clone3: allow spawning processes into cgroups

This adds support for creating a process in a different cgroup than its
parent. Callers can limit and account processes and threads right from
the moment they are spawned:
- A service manager can directly spawn new services into dedicated
  cgroups.
- A process can be directly created in a frozen cgroup and will be
  frozen as well.
- The initial accounting jitter experienced by process supervisors and
  daemons is eliminated with this.
- Threaded applications or even thread implementations can choose to
  create a specific cgroup layout where each thread is spawned
  directly into a dedicated cgroup.

This feature is limited to the unified hierarchy. Callers need to pass
a directory file descriptor for the target cgroup. The caller can
choose to pass an O_PATH file descriptor. All usual migration
restrictions apply, i.e. there can be no processes in inner nodes. In
general, creating a process directly in a target cgroup adheres to all
migration restrictions.

One of the biggest advantages of this feature is that CLONE_INTO_GROUP does
not need to grab the write side of the cgroup cgroup_threadgroup_rwsem.
This global lock makes moving tasks/threads around super expensive. With
clone3() this lock is avoided.

Cc: Tejun Heo <tj@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Li Zefan <lizefan@huawei.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: cgroups@vger.kernel.org
Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com>
Signed-off-by: Tejun Heo <tj@kernel.org>

include/linux/cgroup-defs.h

@@ -628,8 +628,9 @@ 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
 
 /*
@@ -119,9 +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);
@@ -705,9 +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/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/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.c

@@ -5881,8 +5881,7 @@ 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)
 {
@@ -5908,24 +5907,154 @@ static struct cgroup *cgroup_get_from_file(struct file *f)
 	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 child process
  *
+ * 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)
-	__acquires(&cgroup_threadgroup_rwsem) __releases(&cgroup_threadgroup_rwsem)
+int cgroup_can_fork(struct task_struct *child, struct kernel_clone_args *kargs)
 {
 	struct cgroup_subsys *ss;
 	int i, j, ret;
 
-	cgroup_threadgroup_change_begin(current);
+	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();
@@ -5937,32 +6066,34 @@ 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_threadgroup_change_end(current);
+	cgroup_css_set_put_fork(kargs);
 
 	return ret;
 }
 
 /**
-  * cgroup_cancel_fork - called if a fork failed after cgroup_can_fork()
-  * @child: the child process
-  *
-  * This calls the cancel_fork() callbacks if a fork failed *after*
-  * cgroup_can_fork() succeded.
-  */
-void cgroup_cancel_fork(struct task_struct *child)
-	__releases(&cgroup_threadgroup_rwsem)
+ * cgroup_cancel_fork - called if a fork failed after cgroup_can_fork()
+ * @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 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,
+			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_threadgroup_change_end(current);
+	cgroup_css_set_put_fork(kargs);
 }
 
 /**
@@ -5972,22 +6103,27 @@ void cgroup_cancel_fork(struct task_struct *child)
  * Attach the child process to its css_set calling the subsystem fork()
  * callbacks.
  */
-void cgroup_post_fork(struct task_struct *child)
-	__releases(&cgroup_threadgroup_rwsem)
+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;
 	}
 
 	/*
@@ -6020,7 +6156,16 @@ void cgroup_post_fork(struct task_struct *child)
 		ss->fork(child);
 	} while_each_subsys_mask();
 
-	cgroup_threadgroup_change_end(current);
+	/* 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);
 }
 
 /**

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

@@ -2180,7 +2180,7 @@ static __latent_entropy struct task_struct *copy_process(
 	 * 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_put_pidfd;
 
@@ -2287,7 +2287,7 @@ static __latent_entropy struct task_struct *copy_process(
 	write_unlock_irq(&tasklist_lock);
 
 	proc_fork_connector(p);
-	cgroup_post_fork(p);
+	cgroup_post_fork(p, args);
 	perf_event_fork(p);
 
 	trace_task_newtask(p, clone_flags);
@@ -2298,7 +2298,7 @@ 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);
+	cgroup_cancel_fork(p, args);
 bad_fork_put_pidfd:
 	if (clone_flags & CLONE_PIDFD) {
 		fput(pidfile);
@@ -2627,6 +2627,9 @@ 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),
@@ -2637,6 +2640,7 @@ 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 &&
@@ -2680,7 +2684,8 @@ 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;
 
 	/*