2302,9 +2300,7 @@ static __latent_entropy struct task_struct *copy_process(
 bad_fork_cancel_cgroup:
 	spin_unlock(&current->sighand->siglock);
 	write_unlock_irq(&tasklist_lock);
-	cgroup_cancel_fork(p);
-bad_fork_cgroup_threadgroup_change_end:
-	cgroup_threadgroup_change_end(current);
+	cgroup_cancel_fork(p, args);
 bad_fork_put_pidfd:
 	if (clone_flags & CLONE_PIDFD) {
 		fput(pidfile);
@@ -2633,6 +2629,9 @@ noinline static int copy_clone_args_from_user(struct kernel_clone_args *kargs,
 		     !valid_signal(args.exit_signal)))
 		return -EINVAL;
 
+	if ((args.flags & CLONE_INTO_CGROUP) && args.cgroup < 0)
+		return -EINVAL;
+
 	*kargs = (struct kernel_clone_args){
 		.flags		= args.flags,
 		.pidfd		= u64_to_user_ptr(args.pidfd),
@@ -2643,6 +2642,7 @@ noinline static int copy_clone_args_from_user(struct kernel_clone_args *kargs,
 		.stack_size	= args.stack_size,
 		.tls		= args.tls,
 		.set_tid_size	= args.set_tid_size,
+		.cgroup		= args.cgroup,
 	};
 
 	if (args.set_tid &&
@@ -2686,7 +2686,8 @@ static inline bool clone3_stack_valid(struct kernel_clone_args *kargs)
 static bool clone3_args_valid(struct kernel_clone_args *kargs)
 {
 	/* Verify that no unknown flags are passed along. */
-	if (kargs->flags & ~(CLONE_LEGACY_FLAGS | CLONE_CLEAR_SIGHAND))
+	if (kargs->flags &
+	    ~(CLONE_LEGACY_FLAGS | CLONE_CLEAR_SIGHAND | CLONE_INTO_CGROUP))
 		return false;
 
 	/*

mm/shmem.c

@@ -3243,7 +3243,7 @@ static int shmem_xattr_handler_set(const struct xattr_handler *handler,
 	struct shmem_inode_info *info = SHMEM_I(inode);
 
 	name = xattr_full_name(handler, name);
-	return simple_xattr_set(&info->xattrs, name, value, size, flags);
+	return simple_xattr_set(&info->xattrs, name, value, size, flags, NULL);
 }
 
 static const struct xattr_handler shmem_security_xattr_handler = {

tools/testing/selftests/cgroup/Makefile

@@ -11,6 +11,6 @@ TEST_GEN_PROGS += test_freezer
 
 include ../lib.mk
 
-$(OUTPUT)/test_memcontrol: cgroup_util.c
-$(OUTPUT)/test_core: cgroup_util.c
-$(OUTPUT)/test_freezer: cgroup_util.c
+$(OUTPUT)/test_memcontrol: cgroup_util.c ../clone3/clone3_selftests.h
+$(OUTPUT)/test_core: cgroup_util.c ../clone3/clone3_selftests.h
+$(OUTPUT)/test_freezer: cgroup_util.c ../clone3/clone3_selftests.h

tools/testing/selftests/cgroup/cgroup_util.c

@@ -15,6 +15,7 @@
 #include <unistd.h>
 
 #include "cgroup_util.h"
+#include "../clone3/clone3_selftests.h"
 
 static ssize_t read_text(const char *path, char *buf, size_t max_len)
 {
@@ -331,12 +332,112 @@ int cg_run(const char *cgroup,
 	}
 }
 
+pid_t clone_into_cgroup(int cgroup_fd)
+{
+#ifdef CLONE_ARGS_SIZE_VER2
+	pid_t pid;
+
+	struct clone_args args = {
+		.flags = CLONE_INTO_CGROUP,
+		.exit_signal = SIGCHLD,
+		.cgroup = cgroup_fd,
+	};
+
+	pid = sys_clone3(&args, sizeof(struct clone_args));
+	/*
+	 * Verify that this is a genuine test failure:
+	 * ENOSYS -> clone3() not available
+	 * E2BIG  -> CLONE_INTO_CGROUP not available
+	 */
+	if (pid < 0 && (errno == ENOSYS || errno == E2BIG))
+		goto pretend_enosys;
+
+	return pid;
+
+pretend_enosys:
+#endif
+	errno = ENOSYS;
+	return -ENOSYS;
+}
+
+int clone_reap(pid_t pid, int options)
+{
+	int ret;
+	siginfo_t info = {
+		.si_signo = 0,
+	};
+
+again:
+	ret = waitid(P_PID, pid, &info, options | __WALL | __WNOTHREAD);
+	if (ret < 0) {
+		if (errno == EINTR)
+			goto again;
+		return -1;
+	}
+
+	if (options & WEXITED) {
+		if (WIFEXITED(info.si_status))
+			return WEXITSTATUS(info.si_status);
+	}
+
+	if (options & WSTOPPED) {
+		if (WIFSTOPPED(info.si_status))
+			return WSTOPSIG(info.si_status);
+	}
+
+	if (options & WCONTINUED) {
+		if (WIFCONTINUED(info.si_status))
+			return 0;
+	}
+
+	return -1;
+}
+
+int dirfd_open_opath(const char *dir)
+{
+	return open(dir, O_DIRECTORY | O_CLOEXEC | O_NOFOLLOW | O_PATH);
+}
+
+#define close_prot_errno(fd)                                                   \
+	if (fd >= 0) {                                                         \
+		int _e_ = errno;                                               \
+		close(fd);                                                     \
+		errno = _e_;                                                   \
+	}
+
+static int clone_into_cgroup_run_nowait(const char *cgroup,
+					int (*fn)(const char *cgroup, void *arg),
+					void *arg)
+{
+	int cgroup_fd;
+	pid_t pid;
+
+	cgroup_fd =  dirfd_open_opath(cgroup);
+	if (cgroup_fd < 0)
+		return -1;
+
+	pid = clone_into_cgroup(cgroup_fd);
+	close_prot_errno(cgroup_fd);
+	if (pid == 0)
+		exit(fn(cgroup, arg));
+
+	return pid;
+}
+
 int cg_run_nowait(const char *cgroup,
 		  int (*fn)(const char *cgroup, void *arg),
 		  void *arg)
 {
 	int pid;
 
+	pid = clone_into_cgroup_run_nowait(cgroup, fn, arg);
+	if (pid > 0)
+		return pid;
+
+	/* Genuine test failure. */
+	if (pid < 0 && errno != ENOSYS)
+		return -1;
+
 	pid = fork();
 	if (pid == 0) {
 		char buf[64];
@@ -450,3 +551,28 @@ int proc_read_strstr(int pid, bool thread, const char *item, const char *needle)
 
 	return strstr(buf, needle) ? 0 : -1;
 }
+
+int clone_into_cgroup_run_wait(const char *cgroup)
+{
+	int cgroup_fd;
+	pid_t pid;
+
+	cgroup_fd =  dirfd_open_opath(cgroup);
+	if (cgroup_fd < 0)
+		return -1;
+
+	pid = clone_into_cgroup(cgroup_fd);
+	close_prot_errno(cgroup_fd);
+	if (pid < 0)
+		return -1;
+
+	if (pid == 0)
+		exit(EXIT_SUCCESS);
+
+	/*
+	 * We don't care whether this fails. We only care whether the initial
+	 * clone succeeded.
+	 */
+	(void)clone_reap(pid, WEXITED);
+	return 0;
+}

tools/testing/selftests/cgroup/cgroup_util.h

@@ -50,3 +50,7 @@ extern int cg_wait_for_proc_count(const char *cgroup, int count);
 extern int cg_killall(const char *cgroup);
 extern ssize_t proc_read_text(int pid, bool thread, const char *item, char *buf, size_t size);
 extern int proc_read_strstr(int pid, bool thread, const char *item, const char *needle);
+extern pid_t clone_into_cgroup(int cgroup_fd);
+extern int clone_reap(pid_t pid, int options);
+extern int clone_into_cgroup_run_wait(const char *cgroup);
+extern int dirfd_open_opath(const char *dir);

tools/testing/selftests/cgroup/test_core.c

@@ -2,7 +2,10 @@
 
 #include <linux/limits.h>
 #include <sys/types.h>
+#include <sys/mman.h>
+#include <sys/wait.h>
 #include <unistd.h>
+#include <fcntl.h>
 #include <stdio.h>
 #include <errno.h>
 #include <signal.h>
@@ -12,6 +15,115 @@
 #include "../kselftest.h"
 #include "cgroup_util.h"
 
+static int touch_anon(char *buf, size_t size)
+{
+	int fd;
+	char *pos = buf;
+
+	fd = open("/dev/urandom", O_RDONLY);
+	if (fd < 0)
+		return -1;
+
+	while (size > 0) {
+		ssize_t ret = read(fd, pos, size);
+
+		if (ret < 0) {
+			if (errno != EINTR) {
+				close(fd);
+				return -1;
+			}
+		} else {
+			pos += ret;
+			size -= ret;
+		}
+	}
+	close(fd);
+
+	return 0;
+}
+
+static int alloc_and_touch_anon_noexit(const char *cgroup, void *arg)
+{
+	int ppid = getppid();
+	size_t size = (size_t)arg;
+	void *buf;
+
+	buf = mmap(NULL, size, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANON,
+		   0, 0);
+	if (buf == MAP_FAILED)
+		return -1;
+
+	if (touch_anon((char *)buf, size)) {
+		munmap(buf, size);
+		return -1;
+	}
+
+	while (getppid() == ppid)
+		sleep(1);
+
+	munmap(buf, size);
+	return 0;
+}
+
+/*
+ * Create a child process that allocates and touches 100MB, then waits to be
+ * killed. Wait until the child is attached to the cgroup, kill all processes
+ * in that cgroup and wait until "cgroup.procs" is empty. At this point try to
+ * destroy the empty cgroup. The test helps detect race conditions between
+ * dying processes leaving the cgroup and cgroup destruction path.
+ */
+static int test_cgcore_destroy(const char *root)
+{
+	int ret = KSFT_FAIL;
+	char *cg_test = NULL;
+	int child_pid;
+	char buf[PAGE_SIZE];
+
+	cg_test = cg_name(root, "cg_test");
+
+	if (!cg_test)
+		goto cleanup;
+
+	for (int i = 0; i < 10; i++) {
+		if (cg_create(cg_test))
+			goto cleanup;
+
+		child_pid = cg_run_nowait(cg_test, alloc_and_touch_anon_noexit,
+					  (void *) MB(100));
+
+		if (child_pid < 0)
+			goto cleanup;
+
+		/* wait for the child to enter cgroup */
+		if (cg_wait_for_proc_count(cg_test, 1))
+			goto cleanup;
+
+		if (cg_killall(cg_test))
+			goto cleanup;
+
+		/* wait for cgroup to be empty */
+		while (1) {
+			if (cg_read(cg_test, "cgroup.procs", buf, sizeof(buf)))
+				goto cleanup;
+			if (buf[0] == '\0')
+				break;
+			usleep(1000);
+		}
+
+		if (rmdir(cg_test))
+			goto cleanup;
+
+		if (waitpid(child_pid, NULL, 0) < 0)
+			goto cleanup;
+	}
+	ret = KSFT_PASS;
+cleanup:
+	if (cg_test)
+		cg_destroy(cg_test);
+	free(cg_test);
+	return ret;
+}
+
 /*
  * A(0) - B(0) - C(1)
  *        \ D(0)
@@ -25,8 +137,11 @@
 static int test_cgcore_populated(const char *root)
 {
 	int ret = KSFT_FAIL;
+	int err;
 	char *cg_test_a = NULL, *cg_test_b = NULL;
 	char *cg_test_c = NULL, *cg_test_d = NULL;
+	int cgroup_fd = -EBADF;
+	pid_t pid;
 
 	cg_test_a = cg_name(root, "cg_test_a");
 	cg_test_b = cg_name(root, "cg_test_a/cg_test_b");
@@ -78,6 +193,52 @@ static int test_cgcore_populated(const char *root)
 	if (cg_read_strcmp(cg_test_d, "cgroup.events", "populated 0\n"))
 		goto cleanup;
 
+	/* Test that we can directly clone into a new cgroup. */
+	cgroup_fd = dirfd_open_opath(cg_test_d);
+	if (cgroup_fd < 0)
+		goto cleanup;
+
+	pid = clone_into_cgroup(cgroup_fd);
+	if (pid < 0) {
+		if (errno == ENOSYS)
+			goto cleanup_pass;
+		goto cleanup;
+	}
+
+	if (pid == 0) {
+		if (raise(SIGSTOP))
+			exit(EXIT_FAILURE);
+		exit(EXIT_SUCCESS);
+	}
+
+	err = cg_read_strcmp(cg_test_d, "cgroup.events", "populated 1\n");
+
+	(void)clone_reap(pid, WSTOPPED);
+	(void)kill(pid, SIGCONT);
+	(void)clone_reap(pid, WEXITED);
+
+	if (err)
+		goto cleanup;
+
+	if (cg_read_strcmp(cg_test_d, "cgroup.events", "populated 0\n"))
+		goto cleanup;
+
+	/* Remove cgroup. */
+	if (cg_test_d) {
+		cg_destroy(cg_test_d);
+		free(cg_test_d);
+		cg_test_d = NULL;
+	}
+
+	pid = clone_into_cgroup(cgroup_fd);
+	if (pid < 0)
+		goto cleanup_pass;
+	if (pid == 0)
+		exit(EXIT_SUCCESS);
+	(void)clone_reap(pid, WEXITED);
+	goto cleanup;
+
+cleanup_pass:
 	ret = KSFT_PASS;
 
 cleanup:
@@ -93,6 +254,8 @@ static int test_cgcore_populated(const char *root)
 	free(cg_test_c);
 	free(cg_test_b);
 	free(cg_test_a);
+	if (cgroup_fd >= 0)
+		close(cgroup_fd);
 	return ret;
 }
 
@@ -136,6 +299,16 @@ static int test_cgcore_invalid_domain(const char *root)
 	if (errno != EOPNOTSUPP)
 		goto cleanup;
 
+	if (!clone_into_cgroup_run_wait(child))
+		goto cleanup;
+
+	if (errno == ENOSYS)
+		goto cleanup_pass;
+
+	if (errno != EOPNOTSUPP)
+		goto cleanup;
+
+cleanup_pass:
 	ret = KSFT_PASS;
 
 cleanup:
@@ -345,6 +518,9 @@ static int test_cgcore_internal_process_constraint(const char *root)
 	if (!cg_enter_current(parent))
 		goto cleanup;
 
+	if (!clone_into_cgroup_run_wait(parent))
+		goto cleanup;
+
 	ret = KSFT_PASS;
 
 cleanup:
@@ -512,6 +688,7 @@ struct corecg_test {
 	T(test_cgcore_populated),
 	T(test_cgcore_proc_migration),
 	T(test_cgcore_thread_migration),
+	T(test_cgcore_destroy),
 };
 #undef T
 

tools/testing/selftests/clone3/clone3_selftests.h

@@ -5,12 +5,24 @@
 
 #define _GNU_SOURCE
 #include <sched.h>
+#include <linux/sched.h>
+#include <linux/types.h>
 #include <stdint.h>
 #include <syscall.h>
-#include <linux/types.h>
+#include <sys/wait.h>
+
+#include "../kselftest.h"
 
 #define ptr_to_u64(ptr) ((__u64)((uintptr_t)(ptr)))
 
+#ifndef CLONE_INTO_CGROUP
+#define CLONE_INTO_CGROUP 0x200000000ULL /* Clone into a specific cgroup given the right permissions. */
+#endif
+
+#ifndef CLONE_ARGS_SIZE_VER0
+#define CLONE_ARGS_SIZE_VER0 64
+#endif
+
 #ifndef __NR_clone3
 #define __NR_clone3 -1
 struct clone_args {
@@ -22,10 +34,13 @@ struct clone_args {
 	__aligned_u64 stack;
 	__aligned_u64 stack_size;
 	__aligned_u64 tls;
+#define CLONE_ARGS_SIZE_VER1 80
 	__aligned_u64 set_tid;
 	__aligned_u64 set_tid_size;
+#define CLONE_ARGS_SIZE_VER2 88
+	__aligned_u64 cgroup;
 };
-#endif
+#endif /* __NR_clone3 */
 
 static pid_t sys_clone3(struct clone_args *args, size_t size)
 {