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@motorola.com)
 *
 * Spinlocks:               Mohamed Abbas           (abbas.mohamed@intel.com)
 * Lockless receive & send, fd based notify:
 * 			    Manfred Spraul	    (manfred@colorfullife.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/namei.h>
#include <linux/sysctl.h>
#include <linux/poll.h>
#include <linux/mqueue.h>
#include <linux/msg.h>
#include <linux/skbuff.h>
#include <linux/netlink.h>
#include <linux/syscalls.h>
#include <linux/signal.h>
#include <net/sock.h>
#include "util.h"

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

#define SEND		0
#define RECV		1

#define STATE_NONE	0
#define STATE_PENDING	1
#define STATE_READY	2

/* used by sysctl */
#define FS_MQUEUE 	1
#define CTL_QUEUESMAX 	2
#define CTL_MSGMAX 	3
#define CTL_MSGSIZEMAX 	4

/* default values */
#define DFLT_QUEUESMAX	256	/* max number of message queues */
#define DFLT_MSGMAX 	10	/* max number of messages in each queue */
#define HARD_MSGMAX 	(131072/sizeof(void*))
#define DFLT_MSGSIZEMAX 8192	/* max message size */

#define NOTIFY_COOKIE_LEN	32

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 msg_msg **messages;
	struct mq_attr attr;

	struct sigevent notify;
	pid_t notify_owner;
	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 inode_operations mqueue_dir_inode_operations;
static struct file_operations mqueue_file_operations;
static struct super_operations mqueue_super_ops;
static void remove_notification(struct mqueue_inode_info *info);

static spinlock_t mq_lock;
static kmem_cache_t *mqueue_inode_cachep;
static struct vfsmount *mqueue_mnt;

static unsigned int queues_count;
static unsigned int queues_max 	= DFLT_QUEUESMAX;
static unsigned int msg_max 	= DFLT_MSGMAX;
static unsigned int msgsize_max = DFLT_MSGSIZEMAX;

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);
}

static struct inode *mqueue_get_inode(struct super_block *sb, int mode,
							struct mq_attr *attr)
{
	struct inode *inode;

	inode = new_inode(sb);
	if (inode) {
		inode->i_mode = mode;
		inode->i_uid = current->fsuid;
		inode->i_gid = current->fsgid;
		inode->i_blksize = PAGE_CACHE_SIZE;
		inode->i_blocks = 0;
		inode->i_mtime = inode->i_ctime = inode->i_atime =
				CURRENT_TIME;

		if (S_ISREG(mode)) {
			struct mqueue_inode_info *info;
			struct task_struct *p = current;
			struct user_struct *u = p->user;
			unsigned long mq_bytes, mq_msg_tblsz;

			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->messages = NULL;
			info->notify_owner = 0;
			info->qsize = 0;
			info->user = NULL;	/* set when all is ok */
			memset(&info->attr, 0, sizeof(info->attr));
			info->attr.mq_maxmsg = DFLT_MSGMAX;
			info->attr.mq_msgsize = DFLT_MSGSIZEMAX;
			if (attr) {
				info->attr.mq_maxmsg = attr->mq_maxmsg;
				info->attr.mq_msgsize = attr->mq_msgsize;
			}
			mq_msg_tblsz = info->attr.mq_maxmsg * sizeof(struct msg_msg *);
			mq_bytes = (mq_msg_tblsz +
				(info->attr.mq_maxmsg * info->attr.mq_msgsize));

			spin_lock(&mq_lock);
			if (u->mq_bytes + mq_bytes < u->mq_bytes ||
		 	    u->mq_bytes + mq_bytes >
			    p->signal->rlim[RLIMIT_MSGQUEUE].rlim_cur) {
				spin_unlock(&mq_lock);
				goto out_inode;
			}
			u->mq_bytes += mq_bytes;
			spin_unlock(&mq_lock);

			info->messages = kmalloc(mq_msg_tblsz, GFP_KERNEL);
			if (!info->messages) {
				spin_lock(&mq_lock);
				u->mq_bytes -= mq_bytes;
				spin_unlock(&mq_lock);
				goto out_inode;
			}
			/* all is ok */
			info->user = get_uid(u);
		} else if (S_ISDIR(mode)) {
			inode->i_nlink++;
			/* 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:
	make_bad_inode(inode);
	iput(inode);
	return NULL;
}

static int mqueue_fill_super(struct super_block *sb, void *data, int silent)
{
	struct inode *inode;

	sb->s_blocksize = PAGE_CACHE_SIZE;
	sb->s_blocksize_bits = PAGE_CACHE_SHIFT;
	sb->s_magic = MQUEUE_MAGIC;
	sb->s_op = &mqueue_super_ops;

	inode = mqueue_get_inode(sb, S_IFDIR | S_ISVTX | S_IRWXUGO, NULL);
	if (!inode)
		return -