Gentoo中文社区

/*
 * POSIX message queues filesystem for Linux.
 *
 * Copyright (C) 2003,2004  Krzysztof Benedyczak    ([email protected])
 *                          Michal Wronski          ([email protected])
 *
 * Spinlocks:               Mohamed Abbas           ([email protected])
 * Lockless receive & send, fd based notify:
 *			    Manfred Spraul	    ([email protected])
 *
 * Audit:                   George Wilson           ([email protected])
 *
 * 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;
};

#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;
};

struct ext_wait_queue {		/* queue of sleeping tasks */
	struct task_struct *task;
	struct list_head list;
	struct msg_msg *msg;	/* ptr of loaded message */
	int state;		/* one of STATE_* values */
};

struct mqueue_inode_info {
	spinlock_t lock;
	struct inode vfs_inode;
	wait_queue_head_t wait_q;

	struct rb_root msg_tree;
	struct rb_node *msg_tree_rightmost;
	struct posix_msg_tree_node *node_cache;
	struct mq_attr attr;

	struct sigevent notify;
	struct pid *notify_owner;
	struct user_namespace *notify_user_ns;
	struct user_struct *user;	/* user who created, for accounting */
	struct sock *notify_sock;
	struct sk_buff *notify_cookie;

	/* for tasks waiting for free space and messages, respectively */
	struct ext_wait_queue e_wait_q[2];

	unsigned long qsize; /* size of queue in memory (sum of all msgs) */
};

static struct file_system_type mqueue_fs_type;
static const struct inode_operations mqueue_dir_inode_operations;
static const struct file_operations mqueue_file_operations;
static const struct super_operations mqueue_super_ops;
static const struct fs_context_operations mqueue_fs_context_ops;
static void remove_notification(struct mqueue_inode_info *info);

static struct kmem_cache *mqueue_inode_cachep;

static struct ctl_table_header *mq_sysctl_table;

static inline struct mqueue_inode_info *MQUEUE_I(struct inode *inode)
{
	return container_of(inode, struct mqueue_inode_info, vfs_inode);
}

/*
 * This routine should be called with the mq_lock held.
 */
static inline struct ipc_namespace *__get_ns_from_inode(struct inode *inode)
{
	return get_ipc_ns(inode->i_sb->s_fs_info);
}

static struct ipc_namespace *get_ns_from_inode(struct inode *inode)
{
	struct ipc_namespace *ns;

	spin_lock(&mq_lock);
	ns = __get_ns_from_inode(inode);
	spin_unlock(&mq_lock);
	return ns;
}

/* Auxiliary functions to manipulate messages' list */
static int msg_insert(struct msg_msg *msg, struct mqueue_inode_info *info)
{
	struct rb_node **p, *parent = NULL;
	struct posix_msg_tree_node *leaf;
	bool rightmost = true;

	p = &info->msg_tree.rb_node;
	while (*p) {
		parent = *p;
		leaf = rb_entry(parent, struct posix_msg_tree_node, rb_node);

		if (likely(leaf->priority == msg->m_type))
			goto insert_msg;
		else if (msg->m_type < leaf->priority) {
			p = &(*p)->rb_left;
			rightmost = false;
		} else
			p = &(*p)->rb_right;
	}
	if (info->node_cache) {
		leaf = info->node_cache;
		info->node_cache = NULL;
	} else {
		leaf = kmalloc(sizeof(*leaf), GFP_ATOMIC);
		if (!leaf)
			return -ENOMEM;
		INIT_LIST_HEAD(&leaf->msg_list);
	}
	leaf->priority = msg->m_type;

	if (rightmost)
		info->msg_tree_rightmost = &leaf->rb_node;

	rb_link_node(&leaf->rb_node, parent, p);
	rb_insert_color(&leaf->rb_node, &info->msg_tree);
insert_msg:
	info->attr.mq_curmsgs++;
	info->qsize += msg->m_ts;
	list_add_tail(&msg->m_list, &leaf->msg_list);
	return 0;
}

static inline void msg_tree_erase(struct posix_msg_tree_node *leaf,
				  struct mqueue_inode_info *info)
{
	struct rb_node *node = &leaf->rb_node;

	if (info->msg_tree_rightmost == node)
		info->msg_tree_rightmost = rb_prev(node);

	rb_erase(node, &info->msg_tree);
	if (info->node_cache) {
		kfree(leaf);
	} else {
		info->node_cache = leaf;
	}
}

static inline struct msg_msg *msg_get(struct mqueue_inode_info *info)
{
	struct rb_node *parent = NULL;
	struct posix_msg_tree_node *leaf;
	struct msg_msg *msg;

try_again:
	/*
	 * During insert, low priorities go to the left and high to the
	 * right.  On receive, we want the highest priorities first, so
	 * walk all the way to the right.
	 */
	parent = info->msg_tree_rightmost;
	if (!parent) {
		if (info->attr.mq_curmsgs) {
			pr_warn_once("Inconsistency in POSIX message queue, "
				     "no tree element, but supposedly messages "
				     "should exist!\n");
			info->attr.mq_curmsgs = 0;
		}
		return NULL;
	}
	leaf = rb_entry(parent, struct posix_msg_tree_node, rb_node);
	if (unlikely(list_empty(&leaf->msg_list))) {
		pr_warn_once("Inconsistency in POSIX message queue, "
			     "empty leaf node but we haven't implemented "
			     "lazy leaf delete!\n");
		msg_tree_erase(leaf, info);
		goto try_again;
	} else {
		msg = list_first_entry(&leaf->msg_list,
				       struct msg_msg, m_list);
		list_del(&msg->m_list);
		if (list_empty(&leaf->msg_list)) {
			msg_tree_erase(leaf, info);
		}
	}
	info->attr.mq_curmsgs--;
	info->qsize -= msg->m_ts;
	return msg;
}

static struct inode *mqueue_get_inode(struct super_block *sb,
		struct ipc_namespace *ipc_ns, umode_t mode,
		struct mq_attr *attr)
{
	struct user_struct *u = current_user();
	struct inode *inode;
	int ret = -ENOMEM;

	inode = new_inode(sb);
	if (!inode)
		goto err;

	inode->i_ino = get_next_ino();
	inode->i_mode = mode;
	inode->i_uid = current_fsuid();
	inode->i_gid = current_fsgid();
	inode->i_mtime = inode->i_ctime = inode->i_atime = current_time(inode);

	if (S_ISREG(mode)) {
		struct mqueue_inode_info *info;
		unsigned long mq_bytes, mq_treesize;

		inode->i_fop = &mqueue_file_operations;
		inode->i_size = FILENT_SIZE;
		/* mqueue specific info */
		info = MQUEUE_I(inode);
		spin_lock_init(&info->lock);
		init_waitqueue_head(&info->wait_q);
		INIT_LIST_HEAD(&info->e_wait_q[0].list);
		INIT_LIST_HEAD(&info->e_wait_q[1].list);
		info->notify_owner = NULL;
		info->notify_user_ns = NULL;
		info->qsize = 0;
		info->user = NULL;	/* set when all is ok */
		info->msg_tree = RB_ROOT;
		info->msg_tree_rightmost = NULL;
		info->node_cache = NULL;
		memset(&info->attr, 0, sizeof(info->attr));
		info->attr.mq_maxmsg = min(ipc_ns->mq_msg_max,
					   ipc_ns->mq_msg_default);
		info->attr.mq_msgsize = min(ipc_ns->mq_msgsize_max,
					    ipc_ns->mq_msgsize_default);
		if (attr) {
			info->attr.mq_maxmsg = attr->mq_maxmsg;
			info->attr.mq_msgsize = attr->mq_msgsize;
		}
		/*
		 * We used to allocate a static array of pointers and account
		 * the size of that array as well as one msg_msg struct per
		 * possible message into the queue size. That's no longer
		 * accurate as the queue is now an rbtree and will grow and
		 * shrink depending on usage patterns.  We can, however, still
		 * account one msg_msg struct per message, but the nodes are
		 * allocated depending on priority usage, and most programs
		 * only use one, or a handful, of priorities.  However, since
		 * this is pinned memory, we need to assume worst case, so
		 * that means the min(mq_maxmsg, max_priorities) * struct
		 * posix_msg_tree_node.
		 */

		ret = -EINVAL;
		if (info->attr.mq_maxmsg <= 0 || info->attr.mq_msgsize <= 0)
			goto out_inode;
		if (capable(CAP_SYS_RESOURCE)) {
			if (info->attr.mq_maxmsg > HARD_MSGMAX ||
			    info->attr.mq_msgsize > HARD_MSGSIZEMAX)
				goto out_inode;
		} else {
			if (info->attr.mq_maxmsg > ipc_ns->mq_msg_max ||
					info->attr.mq_msgsize > ipc_ns->mq_msgsize_max)
				goto out_inode;
		}
		ret = -EOVERFLOW;
		/* check for overflow */
		if (info->attr.mq_msgsize > ULONG_MAX/info->attr.mq_maxmsg)
			goto out_inode;
		mq_treesize = info->attr.mq_maxmsg * sizeof(struct msg_msg) +
			min_t(unsigned int, info->attr.mq_maxmsg, MQ_PRIO_MAX) *
			sizeof(struct posix_msg_tree_node);
		mq_bytes = info->attr.mq_maxmsg * info->attr.mq_msgsize;
		if (mq_bytes + mq_treesize < mq_bytes)
			goto out_inode;
		mq_bytes += mq_treesize;
		spin_lock(&mq_lock);
		if (u->mq_bytes + mq_bytes < u->mq_bytes ||
		    u->mq_bytes + mq_bytes > rlimit(RLIMIT_MSGQUEUE)) {
			spin_unlock(&mq_lock);
			/* mqueue_evict_inode() releases info->messages */
			ret = -EMFILE;
			goto out_inode;
		}
		u->mq_bytes += mq_bytes;
		spin_unlock(&mq_lock);

		/* all is ok */
		info->user = get_uid(u);
	} else if (S_ISDIR(mode)) {
		inc_nlink(inode);
		/* Some things misbehave if size == 0 on a directory */
		inode->i_size = 2 * DIRENT_SIZE;
		inode->i_op = &mqueue_dir_inode_operations;
		inode->i_fop = &simple_dir_operations;
	}

	return inode;
out_inode:
	iput(inode);
err:
	return ERR_PTR(ret);
}

static int mqueue_fill_super(struct super_block *sb, struct fs_context *fc)
{
	struct inode *inode;
	struct ipc_namespace *ns = sb->s_fs_info;

	sb->s_iflags |= SB_I_NOEXEC | SB_I_NODEV;
	sb->s_blocksize = PAGE_SIZE;
	sb->s_blocksize_bits = PAGE_SHIFT;
	sb->s_magic = MQUEUE_MAGIC;
	sb->s_op = &mqueue_super_ops;

	inode = mqueue_get_inode(sb, ns, S_IFDIR | S_ISVTX | S_IRWXUGO, NULL);
	if (IS_ERR(inode))
		return PTR_ERR(inode);

	sb->s_root = d_make_root(inode);
	if (!sb->s_root)
		return -ENOMEM;
	return 0;
}

static int mqueue_get_tree(struct fs_context *fc)
{
	struct mqueue_fs_context *ctx = fc->fs_private;

	return get_tree_keyed(fc, mqueue_fill_super, ctx->ipc_ns);
}

static void mqueue_fs_context_free(struct fs_context *fc)
{
	struct mqueue_fs_context *ctx = fc->fs_private;

	put_ipc_ns(ctx->ipc_ns);
	kfree(ctx);
}

static int mqueue_init_fs_context(struct fs_context *fc)
{
	struct mqueue_fs_context *ctx;

	ctx = kzalloc(sizeof(struct mqueue_fs_context), GFP_KERNEL);
	if (!ctx)
		return -ENOMEM;

	ctx->ipc_ns = get_ipc_ns(current->nsproxy->ipc_ns);
	put_user_ns(fc->user_ns);
	fc->user_ns = get_user_ns(ctx->ipc_ns->user_ns);
	fc->fs_private = ctx;
	fc->ops = &mqueue_fs_context_ops;
	return 0;
}

static struct vfsmount *mq_create_mount(struct ipc_namespace *ns)
{
	struct mqueue_fs_context *ctx;
	struct fs_context *fc;
	struct vfsmount *mnt;

	fc = fs_context_for_mount(&mqueue_fs_type, SB_KERNMOUNT);
	if (IS_ERR(fc))
		return ERR_CAST(fc);

	ctx = fc->fs_private;
	put_ipc_ns(ctx->ipc_ns);
	ctx->ipc_ns = get_ipc_ns(ns);
	put_user_ns(fc->user_ns);
	fc->user_ns = get_user_ns(ctx->ipc_ns->user_ns);

	mnt = fc_mount(fc);
	put_fs_context(fc);
	return mnt;
}

static void init_once(void *foo)
{
	struct mqueue_inode_info *p = (struct mqueue_inode_info *) foo;

	inode_init_once(&p->vfs_inode);
}

static struct inode *mqueue_alloc_inode(struct super_block *sb)
{
	struct mqueue_inode_info *ei;

	ei = kmem_cache_alloc(mqueue_inode_cachep, GFP_KERNEL);
	if (!ei)
		return NULL;
	return &ei->vfs_inode;
}

static void mqueue_free_inode(struct inode *inode)
{
	kmem_cache_free(mqueue_inode_cachep, MQUEUE_I(inode));
}

static void mqueue_evict_inode(struct inode *inode)
{
	struct mqueue_inode_info *info;
	struct user_struct *user;
	struct ipc_namespace *ipc_ns;
	struct msg_msg *msg, *nmsg;
	LIST_HEAD(tmp_msg);

	clear_inode(inode);

	if (S_ISDIR(inode->i_mode))
		return;

	ipc_ns = get_ns_from_inode(inode);
	info = MQUEUE_I(inode);
	spin_lock(&info->lock);
	while ((msg = msg_get(info)) != NULL)
		list_add_tail(&msg->m_list, &tmp_msg);
	kfree(info->node_cache);
	spin_unlock(&info->lock);

	list_for_each_entry_safe(msg, nmsg, &tmp_msg, m_list) {
		list_del(&msg->m_list);
		free_msg(msg);
	}

	user = info->user;
	if (user) {
		unsigned long mq_bytes, mq_treesize;

		/* Total amount of bytes accounted for the mqueue */
		mq_treesize = info->attr.mq_maxmsg * sizeof(struct msg_msg) +
			min_t(unsigned int, info->attr.mq_maxmsg, MQ_PRIO_MAX) *
			sizeof(struct posix_msg_tree_node);

		mq_bytes = mq_treesize + (info->attr.mq_maxmsg *
					  info->attr.mq_msgsize);

		spin_lock(&mq_lock);
		user->mq_bytes -= mq_bytes;
		/*
		 * get_ns_from_inode() ensures that the
		 * (ipc_ns = sb->s_fs_info) is either a valid ipc_ns
		 * to which we now hold a reference, or it is NULL.
		 * We can't put it here under mq_lock, though.
		 */
		if (ipc_ns)
			ipc_ns->mq_queues_count--;
		spin_unlock(&mq_lock);
		free_uid(user);
	}
	if (ipc_ns)
		put_ipc_ns(ipc_ns);
}

static int mqueue_create_attr(struct dentry *dentry, umode_t mode, void *arg)
{
	struct inode *dir = dentry->d_parent->d_inode;
	struct inode *inode;
	struct mq_attr *attr = arg;
	int error;
	struct ipc_namespace *ipc_ns;

	spin_lock(&mq_lock);
	ipc_ns = __get_ns_from_inode(dir);
	if (!ipc_ns) {
		error = -EACCES;
		goto out_unlock;
	}

	if (ipc_ns->mq_queues_count >= ipc_ns->mq_queues_max &&
	    !capable(CAP_SYS_RESOURCE)) {
		error = -ENOSPC;
		goto out_unlock;
	}
	ipc_ns->mq_queues_count++;
	spin_unlock(&mq_lock);

	inode = mqueue_get_inode(dir->i_sb, ipc_ns, mode, attr);
	if (IS_ERR(inode)) {
		error = PTR_ERR(inode);
		spin_lock(&mq_lock);
		ipc_ns->mq_queues_count--;
		goto out_unlock;
	}

	put_ipc_ns(ipc_ns);
	dir->i_size += DIRENT_SIZE;
	dir->i_ctime = dir->i_mtime = dir->i_atime = current_time(dir);

	d_instantiate(dentry, inode);
	dget(dentry);
	return 0;
out_unlock:
	spin_unlock(&mq_lock);
	if (ipc_ns)
		put_ipc_ns(ipc_ns);
	return error;
}

static int mqueue_create(struct inode *dir, struct dentry *dentry,
				umode_t mode, bool excl)
{
	return mqueue_create_attr(dentry, mode, NULL);
}

static int mqueue_unlink(struct inode *dir, struct dentry *dentry)
{
	struct inode *inode = d_inode(dentry);

	dir->i_ctime = dir->i_mtime = dir->i_atime = current_time(dir);
	dir->i_size -= DIRENT_SIZE;
	drop_nlink(inode);
	dput(dentry);
	return 0;
}

/*
*	This is routine for system read from queue file.
*	To avoid mess with doing here some sort of mq_receive we allow
*	to read only queue size & notification info (the only values
*	that are interesting from user point of view and aren't accessible
*	through std routines)
*/
static ssize_t mqueue_read_file(struct file *filp, char __user *u_data,
				size_t count, loff_t *off)
{
	struct mqueue_inode_info *info = MQUEUE_I(file_inode(filp));
	char buffer[FILENT_SIZE];
	ssize_t ret;

	spin_lock(&info->lock);
	snprintf(buffer, sizeof(buffer),
			"QSIZE:%-10lu NOTIFY:%-5d SIGNO:%-5d NOTIFY_PID:%-6d\n",
			info->qsize,
			info->notify_owner ? info->notify.sigev_notify : 0,
			(info->notify_owner &&
			 info->notify.sigev_notify == SIGEV_SIGNAL) ?
				info->notify.sigev_signo : 0,
			pid_vnr(info->notify_owner));
	spin_unlock(&info->lock);
	buffer[sizeof(buffer)-1] = '\0';

	ret = simple_read_from_buffer(u_data, count, off, buffer,
				strlen(buffer));
	if (ret <= 0)
		return ret;

	file_inode(filp)->i_atime = file_inode(filp)->i_ctime = current_time(file_inode(filp));
	return ret;
}

static int mqueue_flush_file(struct file *filp, fl_owner_t id)
{
	struct mqueue_inode_info *info = MQUEUE_I(file_inode(filp));

	spin_lock(&info->lock);
	if (task_tgid(current) == info->notify_owner)
		remove_notification(info);

	spin_unlock(&info->lock);
	return 0;
}

static __poll_t mqueue_poll_file(struct file *filp, struct poll_table_struct *poll_tab)
{
	struct mqueue_inode_info *info = MQUEUE_I(file_inode(filp));
	__poll_t retval = 0;

	poll_wait(filp, &info->wait_q, poll_tab);

	spin_lock(&info->lock);
	if (info->attr.mq_curmsgs)
		retval = EPOLLIN | EPOLLRDNORM;

	if (info->attr.mq_curmsgs < info->attr.mq_maxmsg)
		retval |= EPOLLOUT | EPOLLWRNORM;
	spin_unlock(&info->lock);

	return retval;
}

/* Adds current to info->e_wait_q[sr] before element with smaller prio */
static void wq_add(struct mqueue_inode_info *info, int sr,
			struct ext_wait_queue *ewp)
{
	struct ext_wait_queue *walk;

	list_for_each_entry(walk, &info->e_wait_q[sr].list, list) {
		if (walk->task->prio <= current->prio) {
			list_add_tail(&ewp->list, &walk->list);
			return;
		}
	}
	list_add_tail(&ewp->list, &info->e_wait_q[sr].list);
}

/*
 * Puts current task to sleep. Caller must hold queue lock. After return
 * lock isn't held.
 * sr: SEND or RECV
 */
static int wq_sleep(struct mqueue_inode_info *info, int sr,
		    ktime_t *timeout, struct ext_wait_queue *ewp)
	__releases(&info->lock)
{
	int retval;
	signed long time;

	wq_add(info, sr, ewp);

	for (;;) {
		__set_current_state(TASK_INTERRUPTIBLE);

		spin_unlock(&info->lock);
		time = schedule_hrtimeout_range_clock(timeout, 0,
			HRTIMER_MODE_ABS, CLOCK_REALTIME);

		if (ewp->state == STATE_READY) {
			retval = 0;
			goto out;
		}
		spin_lock(&info->lock);
		if (ewp->state == STATE_READY) {
			retval = 0;
			goto out_unlock;
		}
		if (signal_pending(current)) {
			retval = -ERESTARTSYS;
			break;
		}
		if (time == 0) {
			retval = -ETIMEDOUT;
			break;
		}
	}
	list_del(&ewp->list);
out_unlock:
	spin_unlock(&info->lock);
out:
	return retval;
}

/*
 * Returns waiting task that should be serviced first or NULL if none exists
 */
static struct ext_wait_queue *wq_get_first_waiter(
		struct mqueue_inode_info *info, int sr)
{
	struct list_head *ptr;

	ptr = info->e_wait_q[sr].list.prev;
	if (ptr == &info->e_wait_q[sr].list)
		return NULL;
	return list_entry(ptr, struct ext_wait_queue, list);
}


static inline void set_cookie(struct sk_buff *skb, char code)
{
	((char *)skb->data)[NOTIFY_COOKIE_LEN-1] = code;
}

/*
 * The next function is only to split too long sys_mq_timedsend
 */
static void __do_notify(struct mqueue_inode_info *info)
{
	/* notification
	 * invoked when there is registered process and there isn't process
	 * waiting synchronously for message AND state of queue changed from
	 * empty to not empty. Here we are sure that no one is waiting
	 * synchronously. */
	if (info->notify_owner &&
	    info->attr.mq_curmsgs == 1) {
		struct kernel_siginfo sig_i;
		switch (info->notify.sigev_notify) {
		case SIGEV_NONE:
			break;
		case SIGEV_SIGNAL:
			/* sends signal */

			clear_siginfo(&sig_i);
			sig_i.si_signo = info->notify.sigev_signo;
			sig_i.si_errno = 0;
			sig_i.si_code = SI_MESGQ;
			sig_i.si_value = info->notify.sigev_value;
			/* map current pid/uid into info->owner's namespaces */
			rcu_read_lock();
			sig_i.si_pid = task_tgid_nr_ns(current,
						ns_of_pid(info->notify_owner));
			sig_i.si_uid = from_kuid_munged(info->notify_user_ns, current_uid());
			rcu_read_unlock();

			kill_pid_info(info->notify.sigev_signo,
				      &sig_i, info->notify_owner);
			break;
		case SIGEV_THREAD:
			set_cookie(info->notify_cookie, NOTIFY_WOKENUP);
			netlink_sendskb(info->notify_sock, info->notify_cookie);
			break;
		}
		/* after notification unregisters process */
		put_pid(info->notify_owner);
		put_user_ns(info->notify_user_ns);
		info->notify_owner = NULL;
		info->notify_user_ns = NULL;
	}
	wake_up(&info->wait_q);
}

static int prepare_timeout(const struct __kernel_timespec __user *u_abs_timeout,
			   struct timespec64 *ts)
{
	if (get_timespec64(ts, u_abs_timeout))
		return -EFAULT;
	if (!timespec64_valid(ts))
		return -EINVAL;
	return 0;
}

static void remove_notification(struct mqueue_inode_info *info)
{
	if (info->notify_owner != NULL &&
	    info->notify.sigev_notify == SIGEV_THREAD) {
		set_cookie(info->notify_cookie, NOTIFY_REMOVED);
		netlink_sendskb(info->notify_sock, info->notify_cookie);
	}
	put_pid(info->notify_owner);
	put_user_ns(info->notify_user_ns);
	info->notify_owner = NULL;
	info->notify_user_ns = NULL;
}

static int prepare_open(struct dentry *dentry, int oflag, int ro,
			umode_t mode, struct filename *name,
			struct mq_attr *attr)
{
	static const int oflag2acc[O_ACCMODE] = { MAY_READ, MAY_WRITE,
						  MAY_READ | MAY_WRITE };
	int acc;

	if (d_really_is_negative(dentry)) {
		if (!(oflag & O_CREAT))
			return -ENOENT;
		if (ro)
			return ro;
		audit_inode_parent_hidden(name, dentry->d_parent);
		return vfs_mkobj(dentry, mode & ~current_umask(),
				  mqueue_create_attr, attr);
	}
	/* it already existed */
	audit_inode(name, dentry, 0);
	if ((oflag & (O_CREAT|O_EXCL)) == (O_CREAT|O_EXCL))
		return -EEXIST;
	if ((oflag & O_ACCMODE) == (O_RDWR | O_WRONLY))
		return -EINVAL;
	acc = oflag2acc[oflag & O_ACCMODE];
	return inode_permission(d_inode(dentry), acc);
}

static int do_mq_open(const char __user *u_name, int oflag, umode_t mode,
		      struct mq_attr *attr)
{
	struct vfsmount *mnt = current->nsproxy->ipc_ns->mq_mnt;
	struct dentry *root = mnt->mnt_root;
	struct filename *name;
	struct path path;
	int fd, error;
	int ro;

	audit_mq_open(oflag, mode, attr);

	if (IS_ERR(name = getname(u_name)))
		return PTR_ERR(name);

	fd = get_unused_fd_flags(O_CLOEXEC);
	if (fd < 0)
		goto out_putname;

	ro = mnt_want_write(mnt);	/* we'll drop it in any case */
	inode_lock(d_inode(root));
	path.dentry = lookup_one_len(name->name, root, strlen(name->name));
	if (IS_ERR(path.dentry)) {
		error = PTR_ERR(path.dentry);
		goto out_putfd;
	}
	path.mnt = mntget(mnt);
	error = prepare_open(path.dentry, oflag, ro, mode, name, attr);
	if (!error) {
		struct file *file = dentry_open(&path, oflag, current_cred());
		if (!IS_ERR(file))
			fd_install(fd, file);
		else
			error = PTR_ERR(file);
	}
	path_put(&path);
out_putfd:
	if (error) {
		put_unused_fd(fd);
		fd = error;
	}
	inode_unlock(d_inode(root));
	if (!ro)
		mnt_drop_write(mnt);
out_putname:
	putname(name);
	return fd;
}

SYSCALL_DEFINE4(mq_open, const char __user *, u_name, int, oflag, umode_t, mode,
		struct mq_attr __user *, u_attr)
{
	struct mq_attr attr;
	if (u_attr && copy_from_user(&attr, u_attr, sizeof(struct mq_attr)))
		return -EFAULT;

	return do_mq_open(u_name, oflag, mode, u_attr ? &attr : NULL);
}

SYSCALL_DEFINE1(mq_unlink, const char __user *, u_name)
{
	int err;
	struct filename *name;
	struct dentry *dentry;
	struct inode *inode = NULL;
	struct ipc_namespace *ipc_ns = current->nsproxy->ipc_ns;
	struct vfsmount *mnt = ipc_ns->mq_mnt;

	name = getname(u_name);
	if (IS_ERR(name))
		return PTR_ERR(name);

	audit_inode_parent_hidden(name, mnt->mnt_root);
	err = mnt_want_write(mnt);
	if (err)
		goto out_name;
	inode_lock_nested(d_inode(mnt->mnt_root), I_MUTEX_PARENT);
	dentry = lookup_one_len(name->name, mnt->mnt_root,
				strlen(name->name));
	if (IS_ERR(dentry)) {
		err = PTR_ERR(dentry);
		goto out_unlock;
	}

	inode = d_inode(dentry);
	if (!inode) {
		err = -ENOENT;
	} else {
		ihold(inode);
		err = vfs_unlink(d_inode(dentry->d_parent), dentry, NULL);
	}
	dput(dentry);

out_unlock:
	inode_unlock(d_inode(mnt->mnt_root));
	if (inode)
		iput(inode);
	mnt_drop_write(mnt);
out_name:
	putname(name);

	return err;
}

/* Pipelined send and receive functions.
 *
 * If a receiver finds no waiting message, then it registers itself in the
 * list of waiting receivers. A sender checks that list before adding the new
 * message into the message array. If there is a waiting receiver, then it
 * bypasses the message array and directly hands the message over to the
 * receiver. The receiver accepts the message and returns without grabbing the
 * queue spinlock:
 *
 * - Set pointer to message.
 * - Queue the receiver task for later wakeup (without the info->lock).
 * - Update its state to STATE_READY. Now the receiver can continue.
 * - Wake up the process after the lock is dropped. Should the process wake up
 *   before this wakeup (due to a timeout or a signal) it will either see
 *   STATE_READY and continue or acquire the lock to check the state again.
 *
 * The same algorithm is used for senders.
 */

/* pipelined_send() - send a message directly to the task waiting in
 * sys_mq_timedreceive() (without inserting message into a queue).
 */
static inline void pipelined_send(struct wake_q_head *wake_q,
				  struct mqueue_inode_info *info,
				  struct msg_msg *message,
				  struct ext_wait_queue *receiver)
{
	receiver->msg = message;
	list_del(&receiver->list);
	wake_q_add(wake_q, receiver->task);
	/*
	 * Rely on the implicit cmpxchg barrier from wake_q_add such
	 * that we can ensure that updating receiver->state is the last
	 * write operation: As once set, the receiver can continue,
	 * and if we don't have the reference count from the wake_q,
	 * yet, at that point we can later have a use-after-free
	 * condition and bogus wakeup.
	 */
	receiver->state = STATE_READY;
}

/* pipelined_receive() - if there is task waiting in sys_mq_timedsend()
 * gets its message and put to the queue (we have one free place for sure). */
static inline void pipelined_receive(struct wake_q_head *wake_q,
				     struct mqueue_inode_info *info)
{
	struct ext_wait_queue *sender = wq_get_first_waiter(info, SEND);

	if (!sender) {
		/* for poll */
		wake_up_interruptible(&info->wait_q);
		return;
	}
	if (msg_insert(sender->msg, info))
		return;

	list_del(&sender->list);
	wake_q_add(wake_q, sender->task);
	sender->state = STATE_READY;
}

static int do_mq_timedsend(mqd_t mqdes, const char __user *u_msg_ptr,
		size_t msg_len, unsigned int msg_prio,
		struct timespec64 *ts)
{
	struct fd f;
	struct inode *inode;
	struct ext_wait_queue wait;
	struct ext_wait_queue *receiver;
	struct msg_msg *msg_ptr;
	struct mqueue_inode_info *info;
	ktime_t expires, *timeout = NULL;
	struct posix_msg_tree_node *new_leaf = NULL;
	int ret = 0;
	DEFINE_WAKE_Q(wake_q);

	if (unlikely(msg_prio >= (unsigned long) MQ_PRIO_MAX))
		return -EINVAL;

	if (ts) {
		expires = timespec64_to_ktime(*ts);
		timeout = &expires;
	}

	audit_mq_sendrecv(mqdes, msg_len, msg_prio, ts);

	f = fdget(mqdes);
	if (unlikely(!f.file)) {
		ret = -EBADF;
		goto out;
	}

	inode = file_inode(f.file);
	if (unlikely(f.file->f_op != &mqueue_file_operations)) {
		ret = -EBADF;
		goto out_fput;
	}
	info = MQUEUE_I(inode);
	audit_file(f.file);

	if (unlikely(!(f.file->f_mode & FMODE_WRITE))) {
		ret = -EBADF;
		goto out_fput;
	}

	if (unlikely(msg_len > info->attr.mq_msgsize)) {
		ret = -EMSGSIZE;
		goto out_fput;
	}

	/* First try to allocate memory, before doing anything with
	 * existing queues. */
	msg_ptr = load_msg(u_msg_ptr, msg_len);
	if (IS_ERR(msg_ptr)) {
		ret = PTR_ERR(msg_ptr);
		goto out_fput;
	}
	msg_ptr->m_ts = msg_len;
	msg_ptr->m_type = msg_prio;

	/*
	 * msg_insert really wants us to have a valid, spare node struct so
	 * it doesn't have to kmalloc a GFP_ATOMIC allocation, but it will
	 * fall back to that if necessary.
	 */
	if (!info->node_cache)
		new_leaf = kmalloc(sizeof(*new_leaf), GFP_KERNEL);

	spin_lock(&info->lock);

	if (!info->node_cache && new_leaf) {
		/* Save our speculative allocation into the cache */
		INIT_LIST_HEAD(&new_leaf->msg_list);
		info->node_cache = new_leaf;
		new_leaf = NULL;
	} else {
		kfree(new_leaf);
	}

	if (info->attr.mq_curmsgs == info->attr.mq_maxmsg) {
		if (f.file->f_flags & O_NONBLOCK) {
			ret = -EAGAIN;
		} else {
			wait.task = current;
			wait.msg = (void *) msg_ptr;
			wait.state = STATE_NONE;
			ret = wq_sleep(info, SEND, timeout, &wait);
			/*
			 * wq_sleep must be called with info->lock held, and
			 * returns with the lock released
			 */
			goto out_free;
		}
	} else {
		receiver = wq_get_first_waiter(info, RECV);
		if (receiver) {
			pipelined_send(&wake_q, info, msg_ptr, receiver);
		} else {
			/* adds message to the queue */
			ret = msg_insert(msg_ptr, info);
			if (ret)
				goto out_unlock;
			__do_notify(info);
		}
		inode->i_atime = inode->i_mtime = inode->i_ctime =
				current_time(inode);
	}
out_unlock:
	spin_unlock(&info->lock);
	wake_up_q(&wake_q);
out_free:
	if (ret)
		free_msg(msg_ptr);
out_fput:
	fdput(f);
out:
	return ret;
}

static int do_mq_timedreceive(mqd_t mqdes, char __user *u_msg_ptr,
		size_t msg_len, unsigned int __user *u_msg_prio,
		struct timespec64 *ts)
{
	ssize_t ret;
	struct msg_msg *msg_ptr;
	struct fd f;
	struct inode *inode;
	struct mqueue_inode_info *info;
	struct ext_wait_queue wait;
	ktime_t expires, *timeout = NULL;
	struct posix_msg_tree_node *new_leaf = NULL;

	if (ts) {
		expires = timespec64_to_ktime(*ts);
		timeout = &expires;
	}

	audit_mq_sendrecv(mqdes, msg_len, 0, ts);

	f = fdget(mqdes);
	if (unlikely(!f.file)) {
		ret = -EBADF;
		goto out;
	}

	inode = file_inode(f.file);
	if (unlikely(f.file->f_op != &mqueue_file_operations)) {
		ret = -EBADF;
		goto out_fput;
	}
	info = MQUEUE_I(inode);
	audit_file(f.file);

	if (unlikely(!(f.file->f_mode & FMODE_READ))) {
		ret = -EBADF;
		goto out_fput;
	}

	/* checks if buffer is big enough */
	if (unlikely(msg_len < info->attr.mq_msgsize)) {
		ret = -EMSGSIZE;
		goto out_fput;
	}

	/*
	 * msg_insert really wants us to have a valid, spare node struct so
	 * it doesn't have to kmalloc a GFP_ATOMIC allocation, but it will
	 * fall back to that if necessary.
	 */
	if (!info->node_cache)
		new_leaf = kmalloc(sizeof(*new_leaf), GFP_KERNEL);

	spin_lock(&info->lock);

	if (!info->node_cache && new_leaf) {
		/* Save our speculative allocation into the cache */
		INIT_LIST_HEAD(&new_leaf->msg_list);
		info->node_cache = new_leaf;
	} else {
		kfree(new_leaf);
	}

	if (info->attr.mq_curmsgs == 0) {
		if (f.file->f_flags & O_NONBLOCK) {
			spin_unlock(&info->lock);
			ret = -EAGAIN;
		} else {
			wait.task = current;
			wait.state = STATE_NONE;
			ret = wq_sleep(info, RECV, timeout, &wait);
			msg_ptr = wait.msg;
		}
	} else {
		DEFINE_WAKE_Q(wake_q);

		msg_ptr = msg_get(info);

		inode->i_atime = inode->i_mtime = inode->i_ctime =
				current_time(inode);

		/* There is now free space in queue. */
		pipelined_receive(&wake_q, info);
		spin_unlock(&info->lock);
		wake_up_q(&wake_q);
		ret = 0;
	}
	if (ret == 0) {
		ret = msg_ptr->m_ts;

		if ((u_msg_prio && put_user(msg_ptr->m_type, u_msg_prio)) ||
			store_msg(u_msg_ptr, msg_ptr, msg_ptr->m_ts)) {
			ret = -EFAULT;
		}
		free_msg(msg_ptr);
	}
out_fput:
	fdput(f);
out:
	return ret;
}

SYSCALL_DEFINE5(mq_timedsend, mqd_t, mqdes, const char __user *, u_msg_ptr,
		size_t, msg_len, unsigned int, msg_prio,
		const struct __kernel_timespec __user *, u_abs_timeout)
{
	struct timespec64 ts, *p = NULL;
	if (u_abs_timeout) {
		int res = prepare_timeout(u_abs_timeout, &ts);
		if (res)
			return res;
		p = &ts;
	}
	return do_mq_timedsend(mqdes, u_msg_ptr, msg_len, msg_prio, p);
}

SYSCALL_DEFINE5(mq_timedreceive, mqd_t, mqdes, char __user *, u_msg_ptr,
		size_t, msg_len, unsigned int __user *, u_msg_prio,
		const struct __kernel_timespec __user *, u_abs_timeout)
{
	struct timespec64 ts, *p = NULL;
	if (u_abs_timeout) {
		int res = prepare_timeout(u_abs_timeout, &ts);
		if (res)
			return res;
		p = &ts;
	}
	return do_mq_timedreceive(mqdes, u_msg_ptr, msg_len, u_msg_prio, p);
}

/*
 * Notes: the case when user wants us to deregister (with NULL as pointer)
 * and he isn't currently owner of notification, will be silently discarded.
 * It isn't explicitly defined in the POSIX.
 */
static int do_mq_notify(mqd_t mqdes, const struct sigevent *notification)
{
	int ret;
	struct fd f;
	struct sock *sock;
	struct inode *inode;
	struct mqueue_inode_info *info;
	struct sk_buff *nc;

	audit_mq_notify(mqdes, notification);

	nc = NULL;
	sock = NULL;
	if (notification != NULL) {
		if (unlikely(notification->sigev_notify != SIGEV_NONE &&
			     notification->sigev_notify != SIGEV_SIGNAL &&
			     notification->sigev_notify != SIGEV_THREAD))
			return -EINVAL;
		if (notification->sigev_notify == SIGEV_SIGNAL &&
			!valid_signal(notification->sigev_signo)) {
			return -EINVAL;
		}
		if (notification->sigev_notify == SIGEV_THREAD) {
			long timeo;

			/* create the notify skb */
			nc = alloc_skb(NOTIFY_COOKIE_LEN, GFP_KERNEL);
			if (!nc)
				return -ENOMEM;

			if (copy_from_user(nc->data,
					notification->sigev_value.sival_ptr,
					NOTIFY_COOKIE_LEN)) {
				ret = -EFAULT;
				goto free_skb;
			}

			/* TODO: add a header? */
			skb_put(nc, NOTIFY_COOKIE_LEN);
			/* and attach it to the socket */
retry:
			f = fdget(notification->sigev_signo);
			if (!f.file) {
				ret = -EBADF;
				goto out;
			}
			sock = netlink_getsockbyfilp(f.file);
			fdput(f);
			if (IS_ERR(sock)) {
				ret = PTR_ERR(sock);
				goto free_skb;
			}

			timeo = MAX_SCHEDULE_TIMEOUT;
			ret = netlink_attachskb(sock, nc, &timeo, NULL);
			if (ret == 1) {
				sock = NULL;
				goto retry;
			}
			if (ret)
				return ret;
		}
	}

	f = fdget(mqdes);
	if (!f.file) {
		ret = -EBADF;
		goto out;
	}

	inode = file_inode(f.file);
	if (unlikely(f.file->f_op != &mqueue_file_operations)) {
		ret = -EBADF;
		goto out_fput;
	}
	info = MQUEUE_I(inode);

	ret = 0;
	spin_lock(&info->lock);
	if (notification == NULL) {
		if (info->notify_owner == task_tgid(current)) {
			remove_notification(info);
			inode->i_atime = inode->i_ctime = current_time(inode);
		}
	} else if (info->notify_owner != NULL) {
		ret = -EBUSY;
	} else {
		switch (notification->sigev_notify) {
		case SIGEV_NONE:
			info->notify.sigev_notify = SIGEV_NONE;
			break;
		case SIGEV_THREAD:
			info->notify_sock = sock;
			info->notify_cookie = nc;
			sock = NULL;
			nc = NULL;
			info->notify.sigev_notify = SIGEV_THREAD;
			break;
		case SIGEV_SIGNAL:
			info->notify.sigev_signo = notification->sigev_signo;
			info->notify.sigev_value = notification->sigev_value;
			info->notify.sigev_notify = SIGEV_SIGNAL;
			break;
		}

		info->notify_owner = get_pid(task_tgid(current));
		info->notify_user_ns = get_user_ns(current_user_ns());
		inode->i_atime = inode->i_ctime = current_time(inode);
	}
	spin_unlock(&info->lock);
out_fput:
	fdput(f);
out:
	if (sock)
		netlink_detachskb(sock, nc);
	else
free_skb:
		dev_kfree_skb(nc);

	return ret;
}

SYSCALL_DEFINE2(mq_notify, mqd_t, mqdes,
		const struct sigevent __user *, u_notification)
{
	struct sigevent n, *p = NULL;
	if (u_notification) {
		if (copy_from_user(&n, u_notification, sizeof(struct sigevent)))
			return -EFAULT;
		p = &n;
	}
	return do_mq_notify(mqdes, p);
}

static int do_mq_getsetattr(int mqdes, struct mq_attr *new, struct mq_attr *old)
{
	struct fd f;
	struct inode *inode;
	struct mqueue_inode_info *info;

	if (new && (new->mq_flags & (~O_NONBLOCK)))
		return -EINVAL;

	f = fdget(mqdes);
	if (!f.file)
		return -EBADF;

	if (unlikely(f.file->f_op != &mqueue_file_operations)) {
		fdput(f);
		return -EBADF;
	}

	inode = file_inode(f.file);
	info = MQUEUE_I(inode);

	spin_lock(&info->lock);

	if (old) {
		*old = info->attr;
		old->mq_flags = f.file->f_flags & O_NONBLOCK;
	}
	if (new) {
		audit_mq_getsetattr(mqdes, new);
		spin_lock(&f.file->f_lock);
		if (new->mq_flags & O_NONBLOCK)
			f.file->f_flags |= O_NONBLOCK;
		else
			f.file->f_flags &= ~O_NONBLOCK;
		spin_unlock(&f.file->f_lock);

		inode->i_atime = inode->i_ctime = current_time(inode);
	}

	spin_unlock(&info->lock);
	fdput(f);
	return 0;
}

SYSCALL_DEFINE3(mq_getsetattr, mqd_t, mqdes,
		const struct mq_attr __user *, u_mqstat,
		struct mq_attr __user *, u_omqstat)
{
	int ret;
	struct mq_attr mqstat, omqstat;
	struct mq_attr *new = NULL, *old = NULL;

	if (u_mqstat) {
		new = &mqstat;
		if (copy_from_user(new, u_mqstat, sizeof(struct mq_attr)))
			return -EFAULT;
	}
	if (u_omqstat)
		old = &omqstat;

	ret = do_mq_getsetattr(mqdes, new, old);
	if (ret || !old)
		return ret;

	if (copy_to_user(u_omqstat, old, sizeof(struct mq_attr)))
		return -EFAULT;
	return 0;
}

#ifdef CONFIG_COMPAT

struct compat_mq_attr {
	compat_long_t mq_flags;      /* message queue flags		     */
	compat_long_t mq_maxmsg;     /* maximum number of messages	     */
	compat_long_t mq_msgsize;    /* maximum message size		     */
	compat_long_t mq_curmsgs;    /* number of messages currently queued  */
	compat_long_t __reserved[4]; /* ignored for input, zeroed for output */
};

static inline int get_compat_mq_attr(struct mq_attr *attr,
			const struct compat_mq_attr __user *uattr)
{
	struct compat_mq_attr v;

	if (copy_from_user(&v, uattr, sizeof(*uattr)))
		return -EFAULT;

	memset(attr, 0, sizeof(*attr));
	attr->mq_flags = v.mq_flags;
	attr->mq_maxmsg = v.mq_maxmsg;
	attr->mq_msgsize = v.mq_msgsize;
	attr->mq_curmsgs = v.mq_curmsgs;
	return 0;
}

static inline int put_compat_mq_attr(const struct mq_attr *attr,
			struct compat_mq_attr __user *uattr)
{
	struct compat_mq_attr v;

	memset(&v, 0, sizeof(v));
	v.mq_flags = attr->mq_flags;
	v.mq_maxmsg = attr->mq_maxmsg;
	v.mq_msgsize = attr->mq_msgsize;
	v.mq_curmsgs = attr->mq_curmsgs;
	if (copy_to_user(uattr, &v, sizeof(*uattr)))
		return -EFAULT;
	return 0;
}

COMPAT_SYSCALL_DEFINE4(mq_open, const char __user *, u_name,
		       int, oflag, compat_mode_t, mode,
		       struct compat_mq_attr __user *, u_attr)
{
	struct mq_attr attr, *p = NULL;
	if (u_attr && oflag & O_CREAT) {
		p = &attr;
		if (get_compat_mq_attr(&attr, u_attr))
			return -EFAULT;
	}
	return do_mq_open(u_name, oflag, mode, p);
}

COMPAT_SYSCALL_DEFINE2(mq_notify, mqd_t, mqdes,
		       const struct compat_sigevent __user *, u_notification)
{
	struct sigevent n, *p = NULL;
	if (u_notification) {
		if (get_compat_sigevent(&n, u_notification))
			return -EFAULT;
		if (n.sigev_notify == SIGEV_THREAD)
			n.sigev_value.sival_ptr = compat_ptr(n.sigev_value.sival_int);
		p = &n;
	}
	return do_mq_notify(mqdes, p);
}

COMPAT_SYSCALL_DEFINE3(mq_getsetattr, mqd_t, mqdes,
		       const struct compat_mq_attr __user *, u_mqstat,
		       struct compat_mq_attr __user *, u_omqstat)
{
	int ret;
	struct mq_attr mqstat, omqstat;
	struct mq_attr *new = NULL, *old = NULL;

	if (u_mqstat) {
		new = &mqstat;
		if (get_compat_mq_attr(new, u_mqstat))
			return -EFAULT;
	}
	if (u_omqstat)
		old = &omqstat;

	ret = do_mq_getsetattr(mqdes, new, old);
	if (ret || !old)
		return ret;

	if (put_compat_mq_attr(old, u_omqstat))
		return -EFAULT;
	return 0;
}
#endif

#ifdef CONFIG_COMPAT_32BIT_TIME
static int compat_prepare_timeout(const struct old_timespec32 __user *p,
				   struct timespec64 *ts)
{
	if (get_old_timespec32(ts, p))
		return -EFAULT;
	if (!timespec64_valid(ts))
		return -EINVAL;
	return 0;
}

SYSCALL_DEFINE5(mq_timedsend_time32, mqd_t, mqdes,
		const char __user *, u_msg_ptr,
		unsigned int, msg_len, unsigned int, msg_prio,
		const struct old_timespec32 __user *, u_abs_timeout)
{
	struct timespec64 ts, *p = NULL;
	if (u_abs_timeout) {
		int res = compat_prepare_timeout(u_abs_timeout, &ts);
		if (res)
			return res;
		p = &ts;
	}
	return do_mq_timedsend(mqdes, u_msg_ptr, msg_len, msg_prio, p);
}

SYSCALL_DEFINE5(mq_timedreceive_time32, mqd_t, mqdes,
		char __user *, u_msg_ptr,
		unsigned int, msg_len, unsigned int __user *, u_msg_prio,
		const struct old_timespec32 __user *, u_abs_timeout)
{
	struct timespec64 ts, *p = NULL;
	if (u_abs_timeout) {
		int res = compat_prepare_timeout(u_abs_timeout, &ts);
		if (res)
			return res;
		p = &ts;
	}
	return do_mq_timedreceive(mqdes, u_msg_ptr, msg_len, u_msg_prio, p);
}
#endif

static const struct inode_operations mqueue_dir_inode_operations = {
	.lookup = simple_lookup,
	.create = mqueue_create,
	.unlink = mqueue_unlink,
};

static const struct file_operations mqueue_file_operations = {
	.flush = mqueue_flush_file,
	.poll = mqueue_poll_file,
	.read = mqueue_read_file,
	.llseek = default_llseek,
};

static const struct super_operations mqueue_super_ops = {
	.alloc_inode = mqueue_alloc_inode,
	.free_inode = mqueue_free_inode,
	.evict_inode = mqueue_evict_inode,
	.statfs = simple_statfs,
};

static const struct fs_context_operations mqueue_fs_context_ops = {
	.free		= mqueue_fs_context_free,
	.get_tree	= mqueue_get_tree,
};

static struct file_system_type mqueue_fs_type = {
	.name			= "mqueue",
	.init_fs_context	= mqueue_init_fs_context,
	.kill_sb		= kill_litter_super,
	.fs_flags		= FS_USERNS_MOUNT,
};

int mq_init_ns(struct ipc_namespace *ns)
{
	struct vfsmount *m;

	ns->mq_queues_count  = 0;
	ns->mq_queues_max    = DFLT_QUEUESMAX;
	ns->mq_msg_max       = DFLT_MSGMAX;
	ns->mq_msgsize_max   = DFLT_MSGSIZEMAX;
	ns->mq_msg_default   = DFLT_MSG;
	ns->mq_msgsize_default  = DFLT_MSGSIZE;

	m = mq_create_mount(ns);
	if (IS_ERR(m))
		return PTR_ERR(m);
	ns->mq_mnt = m;
	return 0;
}

void mq_clear_sbinfo(struct ipc_namespace *ns)
{
	ns->mq_mnt->mnt_sb->s_fs_info = NULL;
}

void mq_put_mnt(struct ipc_namespace *ns)
{
	kern_unmount(ns->mq_mnt);
}

static int __init init_mqueue_fs(void)
{
	int error;

	mqueue_inode_cachep = kmem_cache_create("mqueue_inode_cache",
				sizeof(struct mqueue_inode_info), 0,
				SLAB_HWCACHE_ALIGN|SLAB_ACCOUNT, init_once);
	if (mqueue_inode_cachep == NULL)
		return -ENOMEM;

	/* ignore failures - they are not fatal */
	mq_sysctl_table = mq_register_sysctl_table();

	error = register_filesystem(&mqueue_fs_type);
	if (error)
		goto out_sysctl;

	spin_lock_init(&mq_lock);

	error = mq_init_ns(&init_ipc_ns);
	if (error)
		goto out_filesystem;

	return 0;

out_filesystem:
	unregister_filesystem(&mqueue_fs_type);
out_sysctl:
	if (mq_sysctl_table)
		unregister_sysctl_table(mq_sysctl_table);
	kmem_cache_destroy(mqueue_inode_cachep);
	return error;
}

device_initcall(init_mqueue_fs);

//每个信号量集，内核维护如下信息结构:<sys/sem.h>
struct semid_ds
{
  struct ipc_perm 	sem_perm;		/* 操作权限结构 */
  struct sem		*sem_base;		//指向sem结构数组指针
  time_t 			sem_otime;			/* 上次semop()时间 */
  time_t 			sem_ctime;			/* 上次由semctl()更改的时间 */
  ushort 	 		sem_nsems;		/* 集合中的信号量数量 */
};

//ipc_perm含有当前信号量访问权限
struct ipc_perm{
	uid_t uid;
	gid_t gid;
	uid_t cuid;
	gid_t cgid;
	mode_t mode;
	ulong_t seq;
	key_t key;
}

//维护某个信号量的一组的内部数据结构，一个信号量集的每个成员如下这个结构描述：
struct sem{
ushort_t 	semval;
short 		sempid;
ushort_t 	semncnt;
ushort_t 	semzcnt;
}
 

#include<sys/types.h>
#include<sys/sem.h>
int semget(key_t key,int nsems,int semflg);
//key是ftok生成键值
//nsems参数可以指定新的集合中应该创建的信号量的数目
//semflsg是打开信号的方式

//CreateSem()函数按照用户的键值生成一个信号量，把信号量的初始值设为用户输入的value。
typedef int sem_t;

union semun{		//信号量操作的联合结构
		int val;	//整型变量
		struct semid_ds *buf;//semid_ds结构指针
		unsigned	short  *array;//数组类型
		}arg;//全局变量
sem_t CreateSem(key_t key,int value)//建立信号量，魔数key和信号量的初始值value
{
	union	semun	sem; //信号量结构变量
	sem_t	semid;//信号量ID
	sem.val = val;//设置初值
	semid = semget(key,0,IPC_CREAT|0666);//获得信号量ID
	if(-1 == semid)
	{
		printf("create semaphore error\n");
		return -1;
	}
	semctl(semid,0,SETVAL,sem);//发送命令，建立value个初始值的信号量
	return semid;
}

#include<sys/types.h>
#include<sys/ipc.h>
#inlcude<sys/sem.h>

int semctl(int semid,int semnum,int cmd,/*union semun arg*/...);

//第4个参数指向如下联合体：
union semun{
	int val;//当执行SETVAL命令时将用到这个成员，它用于指定要把信号量设置成什么值。
	struct semid_ds *buf;//在命令IPC_STAT/IPC_SET中使用。它代表内核中所使用的内部信号量数据结构的一 个复制。
	ushort *array;//用在GETALL/SET ALL命令中的 一 个指针。它应当指向整数值的一 个数组。在设置或获取集合中所有信号量的值的过程中，将会用到该数组。
	struct seminfo *buf;//信号量内部结构
};

void SetvalueSem(sem_t semid,int value)//设置信号的值，通过SETVAL实现，所设置的值通过联合变量sem的val域实现
{
	union semun sem;//信号量操作的结构
	sem.val = value;//初始化
	semctl(semid,0,SETVAL,sem);//设置信号量的值
}


int GetvalueSem(sem_t semid)//获得信号量的值
{
	union semun sem;//信号量操作的结构
	return semctl(semid,0,GETVAL,sem);//获得信号量的值，通过GETVAL会是其返回给定信号量的当前值
}


void DestroySem(sem_t semid)//销毁信号量
{
	union semun sem;//信号量操作的结构
	sem.val = 0;//初始化
	semctl(semid,0,IPC_RMID,sem);//设置信号量
}

#include<sys/types.h>
#include<sys/ipc.h>
#include<sys/sem.h>
int semop(int semid,struct sembuf *sops,unsigned nsops);
int semtimedop(int semid, struct sembuf *sops, unsigned nsops,
                      struct timespec *timeout);

struct sembuf{
	ushort sem_num;//信号量的编号
	short  sem_op;//信号量的操作；将要执行的操作(正、负或者零)。
	short sem_flag;//信号量的操作标志；如果sem_op为负，则从信号量中减掉一个值。为正，则从信号量中加上值。如果为0，则将进程设置为睡眠状态，直到信号量的值为0为止。
	};
//例如
	struct sembuf sem= {O, +1, NOWAJT};
//表示对信号量 0,进行加1的操作。

int Sem_P(sem_t semid) //增加信号量
{
	struct sembuf sops={0,+1,IPC_NOWAIT};//建立信号量结构值
	return (semop(semid,&sops,1));//发送命令
}
int Sem_V(sem_t semid) //减小信号量值
{
	struct sembuf sops = {0,-1,IPC_NOWAIT};//建立信号量结构值
	return (semop(semid,&sops,1));//发送信号量操作方法
}

#include<stdio.h>
#include<sys/types.h>
#include<sys/ipc.h>
#include<sys/sem.h>

typedef int sem_t;

union semun{
        int     val;
        struct semid_ds *buf;
        unsigned short  *array;
}arg;

sem_t CreateSem(key_t key,int value)
{
        union semun sem;
        sem_t semid;
        sem.val = value;

        semid = semget(key,0,IPC_CREAT|0666);
        if(-1 == semid)
        {
                printf("create semaphore error\n");
                return -1;
        }
        semctl(semid,0,SETVAL,sem);
        return semid;
}

int Sem_P(sem_t semid)
{
        struct sembuf sops = {0,+1,IPC_NOWAIT};
        return (semop(semid,&sops,1));
}

int Sem_V(sem_t semid)
{
        struct sembuf sops = {0,-1,IPC_NOWAIT};
        return (semop(semid,&sops,1));
}

void SetvalueSem(sem_t semid,int value)
{      union semun sem;
        sem.val = value;
        semctl(semid,0,SETVAL,sem);
}

int GetvalueSem(sem_t semid)
{
        union semun sem;
        return semctl(semid,0,GETVAL,sem);
}


void DestroySem(sem_t semid)
{
        union semun sem;
        sem.val = 0;
        semctl(semid,0,IPC_RMID,sem);
}


int main(void)
{
        key_t key;
        int semid;
        char i;
        int value = 0;
        key = ftok("/ipc/sem",'a');
        semid = CreateSem(key,100);
        for(i=0;i<=3;i++){
                Sem_P(semid);
                Sem_V(semid);
        }
        value = GetvalueSem(semid);
        printf("信号量为:%d\n",value);
        DestroySem(semid);
        return 0;
}

	 		1. 若一个信号量的当值为 0，进程 A 请求将信号量值减去 2，然后进程 B 请求将信号量值减去 1。如果第三个进程将信号量值加上了 1，那么进程 B 首先会被解除阻塞并执行它的操作
			
			2. 这种场景可能会导致饿死情况的发生，即一个进程因信号量的状态无法满足所请求的操作继续往前执行的条件而永远保持阻塞。

  		1. 进程 A 请求将信号量 0 和 1 的值减去 1（阻塞）。
  		2. 进程 B 请求将信号量 0 的值减去 1（阻塞）
  		3. 进程 C 将信号量 0 的值加上 1

oflag = IPC_CREAT|IPC_EXCL|SVSEM_MODE;
if((semid = semget(key,1,oflag))>0){
	arg.val = 1;
	semctl(semid,0,SETVAL,arg);
	}else if(errno == EEXIST){
	semid = semget(key,1,SVSEM_MODE);
}else
err_sys("semget error");
semop(semid,...);

#define _GNU_SOURCE
#include <string.h>
#include <stdio.h>
#include <stdlib.h>
#include <zconf.h>
#include <sys/types.h>
#include <sys/ipc.h>
#include <sys/msg.h>
#include <sys/stat.h>
#include <errno.h>
#include <cstdarg>
#include <sys/types.h>          /* For portability */
#include <sys/sem.h>
#include <time.h>
#include <memory.h>
union semun {                   /* Used in calls to semctl() */
    int                 val;
    struct semid_ds *   buf;
    unsigned short *    array;
#if defined(__linux__)
    struct seminfo *    __buf;
#endif
};

int main(int argc, char *argv[])
{
    int semid, key, perms;
    struct sembuf sops[2];

    key = 12345;
    perms = S_IRUSR | S_IWUSR;
    semid = semget(key, 1, IPC_CREAT | IPC_EXCL | perms);

    if (semid != -1) {                  /* Successfully created the semaphore */
        union semun arg;

        /* XXXX */

        arg.val = 0;                    /* So initialize it */
        if (semctl(semid, 0, SETVAL, arg) == -1){
            perror("semctl");
            exit(EXIT_FAILURE);
        }
            

    } else {                            /* We didn't create semaphore set */
        if (errno != EEXIST) {          /* Unexpected error from semget() */
            perror("semget 1");
            exit(EXIT_FAILURE);
        } else {                        /* Someone else already created it */
            semid = semget(key, 1, perms);      /* So just get ID */
            if (semid == -1){
                perror("semget 2");
                exit(EXIT_FAILURE);
            }
        }
    }

    /* Now perform some operation on the semaphore */

    sops[0].sem_op = 1;         /* Add 1 */
    sops[0].sem_num = 0;        /* ... to semaphore 0 */
    sops[0].sem_flg = 0;
    if (semop(semid, sops, 1) == -1){
        perror("semop");
        exit(EXIT_FAILURE);
    }
        

    exit(EXIT_SUCCESS);
}

#define _GNU_SOURCE
#include <string.h>
#include <stdio.h>
#include <stdlib.h>
#include <zconf.h>
#include <sys/types.h>
#include <sys/ipc.h>
#include <sys/msg.h>
#include <sys/stat.h>
#include <errno.h>
#include <cstdarg>
#include <sys/types.h>          /* For portability */
#include <sys/sem.h>
#include <time.h>
#include <memory.h>
union semun {                   /* Used in calls to semctl() */
    int                 val;
    struct semid_ds *   buf;
    unsigned short *    array;
#if defined(__linux__)
    struct seminfo *    __buf;
#endif
};

int
main(int argc, char *argv[])
{
    int semid, key, perms;
    struct sembuf sops[2];

    if (argc != 2 || strcmp(argv[1], "--help") == 0){
        printf("%s sem-op\n", argv[0]);
        exit(EXIT_FAILURE);
    }
        

    key = 12345;
    perms = S_IRUSR | S_IWUSR;

    semid = semget(key, 1, IPC_CREAT | IPC_EXCL | perms);
    if (semid != -1) {                  /* Successfully created the semaphore */
        union semun arg;
        struct sembuf sop;

        sleep(5);
        printf("%ld: created semaphore\n", (long) getpid());

        arg.val = 0;                    /* So initialize it to 0 */
        if (semctl(semid, 0, SETVAL, arg) == -1){
            printf("semctl 1");
            exit(EXIT_FAILURE);
        }
           
        printf("%ld: initialized semaphore\n", (long) getpid());

        /* Perform a "no-op" semaphore operation - changes sem_otime
           so other processes can see we've initialized the set. */

        sop.sem_num = 0;                /* Operate on semaphore 0 */
        sop.sem_op = 0;                 /* Wait for value to equal 0 */
        sop.sem_flg = 0;
        if (semop(semid, &sop, 1) == -1){
            printf("semop");
            exit(EXIT_FAILURE);
        }
            
        printf("%ld: completed dummy semop()\n", (long) getpid());

    } else {                            /* We didn't create the semaphore set */

        if (errno != EEXIST) {          /* Unexpected error from semget() */
            printf("semget 1");
            exit(EXIT_FAILURE);
        } else {                        /* Someone else already created it */
            const int MAX_TRIES = 10;
            int j;
            union semun arg;
            struct semid_ds ds;

            semid = semget(key, 1, perms);      /* So just get ID */
            if (semid == -1){
                printf("semget 2");
                exit(EXIT_FAILURE);
            }
                

            printf("%ld: got semaphore key\n", (long) getpid());
            /* Wait until another process has called semop() */

            arg.buf = &ds;
            for (j = 0; j < MAX_TRIES; j++) {
                printf("Try %d\n", j);
                if (semctl(semid, 0, IPC_STAT, arg) == -1){
                    printf("semctl 2");
                    exit(EXIT_FAILURE);
                }
                    

                if (ds.sem_otime != 0)          /* Semop() performed? */
                    break;                      /* Yes, quit loop */
                sleep(1);                       /* If not, wait and retry */
            }

            if (ds.sem_otime == 0)              /* Loop ran to completion! */
            {
                printf("Existing semaphore not initialized");
                exit(EXIT_FAILURE);
            }
        }
    }

    /* Now perform some operation on the semaphore */

    sops[0].sem_num = 0;                        /* Operate on semaphore 0... */
    sops[0].sem_op = atoi(argv[1]);
    sops[0].sem_flg = 0;
    if (semop(semid, sops, 1) == -1){
        printf("semop");
        exit(EXIT_FAILURE);
    }
        

    exit(EXIT_SUCCESS);
}

NAME
       shmget - allocates a System V shared memory segment

SYNOPSIS
       #include <sys/ipc.h>
       #include <sys/shm.h>

       int shmget(key_t key, size_t size, int shmflg);

NAME
       shmat, shmdt - System V shared memory operations

SYNOPSIS
       #include <sys/types.h>
       #include <sys/shm.h>

       void *shmat(int shmid, const void *shmaddr, int shmflg); 

NAME
       shmat, shmdt - System V shared memory operations

SYNOPSIS
       #include <sys/types.h>
       #include <sys/shm.h>

       int shmdt(const void *shmaddr); 

NAME
       shmctl - System V shared memory control

SYNOPSIS
       #include <sys/ipc.h>
       #include <sys/shm.h>

       int shmctl(int shmid, int cmd, struct shmid_ds *buf); 

 struct shmid_ds
  {
    struct ipc_perm shm_perm;        /* operation permission struct */
    size_t shm_segsz;            /* size of segment in bytes */
    __time_t shm_atime;            /* time of last shmat() */
#ifndef __x86_64__
    unsigned long int __unused1;
#endif
    __time_t shm_dtime;            /* time of last shmdt() */
#ifndef __x86_64__
    unsigned long int __unused2;
#endif
    __time_t shm_ctime;            /* time of last change by shmctl() */
#ifndef __x86_64__
    unsigned long int __unused3;
#endif
    __pid_t shm_cpid;            /* pid of creator */
    __pid_t shm_lpid;            /* pid of last shmop */
    shmatt_t shm_nattch;        /* number of current attaches */
    __syscall_ulong_t __unused4;
    __syscall_ulong_t __unused5;
  };

 #include <unistd.h>
#include <signal.h>
#include <stdio.h>
#include <malloc.h>
#include <stdlib.h>
#include <errno.h>
#include <sys/mman.h>
#include <string.h>
#include <semaphore.h>
#include <sys/stat.h>
#include <fcntl.h>
#include <mqueue.h>
#include <sys/stat.h>
#include <fcntl.h>
#include <sys/types.h>
#include <sys/ipc.h>
#include <sys/shm.h>
#include <sys/stat.h>
static void usageError(const char *progName, const char *msg)
{
    if (msg != NULL)
        fprintf(stderr, "%s", msg);
    fprintf(stderr, "Usage: %s [-cx] {-f pathname | -k key | -p} "
                    "seg-size [octal-perms]\n", progName);
    fprintf(stderr, "    -c           Use IPC_CREAT flag\n");
    fprintf(stderr, "    -x           Use IPC_EXCL flag\n");
    fprintf(stderr, "    -f pathname  Generate key using ftok()\n");
    fprintf(stderr, "    -k key       Use 'key' as key\n");
    fprintf(stderr, "    -p           Use IPC_PRIVATE key\n");
    exit(EXIT_FAILURE);
}
int main(int argc, char *argv[])
{
    /* Parse command-line options and arguments */

    int numKeyFlags = 0;        /* Counts -f, -k, and -p options */
    int flags = 0;
    long lkey;
    key_t key;
    int opt;                    /* Option character from getopt() */

    while ((opt = getopt(argc, argv, "cf:k:px")) != -1) {
        switch (opt) {
            case 'c':
                flags |= IPC_CREAT;
                break;

            case 'f':               /* -f pathname */
                key = ftok(optarg, 1);
                if (key == -1){
                    printf("ftok");
                    exit(EXIT_FAILURE);
                }
                    
                numKeyFlags++;
                break;

            case 'k':               /* -k key (octal, decimal or hexadecimal) */
                if (sscanf(optarg, "%li", &lkey) != 1){
                    printf("-k option requires a numeric argument\n");
                    exit(EXIT_FAILURE);
                }
                    
                key = lkey;
                numKeyFlags++;
                break;

            case 'p':
                key = IPC_PRIVATE;
                numKeyFlags++;
                break;

            case 'x':
                flags |= IPC_EXCL;
                break;

            default:
                usageError(argv[0], NULL);
        }
    }

    if (numKeyFlags != 1)
        usageError(argv[0], "Exactly one of the options -f, -k, "
                            "or -p must be supplied\n");

    if (optind >= argc)
        usageError(argv[0], "Size of segment must be specified\n");

    int segSize = atoi(argv[optind]);

    unsigned int perms = (argc <= optind + 1) ? (S_IRUSR | S_IWUSR) :
                         atoi(argv[optind + 1]);

    int shmid = shmget(key, segSize, flags | perms);
    if (shmid == -1){
        perror("shmget");
        exit(EXIT_FAILURE);
    }
        

    printf("%d\n", shmid);      /* On success, display shared mem. id */
    exit(EXIT_SUCCESS);
}

// svshm_attach.c
#include <unistd.h>
#include <signal.h>
#include <stdio.h>
#include <malloc.h>
#include <stdlib.h>
#include <errno.h>
#include <sys/mman.h>
#include <string.h>
#include <semaphore.h>
#include <sys/stat.h>
#include <fcntl.h>
#include <mqueue.h>
#include <sys/stat.h>
#include <fcntl.h>
#include <sys/types.h>
#include <sys/ipc.h>
#include <sys/shm.h>
#include <sys/stat.h>
static void
usageError(char *progName)
{
    fprintf(stderr, "Usage: %s [shmid:address[rR]]...\n", progName);
    fprintf(stderr, "            r=SHM_RND; R=SHM_RDONLY\n");
    exit(EXIT_FAILURE);
}
int main(int argc, char *argv[])
{
    printf("SHMLBA = %ld (%#lx), PID = %ld\n",
           (long) SHMLBA, (unsigned long) SHMLBA, (long) getpid());

    for (int j = 1; j < argc; j++) {
        char *p;
        int shmid = strtol(argv[j], &p, 0);
        if (*p != ':')
            usageError(argv[0]);

        void *addr = (void *) strtol(p + 1, NULL, 0);
        int flags = (strchr(p + 1, 'r') != NULL) ? SHM_RND : 0;
        if (strchr(p + 1, 'R') != NULL)
            flags |= SHM_RDONLY;

        char *retAddr = (char *)shmat(shmid, addr, flags);
        if (retAddr == (void *) -1){
            printf("shmat: %s", argv[j]);
            exit(EXIT_FAILURE);
        }
            

        printf("%d: %s ==> %p\n", j, argv[j], retAddr);
    }

    printf("Sleeping 5 seconds\n");
    sleep(5);

    exit(EXIT_SUCCESS);
}
 

#include <unistd.h>
#include <signal.h>
#include <stdio.h>
#include <malloc.h>
#include <stdlib.h>
#include <errno.h>
#include <sys/mman.h>
#include <string.h>
#include <semaphore.h>
#include <sys/stat.h>
#include <fcntl.h>
#include <mqueue.h>
#include <sys/stat.h>
#include <fcntl.h>
#include <sys/types.h>
#include <sys/ipc.h>
#include <sys/shm.h>
#include <sys/stat.h>
#include <time.h>
static void
printShmDS(const struct shmid_ds *ds)
{
    printf("Size:                      %ld\n", (long) ds->shm_segsz);
    printf("# of attached processes:   %ld\n", (long) ds->shm_nattch);

    printf("Mode:                      %lo",
           (unsigned long) ds->shm_perm.mode);
#ifdef SHM_DEST
    printf("%s", (ds->shm_perm.mode & SHM_DEST) ? " [DEST]" : "");
#endif
#ifdef SHM_LOCKED
    printf("%s", (ds->shm_perm.mode & SHM_LOCKED) ? " [LOCKED]" : "");
#endif
    printf("\n");

    printf("Last shmat():              %s", ctime(&ds->shm_atime));
    printf("Last shmdt():              %s", ctime(&ds->shm_dtime));
    printf("Last change:               %s", ctime(&ds->shm_ctime));

    printf("Creator PID:               %ld\n", (long) ds->shm_cpid);
    printf("PID of last attach/detach: %ld\n", (long) ds->shm_lpid);
}
int main(int argc, char *argv[])
{
    if (argc != 2 || strcmp(argv[1], "--help") == 0){
        printf("%s shmid\n", argv[0]);
        exit(EXIT_FAILURE);
    }
        

    struct shmid_ds ds;
    if (shmctl(atoi(argv[1]), IPC_STAT, &ds) == -1){
        printf("shmctl");
        exit(EXIT_FAILURE);
    }
        

    printShmDS(&ds);

    exit(EXIT_SUCCESS);
}

// svshm_info.c
#define _GNU_SOURCE
#include <sys/shm.h>
int
main(int argc, char *argv[])
{
    struct shm_info info;

    int s = shmctl(0, SHM_INFO, (struct shmid_ds *) &info);
    if (s == -1){
			perror("shmctl");
			exit(EXIT_FAILURE);
		}

    printf("Maximum ID index = %d\n", s);
    printf("shm_tot          = %ld\n", (long) info.shm_tot);
    printf("shm_rss          = %ld\n", (long) info.shm_rss);
    printf("shm_swp          = %ld\n", (long) info.shm_swp);
    printf("swap_attempts    = %ld\n", (long) info.swap_attempts);
    printf("swap_successes   = %ld\n", (long) info.swap_successes);

    exit(EXIT_SUCCESS);
}

 // svshm_lock
int
main(int argc, char *argv[])
{
    for (int j = 1; j < argc; j++)
        if (shmctl(atoi(argv[j]), SHM_LOCK, NULL) == -1){
			perror("shmctl");
			exit(EXIT_FAILURE);
		}
            

    exit(EXIT_SUCCESS);
}

// svshm_rm.c
int
main(int argc, char *argv[])
{
    for (int j = 1; j < argc; j++)
        if (shmctl(atoi(argv[j]), IPC_RMID, NULL) == -1){
			perror("shmctl");
			exit(EXIT_FAILURE);
		}
            

    exit(EXIT_SUCCESS);
}
 

 // svshm_unlock 解锁

int
main(int argc, char *argv[])
{
    for (int j = 1; j < argc; j++)
        if (shmctl(atoi(argv[j]), SHM_UNLOCK, NULL) == -1){
			perror("shmctl");
			exit(EXIT_FAILURE);
		}
            

    exit(EXIT_SUCCESS);
}

 #include<unistd.h>
#include<stdio.h>
#include<stdlib.h>
#include <string>
#include <sys/ipc.h>
#include <sys/shm.h>
#include "memory.h"


typedef struct Stu{
    int  age;
    char name[10];
}Stu;

int main(int argc,char *argv[]){
    Stu s;
    strcpy(s.name, "jack");

    //创建共享内存段
    int id = shmget(1234, 8, IPC_CREAT | 0644);
    if (id == -1){
        perror("shmget");
        exit(1);
    }

    //挂载到进程的地址空间
    Stu *p = (Stu *)shmat(id, nullptr, 0);

    int i = 0;
    while (1){
        s.age = i++;
        memcpy(p, &s, sizeof(Stu));  //写到共享段中
        sleep(2);
    }

    return 0;
}

 #include <iostream>
#include <string>
#include "unistd.h"
#include <sys/ipc.h>
#include <sys/shm.h>
typedef struct Stu{
    int  age;
    char name[10];
}Stu;

int main() {
    int id = shmget(1234, 8, 0);
    if (id == -1){
        perror("shmget");
        exit(1);
    }

    //挂载到进程的地址空间
    Stu *p = (Stu *)shmat(id, nullptr, 0);
    while (1){
        std::cout << "age = " << p->age << ", name = " << p->name << "\n";
        sleep(2);
    }

    return 0;
}

struct msgbuf{
				long mtype;         /* 放消息编号，必须> 0 */
				char mtext[msgsz];   /* 消息内容（消息正文） */
			};	

 #include <sys/types.h>
#include <sys/ipc.h>
#include <sys/msg.h>
//功能：利用key值创建、或者获取一个消息队列
/*
1.如果key没有对应任何消息队列，那就创建一个新的消息队列
2.如果key已经对应了某个消息队列，说明消息队列已经存在了，那就获取这个消息队列来使用
*/
//msgflg:指定创建时的原始权限，比如0664
int msgget(key_t key, int msgflg);

#include <sys/types.h>
#include <sys/ipc.h>
/*
ftok通过指定路径名和一个整形数，就可以计算并返回一个唯一对应的key值，
---------只要路径名和整形数不变，所对应的key值就唯一不变的
*/
//ftok只会使用整形数（proj_id）的低8位，因此我们往往会指定为一个ASCII码值
key_t ftok(const char *pathname, int proj_id);

#include <stdio.h>
#include <stdlib.h>
#include <unistd.h>
#include <sys/types.h>
#include <sys/ipc.h>
#include <sys/msg.h>
#include <sys/stat.h>
#include <fcntl.h>
#define MSG_FIFE "./msgfile"
int  create_or_get_msgque(){
    //创建消息队列，返回msgid
     int msgId=-1;
     key_t key=-1;
     int fd=0;
     //为了用到文件路径名，用open创建
     fd=open(MSG_FIFE,O_RDWR|O_CREAT,0664);
     //用生成的路径+asc码生成唯一整数
     key=ftok(MSG_FIFE,'a');
     msgId=msgget(key,0664|IPC_CREAT);
     return msgId;
}
int main(void){
    int msgID=-1;
    int ret=-1;
    msgID=create_or_get_msgque();
    /*父子进程收发消息*/
    ret=fork();
    if(ret>0){//父进程发送消息

    }
    else if(ret==0){//子进程接收消息

    }
    return 0;
}