path: root/ipc/mqueue.c

/*
 * POSIX message queues filesystem for Linux.
 *
 * Copyright (C) 2003,2004  Krzysztof Benedyczak    (golbi@mat.uni.torun.pl)
 *                          Michal Wronski          (michal.wronski@gmail.com)
 *
 * Spinlocks:               Mohamed Abbas           (abbas.mohamed@intel.com)
 * Lockless receive & send, fd based notify:
 *			    Manfred Spraul	    (manfred@colorfullife.com)
 *
 * Audit:                   George Wilson           (ltcgcw@us.ibm.com)
 *
 * This file is released under the GPL.
 */

#include <linux/capability.h>
#include <linux/init.h>
#include <linux/pagemap.h>
#include <linux/file.h>
#include <linux/mount.h>
#include <linux/fs_context.h>
#include <linux/namei.h>
#include <linux/sysctl.h>
#include <linux/poll.h>
#include <linux/mqueue.h>
#include <linux/msg.h>
#include <linux/skbuff.h>
#include <linux/vmalloc.h>
#include <linux/netlink.h>
#include <linux/syscalls.h>
#include <linux/audit.h>
#include <linux/signal.h>
#include <linux/mutex.h>
#include <linux/nsproxy.h>
#include <linux/pid.h>
#include <linux/ipc_namespace.h>
#include <linux/user_namespace.h>
#include <linux/slab.h>
#include <linux/sched/wake_q.h>
#include <linux/sched/signal.h>
#include <linux/sched/user.h>

#include <net/sock.h>
#include "util.h"

struct mqueue_fs_context {
	struct ipc_namespace	*ipc_ns;
	bool			 newns;	/* Set if newly created ipc namespace */
};

#define MQUEUE_MAGIC	0x19800202
#define DIRENT_SIZE	20
#define FILENT_SIZE	80

#define SEND		0
#define RECV		1

#define STATE_NONE	0
#define STATE_READY	1

struct posix_msg_tree_node {
	struct rb_node		rb_node;
	struct list_head	msg_list;
	int			priority;
};

/*
 * Locking:
 *
 * Accesses to a message queue are synchronized by acquiring info->lock.
 *
 * There are two notable exceptions:
 * - The actual wakeup of a sleeping task is performed using the wake_q
 *   framework. info->lock is already released when wake_up_q is called.
 * - The exit codepaths after sleeping check ext_wait_queue->state without
 *   any locks. If it is STATE_READY, then the syscall is completed without
 *   acquiring info->lock.
 *
 * MQ_BARRIER:
 * To achieve proper release/acquire memory barrier pairing, the state is