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>

4 files changed, 26 insertions, 8 deletions

diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
index 63097cb243cb..68c391f451d1 100644
--- a/include/linux/cgroup-defs.h
+++ b/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);
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index f1219b927817..4598e4da6b1b 100644
--- a/include/linux/cgroup.h
+++ b/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) {}
diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h
index f1879884238e..38359071236a 100644
--- a/include/linux/sched/task.h
+++ b/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;
 };
 
 /*
diff --git a/include/uapi/linux/sched.h b/include/uapi/linux/sched.h
index 2e3bc22c6f20..3bac0a8ceab2 100644
--- a/include/uapi/linux/sched.h
+++ b/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