cgroup: allow a cgroup subsystem to reject a fork

Add a new cgroup subsystem callback can_fork that conditionally
states whether or not the fork is accepted or rejected by a cgroup
policy. In addition, add a cancel_fork callback so that if an error
occurs later in the forking process, any state modified by can_fork can
be reverted.

Allow for a private opaque pointer to be passed from cgroup_can_fork to
cgroup_post_fork, allowing for the fork state to be stored by each
subsystem separately.

Also add a tagging system for cgroup_subsys.h to allow for CGROUP_<TAG>
enumerations to be be defined and used. In addition, explicitly add a
CGROUP_CANFORK_COUNT macro to make arrays easier to define.

This is in preparation for implementing the pids cgroup subsystem.

Signed-off-by: Aleksa Sarai <cyphar@cyphar.com>
Signed-off-by: Tejun Heo <tj@kernel.org>

include/linux/cgroup-defs.h

@@ -34,12 +34,17 @@ struct seq_file;
 
 /* define the enumeration of all cgroup subsystems */
 #define SUBSYS(_x) _x ## _cgrp_id,
+#define SUBSYS_TAG(_t) CGROUP_ ## _t, \
+	__unused_tag_ ## _t = CGROUP_ ## _t - 1,
 enum cgroup_subsys_id {
 #include <linux/cgroup_subsys.h>
 	CGROUP_SUBSYS_COUNT,
 };
+#undef SUBSYS_TAG
 #undef SUBSYS
 
+#define CGROUP_CANFORK_COUNT (CGROUP_CANFORK_END - CGROUP_CANFORK_START)
+
 /* bits in struct cgroup_subsys_state flags field */
 enum {
 	CSS_NO_REF	= (1 << 0), /* no reference counting for this css */
@@ -406,7 +411,9 @@ struct cgroup_subsys {
 			      struct cgroup_taskset *tset);
 	void (*attach)(struct cgroup_subsys_state *css,
 		       struct cgroup_taskset *tset);
-	void (*fork)(struct task_struct *task);
+	int (*can_fork)(struct task_struct *task, void **priv_p);
+	void (*cancel_fork)(struct task_struct *task, void *priv);
+	void (*fork)(struct task_struct *task, void *priv);
 	void (*exit)(struct cgroup_subsys_state *css,
 		     struct cgroup_subsys_state *old_css,
 		     struct task_struct *task);
@@ -491,6 +498,7 @@ static inline void cgroup_threadgroup_change_end(struct task_struct *tsk)
 
 #else	/* CONFIG_CGROUPS */
 
+#define CGROUP_CANFORK_COUNT 0
 #define CGROUP_SUBSYS_COUNT 0
 
 static inline void cgroup_threadgroup_change_begin(struct task_struct *tsk) {}

include/linux/cgroup.h

@@ -62,7 +62,12 @@ 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);
-void cgroup_post_fork(struct task_struct *p);
+extern int cgroup_can_fork(struct task_struct *p,
+			   void *ss_priv[CGROUP_CANFORK_COUNT]);
+extern void cgroup_cancel_fork(struct task_struct *p,
+			       void *ss_priv[CGROUP_CANFORK_COUNT]);
+extern void cgroup_post_fork(struct task_struct *p,
+			     void *old_ss_priv[CGROUP_CANFORK_COUNT]);
 void cgroup_exit(struct task_struct *p);
 
 int cgroup_init_early(void);
@@ -524,7 +529,13 @@ static inline int cgroupstats_build(struct cgroupstats *stats,
 				    struct dentry *dentry) { return -EINVAL; }
 
 static inline void cgroup_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,
+				  void *ss_priv[CGROUP_CANFORK_COUNT])
+{ return 0; }
+static inline void cgroup_cancel_fork(struct task_struct *p,
+				      void *ss_priv[CGROUP_CANFORK_COUNT]) {}
+static inline void cgroup_post_fork(struct task_struct *p,
+				    void *ss_priv[CGROUP_CANFORK_COUNT]) {}
 static inline void cgroup_exit(struct task_struct *p) {}
 
 static inline int cgroup_init_early(void) { return 0; }

include/linux/cgroup_subsys.h

@@ -3,6 +3,17 @@
  *
  * DO NOT ADD ANY SUBSYSTEM WITHOUT EXPLICIT ACKS FROM CGROUP MAINTAINERS.
  */
+
+/*
+ * This file *must* be included with SUBSYS() defined.
+ * SUBSYS_TAG() is a noop if undefined.
+ */
+
+#ifndef SUBSYS_TAG
+#define __TMP_SUBSYS_TAG
+#define SUBSYS_TAG(_x)
+#endif
+
 #if IS_ENABLED(CONFIG_CPUSETS)
 SUBSYS(cpuset)
 #endif
@@ -47,12 +58,24 @@ SUBSYS(net_prio)
 SUBSYS(hugetlb)
 #endif
 
+/*
+ * Subsystems that implement the can_fork() family of callbacks.
+ */
+SUBSYS_TAG(CANFORK_START)
+SUBSYS_TAG(CANFORK_END)
+
 /*
  * The following subsystems are not supported on the default hierarchy.
  */
 #if IS_ENABLED(CONFIG_CGROUP_DEBUG)
 SUBSYS(debug)
 #endif
+
+#ifdef __TMP_SUBSYS_TAG
+#undef __TMP_SUBSYS_TAG
+#undef SUBSYS_TAG
+#endif
+
 /*
  * DO NOT ADD ANY SUBSYSTEM WITHOUT EXPLICIT ACKS FROM CGROUP MAINTAINERS.
  */

kernel/cgroup.c

@@ -186,6 +186,9 @@ static u64 css_serial_nr_next = 1;
 static unsigned long have_fork_callback __read_mostly;
 static unsigned long have_exit_callback __read_mostly;
 
+/* Ditto for the can_fork callback. */
+static unsigned long have_canfork_callback __read_mostly;
+
 static struct cftype cgroup_dfl_base_files[];
 static struct cftype cgroup_legacy_base_files[];
 
@@ -4955,6 +4958,7 @@ 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_canfork_callback |= (bool)ss->can_fork << ss->id;
 
 	/* At system boot, before all subsystems have been
 	 * registered, no tasks have been forked, so we don't
@@ -5197,6 +5201,19 @@ static const struct file_operations proc_cgroupstats_operations = {
 	.release = single_release,
 };
 
+static void **subsys_canfork_priv_p(void *ss_priv[CGROUP_CANFORK_COUNT], int i)
+{
+	if (CGROUP_CANFORK_START <= i && i < CGROUP_CANFORK_END)
+		return &ss_priv[i - CGROUP_CANFORK_START];
+	return NULL;
+}
+
+static void *subsys_canfork_priv(void *ss_priv[CGROUP_CANFORK_COUNT], int i)
+{
+	void **private = subsys_canfork_priv_p(ss_priv, i);
+	return private ? *private : NULL;
+}
+
 /**
  * cgroup_fork - initialize cgroup related fields during copy_process()
  * @child: pointer to task_struct of forking parent process.
@@ -5211,6 +5228,57 @@ void cgroup_fork(struct task_struct *child)
 	INIT_LIST_HEAD(&child->cg_list);
 }
 
+/**
+ * cgroup_can_fork - called on a new task before the process is exposed
+ * @child: the task in question.
+ *
+ * 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.
+ */
+int cgroup_can_fork(struct task_struct *child,
+		    void *ss_priv[CGROUP_CANFORK_COUNT])
+{
+	struct cgroup_subsys *ss;
+	int i, j, ret;
+
+	for_each_subsys_which(ss, i, &have_canfork_callback) {
+		ret = ss->can_fork(child, subsys_canfork_priv_p(ss_priv, i));
+		if (ret)
+			goto out_revert;
+	}
+
+	return 0;
+
+out_revert:
+	for_each_subsys(ss, j) {
+		if (j >= i)
+			break;
+		if (ss->cancel_fork)
+			ss->cancel_fork(child, subsys_canfork_priv(ss_priv, j));
+	}
+
+	return ret;
+}
+
+/**
+ * cgroup_cancel_fork - called if a fork failed after cgroup_can_fork()
+ * @child: the task in question
+ *
+ * This calls the cancel_fork() callbacks if a fork failed *after*
+ * cgroup_can_fork() succeded.
+ */
+void cgroup_cancel_fork(struct task_struct *child,
+			void *ss_priv[CGROUP_CANFORK_COUNT])
+{
+	struct cgroup_subsys *ss;
+	int i;
+
+	for_each_subsys(ss, i)
+		if (ss->cancel_fork)
+			ss->cancel_fork(child, subsys_canfork_priv(ss_priv, i));
+}
+
 /**
  * cgroup_post_fork - called on a new task after adding it to the task list
  * @child: the task in question
@@ -5221,7 +5289,8 @@ void cgroup_fork(struct task_struct *child)
  * cgroup_task_iter_start() - to guarantee that the new task ends up on its
  * list.
  */
-void cgroup_post_fork(struct task_struct *child)
+void cgroup_post_fork(struct task_struct *child,
+		      void *old_ss_priv[CGROUP_CANFORK_COUNT])
 {
 	struct cgroup_subsys *ss;
 	int i;
@@ -5266,7 +5335,7 @@ void cgroup_post_fork(struct task_struct *child)
 	 * and addition to css_set.
 	 */
 	for_each_subsys_which(ss, i, &have_fork_callback)
-		ss->fork(child);
+		ss->fork(child, subsys_canfork_priv(old_ss_priv, i));
 }
 
 /**

kernel/cgroup_freezer.c

@@ -203,7 +203,7 @@ static void freezer_attach(struct cgroup_subsys_state *new_css,
  * to do anything as freezer_attach() will put @task into the appropriate
  * state.
  */
-static void freezer_fork(struct task_struct *task)
+static void freezer_fork(struct task_struct *task, void *private)
 {
 	struct freezer *freezer;
 

kernel/fork.c

@@ -1239,6 +1239,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 {
 	int retval;
 	struct task_struct *p;
+	void *cgrp_ss_priv[CGROUP_CANFORK_COUNT] = {};
 
 	if ((clone_flags & (CLONE_NEWNS|CLONE_FS)) == (CLONE_NEWNS|CLONE_FS))
 		return ERR_PTR(-EINVAL);
@@ -1512,6 +1513,16 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	INIT_LIST_HEAD(&p->thread_group);
 	p->task_works = NULL;
 
+	/*
+	 * 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, cgrp_ss_priv);
+	if (retval)
+		goto bad_fork_free_pid;
+
 	/*
 	 * Make it visible to the rest of the system, but dont wake it up yet.
 	 * Need tasklist lock for parent etc handling!
@@ -1548,7 +1559,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 		spin_unlock(&current->sighand->siglock);
 		write_unlock_irq(&tasklist_lock);
 		retval = -ERESTARTNOINTR;
-		goto bad_fork_free_pid;
+		goto bad_fork_cancel_cgroup;
 	}
 
 	if (likely(p->pid)) {
@@ -1590,7 +1601,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	write_unlock_irq(&tasklist_lock);
 
 	proc_fork_connector(p);
-	cgroup_post_fork(p);
+	cgroup_post_fork(p, cgrp_ss_priv);
 	if (clone_flags & CLONE_THREAD)
 		threadgroup_change_end(current);
 	perf_event_fork(p);
@@ -1600,6 +1611,8 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 
 	return p;
 
+bad_fork_cancel_cgroup:
+	cgroup_cancel_fork(p, cgrp_ss_priv);
 bad_fork_free_pid:
 	if (pid != &init_struct_pid)
 		free_pid(pid);

kernel/sched/core.c

@@ -8068,7 +8068,7 @@ static void cpu_cgroup_css_offline(struct cgroup_subsys_state *css)
 	sched_offline_group(tg);
 }
 
-static void cpu_cgroup_fork(struct task_struct *task)
+static void cpu_cgroup_fork(struct task_struct *task, void *private)
 {
 	sched_move_task(task);
 }