path: root/kernel/pid.c

// SPDX-License-Identifier: GPL-2.0-only
/*
 * Generic pidhash and scalable, time-bounded PID allocator
 *
 * (C) 2002-2003 Nadia Yvette Chambers, IBM
 * (C) 2004 Nadia Yvette Chambers, Oracle
 * (C) 2002-2004 Ingo Molnar, Red Hat
 *
 * pid-structures are backing objects for tasks sharing a given ID to chain
 * against. There is very little to them aside from hashing them and
 * parking tasks using given ID's on a list.
 *
 * The hash is always changed with the tasklist_lock write-acquired,
 * and the hash is only accessed with the tasklist_lock at least
 * read-acquired, so there's no additional SMP locking needed here.
 *
 * We have a list of bitmap pages, which bitmaps represent the PID space.
 * Allocating and freeing PIDs is completely lockless. The worst-case
 * allocation scenario when all but one out of 1 million PIDs possible are
 * allocated already: the scanning of 32 list entries and at most PAGE_SIZE
 * bytes. The typical fastpath is a single successful setbit. Freeing is O(1).
 *
 * Pid namespaces:
 *    (C) 2007 Pavel Emelyanov <xemul@openvz.org>, OpenVZ, SWsoft Inc.
 *    (C) 2007 Sukadev Bhattiprolu <sukadev@us.ibm.com>, IBM
 *     Many thanks to Oleg Nesterov for comments and help
 *
 */

#include <linux/mm.h>
#include <linux/export.h>
#include <linux/slab.h>
#include <linux/init.h>
#include <linux/rculist.h>
#include <linux/memblock.h>
#include <linux/pid_namespace.h>
#include <linux/init_task.h>
#include <linux/syscalls.h>
#include <linux/proc_ns.h>
#include <linux/refcount.h>
#include <linux/anon_inodes.h>
#include <linux/sched/signal.h>
#include <linux/sched/task.h>
#include <linux/idr.h>
#include <linux/pidfs.h>
#include <net/sock.h>
#include <uapi/linux/pidfd.h>

struct pid init_struct_pid = {
	.count		= REFCOUNT_INIT(1),
	.tasks		= {
		{ .first = NULL },
		{ .first = NULL },
		{ .first = NULL },
	},
	.level		= 0,
	.numbers	= { {
		.nr		= 0,
		.ns		= &init_pid_ns,
	}, }
};

static int pid_max_min = RESERVED_PIDS + 1;
static int pid_max_max = PID_MAX_LIMIT;

/*
 * PID-map pages start out as NULL, they get allocated upon
 * first use and are never deallocated. This way a low pid_max
 * value does not cause lots of bitmaps to be allocated, but
 * the scheme scales to up to 4 million PIDs, runtime.
 */
struct pid_namespace init_pid_ns = {
	.ns = NS_COMMON_INIT(init_pid_ns),
	.idr = IDR_INIT(init_pid_ns.idr),
	.pid_allocated = PIDNS_ADDING,
	.level = 0,
	.child_reaper = &init_task,
	.user_ns = &init_user_ns,
	.pid_max = PID_MAX_DEFAULT,
#if defined(CONFIG_SYSCTL) && defined(CONFIG_MEMFD_CREATE)
	.memfd_noexec_scope = MEMFD_NOEXEC_SCOPE_EXEC,
#endif
};
EXPORT_SYMBOL_GPL(init_pid_ns);

static  __cacheline_aligned_in_smp DEFINE_SPINLOCK(pidmap_lock);

void put_pid(struct pid *pid)
{
	struct pid_namespace *ns;

	if (!pid)
		return;

	ns = pid->numbers[pid->level].ns;
	if (refcount_dec_and_test(&pid->count)) {
		pidfs_free_pid(pid);
		kmem_cache_free(ns->pid_cachep, pid);
		put_pid_ns(ns);
	}
}
EXPORT_SYMBOL_GPL(put_pid);

static void delayed_put_pid(struct rcu_head *rhp)
{
	struct pid *pid = container_of(rhp, struct pid, rcu);
	put_pid(pid);
}

void free_pid(struct pid *pid)
{
	int i;
	struct pid_namespace *active_ns;

	lockdep_assert_not_held(&tasklist_lock);

	active_ns = pid->numbers[pid->level].ns;
	ns_ref_active_put(active_ns);

	spin_lock(&pidmap_lock);
	for (i = 0; i <= pid->level; i++) {
		struct upid *upid = pid->numbers + i;
		struct pid_namespace *ns = upid->ns;
		switch (--ns->pid_allocated) {
		case 2:
		case 1:
			/* When all that is left in the pid namespace
			 * is the reaper wake up the reaper.  The reaper
			 * may be sleeping in zap_pid_ns_processes().
			 */
			wake_up_process(ns->child_reaper);
			break;
		case PIDNS_ADDING:
			/* Handle a fork failure of the first process */
			WARN_ON(ns->child_reaper);
			ns->pid_allocated = 0;
			break;
		}

		idr_remove(&ns->idr, upid->nr);
	}
	spin_unlock(&pidmap_lock);

	pidfs_remove_pid(pid);
	call_rcu(&pid->rcu, delayed_put_pid);
}

void free_pids(struct pid **pids)
{
	int tmp;

	/*
	 * This can batch pidmap_lock.
	 */
	for (tmp = PIDTYPE_MAX; --tmp >= 0; )
		if (pids[tmp])
			free_pid(pids[tmp]);
}

struct pid *alloc_pid(struct pid_namespace *ns, pid_t *arg_set_tid,
		      size_t arg_set_tid_size)
{
	int set_tid[MAX_PID_NS_LEVEL + 1] = {};
	int pid_max[MAX_PID_NS_LEVEL + 1] = {};
	struct pid *pid;
	enum pid_type type;
	int i, nr;
	struct pid_namespace *tmp;
	struct upid *upid;
	int retval = -ENOMEM;
	bool retried_preload