linux/kernel/cgroup/pids.c

// SPDX-License-Identifier: GPL-2.0-only
/*
 * Process number limiting controller for cgroups.
 *
 * Used to allow a cgroup hierarchy to stop any new processes from fork()ing
 * after a certain limit is reached.
 *
 * Since it is trivial to hit the task limit without hitting any kmemcg limits
 * in place, PIDs are a fundamental resource. As such, PID exhaustion must be
 * preventable in the scope of a cgroup hierarchy by allowing resource limiting
 * of the number of tasks in a cgroup.
 *
 * In order to use the `pids` controller, set the maximum number of tasks in
 * pids.max (this is not available in the root cgroup for obvious reasons). The
 * number of processes currently in the cgroup is given by pids.current.
 * Organisational operations are not blocked by cgroup policies, so it is
 * possible to have pids.current > pids.max. However, it is not possible to
 * violate a cgroup policy through fork(). fork() will return -EAGAIN if forking
 * would cause a cgroup policy to be violated.
 *
 * To set a cgroup to have no limit, set pids.max to "max". This is the default
 * for all new cgroups (N.B. that PID limits are hierarchical, so the most
 * stringent limit in the hierarchy is followed).
 *
 * pids.current tracks all child cgroup hierarchies, so parent/pids.current is
 * a superset of parent/child/pids.current.
 *
 * Copyright (C) 2015 Aleksa Sarai <[email protected]>
 */

#include <linux/kernel.h>
#include <linux/threads.h>
#include <linux/atomic.h>
#include <linux/cgroup.h>
#include <linux/slab.h>
#include <linux/sched/task.h>

#define PIDS_MAX …
#define PIDS_MAX_STR …

enum pidcg_event { … };

struct pids_cgroup { … };

static struct pids_cgroup *css_pids(struct cgroup_subsys_state *css)
{ … }

static struct pids_cgroup *parent_pids(struct pids_cgroup *pids)
{ … }

static struct cgroup_subsys_state *
pids_css_alloc(struct cgroup_subsys_state *parent)
{ … }

static void pids_css_free(struct cgroup_subsys_state *css)
{ … }

static void pids_update_watermark(struct pids_cgroup *p, int64_t nr_pids)
{ … }

/**
 * pids_cancel - uncharge the local pid count
 * @pids: the pid cgroup state
 * @num: the number of pids to cancel
 *
 * This function will WARN if the pid count goes under 0, because such a case is
 * a bug in the pids controller proper.
 */
static void pids_cancel(struct pids_cgroup *pids, int num)
{ … }

/**
 * pids_uncharge - hierarchically uncharge the pid count
 * @pids: the pid cgroup state
 * @num: the number of pids to uncharge
 */
static void pids_uncharge(struct pids_cgroup *pids, int num)
{ … }

/**
 * pids_charge - hierarchically charge the pid count
 * @pids: the pid cgroup state
 * @num: the number of pids to charge
 *
 * This function does *not* follow the pid limit set. It cannot fail and the new
 * pid count may exceed the limit. This is only used for reverting failed
 * attaches, where there is no other way out than violating the limit.
 */
static void pids_charge(struct pids_cgroup *pids, int num)
{ … }

/**
 * pids_try_charge - hierarchically try to charge the pid count
 * @pids: the pid cgroup state
 * @num: the number of pids to charge
 * @fail: storage of pid cgroup causing the fail
 *
 * This function follows the set limit. It will fail if the charge would cause
 * the new value to exceed the hierarchical limit. Returns 0 if the charge
 * succeeded, otherwise -EAGAIN.
 */
static int pids_try_charge(struct pids_cgroup *pids, int num, struct pids_cgroup **fail)
{ … }

static int pids_can_attach(struct cgroup_taskset *tset)
{ … }

static void pids_cancel_attach(struct cgroup_taskset *tset)
{ … }

static void pids_event(struct pids_cgroup *pids_forking,
		       struct pids_cgroup *pids_over_limit)
{ … }

/*
 * 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, struct css_set *cset)
{ … }

static void pids_cancel_fork(struct task_struct *task, struct css_set *cset)
{ … }

static void pids_release(struct task_struct *task)
{ … }

static ssize_t pids_max_write(struct kernfs_open_file *of, char *buf,
			      size_t nbytes, loff_t off)
{ … }

static int pids_max_show(struct seq_file *sf, void *v)
{ … }

static s64 pids_current_read(struct cgroup_subsys_state *css,
			     struct cftype *cft)
{ … }

static s64 pids_peak_read(struct cgroup_subsys_state *css,
			  struct cftype *cft)
{ … }

static int __pids_events_show(struct seq_file *sf, bool local)
{ … }

static int pids_events_show(struct seq_file *sf, void *v)
{ … }

static int pids_events_local_show(struct seq_file *sf, void *v)
{ … }

static struct cftype pids_files[] = …;

static struct cftype pids_files_legacy[] = …;


struct cgroup_subsys pids_cgrp_subsys = …;