Merge bk://bk.arm.linux.org.uk/linux-2.6-rmk

into ppc970.osdl.org:/home/torvalds/v2.6/linux

8 files changed, 1557 insertions, 129 deletions

diff --git a/ipc/Makefile b/ipc/Makefile
index ccc6c64c2493..0a6d626cd794 100644
--- a/ipc/Makefile
+++ b/ipc/Makefile
@@ -2,7 +2,8 @@
 # Makefile for the linux ipc.
 #
 
-obj-y   := util.o
-
 obj-$(CONFIG_SYSVIPC_COMPAT) += compat.o
-obj-$(CONFIG_SYSVIPC) += msg.o sem.o shm.o
+obj-$(CONFIG_SYSVIPC) += util.o msgutil.o msg.o sem.o shm.o
+obj_mq-$(CONFIG_COMPAT) += compat_mq.o
+obj-$(CONFIG_POSIX_MQUEUE) += mqueue.o msgutil.o $(obj_mq-y)
+
diff --git a/ipc/compat_mq.c b/ipc/compat_mq.c
new file mode 100644
index 000000000000..1520df89c424
--- /dev/null
+++ b/ipc/compat_mq.c
@@ -0,0 +1,196 @@
+/*
+ *  ipc/compat_mq.c
+ *    32 bit emulation for POSIX message queue system calls
+ *
+ *    Copyright (C) 2004 IBM Deutschland Entwicklung GmbH, IBM Corporation
+ *    Author: Arnd Bergmann <arnd@arndb.de>
+ */
+
+#include <linux/compat.h>
+#include <linux/fs.h>
+#include <linux/kernel.h>
+#include <linux/mqueue.h>
+#include <linux/syscalls.h>
+
+#include <asm/uaccess.h>
+
+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)
+{
+	if (verify_area(VERIFY_READ, uattr, sizeof *uattr))
+		return -EFAULT;
+
+	return __get_user(attr->mq_flags, &uattr->mq_flags)
+		| __get_user(attr->mq_maxmsg, &uattr->mq_maxmsg)
+		| __get_user(attr->mq_msgsize, &uattr->mq_msgsize)
+		| __get_user(attr->mq_curmsgs, &uattr->mq_curmsgs);
+}
+
+static inline int put_compat_mq_attr(const struct mq_attr *attr,
+			struct compat_mq_attr __user *uattr)
+{
+	if (clear_user(uattr, sizeof *uattr))
+		return -EFAULT;
+
+	return __put_user(attr->mq_flags, &uattr->mq_flags)
+		| __put_user(attr->mq_maxmsg, &uattr->mq_maxmsg)
+		| __put_user(attr->mq_msgsize, &uattr->mq_msgsize)
+		| __put_user(attr->mq_curmsgs, &uattr->mq_curmsgs);
+}
+
+asmlinkage long compat_sys_mq_open(const char __user *u_name,
+			int oflag, compat_mode_t mode,
+			struct compat_mq_attr __user *u_attr)
+{
+	struct mq_attr attr;
+	mm_segment_t oldfs;
+	char *name;
+	long ret;
+
+	if ((oflag & O_CREAT) == 0 || !u_attr)
+		return sys_mq_open(u_name, oflag, mode, 0);
+
+	if (get_compat_mq_attr(&attr, u_attr))
+		return -EFAULT;
+
+	name = getname(u_name);
+	if (IS_ERR(name))
+		return PTR_ERR(name);
+
+	oldfs = get_fs();
+	set_fs(KERNEL_DS);
+	ret = sys_mq_open(name, oflag, mode, &attr);
+	set_fs(oldfs);
+
+	putname(name);
+	return ret;
+}
+
+static struct timespec __user *compat_prepare_timeout(
+			const struct compat_timespec __user *u_abs_timeout)
+{
+	struct timespec ts, __user *u_ts;
+
+	if (!u_abs_timeout)
+		return 0;
+
+	u_ts = compat_alloc_user_space(sizeof(*u_ts));
+	if (get_compat_timespec(&ts, u_abs_timeout)
+		|| copy_to_user(u_ts, &ts, sizeof(*u_ts)))
+		return ERR_PTR(-EFAULT);
+
+	return u_ts;
+}
+
+asmlinkage long compat_sys_mq_timedsend(mqd_t mqdes,
+			const char __user *u_msg_ptr,
+			size_t msg_len, unsigned int msg_prio,
+			const struct compat_timespec __user *u_abs_timeout)
+{
+	struct timespec __user *u_ts;
+
+	u_ts = compat_prepare_timeout(u_abs_timeout);
+	if (IS_ERR(u_ts))
+		return -EFAULT;
+
+	return sys_mq_timedsend(mqdes, u_msg_ptr, msg_len,
+			msg_prio, u_ts);
+}
+
+asmlinkage ssize_t compat_sys_mq_timedreceive(mqd_t mqdes,
+			char __user *u_msg_ptr,
+			size_t msg_len, unsigned int __user *u_msg_prio,
+			const struct compat_timespec __user *u_abs_timeout)
+{
+	struct timespec *u_ts;
+
+	u_ts = compat_prepare_timeout(u_abs_timeout);
+	if (IS_ERR(u_ts))
+		return -EFAULT;
+
+	return sys_mq_timedreceive(mqdes, u_msg_ptr, msg_len,
+			u_msg_prio, u_ts);
+}
+
+static int get_compat_sigevent(struct sigevent *event,
+		const struct compat_sigevent __user *u_event)
+{
+	if (verify_area(VERIFY_READ, u_event, sizeof(*u_event)))
+		return -EFAULT;
+
+	return __get_user(event->sigev_value.sival_int,
+			  &u_event->sigev_value.sival_int)
+	     | __get_user(event->sigev_signo, &u_event->sigev_signo)
+	     | __get_user(event->sigev_notify, &u_event->sigev_notify)
+	     | __get_user(event->sigev_notify_thread_id,
+			  &u_event->sigev_notify_thread_id);
+}
+
+asmlinkage long compat_sys_mq_notify(mqd_t mqdes,
+			const struct compat_sigevent __user *u_notification)
+{
+	mm_segment_t oldfs;
+	struct sigevent notification;
+	char cookie[NOTIFY_COOKIE_LEN];
+	compat_uptr_t u_cookie;
+	long ret;
+
+	if (!u_notification)
+		return sys_mq_notify(mqdes, 0);
+
+	if (get_compat_sigevent(&notification, u_notification))
+		return -EFAULT;
+
+	if (notification.sigev_notify == SIGEV_THREAD) {
+		u_cookie = (compat_uptr_t)notification.sigev_value.sival_int;
+		if (copy_from_user(cookie, compat_ptr(u_cookie),
+						NOTIFY_COOKIE_LEN)) {
+			return -EFAULT;
+		}
+		notification.sigev_value.sival_ptr = cookie;
+	}
+
+	oldfs = get_fs();
+	set_fs(KERNEL_DS);
+	ret = sys_mq_notify(mqdes, &notification);
+	set_fs(oldfs);
+
+	return ret;
+}
+
+asmlinkage long compat_sys_mq_getsetattr(mqd_t mqdes,
+			const struct compat_mq_attr __user *u_mqstat,
+			struct compat_mq_attr __user *u_omqstat)
+{
+	struct mq_attr mqstat, omqstat;
+	struct mq_attr *p_mqstat = 0, *p_omqstat = 0;
+	mm_segment_t oldfs;
+	long ret;
+
+	if (u_mqstat) {
+		p_mqstat = &mqstat;
+		if (get_compat_mq_attr(p_mqstat, u_mqstat))
+			return -EFAULT;
+	}
+
+	if (u_omqstat)
+		p_omqstat = &omqstat;
+
+	oldfs = get_fs();
+	set_fs(KERNEL_DS);
+	ret = sys_mq_getsetattr(mqdes, p_mqstat, p_omqstat);
+	set_fs(oldfs);
+
+	if (ret)
+		return ret;
+
+	return (u_omqstat) ? put_compat_mq_attr(&omqstat, u_omqstat) : 0;
+}
diff --git a/ipc/mqueue.c b/ipc/mqueue.c
new file mode 100644
index 000000000000..f81441d63564
--- /dev/null
+++ b/ipc/mqueue.c
@@ -0,0 +1,1220 @@
+/*
+ * POSIX message queues filesystem for Linux.
+ *
+ * Copyright (C) 2003,2004  Krzysztof Benedyczak    (golbi@mat.uni.torun.pl)
+ *                          Michal Wronski          (wrona@mat.uni.torun.pl)
+ *
+ * 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/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 <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	64	/* max number of message queues */
+#define DFLT_MSGMAX 	40	/* max number of messages in each queue */
+#define HARD_MSGMAX 	(131072/sizeof(void*))
+#define DFLT_MSGSIZEMAX 16384	/* 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; /* notify.sigev_notify == SIGEV_NONE means */
+	pid_t notify_owner;	/*           no notification registered */
+	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 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;
+
+			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.sigev_notify = SIGEV_NONE;
+			info->qsize = 0;
+			memset(&info->attr, 0, sizeof(info->attr));
+			info->attr.mq_maxmsg = DFLT_MSGMAX;
+			info->attr.mq_msgsize = DFLT_MSGSIZEMAX;
+			info->messages = kmalloc(DFLT_MSGMAX * sizeof(struct msg_msg *), GFP_KERNEL);
+			if (!info->messages) {
+				make_bad_inode(inode);
+				iput(inode);
+				inode = NULL;
+			}
+		} 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;
+}
+
+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_IRWXUGO);
+	if (!inode)
+		return -ENOMEM;
+
+	sb->s_root = d_alloc_root(inode);
+	if (!sb->s_root) {
+		iput(inode);
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+static struct super_block *mqueue_get_sb(struct file_system_type *fs_type,
+					 int flags, const char *dev_name,
+					 void *data)
+{
+	return get_sb_single(fs_type, flags, data, mqueue_fill_super);
+}
+
+static void init_once(void *foo, kmem_cache_t * cachep, unsigned long flags)
+{
+	struct mqueue_inode_info *p = (struct mqueue_inode_info *) foo;
+
+	if ((flags & (SLAB_CTOR_VERIFY | SLAB_CTOR_CONSTRUCTOR)) ==
+		SLAB_CTOR_CONSTRUCTOR)
+		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, SLAB_KERNEL);
+	if (!ei)
+		return NULL;
+	return &ei->vfs_inode;
+}
+
+static void mqueue_destroy_inode(struct inode *inode)
+{
+	kmem_cache_free(mqueue_inode_cachep, MQUEUE_I(inode));
+}
+
+static void mqueue_delete_inode(struct inode *inode)
+{
+	struct mqueue_inode_info *info;
+	int i;
+
+	if (S_ISDIR(inode->i_mode)) {
+		clear_inode(inode);
+		return;
+	}
+	info = MQUEUE_I(inode);
+	spin_lock(&info->lock);
+	for (i = 0; i < info->attr.mq_curmsgs; i++)
+		free_msg(info->messages[i]);
+	kfree(info->messages);
+	spin_unlock(&info->lock);
+
+	clear_inode(inode);
+
+	spin_lock(&mq_lock);
+	queues_count--;
+	spin_unlock(&mq_lock);
+}
+
+static int mqueue_create(struct inode *dir, struct dentry *dentry,
+				int mode, struct nameidata *nd)
+{
+	struct inode *inode;
+	int error;
+
+	spin_lock(&mq_lock);
+	if (queues_count >= queues_max && !capable(CAP_SYS_RESOURCE)) {
+		error = -ENOSPC;
+		goto out_lock;
+	}
+	queues_count++;
+	spin_unlock(&mq_lock);
+
+	inode = mqueue_get_inode(dir->i_sb, mode);
+	if (!inode) {
+		error = -ENOMEM;
+		spin_lock(&mq_lock);
+		queues_count--;
+		goto out_lock;
+	}
+
+	dir->i_size += DIRENT_SIZE;
+	dir->i_ctime = dir->i_mtime = dir->i_atime = CURRENT_TIME;
+
+	d_instantiate(dentry, inode);
+	dget(dentry);
+	return 0;
+out_lock:
+	spin_unlock(&mq_lock);
+	return error;
+}
+
+static int mqueue_unlink(struct inode *dir, struct dentry *dentry)
+{
+  	struct inode *inode = dentry->d_inode;
+
+	dir->i_ctime = dir->i_mtime = dir->i_atime = CURRENT_TIME;
+	dir->i_size -= DIRENT_SIZE;
+  	inode->i_nlink--;
+  	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(filp->f_dentry->d_inode);
+	char buffer[FILENT_SIZE];
+	size_t slen;
+	loff_t o;
+
+	if (!count)
+		return 0;
+
+	spin_lock(&info->lock);
+	snprintf(buffer, sizeof(buffer),
+			"QSIZE:%-10lu NOTIFY:%-5d SIGNO:%-5d NOTIFY_PID:%-6d\n",
+			info->qsize,
+			info->notify.sigev_notify,
+			(info->notify.sigev_notify == SIGEV_SIGNAL ) ?
+				info->notify.sigev_signo : 0,
+			(info->notify.sigev_notify != SIGEV_NONE) ?
+				info->notify_owner : 0);
+	spin_unlock(&info->lock);
+	buffer[sizeof(buffer)-1] = '\0';
+	slen = strlen(buffer)+1;
+
+	o = *off;
+	if (o > slen)
+		return 0;
+
+	if (o + count > slen)
+		count = slen - o;
+
+	if (copy_to_user(u_data, buffer + o, count))
+		return -EFAULT;
+
+	*off = o + count;
+	filp->f_dentry->d_inode->i_atime = filp->f_dentry->d_inode->i_ctime = CURRENT_TIME;
+	return count;
+}
+
+static int mqueue_flush_file(struct file *filp)
+{
+	struct mqueue_inode_info *info = MQUEUE_I(filp->f_dentry->d_inode);
+
+	spin_lock(&info->lock);
+	if (info->notify.sigev_notify != SIGEV_NONE &&
+			current->tgid == info->notify_owner)
+		remove_notification(info);
+
+	spin_unlock(&info->lock);
+	return 0;
+}
+
+static unsigned int mqueue_poll_file(struct file *filp, struct poll_table_struct *poll_tab)
+{
+	struct mqueue_inode_info *info = MQUEUE_I(filp->f_dentry->d_inode);
+	int retval = 0;
+
+	poll_wait(filp, &info->wait_q, poll_tab);
+
+	spin_lock(&info->lock);
+	if (info->attr.mq_curmsgs)
+		retval = POLLIN | POLLRDNORM;
+
+	if (info->attr.mq_curmsgs < info->attr.mq_maxmsg)
+		retval |= POLLOUT | POLLWRNORM;
+	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;
+
+	ewp->task = current;
+
+	list_for_each_entry(walk, &info->e_wait_q[sr].list, list) {
+		if (walk->task->static_prio <= current->static_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,
+			long timeout, struct ext_wait_queue *ewp)
+{
+	int retval;
+	signed long time;
+
+	wq_add(info, sr, ewp);
+
+	for (;;) {
+		set_current_state(TASK_INTERRUPTIBLE);
+
+		spin_unlock(&info->lock);
+		time = schedule_timeout(timeout);
+
+		while (ewp->state == STATE_PENDING)
+			cpu_relax();
+
+		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);
+}
+
+/* Auxiliary functions to manipulate messages' list */
+static void msg_insert(struct msg_msg *ptr, struct mqueue_inode_info *info)
+{
+	int k;
+
+	k = info->attr.mq_curmsgs - 1;
+	while (k >= 0 && info->messages[k]->m_type >= ptr->m_type) {
+		info->messages[k + 1] = info->messages[k];
+		k--;
+	}
+	info->attr.mq_curmsgs++;
+	info->qsize += ptr->m_ts;
+	info->messages[k + 1] = ptr;
+}
+
+static inline struct msg_msg *msg_get(struct mqueue_inode_info *info)
+{
+	info->qsize -= info->messages[--info->attr.mq_curmsgs]->m_ts;
+	return info->messages[info->attr.mq_curmsgs];
+}
+
+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.sigev_notify != SIGEV_NONE &&
+			info->attr.mq_curmsgs == 1) {
+		/* sends signal */
+		if (info->notify.sigev_notify == SIGEV_SIGNAL) {
+			struct 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;
+			sig_i.si_pid = current->tgid;
+			sig_i.si_uid = current->uid;
+
+			kill_proc_info(info->notify.sigev_signo,
+				       &sig_i, info->notify_owner);
+		} else if (info->notify.sigev_notify == SIGEV_THREAD) {
+			set_cookie(info->notify_cookie, NOTIFY_WOKENUP);
+			netlink_sendskb(info->notify_sock,
+					info->notify_cookie, 0);
+		}
+		/* after notification unregisters process */
+		info->notify.sigev_notify = SIGEV_NONE;
+	}
+	wake_up(&info->wait_q);
+}
+
+static long prepare_timeout(const struct timespec __user *u_arg)
+{
+	struct timespec ts, nowts;
+	long timeout;
+
+	if (u_arg) {
+		if (unlikely(copy_from_user(&ts, u_arg,
+					sizeof(struct timespec))))
+			return -EFAULT;
+
+		if (unlikely(ts.tv_nsec < 0 || ts.tv_sec < 0
+			|| ts.tv_nsec >= NSEC_PER_SEC))
+			return -EINVAL;
+		nowts = CURRENT_TIME;
+		/* first subtract as jiffies can't be too big */
+		ts.tv_sec -= nowts.tv_sec;
+		if (ts.tv_nsec < nowts.tv_nsec) {
+			ts.tv_nsec += NSEC_PER_SEC;
+			ts.tv_sec--;
+		}
+		ts.tv_nsec -= nowts.tv_nsec;
+		if (ts.tv_sec < 0)
+			return 0;
+
+		timeout = timespec_to_jiffies(&ts) + 1;
+	} else
+		return MAX_SCHEDULE_TIMEOUT;
+
+	return timeout;
+}
+
+static void remove_notification(struct mqueue_inode_info *info)
+{
+	if (info->notify.sigev_notify == SIGEV_THREAD) {
+		set_cookie(info->notify_cookie, NOTIFY_REMOVED);
+		netlink_sendskb(info->notify_sock, info->notify_cookie, 0);
+	}
+	info->notify.sigev_notify = SIGEV_NONE;
+}
+
+/*
+ * Invoked when creating a new queue via sys_mq_open
+ */
+static struct file *do_create(struct dentry *dir, struct dentry *dentry,
+			int oflag, mode_t mode, struct mq_attr __user *u_attr)
+{
+	struct file *filp;
+	struct inode *inode;
+	struct mqueue_inode_info *info;
+	struct msg_msg **msgs = NULL;
+	struct mq_attr attr;
+	int ret;
+
+	if (u_attr != NULL) {
+		if (copy_from_user(&attr, u_attr, sizeof(attr)))
+			return ERR_PTR(-EFAULT);
+
+		if (attr.mq_maxmsg <= 0 || attr.mq_msgsize <= 0)
+			return ERR_PTR(-EINVAL);
+		if (capable(CAP_SYS_RESOURCE)) {
+			if (attr.mq_maxmsg > HARD_MSGMAX)
+				return ERR_PTR(-EINVAL);
+		} else {
+			if (attr.mq_maxmsg > msg_max ||
+					attr.mq_msgsize > msgsize_max)
+				return ERR_PTR(-EINVAL);
+		}
+		msgs = kmalloc(attr.mq_maxmsg * sizeof(*msgs), GFP_KERNEL);
+		if (!msgs)
+			return ERR_PTR(-ENOMEM);
+	} else {
+		msgs = NULL;
+	}
+
+	ret = vfs_create(dir->d_inode, dentry, mode, NULL);
+	if (ret) {
+		kfree(msgs);
+		return ERR_PTR(ret);
+	}
+
+	inode = dentry->d_inode;
+	info = MQUEUE_I(inode);
+
+	if (msgs) {
+		info->attr.mq_maxmsg = attr.mq_maxmsg;
+		info->attr.mq_msgsize = attr.mq_msgsize;
+		kfree(info->messages);
+		info->messages = msgs;
+	}
+
+	filp = dentry_open(dentry, mqueue_mnt, oflag);
+	if (!IS_ERR(filp))
+		dget(dentry);
+
+	return filp;
+}
+
+/* Opens existing queue */
+static struct file *do_open(struct dentry *dentry, int oflag)
+{
+static int oflag2acc[O_ACCMODE] = { MAY_READ, MAY_WRITE,
+					MAY_READ | MAY_WRITE };
+	struct file *filp;
+
+	if ((oflag & O_ACCMODE) == (O_RDWR | O_WRONLY))
+		return ERR_PTR(-EINVAL);
+
+	if (permission(dentry->d_inode, oflag2acc[oflag & O_ACCMODE], NULL))
+		return ERR_PTR(-EACCES);
+
+	filp = dentry_open(dentry, mqueue_mnt, oflag);
+
+	if (!IS_ERR(filp))
+		dget(dentry);
+
+	return filp;
+}
+
+asmlinkage long sys_mq_open(const char __user *u_name, int oflag, mode_t mode,
+				struct mq_attr __user *u_attr)
+{
+	struct dentry *dentry;
+	struct file *filp;
+	char *name;
+	int fd, error;
+
+	if (IS_ERR(name = getname(u_name)))
+		return PTR_ERR(name);
+
+	fd = get_unused_fd();
+	if (fd < 0)
+		goto out_putname;
+
+	down(&mqueue_mnt->mnt_root->d_inode->i_sem);
+	dentry = lookup_one_len(name, mqueue_mnt->mnt_root, strlen(name));
+	if (IS_ERR(dentry)) {
+		error = PTR_ERR(dentry);
+		goto out_err;
+	}
+	mntget(mqueue_mnt);
+
+	if (oflag & O_CREAT) {
+		if (dentry->d_inode) {	/* entry already exists */
+			filp = (oflag & O_EXCL) ? ERR_PTR(-EEXIST) :
+					do_open(dentry, oflag);
+		} else {
+			filp = do_create(mqueue_mnt->mnt_root, dentry,
+						oflag, mode, u_attr);
+		}
+	} else
+		filp = (dentry->d_inode) ? do_open(dentry, oflag) :
+					ERR_PTR(-ENOENT);
+
+	dput(dentry);
+
+	if (IS_ERR(filp)) {
+		error = PTR_ERR(filp);
+		goto out_putfd;
+	}
+
+	fd_install(fd, filp);
+	goto out_upsem;
+
+out_putfd:
+	mntput(mqueue_mnt);
+	put_unused_fd(fd);
+out_err:
+	fd = error;
+out_upsem:
+	up(&mqueue_mnt->mnt_root->d_inode->i_sem);
+out_putname:
+	putname(name);
+	return fd;
+}
+
+asmlinkage long sys_mq_unlink(const char __user *u_name)
+{
+	int err;
+	char *name;
+	struct dentry *dentry;
+	struct inode *inode = NULL;
+
+	name = getname(u_name);
+	if (IS_ERR(name))
+		return PTR_ERR(name);
+
+	down(&mqueue_mnt->mnt_root->d_inode->i_sem);
+	dentry = lookup_one_len(name, mqueue_mnt->mnt_root, strlen(name));
+	if (IS_ERR(dentry)) {
+		err = PTR_ERR(dentry);
+		goto out_unlock;
+	}
+
+	if (!dentry->d_inode) {
+		err = -ENOENT;
+		goto out_err;
+	}
+
+	if (permission(dentry->d_inode, MAY_WRITE, NULL)) {
+		err = -EACCES;
+		goto out_err;
+	}
+	inode = dentry->d_inode;
+	if (inode)
+		atomic_inc(&inode->i_count);
+
+	err = vfs_unlink(dentry->d_parent->d_inode, dentry);
+out_err:
+	dput(dentry);
+
+out_unlock:
+	up(&mqueue_mnt->mnt_root->d_inode->i_sem);
+	putname(name);
+	if (inode)
+		iput(inode);
+
+	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. Therefore an intermediate STATE_PENDING state and memory barriers
+ * are necessary. The same algorithm is used for sysv semaphores, see
+ * ipc/sem.c fore more details.
+ *
+ * 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 mqueue_inode_info *info,
+				  struct msg_msg *message,
+				  struct ext_wait_queue *receiver)
+{
+	receiver->msg = message;
+	list_del(&receiver->list);
+	receiver->state = STATE_PENDING;
+	wake_up_process(receiver->task);
+	wmb();
+	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 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;
+	}
+	msg_insert(sender->msg, info);
+	list_del(&sender->list);
+	sender->state = STATE_PENDING;
+	wake_up_process(sender->task);
+	wmb();
+	sender->state = STATE_READY;
+}
+
+asmlinkage long sys_mq_timedsend(mqd_t mqdes, const char __user *u_msg_ptr,
+	size_t msg_len, unsigned int msg_prio,
+	const struct timespec __user *u_abs_timeout)
+{
+	struct file *filp;
+	struct inode *inode;
+	struct ext_wait_queue wait;
+	struct ext_wait_queue *receiver;
+	struct msg_msg *msg_ptr;
+	struct mqueue_inode_info *info;
+	long timeout;
+	int ret;
+
+	if (unlikely(msg_prio >= (unsigned long) MQ_PRIO_MAX))
+		return -EINVAL;
+
+	timeout = prepare_timeout(u_abs_timeout);
+
+	ret = -EBADF;
+	filp = fget(mqdes);
+	if (unlikely(!filp))
+		goto out;
+
+	inode = filp->f_dentry->d_inode;
+	if (unlikely(filp->f_op != &mqueue_file_operations))
+		goto out_fput;
+	info = MQUEUE_I(inode);
+
+	if (unlikely(!(filp->f_mode & FMODE_WRITE)))
+		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((void *)u_msg_ptr, msg_len);
+	if (unlikely(IS_ERR(msg_ptr))) {
+		ret = PTR_ERR(msg_ptr);
+		goto out_fput;
+	}
+	msg_ptr->m_ts = msg_len;
+	msg_ptr->m_type = msg_prio;
+
+	spin_lock(&info->lock);
+
+	if (info->attr.mq_curmsgs == info->attr.mq_maxmsg) {
+		if (filp->f_flags & O_NONBLOCK) {
+			spin_unlock(&info->lock);
+			ret = -EAGAIN;
+		} else if (unlikely(timeout < 0)) {
+			spin_unlock(&info->lock);
+			ret = timeout;
+		} else {
+			wait.task = current;
+			wait.msg = (void *) msg_ptr;
+			wait.state = STATE_NONE;
+			ret = wq_sleep(info, SEND, timeout, &wait);
+			if (ret < 0)
+				free_msg(msg_ptr);
+		}
+	} else {
+		receiver = wq_get_first_waiter(info, RECV);
+		if (receiver) {
+			pipelined_send(info, msg_ptr, receiver);
+		} else {
+			/* adds message to the queue */
+			msg_insert(msg_ptr, info);
+			__do_notify(info);
+		}
+		inode->i_atime = inode->i_mtime = inode->i_ctime =
+				CURRENT_TIME;
+		spin_unlock(&info->lock);
+		ret = 0;
+	}
+out_fput:
+	fput(filp);
+out:
+	return ret;
+}
+
+asmlinkage ssize_t sys_mq_timedreceive(mqd_t mqdes, char __user *u_msg_ptr,
+	size_t msg_len, unsigned int __user *u_msg_prio,
+	const struct timespec __user *u_abs_timeout)
+{
+	long timeout;
+	ssize_t ret;
+	struct msg_msg *msg_ptr;
+	struct file *filp;
+	struct inode *inode;
+	struct mqueue_inode_info *info;
+	struct ext_wait_queue wait;
+
+	timeout = prepare_timeout(u_abs_timeout);
+
+	ret = -EBADF;
+	filp = fget(mqdes);
+	if (unlikely(!filp))
+		goto out;
+
+	inode = filp->f_dentry->d_inode;
+	if (unlikely(filp->f_op != &mqueue_file_operations))
+		goto out_fput;
+	info = MQUEUE_I(inode);
+
+	if (unlikely(!(filp->f_mode & FMODE_READ)))
+		goto out_fput;
+
+	/* checks if buffer is big enough */
+	if (unlikely(msg_len < info->attr.mq_msgsize)) {
+		ret = -EMSGSIZE;
+		goto out_fput;
+	}
+
+	spin_lock(&info->lock);
+	if (info->attr.mq_curmsgs == 0) {
+		if (filp->f_flags & O_NONBLOCK) {
+			spin_unlock(&info->lock);
+			ret = -EAGAIN;
+			msg_ptr = NULL;
+		} else if (unlikely(timeout < 0)) {
+			spin_unlock(&info->lock);
+			ret = timeout;
+			msg_ptr = NULL;
+		} else {
+			wait.task = current;
+			wait.state = STATE_NONE;
+			ret = wq_sleep(info, RECV, timeout, &wait);
+			msg_ptr = wait.msg;
+		}
+	} else {
+		msg_ptr = msg_get(info);
+
+		inode->i_atime = inode->i_mtime = inode->i_ctime =
+				CURRENT_TIME;
+
+		/* There is now free space in queue. */
+		pipelined_receive(info);
+		spin_unlock(&info->lock);
+		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:
+	fput(filp);
+out:
+	return ret;
+}
+
+/*
+ * Notes: the case when user wants us to deregister (with NULL as pointer
+ * or SIGEV_NONE) and he isn't currently owner of notification will be
+ * silently discarded. It isn't explicitly defined in the POSIX.
+ */
+asmlinkage long sys_mq_notify(mqd_t mqdes,
+				const struct sigevent __user *u_notification)
+{
+	int ret;
+	struct file *filp;
+	struct sock *sock;
+	struct inode *inode;
+	struct sigevent notification;
+	struct mqueue_inode_info *info;
+	struct sk_buff *nc;
+
+	nc = NULL;
+	sock = NULL;
+	if (u_notification == NULL) {
+		notification.sigev_notify = SIGEV_NONE;
+	} else {
+		if (copy_from_user(&notification, u_notification,
+					sizeof(struct sigevent)))
+			return -EFAULT;
+
+		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 &&
+			(notification.sigev_signo < 0 ||
+			 notification.sigev_signo > _NSIG)) {
+			return -EINVAL;
+		}
+		if (notification.sigev_notify == SIGEV_THREAD) {
+			/* create the notify skb */
+			nc = alloc_skb(NOTIFY_COOKIE_LEN, GFP_KERNEL);
+			ret = -ENOMEM;
+			if (!nc)
+				goto out;
+			ret = -EFAULT;
+			if (copy_from_user(nc->data,
+					notification.sigev_value.sival_ptr,
+					NOTIFY_COOKIE_LEN)) {
+				goto out;
+			}
+
+			/* TODO: add a header? */
+			skb_put(nc, NOTIFY_COOKIE_LEN);
+			/* and attach it to the socket */
+retry:
+			filp = fget(notification.sigev_signo);
+			ret = -EBADF;
+			if (!filp)
+				goto out;
+			sock = netlink_getsockbyfilp(filp);
+			fput(filp);
+			if (IS_ERR(sock)) {
+				ret = PTR_ERR(sock);
+				sock = NULL;
+				goto out;
+			}
+
+			ret = netlink_attachskb(sock, nc, 0, MAX_SCHEDULE_TIMEOUT);
+			if (ret == 1)
+		       		goto retry;
+			if (ret) {
+				sock = NULL;
+				nc = NULL;
+				goto out;
+			}
+		}
+	}
+
+	ret = -EBADF;
+	filp = fget(mqdes);
+	if (!filp)
+		goto out;
+
+	inode = filp->f_dentry->d_inode;
+	if (unlikely(filp->f_op != &mqueue_file_operations))
+		goto out_fput;
+	info = MQUEUE_I(inode);
+
+	ret = 0;
+	spin_lock(&info->lock);
+	switch (notification.sigev_notify) {
+	case SIGEV_NONE:
+		if (info->notify.sigev_notify != SIGEV_NONE &&
+				info->notify_owner == current->tgid) {
+			remove_notification(info);
+			inode->i_atime = inode->i_ctime = CURRENT_TIME;
+		}
+		break;
+	case SIGEV_THREAD:
+		if (info->notify.sigev_notify != SIGEV_NONE) {
+			ret = -EBUSY;
+			break;
+		}
+		info->notify_sock = sock;
+		info->notify_cookie = nc;
+		sock = NULL;
+		nc = NULL;
+		info->notify.sigev_notify = SIGEV_THREAD;
+		info->notify_owner = current->tgid;
+		inode->i_atime = inode->i_ctime = CURRENT_TIME;
+		break;
+	case SIGEV_SIGNAL:
+		if (info->notify.sigev_notify != SIGEV_NONE) {
+			ret = -EBUSY;
+			break;
+		}
+		info->notify.sigev_signo = notification.sigev_signo;
+		info->notify.sigev_value = notification.sigev_value;
+		info->notify.sigev_notify = SIGEV_SIGNAL;
+		info->notify_owner = current->tgid;
+		inode->i_atime = inode->i_ctime = CURRENT_TIME;
+	}
+	spin_unlock(&info->lock);
+out_fput:
+	fput(filp);
+out:
+	if (sock) {
+		netlink_detachskb(sock, nc);
+	} else if (nc) {
+		dev_kfree_skb(nc);
+	}
+	return ret;
+}
+
+asmlinkage long sys_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 file *filp;
+	struct inode *inode;
+	struct mqueue_inode_info *info;
+
+	if (u_mqstat != NULL) {
+		if (copy_from_user(&mqstat, u_mqstat, sizeof(struct mq_attr)))
+			return -EFAULT;
+		if (mqstat.mq_flags & (~O_NONBLOCK))
+			return -EINVAL;
+	}
+
+	ret = -EBADF;
+	filp = fget(mqdes);
+	if (!filp)
+		goto out;
+
+	inode = filp->f_dentry->d_inode;
+	if (unlikely(filp->f_op != &mqueue_file_operations))
+		goto out_fput;
+	info = MQUEUE_I(inode);
+
+	spin_lock(&info->lock);
+
+	omqstat = info->attr;
+	omqstat.mq_flags = filp->f_flags & O_NONBLOCK;
+	if (u_mqstat) {
+		if (mqstat.mq_flags & O_NONBLOCK)
+			filp->f_flags |= O_NONBLOCK;
+		else
+			filp->f_flags &= ~O_NONBLOCK;
+
+		inode->i_atime = inode->i_ctime = CURRENT_TIME;
+	}
+
+	spin_unlock(&info->lock);
+
+	ret = 0;
+	if (u_omqstat != NULL && copy_to_user(u_omqstat, &omqstat,
+						sizeof(struct mq_attr)))
+		ret = -EFAULT;
+
+out_fput:
+	fput(filp);
+out:
+	return ret;
+}
+
+static struct inode_operations mqueue_dir_inode_operations = {
+	.lookup = simple_lookup,
+	.create = mqueue_create,
+	.unlink = mqueue_unlink,
+};
+
+static struct file_operations mqueue_file_operations = {
+	.flush = mqueue_flush_file,
+	.poll = mqueue_poll_file,
+	.read = mqueue_read_file,
+};
+
+static struct super_operations mqueue_super_ops = {
+	.alloc_inode = mqueue_alloc_inode,
+	.destroy_inode = mqueue_destroy_inode,
+	.statfs = simple_statfs,
+	.delete_inode = mqueue_delete_inode,
+	.drop_inode = generic_delete_inode,
+};
+
+static struct file_system_type mqueue_fs_type = {
+	.name = "mqueue",
+	.get_sb = mqueue_get_sb,
+	.kill_sb = kill_litter_super,
+};
+
+static int msg_max_limit_min = DFLT_MSGMAX;
+static int msg_max_limit_max = HARD_MSGMAX;
+
+static int msg_maxsize_limit_min = DFLT_MSGSIZEMAX;
+static int msg_maxsize_limit_max = INT_MAX;
+
+static ctl_table mq_sysctls[] = {
+	{
+		.ctl_name	= CTL_QUEUESMAX,
+		.procname	= "queues_max",
+		.data		= &queues_max,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec,
+	},
+	{
+		.ctl_name	= CTL_MSGMAX,
+		.procname	= "msg_max",
+		.data		= &msg_max,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec_minmax,
+		.extra1		= &msg_max_limit_min,
+		.extra2		= &msg_max_limit_max,
+	},
+	{
+		.ctl_name	= CTL_MSGSIZEMAX,
+		.procname	= "msgsize_max",
+		.data		= &msgsize_max,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec_minmax,
+		.extra1		= &msg_maxsize_limit_min,
+		.extra2		= &msg_maxsize_limit_max,
+	},
+	{ .ctl_name = 0 }
+};
+
+static ctl_table mq_sysctl_dir[] = {
+	{
+		.ctl_name	= FS_MQUEUE,
+		.procname	= "mqueue",
+		.mode		= 0555,
+		.child		= mq_sysctls,
+	},
+	{ .ctl_name = 0 }
+};
+
+static ctl_table mq_sysctl_root[] = {
+	{
+		.ctl_name	= CTL_FS,
+		.procname	= "fs",
+		.mode		= 0555,
+		.child		= mq_sysctl_dir,
+	},
+	{ .ctl_name = 0 }
+};
+
+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, init_once, NULL);
+	if (mqueue_inode_cachep == NULL)
+		return -ENOMEM;
+
+	mq_sysctl_table = register_sysctl_table(mq_sysctl_root, 0);
+	if (!mq_sysctl_table) {
+		error = -ENOMEM;
+		goto out_cache;
+	}
+
+	error = register_filesystem(&mqueue_fs_type);
+	if (error)
+		goto out_sysctl;
+
+	if (IS_ERR(mqueue_mnt = kern_mount(&mqueue_fs_type))) {
+		error = PTR_ERR(mqueue_mnt);
+		goto out_filesystem;
+	}
+
+	/* internal initialization - not common for vfs */
+	queues_count = 0;
+	spin_lock_init(&mq_lock);
+
+	return 0;
+
+out_filesystem:
+	unregister_filesystem(&mqueue_fs_type);
+out_sysctl:
+	unregister_sysctl_table(mq_sysctl_table);
+out_cache:
+	if (kmem_cache_destroy(mqueue_inode_cachep)) {
+		printk(KERN_INFO
+			"mqueue_inode_cache: not all structures were freed\n");
+	}
+	return error;
+}
+
+__initcall(init_mqueue_fs);
diff --git a/ipc/msg.c b/ipc/msg.c
index 709ff71bf5c1..37e2d3bb17cb 100644
--- a/ipc/msg.c
+++ b/ipc/msg.c
@@ -51,11 +51,6 @@ struct msg_sender {
 	struct task_struct* tsk;
 };
 
-struct msg_msgseg {
-	struct msg_msgseg* next;
-	/* the next part of the message follows immediately */
-};
-
 #define SEARCH_ANY		1
 #define SEARCH_EQUAL		2
 #define SEARCH_NOTEQUAL		3
@@ -129,106 +124,6 @@ static int newque (key_t key, int msgflg)
 	return msg_buildid(id,msq->q_perm.seq);
 }
 
-static void free_msg(struct msg_msg* msg)
-{
-	struct msg_msgseg* seg;
-
-	security_msg_msg_free(msg);
-
-	seg = msg->next;
-	kfree(msg);
-	while(seg != NULL) {
-		struct msg_msgseg* tmp = seg->next;
-		kfree(seg);
-		seg = tmp;
-	}
-}
-
-static struct msg_msg* load_msg(void* src, int len)
-{
-	struct msg_msg* msg;
-	struct msg_msgseg** pseg;
-	int err;
-	int alen;
-
-	alen = len;
-	if(alen > DATALEN_MSG)
-		alen = DATALEN_MSG;
-
-	msg = (struct msg_msg *) kmalloc (sizeof(*msg) + alen, GFP_KERNEL);
-	if(msg==NULL)
-		return ERR_PTR(-ENOMEM);
-
-	msg->next = NULL;
-	msg->security = NULL;
-
-	if (copy_from_user(msg+1, src, alen)) {
-		err = -EFAULT;
-		goto out_err;
-	}
-
-	len -= alen;
-	src = ((char*)src)+alen;
-	pseg = &msg->next;
-	while(len > 0) {
-		struct msg_msgseg* seg;
-		alen = len;
-		if(alen > DATALEN_SEG)
-			alen = DATALEN_SEG;
-		seg = (struct msg_msgseg *) kmalloc (sizeof(*seg) + alen, GFP_KERNEL);
-		if(seg==NULL) {
-			err=-ENOMEM;
-			goto out_err;
-		}
-		*pseg = seg;
-		seg->next = NULL;
-		if(copy_from_user (seg+1, src, alen)) {
-			err = -EFAULT;
-			goto out_err;
-		}
-		pseg = &seg->next;
-		len -= alen;
-		src = ((char*)src)+alen;
-	}
-	
-	err = security_msg_msg_alloc(msg);
-	if (err)
-		goto out_err;
-
-	return msg;
-
-out_err:
-	free_msg(msg);
-	return ERR_PTR(err);
-}
-
-static int store_msg(void* dest, struct msg_msg* msg, int len)
-{
-	int alen;
-	struct msg_msgseg *seg;
-
-	alen = len;
-	if(alen > DATALEN_MSG)
-		alen = DATALEN_MSG;
-	if(copy_to_user (dest, msg+1, alen))
-		return -1;
-
-	len -= alen;
-	dest = ((char*)dest)+alen;
-	seg = msg->next;
-	while(len > 0) {
-		alen = len;
-		if(alen > DATALEN_SEG)
-			alen = DATALEN_SEG;
-		if(copy_to_user (dest, seg+1, alen))
-			return -1;
-		len -= alen;
-		dest = ((char*)dest)+alen;
-		seg=seg->next;
-	}
-	return 0;
-}
-
 static inline void ss_add(struct msg_queue* msq, struct msg_sender* mss)
 {
 	mss->tsk=current;
diff --git a/ipc/msgutil.c b/ipc/msgutil.c
new file mode 100644
index 000000000000..e48d777de2a3
--- /dev/null
+++ b/ipc/msgutil.c
@@ -0,0 +1,127 @@
+/*
+ * linux/ipc/util.c
+ * Copyright (C) 1999, 2004 Manfred Spraul
+ *
+ * This file is released under GNU General Public Licence version 2 or
+ * (at your option) any later version.
+ *
+ * See the file COPYING for more details.
+ */
+
+#include <linux/spinlock.h>
+#include <linux/init.h>
+#include <linux/security.h>
+#include <linux/slab.h>
+#include <linux/ipc.h>
+#include <asm/uaccess.h>
+
+#include "util.h"
+
+struct msg_msgseg {
+	struct msg_msgseg* next;
+	/* the next part of the message follows immediately */
+};
+
+#define DATALEN_MSG	(PAGE_SIZE-sizeof(struct msg_msg))
+#define DATALEN_SEG	(PAGE_SIZE-sizeof(struct msg_msgseg))
+
+struct msg_msg *load_msg(void __user *src, int len)
+{
+	struct msg_msg *msg;
+	struct msg_msgseg **pseg;
+	int err;
+	int alen;
+
+	alen = len;
+	if (alen > DATALEN_MSG)
+		alen = DATALEN_MSG;
+
+	msg = (struct msg_msg *)kmalloc(sizeof(*msg) + alen, GFP_KERNEL);
+	if (msg == NULL)
+		return ERR_PTR(-ENOMEM);
+
+	msg->next = NULL;
+	msg->security = NULL;
+
+	if (copy_from_user(msg + 1, src, alen)) {
+		err = -EFAULT;
+		goto out_err;
+	}
+
+	len -= alen;
+	src = ((char *)src) + alen;
+	pseg = &msg->next;
+	while (len > 0) {
+		struct msg_msgseg *seg;
+		alen = len;
+		if (alen > DATALEN_SEG)
+			alen = DATALEN_SEG;
+		seg = (struct msg_msgseg *)kmalloc(sizeof(*seg) + alen,
+						 GFP_KERNEL);
+		if (seg == NULL) {
+			err = -ENOMEM;
+			goto out_err;
+		}
+		*pseg = seg;
+		seg->next = NULL;
+		if (copy_from_user(seg + 1, src, alen)) {
+			err = -EFAULT;
+			goto out_err;
+		}
+		pseg = &seg->next;
+		len -= alen;
+		src = ((char *)src) + alen;
+	}
+
+	err = security_msg_msg_alloc(msg);
+	if (err)
+		goto out_err;
+
+	return msg;
+
+out_err:
+	free_msg(msg);
+	return ERR_PTR(err);
+}
+
+int store_msg(void __user *dest, struct msg_msg *msg, int len)
+{
+	int alen;
+	struct msg_msgseg *seg;
+
+	alen = len;
+	if (alen > DATALEN_MSG)
+		alen = DATALEN_MSG;
+	if (copy_to_user(dest, msg + 1, alen))
+		return -1;
+
+	len -= alen;
+	dest = ((char *)dest) + alen;
+	seg = msg->next;
+	while (len > 0) {
+		alen = len;
+		if (alen > DATALEN_SEG)
+			alen = DATALEN_SEG;
+		if (copy_to_user(dest, seg + 1, alen))
+			return -1;
+		len -= alen;
+		dest = ((char *)dest) + alen;
+		seg = seg->next;
+	}
+	return 0;
+}
+
+void free_msg(struct msg_msg *msg)
+{
+	struct msg_msgseg *seg;
+
+	security_msg_msg_free(msg);
+
+	seg = msg->next;
+	kfree(msg);
+	while (seg != NULL) {
+		struct msg_msgseg *tmp = seg->next;
+		kfree(seg);
+		seg = tmp;
+	}
+}
diff --git a/ipc/shm.c b/ipc/shm.c
index 4897cfe16f27..714933b144fa 100644
--- a/ipc/shm.c
+++ b/ipc/shm.c
@@ -380,9 +380,7 @@ static void shm_get_stat(unsigned long *rss, unsigned long *swp)
 
 		if (is_file_hugepages(shp->shm_file)) {
 			struct address_space *mapping = inode->i_mapping;
-			spin_lock(&mapping->page_lock);
 			*rss += (HPAGE_SIZE/PAGE_SIZE)*mapping->nrpages;
-			spin_unlock(&mapping->page_lock);
 		} else {
 			struct shmem_inode_info *info = SHMEM_I(inode);
 			spin_lock(&info->lock);
diff --git a/ipc/util.c b/ipc/util.c
index 6d94883edae0..f74c5eef57d0 100644
--- a/ipc/util.c
+++ b/ipc/util.c
@@ -25,8 +25,6 @@
 #include <linux/rcupdate.h>
 #include <linux/workqueue.h>
 
-#if defined(CONFIG_SYSVIPC)
-
 #include "util.h"
 
 /**
@@ -531,20 +529,3 @@ int ipc_parse_version (int *cmd)
 }
 
 #endif /* __ia64__ */
-
-#else
-/*
- * Dummy functions when SYSV IPC isn't configured
- */
-
-int copy_semundo(unsigned long clone_flags, struct task_struct *tsk)
-{
-	return 0;
-}
-
-void exit_sem(struct task_struct *tsk)
-{
-	return;
-}
-
-#endif /* CONFIG_SYSVIPC */
diff --git a/ipc/util.h b/ipc/util.h
index 79c8fc901317..e6434942c097 100644
--- a/ipc/util.h
+++ b/ipc/util.h
@@ -4,6 +4,10 @@
  *
  * ipc helper functions (c) 1999 Manfred Spraul <manfreds@colorfullife.com>
  */
+
+#ifndef _IPC_UTIL_H
+#define _IPC_UTIL_H
+
 #define USHRT_MAX 0xffff
 #define SEQ_MULTIPLIER	(IPCMNI)
 
@@ -62,3 +66,9 @@ void ipc64_perm_to_ipc_perm(struct ipc64_perm *in, struct ipc_perm *out);
 #else
 int ipc_parse_version (int *cmd);
 #endif
+
+extern void free_msg(struct msg_msg *msg);
+extern struct msg_msg *load_msg(void __user *src, int len);
+extern int store_msg(void __user *dest, struct msg_msg *msg, int len);
+
+#endif