Add the rt linux 4.1.3-rt3 as base

Import the rt linux 4.1.3-rt3 as OPNFV kvm base.

It's from git://git.kernel.org/pub/scm/linux/kernel/git/rt/linux-rt-devel.git linux-4.1.y-rt and
the base is:

commit 0917f823c59692d751951bf5ea699a2d1e2f26a2
Author: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date:   Sat Jul 25 12:13:34 2015 +0200

    Prepare v4.1.3-rt3

    Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>

We lose all the git history this way and it's not good. We
should apply another opnfv project repo in future.

Change-Id: I87543d81c9df70d99c5001fbdf646b202c19f423
Signed-off-by: Yunhong Jiang <yunhong.jiang@intel.com>

14 files changed, 8904 insertions, 0 deletions

diff --git a/kernel/ipc/Makefile b/kernel/ipc/Makefile
new file mode 100644
index 000000000..86c7300ec
--- /dev/null
+++ b/kernel/ipc/Makefile
@@ -0,0 +1,12 @@
+#
+# Makefile for the linux ipc.
+#
+
+obj-$(CONFIG_SYSVIPC_COMPAT) += compat.o
+obj-$(CONFIG_SYSVIPC) += util.o msgutil.o msg.o sem.o shm.o syscall.o
+obj-$(CONFIG_SYSVIPC_SYSCTL) += ipc_sysctl.o
+obj_mq-$(CONFIG_COMPAT) += compat_mq.o
+obj-$(CONFIG_POSIX_MQUEUE) += mqueue.o msgutil.o $(obj_mq-y)
+obj-$(CONFIG_IPC_NS) += namespace.o
+obj-$(CONFIG_POSIX_MQUEUE_SYSCTL) += mq_sysctl.o
+
diff --git a/kernel/ipc/compat.c b/kernel/ipc/compat.c
new file mode 100644
index 000000000..9b3c85f8a
--- /dev/null
+++ b/kernel/ipc/compat.c
@@ -0,0 +1,757 @@
+/*
+ * 32 bit compatibility code for System V IPC
+ *
+ * Copyright (C) 1997,1998	Jakub Jelinek (jj@sunsite.mff.cuni.cz)
+ * Copyright (C) 1997		David S. Miller (davem@caip.rutgers.edu)
+ * Copyright (C) 1999		Arun Sharma <arun.sharma@intel.com>
+ * Copyright (C) 2000		VA Linux Co
+ * Copyright (C) 2000		Don Dugger <n0ano@valinux.com>
+ * Copyright (C) 2000           Hewlett-Packard Co.
+ * Copyright (C) 2000           David Mosberger-Tang <davidm@hpl.hp.com>
+ * Copyright (C) 2000           Gerhard Tonn (ton@de.ibm.com)
+ * Copyright (C) 2000-2002      Andi Kleen, SuSE Labs (x86-64 port)
+ * Copyright (C) 2000		Silicon Graphics, Inc.
+ * Copyright (C) 2001		IBM
+ * Copyright (C) 2004		IBM Deutschland Entwicklung GmbH, IBM Corporation
+ * Copyright (C) 2004		Arnd Bergmann (arnd@arndb.de)
+ *
+ * This code is collected from the versions for sparc64, mips64, s390x, ia64,
+ * ppc64 and x86_64, all of which are based on the original sparc64 version
+ * by Jakub Jelinek.
+ *
+ */
+#include <linux/compat.h>
+#include <linux/errno.h>
+#include <linux/highuid.h>
+#include <linux/init.h>
+#include <linux/msg.h>
+#include <linux/shm.h>
+#include <linux/syscalls.h>
+#include <linux/ptrace.h>
+
+#include <linux/mutex.h>
+#include <linux/uaccess.h>
+
+#include "util.h"
+
+struct compat_msgbuf {
+	compat_long_t mtype;
+	char mtext[1];
+};
+
+struct compat_ipc_perm {
+	key_t key;
+	__compat_uid_t uid;
+	__compat_gid_t gid;
+	__compat_uid_t cuid;
+	__compat_gid_t cgid;
+	compat_mode_t mode;
+	unsigned short seq;
+};
+
+struct compat_semid_ds {
+	struct compat_ipc_perm sem_perm;
+	compat_time_t sem_otime;
+	compat_time_t sem_ctime;
+	compat_uptr_t sem_base;
+	compat_uptr_t sem_pending;
+	compat_uptr_t sem_pending_last;
+	compat_uptr_t undo;
+	unsigned short sem_nsems;
+};
+
+struct compat_msqid_ds {
+	struct compat_ipc_perm msg_perm;
+	compat_uptr_t msg_first;
+	compat_uptr_t msg_last;
+	compat_time_t msg_stime;
+	compat_time_t msg_rtime;
+	compat_time_t msg_ctime;
+	compat_ulong_t msg_lcbytes;
+	compat_ulong_t msg_lqbytes;
+	unsigned short msg_cbytes;
+	unsigned short msg_qnum;
+	unsigned short msg_qbytes;
+	compat_ipc_pid_t msg_lspid;
+	compat_ipc_pid_t msg_lrpid;
+};
+
+struct compat_shmid_ds {
+	struct compat_ipc_perm shm_perm;
+	int shm_segsz;
+	compat_time_t shm_atime;
+	compat_time_t shm_dtime;
+	compat_time_t shm_ctime;
+	compat_ipc_pid_t shm_cpid;
+	compat_ipc_pid_t shm_lpid;
+	unsigned short shm_nattch;
+	unsigned short shm_unused;
+	compat_uptr_t shm_unused2;
+	compat_uptr_t shm_unused3;
+};
+
+struct compat_ipc_kludge {
+	compat_uptr_t msgp;
+	compat_long_t msgtyp;
+};
+
+struct compat_shminfo64 {
+	compat_ulong_t shmmax;
+	compat_ulong_t shmmin;
+	compat_ulong_t shmmni;
+	compat_ulong_t shmseg;
+	compat_ulong_t shmall;
+	compat_ulong_t __unused1;
+	compat_ulong_t __unused2;
+	compat_ulong_t __unused3;
+	compat_ulong_t __unused4;
+};
+
+struct compat_shm_info {
+	compat_int_t used_ids;
+	compat_ulong_t shm_tot, shm_rss, shm_swp;
+	compat_ulong_t swap_attempts, swap_successes;
+};
+
+static inline int compat_ipc_parse_version(int *cmd)
+{
+#ifdef	CONFIG_ARCH_WANT_COMPAT_IPC_PARSE_VERSION
+	int version = *cmd & IPC_64;
+
+	/* this is tricky: architectures that have support for the old
+	 * ipc structures in 64 bit binaries need to have IPC_64 set
+	 * in cmd, the others need to have it cleared */
+#ifndef ipc_parse_version
+	*cmd |= IPC_64;
+#else
+	*cmd &= ~IPC_64;
+#endif
+	return version;
+#else
+	/* With the asm-generic APIs, we always use the 64-bit versions. */
+	return IPC_64;
+#endif
+}
+
+static inline int __get_compat_ipc64_perm(struct ipc64_perm *p64,
+					  struct compat_ipc64_perm __user *up64)
+{
+	int err;
+
+	err  = __get_user(p64->uid, &up64->uid);
+	err |= __get_user(p64->gid, &up64->gid);
+	err |= __get_user(p64->mode, &up64->mode);
+	return err;
+}
+
+static inline int __get_compat_ipc_perm(struct ipc64_perm *p,
+					struct compat_ipc_perm __user *up)
+{
+	int err;
+
+	err  = __get_user(p->uid, &up->uid);
+	err |= __get_user(p->gid, &up->gid);
+	err |= __get_user(p->mode, &up->mode);
+	return err;
+}
+
+static inline int __put_compat_ipc64_perm(struct ipc64_perm *p64,
+					  struct compat_ipc64_perm __user *up64)
+{
+	int err;
+
+	err  = __put_user(p64->key, &up64->key);
+	err |= __put_user(p64->uid, &up64->uid);
+	err |= __put_user(p64->gid, &up64->gid);
+	err |= __put_user(p64->cuid, &up64->cuid);
+	err |= __put_user(p64->cgid, &up64->cgid);
+	err |= __put_user(p64->mode, &up64->mode);
+	err |= __put_user(p64->seq, &up64->seq);
+	return err;
+}
+
+static inline int __put_compat_ipc_perm(struct ipc64_perm *p,
+					struct compat_ipc_perm __user *uip)
+{
+	int err;
+	__compat_uid_t u;
+	__compat_gid_t g;
+
+	err  = __put_user(p->key, &uip->key);
+	SET_UID(u, p->uid);
+	err |= __put_user(u, &uip->uid);
+	SET_GID(g, p->gid);
+	err |= __put_user(g, &uip->gid);
+	SET_UID(u, p->cuid);
+	err |= __put_user(u, &uip->cuid);
+	SET_GID(g, p->cgid);
+	err |= __put_user(g, &uip->cgid);
+	err |= __put_user(p->mode, &uip->mode);
+	err |= __put_user(p->seq, &uip->seq);
+	return err;
+}
+
+static inline int get_compat_semid64_ds(struct semid64_ds *sem64,
+					struct compat_semid64_ds __user *up64)
+{
+	if (!access_ok(VERIFY_READ, up64, sizeof(*up64)))
+		return -EFAULT;
+	return __get_compat_ipc64_perm(&sem64->sem_perm, &up64->sem_perm);
+}
+
+static inline int get_compat_semid_ds(struct semid64_ds *s,
+				      struct compat_semid_ds __user *up)
+{
+	if (!access_ok(VERIFY_READ, up, sizeof(*up)))
+		return -EFAULT;
+	return __get_compat_ipc_perm(&s->sem_perm, &up->sem_perm);
+}
+
+static inline int put_compat_semid64_ds(struct semid64_ds *sem64,
+					struct compat_semid64_ds __user *up64)
+{
+	int err;
+
+	if (!access_ok(VERIFY_WRITE, up64, sizeof(*up64)))
+		return -EFAULT;
+	err  = __put_compat_ipc64_perm(&sem64->sem_perm, &up64->sem_perm);
+	err |= __put_user(sem64->sem_otime, &up64->sem_otime);
+	err |= __put_user(sem64->sem_ctime, &up64->sem_ctime);
+	err |= __put_user(sem64->sem_nsems, &up64->sem_nsems);
+	return err;
+}
+
+static inline int put_compat_semid_ds(struct semid64_ds *s,
+				      struct compat_semid_ds __user *up)
+{
+	int err;
+
+	if (!access_ok(VERIFY_WRITE, up, sizeof(*up)))
+		return -EFAULT;
+	err  = __put_compat_ipc_perm(&s->sem_perm, &up->sem_perm);
+	err |= __put_user(s->sem_otime, &up->sem_otime);
+	err |= __put_user(s->sem_ctime, &up->sem_ctime);
+	err |= __put_user(s->sem_nsems, &up->sem_nsems);
+	return err;
+}
+
+static long do_compat_semctl(int first, int second, int third, u32 pad)
+{
+	unsigned long fourth;
+	int err, err2;
+	struct semid64_ds sem64;
+	struct semid64_ds __user *up64;
+	int version = compat_ipc_parse_version(&third);
+
+	memset(&sem64, 0, sizeof(sem64));
+
+	if ((third & (~IPC_64)) == SETVAL)
+#ifdef __BIG_ENDIAN
+		fourth = (unsigned long)pad << 32;
+#else
+		fourth = pad;
+#endif
+	else
+		fourth = (unsigned long)compat_ptr(pad);
+	switch (third & (~IPC_64)) {
+	case IPC_INFO:
+	case IPC_RMID:
+	case SEM_INFO:
+	case GETVAL:
+	case GETPID:
+	case GETNCNT:
+	case GETZCNT:
+	case GETALL:
+	case SETVAL:
+	case SETALL:
+		err = sys_semctl(first, second, third, fourth);
+		break;
+
+	case IPC_STAT:
+	case SEM_STAT:
+		up64 = compat_alloc_user_space(sizeof(sem64));
+		fourth = (unsigned long)up64;
+		err = sys_semctl(first, second, third, fourth);
+		if (err < 0)
+			break;
+		if (copy_from_user(&sem64, up64, sizeof(sem64)))
+			err2 = -EFAULT;
+		else if (version == IPC_64)
+			err2 = put_compat_semid64_ds(&sem64, compat_ptr(pad));
+		else
+			err2 = put_compat_semid_ds(&sem64, compat_ptr(pad));
+		if (err2)
+			err = -EFAULT;
+		break;
+
+	case IPC_SET:
+		if (version == IPC_64)
+			err = get_compat_semid64_ds(&sem64, compat_ptr(pad));
+		else
+			err = get_compat_semid_ds(&sem64, compat_ptr(pad));
+
+		up64 = compat_alloc_user_space(sizeof(sem64));
+		if (copy_to_user(up64, &sem64, sizeof(sem64)))
+			err = -EFAULT;
+		if (err)
+			break;
+
+		fourth = (unsigned long)up64;
+		err = sys_semctl(first, second, third, fourth);
+		break;
+
+	default:
+		err = -EINVAL;
+		break;
+	}
+	return err;
+}
+
+static long compat_do_msg_fill(void __user *dest, struct msg_msg *msg, size_t bufsz)
+{
+	struct compat_msgbuf __user *msgp = dest;
+	size_t msgsz;
+
+	if (put_user(msg->m_type, &msgp->mtype))
+		return -EFAULT;
+
+	msgsz = (bufsz > msg->m_ts) ? msg->m_ts : bufsz;
+	if (store_msg(msgp->mtext, msg, msgsz))
+		return -EFAULT;
+	return msgsz;
+}
+
+#ifndef COMPAT_SHMLBA
+#define COMPAT_SHMLBA	SHMLBA
+#endif
+
+#ifdef CONFIG_ARCH_WANT_OLD_COMPAT_IPC
+COMPAT_SYSCALL_DEFINE6(ipc, u32, call, int, first, int, second,
+	u32, third, compat_uptr_t, ptr, u32, fifth)
+{
+	int version;
+	u32 pad;
+
+	version = call >> 16; /* hack for backward compatibility */
+	call &= 0xffff;
+
+	switch (call) {
+	case SEMOP:
+		/* struct sembuf is the same on 32 and 64bit :)) */
+		return sys_semtimedop(first, compat_ptr(ptr), second, NULL);
+	case SEMTIMEDOP:
+		return compat_sys_semtimedop(first, compat_ptr(ptr), second,
+						compat_ptr(fifth));
+	case SEMGET:
+		return sys_semget(first, second, third);
+	case SEMCTL:
+		if (!ptr)
+			return -EINVAL;
+		if (get_user(pad, (u32 __user *) compat_ptr(ptr)))
+			return -EFAULT;
+		return do_compat_semctl(first, second, third, pad);
+
+	case MSGSND: {
+		struct compat_msgbuf __user *up = compat_ptr(ptr);
+		compat_long_t type;
+
+		if (first < 0 || second < 0)
+			return -EINVAL;
+
+		if (get_user(type, &up->mtype))
+			return -EFAULT;
+
+		return do_msgsnd(first, type, up->mtext, second, third);
+	}
+	case MSGRCV: {
+		void __user *uptr = compat_ptr(ptr);
+
+		if (first < 0 || second < 0)
+			return -EINVAL;
+
+		if (!version) {
+			struct compat_ipc_kludge ipck;
+			if (!uptr)
+				return -EINVAL;
+			if (copy_from_user(&ipck, uptr, sizeof(ipck)))
+				return -EFAULT;
+			uptr = compat_ptr(ipck.msgp);
+			fifth = ipck.msgtyp;
+		}
+		return do_msgrcv(first, uptr, second, (s32)fifth, third,
+				 compat_do_msg_fill);
+	}
+	case MSGGET:
+		return sys_msgget(first, second);
+	case MSGCTL:
+		return compat_sys_msgctl(first, second, compat_ptr(ptr));
+
+	case SHMAT: {
+		int err;
+		unsigned long raddr;
+
+		if (version == 1)
+			return -EINVAL;
+		err = do_shmat(first, compat_ptr(ptr), second, &raddr,
+			       COMPAT_SHMLBA);
+		if (err < 0)
+			return err;
+		return put_user(raddr, (compat_ulong_t *)compat_ptr(third));
+	}
+	case SHMDT:
+		return sys_shmdt(compat_ptr(ptr));
+	case SHMGET:
+		return sys_shmget(first, (unsigned)second, third);
+	case SHMCTL:
+		return compat_sys_shmctl(first, second, compat_ptr(ptr));
+	}
+
+	return -ENOSYS;
+}
+#endif
+
+COMPAT_SYSCALL_DEFINE4(semctl, int, semid, int, semnum, int, cmd, int, arg)
+{
+	return do_compat_semctl(semid, semnum, cmd, arg);
+}
+
+COMPAT_SYSCALL_DEFINE4(msgsnd, int, msqid, compat_uptr_t, msgp,
+		       compat_ssize_t, msgsz, int, msgflg)
+{
+	struct compat_msgbuf __user *up = compat_ptr(msgp);
+	compat_long_t mtype;
+
+	if (get_user(mtype, &up->mtype))
+		return -EFAULT;
+	return do_msgsnd(msqid, mtype, up->mtext, (ssize_t)msgsz, msgflg);
+}
+
+COMPAT_SYSCALL_DEFINE5(msgrcv, int, msqid, compat_uptr_t, msgp,
+		       compat_ssize_t, msgsz, compat_long_t, msgtyp, int, msgflg)
+{
+	return do_msgrcv(msqid, compat_ptr(msgp), (ssize_t)msgsz, (long)msgtyp,
+			 msgflg, compat_do_msg_fill);
+}
+
+static inline int get_compat_msqid64(struct msqid64_ds *m64,
+				     struct compat_msqid64_ds __user *up64)
+{
+	int err;
+
+	if (!access_ok(VERIFY_READ, up64, sizeof(*up64)))
+		return -EFAULT;
+	err  = __get_compat_ipc64_perm(&m64->msg_perm, &up64->msg_perm);
+	err |= __get_user(m64->msg_qbytes, &up64->msg_qbytes);
+	return err;
+}
+
+static inline int get_compat_msqid(struct msqid64_ds *m,
+				   struct compat_msqid_ds __user *up)
+{
+	int err;
+
+	if (!access_ok(VERIFY_READ, up, sizeof(*up)))
+		return -EFAULT;
+	err  = __get_compat_ipc_perm(&m->msg_perm, &up->msg_perm);
+	err |= __get_user(m->msg_qbytes, &up->msg_qbytes);
+	return err;
+}
+
+static inline int put_compat_msqid64_ds(struct msqid64_ds *m64,
+				 struct compat_msqid64_ds __user *up64)
+{
+	int err;
+
+	if (!access_ok(VERIFY_WRITE, up64, sizeof(*up64)))
+		return -EFAULT;
+	err  = __put_compat_ipc64_perm(&m64->msg_perm, &up64->msg_perm);
+	err |= __put_user(m64->msg_stime, &up64->msg_stime);
+	err |= __put_user(m64->msg_rtime, &up64->msg_rtime);
+	err |= __put_user(m64->msg_ctime, &up64->msg_ctime);
+	err |= __put_user(m64->msg_cbytes, &up64->msg_cbytes);
+	err |= __put_user(m64->msg_qnum, &up64->msg_qnum);
+	err |= __put_user(m64->msg_qbytes, &up64->msg_qbytes);
+	err |= __put_user(m64->msg_lspid, &up64->msg_lspid);
+	err |= __put_user(m64->msg_lrpid, &up64->msg_lrpid);
+	return err;
+}
+
+static inline int put_compat_msqid_ds(struct msqid64_ds *m,
+				      struct compat_msqid_ds __user *up)
+{
+	int err;
+
+	if (!access_ok(VERIFY_WRITE, up, sizeof(*up)))
+		return -EFAULT;
+	err  = __put_compat_ipc_perm(&m->msg_perm, &up->msg_perm);
+	err |= __put_user(m->msg_stime, &up->msg_stime);
+	err |= __put_user(m->msg_rtime, &up->msg_rtime);
+	err |= __put_user(m->msg_ctime, &up->msg_ctime);
+	err |= __put_user(m->msg_cbytes, &up->msg_cbytes);
+	err |= __put_user(m->msg_qnum, &up->msg_qnum);
+	err |= __put_user(m->msg_qbytes, &up->msg_qbytes);
+	err |= __put_user(m->msg_lspid, &up->msg_lspid);
+	err |= __put_user(m->msg_lrpid, &up->msg_lrpid);
+	return err;
+}
+
+COMPAT_SYSCALL_DEFINE3(msgctl, int, first, int, second, void __user *, uptr)
+{
+	int err, err2;
+	struct msqid64_ds m64;
+	int version = compat_ipc_parse_version(&second);
+	void __user *p;
+
+	memset(&m64, 0, sizeof(m64));
+
+	switch (second & (~IPC_64)) {
+	case IPC_INFO:
+	case IPC_RMID:
+	case MSG_INFO:
+		err = sys_msgctl(first, second, uptr);
+		break;
+
+	case IPC_SET:
+		if (version == IPC_64)
+			err = get_compat_msqid64(&m64, uptr);
+		else
+			err = get_compat_msqid(&m64, uptr);
+
+		if (err)
+			break;
+		p = compat_alloc_user_space(sizeof(m64));
+		if (copy_to_user(p, &m64, sizeof(m64)))
+			err = -EFAULT;
+		else
+			err = sys_msgctl(first, second, p);
+		break;
+
+	case IPC_STAT:
+	case MSG_STAT:
+		p = compat_alloc_user_space(sizeof(m64));
+		err = sys_msgctl(first, second, p);
+		if (err < 0)
+			break;
+		if (copy_from_user(&m64, p, sizeof(m64)))
+			err2 = -EFAULT;
+		else if (version == IPC_64)
+			err2 = put_compat_msqid64_ds(&m64, uptr);
+		else
+			err2 = put_compat_msqid_ds(&m64, uptr);
+		if (err2)
+			err = -EFAULT;
+		break;
+
+	default:
+		err = -EINVAL;
+		break;
+	}
+	return err;
+}
+
+COMPAT_SYSCALL_DEFINE3(shmat, int, shmid, compat_uptr_t, shmaddr, int, shmflg)
+{
+	unsigned long ret;
+	long err;
+
+	err = do_shmat(shmid, compat_ptr(shmaddr), shmflg, &ret, COMPAT_SHMLBA);
+	if (err)
+		return err;
+	force_successful_syscall_return();
+	return (long)ret;
+}
+
+static inline int get_compat_shmid64_ds(struct shmid64_ds *sem64,
+					struct compat_shmid64_ds __user *up64)
+{
+	if (!access_ok(VERIFY_READ, up64, sizeof(*up64)))
+		return -EFAULT;
+	return __get_compat_ipc64_perm(&sem64->shm_perm, &up64->shm_perm);
+}
+
+static inline int get_compat_shmid_ds(struct shmid64_ds *s,
+				      struct compat_shmid_ds __user *up)
+{
+	if (!access_ok(VERIFY_READ, up, sizeof(*up)))
+		return -EFAULT;
+	return __get_compat_ipc_perm(&s->shm_perm, &up->shm_perm);
+}
+
+static inline int put_compat_shmid64_ds(struct shmid64_ds *sem64,
+					struct compat_shmid64_ds __user *up64)
+{
+	int err;
+
+	if (!access_ok(VERIFY_WRITE, up64, sizeof(*up64)))
+		return -EFAULT;
+	err  = __put_compat_ipc64_perm(&sem64->shm_perm, &up64->shm_perm);
+	err |= __put_user(sem64->shm_atime, &up64->shm_atime);
+	err |= __put_user(sem64->shm_dtime, &up64->shm_dtime);
+	err |= __put_user(sem64->shm_ctime, &up64->shm_ctime);
+	err |= __put_user(sem64->shm_segsz, &up64->shm_segsz);
+	err |= __put_user(sem64->shm_nattch, &up64->shm_nattch);
+	err |= __put_user(sem64->shm_cpid, &up64->shm_cpid);
+	err |= __put_user(sem64->shm_lpid, &up64->shm_lpid);
+	return err;
+}
+
+static inline int put_compat_shmid_ds(struct shmid64_ds *s,
+				      struct compat_shmid_ds __user *up)
+{
+	int err;
+
+	if (!access_ok(VERIFY_WRITE, up, sizeof(*up)))
+		return -EFAULT;
+	err  = __put_compat_ipc_perm(&s->shm_perm, &up->shm_perm);
+	err |= __put_user(s->shm_atime, &up->shm_atime);
+	err |= __put_user(s->shm_dtime, &up->shm_dtime);
+	err |= __put_user(s->shm_ctime, &up->shm_ctime);
+	err |= __put_user(s->shm_segsz, &up->shm_segsz);
+	err |= __put_user(s->shm_nattch, &up->shm_nattch);
+	err |= __put_user(s->shm_cpid, &up->shm_cpid);
+	err |= __put_user(s->shm_lpid, &up->shm_lpid);
+	return err;
+}
+
+static inline int put_compat_shminfo64(struct shminfo64 *smi,
+				       struct compat_shminfo64 __user *up64)
+{
+	int err;
+
+	if (!access_ok(VERIFY_WRITE, up64, sizeof(*up64)))
+		return -EFAULT;
+	if (smi->shmmax > INT_MAX)
+		smi->shmmax = INT_MAX;
+	err  = __put_user(smi->shmmax, &up64->shmmax);
+	err |= __put_user(smi->shmmin, &up64->shmmin);
+	err |= __put_user(smi->shmmni, &up64->shmmni);
+	err |= __put_user(smi->shmseg, &up64->shmseg);
+	err |= __put_user(smi->shmall, &up64->shmall);
+	return err;
+}
+
+static inline int put_compat_shminfo(struct shminfo64 *smi,
+				     struct shminfo __user *up)
+{
+	int err;
+
+	if (!access_ok(VERIFY_WRITE, up, sizeof(*up)))
+		return -EFAULT;
+	if (smi->shmmax > INT_MAX)
+		smi->shmmax = INT_MAX;
+	err  = __put_user(smi->shmmax, &up->shmmax);
+	err |= __put_user(smi->shmmin, &up->shmmin);
+	err |= __put_user(smi->shmmni, &up->shmmni);
+	err |= __put_user(smi->shmseg, &up->shmseg);
+	err |= __put_user(smi->shmall, &up->shmall);
+	return err;
+}
+
+static inline int put_compat_shm_info(struct shm_info __user *ip,
+				      struct compat_shm_info __user *uip)
+{
+	int err;
+	struct shm_info si;
+
+	if (!access_ok(VERIFY_WRITE, uip, sizeof(*uip)) ||
+	    copy_from_user(&si, ip, sizeof(si)))
+		return -EFAULT;
+	err  = __put_user(si.used_ids, &uip->used_ids);
+	err |= __put_user(si.shm_tot, &uip->shm_tot);
+	err |= __put_user(si.shm_rss, &uip->shm_rss);
+	err |= __put_user(si.shm_swp, &uip->shm_swp);
+	err |= __put_user(si.swap_attempts, &uip->swap_attempts);
+	err |= __put_user(si.swap_successes, &uip->swap_successes);
+	return err;
+}
+
+COMPAT_SYSCALL_DEFINE3(shmctl, int, first, int, second, void __user *, uptr)
+{
+	void __user *p;
+	struct shmid64_ds sem64;
+	struct shminfo64 smi;
+	int err, err2;
+	int version = compat_ipc_parse_version(&second);
+
+	memset(&sem64, 0, sizeof(sem64));
+
+	switch (second & (~IPC_64)) {
+	case IPC_RMID:
+	case SHM_LOCK:
+	case SHM_UNLOCK:
+		err = sys_shmctl(first, second, uptr);
+		break;
+
+	case IPC_INFO:
+		p = compat_alloc_user_space(sizeof(smi));
+		err = sys_shmctl(first, second, p);
+		if (err < 0)
+			break;
+		if (copy_from_user(&smi, p, sizeof(smi)))
+			err2 = -EFAULT;
+		else if (version == IPC_64)
+			err2 = put_compat_shminfo64(&smi, uptr);
+		else
+			err2 = put_compat_shminfo(&smi, uptr);
+		if (err2)
+			err = -EFAULT;
+		break;
+
+
+	case IPC_SET:
+		if (version == IPC_64)
+			err = get_compat_shmid64_ds(&sem64, uptr);
+		else
+			err = get_compat_shmid_ds(&sem64, uptr);
+
+		if (err)
+			break;
+		p = compat_alloc_user_space(sizeof(sem64));
+		if (copy_to_user(p, &sem64, sizeof(sem64)))
+			err = -EFAULT;
+		else
+			err = sys_shmctl(first, second, p);
+		break;
+
+	case IPC_STAT:
+	case SHM_STAT:
+		p = compat_alloc_user_space(sizeof(sem64));
+		err = sys_shmctl(first, second, p);
+		if (err < 0)
+			break;
+		if (copy_from_user(&sem64, p, sizeof(sem64)))
+			err2 = -EFAULT;
+		else if (version == IPC_64)
+			err2 = put_compat_shmid64_ds(&sem64, uptr);
+		else
+			err2 = put_compat_shmid_ds(&sem64, uptr);
+		if (err2)
+			err = -EFAULT;
+		break;
+
+	case SHM_INFO:
+		p = compat_alloc_user_space(sizeof(struct shm_info));
+		err = sys_shmctl(first, second, p);
+		if (err < 0)
+			break;
+		err2 = put_compat_shm_info(p, uptr);
+		if (err2)
+			err = -EFAULT;
+		break;
+
+	default:
+		err = -EINVAL;
+		break;
+	}
+	return err;
+}
+
+COMPAT_SYSCALL_DEFINE4(semtimedop, int, semid, struct sembuf __user *, tsems,
+		       unsigned, nsops,
+		       const struct compat_timespec __user *, timeout)
+{
+	struct timespec __user *ts64;
+	if (compat_convert_timespec(&ts64, timeout))
+		return -EFAULT;
+	return sys_semtimedop(semid, tsems, nsops, ts64);
+}
diff --git a/kernel/ipc/compat_mq.c b/kernel/ipc/compat_mq.c
new file mode 100644
index 000000000..ef6f91cc4
--- /dev/null
+++ b/kernel/ipc/compat_mq.c
@@ -0,0 +1,138 @@
+/*
+ *  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 <linux/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 (!access_ok(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);
+}
+
+COMPAT_SYSCALL_DEFINE4(mq_open, const char __user *, u_name,
+		       int, oflag, compat_mode_t, mode,
+		       struct compat_mq_attr __user *, u_attr)
+{
+	void __user *p = NULL;
+	if (u_attr && oflag & O_CREAT) {
+		struct mq_attr attr;
+
+		memset(&attr, 0, sizeof(attr));
+
+		p = compat_alloc_user_space(sizeof(attr));
+		if (get_compat_mq_attr(&attr, u_attr) ||
+		    copy_to_user(p, &attr, sizeof(attr)))
+			return -EFAULT;
+	}
+	return sys_mq_open(u_name, oflag, mode, p);
+}
+
+COMPAT_SYSCALL_DEFINE5(mq_timedsend, mqd_t, mqdes,
+		       const char __user *, u_msg_ptr,
+		       compat_size_t, msg_len, unsigned int, msg_prio,
+		       const struct compat_timespec __user *, u_abs_timeout)
+{
+	struct timespec __user *u_ts;
+
+	if (compat_convert_timespec(&u_ts, u_abs_timeout))
+		return -EFAULT;
+
+	return sys_mq_timedsend(mqdes, u_msg_ptr, msg_len,
+			msg_prio, u_ts);
+}
+
+COMPAT_SYSCALL_DEFINE5(mq_timedreceive, mqd_t, mqdes,
+		       char __user *, u_msg_ptr,
+		       compat_size_t, msg_len, unsigned int __user *, u_msg_prio,
+		       const struct compat_timespec __user *, u_abs_timeout)
+{
+	struct timespec __user *u_ts;
+
+	if (compat_convert_timespec(&u_ts, u_abs_timeout))
+		return -EFAULT;
+
+	return sys_mq_timedreceive(mqdes, u_msg_ptr, msg_len,
+			u_msg_prio, u_ts);
+}
+
+COMPAT_SYSCALL_DEFINE2(mq_notify, mqd_t, mqdes,
+		       const struct compat_sigevent __user *, u_notification)
+{
+	struct sigevent __user *p = NULL;
+	if (u_notification) {
+		struct sigevent n;
+		p = compat_alloc_user_space(sizeof(*p));
+		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);
+		if (copy_to_user(p, &n, sizeof(*p)))
+			return -EFAULT;
+	}
+	return sys_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)
+{
+	struct mq_attr mqstat;
+	struct mq_attr __user *p = compat_alloc_user_space(2 * sizeof(*p));
+	long ret;
+
+	memset(&mqstat, 0, sizeof(mqstat));
+
+	if (u_mqstat) {
+		if (get_compat_mq_attr(&mqstat, u_mqstat) ||
+		    copy_to_user(p, &mqstat, sizeof(mqstat)))
+			return -EFAULT;
+	}
+	ret = sys_mq_getsetattr(mqdes,
+				u_mqstat ? p : NULL,
+				u_omqstat ? p + 1 : NULL);
+	if (ret)
+		return ret;
+	if (u_omqstat) {
+		if (copy_from_user(&mqstat, p + 1, sizeof(mqstat)) ||
+		    put_compat_mq_attr(&mqstat, u_omqstat))
+			return -EFAULT;
+	}
+	return 0;
+}
diff --git a/kernel/ipc/ipc_sysctl.c b/kernel/ipc/ipc_sysctl.c
new file mode 100644
index 000000000..8ad93c29f
--- /dev/null
+++ b/kernel/ipc/ipc_sysctl.c
@@ -0,0 +1,224 @@
+/*
+ *  Copyright (C) 2007
+ *
+ *  Author: Eric Biederman <ebiederm@xmision.com>
+ *
+ *  This program is free software; you can redistribute it and/or
+ *  modify it under the terms of the GNU General Public License as
+ *  published by the Free Software Foundation, version 2 of the
+ *  License.
+ */
+
+#include <linux/module.h>
+#include <linux/ipc.h>
+#include <linux/nsproxy.h>
+#include <linux/sysctl.h>
+#include <linux/uaccess.h>
+#include <linux/ipc_namespace.h>
+#include <linux/msg.h>
+#include "util.h"
+
+static void *get_ipc(struct ctl_table *table)
+{
+	char *which = table->data;
+	struct ipc_namespace *ipc_ns = current->nsproxy->ipc_ns;
+	which = (which - (char *)&init_ipc_ns) + (char *)ipc_ns;
+	return which;
+}
+
+#ifdef CONFIG_PROC_SYSCTL
+static int proc_ipc_dointvec(struct ctl_table *table, int write,
+	void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+	struct ctl_table ipc_table;
+
+	memcpy(&ipc_table, table, sizeof(ipc_table));
+	ipc_table.data = get_ipc(table);
+
+	return proc_dointvec(&ipc_table, write, buffer, lenp, ppos);
+}
+
+static int proc_ipc_dointvec_minmax(struct ctl_table *table, int write,
+	void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+	struct ctl_table ipc_table;
+
+	memcpy(&ipc_table, table, sizeof(ipc_table));
+	ipc_table.data = get_ipc(table);
+
+	return proc_dointvec_minmax(&ipc_table, write, buffer, lenp, ppos);
+}
+
+static int proc_ipc_dointvec_minmax_orphans(struct ctl_table *table, int write,
+	void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+	struct ipc_namespace *ns = current->nsproxy->ipc_ns;
+	int err = proc_ipc_dointvec_minmax(table, write, buffer, lenp, ppos);
+
+	if (err < 0)
+		return err;
+	if (ns->shm_rmid_forced)
+		shm_destroy_orphaned(ns);
+	return err;
+}
+
+static int proc_ipc_doulongvec_minmax(struct ctl_table *table, int write,
+	void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+	struct ctl_table ipc_table;
+	memcpy(&ipc_table, table, sizeof(ipc_table));
+	ipc_table.data = get_ipc(table);
+
+	return proc_doulongvec_minmax(&ipc_table, write, buffer,
+					lenp, ppos);
+}
+
+static int proc_ipc_auto_msgmni(struct ctl_table *table, int write,
+	void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+	struct ctl_table ipc_table;
+	int dummy = 0;
+
+	memcpy(&ipc_table, table, sizeof(ipc_table));
+	ipc_table.data = &dummy;
+
+	if (write)
+		pr_info_once("writing to auto_msgmni has no effect");
+
+	return proc_dointvec_minmax(&ipc_table, write, buffer, lenp, ppos);
+}
+
+#else
+#define proc_ipc_doulongvec_minmax NULL
+#define proc_ipc_dointvec	   NULL
+#define proc_ipc_dointvec_minmax   NULL
+#define proc_ipc_dointvec_minmax_orphans   NULL
+#define proc_ipc_auto_msgmni	   NULL
+#endif
+
+static int zero;
+static int one = 1;
+static int int_max = INT_MAX;
+
+static struct ctl_table ipc_kern_table[] = {
+	{
+		.procname	= "shmmax",
+		.data		= &init_ipc_ns.shm_ctlmax,
+		.maxlen		= sizeof(init_ipc_ns.shm_ctlmax),
+		.mode		= 0644,
+		.proc_handler	= proc_ipc_doulongvec_minmax,
+	},
+	{
+		.procname	= "shmall",
+		.data		= &init_ipc_ns.shm_ctlall,
+		.maxlen		= sizeof(init_ipc_ns.shm_ctlall),
+		.mode		= 0644,
+		.proc_handler	= proc_ipc_doulongvec_minmax,
+	},
+	{
+		.procname	= "shmmni",
+		.data		= &init_ipc_ns.shm_ctlmni,
+		.maxlen		= sizeof(init_ipc_ns.shm_ctlmni),
+		.mode		= 0644,
+		.proc_handler	= proc_ipc_dointvec,
+	},
+	{
+		.procname	= "shm_rmid_forced",
+		.data		= &init_ipc_ns.shm_rmid_forced,
+		.maxlen		= sizeof(init_ipc_ns.shm_rmid_forced),
+		.mode		= 0644,
+		.proc_handler	= proc_ipc_dointvec_minmax_orphans,
+		.extra1		= &zero,
+		.extra2		= &one,
+	},
+	{
+		.procname	= "msgmax",
+		.data		= &init_ipc_ns.msg_ctlmax,
+		.maxlen		= sizeof(init_ipc_ns.msg_ctlmax),
+		.mode		= 0644,
+		.proc_handler	= proc_ipc_dointvec_minmax,
+		.extra1		= &zero,
+		.extra2		= &int_max,
+	},
+	{
+		.procname	= "msgmni",
+		.data		= &init_ipc_ns.msg_ctlmni,
+		.maxlen		= sizeof(init_ipc_ns.msg_ctlmni),
+		.mode		= 0644,
+		.proc_handler	= proc_ipc_dointvec_minmax,
+		.extra1		= &zero,
+		.extra2		= &int_max,
+	},
+	{
+		.procname	= "auto_msgmni",
+		.data		= NULL,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_ipc_auto_msgmni,
+		.extra1		= &zero,
+		.extra2		= &one,
+	},
+	{
+		.procname	=  "msgmnb",
+		.data		= &init_ipc_ns.msg_ctlmnb,
+		.maxlen		= sizeof(init_ipc_ns.msg_ctlmnb),
+		.mode		= 0644,
+		.proc_handler	= proc_ipc_dointvec_minmax,
+		.extra1		= &zero,
+		.extra2		= &int_max,
+	},
+	{
+		.procname	= "sem",
+		.data		= &init_ipc_ns.sem_ctls,
+		.maxlen		= 4*sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_ipc_dointvec,
+	},
+#ifdef CONFIG_CHECKPOINT_RESTORE
+	{
+		.procname	= "sem_next_id",
+		.data		= &init_ipc_ns.ids[IPC_SEM_IDS].next_id,
+		.maxlen		= sizeof(init_ipc_ns.ids[IPC_SEM_IDS].next_id),
+		.mode		= 0644,
+		.proc_handler	= proc_ipc_dointvec_minmax,
+		.extra1		= &zero,
+		.extra2		= &int_max,
+	},
+	{
+		.procname	= "msg_next_id",
+		.data		= &init_ipc_ns.ids[IPC_MSG_IDS].next_id,
+		.maxlen		= sizeof(init_ipc_ns.ids[IPC_MSG_IDS].next_id),
+		.mode		= 0644,
+		.proc_handler	= proc_ipc_dointvec_minmax,
+		.extra1		= &zero,
+		.extra2		= &int_max,
+	},
+	{
+		.procname	= "shm_next_id",
+		.data		= &init_ipc_ns.ids[IPC_SHM_IDS].next_id,
+		.maxlen		= sizeof(init_ipc_ns.ids[IPC_SHM_IDS].next_id),
+		.mode		= 0644,
+		.proc_handler	= proc_ipc_dointvec_minmax,
+		.extra1		= &zero,
+		.extra2		= &int_max,
+	},
+#endif
+	{}
+};
+
+static struct ctl_table ipc_root_table[] = {
+	{
+		.procname	= "kernel",
+		.mode		= 0555,
+		.child		= ipc_kern_table,
+	},
+	{}
+};
+
+static int __init ipc_sysctl_init(void)
+{
+	register_sysctl_table(ipc_root_table);
+	return 0;
+}
+
+device_initcall(ipc_sysctl_init);
diff --git a/kernel/ipc/mq_sysctl.c b/kernel/ipc/mq_sysctl.c
new file mode 100644
index 000000000..68d4e9537
--- /dev/null
+++ b/kernel/ipc/mq_sysctl.c
@@ -0,0 +1,124 @@
+/*
+ *  Copyright (C) 2007 IBM Corporation
+ *
+ *  Author: Cedric Le Goater <clg@fr.ibm.com>
+ *
+ *  This program is free software; you can redistribute it and/or
+ *  modify it under the terms of the GNU General Public License as
+ *  published by the Free Software Foundation, version 2 of the
+ *  License.
+ */
+
+#include <linux/nsproxy.h>
+#include <linux/ipc_namespace.h>
+#include <linux/sysctl.h>
+
+#ifdef CONFIG_PROC_SYSCTL
+static void *get_mq(struct ctl_table *table)
+{
+	char *which = table->data;
+	struct ipc_namespace *ipc_ns = current->nsproxy->ipc_ns;
+	which = (which - (char *)&init_ipc_ns) + (char *)ipc_ns;
+	return which;
+}
+
+static int proc_mq_dointvec(struct ctl_table *table, int write,
+			    void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+	struct ctl_table mq_table;
+	memcpy(&mq_table, table, sizeof(mq_table));
+	mq_table.data = get_mq(table);
+
+	return proc_dointvec(&mq_table, write, buffer, lenp, ppos);
+}
+
+static int proc_mq_dointvec_minmax(struct ctl_table *table, int write,
+	void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+	struct ctl_table mq_table;
+	memcpy(&mq_table, table, sizeof(mq_table));
+	mq_table.data = get_mq(table);
+
+	return proc_dointvec_minmax(&mq_table, write, buffer,
+					lenp, ppos);
+}
+#else
+#define proc_mq_dointvec NULL
+#define proc_mq_dointvec_minmax NULL
+#endif
+
+static int msg_max_limit_min = MIN_MSGMAX;
+static int msg_max_limit_max = HARD_MSGMAX;
+
+static int msg_maxsize_limit_min = MIN_MSGSIZEMAX;
+static int msg_maxsize_limit_max = HARD_MSGSIZEMAX;
+
+static struct ctl_table mq_sysctls[] = {
+	{
+		.procname	= "queues_max",
+		.data		= &init_ipc_ns.mq_queues_max,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_mq_dointvec,
+	},
+	{
+		.procname	= "msg_max",
+		.data		= &init_ipc_ns.mq_msg_max,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_mq_dointvec_minmax,
+		.extra1		= &msg_max_limit_min,
+		.extra2		= &msg_max_limit_max,
+	},
+	{
+		.procname	= "msgsize_max",
+		.data		= &init_ipc_ns.mq_msgsize_max,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_mq_dointvec_minmax,
+		.extra1		= &msg_maxsize_limit_min,
+		.extra2		= &msg_maxsize_limit_max,
+	},
+	{
+		.procname	= "msg_default",
+		.data		= &init_ipc_ns.mq_msg_default,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_mq_dointvec_minmax,
+		.extra1		= &msg_max_limit_min,
+		.extra2		= &msg_max_limit_max,
+	},
+	{
+		.procname	= "msgsize_default",
+		.data		= &init_ipc_ns.mq_msgsize_default,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_mq_dointvec_minmax,
+		.extra1		= &msg_maxsize_limit_min,
+		.extra2		= &msg_maxsize_limit_max,
+	},
+	{}
+};
+
+static struct ctl_table mq_sysctl_dir[] = {
+	{
+		.procname	= "mqueue",
+		.mode		= 0555,
+		.child		= mq_sysctls,
+	},
+	{}
+};
+
+static struct ctl_table mq_sysctl_root[] = {
+	{
+		.procname	= "fs",
+		.mode		= 0555,
+		.child		= mq_sysctl_dir,
+	},
+	{}
+};
+
+struct ctl_table_header *mq_register_sysctl_table(void)
+{
+	return register_sysctl_table(mq_sysctl_root);
+}
diff --git a/kernel/ipc/mqueue.c b/kernel/ipc/mqueue.c
new file mode 100644
index 000000000..a24ba9fe5
--- /dev/null
+++ b/kernel/ipc/mqueue.c
@@ -0,0 +1,1474 @@
+/*
+ * POSIX message queues filesystem for Linux.
+ *
+ * Copyright (C) 2003,2004  Krzysztof Benedyczak    (golbi@mat.uni.torun.pl)
+ *                          Michal Wronski          (michal.wronski@gmail.com)
+ *
+ * Spinlocks:               Mohamed Abbas           (abbas.mohamed@intel.com)
+ * Lockless receive & send, fd based notify:
+ *			    Manfred Spraul	    (manfred@colorfullife.com)
+ *
+ * Audit:                   George Wilson           (ltcgcw@us.ibm.com)
+ *
+ * This file is released under the GPL.
+ */
+
+#include <linux/capability.h>
+#include <linux/init.h>
+#include <linux/pagemap.h>
+#include <linux/file.h>
+#include <linux/mount.h>
+#include <linux/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 <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_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 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 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 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;
+
+	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;
+		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);
+		info->qsize += sizeof(*leaf);
+	}
+	leaf->priority = msg->m_type;
+	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 struct msg_msg *msg_get(struct mqueue_inode_info *info)
+{
+	struct rb_node **p, *parent = NULL;
+	struct posix_msg_tree_node *leaf;
+	struct msg_msg *msg;
+
+try_again:
+	p = &info->msg_tree.rb_node;
+	while (*p) {
+		parent = *p;
+		/*
+		 * 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.
+		 */
+		p = &(*p)->rb_right;
+	}
+	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");
+		rb_erase(&leaf->rb_node, &info->msg_tree);
+		if (info->node_cache) {
+			info->qsize -= sizeof(*leaf);
+			kfree(leaf);
+		} else {
+			info->node_cache = leaf;
+		}
+		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)) {
+			rb_erase(&leaf->rb_node, &info->msg_tree);
+			if (info->node_cache) {
+				info->qsize -= sizeof(*leaf);
+				kfree(leaf);
+			} else {
+				info->node_cache = leaf;
+			}
+		}
+	}
+	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;
+
+	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->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.
+		 */
+		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);
+		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, void *data, int silent)
+{
+	struct inode *inode;
+	struct ipc_namespace *ns = data;
+
+	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, 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 struct dentry *mqueue_mount(struct file_system_type *fs_type,
+			 int flags, const char *dev_name,
+			 void *data)
+{
+	if (!(flags & MS_KERNMOUNT)) {
+		struct ipc_namespace *ns = current->nsproxy->ipc_ns;
+		/* Don't allow mounting unless the caller has CAP_SYS_ADMIN
+		 * over the ipc namespace.
+		 */
+		if (!ns_capable(ns->user_ns, CAP_SYS_ADMIN))
+			return ERR_PTR(-EPERM);
+
+		data = ns;
+	}
+	return mount_ns(fs_type, flags, data, mqueue_fill_super);
+}
+
+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_i_callback(struct rcu_head *head)
+{
+	struct inode *inode = container_of(head, struct inode, i_rcu);
+	kmem_cache_free(mqueue_inode_cachep, MQUEUE_I(inode));
+}
+
+static void mqueue_destroy_inode(struct inode *inode)
+{
+	call_rcu(&inode->i_rcu, mqueue_i_callback);
+}
+
+static void mqueue_evict_inode(struct inode *inode)
+{
+	struct mqueue_inode_info *info;
+	struct user_struct *user;
+	unsigned long mq_bytes, mq_treesize;
+	struct ipc_namespace *ipc_ns;
+	struct msg_msg *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)
+		free_msg(msg);
+	kfree(info->node_cache);
+	spin_unlock(&info->lock);
+
+	/* 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);
+
+	user = info->user;
+	if (user) {
+		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(struct inode *dir, struct dentry *dentry,
+				umode_t mode, bool excl)
+{
+	struct inode *inode;
+	struct mq_attr *attr = dentry->d_fsdata;
+	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;
+
+	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_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->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;
+	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 unsigned int mqueue_poll_file(struct file *filp, struct poll_table_struct *poll_tab)
+{
+	struct mqueue_inode_info *info = MQUEUE_I(file_inode(filp));
+	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,
+		    ktime_t *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_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 siginfo sig_i;
+		switch (info->notify.sigev_notify) {
+		case SIGEV_NONE:
+			break;
+		case SIGEV_SIGNAL:
+			/* sends signal */
+
+			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 timespec __user *u_abs_timeout,
+			   ktime_t *expires, struct timespec *ts)
+{
+	if (copy_from_user(ts, u_abs_timeout, sizeof(struct timespec)))
+		return -EFAULT;
+	if (!timespec_valid(ts))
+		return -EINVAL;
+
+	*expires = timespec_to_ktime(*ts);
+	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 mq_attr_ok(struct ipc_namespace *ipc_ns, struct mq_attr *attr)
+{
+	int mq_treesize;
+	unsigned long total_size;
+
+	if (attr->mq_maxmsg <= 0 || attr->mq_msgsize <= 0)
+		return -EINVAL;
+	if (capable(CAP_SYS_RESOURCE)) {
+		if (attr->mq_maxmsg > HARD_MSGMAX ||
+		    attr->mq_msgsize > HARD_MSGSIZEMAX)
+			return -EINVAL;
+	} else {
+		if (attr->mq_maxmsg > ipc_ns->mq_msg_max ||
+				attr->mq_msgsize > ipc_ns->mq_msgsize_max)
+			return -EINVAL;
+	}
+	/* check for overflow */
+	if (attr->mq_msgsize > ULONG_MAX/attr->mq_maxmsg)
+		return -EOVERFLOW;
+	mq_treesize = attr->mq_maxmsg * sizeof(struct msg_msg) +
+		min_t(unsigned int, attr->mq_maxmsg, MQ_PRIO_MAX) *
+		sizeof(struct posix_msg_tree_node);
+	total_size = attr->mq_maxmsg * attr->mq_msgsize;
+	if (total_size + mq_treesize < total_size)
+		return -EOVERFLOW;
+	return 0;
+}
+
+/*
+ * Invoked when creating a new queue via sys_mq_open
+ */
+static struct file *do_create(struct ipc_namespace *ipc_ns, struct inode *dir,
+			struct path *path, int oflag, umode_t mode,
+			struct mq_attr *attr)
+{
+	const struct cred *cred = current_cred();
+	int ret;
+
+	if (attr) {
+		ret = mq_attr_ok(ipc_ns, attr);
+		if (ret)
+			return ERR_PTR(ret);
+		/* store for use during create */
+		path->dentry->d_fsdata = attr;
+	} else {
+		struct mq_attr def_attr;
+
+		def_attr.mq_maxmsg = min(ipc_ns->mq_msg_max,
+					 ipc_ns->mq_msg_default);
+		def_attr.mq_msgsize = min(ipc_ns->mq_msgsize_max,
+					  ipc_ns->mq_msgsize_default);
+		ret = mq_attr_ok(ipc_ns, &def_attr);
+		if (ret)
+			return ERR_PTR(ret);
+	}
+
+	mode &= ~current_umask();
+	ret = vfs_create(dir, path->dentry, mode, true);
+	path->dentry->d_fsdata = NULL;
+	if (ret)
+		return ERR_PTR(ret);
+	return dentry_open(path, oflag, cred);
+}
+
+/* Opens existing queue */
+static struct file *do_open(struct path *path, int oflag)
+{
+	static const int oflag2acc[O_ACCMODE] = { MAY_READ, MAY_WRITE,
+						  MAY_READ | MAY_WRITE };
+	int acc;
+	if ((oflag & O_ACCMODE) == (O_RDWR | O_WRONLY))
+		return ERR_PTR(-EINVAL);
+	acc = oflag2acc[oflag & O_ACCMODE];
+	if (inode_permission(d_inode(path->dentry), acc))
+		return ERR_PTR(-EACCES);
+	return dentry_open(path, oflag, current_cred());
+}
+
+SYSCALL_DEFINE4(mq_open, const char __user *, u_name, int, oflag, umode_t, mode,
+		struct mq_attr __user *, u_attr)
+{
+	struct path path;
+	struct file *filp;
+	struct filename *name;
+	struct mq_attr attr;
+	int fd, error;
+	struct ipc_namespace *ipc_ns = current->nsproxy->ipc_ns;
+	struct vfsmount *mnt = ipc_ns->mq_mnt;
+	struct dentry *root = mnt->mnt_root;
+	int ro;
+
+	if (u_attr && copy_from_user(&attr, u_attr, sizeof(struct mq_attr)))
+		return -EFAULT;
+
+	audit_mq_open(oflag, mode, u_attr ? &attr : NULL);
+
+	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 */
+	error = 0;
+	mutex_lock(&d_inode(root)->i_mutex);
+	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);
+
+	if (oflag & O_CREAT) {
+		if (d_really_is_positive(path.dentry)) {	/* entry already exists */
+			audit_inode(name, path.dentry, 0);
+			if (oflag & O_EXCL) {
+				error = -EEXIST;
+				goto out;
+			}
+			filp = do_open(&path, oflag);
+		} else {
+			if (ro) {
+				error = ro;
+				goto out;
+			}
+			audit_inode_parent_hidden(name, root);
+			filp = do_create(ipc_ns, d_inode(root),
+						&path, oflag, mode,
+						u_attr ? &attr : NULL);
+		}
+	} else {
+		if (d_really_is_negative(path.dentry)) {
+			error = -ENOENT;
+			goto out;
+		}
+		audit_inode(name, path.dentry, 0);
+		filp = do_open(&path, oflag);
+	}
+
+	if (!IS_ERR(filp))
+		fd_install(fd, filp);
+	else
+		error = PTR_ERR(filp);
+out:
+	path_put(&path);
+out_putfd:
+	if (error) {
+		put_unused_fd(fd);
+		fd = error;
+	}
+	mutex_unlock(&d_inode(root)->i_mutex);
+	if (!ro)
+		mnt_drop_write(mnt);
+out_putname:
+	putname(name);
+	return fd;
+}
+
+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;
+	mutex_lock_nested(&d_inode(mnt->mnt_root)->i_mutex, 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:
+	mutex_unlock(&d_inode(mnt->mnt_root)->i_mutex);
+	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;
+}
+
+SYSCALL_DEFINE5(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 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 timespec ts;
+	struct posix_msg_tree_node *new_leaf = NULL;
+	int ret = 0;
+	WAKE_Q(wake_q);
+
+	if (u_abs_timeout) {
+		int res = prepare_timeout(u_abs_timeout, &expires, &ts);
+		if (res)
+			return res;
+		timeout = &expires;
+	}
+
+	if (unlikely(msg_prio >= (unsigned long) MQ_PRIO_MAX))
+		return -EINVAL;
+
+	audit_mq_sendrecv(mqdes, msg_len, msg_prio, timeout ? &ts : NULL);
+
+	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;
+		info->qsize += sizeof(*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;
+	}
+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;
+}
+
+SYSCALL_DEFINE5(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)
+{
+	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 timespec ts;
+	struct posix_msg_tree_node *new_leaf = NULL;
+
+	if (u_abs_timeout) {
+		int res = prepare_timeout(u_abs_timeout, &expires, &ts);
+		if (res)
+			return res;
+		timeout = &expires;
+	}
+
+	audit_mq_sendrecv(mqdes, msg_len, 0, timeout ? &ts : NULL);
+
+	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;
+		info->qsize += sizeof(*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 {
+		WAKE_Q(wake_q);
+
+		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(&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;
+}
+
+/*
+ * 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.
+ */
+SYSCALL_DEFINE2(mq_notify, mqd_t, mqdes,
+		const struct sigevent __user *, u_notification)
+{
+	int ret;
+	struct fd f;
+	struct sock *sock;
+	struct inode *inode;
+	struct sigevent notification;
+	struct mqueue_inode_info *info;
+	struct sk_buff *nc;
+
+	if (u_notification) {
+		if (copy_from_user(&notification, u_notification,
+					sizeof(struct sigevent)))
+			return -EFAULT;
+	}
+
+	audit_mq_notify(mqdes, u_notification ? &notification : NULL);
+
+	nc = NULL;
+	sock = NULL;
+	if (u_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) {
+				ret = -ENOMEM;
+				goto out;
+			}
+			if (copy_from_user(nc->data,
+					notification.sigev_value.sival_ptr,
+					NOTIFY_COOKIE_LEN)) {
+				ret = -EFAULT;
+				goto out;
+			}
+
+			/* 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);
+				sock = NULL;
+				goto out;
+			}
+
+			timeo = MAX_SCHEDULE_TIMEOUT;
+			ret = netlink_attachskb(sock, nc, &timeo, NULL);
+			if (ret == 1)
+				goto retry;
+			if (ret) {
+				sock = NULL;
+				nc = NULL;
+				goto out;
+			}
+		}
+	}
+
+	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 (u_notification == NULL) {
+		if (info->notify_owner == task_tgid(current)) {
+			remove_notification(info);
+			inode->i_atime = inode->i_ctime = CURRENT_TIME;
+		}
+	} 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;
+	}
+	spin_unlock(&info->lock);
+out_fput:
+	fdput(f);
+out:
+	if (sock)
+		netlink_detachskb(sock, nc);
+	else if (nc)
+		dev_kfree_skb(nc);
+
+	return ret;
+}
+
+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 fd f;
+	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;
+	}
+
+	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);
+
+	spin_lock(&info->lock);
+
+	omqstat = info->attr;
+	omqstat.mq_flags = f.file->f_flags & O_NONBLOCK;
+	if (u_mqstat) {
+		audit_mq_getsetattr(mqdes, &mqstat);
+		spin_lock(&f.file->f_lock);
+		if (mqstat.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;
+	}
+
+	spin_unlock(&info->lock);
+
+	ret = 0;
+	if (u_omqstat != NULL && copy_to_user(u_omqstat, &omqstat,
+						sizeof(struct mq_attr)))
+		ret = -EFAULT;
+
+out_fput:
+	fdput(f);
+out:
+	return ret;
+}
+
+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,
+	.destroy_inode = mqueue_destroy_inode,
+	.evict_inode = mqueue_evict_inode,
+	.statfs = simple_statfs,
+};
+
+static struct file_system_type mqueue_fs_type = {
+	.name = "mqueue",
+	.mount = mqueue_mount,
+	.kill_sb = kill_litter_super,
+	.fs_flags = FS_USERNS_MOUNT,
+};
+
+int mq_init_ns(struct ipc_namespace *ns)
+{
+	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;
+
+	ns->mq_mnt = kern_mount_data(&mqueue_fs_type, ns);
+	if (IS_ERR(ns->mq_mnt)) {
+		int err = PTR_ERR(ns->mq_mnt);
+		ns->mq_mnt = NULL;
+		return err;
+	}
+	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, 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);
diff --git a/kernel/ipc/msg.c b/kernel/ipc/msg.c
new file mode 100644
index 000000000..cedbf5f50
--- /dev/null
+++ b/kernel/ipc/msg.c
@@ -0,0 +1,1060 @@
+/*
+ * linux/ipc/msg.c
+ * Copyright (C) 1992 Krishna Balasubramanian
+ *
+ * Removed all the remaining kerneld mess
+ * Catch the -EFAULT stuff properly
+ * Use GFP_KERNEL for messages as in 1.2
+ * Fixed up the unchecked user space derefs
+ * Copyright (C) 1998 Alan Cox & Andi Kleen
+ *
+ * /proc/sysvipc/msg support (c) 1999 Dragos Acostachioaie <dragos@iname.com>
+ *
+ * mostly rewritten, threaded and wake-one semantics added
+ * MSGMAX limit removed, sysctl's added
+ * (c) 1999 Manfred Spraul <manfred@colorfullife.com>
+ *
+ * support for audit of ipc object properties and permission changes
+ * Dustin Kirkland <dustin.kirkland@us.ibm.com>
+ *
+ * namespaces support
+ * OpenVZ, SWsoft Inc.
+ * Pavel Emelianov <xemul@openvz.org>
+ */
+
+#include <linux/capability.h>
+#include <linux/msg.h>
+#include <linux/spinlock.h>
+#include <linux/init.h>
+#include <linux/mm.h>
+#include <linux/proc_fs.h>
+#include <linux/list.h>
+#include <linux/security.h>
+#include <linux/sched.h>
+#include <linux/syscalls.h>
+#include <linux/audit.h>
+#include <linux/seq_file.h>
+#include <linux/rwsem.h>
+#include <linux/nsproxy.h>
+#include <linux/ipc_namespace.h>
+
+#include <asm/current.h>
+#include <linux/uaccess.h>
+#include "util.h"
+
+/* one msg_receiver structure for each sleeping receiver */
+struct msg_receiver {
+	struct list_head	r_list;
+	struct task_struct	*r_tsk;
+
+	int			r_mode;
+	long			r_msgtype;
+	long			r_maxsize;
+
+	/*
+	 * Mark r_msg volatile so that the compiler
+	 * does not try to get smart and optimize
+	 * it. We rely on this for the lockless
+	 * receive algorithm.
+	 */
+	struct msg_msg		*volatile r_msg;
+};
+
+/* one msg_sender for each sleeping sender */
+struct msg_sender {
+	struct list_head	list;
+	struct task_struct	*tsk;
+};
+
+#define SEARCH_ANY		1
+#define SEARCH_EQUAL		2
+#define SEARCH_NOTEQUAL		3
+#define SEARCH_LESSEQUAL	4
+#define SEARCH_NUMBER		5
+
+#define msg_ids(ns)	((ns)->ids[IPC_MSG_IDS])
+
+static inline struct msg_queue *msq_obtain_object(struct ipc_namespace *ns, int id)
+{
+	struct kern_ipc_perm *ipcp = ipc_obtain_object(&msg_ids(ns), id);
+
+	if (IS_ERR(ipcp))
+		return ERR_CAST(ipcp);
+
+	return container_of(ipcp, struct msg_queue, q_perm);
+}
+
+static inline struct msg_queue *msq_obtain_object_check(struct ipc_namespace *ns,
+							int id)
+{
+	struct kern_ipc_perm *ipcp = ipc_obtain_object_check(&msg_ids(ns), id);
+
+	if (IS_ERR(ipcp))
+		return ERR_CAST(ipcp);
+
+	return container_of(ipcp, struct msg_queue, q_perm);
+}
+
+static inline void msg_rmid(struct ipc_namespace *ns, struct msg_queue *s)
+{
+	ipc_rmid(&msg_ids(ns), &s->q_perm);
+}
+
+static void msg_rcu_free(struct rcu_head *head)
+{
+	struct ipc_rcu *p = container_of(head, struct ipc_rcu, rcu);
+	struct msg_queue *msq = ipc_rcu_to_struct(p);
+
+	security_msg_queue_free(msq);
+	ipc_rcu_free(head);
+}
+
+/**
+ * newque - Create a new msg queue
+ * @ns: namespace
+ * @params: ptr to the structure that contains the key and msgflg
+ *
+ * Called with msg_ids.rwsem held (writer)
+ */
+static int newque(struct ipc_namespace *ns, struct ipc_params *params)
+{
+	struct msg_queue *msq;
+	int id, retval;
+	key_t key = params->key;
+	int msgflg = params->flg;
+
+	msq = ipc_rcu_alloc(sizeof(*msq));
+	if (!msq)
+		return -ENOMEM;
+
+	msq->q_perm.mode = msgflg & S_IRWXUGO;
+	msq->q_perm.key = key;
+
+	msq->q_perm.security = NULL;
+	retval = security_msg_queue_alloc(msq);
+	if (retval) {
+		ipc_rcu_putref(msq, ipc_rcu_free);
+		return retval;
+	}
+
+	/* ipc_addid() locks msq upon success. */
+	id = ipc_addid(&msg_ids(ns), &msq->q_perm, ns->msg_ctlmni);
+	if (id < 0) {
+		ipc_rcu_putref(msq, msg_rcu_free);
+		return id;
+	}
+
+	msq->q_stime = msq->q_rtime = 0;
+	msq->q_ctime = get_seconds();
+	msq->q_cbytes = msq->q_qnum = 0;
+	msq->q_qbytes = ns->msg_ctlmnb;
+	msq->q_lspid = msq->q_lrpid = 0;
+	INIT_LIST_HEAD(&msq->q_messages);
+	INIT_LIST_HEAD(&msq->q_receivers);
+	INIT_LIST_HEAD(&msq->q_senders);
+
+	ipc_unlock_object(&msq->q_perm);
+	rcu_read_unlock();
+
+	return msq->q_perm.id;
+}
+
+static inline void ss_add(struct msg_queue *msq, struct msg_sender *mss)
+{
+	mss->tsk = current;
+	__set_current_state(TASK_INTERRUPTIBLE);
+	list_add_tail(&mss->list, &msq->q_senders);
+}
+
+static inline void ss_del(struct msg_sender *mss)
+{
+	if (mss->list.next != NULL)
+		list_del(&mss->list);
+}
+
+static void ss_wakeup(struct list_head *h, int kill)
+{
+	struct msg_sender *mss, *t;
+
+	list_for_each_entry_safe(mss, t, h, list) {
+		if (kill)
+			mss->list.next = NULL;
+		wake_up_process(mss->tsk);
+	}
+}
+
+static void expunge_all(struct msg_queue *msq, int res)
+{
+	struct msg_receiver *msr, *t;
+
+	list_for_each_entry_safe(msr, t, &msq->q_receivers, r_list) {
+		/*
+		 * Make sure that the wakeup doesnt preempt
+		 * this CPU prematurely. (on PREEMPT_RT)
+		 */
+		preempt_disable_rt();
+
+		msr->r_msg = NULL; /* initialize expunge ordering */
+		wake_up_process(msr->r_tsk);
+		/*
+		 * Ensure that the wakeup is visible before setting r_msg as
+		 * the receiving end depends on it: either spinning on a nil,
+		 * or dealing with -EAGAIN cases. See lockless receive part 1
+		 * and 2 in do_msgrcv().
+		 */
+		smp_mb();
+		msr->r_msg = ERR_PTR(res);
+
+		preempt_enable_rt();
+	}
+}
+
+/*
+ * freeque() wakes up waiters on the sender and receiver waiting queue,
+ * removes the message queue from message queue ID IDR, and cleans up all the
+ * messages associated with this queue.
+ *
+ * msg_ids.rwsem (writer) and the spinlock for this message queue are held
+ * before freeque() is called. msg_ids.rwsem remains locked on exit.
+ */
+static void freeque(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp)
+{
+	struct msg_msg *msg, *t;
+	struct msg_queue *msq = container_of(ipcp, struct msg_queue, q_perm);
+
+	expunge_all(msq, -EIDRM);
+	ss_wakeup(&msq->q_senders, 1);
+	msg_rmid(ns, msq);
+	ipc_unlock_object(&msq->q_perm);
+	rcu_read_unlock();
+
+	list_for_each_entry_safe(msg, t, &msq->q_messages, m_list) {
+		atomic_dec(&ns->msg_hdrs);
+		free_msg(msg);
+	}
+	atomic_sub(msq->q_cbytes, &ns->msg_bytes);
+	ipc_rcu_putref(msq, msg_rcu_free);
+}
+
+/*
+ * Called with msg_ids.rwsem and ipcp locked.
+ */
+static inline int msg_security(struct kern_ipc_perm *ipcp, int msgflg)
+{
+	struct msg_queue *msq = container_of(ipcp, struct msg_queue, q_perm);
+
+	return security_msg_queue_associate(msq, msgflg);
+}
+
+SYSCALL_DEFINE2(msgget, key_t, key, int, msgflg)
+{
+	struct ipc_namespace *ns;
+	static const struct ipc_ops msg_ops = {
+		.getnew = newque,
+		.associate = msg_security,
+	};
+	struct ipc_params msg_params;
+
+	ns = current->nsproxy->ipc_ns;
+
+	msg_params.key = key;
+	msg_params.flg = msgflg;
+
+	return ipcget(ns, &msg_ids(ns), &msg_ops, &msg_params);
+}
+
+static inline unsigned long
+copy_msqid_to_user(void __user *buf, struct msqid64_ds *in, int version)
+{
+	switch (version) {
+	case IPC_64:
+		return copy_to_user(buf, in, sizeof(*in));
+	case IPC_OLD:
+	{
+		struct msqid_ds out;
+
+		memset(&out, 0, sizeof(out));
+
+		ipc64_perm_to_ipc_perm(&in->msg_perm, &out.msg_perm);
+
+		out.msg_stime		= in->msg_stime;
+		out.msg_rtime		= in->msg_rtime;
+		out.msg_ctime		= in->msg_ctime;
+
+		if (in->msg_cbytes > USHRT_MAX)
+			out.msg_cbytes	= USHRT_MAX;
+		else
+			out.msg_cbytes	= in->msg_cbytes;
+		out.msg_lcbytes		= in->msg_cbytes;
+
+		if (in->msg_qnum > USHRT_MAX)
+			out.msg_qnum	= USHRT_MAX;
+		else
+			out.msg_qnum	= in->msg_qnum;
+
+		if (in->msg_qbytes > USHRT_MAX)
+			out.msg_qbytes	= USHRT_MAX;
+		else
+			out.msg_qbytes	= in->msg_qbytes;
+		out.msg_lqbytes		= in->msg_qbytes;
+
+		out.msg_lspid		= in->msg_lspid;
+		out.msg_lrpid		= in->msg_lrpid;
+
+		return copy_to_user(buf, &out, sizeof(out));
+	}
+	default:
+		return -EINVAL;
+	}
+}
+
+static inline unsigned long
+copy_msqid_from_user(struct msqid64_ds *out, void __user *buf, int version)
+{
+	switch (version) {
+	case IPC_64:
+		if (copy_from_user(out, buf, sizeof(*out)))
+			return -EFAULT;
+		return 0;
+	case IPC_OLD:
+	{
+		struct msqid_ds tbuf_old;
+
+		if (copy_from_user(&tbuf_old, buf, sizeof(tbuf_old)))
+			return -EFAULT;
+
+		out->msg_perm.uid	= tbuf_old.msg_perm.uid;
+		out->msg_perm.gid	= tbuf_old.msg_perm.gid;
+		out->msg_perm.mode	= tbuf_old.msg_perm.mode;
+
+		if (tbuf_old.msg_qbytes == 0)
+			out->msg_qbytes	= tbuf_old.msg_lqbytes;
+		else
+			out->msg_qbytes	= tbuf_old.msg_qbytes;
+
+		return 0;
+	}
+	default:
+		return -EINVAL;
+	}
+}
+
+/*
+ * This function handles some msgctl commands which require the rwsem
+ * to be held in write mode.
+ * NOTE: no locks must be held, the rwsem is taken inside this function.
+ */
+static int msgctl_down(struct ipc_namespace *ns, int msqid, int cmd,
+		       struct msqid_ds __user *buf, int version)
+{
+	struct kern_ipc_perm *ipcp;
+	struct msqid64_ds uninitialized_var(msqid64);
+	struct msg_queue *msq;
+	int err;
+
+	if (cmd == IPC_SET) {
+		if (copy_msqid_from_user(&msqid64, buf, version))
+			return -EFAULT;
+	}
+
+	down_write(&msg_ids(ns).rwsem);
+	rcu_read_lock();
+
+	ipcp = ipcctl_pre_down_nolock(ns, &msg_ids(ns), msqid, cmd,
+				      &msqid64.msg_perm, msqid64.msg_qbytes);
+	if (IS_ERR(ipcp)) {
+		err = PTR_ERR(ipcp);
+		goto out_unlock1;
+	}
+
+	msq = container_of(ipcp, struct msg_queue, q_perm);
+
+	err = security_msg_queue_msgctl(msq, cmd);
+	if (err)
+		goto out_unlock1;
+
+	switch (cmd) {
+	case IPC_RMID:
+		ipc_lock_object(&msq->q_perm);
+		/* freeque unlocks the ipc object and rcu */
+		freeque(ns, ipcp);
+		goto out_up;
+	case IPC_SET:
+		if (msqid64.msg_qbytes > ns->msg_ctlmnb &&
+		    !capable(CAP_SYS_RESOURCE)) {
+			err = -EPERM;
+			goto out_unlock1;
+		}
+
+		ipc_lock_object(&msq->q_perm);
+		err = ipc_update_perm(&msqid64.msg_perm, ipcp);
+		if (err)
+			goto out_unlock0;
+
+		msq->q_qbytes = msqid64.msg_qbytes;
+
+		msq->q_ctime = get_seconds();
+		/* sleeping receivers might be excluded by
+		 * stricter permissions.
+		 */
+		expunge_all(msq, -EAGAIN);
+		/* sleeping senders might be able to send
+		 * due to a larger queue size.
+		 */
+		ss_wakeup(&msq->q_senders, 0);
+		break;
+	default:
+		err = -EINVAL;
+		goto out_unlock1;
+	}
+
+out_unlock0:
+	ipc_unlock_object(&msq->q_perm);
+out_unlock1:
+	rcu_read_unlock();
+out_up:
+	up_write(&msg_ids(ns).rwsem);
+	return err;
+}
+
+static int msgctl_nolock(struct ipc_namespace *ns, int msqid,
+			 int cmd, int version, void __user *buf)
+{
+	int err;
+	struct msg_queue *msq;
+
+	switch (cmd) {
+	case IPC_INFO:
+	case MSG_INFO:
+	{
+		struct msginfo msginfo;
+		int max_id;
+
+		if (!buf)
+			return -EFAULT;
+
+		/*
+		 * We must not return kernel stack data.
+		 * due to padding, it's not enough
+		 * to set all member fields.
+		 */
+		err = security_msg_queue_msgctl(NULL, cmd);
+		if (err)
+			return err;
+
+		memset(&msginfo, 0, sizeof(msginfo));
+		msginfo.msgmni = ns->msg_ctlmni;
+		msginfo.msgmax = ns->msg_ctlmax;
+		msginfo.msgmnb = ns->msg_ctlmnb;
+		msginfo.msgssz = MSGSSZ;
+		msginfo.msgseg = MSGSEG;
+		down_read(&msg_ids(ns).rwsem);
+		if (cmd == MSG_INFO) {
+			msginfo.msgpool = msg_ids(ns).in_use;
+			msginfo.msgmap = atomic_read(&ns->msg_hdrs);
+			msginfo.msgtql = atomic_read(&ns->msg_bytes);
+		} else {
+			msginfo.msgmap = MSGMAP;
+			msginfo.msgpool = MSGPOOL;
+			msginfo.msgtql = MSGTQL;
+		}
+		max_id = ipc_get_maxid(&msg_ids(ns));
+		up_read(&msg_ids(ns).rwsem);
+		if (copy_to_user(buf, &msginfo, sizeof(struct msginfo)))
+			return -EFAULT;
+		return (max_id < 0) ? 0 : max_id;
+	}
+
+	case MSG_STAT:
+	case IPC_STAT:
+	{
+		struct msqid64_ds tbuf;
+		int success_return;
+
+		if (!buf)
+			return -EFAULT;
+
+		memset(&tbuf, 0, sizeof(tbuf));
+
+		rcu_read_lock();
+		if (cmd == MSG_STAT) {
+			msq = msq_obtain_object(ns, msqid);
+			if (IS_ERR(msq)) {
+				err = PTR_ERR(msq);
+				goto out_unlock;
+			}
+			success_return = msq->q_perm.id;
+		} else {
+			msq = msq_obtain_object_check(ns, msqid);
+			if (IS_ERR(msq)) {
+				err = PTR_ERR(msq);
+				goto out_unlock;
+			}
+			success_return = 0;
+		}
+
+		err = -EACCES;
+		if (ipcperms(ns, &msq->q_perm, S_IRUGO))
+			goto out_unlock;
+
+		err = security_msg_queue_msgctl(msq, cmd);
+		if (err)
+			goto out_unlock;
+
+		kernel_to_ipc64_perm(&msq->q_perm, &tbuf.msg_perm);
+		tbuf.msg_stime  = msq->q_stime;
+		tbuf.msg_rtime  = msq->q_rtime;
+		tbuf.msg_ctime  = msq->q_ctime;
+		tbuf.msg_cbytes = msq->q_cbytes;
+		tbuf.msg_qnum   = msq->q_qnum;
+		tbuf.msg_qbytes = msq->q_qbytes;
+		tbuf.msg_lspid  = msq->q_lspid;
+		tbuf.msg_lrpid  = msq->q_lrpid;
+		rcu_read_unlock();
+
+		if (copy_msqid_to_user(buf, &tbuf, version))
+			return -EFAULT;
+		return success_return;
+	}
+
+	default:
+		return -EINVAL;
+	}
+
+	return err;
+out_unlock:
+	rcu_read_unlock();
+	return err;
+}
+
+SYSCALL_DEFINE3(msgctl, int, msqid, int, cmd, struct msqid_ds __user *, buf)
+{
+	int version;
+	struct ipc_namespace *ns;
+
+	if (msqid < 0 || cmd < 0)
+		return -EINVAL;
+
+	version = ipc_parse_version(&cmd);
+	ns = current->nsproxy->ipc_ns;
+
+	switch (cmd) {
+	case IPC_INFO:
+	case MSG_INFO:
+	case MSG_STAT:	/* msqid is an index rather than a msg queue id */
+	case IPC_STAT:
+		return msgctl_nolock(ns, msqid, cmd, version, buf);
+	case IPC_SET:
+	case IPC_RMID:
+		return msgctl_down(ns, msqid, cmd, buf, version);
+	default:
+		return  -EINVAL;
+	}
+}
+
+static int testmsg(struct msg_msg *msg, long type, int mode)
+{
+	switch (mode) {
+	case SEARCH_ANY:
+	case SEARCH_NUMBER:
+		return 1;
+	case SEARCH_LESSEQUAL:
+		if (msg->m_type <= type)
+			return 1;
+		break;
+	case SEARCH_EQUAL:
+		if (msg->m_type == type)
+			return 1;
+		break;
+	case SEARCH_NOTEQUAL:
+		if (msg->m_type != type)
+			return 1;
+		break;
+	}
+	return 0;
+}
+
+static inline int pipelined_send(struct msg_queue *msq, struct msg_msg *msg)
+{
+	struct msg_receiver *msr, *t;
+
+	list_for_each_entry_safe(msr, t, &msq->q_receivers, r_list) {
+		if (testmsg(msg, msr->r_msgtype, msr->r_mode) &&
+		    !security_msg_queue_msgrcv(msq, msg, msr->r_tsk,
+					       msr->r_msgtype, msr->r_mode)) {
+			/*
+			 * Make sure that the wakeup doesnt preempt
+			 * this CPU prematurely. (on PREEMPT_RT)
+			 */
+			preempt_disable_rt();
+
+			list_del(&msr->r_list);
+			if (msr->r_maxsize < msg->m_ts) {
+				/* initialize pipelined send ordering */
+				msr->r_msg = NULL;
+				wake_up_process(msr->r_tsk);
+				smp_mb(); /* see barrier comment below */
+				msr->r_msg = ERR_PTR(-E2BIG);
+			} else {
+				msr->r_msg = NULL;
+				msq->q_lrpid = task_pid_vnr(msr->r_tsk);
+				msq->q_rtime = get_seconds();
+				wake_up_process(msr->r_tsk);
+				/*
+				 * Ensure that the wakeup is visible before
+				 * setting r_msg, as the receiving end depends
+				 * on it. See lockless receive part 1 and 2 in
+				 * do_msgrcv().
+				 */
+				smp_mb();
+				msr->r_msg = msg;
+				preempt_enable_rt();
+
+				return 1;
+			}
+			preempt_enable_rt();
+		}
+	}
+	return 0;
+}
+
+long do_msgsnd(int msqid, long mtype, void __user *mtext,
+		size_t msgsz, int msgflg)
+{
+	struct msg_queue *msq;
+	struct msg_msg *msg;
+	int err;
+	struct ipc_namespace *ns;
+
+	ns = current->nsproxy->ipc_ns;
+
+	if (msgsz > ns->msg_ctlmax || (long) msgsz < 0 || msqid < 0)
+		return -EINVAL;
+	if (mtype < 1)
+		return -EINVAL;
+
+	msg = load_msg(mtext, msgsz);
+	if (IS_ERR(msg))
+		return PTR_ERR(msg);
+
+	msg->m_type = mtype;
+	msg->m_ts = msgsz;
+
+	rcu_read_lock();
+	msq = msq_obtain_object_check(ns, msqid);
+	if (IS_ERR(msq)) {
+		err = PTR_ERR(msq);
+		goto out_unlock1;
+	}
+
+	ipc_lock_object(&msq->q_perm);
+
+	for (;;) {
+		struct msg_sender s;
+
+		err = -EACCES;
+		if (ipcperms(ns, &msq->q_perm, S_IWUGO))
+			goto out_unlock0;
+
+		/* raced with RMID? */
+		if (!ipc_valid_object(&msq->q_perm)) {
+			err = -EIDRM;
+			goto out_unlock0;
+		}
+
+		err = security_msg_queue_msgsnd(msq, msg, msgflg);
+		if (err)
+			goto out_unlock0;
+
+		if (msgsz + msq->q_cbytes <= msq->q_qbytes &&
+				1 + msq->q_qnum <= msq->q_qbytes) {
+			break;
+		}
+
+		/* queue full, wait: */
+		if (msgflg & IPC_NOWAIT) {
+			err = -EAGAIN;
+			goto out_unlock0;
+		}
+
+		/* enqueue the sender and prepare to block */
+		ss_add(msq, &s);
+
+		if (!ipc_rcu_getref(msq)) {
+			err = -EIDRM;
+			goto out_unlock0;
+		}
+
+		ipc_unlock_object(&msq->q_perm);
+		rcu_read_unlock();
+		schedule();
+
+		rcu_read_lock();
+		ipc_lock_object(&msq->q_perm);
+
+		ipc_rcu_putref(msq, ipc_rcu_free);
+		/* raced with RMID? */
+		if (!ipc_valid_object(&msq->q_perm)) {
+			err = -EIDRM;
+			goto out_unlock0;
+		}
+
+		ss_del(&s);
+
+		if (signal_pending(current)) {
+			err = -ERESTARTNOHAND;
+			goto out_unlock0;
+		}
+
+	}
+	msq->q_lspid = task_tgid_vnr(current);
+	msq->q_stime = get_seconds();
+
+	if (!pipelined_send(msq, msg)) {
+		/* no one is waiting for this message, enqueue it */
+		list_add_tail(&msg->m_list, &msq->q_messages);
+		msq->q_cbytes += msgsz;
+		msq->q_qnum++;
+		atomic_add(msgsz, &ns->msg_bytes);
+		atomic_inc(&ns->msg_hdrs);
+	}
+
+	err = 0;
+	msg = NULL;
+
+out_unlock0:
+	ipc_unlock_object(&msq->q_perm);
+out_unlock1:
+	rcu_read_unlock();
+	if (msg != NULL)
+		free_msg(msg);
+	return err;
+}
+
+SYSCALL_DEFINE4(msgsnd, int, msqid, struct msgbuf __user *, msgp, size_t, msgsz,
+		int, msgflg)
+{
+	long mtype;
+
+	if (get_user(mtype, &msgp->mtype))
+		return -EFAULT;
+	return do_msgsnd(msqid, mtype, msgp->mtext, msgsz, msgflg);
+}
+
+static inline int convert_mode(long *msgtyp, int msgflg)
+{
+	if (msgflg & MSG_COPY)
+		return SEARCH_NUMBER;
+	/*
+	 *  find message of correct type.
+	 *  msgtyp = 0 => get first.
+	 *  msgtyp > 0 => get first message of matching type.
+	 *  msgtyp < 0 => get message with least type must be < abs(msgtype).
+	 */
+	if (*msgtyp == 0)
+		return SEARCH_ANY;
+	if (*msgtyp < 0) {
+		*msgtyp = -*msgtyp;
+		return SEARCH_LESSEQUAL;
+	}
+	if (msgflg & MSG_EXCEPT)
+		return SEARCH_NOTEQUAL;
+	return SEARCH_EQUAL;
+}
+
+static long do_msg_fill(void __user *dest, struct msg_msg *msg, size_t bufsz)
+{
+	struct msgbuf __user *msgp = dest;
+	size_t msgsz;
+
+	if (put_user(msg->m_type, &msgp->mtype))
+		return -EFAULT;
+
+	msgsz = (bufsz > msg->m_ts) ? msg->m_ts : bufsz;
+	if (store_msg(msgp->mtext, msg, msgsz))
+		return -EFAULT;
+	return msgsz;
+}
+
+#ifdef CONFIG_CHECKPOINT_RESTORE
+/*
+ * This function creates new kernel message structure, large enough to store
+ * bufsz message bytes.
+ */
+static inline struct msg_msg *prepare_copy(void __user *buf, size_t bufsz)
+{
+	struct msg_msg *copy;
+
+	/*
+	 * Create dummy message to copy real message to.
+	 */
+	copy = load_msg(buf, bufsz);
+	if (!IS_ERR(copy))
+		copy->m_ts = bufsz;
+	return copy;
+}
+
+static inline void free_copy(struct msg_msg *copy)
+{
+	if (copy)
+		free_msg(copy);
+}
+#else
+static inline struct msg_msg *prepare_copy(void __user *buf, size_t bufsz)
+{
+	return ERR_PTR(-ENOSYS);
+}
+
+static inline void free_copy(struct msg_msg *copy)
+{
+}
+#endif
+
+static struct msg_msg *find_msg(struct msg_queue *msq, long *msgtyp, int mode)
+{
+	struct msg_msg *msg, *found = NULL;
+	long count = 0;
+
+	list_for_each_entry(msg, &msq->q_messages, m_list) {
+		if (testmsg(msg, *msgtyp, mode) &&
+		    !security_msg_queue_msgrcv(msq, msg, current,
+					       *msgtyp, mode)) {
+			if (mode == SEARCH_LESSEQUAL && msg->m_type != 1) {
+				*msgtyp = msg->m_type - 1;
+				found = msg;
+			} else if (mode == SEARCH_NUMBER) {
+				if (*msgtyp == count)
+					return msg;
+			} else
+				return msg;
+			count++;
+		}
+	}
+
+	return found ?: ERR_PTR(-EAGAIN);
+}
+
+long do_msgrcv(int msqid, void __user *buf, size_t bufsz, long msgtyp, int msgflg,
+	       long (*msg_handler)(void __user *, struct msg_msg *, size_t))
+{
+	int mode;
+	struct msg_queue *msq;
+	struct ipc_namespace *ns;
+	struct msg_msg *msg, *copy = NULL;
+
+	ns = current->nsproxy->ipc_ns;
+
+	if (msqid < 0 || (long) bufsz < 0)
+		return -EINVAL;
+
+	if (msgflg & MSG_COPY) {
+		if ((msgflg & MSG_EXCEPT) || !(msgflg & IPC_NOWAIT))
+			return -EINVAL;
+		copy = prepare_copy(buf, min_t(size_t, bufsz, ns->msg_ctlmax));
+		if (IS_ERR(copy))
+			return PTR_ERR(copy);
+	}
+	mode = convert_mode(&msgtyp, msgflg);
+
+	rcu_read_lock();
+	msq = msq_obtain_object_check(ns, msqid);
+	if (IS_ERR(msq)) {
+		rcu_read_unlock();
+		free_copy(copy);
+		return PTR_ERR(msq);
+	}
+
+	for (;;) {
+		struct msg_receiver msr_d;
+
+		msg = ERR_PTR(-EACCES);
+		if (ipcperms(ns, &msq->q_perm, S_IRUGO))
+			goto out_unlock1;
+
+		ipc_lock_object(&msq->q_perm);
+
+		/* raced with RMID? */
+		if (!ipc_valid_object(&msq->q_perm)) {
+			msg = ERR_PTR(-EIDRM);
+			goto out_unlock0;
+		}
+
+		msg = find_msg(msq, &msgtyp, mode);
+		if (!IS_ERR(msg)) {
+			/*
+			 * Found a suitable message.
+			 * Unlink it from the queue.
+			 */
+			if ((bufsz < msg->m_ts) && !(msgflg & MSG_NOERROR)) {
+				msg = ERR_PTR(-E2BIG);
+				goto out_unlock0;
+			}
+			/*
+			 * If we are copying, then do not unlink message and do
+			 * not update queue parameters.
+			 */
+			if (msgflg & MSG_COPY) {
+				msg = copy_msg(msg, copy);
+				goto out_unlock0;
+			}
+
+			list_del(&msg->m_list);
+			msq->q_qnum--;
+			msq->q_rtime = get_seconds();
+			msq->q_lrpid = task_tgid_vnr(current);
+			msq->q_cbytes -= msg->m_ts;
+			atomic_sub(msg->m_ts, &ns->msg_bytes);
+			atomic_dec(&ns->msg_hdrs);
+			ss_wakeup(&msq->q_senders, 0);
+
+			goto out_unlock0;
+		}
+
+		/* No message waiting. Wait for a message */
+		if (msgflg & IPC_NOWAIT) {
+			msg = ERR_PTR(-ENOMSG);
+			goto out_unlock0;
+		}
+
+		list_add_tail(&msr_d.r_list, &msq->q_receivers);
+		msr_d.r_tsk = current;
+		msr_d.r_msgtype = msgtyp;
+		msr_d.r_mode = mode;
+		if (msgflg & MSG_NOERROR)
+			msr_d.r_maxsize = INT_MAX;
+		else
+			msr_d.r_maxsize = bufsz;
+		msr_d.r_msg = ERR_PTR(-EAGAIN);
+		__set_current_state(TASK_INTERRUPTIBLE);
+
+		ipc_unlock_object(&msq->q_perm);
+		rcu_read_unlock();
+		schedule();
+
+		/* Lockless receive, part 1:
+		 * Disable preemption.  We don't hold a reference to the queue
+		 * and getting a reference would defeat the idea of a lockless
+		 * operation, thus the code relies on rcu to guarantee the
+		 * existence of msq:
+		 * Prior to destruction, expunge_all(-EIRDM) changes r_msg.
+		 * Thus if r_msg is -EAGAIN, then the queue not yet destroyed.
+		 * rcu_read_lock() prevents preemption between reading r_msg
+		 * and acquiring the q_perm.lock in ipc_lock_object().
+		 */
+		rcu_read_lock();
+
+		/* Lockless receive, part 2:
+		 * Wait until pipelined_send or expunge_all are outside of
+		 * wake_up_process(). There is a race with exit(), see
+		 * ipc/mqueue.c for the details.
+		 */
+		msg = (struct msg_msg *)msr_d.r_msg;
+		while (msg == NULL) {
+			cpu_relax();
+			msg = (struct msg_msg *)msr_d.r_msg;
+		}
+
+		/* Lockless receive, part 3:
+		 * If there is a message or an error then accept it without
+		 * locking.
+		 */
+		if (msg != ERR_PTR(-EAGAIN))
+			goto out_unlock1;
+
+		/* Lockless receive, part 3:
+		 * Acquire the queue spinlock.
+		 */
+		ipc_lock_object(&msq->q_perm);
+
+		/* Lockless receive, part 4:
+		 * Repeat test after acquiring the spinlock.
+		 */
+		msg = (struct msg_msg *)msr_d.r_msg;
+		if (msg != ERR_PTR(-EAGAIN))
+			goto out_unlock0;
+
+		list_del(&msr_d.r_list);
+		if (signal_pending(current)) {
+			msg = ERR_PTR(-ERESTARTNOHAND);
+			goto out_unlock0;
+		}
+
+		ipc_unlock_object(&msq->q_perm);
+	}
+
+out_unlock0:
+	ipc_unlock_object(&msq->q_perm);
+out_unlock1:
+	rcu_read_unlock();
+	if (IS_ERR(msg)) {
+		free_copy(copy);
+		return PTR_ERR(msg);
+	}
+
+	bufsz = msg_handler(buf, msg, bufsz);
+	free_msg(msg);
+
+	return bufsz;
+}
+
+SYSCALL_DEFINE5(msgrcv, int, msqid, struct msgbuf __user *, msgp, size_t, msgsz,
+		long, msgtyp, int, msgflg)
+{
+	return do_msgrcv(msqid, msgp, msgsz, msgtyp, msgflg, do_msg_fill);
+}
+
+
+void msg_init_ns(struct ipc_namespace *ns)
+{
+	ns->msg_ctlmax = MSGMAX;
+	ns->msg_ctlmnb = MSGMNB;
+	ns->msg_ctlmni = MSGMNI;
+
+	atomic_set(&ns->msg_bytes, 0);
+	atomic_set(&ns->msg_hdrs, 0);
+	ipc_init_ids(&ns->ids[IPC_MSG_IDS]);
+}
+
+#ifdef CONFIG_IPC_NS
+void msg_exit_ns(struct ipc_namespace *ns)
+{
+	free_ipcs(ns, &msg_ids(ns), freeque);
+	idr_destroy(&ns->ids[IPC_MSG_IDS].ipcs_idr);
+}
+#endif
+
+#ifdef CONFIG_PROC_FS
+static int sysvipc_msg_proc_show(struct seq_file *s, void *it)
+{
+	struct user_namespace *user_ns = seq_user_ns(s);
+	struct msg_queue *msq = it;
+
+	seq_printf(s,
+		   "%10d %10d  %4o  %10lu %10lu %5u %5u %5u %5u %5u %5u %10lu %10lu %10lu\n",
+		   msq->q_perm.key,
+		   msq->q_perm.id,
+		   msq->q_perm.mode,
+		   msq->q_cbytes,
+		   msq->q_qnum,
+		   msq->q_lspid,
+		   msq->q_lrpid,
+		   from_kuid_munged(user_ns, msq->q_perm.uid),
+		   from_kgid_munged(user_ns, msq->q_perm.gid),
+		   from_kuid_munged(user_ns, msq->q_perm.cuid),
+		   from_kgid_munged(user_ns, msq->q_perm.cgid),
+		   msq->q_stime,
+		   msq->q_rtime,
+		   msq->q_ctime);
+
+	return 0;
+}
+#endif
+
+void __init msg_init(void)
+{
+	msg_init_ns(&init_ipc_ns);
+
+	ipc_init_proc_interface("sysvipc/msg",
+				"       key      msqid perms      cbytes       qnum lspid lrpid   uid   gid  cuid  cgid      stime      rtime      ctime\n",
+				IPC_MSG_IDS, sysvipc_msg_proc_show);
+}
diff --git a/kernel/ipc/msgutil.c b/kernel/ipc/msgutil.c
new file mode 100644
index 000000000..2b491590e
--- /dev/null
+++ b/kernel/ipc/msgutil.c
@@ -0,0 +1,185 @@
+/*
+ * linux/ipc/msgutil.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 <linux/msg.h>
+#include <linux/ipc_namespace.h>
+#include <linux/utsname.h>
+#include <linux/proc_ns.h>
+#include <linux/uaccess.h>
+
+#include "util.h"
+
+DEFINE_SPINLOCK(mq_lock);
+
+/*
+ * The next 2 defines are here bc this is the only file
+ * compiled when either CONFIG_SYSVIPC and CONFIG_POSIX_MQUEUE
+ * and not CONFIG_IPC_NS.
+ */
+struct ipc_namespace init_ipc_ns = {
+	.count		= ATOMIC_INIT(1),
+	.user_ns = &init_user_ns,
+	.ns.inum = PROC_IPC_INIT_INO,
+#ifdef CONFIG_IPC_NS
+	.ns.ops = &ipcns_operations,
+#endif
+};
+
+atomic_t nr_ipc_ns = ATOMIC_INIT(1);
+
+struct msg_msgseg {
+	struct msg_msgseg *next;
+	/* the next part of the message follows immediately */
+};
+
+#define DATALEN_MSG	((size_t)PAGE_SIZE-sizeof(struct msg_msg))
+#define DATALEN_SEG	((size_t)PAGE_SIZE-sizeof(struct msg_msgseg))
+
+
+static struct msg_msg *alloc_msg(size_t len)
+{
+	struct msg_msg *msg;
+	struct msg_msgseg **pseg;
+	size_t alen;
+
+	alen = min(len, DATALEN_MSG);
+	msg = kmalloc(sizeof(*msg) + alen, GFP_KERNEL);
+	if (msg == NULL)
+		return NULL;
+
+	msg->next = NULL;
+	msg->security = NULL;
+
+	len -= alen;
+	pseg = &msg->next;
+	while (len > 0) {
+		struct msg_msgseg *seg;
+		alen = min(len, DATALEN_SEG);
+		seg = kmalloc(sizeof(*seg) + alen, GFP_KERNEL);
+		if (seg == NULL)
+			goto out_err;
+		*pseg = seg;
+		seg->next = NULL;
+		pseg = &seg->next;
+		len -= alen;
+	}
+
+	return msg;
+
+out_err:
+	free_msg(msg);
+	return NULL;
+}
+
+struct msg_msg *load_msg(const void __user *src, size_t len)
+{
+	struct msg_msg *msg;
+	struct msg_msgseg *seg;
+	int err = -EFAULT;
+	size_t alen;
+
+	msg = alloc_msg(len);
+	if (msg == NULL)
+		return ERR_PTR(-ENOMEM);
+
+	alen = min(len, DATALEN_MSG);
+	if (copy_from_user(msg + 1, src, alen))
+		goto out_err;
+
+	for (seg = msg->next; seg != NULL; seg = seg->next) {
+		len -= alen;
+		src = (char __user *)src + alen;
+		alen = min(len, DATALEN_SEG);
+		if (copy_from_user(seg + 1, src, alen))
+			goto out_err;
+	}
+
+	err = security_msg_msg_alloc(msg);
+	if (err)
+		goto out_err;
+
+	return msg;
+
+out_err:
+	free_msg(msg);
+	return ERR_PTR(err);
+}
+#ifdef CONFIG_CHECKPOINT_RESTORE
+struct msg_msg *copy_msg(struct msg_msg *src, struct msg_msg *dst)
+{
+	struct msg_msgseg *dst_pseg, *src_pseg;
+	size_t len = src->m_ts;
+	size_t alen;
+
+	BUG_ON(dst == NULL);
+	if (src->m_ts > dst->m_ts)
+		return ERR_PTR(-EINVAL);
+
+	alen = min(len, DATALEN_MSG);
+	memcpy(dst + 1, src + 1, alen);
+
+	for (dst_pseg = dst->next, src_pseg = src->next;
+	     src_pseg != NULL;
+	     dst_pseg = dst_pseg->next, src_pseg = src_pseg->next) {
+
+		len -= alen;
+		alen = min(len, DATALEN_SEG);
+		memcpy(dst_pseg + 1, src_pseg + 1, alen);
+	}
+
+	dst->m_type = src->m_type;
+	dst->m_ts = src->m_ts;
+
+	return dst;
+}
+#else
+struct msg_msg *copy_msg(struct msg_msg *src, struct msg_msg *dst)
+{
+	return ERR_PTR(-ENOSYS);
+}
+#endif
+int store_msg(void __user *dest, struct msg_msg *msg, size_t len)
+{
+	size_t alen;
+	struct msg_msgseg *seg;
+
+	alen = min(len, DATALEN_MSG);
+	if (copy_to_user(dest, msg + 1, alen))
+		return -1;
+
+	for (seg = msg->next; seg != NULL; seg = seg->next) {
+		len -= alen;
+		dest = (char __user *)dest + alen;
+		alen = min(len, DATALEN_SEG);
+		if (copy_to_user(dest, seg + 1, alen))
+			return -1;
+	}
+	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/kernel/ipc/namespace.c b/kernel/ipc/namespace.c
new file mode 100644
index 000000000..068caf18d
--- /dev/null
+++ b/kernel/ipc/namespace.c
@@ -0,0 +1,175 @@
+/*
+ * linux/ipc/namespace.c
+ * Copyright (C) 2006 Pavel Emelyanov <xemul@openvz.org> OpenVZ, SWsoft Inc.
+ */
+
+#include <linux/ipc.h>
+#include <linux/msg.h>
+#include <linux/ipc_namespace.h>
+#include <linux/rcupdate.h>
+#include <linux/nsproxy.h>
+#include <linux/slab.h>
+#include <linux/fs.h>
+#include <linux/mount.h>
+#include <linux/user_namespace.h>
+#include <linux/proc_ns.h>
+
+#include "util.h"
+
+static struct ipc_namespace *create_ipc_ns(struct user_namespace *user_ns,
+					   struct ipc_namespace *old_ns)
+{
+	struct ipc_namespace *ns;
+	int err;
+
+	ns = kmalloc(sizeof(struct ipc_namespace), GFP_KERNEL);
+	if (ns == NULL)
+		return ERR_PTR(-ENOMEM);
+
+	err = ns_alloc_inum(&ns->ns);
+	if (err) {
+		kfree(ns);
+		return ERR_PTR(err);
+	}
+	ns->ns.ops = &ipcns_operations;
+
+	atomic_set(&ns->count, 1);
+	err = mq_init_ns(ns);
+	if (err) {
+		ns_free_inum(&ns->ns);
+		kfree(ns);
+		return ERR_PTR(err);
+	}
+	atomic_inc(&nr_ipc_ns);
+
+	sem_init_ns(ns);
+	msg_init_ns(ns);
+	shm_init_ns(ns);
+
+	ns->user_ns = get_user_ns(user_ns);
+
+	return ns;
+}
+
+struct ipc_namespace *copy_ipcs(unsigned long flags,
+	struct user_namespace *user_ns, struct ipc_namespace *ns)
+{
+	if (!(flags & CLONE_NEWIPC))
+		return get_ipc_ns(ns);
+	return create_ipc_ns(user_ns, ns);
+}
+
+/*
+ * free_ipcs - free all ipcs of one type
+ * @ns:   the namespace to remove the ipcs from
+ * @ids:  the table of ipcs to free
+ * @free: the function called to free each individual ipc
+ *
+ * Called for each kind of ipc when an ipc_namespace exits.
+ */
+void free_ipcs(struct ipc_namespace *ns, struct ipc_ids *ids,
+	       void (*free)(struct ipc_namespace *, struct kern_ipc_perm *))
+{
+	struct kern_ipc_perm *perm;
+	int next_id;
+	int total, in_use;
+
+	down_write(&ids->rwsem);
+
+	in_use = ids->in_use;
+
+	for (total = 0, next_id = 0; total < in_use; next_id++) {
+		perm = idr_find(&ids->ipcs_idr, next_id);
+		if (perm == NULL)
+			continue;
+		rcu_read_lock();
+		ipc_lock_object(perm);
+		free(ns, perm);
+		total++;
+	}
+	up_write(&ids->rwsem);
+}
+
+static void free_ipc_ns(struct ipc_namespace *ns)
+{
+	sem_exit_ns(ns);
+	msg_exit_ns(ns);
+	shm_exit_ns(ns);
+	atomic_dec(&nr_ipc_ns);
+
+	put_user_ns(ns->user_ns);
+	ns_free_inum(&ns->ns);
+	kfree(ns);
+}
+
+/*
+ * put_ipc_ns - drop a reference to an ipc namespace.
+ * @ns: the namespace to put
+ *
+ * If this is the last task in the namespace exiting, and
+ * it is dropping the refcount to 0, then it can race with
+ * a task in another ipc namespace but in a mounts namespace
+ * which has this ipcns's mqueuefs mounted, doing some action
+ * with one of the mqueuefs files.  That can raise the refcount.
+ * So dropping the refcount, and raising the refcount when
+ * accessing it through the VFS, are protected with mq_lock.
+ *
+ * (Clearly, a task raising the refcount on its own ipc_ns
+ * needn't take mq_lock since it can't race with the last task
+ * in the ipcns exiting).
+ */
+void put_ipc_ns(struct ipc_namespace *ns)
+{
+	if (atomic_dec_and_lock(&ns->count, &mq_lock)) {
+		mq_clear_sbinfo(ns);
+		spin_unlock(&mq_lock);
+		mq_put_mnt(ns);
+		free_ipc_ns(ns);
+	}
+}
+
+static inline struct ipc_namespace *to_ipc_ns(struct ns_common *ns)
+{
+	return container_of(ns, struct ipc_namespace, ns);
+}
+
+static struct ns_common *ipcns_get(struct task_struct *task)
+{
+	struct ipc_namespace *ns = NULL;
+	struct nsproxy *nsproxy;
+
+	task_lock(task);
+	nsproxy = task->nsproxy;
+	if (nsproxy)
+		ns = get_ipc_ns(nsproxy->ipc_ns);
+	task_unlock(task);
+
+	return ns ? &ns->ns : NULL;
+}
+
+static void ipcns_put(struct ns_common *ns)
+{
+	return put_ipc_ns(to_ipc_ns(ns));
+}
+
+static int ipcns_install(struct nsproxy *nsproxy, struct ns_common *new)
+{
+	struct ipc_namespace *ns = to_ipc_ns(new);
+	if (!ns_capable(ns->user_ns, CAP_SYS_ADMIN) ||
+	    !ns_capable(current_user_ns(), CAP_SYS_ADMIN))
+		return -EPERM;
+
+	/* Ditch state from the old ipc namespace */
+	exit_sem(current);
+	put_ipc_ns(nsproxy->ipc_ns);
+	nsproxy->ipc_ns = get_ipc_ns(ns);
+	return 0;
+}
+
+const struct proc_ns_operations ipcns_operations = {
+	.name		= "ipc",
+	.type		= CLONE_NEWIPC,
+	.get		= ipcns_get,
+	.put		= ipcns_put,
+	.install	= ipcns_install,
+};
diff --git a/kernel/ipc/sem.c b/kernel/ipc/sem.c
new file mode 100644
index 000000000..8f99bac19
--- /dev/null
+++ b/kernel/ipc/sem.c
@@ -0,0 +1,2198 @@
+/*
+ * linux/ipc/sem.c
+ * Copyright (C) 1992 Krishna Balasubramanian
+ * Copyright (C) 1995 Eric Schenk, Bruno Haible
+ *
+ * /proc/sysvipc/sem support (c) 1999 Dragos Acostachioaie <dragos@iname.com>
+ *
+ * SMP-threaded, sysctl's added
+ * (c) 1999 Manfred Spraul <manfred@colorfullife.com>
+ * Enforced range limit on SEM_UNDO
+ * (c) 2001 Red Hat Inc
+ * Lockless wakeup
+ * (c) 2003 Manfred Spraul <manfred@colorfullife.com>
+ * Further wakeup optimizations, documentation
+ * (c) 2010 Manfred Spraul <manfred@colorfullife.com>
+ *
+ * support for audit of ipc object properties and permission changes
+ * Dustin Kirkland <dustin.kirkland@us.ibm.com>
+ *
+ * namespaces support
+ * OpenVZ, SWsoft Inc.
+ * Pavel Emelianov <xemul@openvz.org>
+ *
+ * Implementation notes: (May 2010)
+ * This file implements System V semaphores.
+ *
+ * User space visible behavior:
+ * - FIFO ordering for semop() operations (just FIFO, not starvation
+ *   protection)
+ * - multiple semaphore operations that alter the same semaphore in
+ *   one semop() are handled.
+ * - sem_ctime (time of last semctl()) is updated in the IPC_SET, SETVAL and
+ *   SETALL calls.
+ * - two Linux specific semctl() commands: SEM_STAT, SEM_INFO.
+ * - undo adjustments at process exit are limited to 0..SEMVMX.
+ * - namespace are supported.
+ * - SEMMSL, SEMMNS, SEMOPM and SEMMNI can be configured at runtine by writing
+ *   to /proc/sys/kernel/sem.
+ * - statistics about the usage are reported in /proc/sysvipc/sem.
+ *
+ * Internals:
+ * - scalability:
+ *   - all global variables are read-mostly.
+ *   - semop() calls and semctl(RMID) are synchronized by RCU.
+ *   - most operations do write operations (actually: spin_lock calls) to
+ *     the per-semaphore array structure.
+ *   Thus: Perfect SMP scaling between independent semaphore arrays.
+ *         If multiple semaphores in one array are used, then cache line
+ *         trashing on the semaphore array spinlock will limit the scaling.
+ * - semncnt and semzcnt are calculated on demand in count_semcnt()
+ * - the task that performs a successful semop() scans the list of all
+ *   sleeping tasks and completes any pending operations that can be fulfilled.
+ *   Semaphores are actively given to waiting tasks (necessary for FIFO).
+ *   (see update_queue())
+ * - To improve the scalability, the actual wake-up calls are performed after
+ *   dropping all locks. (see wake_up_sem_queue_prepare(),
+ *   wake_up_sem_queue_do())
+ * - All work is done by the waker, the woken up task does not have to do
+ *   anything - not even acquiring a lock or dropping a refcount.
+ * - A woken up task may not even touch the semaphore array anymore, it may
+ *   have been destroyed already by a semctl(RMID).
+ * - The synchronizations between wake-ups due to a timeout/signal and a
+ *   wake-up due to a completed semaphore operation is achieved by using an
+ *   intermediate state (IN_WAKEUP).
+ * - UNDO values are stored in an array (one per process and per
+ *   semaphore array, lazily allocated). For backwards compatibility, multiple
+ *   modes for the UNDO variables are supported (per process, per thread)
+ *   (see copy_semundo, CLONE_SYSVSEM)
+ * - There are two lists of the pending operations: a per-array list
+ *   and per-semaphore list (stored in the array). This allows to achieve FIFO
+ *   ordering without always scanning all pending operations.
+ *   The worst-case behavior is nevertheless O(N^2) for N wakeups.
+ */
+
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/init.h>
+#include <linux/proc_fs.h>
+#include <linux/time.h>
+#include <linux/security.h>
+#include <linux/syscalls.h>
+#include <linux/audit.h>
+#include <linux/capability.h>
+#include <linux/seq_file.h>
+#include <linux/rwsem.h>
+#include <linux/nsproxy.h>
+#include <linux/ipc_namespace.h>
+
+#include <linux/uaccess.h>
+#include "util.h"
+
+/* One semaphore structure for each semaphore in the system. */
+struct sem {
+	int	semval;		/* current value */
+	int	sempid;		/* pid of last operation */
+	spinlock_t	lock;	/* spinlock for fine-grained semtimedop */
+	struct list_head pending_alter; /* pending single-sop operations */
+					/* that alter the semaphore */
+	struct list_head pending_const; /* pending single-sop operations */
+					/* that do not alter the semaphore*/
+	time_t	sem_otime;	/* candidate for sem_otime */
+} ____cacheline_aligned_in_smp;
+
+/* One queue for each sleeping process in the system. */
+struct sem_queue {
+	struct list_head	list;	 /* queue of pending operations */
+	struct task_struct	*sleeper; /* this process */
+	struct sem_undo		*undo;	 /* undo structure */
+	int			pid;	 /* process id of requesting process */
+	int			status;	 /* completion status of operation */
+	struct sembuf		*sops;	 /* array of pending operations */
+	struct sembuf		*blocking; /* the operation that blocked */
+	int			nsops;	 /* number of operations */
+	int			alter;	 /* does *sops alter the array? */
+};
+
+/* Each task has a list of undo requests. They are executed automatically
+ * when the process exits.
+ */
+struct sem_undo {
+	struct list_head	list_proc;	/* per-process list: *
+						 * all undos from one process
+						 * rcu protected */
+	struct rcu_head		rcu;		/* rcu struct for sem_undo */
+	struct sem_undo_list	*ulp;		/* back ptr to sem_undo_list */
+	struct list_head	list_id;	/* per semaphore array list:
+						 * all undos for one array */
+	int			semid;		/* semaphore set identifier */
+	short			*semadj;	/* array of adjustments */
+						/* one per semaphore */
+};
+
+/* sem_undo_list controls shared access to the list of sem_undo structures
+ * that may be shared among all a CLONE_SYSVSEM task group.
+ */
+struct sem_undo_list {
+	atomic_t		refcnt;
+	spinlock_t		lock;
+	struct list_head	list_proc;
+};
+
+
+#define sem_ids(ns)	((ns)->ids[IPC_SEM_IDS])
+
+#define sem_checkid(sma, semid)	ipc_checkid(&sma->sem_perm, semid)
+
+static int newary(struct ipc_namespace *, struct ipc_params *);
+static void freeary(struct ipc_namespace *, struct kern_ipc_perm *);
+#ifdef CONFIG_PROC_FS
+static int sysvipc_sem_proc_show(struct seq_file *s, void *it);
+#endif
+
+#define SEMMSL_FAST	256 /* 512 bytes on stack */
+#define SEMOPM_FAST	64  /* ~ 372 bytes on stack */
+
+/*
+ * Locking:
+ *	sem_undo.id_next,
+ *	sem_array.complex_count,
+ *	sem_array.pending{_alter,_cont},
+ *	sem_array.sem_undo: global sem_lock() for read/write
+ *	sem_undo.proc_next: only "current" is allowed to read/write that field.
+ *
+ *	sem_array.sem_base[i].pending_{const,alter}:
+ *		global or semaphore sem_lock() for read/write
+ */
+
+#define sc_semmsl	sem_ctls[0]
+#define sc_semmns	sem_ctls[1]
+#define sc_semopm	sem_ctls[2]
+#define sc_semmni	sem_ctls[3]
+
+void sem_init_ns(struct ipc_namespace *ns)
+{
+	ns->sc_semmsl = SEMMSL;
+	ns->sc_semmns = SEMMNS;
+	ns->sc_semopm = SEMOPM;
+	ns->sc_semmni = SEMMNI;
+	ns->used_sems = 0;
+	ipc_init_ids(&ns->ids[IPC_SEM_IDS]);
+}
+
+#ifdef CONFIG_IPC_NS
+void sem_exit_ns(struct ipc_namespace *ns)
+{
+	free_ipcs(ns, &sem_ids(ns), freeary);
+	idr_destroy(&ns->ids[IPC_SEM_IDS].ipcs_idr);
+}
+#endif
+
+void __init sem_init(void)
+{
+	sem_init_ns(&init_ipc_ns);
+	ipc_init_proc_interface("sysvipc/sem",
+				"       key      semid perms      nsems   uid   gid  cuid  cgid      otime      ctime\n",
+				IPC_SEM_IDS, sysvipc_sem_proc_show);
+}
+
+/**
+ * unmerge_queues - unmerge queues, if possible.
+ * @sma: semaphore array
+ *
+ * The function unmerges the wait queues if complex_count is 0.
+ * It must be called prior to dropping the global semaphore array lock.
+ */
+static void unmerge_queues(struct sem_array *sma)
+{
+	struct sem_queue *q, *tq;
+
+	/* complex operations still around? */
+	if (sma->complex_count)
+		return;
+	/*
+	 * We will switch back to simple mode.
+	 * Move all pending operation back into the per-semaphore
+	 * queues.
+	 */
+	list_for_each_entry_safe(q, tq, &sma->pending_alter, list) {
+		struct sem *curr;
+		curr = &sma->sem_base[q->sops[0].sem_num];
+
+		list_add_tail(&q->list, &curr->pending_alter);
+	}
+	INIT_LIST_HEAD(&sma->pending_alter);
+}
+
+/**
+ * merge_queues - merge single semop queues into global queue
+ * @sma: semaphore array
+ *
+ * This function merges all per-semaphore queues into the global queue.
+ * It is necessary to achieve FIFO ordering for the pending single-sop
+ * operations when a multi-semop operation must sleep.
+ * Only the alter operations must be moved, the const operations can stay.
+ */
+static void merge_queues(struct sem_array *sma)
+{
+	int i;
+	for (i = 0; i < sma->sem_nsems; i++) {
+		struct sem *sem = sma->sem_base + i;
+
+		list_splice_init(&sem->pending_alter, &sma->pending_alter);
+	}
+}
+
+static void sem_rcu_free(struct rcu_head *head)
+{
+	struct ipc_rcu *p = container_of(head, struct ipc_rcu, rcu);
+	struct sem_array *sma = ipc_rcu_to_struct(p);
+
+	security_sem_free(sma);
+	ipc_rcu_free(head);
+}
+
+/*
+ * Wait until all currently ongoing simple ops have completed.
+ * Caller must own sem_perm.lock.
+ * New simple ops cannot start, because simple ops first check
+ * that sem_perm.lock is free.
+ * that a) sem_perm.lock is free and b) complex_count is 0.
+ */
+static void sem_wait_array(struct sem_array *sma)
+{
+	int i;
+	struct sem *sem;
+
+	if (sma->complex_count)  {
+		/* The thread that increased sma->complex_count waited on
+		 * all sem->lock locks. Thus we don't need to wait again.
+		 */
+		return;
+	}
+
+	for (i = 0; i < sma->sem_nsems; i++) {
+		sem = sma->sem_base + i;
+		spin_unlock_wait(&sem->lock);
+	}
+}
+
+/*
+ * If the request contains only one semaphore operation, and there are
+ * no complex transactions pending, lock only the semaphore involved.
+ * Otherwise, lock the entire semaphore array, since we either have
+ * multiple semaphores in our own semops, or we need to look at
+ * semaphores from other pending complex operations.
+ */
+static inline int sem_lock(struct sem_array *sma, struct sembuf *sops,
+			      int nsops)
+{
+	struct sem *sem;
+
+	if (nsops != 1) {
+		/* Complex operation - acquire a full lock */
+		ipc_lock_object(&sma->sem_perm);
+
+		/* And wait until all simple ops that are processed
+		 * right now have dropped their locks.
+		 */
+		sem_wait_array(sma);
+		return -1;
+	}
+
+	/*
+	 * Only one semaphore affected - try to optimize locking.
+	 * The rules are:
+	 * - optimized locking is possible if no complex operation
+	 *   is either enqueued or processed right now.
+	 * - The test for enqueued complex ops is simple:
+	 *      sma->complex_count != 0
+	 * - Testing for complex ops that are processed right now is
+	 *   a bit more difficult. Complex ops acquire the full lock
+	 *   and first wait that the running simple ops have completed.
+	 *   (see above)
+	 *   Thus: If we own a simple lock and the global lock is free
+	 *	and complex_count is now 0, then it will stay 0 and
+	 *	thus just locking sem->lock is sufficient.
+	 */
+	sem = sma->sem_base + sops->sem_num;
+
+	if (sma->complex_count == 0) {
+		/*
+		 * It appears that no complex operation is around.
+		 * Acquire the per-semaphore lock.
+		 */
+		spin_lock(&sem->lock);
+
+		/* Then check that the global lock is free */
+		if (!spin_is_locked(&sma->sem_perm.lock)) {
+			/*
+			 * The ipc object lock check must be visible on all
+			 * cores before rechecking the complex count.  Otherwise
+			 * we can race with  another thread that does:
+			 *	complex_count++;
+			 *	spin_unlock(sem_perm.lock);
+			 */
+			smp_rmb();
+
+			/*
+			 * Now repeat the test of complex_count:
+			 * It can't change anymore until we drop sem->lock.
+			 * Thus: if is now 0, then it will stay 0.
+			 */
+			if (sma->complex_count == 0) {
+				/* fast path successful! */
+				return sops->sem_num;
+			}
+		}
+		spin_unlock(&sem->lock);
+	}
+
+	/* slow path: acquire the full lock */
+	ipc_lock_object(&sma->sem_perm);
+
+	if (sma->complex_count == 0) {
+		/* False alarm:
+		 * There is no complex operation, thus we can switch
+		 * back to the fast path.
+		 */
+		spin_lock(&sem->lock);
+		ipc_unlock_object(&sma->sem_perm);
+		return sops->sem_num;
+	} else {
+		/* Not a false alarm, thus complete the sequence for a
+		 * full lock.
+		 */
+		sem_wait_array(sma);
+		return -1;
+	}
+}
+
+static inline void sem_unlock(struct sem_array *sma, int locknum)
+{
+	if (locknum == -1) {
+		unmerge_queues(sma);
+		ipc_unlock_object(&sma->sem_perm);
+	} else {
+		struct sem *sem = sma->sem_base + locknum;
+		spin_unlock(&sem->lock);
+	}
+}
+
+/*
+ * sem_lock_(check_) routines are called in the paths where the rwsem
+ * is not held.
+ *
+ * The caller holds the RCU read lock.
+ */
+static inline struct sem_array *sem_obtain_lock(struct ipc_namespace *ns,
+			int id, struct sembuf *sops, int nsops, int *locknum)
+{
+	struct kern_ipc_perm *ipcp;
+	struct sem_array *sma;
+
+	ipcp = ipc_obtain_object(&sem_ids(ns), id);
+	if (IS_ERR(ipcp))
+		return ERR_CAST(ipcp);
+
+	sma = container_of(ipcp, struct sem_array, sem_perm);
+	*locknum = sem_lock(sma, sops, nsops);
+
+	/* ipc_rmid() may have already freed the ID while sem_lock
+	 * was spinning: verify that the structure is still valid
+	 */
+	if (ipc_valid_object(ipcp))
+		return container_of(ipcp, struct sem_array, sem_perm);
+
+	sem_unlock(sma, *locknum);
+	return ERR_PTR(-EINVAL);
+}
+
+static inline struct sem_array *sem_obtain_object(struct ipc_namespace *ns, int id)
+{
+	struct kern_ipc_perm *ipcp = ipc_obtain_object(&sem_ids(ns), id);
+
+	if (IS_ERR(ipcp))
+		return ERR_CAST(ipcp);
+
+	return container_of(ipcp, struct sem_array, sem_perm);
+}
+
+static inline struct sem_array *sem_obtain_object_check(struct ipc_namespace *ns,
+							int id)
+{
+	struct kern_ipc_perm *ipcp = ipc_obtain_object_check(&sem_ids(ns), id);
+
+	if (IS_ERR(ipcp))
+		return ERR_CAST(ipcp);
+
+	return container_of(ipcp, struct sem_array, sem_perm);
+}
+
+static inline void sem_lock_and_putref(struct sem_array *sma)
+{
+	sem_lock(sma, NULL, -1);
+	ipc_rcu_putref(sma, ipc_rcu_free);
+}
+
+static inline void sem_rmid(struct ipc_namespace *ns, struct sem_array *s)
+{
+	ipc_rmid(&sem_ids(ns), &s->sem_perm);
+}
+
+/*
+ * Lockless wakeup algorithm:
+ * Without the check/retry algorithm a lockless wakeup is possible:
+ * - queue.status is initialized to -EINTR before blocking.
+ * - wakeup is performed by
+ *	* unlinking the queue entry from the pending list
+ *	* setting queue.status to IN_WAKEUP
+ *	  This is the notification for the blocked thread that a
+ *	  result value is imminent.
+ *	* call wake_up_process
+ *	* set queue.status to the final value.
+ * - the previously blocked thread checks queue.status:
+ *	* if it's IN_WAKEUP, then it must wait until the value changes
+ *	* if it's not -EINTR, then the operation was completed by
+ *	  update_queue. semtimedop can return queue.status without
+ *	  performing any operation on the sem array.
+ *	* otherwise it must acquire the spinlock and check what's up.
+ *
+ * The two-stage algorithm is necessary to protect against the following
+ * races:
+ * - if queue.status is set after wake_up_process, then the woken up idle
+ *   thread could race forward and try (and fail) to acquire sma->lock
+ *   before update_queue had a chance to set queue.status
+ * - if queue.status is written before wake_up_process and if the
+ *   blocked process is woken up by a signal between writing
+ *   queue.status and the wake_up_process, then the woken up
+ *   process could return from semtimedop and die by calling
+ *   sys_exit before wake_up_process is called. Then wake_up_process
+ *   will oops, because the task structure is already invalid.
+ *   (yes, this happened on s390 with sysv msg).
+ *
+ */
+#define IN_WAKEUP	1
+
+/**
+ * newary - Create a new semaphore set
+ * @ns: namespace
+ * @params: ptr to the structure that contains key, semflg and nsems
+ *
+ * Called with sem_ids.rwsem held (as a writer)
+ */
+static int newary(struct ipc_namespace *ns, struct ipc_params *params)
+{
+	int id;
+	int retval;
+	struct sem_array *sma;
+	int size;
+	key_t key = params->key;
+	int nsems = params->u.nsems;
+	int semflg = params->flg;
+	int i;
+
+	if (!nsems)
+		return -EINVAL;
+	if (ns->used_sems + nsems > ns->sc_semmns)
+		return -ENOSPC;
+
+	size = sizeof(*sma) + nsems * sizeof(struct sem);
+	sma = ipc_rcu_alloc(size);
+	if (!sma)
+		return -ENOMEM;
+
+	memset(sma, 0, size);
+
+	sma->sem_perm.mode = (semflg & S_IRWXUGO);
+	sma->sem_perm.key = key;
+
+	sma->sem_perm.security = NULL;
+	retval = security_sem_alloc(sma);
+	if (retval) {
+		ipc_rcu_putref(sma, ipc_rcu_free);
+		return retval;
+	}
+
+	sma->sem_base = (struct sem *) &sma[1];
+
+	for (i = 0; i < nsems; i++) {
+		INIT_LIST_HEAD(&sma->sem_base[i].pending_alter);
+		INIT_LIST_HEAD(&sma->sem_base[i].pending_const);
+		spin_lock_init(&sma->sem_base[i].lock);
+	}
+
+	sma->complex_count = 0;
+	INIT_LIST_HEAD(&sma->pending_alter);
+	INIT_LIST_HEAD(&sma->pending_const);
+	INIT_LIST_HEAD(&sma->list_id);
+	sma->sem_nsems = nsems;
+	sma->sem_ctime = get_seconds();
+
+	id = ipc_addid(&sem_ids(ns), &sma->sem_perm, ns->sc_semmni);
+	if (id < 0) {
+		ipc_rcu_putref(sma, sem_rcu_free);
+		return id;
+	}
+	ns->used_sems += nsems;
+
+	sem_unlock(sma, -1);
+	rcu_read_unlock();
+
+	return sma->sem_perm.id;
+}
+
+
+/*
+ * Called with sem_ids.rwsem and ipcp locked.
+ */
+static inline int sem_security(struct kern_ipc_perm *ipcp, int semflg)
+{
+	struct sem_array *sma;
+
+	sma = container_of(ipcp, struct sem_array, sem_perm);
+	return security_sem_associate(sma, semflg);
+}
+
+/*
+ * Called with sem_ids.rwsem and ipcp locked.
+ */
+static inline int sem_more_checks(struct kern_ipc_perm *ipcp,
+				struct ipc_params *params)
+{
+	struct sem_array *sma;
+
+	sma = container_of(ipcp, struct sem_array, sem_perm);
+	if (params->u.nsems > sma->sem_nsems)
+		return -EINVAL;
+
+	return 0;
+}
+
+SYSCALL_DEFINE3(semget, key_t, key, int, nsems, int, semflg)
+{
+	struct ipc_namespace *ns;
+	static const struct ipc_ops sem_ops = {
+		.getnew = newary,
+		.associate = sem_security,
+		.more_checks = sem_more_checks,
+	};
+	struct ipc_params sem_params;
+
+	ns = current->nsproxy->ipc_ns;
+
+	if (nsems < 0 || nsems > ns->sc_semmsl)
+		return -EINVAL;
+
+	sem_params.key = key;
+	sem_params.flg = semflg;
+	sem_params.u.nsems = nsems;
+
+	return ipcget(ns, &sem_ids(ns), &sem_ops, &sem_params);
+}
+
+/**
+ * perform_atomic_semop - Perform (if possible) a semaphore operation
+ * @sma: semaphore array
+ * @q: struct sem_queue that describes the operation
+ *
+ * Returns 0 if the operation was possible.
+ * Returns 1 if the operation is impossible, the caller must sleep.
+ * Negative values are error codes.
+ */
+static int perform_atomic_semop(struct sem_array *sma, struct sem_queue *q)
+{
+	int result, sem_op, nsops, pid;
+	struct sembuf *sop;
+	struct sem *curr;
+	struct sembuf *sops;
+	struct sem_undo *un;
+
+	sops = q->sops;
+	nsops = q->nsops;
+	un = q->undo;
+
+	for (sop = sops; sop < sops + nsops; sop++) {
+		curr = sma->sem_base + sop->sem_num;
+		sem_op = sop->sem_op;
+		result = curr->semval;
+
+		if (!sem_op && result)
+			goto would_block;
+
+		result += sem_op;
+		if (result < 0)
+			goto would_block;
+		if (result > SEMVMX)
+			goto out_of_range;
+
+		if (sop->sem_flg & SEM_UNDO) {
+			int undo = un->semadj[sop->sem_num] - sem_op;
+			/* Exceeding the undo range is an error. */
+			if (undo < (-SEMAEM - 1) || undo > SEMAEM)
+				goto out_of_range;
+			un->semadj[sop->sem_num] = undo;
+		}
+
+		curr->semval = result;
+	}
+
+	sop--;
+	pid = q->pid;
+	while (sop >= sops) {
+		sma->sem_base[sop->sem_num].sempid = pid;
+		sop--;
+	}
+
+	return 0;
+
+out_of_range:
+	result = -ERANGE;
+	goto undo;
+
+would_block:
+	q->blocking = sop;
+
+	if (sop->sem_flg & IPC_NOWAIT)
+		result = -EAGAIN;
+	else
+		result = 1;
+
+undo:
+	sop--;
+	while (sop >= sops) {
+		sem_op = sop->sem_op;
+		sma->sem_base[sop->sem_num].semval -= sem_op;
+		if (sop->sem_flg & SEM_UNDO)
+			un->semadj[sop->sem_num] += sem_op;
+		sop--;
+	}
+
+	return result;
+}
+
+/** wake_up_sem_queue_prepare(q, error): Prepare wake-up
+ * @q: queue entry that must be signaled
+ * @error: Error value for the signal
+ *
+ * Prepare the wake-up of the queue entry q.
+ */
+static void wake_up_sem_queue_prepare(struct list_head *pt,
+				struct sem_queue *q, int error)
+{
+#ifdef CONFIG_PREEMPT_RT_BASE
+	struct task_struct *p = q->sleeper;
+	get_task_struct(p);
+	q->status = error;
+	wake_up_process(p);
+	put_task_struct(p);
+#else
+	if (list_empty(pt)) {
+		/*
+		 * Hold preempt off so that we don't get preempted and have the
+		 * wakee busy-wait until we're scheduled back on.
+		 */
+		preempt_disable();
+	}
+	q->status = IN_WAKEUP;
+	q->pid = error;
+
+	list_add_tail(&q->list, pt);
+#endif
+}
+
+/**
+ * wake_up_sem_queue_do - do the actual wake-up
+ * @pt: list of tasks to be woken up
+ *
+ * Do the actual wake-up.
+ * The function is called without any locks held, thus the semaphore array
+ * could be destroyed already and the tasks can disappear as soon as the
+ * status is set to the actual return code.
+ */
+static void wake_up_sem_queue_do(struct list_head *pt)
+{
+#ifndef CONFIG_PREEMPT_RT_BASE
+	struct sem_queue *q, *t;
+	int did_something;
+
+	did_something = !list_empty(pt);
+	list_for_each_entry_safe(q, t, pt, list) {
+		wake_up_process(q->sleeper);
+		/* q can disappear immediately after writing q->status. */
+		smp_wmb();
+		q->status = q->pid;
+	}
+	if (did_something)
+		preempt_enable();
+#endif
+}
+
+static void unlink_queue(struct sem_array *sma, struct sem_queue *q)
+{
+	list_del(&q->list);
+	if (q->nsops > 1)
+		sma->complex_count--;
+}
+
+/** check_restart(sma, q)
+ * @sma: semaphore array
+ * @q: the operation that just completed
+ *
+ * update_queue is O(N^2) when it restarts scanning the whole queue of
+ * waiting operations. Therefore this function checks if the restart is
+ * really necessary. It is called after a previously waiting operation
+ * modified the array.
+ * Note that wait-for-zero operations are handled without restart.
+ */
+static int check_restart(struct sem_array *sma, struct sem_queue *q)
+{
+	/* pending complex alter operations are too difficult to analyse */
+	if (!list_empty(&sma->pending_alter))
+		return 1;
+
+	/* we were a sleeping complex operation. Too difficult */
+	if (q->nsops > 1)
+		return 1;
+
+	/* It is impossible that someone waits for the new value:
+	 * - complex operations always restart.
+	 * - wait-for-zero are handled seperately.
+	 * - q is a previously sleeping simple operation that
+	 *   altered the array. It must be a decrement, because
+	 *   simple increments never sleep.
+	 * - If there are older (higher priority) decrements
+	 *   in the queue, then they have observed the original
+	 *   semval value and couldn't proceed. The operation
+	 *   decremented to value - thus they won't proceed either.
+	 */
+	return 0;
+}
+
+/**
+ * wake_const_ops - wake up non-alter tasks
+ * @sma: semaphore array.
+ * @semnum: semaphore that was modified.
+ * @pt: list head for the tasks that must be woken up.
+ *
+ * wake_const_ops must be called after a semaphore in a semaphore array
+ * was set to 0. If complex const operations are pending, wake_const_ops must
+ * be called with semnum = -1, as well as with the number of each modified
+ * semaphore.
+ * The tasks that must be woken up are added to @pt. The return code
+ * is stored in q->pid.
+ * The function returns 1 if at least one operation was completed successfully.
+ */
+static int wake_const_ops(struct sem_array *sma, int semnum,
+				struct list_head *pt)
+{
+	struct sem_queue *q;
+	struct list_head *walk;
+	struct list_head *pending_list;
+	int semop_completed = 0;
+
+	if (semnum == -1)
+		pending_list = &sma->pending_const;
+	else
+		pending_list = &sma->sem_base[semnum].pending_const;
+
+	walk = pending_list->next;
+	while (walk != pending_list) {
+		int error;
+
+		q = container_of(walk, struct sem_queue, list);
+		walk = walk->next;
+
+		error = perform_atomic_semop(sma, q);
+
+		if (error <= 0) {
+			/* operation completed, remove from queue & wakeup */
+
+			unlink_queue(sma, q);
+
+			wake_up_sem_queue_prepare(pt, q, error);
+			if (error == 0)
+				semop_completed = 1;
+		}
+	}
+	return semop_completed;
+}
+
+/**
+ * do_smart_wakeup_zero - wakeup all wait for zero tasks
+ * @sma: semaphore array
+ * @sops: operations that were performed
+ * @nsops: number of operations
+ * @pt: list head of the tasks that must be woken up.
+ *
+ * Checks all required queue for wait-for-zero operations, based
+ * on the actual changes that were performed on the semaphore array.
+ * The function returns 1 if at least one operation was completed successfully.
+ */
+static int do_smart_wakeup_zero(struct sem_array *sma, struct sembuf *sops,
+					int nsops, struct list_head *pt)
+{
+	int i;
+	int semop_completed = 0;
+	int got_zero = 0;
+
+	/* first: the per-semaphore queues, if known */
+	if (sops) {
+		for (i = 0; i < nsops; i++) {
+			int num = sops[i].sem_num;
+
+			if (sma->sem_base[num].semval == 0) {
+				got_zero = 1;
+				semop_completed |= wake_const_ops(sma, num, pt);
+			}
+		}
+	} else {
+		/*
+		 * No sops means modified semaphores not known.
+		 * Assume all were changed.
+		 */
+		for (i = 0; i < sma->sem_nsems; i++) {
+			if (sma->sem_base[i].semval == 0) {
+				got_zero = 1;
+				semop_completed |= wake_const_ops(sma, i, pt);
+			}
+		}
+	}
+	/*
+	 * If one of the modified semaphores got 0,
+	 * then check the global queue, too.
+	 */
+	if (got_zero)
+		semop_completed |= wake_const_ops(sma, -1, pt);
+
+	return semop_completed;
+}
+
+
+/**
+ * update_queue - look for tasks that can be completed.
+ * @sma: semaphore array.
+ * @semnum: semaphore that was modified.
+ * @pt: list head for the tasks that must be woken up.
+ *
+ * update_queue must be called after a semaphore in a semaphore array
+ * was modified. If multiple semaphores were modified, update_queue must
+ * be called with semnum = -1, as well as with the number of each modified
+ * semaphore.
+ * The tasks that must be woken up are added to @pt. The return code
+ * is stored in q->pid.
+ * The function internally checks if const operations can now succeed.
+ *
+ * The function return 1 if at least one semop was completed successfully.
+ */
+static int update_queue(struct sem_array *sma, int semnum, struct list_head *pt)
+{
+	struct sem_queue *q;
+	struct list_head *walk;
+	struct list_head *pending_list;
+	int semop_completed = 0;
+
+	if (semnum == -1)
+		pending_list = &sma->pending_alter;
+	else
+		pending_list = &sma->sem_base[semnum].pending_alter;
+
+again:
+	walk = pending_list->next;
+	while (walk != pending_list) {
+		int error, restart;
+
+		q = container_of(walk, struct sem_queue, list);
+		walk = walk->next;
+
+		/* If we are scanning the single sop, per-semaphore list of
+		 * one semaphore and that semaphore is 0, then it is not
+		 * necessary to scan further: simple increments
+		 * that affect only one entry succeed immediately and cannot
+		 * be in the  per semaphore pending queue, and decrements
+		 * cannot be successful if the value is already 0.
+		 */
+		if (semnum != -1 && sma->sem_base[semnum].semval == 0)
+			break;
+
+		error = perform_atomic_semop(sma, q);
+
+		/* Does q->sleeper still need to sleep? */
+		if (error > 0)
+			continue;
+
+		unlink_queue(sma, q);
+
+		if (error) {
+			restart = 0;
+		} else {
+			semop_completed = 1;
+			do_smart_wakeup_zero(sma, q->sops, q->nsops, pt);
+			restart = check_restart(sma, q);
+		}
+
+		wake_up_sem_queue_prepare(pt, q, error);
+		if (restart)
+			goto again;
+	}
+	return semop_completed;
+}
+
+/**
+ * set_semotime - set sem_otime
+ * @sma: semaphore array
+ * @sops: operations that modified the array, may be NULL
+ *
+ * sem_otime is replicated to avoid cache line trashing.
+ * This function sets one instance to the current time.
+ */
+static void set_semotime(struct sem_array *sma, struct sembuf *sops)
+{
+	if (sops == NULL) {
+		sma->sem_base[0].sem_otime = get_seconds();
+	} else {
+		sma->sem_base[sops[0].sem_num].sem_otime =
+							get_seconds();
+	}
+}
+
+/**
+ * do_smart_update - optimized update_queue
+ * @sma: semaphore array
+ * @sops: operations that were performed
+ * @nsops: number of operations
+ * @otime: force setting otime
+ * @pt: list head of the tasks that must be woken up.
+ *
+ * do_smart_update() does the required calls to update_queue and wakeup_zero,
+ * based on the actual changes that were performed on the semaphore array.
+ * Note that the function does not do the actual wake-up: the caller is
+ * responsible for calling wake_up_sem_queue_do(@pt).
+ * It is safe to perform this call after dropping all locks.
+ */
+static void do_smart_update(struct sem_array *sma, struct sembuf *sops, int nsops,
+			int otime, struct list_head *pt)
+{
+	int i;
+
+	otime |= do_smart_wakeup_zero(sma, sops, nsops, pt);
+
+	if (!list_empty(&sma->pending_alter)) {
+		/* semaphore array uses the global queue - just process it. */
+		otime |= update_queue(sma, -1, pt);
+	} else {
+		if (!sops) {
+			/*
+			 * No sops, thus the modified semaphores are not
+			 * known. Check all.
+			 */
+			for (i = 0; i < sma->sem_nsems; i++)
+				otime |= update_queue(sma, i, pt);
+		} else {
+			/*
+			 * Check the semaphores that were increased:
+			 * - No complex ops, thus all sleeping ops are
+			 *   decrease.
+			 * - if we decreased the value, then any sleeping
+			 *   semaphore ops wont be able to run: If the
+			 *   previous value was too small, then the new
+			 *   value will be too small, too.
+			 */
+			for (i = 0; i < nsops; i++) {
+				if (sops[i].sem_op > 0) {
+					otime |= update_queue(sma,
+							sops[i].sem_num, pt);
+				}
+			}
+		}
+	}
+	if (otime)
+		set_semotime(sma, sops);
+}
+
+/*
+ * check_qop: Test if a queued operation sleeps on the semaphore semnum
+ */
+static int check_qop(struct sem_array *sma, int semnum, struct sem_queue *q,
+			bool count_zero)
+{
+	struct sembuf *sop = q->blocking;
+
+	/*
+	 * Linux always (since 0.99.10) reported a task as sleeping on all
+	 * semaphores. This violates SUS, therefore it was changed to the
+	 * standard compliant behavior.
+	 * Give the administrators a chance to notice that an application
+	 * might misbehave because it relies on the Linux behavior.
+	 */
+	pr_info_once("semctl(GETNCNT/GETZCNT) is since 3.16 Single Unix Specification compliant.\n"
+			"The task %s (%d) triggered the difference, watch for misbehavior.\n",
+			current->comm, task_pid_nr(current));
+
+	if (sop->sem_num != semnum)
+		return 0;
+
+	if (count_zero && sop->sem_op == 0)
+		return 1;
+	if (!count_zero && sop->sem_op < 0)
+		return 1;
+
+	return 0;
+}
+
+/* The following counts are associated to each semaphore:
+ *   semncnt        number of tasks waiting on semval being nonzero
+ *   semzcnt        number of tasks waiting on semval being zero
+ *
+ * Per definition, a task waits only on the semaphore of the first semop
+ * that cannot proceed, even if additional operation would block, too.
+ */
+static int count_semcnt(struct sem_array *sma, ushort semnum,
+			bool count_zero)
+{
+	struct list_head *l;
+	struct sem_queue *q;
+	int semcnt;
+
+	semcnt = 0;
+	/* First: check the simple operations. They are easy to evaluate */
+	if (count_zero)
+		l = &sma->sem_base[semnum].pending_const;
+	else
+		l = &sma->sem_base[semnum].pending_alter;
+
+	list_for_each_entry(q, l, list) {
+		/* all task on a per-semaphore list sleep on exactly
+		 * that semaphore
+		 */
+		semcnt++;
+	}
+
+	/* Then: check the complex operations. */
+	list_for_each_entry(q, &sma->pending_alter, list) {
+		semcnt += check_qop(sma, semnum, q, count_zero);
+	}
+	if (count_zero) {
+		list_for_each_entry(q, &sma->pending_const, list) {
+			semcnt += check_qop(sma, semnum, q, count_zero);
+		}
+	}
+	return semcnt;
+}
+
+/* Free a semaphore set. freeary() is called with sem_ids.rwsem locked
+ * as a writer and the spinlock for this semaphore set hold. sem_ids.rwsem
+ * remains locked on exit.
+ */
+static void freeary(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp)
+{
+	struct sem_undo *un, *tu;
+	struct sem_queue *q, *tq;
+	struct sem_array *sma = container_of(ipcp, struct sem_array, sem_perm);
+	struct list_head tasks;
+	int i;
+
+	/* Free the existing undo structures for this semaphore set.  */
+	ipc_assert_locked_object(&sma->sem_perm);
+	list_for_each_entry_safe(un, tu, &sma->list_id, list_id) {
+		list_del(&un->list_id);
+		spin_lock(&un->ulp->lock);
+		un->semid = -1;
+		list_del_rcu(&un->list_proc);
+		spin_unlock(&un->ulp->lock);
+		kfree_rcu(un, rcu);
+	}
+
+	/* Wake up all pending processes and let them fail with EIDRM. */
+	INIT_LIST_HEAD(&tasks);
+	list_for_each_entry_safe(q, tq, &sma->pending_const, list) {
+		unlink_queue(sma, q);
+		wake_up_sem_queue_prepare(&tasks, q, -EIDRM);
+	}
+
+	list_for_each_entry_safe(q, tq, &sma->pending_alter, list) {
+		unlink_queue(sma, q);
+		wake_up_sem_queue_prepare(&tasks, q, -EIDRM);
+	}
+	for (i = 0; i < sma->sem_nsems; i++) {
+		struct sem *sem = sma->sem_base + i;
+		list_for_each_entry_safe(q, tq, &sem->pending_const, list) {
+			unlink_queue(sma, q);
+			wake_up_sem_queue_prepare(&tasks, q, -EIDRM);
+		}
+		list_for_each_entry_safe(q, tq, &sem->pending_alter, list) {
+			unlink_queue(sma, q);
+			wake_up_sem_queue_prepare(&tasks, q, -EIDRM);
+		}
+	}
+
+	/* Remove the semaphore set from the IDR */
+	sem_rmid(ns, sma);
+	sem_unlock(sma, -1);
+	rcu_read_unlock();
+
+	wake_up_sem_queue_do(&tasks);
+	ns->used_sems -= sma->sem_nsems;
+	ipc_rcu_putref(sma, sem_rcu_free);
+}
+
+static unsigned long copy_semid_to_user(void __user *buf, struct semid64_ds *in, int version)
+{
+	switch (version) {
+	case IPC_64:
+		return copy_to_user(buf, in, sizeof(*in));
+	case IPC_OLD:
+	    {
+		struct semid_ds out;
+
+		memset(&out, 0, sizeof(out));
+
+		ipc64_perm_to_ipc_perm(&in->sem_perm, &out.sem_perm);
+
+		out.sem_otime	= in->sem_otime;
+		out.sem_ctime	= in->sem_ctime;
+		out.sem_nsems	= in->sem_nsems;
+
+		return copy_to_user(buf, &out, sizeof(out));
+	    }
+	default:
+		return -EINVAL;
+	}
+}
+
+static time_t get_semotime(struct sem_array *sma)
+{
+	int i;
+	time_t res;
+
+	res = sma->sem_base[0].sem_otime;
+	for (i = 1; i < sma->sem_nsems; i++) {
+		time_t to = sma->sem_base[i].sem_otime;
+
+		if (to > res)
+			res = to;
+	}
+	return res;
+}
+
+static int semctl_nolock(struct ipc_namespace *ns, int semid,
+			 int cmd, int version, void __user *p)
+{
+	int err;
+	struct sem_array *sma;
+
+	switch (cmd) {
+	case IPC_INFO:
+	case SEM_INFO:
+	{
+		struct seminfo seminfo;
+		int max_id;
+
+		err = security_sem_semctl(NULL, cmd);
+		if (err)
+			return err;
+
+		memset(&seminfo, 0, sizeof(seminfo));
+		seminfo.semmni = ns->sc_semmni;
+		seminfo.semmns = ns->sc_semmns;
+		seminfo.semmsl = ns->sc_semmsl;
+		seminfo.semopm = ns->sc_semopm;
+		seminfo.semvmx = SEMVMX;
+		seminfo.semmnu = SEMMNU;
+		seminfo.semmap = SEMMAP;
+		seminfo.semume = SEMUME;
+		down_read(&sem_ids(ns).rwsem);
+		if (cmd == SEM_INFO) {
+			seminfo.semusz = sem_ids(ns).in_use;
+			seminfo.semaem = ns->used_sems;
+		} else {
+			seminfo.semusz = SEMUSZ;
+			seminfo.semaem = SEMAEM;
+		}
+		max_id = ipc_get_maxid(&sem_ids(ns));
+		up_read(&sem_ids(ns).rwsem);
+		if (copy_to_user(p, &seminfo, sizeof(struct seminfo)))
+			return -EFAULT;
+		return (max_id < 0) ? 0 : max_id;
+	}
+	case IPC_STAT:
+	case SEM_STAT:
+	{
+		struct semid64_ds tbuf;
+		int id = 0;
+
+		memset(&tbuf, 0, sizeof(tbuf));
+
+		rcu_read_lock();
+		if (cmd == SEM_STAT) {
+			sma = sem_obtain_object(ns, semid);
+			if (IS_ERR(sma)) {
+				err = PTR_ERR(sma);
+				goto out_unlock;
+			}
+			id = sma->sem_perm.id;
+		} else {
+			sma = sem_obtain_object_check(ns, semid);
+			if (IS_ERR(sma)) {
+				err = PTR_ERR(sma);
+				goto out_unlock;
+			}
+		}
+
+		err = -EACCES;
+		if (ipcperms(ns, &sma->sem_perm, S_IRUGO))
+			goto out_unlock;
+
+		err = security_sem_semctl(sma, cmd);
+		if (err)
+			goto out_unlock;
+
+		kernel_to_ipc64_perm(&sma->sem_perm, &tbuf.sem_perm);
+		tbuf.sem_otime = get_semotime(sma);
+		tbuf.sem_ctime = sma->sem_ctime;
+		tbuf.sem_nsems = sma->sem_nsems;
+		rcu_read_unlock();
+		if (copy_semid_to_user(p, &tbuf, version))
+			return -EFAULT;
+		return id;
+	}
+	default:
+		return -EINVAL;
+	}
+out_unlock:
+	rcu_read_unlock();
+	return err;
+}
+
+static int semctl_setval(struct ipc_namespace *ns, int semid, int semnum,
+		unsigned long arg)
+{
+	struct sem_undo *un;
+	struct sem_array *sma;
+	struct sem *curr;
+	int err;
+	struct list_head tasks;
+	int val;
+#if defined(CONFIG_64BIT) && defined(__BIG_ENDIAN)
+	/* big-endian 64bit */
+	val = arg >> 32;
+#else
+	/* 32bit or little-endian 64bit */
+	val = arg;
+#endif
+
+	if (val > SEMVMX || val < 0)
+		return -ERANGE;
+
+	INIT_LIST_HEAD(&tasks);
+
+	rcu_read_lock();
+	sma = sem_obtain_object_check(ns, semid);
+	if (IS_ERR(sma)) {
+		rcu_read_unlock();
+		return PTR_ERR(sma);
+	}
+
+	if (semnum < 0 || semnum >= sma->sem_nsems) {
+		rcu_read_unlock();
+		return -EINVAL;
+	}
+
+
+	if (ipcperms(ns, &sma->sem_perm, S_IWUGO)) {
+		rcu_read_unlock();
+		return -EACCES;
+	}
+
+	err = security_sem_semctl(sma, SETVAL);
+	if (err) {
+		rcu_read_unlock();
+		return -EACCES;
+	}
+
+	sem_lock(sma, NULL, -1);
+
+	if (!ipc_valid_object(&sma->sem_perm)) {
+		sem_unlock(sma, -1);
+		rcu_read_unlock();
+		return -EIDRM;
+	}
+
+	curr = &sma->sem_base[semnum];
+
+	ipc_assert_locked_object(&sma->sem_perm);
+	list_for_each_entry(un, &sma->list_id, list_id)
+		un->semadj[semnum] = 0;
+
+	curr->semval = val;
+	curr->sempid = task_tgid_vnr(current);
+	sma->sem_ctime = get_seconds();
+	/* maybe some queued-up processes were waiting for this */
+	do_smart_update(sma, NULL, 0, 0, &tasks);
+	sem_unlock(sma, -1);
+	rcu_read_unlock();
+	wake_up_sem_queue_do(&tasks);
+	return 0;
+}
+
+static int semctl_main(struct ipc_namespace *ns, int semid, int semnum,
+		int cmd, void __user *p)
+{
+	struct sem_array *sma;
+	struct sem *curr;
+	int err, nsems;
+	ushort fast_sem_io[SEMMSL_FAST];
+	ushort *sem_io = fast_sem_io;
+	struct list_head tasks;
+
+	INIT_LIST_HEAD(&tasks);
+
+	rcu_read_lock();
+	sma = sem_obtain_object_check(ns, semid);
+	if (IS_ERR(sma)) {
+		rcu_read_unlock();
+		return PTR_ERR(sma);
+	}
+
+	nsems = sma->sem_nsems;
+
+	err = -EACCES;
+	if (ipcperms(ns, &sma->sem_perm, cmd == SETALL ? S_IWUGO : S_IRUGO))
+		goto out_rcu_wakeup;
+
+	err = security_sem_semctl(sma, cmd);
+	if (err)
+		goto out_rcu_wakeup;
+
+	err = -EACCES;
+	switch (cmd) {
+	case GETALL:
+	{
+		ushort __user *array = p;
+		int i;
+
+		sem_lock(sma, NULL, -1);
+		if (!ipc_valid_object(&sma->sem_perm)) {
+			err = -EIDRM;
+			goto out_unlock;
+		}
+		if (nsems > SEMMSL_FAST) {
+			if (!ipc_rcu_getref(sma)) {
+				err = -EIDRM;
+				goto out_unlock;
+			}
+			sem_unlock(sma, -1);
+			rcu_read_unlock();
+			sem_io = ipc_alloc(sizeof(ushort)*nsems);
+			if (sem_io == NULL) {
+				ipc_rcu_putref(sma, ipc_rcu_free);
+				return -ENOMEM;
+			}
+
+			rcu_read_lock();
+			sem_lock_and_putref(sma);
+			if (!ipc_valid_object(&sma->sem_perm)) {
+				err = -EIDRM;
+				goto out_unlock;
+			}
+		}
+		for (i = 0; i < sma->sem_nsems; i++)
+			sem_io[i] = sma->sem_base[i].semval;
+		sem_unlock(sma, -1);
+		rcu_read_unlock();
+		err = 0;
+		if (copy_to_user(array, sem_io, nsems*sizeof(ushort)))
+			err = -EFAULT;
+		goto out_free;
+	}
+	case SETALL:
+	{
+		int i;
+		struct sem_undo *un;
+
+		if (!ipc_rcu_getref(sma)) {
+			err = -EIDRM;
+			goto out_rcu_wakeup;
+		}
+		rcu_read_unlock();
+
+		if (nsems > SEMMSL_FAST) {
+			sem_io = ipc_alloc(sizeof(ushort)*nsems);
+			if (sem_io == NULL) {
+				ipc_rcu_putref(sma, ipc_rcu_free);
+				return -ENOMEM;
+			}
+		}
+
+		if (copy_from_user(sem_io, p, nsems*sizeof(ushort))) {
+			ipc_rcu_putref(sma, ipc_rcu_free);
+			err = -EFAULT;
+			goto out_free;
+		}
+
+		for (i = 0; i < nsems; i++) {
+			if (sem_io[i] > SEMVMX) {
+				ipc_rcu_putref(sma, ipc_rcu_free);
+				err = -ERANGE;
+				goto out_free;
+			}
+		}
+		rcu_read_lock();
+		sem_lock_and_putref(sma);
+		if (!ipc_valid_object(&sma->sem_perm)) {
+			err = -EIDRM;
+			goto out_unlock;
+		}
+
+		for (i = 0; i < nsems; i++)
+			sma->sem_base[i].semval = sem_io[i];
+
+		ipc_assert_locked_object(&sma->sem_perm);
+		list_for_each_entry(un, &sma->list_id, list_id) {
+			for (i = 0; i < nsems; i++)
+				un->semadj[i] = 0;
+		}
+		sma->sem_ctime = get_seconds();
+		/* maybe some queued-up processes were waiting for this */
+		do_smart_update(sma, NULL, 0, 0, &tasks);
+		err = 0;
+		goto out_unlock;
+	}
+	/* GETVAL, GETPID, GETNCTN, GETZCNT: fall-through */
+	}
+	err = -EINVAL;
+	if (semnum < 0 || semnum >= nsems)
+		goto out_rcu_wakeup;
+
+	sem_lock(sma, NULL, -1);
+	if (!ipc_valid_object(&sma->sem_perm)) {
+		err = -EIDRM;
+		goto out_unlock;
+	}
+	curr = &sma->sem_base[semnum];
+
+	switch (cmd) {
+	case GETVAL:
+		err = curr->semval;
+		goto out_unlock;
+	case GETPID:
+		err = curr->sempid;
+		goto out_unlock;
+	case GETNCNT:
+		err = count_semcnt(sma, semnum, 0);
+		goto out_unlock;
+	case GETZCNT:
+		err = count_semcnt(sma, semnum, 1);
+		goto out_unlock;
+	}
+
+out_unlock:
+	sem_unlock(sma, -1);
+out_rcu_wakeup:
+	rcu_read_unlock();
+	wake_up_sem_queue_do(&tasks);
+out_free:
+	if (sem_io != fast_sem_io)
+		ipc_free(sem_io, sizeof(ushort)*nsems);
+	return err;
+}
+
+static inline unsigned long
+copy_semid_from_user(struct semid64_ds *out, void __user *buf, int version)
+{
+	switch (version) {
+	case IPC_64:
+		if (copy_from_user(out, buf, sizeof(*out)))
+			return -EFAULT;
+		return 0;
+	case IPC_OLD:
+	    {
+		struct semid_ds tbuf_old;
+
+		if (copy_from_user(&tbuf_old, buf, sizeof(tbuf_old)))
+			return -EFAULT;
+
+		out->sem_perm.uid	= tbuf_old.sem_perm.uid;
+		out->sem_perm.gid	= tbuf_old.sem_perm.gid;
+		out->sem_perm.mode	= tbuf_old.sem_perm.mode;
+
+		return 0;
+	    }
+	default:
+		return -EINVAL;
+	}
+}
+
+/*
+ * This function handles some semctl commands which require the rwsem
+ * to be held in write mode.
+ * NOTE: no locks must be held, the rwsem is taken inside this function.
+ */
+static int semctl_down(struct ipc_namespace *ns, int semid,
+		       int cmd, int version, void __user *p)
+{
+	struct sem_array *sma;
+	int err;
+	struct semid64_ds semid64;
+	struct kern_ipc_perm *ipcp;
+
+	if (cmd == IPC_SET) {
+		if (copy_semid_from_user(&semid64, p, version))
+			return -EFAULT;
+	}
+
+	down_write(&sem_ids(ns).rwsem);
+	rcu_read_lock();
+
+	ipcp = ipcctl_pre_down_nolock(ns, &sem_ids(ns), semid, cmd,
+				      &semid64.sem_perm, 0);
+	if (IS_ERR(ipcp)) {
+		err = PTR_ERR(ipcp);
+		goto out_unlock1;
+	}
+
+	sma = container_of(ipcp, struct sem_array, sem_perm);
+
+	err = security_sem_semctl(sma, cmd);
+	if (err)
+		goto out_unlock1;
+
+	switch (cmd) {
+	case IPC_RMID:
+		sem_lock(sma, NULL, -1);
+		/* freeary unlocks the ipc object and rcu */
+		freeary(ns, ipcp);
+		goto out_up;
+	case IPC_SET:
+		sem_lock(sma, NULL, -1);
+		err = ipc_update_perm(&semid64.sem_perm, ipcp);
+		if (err)
+			goto out_unlock0;
+		sma->sem_ctime = get_seconds();
+		break;
+	default:
+		err = -EINVAL;
+		goto out_unlock1;
+	}
+
+out_unlock0:
+	sem_unlock(sma, -1);
+out_unlock1:
+	rcu_read_unlock();
+out_up:
+	up_write(&sem_ids(ns).rwsem);
+	return err;
+}
+
+SYSCALL_DEFINE4(semctl, int, semid, int, semnum, int, cmd, unsigned long, arg)
+{
+	int version;
+	struct ipc_namespace *ns;
+	void __user *p = (void __user *)arg;
+
+	if (semid < 0)
+		return -EINVAL;
+
+	version = ipc_parse_version(&cmd);
+	ns = current->nsproxy->ipc_ns;
+
+	switch (cmd) {
+	case IPC_INFO:
+	case SEM_INFO:
+	case IPC_STAT:
+	case SEM_STAT:
+		return semctl_nolock(ns, semid, cmd, version, p);
+	case GETALL:
+	case GETVAL:
+	case GETPID:
+	case GETNCNT:
+	case GETZCNT:
+	case SETALL:
+		return semctl_main(ns, semid, semnum, cmd, p);
+	case SETVAL:
+		return semctl_setval(ns, semid, semnum, arg);
+	case IPC_RMID:
+	case IPC_SET:
+		return semctl_down(ns, semid, cmd, version, p);
+	default:
+		return -EINVAL;
+	}
+}
+
+/* If the task doesn't already have a undo_list, then allocate one
+ * here.  We guarantee there is only one thread using this undo list,
+ * and current is THE ONE
+ *
+ * If this allocation and assignment succeeds, but later
+ * portions of this code fail, there is no need to free the sem_undo_list.
+ * Just let it stay associated with the task, and it'll be freed later
+ * at exit time.
+ *
+ * This can block, so callers must hold no locks.
+ */
+static inline int get_undo_list(struct sem_undo_list **undo_listp)
+{
+	struct sem_undo_list *undo_list;
+
+	undo_list = current->sysvsem.undo_list;
+	if (!undo_list) {
+		undo_list = kzalloc(sizeof(*undo_list), GFP_KERNEL);
+		if (undo_list == NULL)
+			return -ENOMEM;
+		spin_lock_init(&undo_list->lock);
+		atomic_set(&undo_list->refcnt, 1);
+		INIT_LIST_HEAD(&undo_list->list_proc);
+
+		current->sysvsem.undo_list = undo_list;
+	}
+	*undo_listp = undo_list;
+	return 0;
+}
+
+static struct sem_undo *__lookup_undo(struct sem_undo_list *ulp, int semid)
+{
+	struct sem_undo *un;
+
+	list_for_each_entry_rcu(un, &ulp->list_proc, list_proc) {
+		if (un->semid == semid)
+			return un;
+	}
+	return NULL;
+}
+
+static struct sem_undo *lookup_undo(struct sem_undo_list *ulp, int semid)
+{
+	struct sem_undo *un;
+
+	assert_spin_locked(&ulp->lock);
+
+	un = __lookup_undo(ulp, semid);
+	if (un) {
+		list_del_rcu(&un->list_proc);
+		list_add_rcu(&un->list_proc, &ulp->list_proc);
+	}
+	return un;
+}
+
+/**
+ * find_alloc_undo - lookup (and if not present create) undo array
+ * @ns: namespace
+ * @semid: semaphore array id
+ *
+ * The function looks up (and if not present creates) the undo structure.
+ * The size of the undo structure depends on the size of the semaphore
+ * array, thus the alloc path is not that straightforward.
+ * Lifetime-rules: sem_undo is rcu-protected, on success, the function
+ * performs a rcu_read_lock().
+ */
+static struct sem_undo *find_alloc_undo(struct ipc_namespace *ns, int semid)
+{
+	struct sem_array *sma;
+	struct sem_undo_list *ulp;
+	struct sem_undo *un, *new;
+	int nsems, error;
+
+	error = get_undo_list(&ulp);
+	if (error)
+		return ERR_PTR(error);
+
+	rcu_read_lock();
+	spin_lock(&ulp->lock);
+	un = lookup_undo(ulp, semid);
+	spin_unlock(&ulp->lock);
+	if (likely(un != NULL))
+		goto out;
+
+	/* no undo structure around - allocate one. */
+	/* step 1: figure out the size of the semaphore array */
+	sma = sem_obtain_object_check(ns, semid);
+	if (IS_ERR(sma)) {
+		rcu_read_unlock();
+		return ERR_CAST(sma);
+	}
+
+	nsems = sma->sem_nsems;
+	if (!ipc_rcu_getref(sma)) {
+		rcu_read_unlock();
+		un = ERR_PTR(-EIDRM);
+		goto out;
+	}
+	rcu_read_unlock();
+
+	/* step 2: allocate new undo structure */
+	new = kzalloc(sizeof(struct sem_undo) + sizeof(short)*nsems, GFP_KERNEL);
+	if (!new) {
+		ipc_rcu_putref(sma, ipc_rcu_free);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	/* step 3: Acquire the lock on semaphore array */
+	rcu_read_lock();
+	sem_lock_and_putref(sma);
+	if (!ipc_valid_object(&sma->sem_perm)) {
+		sem_unlock(sma, -1);
+		rcu_read_unlock();
+		kfree(new);
+		un = ERR_PTR(-EIDRM);
+		goto out;
+	}
+	spin_lock(&ulp->lock);
+
+	/*
+	 * step 4: check for races: did someone else allocate the undo struct?
+	 */
+	un = lookup_undo(ulp, semid);
+	if (un) {
+		kfree(new);
+		goto success;
+	}
+	/* step 5: initialize & link new undo structure */
+	new->semadj = (short *) &new[1];
+	new->ulp = ulp;
+	new->semid = semid;
+	assert_spin_locked(&ulp->lock);
+	list_add_rcu(&new->list_proc, &ulp->list_proc);
+	ipc_assert_locked_object(&sma->sem_perm);
+	list_add(&new->list_id, &sma->list_id);
+	un = new;
+
+success:
+	spin_unlock(&ulp->lock);
+	sem_unlock(sma, -1);
+out:
+	return un;
+}
+
+
+/**
+ * get_queue_result - retrieve the result code from sem_queue
+ * @q: Pointer to queue structure
+ *
+ * Retrieve the return code from the pending queue. If IN_WAKEUP is found in
+ * q->status, then we must loop until the value is replaced with the final
+ * value: This may happen if a task is woken up by an unrelated event (e.g.
+ * signal) and in parallel the task is woken up by another task because it got
+ * the requested semaphores.
+ *
+ * The function can be called with or without holding the semaphore spinlock.
+ */
+static int get_queue_result(struct sem_queue *q)
+{
+	int error;
+
+	error = q->status;
+	while (unlikely(error == IN_WAKEUP)) {
+		cpu_relax();
+		error = q->status;
+	}
+
+	return error;
+}
+
+SYSCALL_DEFINE4(semtimedop, int, semid, struct sembuf __user *, tsops,
+		unsigned, nsops, const struct timespec __user *, timeout)
+{
+	int error = -EINVAL;
+	struct sem_array *sma;
+	struct sembuf fast_sops[SEMOPM_FAST];
+	struct sembuf *sops = fast_sops, *sop;
+	struct sem_undo *un;
+	int undos = 0, alter = 0, max, locknum;
+	struct sem_queue queue;
+	unsigned long jiffies_left = 0;
+	struct ipc_namespace *ns;
+	struct list_head tasks;
+
+	ns = current->nsproxy->ipc_ns;
+
+	if (nsops < 1 || semid < 0)
+		return -EINVAL;
+	if (nsops > ns->sc_semopm)
+		return -E2BIG;
+	if (nsops > SEMOPM_FAST) {
+		sops = kmalloc(sizeof(*sops)*nsops, GFP_KERNEL);
+		if (sops == NULL)
+			return -ENOMEM;
+	}
+	if (copy_from_user(sops, tsops, nsops * sizeof(*tsops))) {
+		error =  -EFAULT;
+		goto out_free;
+	}
+	if (timeout) {
+		struct timespec _timeout;
+		if (copy_from_user(&_timeout, timeout, sizeof(*timeout))) {
+			error = -EFAULT;
+			goto out_free;
+		}
+		if (_timeout.tv_sec < 0 || _timeout.tv_nsec < 0 ||
+			_timeout.tv_nsec >= 1000000000L) {
+			error = -EINVAL;
+			goto out_free;
+		}
+		jiffies_left = timespec_to_jiffies(&_timeout);
+	}
+	max = 0;
+	for (sop = sops; sop < sops + nsops; sop++) {
+		if (sop->sem_num >= max)
+			max = sop->sem_num;
+		if (sop->sem_flg & SEM_UNDO)
+			undos = 1;
+		if (sop->sem_op != 0)
+			alter = 1;
+	}
+
+	INIT_LIST_HEAD(&tasks);
+
+	if (undos) {
+		/* On success, find_alloc_undo takes the rcu_read_lock */
+		un = find_alloc_undo(ns, semid);
+		if (IS_ERR(un)) {
+			error = PTR_ERR(un);
+			goto out_free;
+		}
+	} else {
+		un = NULL;
+		rcu_read_lock();
+	}
+
+	sma = sem_obtain_object_check(ns, semid);
+	if (IS_ERR(sma)) {
+		rcu_read_unlock();
+		error = PTR_ERR(sma);
+		goto out_free;
+	}
+
+	error = -EFBIG;
+	if (max >= sma->sem_nsems)
+		goto out_rcu_wakeup;
+
+	error = -EACCES;
+	if (ipcperms(ns, &sma->sem_perm, alter ? S_IWUGO : S_IRUGO))
+		goto out_rcu_wakeup;
+
+	error = security_sem_semop(sma, sops, nsops, alter);
+	if (error)
+		goto out_rcu_wakeup;
+
+	error = -EIDRM;
+	locknum = sem_lock(sma, sops, nsops);
+	/*
+	 * We eventually might perform the following check in a lockless
+	 * fashion, considering ipc_valid_object() locking constraints.
+	 * If nsops == 1 and there is no contention for sem_perm.lock, then
+	 * only a per-semaphore lock is held and it's OK to proceed with the
+	 * check below. More details on the fine grained locking scheme
+	 * entangled here and why it's RMID race safe on comments at sem_lock()
+	 */
+	if (!ipc_valid_object(&sma->sem_perm))
+		goto out_unlock_free;
+	/*
+	 * semid identifiers are not unique - find_alloc_undo may have
+	 * allocated an undo structure, it was invalidated by an RMID
+	 * and now a new array with received the same id. Check and fail.
+	 * This case can be detected checking un->semid. The existence of
+	 * "un" itself is guaranteed by rcu.
+	 */
+	if (un && un->semid == -1)
+		goto out_unlock_free;
+
+	queue.sops = sops;
+	queue.nsops = nsops;
+	queue.undo = un;
+	queue.pid = task_tgid_vnr(current);
+	queue.alter = alter;
+
+	error = perform_atomic_semop(sma, &queue);
+	if (error == 0) {
+		/* If the operation was successful, then do
+		 * the required updates.
+		 */
+		if (alter)
+			do_smart_update(sma, sops, nsops, 1, &tasks);
+		else
+			set_semotime(sma, sops);
+	}
+	if (error <= 0)
+		goto out_unlock_free;
+
+	/* We need to sleep on this operation, so we put the current
+	 * task into the pending queue and go to sleep.
+	 */
+
+	if (nsops == 1) {
+		struct sem *curr;
+		curr = &sma->sem_base[sops->sem_num];
+
+		if (alter) {
+			if (sma->complex_count) {
+				list_add_tail(&queue.list,
+						&sma->pending_alter);
+			} else {
+
+				list_add_tail(&queue.list,
+						&curr->pending_alter);
+			}
+		} else {
+			list_add_tail(&queue.list, &curr->pending_const);
+		}
+	} else {
+		if (!sma->complex_count)
+			merge_queues(sma);
+
+		if (alter)
+			list_add_tail(&queue.list, &sma->pending_alter);
+		else
+			list_add_tail(&queue.list, &sma->pending_const);
+
+		sma->complex_count++;
+	}
+
+	queue.status = -EINTR;
+	queue.sleeper = current;
+
+sleep_again:
+	__set_current_state(TASK_INTERRUPTIBLE);
+	sem_unlock(sma, locknum);
+	rcu_read_unlock();
+
+	if (timeout)
+		jiffies_left = schedule_timeout(jiffies_left);
+	else
+		schedule();
+
+	error = get_queue_result(&queue);
+
+	if (error != -EINTR) {
+		/* fast path: update_queue already obtained all requested
+		 * resources.
+		 * Perform a smp_mb(): User space could assume that semop()
+		 * is a memory barrier: Without the mb(), the cpu could
+		 * speculatively read in user space stale data that was
+		 * overwritten by the previous owner of the semaphore.
+		 */
+		smp_mb();
+
+		goto out_free;
+	}
+
+	rcu_read_lock();
+	sma = sem_obtain_lock(ns, semid, sops, nsops, &locknum);
+
+	/*
+	 * Wait until it's guaranteed that no wakeup_sem_queue_do() is ongoing.
+	 */
+	error = get_queue_result(&queue);
+
+	/*
+	 * Array removed? If yes, leave without sem_unlock().
+	 */
+	if (IS_ERR(sma)) {
+		rcu_read_unlock();
+		goto out_free;
+	}
+
+
+	/*
+	 * If queue.status != -EINTR we are woken up by another process.
+	 * Leave without unlink_queue(), but with sem_unlock().
+	 */
+	if (error != -EINTR)
+		goto out_unlock_free;
+
+	/*
+	 * If an interrupt occurred we have to clean up the queue
+	 */
+	if (timeout && jiffies_left == 0)
+		error = -EAGAIN;
+
+	/*
+	 * If the wakeup was spurious, just retry
+	 */
+	if (error == -EINTR && !signal_pending(current))
+		goto sleep_again;
+
+	unlink_queue(sma, &queue);
+
+out_unlock_free:
+	sem_unlock(sma, locknum);
+out_rcu_wakeup:
+	rcu_read_unlock();
+	wake_up_sem_queue_do(&tasks);
+out_free:
+	if (sops != fast_sops)
+		kfree(sops);
+	return error;
+}
+
+SYSCALL_DEFINE3(semop, int, semid, struct sembuf __user *, tsops,
+		unsigned, nsops)
+{
+	return sys_semtimedop(semid, tsops, nsops, NULL);
+}
+
+/* If CLONE_SYSVSEM is set, establish sharing of SEM_UNDO state between
+ * parent and child tasks.
+ */
+
+int copy_semundo(unsigned long clone_flags, struct task_struct *tsk)
+{
+	struct sem_undo_list *undo_list;
+	int error;
+
+	if (clone_flags & CLONE_SYSVSEM) {
+		error = get_undo_list(&undo_list);
+		if (error)
+			return error;
+		atomic_inc(&undo_list->refcnt);
+		tsk->sysvsem.undo_list = undo_list;
+	} else
+		tsk->sysvsem.undo_list = NULL;
+
+	return 0;
+}
+
+/*
+ * add semadj values to semaphores, free undo structures.
+ * undo structures are not freed when semaphore arrays are destroyed
+ * so some of them may be out of date.
+ * IMPLEMENTATION NOTE: There is some confusion over whether the
+ * set of adjustments that needs to be done should be done in an atomic
+ * manner or not. That is, if we are attempting to decrement the semval
+ * should we queue up and wait until we can do so legally?
+ * The original implementation attempted to do this (queue and wait).
+ * The current implementation does not do so. The POSIX standard
+ * and SVID should be consulted to determine what behavior is mandated.
+ */
+void exit_sem(struct task_struct *tsk)
+{
+	struct sem_undo_list *ulp;
+
+	ulp = tsk->sysvsem.undo_list;
+	if (!ulp)
+		return;
+	tsk->sysvsem.undo_list = NULL;
+
+	if (!atomic_dec_and_test(&ulp->refcnt))
+		return;
+
+	for (;;) {
+		struct sem_array *sma;
+		struct sem_undo *un;
+		struct list_head tasks;
+		int semid, i;
+
+		rcu_read_lock();
+		un = list_entry_rcu(ulp->list_proc.next,
+				    struct sem_undo, list_proc);
+		if (&un->list_proc == &ulp->list_proc)
+			semid = -1;
+		 else
+			semid = un->semid;
+
+		if (semid == -1) {
+			rcu_read_unlock();
+			break;
+		}
+
+		sma = sem_obtain_object_check(tsk->nsproxy->ipc_ns, un->semid);
+		/* exit_sem raced with IPC_RMID, nothing to do */
+		if (IS_ERR(sma)) {
+			rcu_read_unlock();
+			continue;
+		}
+
+		sem_lock(sma, NULL, -1);
+		/* exit_sem raced with IPC_RMID, nothing to do */
+		if (!ipc_valid_object(&sma->sem_perm)) {
+			sem_unlock(sma, -1);
+			rcu_read_unlock();
+			continue;
+		}
+		un = __lookup_undo(ulp, semid);
+		if (un == NULL) {
+			/* exit_sem raced with IPC_RMID+semget() that created
+			 * exactly the same semid. Nothing to do.
+			 */
+			sem_unlock(sma, -1);
+			rcu_read_unlock();
+			continue;
+		}
+
+		/* remove un from the linked lists */
+		ipc_assert_locked_object(&sma->sem_perm);
+		list_del(&un->list_id);
+
+		spin_lock(&ulp->lock);
+		list_del_rcu(&un->list_proc);
+		spin_unlock(&ulp->lock);
+
+		/* perform adjustments registered in un */
+		for (i = 0; i < sma->sem_nsems; i++) {
+			struct sem *semaphore = &sma->sem_base[i];
+			if (un->semadj[i]) {
+				semaphore->semval += un->semadj[i];
+				/*
+				 * Range checks of the new semaphore value,
+				 * not defined by sus:
+				 * - Some unices ignore the undo entirely
+				 *   (e.g. HP UX 11i 11.22, Tru64 V5.1)
+				 * - some cap the value (e.g. FreeBSD caps
+				 *   at 0, but doesn't enforce SEMVMX)
+				 *
+				 * Linux caps the semaphore value, both at 0
+				 * and at SEMVMX.
+				 *
+				 *	Manfred <manfred@colorfullife.com>
+				 */
+				if (semaphore->semval < 0)
+					semaphore->semval = 0;
+				if (semaphore->semval > SEMVMX)
+					semaphore->semval = SEMVMX;
+				semaphore->sempid = task_tgid_vnr(current);
+			}
+		}
+		/* maybe some queued-up processes were waiting for this */
+		INIT_LIST_HEAD(&tasks);
+		do_smart_update(sma, NULL, 0, 1, &tasks);
+		sem_unlock(sma, -1);
+		rcu_read_unlock();
+		wake_up_sem_queue_do(&tasks);
+
+		kfree_rcu(un, rcu);
+	}
+	kfree(ulp);
+}
+
+#ifdef CONFIG_PROC_FS
+static int sysvipc_sem_proc_show(struct seq_file *s, void *it)
+{
+	struct user_namespace *user_ns = seq_user_ns(s);
+	struct sem_array *sma = it;
+	time_t sem_otime;
+
+	/*
+	 * The proc interface isn't aware of sem_lock(), it calls
+	 * ipc_lock_object() directly (in sysvipc_find_ipc).
+	 * In order to stay compatible with sem_lock(), we must wait until
+	 * all simple semop() calls have left their critical regions.
+	 */
+	sem_wait_array(sma);
+
+	sem_otime = get_semotime(sma);
+
+	seq_printf(s,
+		   "%10d %10d  %4o %10u %5u %5u %5u %5u %10lu %10lu\n",
+		   sma->sem_perm.key,
+		   sma->sem_perm.id,
+		   sma->sem_perm.mode,
+		   sma->sem_nsems,
+		   from_kuid_munged(user_ns, sma->sem_perm.uid),
+		   from_kgid_munged(user_ns, sma->sem_perm.gid),
+		   from_kuid_munged(user_ns, sma->sem_perm.cuid),
+		   from_kgid_munged(user_ns, sma->sem_perm.cgid),
+		   sem_otime,
+		   sma->sem_ctime);
+
+	return 0;
+}
+#endif
diff --git a/kernel/ipc/shm.c b/kernel/ipc/shm.c
new file mode 100644
index 000000000..6d767071c
--- /dev/null
+++ b/kernel/ipc/shm.c
@@ -0,0 +1,1368 @@
+/*
+ * linux/ipc/shm.c
+ * Copyright (C) 1992, 1993 Krishna Balasubramanian
+ *	 Many improvements/fixes by Bruno Haible.
+ * Replaced `struct shm_desc' by `struct vm_area_struct', July 1994.
+ * Fixed the shm swap deallocation (shm_unuse()), August 1998 Andrea Arcangeli.
+ *
+ * /proc/sysvipc/shm support (c) 1999 Dragos Acostachioaie <dragos@iname.com>
+ * BIGMEM support, Andrea Arcangeli <andrea@suse.de>
+ * SMP thread shm, Jean-Luc Boyard <jean-luc.boyard@siemens.fr>
+ * HIGHMEM support, Ingo Molnar <mingo@redhat.com>
+ * Make shmmax, shmall, shmmni sysctl'able, Christoph Rohland <cr@sap.com>
+ * Shared /dev/zero support, Kanoj Sarcar <kanoj@sgi.com>
+ * Move the mm functionality over to mm/shmem.c, Christoph Rohland <cr@sap.com>
+ *
+ * support for audit of ipc object properties and permission changes
+ * Dustin Kirkland <dustin.kirkland@us.ibm.com>
+ *
+ * namespaces support
+ * OpenVZ, SWsoft Inc.
+ * Pavel Emelianov <xemul@openvz.org>
+ *
+ * Better ipc lock (kern_ipc_perm.lock) handling
+ * Davidlohr Bueso <davidlohr.bueso@hp.com>, June 2013.
+ */
+
+#include <linux/slab.h>
+#include <linux/mm.h>
+#include <linux/hugetlb.h>
+#include <linux/shm.h>
+#include <linux/init.h>
+#include <linux/file.h>
+#include <linux/mman.h>
+#include <linux/shmem_fs.h>
+#include <linux/security.h>
+#include <linux/syscalls.h>
+#include <linux/audit.h>
+#include <linux/capability.h>
+#include <linux/ptrace.h>
+#include <linux/seq_file.h>
+#include <linux/rwsem.h>
+#include <linux/nsproxy.h>
+#include <linux/mount.h>
+#include <linux/ipc_namespace.h>
+
+#include <linux/uaccess.h>
+
+#include "util.h"
+
+struct shm_file_data {
+	int id;
+	struct ipc_namespace *ns;
+	struct file *file;
+	const struct vm_operations_struct *vm_ops;
+};
+
+#define shm_file_data(file) (*((struct shm_file_data **)&(file)->private_data))
+
+static const struct file_operations shm_file_operations;
+static const struct vm_operations_struct shm_vm_ops;
+
+#define shm_ids(ns)	((ns)->ids[IPC_SHM_IDS])
+
+#define shm_unlock(shp)			\
+	ipc_unlock(&(shp)->shm_perm)
+
+static int newseg(struct ipc_namespace *, struct ipc_params *);
+static void shm_open(struct vm_area_struct *vma);
+static void shm_close(struct vm_area_struct *vma);
+static void shm_destroy(struct ipc_namespace *ns, struct shmid_kernel *shp);
+#ifdef CONFIG_PROC_FS
+static int sysvipc_shm_proc_show(struct seq_file *s, void *it);
+#endif
+
+void shm_init_ns(struct ipc_namespace *ns)
+{
+	ns->shm_ctlmax = SHMMAX;
+	ns->shm_ctlall = SHMALL;
+	ns->shm_ctlmni = SHMMNI;
+	ns->shm_rmid_forced = 0;
+	ns->shm_tot = 0;
+	ipc_init_ids(&shm_ids(ns));
+}
+
+/*
+ * Called with shm_ids.rwsem (writer) and the shp structure locked.
+ * Only shm_ids.rwsem remains locked on exit.
+ */
+static void do_shm_rmid(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp)
+{
+	struct shmid_kernel *shp;
+	shp = container_of(ipcp, struct shmid_kernel, shm_perm);
+
+	if (shp->shm_nattch) {
+		shp->shm_perm.mode |= SHM_DEST;
+		/* Do not find it any more */
+		shp->shm_perm.key = IPC_PRIVATE;
+		shm_unlock(shp);
+	} else
+		shm_destroy(ns, shp);
+}
+
+#ifdef CONFIG_IPC_NS
+void shm_exit_ns(struct ipc_namespace *ns)
+{
+	free_ipcs(ns, &shm_ids(ns), do_shm_rmid);
+	idr_destroy(&ns->ids[IPC_SHM_IDS].ipcs_idr);
+}
+#endif
+
+static int __init ipc_ns_init(void)
+{
+	shm_init_ns(&init_ipc_ns);
+	return 0;
+}
+
+pure_initcall(ipc_ns_init);
+
+void __init shm_init(void)
+{
+	ipc_init_proc_interface("sysvipc/shm",
+#if BITS_PER_LONG <= 32
+				"       key      shmid perms       size  cpid  lpid nattch   uid   gid  cuid  cgid      atime      dtime      ctime        rss       swap\n",
+#else
+				"       key      shmid perms                  size  cpid  lpid nattch   uid   gid  cuid  cgid      atime      dtime      ctime                   rss                  swap\n",
+#endif
+				IPC_SHM_IDS, sysvipc_shm_proc_show);
+}
+
+static inline struct shmid_kernel *shm_obtain_object(struct ipc_namespace *ns, int id)
+{
+	struct kern_ipc_perm *ipcp = ipc_obtain_object(&shm_ids(ns), id);
+
+	if (IS_ERR(ipcp))
+		return ERR_CAST(ipcp);
+
+	return container_of(ipcp, struct shmid_kernel, shm_perm);
+}
+
+static inline struct shmid_kernel *shm_obtain_object_check(struct ipc_namespace *ns, int id)
+{
+	struct kern_ipc_perm *ipcp = ipc_obtain_object_check(&shm_ids(ns), id);
+
+	if (IS_ERR(ipcp))
+		return ERR_CAST(ipcp);
+
+	return container_of(ipcp, struct shmid_kernel, shm_perm);
+}
+
+/*
+ * shm_lock_(check_) routines are called in the paths where the rwsem
+ * is not necessarily held.
+ */
+static inline struct shmid_kernel *shm_lock(struct ipc_namespace *ns, int id)
+{
+	struct kern_ipc_perm *ipcp = ipc_lock(&shm_ids(ns), id);
+
+	if (IS_ERR(ipcp))
+		return (struct shmid_kernel *)ipcp;
+
+	return container_of(ipcp, struct shmid_kernel, shm_perm);
+}
+
+static inline void shm_lock_by_ptr(struct shmid_kernel *ipcp)
+{
+	rcu_read_lock();
+	ipc_lock_object(&ipcp->shm_perm);
+}
+
+static void shm_rcu_free(struct rcu_head *head)
+{
+	struct ipc_rcu *p = container_of(head, struct ipc_rcu, rcu);
+	struct shmid_kernel *shp = ipc_rcu_to_struct(p);
+
+	security_shm_free(shp);
+	ipc_rcu_free(head);
+}
+
+static inline void shm_rmid(struct ipc_namespace *ns, struct shmid_kernel *s)
+{
+	list_del(&s->shm_clist);
+	ipc_rmid(&shm_ids(ns), &s->shm_perm);
+}
+
+
+/* This is called by fork, once for every shm attach. */
+static void shm_open(struct vm_area_struct *vma)
+{
+	struct file *file = vma->vm_file;
+	struct shm_file_data *sfd = shm_file_data(file);
+	struct shmid_kernel *shp;
+
+	shp = shm_lock(sfd->ns, sfd->id);
+	BUG_ON(IS_ERR(shp));
+	shp->shm_atim = get_seconds();
+	shp->shm_lprid = task_tgid_vnr(current);
+	shp->shm_nattch++;
+	shm_unlock(shp);
+}
+
+/*
+ * shm_destroy - free the struct shmid_kernel
+ *
+ * @ns: namespace
+ * @shp: struct to free
+ *
+ * It has to be called with shp and shm_ids.rwsem (writer) locked,
+ * but returns with shp unlocked and freed.
+ */
+static void shm_destroy(struct ipc_namespace *ns, struct shmid_kernel *shp)
+{
+	struct file *shm_file;
+
+	shm_file = shp->shm_file;
+	shp->shm_file = NULL;
+	ns->shm_tot -= (shp->shm_segsz + PAGE_SIZE - 1) >> PAGE_SHIFT;
+	shm_rmid(ns, shp);
+	shm_unlock(shp);
+	if (!is_file_hugepages(shm_file))
+		shmem_lock(shm_file, 0, shp->mlock_user);
+	else if (shp->mlock_user)
+		user_shm_unlock(i_size_read(file_inode(shm_file)),
+				shp->mlock_user);
+	fput(shm_file);
+	ipc_rcu_putref(shp, shm_rcu_free);
+}
+
+/*
+ * shm_may_destroy - identifies whether shm segment should be destroyed now
+ *
+ * Returns true if and only if there are no active users of the segment and
+ * one of the following is true:
+ *
+ * 1) shmctl(id, IPC_RMID, NULL) was called for this shp
+ *
+ * 2) sysctl kernel.shm_rmid_forced is set to 1.
+ */
+static bool shm_may_destroy(struct ipc_namespace *ns, struct shmid_kernel *shp)
+{
+	return (shp->shm_nattch == 0) &&
+	       (ns->shm_rmid_forced ||
+		(shp->shm_perm.mode & SHM_DEST));
+}
+
+/*
+ * remove the attach descriptor vma.
+ * free memory for segment if it is marked destroyed.
+ * The descriptor has already been removed from the current->mm->mmap list
+ * and will later be kfree()d.
+ */
+static void shm_close(struct vm_area_struct *vma)
+{
+	struct file *file = vma->vm_file;
+	struct shm_file_data *sfd = shm_file_data(file);
+	struct shmid_kernel *shp;
+	struct ipc_namespace *ns = sfd->ns;
+
+	down_write(&shm_ids(ns).rwsem);
+	/* remove from the list of attaches of the shm segment */
+	shp = shm_lock(ns, sfd->id);
+	BUG_ON(IS_ERR(shp));
+	shp->shm_lprid = task_tgid_vnr(current);
+	shp->shm_dtim = get_seconds();
+	shp->shm_nattch--;
+	if (shm_may_destroy(ns, shp))
+		shm_destroy(ns, shp);
+	else
+		shm_unlock(shp);
+	up_write(&shm_ids(ns).rwsem);
+}
+
+/* Called with ns->shm_ids(ns).rwsem locked */
+static int shm_try_destroy_orphaned(int id, void *p, void *data)
+{
+	struct ipc_namespace *ns = data;
+	struct kern_ipc_perm *ipcp = p;
+	struct shmid_kernel *shp = container_of(ipcp, struct shmid_kernel, shm_perm);
+
+	/*
+	 * We want to destroy segments without users and with already
+	 * exit'ed originating process.
+	 *
+	 * As shp->* are changed under rwsem, it's safe to skip shp locking.
+	 */
+	if (shp->shm_creator != NULL)
+		return 0;
+
+	if (shm_may_destroy(ns, shp)) {
+		shm_lock_by_ptr(shp);
+		shm_destroy(ns, shp);
+	}
+	return 0;
+}
+
+void shm_destroy_orphaned(struct ipc_namespace *ns)
+{
+	down_write(&shm_ids(ns).rwsem);
+	if (shm_ids(ns).in_use)
+		idr_for_each(&shm_ids(ns).ipcs_idr, &shm_try_destroy_orphaned, ns);
+	up_write(&shm_ids(ns).rwsem);
+}
+
+/* Locking assumes this will only be called with task == current */
+void exit_shm(struct task_struct *task)
+{
+	struct ipc_namespace *ns = task->nsproxy->ipc_ns;
+	struct shmid_kernel *shp, *n;
+
+	if (list_empty(&task->sysvshm.shm_clist))
+		return;
+
+	/*
+	 * If kernel.shm_rmid_forced is not set then only keep track of
+	 * which shmids are orphaned, so that a later set of the sysctl
+	 * can clean them up.
+	 */
+	if (!ns->shm_rmid_forced) {
+		down_read(&shm_ids(ns).rwsem);
+		list_for_each_entry(shp, &task->sysvshm.shm_clist, shm_clist)
+			shp->shm_creator = NULL;
+		/*
+		 * Only under read lock but we are only called on current
+		 * so no entry on the list will be shared.
+		 */
+		list_del(&task->sysvshm.shm_clist);
+		up_read(&shm_ids(ns).rwsem);
+		return;
+	}
+
+	/*
+	 * Destroy all already created segments, that were not yet mapped,
+	 * and mark any mapped as orphan to cover the sysctl toggling.
+	 * Destroy is skipped if shm_may_destroy() returns false.
+	 */
+	down_write(&shm_ids(ns).rwsem);
+	list_for_each_entry_safe(shp, n, &task->sysvshm.shm_clist, shm_clist) {
+		shp->shm_creator = NULL;
+
+		if (shm_may_destroy(ns, shp)) {
+			shm_lock_by_ptr(shp);
+			shm_destroy(ns, shp);
+		}
+	}
+
+	/* Remove the list head from any segments still attached. */
+	list_del(&task->sysvshm.shm_clist);
+	up_write(&shm_ids(ns).rwsem);
+}
+
+static int shm_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+	struct file *file = vma->vm_file;
+	struct shm_file_data *sfd = shm_file_data(file);
+
+	return sfd->vm_ops->fault(vma, vmf);
+}
+
+#ifdef CONFIG_NUMA
+static int shm_set_policy(struct vm_area_struct *vma, struct mempolicy *new)
+{
+	struct file *file = vma->vm_file;
+	struct shm_file_data *sfd = shm_file_data(file);
+	int err = 0;
+	if (sfd->vm_ops->set_policy)
+		err = sfd->vm_ops->set_policy(vma, new);
+	return err;
+}
+
+static struct mempolicy *shm_get_policy(struct vm_area_struct *vma,
+					unsigned long addr)
+{
+	struct file *file = vma->vm_file;
+	struct shm_file_data *sfd = shm_file_data(file);
+	struct mempolicy *pol = NULL;
+
+	if (sfd->vm_ops->get_policy)
+		pol = sfd->vm_ops->get_policy(vma, addr);
+	else if (vma->vm_policy)
+		pol = vma->vm_policy;
+
+	return pol;
+}
+#endif
+
+static int shm_mmap(struct file *file, struct vm_area_struct *vma)
+{
+	struct shm_file_data *sfd = shm_file_data(file);
+	int ret;
+
+	ret = sfd->file->f_op->mmap(sfd->file, vma);
+	if (ret != 0)
+		return ret;
+	sfd->vm_ops = vma->vm_ops;
+#ifdef CONFIG_MMU
+	BUG_ON(!sfd->vm_ops->fault);
+#endif
+	vma->vm_ops = &shm_vm_ops;
+	shm_open(vma);
+
+	return ret;
+}
+
+static int shm_release(struct inode *ino, struct file *file)
+{
+	struct shm_file_data *sfd = shm_file_data(file);
+
+	put_ipc_ns(sfd->ns);
+	shm_file_data(file) = NULL;
+	kfree(sfd);
+	return 0;
+}
+
+static int shm_fsync(struct file *file, loff_t start, loff_t end, int datasync)
+{
+	struct shm_file_data *sfd = shm_file_data(file);
+
+	if (!sfd->file->f_op->fsync)
+		return -EINVAL;
+	return sfd->file->f_op->fsync(sfd->file, start, end, datasync);
+}
+
+static long shm_fallocate(struct file *file, int mode, loff_t offset,
+			  loff_t len)
+{
+	struct shm_file_data *sfd = shm_file_data(file);
+
+	if (!sfd->file->f_op->fallocate)
+		return -EOPNOTSUPP;
+	return sfd->file->f_op->fallocate(file, mode, offset, len);
+}
+
+static unsigned long shm_get_unmapped_area(struct file *file,
+	unsigned long addr, unsigned long len, unsigned long pgoff,
+	unsigned long flags)
+{
+	struct shm_file_data *sfd = shm_file_data(file);
+	return sfd->file->f_op->get_unmapped_area(sfd->file, addr, len,
+						pgoff, flags);
+}
+
+static const struct file_operations shm_file_operations = {
+	.mmap		= shm_mmap,
+	.fsync		= shm_fsync,
+	.release	= shm_release,
+#ifndef CONFIG_MMU
+	.get_unmapped_area	= shm_get_unmapped_area,
+#endif
+	.llseek		= noop_llseek,
+	.fallocate	= shm_fallocate,
+};
+
+static const struct file_operations shm_file_operations_huge = {
+	.mmap		= shm_mmap,
+	.fsync		= shm_fsync,
+	.release	= shm_release,
+	.get_unmapped_area	= shm_get_unmapped_area,
+	.llseek		= noop_llseek,
+	.fallocate	= shm_fallocate,
+};
+
+int is_file_shm_hugepages(struct file *file)
+{
+	return file->f_op == &shm_file_operations_huge;
+}
+
+static const struct vm_operations_struct shm_vm_ops = {
+	.open	= shm_open,	/* callback for a new vm-area open */
+	.close	= shm_close,	/* callback for when the vm-area is released */
+	.fault	= shm_fault,
+#if defined(CONFIG_NUMA)
+	.set_policy = shm_set_policy,
+	.get_policy = shm_get_policy,
+#endif
+};
+
+/**
+ * newseg - Create a new shared memory segment
+ * @ns: namespace
+ * @params: ptr to the structure that contains key, size and shmflg
+ *
+ * Called with shm_ids.rwsem held as a writer.
+ */
+static int newseg(struct ipc_namespace *ns, struct ipc_params *params)
+{
+	key_t key = params->key;
+	int shmflg = params->flg;
+	size_t size = params->u.size;
+	int error;
+	struct shmid_kernel *shp;
+	size_t numpages = (size + PAGE_SIZE - 1) >> PAGE_SHIFT;
+	struct file *file;
+	char name[13];
+	int id;
+	vm_flags_t acctflag = 0;
+
+	if (size < SHMMIN || size > ns->shm_ctlmax)
+		return -EINVAL;
+
+	if (numpages << PAGE_SHIFT < size)
+		return -ENOSPC;
+
+	if (ns->shm_tot + numpages < ns->shm_tot ||
+			ns->shm_tot + numpages > ns->shm_ctlall)
+		return -ENOSPC;
+
+	shp = ipc_rcu_alloc(sizeof(*shp));
+	if (!shp)
+		return -ENOMEM;
+
+	shp->shm_perm.key = key;
+	shp->shm_perm.mode = (shmflg & S_IRWXUGO);
+	shp->mlock_user = NULL;
+
+	shp->shm_perm.security = NULL;
+	error = security_shm_alloc(shp);
+	if (error) {
+		ipc_rcu_putref(shp, ipc_rcu_free);
+		return error;
+	}
+
+	sprintf(name, "SYSV%08x", key);
+	if (shmflg & SHM_HUGETLB) {
+		struct hstate *hs;
+		size_t hugesize;
+
+		hs = hstate_sizelog((shmflg >> SHM_HUGE_SHIFT) & SHM_HUGE_MASK);
+		if (!hs) {
+			error = -EINVAL;
+			goto no_file;
+		}
+		hugesize = ALIGN(size, huge_page_size(hs));
+
+		/* hugetlb_file_setup applies strict accounting */
+		if (shmflg & SHM_NORESERVE)
+			acctflag = VM_NORESERVE;
+		file = hugetlb_file_setup(name, hugesize, acctflag,
+				  &shp->mlock_user, HUGETLB_SHMFS_INODE,
+				(shmflg >> SHM_HUGE_SHIFT) & SHM_HUGE_MASK);
+	} else {
+		/*
+		 * Do not allow no accounting for OVERCOMMIT_NEVER, even
+		 * if it's asked for.
+		 */
+		if  ((shmflg & SHM_NORESERVE) &&
+				sysctl_overcommit_memory != OVERCOMMIT_NEVER)
+			acctflag = VM_NORESERVE;
+		file = shmem_file_setup(name, size, acctflag);
+	}
+	error = PTR_ERR(file);
+	if (IS_ERR(file))
+		goto no_file;
+
+	id = ipc_addid(&shm_ids(ns), &shp->shm_perm, ns->shm_ctlmni);
+	if (id < 0) {
+		error = id;
+		goto no_id;
+	}
+
+	shp->shm_cprid = task_tgid_vnr(current);
+	shp->shm_lprid = 0;
+	shp->shm_atim = shp->shm_dtim = 0;
+	shp->shm_ctim = get_seconds();
+	shp->shm_segsz = size;
+	shp->shm_nattch = 0;
+	shp->shm_file = file;
+	shp->shm_creator = current;
+	list_add(&shp->shm_clist, &current->sysvshm.shm_clist);
+
+	/*
+	 * shmid gets reported as "inode#" in /proc/pid/maps.
+	 * proc-ps tools use this. Changing this will break them.
+	 */
+	file_inode(file)->i_ino = shp->shm_perm.id;
+
+	ns->shm_tot += numpages;
+	error = shp->shm_perm.id;
+
+	ipc_unlock_object(&shp->shm_perm);
+	rcu_read_unlock();
+	return error;
+
+no_id:
+	if (is_file_hugepages(file) && shp->mlock_user)
+		user_shm_unlock(size, shp->mlock_user);
+	fput(file);
+no_file:
+	ipc_rcu_putref(shp, shm_rcu_free);
+	return error;
+}
+
+/*
+ * Called with shm_ids.rwsem and ipcp locked.
+ */
+static inline int shm_security(struct kern_ipc_perm *ipcp, int shmflg)
+{
+	struct shmid_kernel *shp;
+
+	shp = container_of(ipcp, struct shmid_kernel, shm_perm);
+	return security_shm_associate(shp, shmflg);
+}
+
+/*
+ * Called with shm_ids.rwsem and ipcp locked.
+ */
+static inline int shm_more_checks(struct kern_ipc_perm *ipcp,
+				struct ipc_params *params)
+{
+	struct shmid_kernel *shp;
+
+	shp = container_of(ipcp, struct shmid_kernel, shm_perm);
+	if (shp->shm_segsz < params->u.size)
+		return -EINVAL;
+
+	return 0;
+}
+
+SYSCALL_DEFINE3(shmget, key_t, key, size_t, size, int, shmflg)
+{
+	struct ipc_namespace *ns;
+	static const struct ipc_ops shm_ops = {
+		.getnew = newseg,
+		.associate = shm_security,
+		.more_checks = shm_more_checks,
+	};
+	struct ipc_params shm_params;
+
+	ns = current->nsproxy->ipc_ns;
+
+	shm_params.key = key;
+	shm_params.flg = shmflg;
+	shm_params.u.size = size;
+
+	return ipcget(ns, &shm_ids(ns), &shm_ops, &shm_params);
+}
+
+static inline unsigned long copy_shmid_to_user(void __user *buf, struct shmid64_ds *in, int version)
+{
+	switch (version) {
+	case IPC_64:
+		return copy_to_user(buf, in, sizeof(*in));
+	case IPC_OLD:
+	    {
+		struct shmid_ds out;
+
+		memset(&out, 0, sizeof(out));
+		ipc64_perm_to_ipc_perm(&in->shm_perm, &out.shm_perm);
+		out.shm_segsz	= in->shm_segsz;
+		out.shm_atime	= in->shm_atime;
+		out.shm_dtime	= in->shm_dtime;
+		out.shm_ctime	= in->shm_ctime;
+		out.shm_cpid	= in->shm_cpid;
+		out.shm_lpid	= in->shm_lpid;
+		out.shm_nattch	= in->shm_nattch;
+
+		return copy_to_user(buf, &out, sizeof(out));
+	    }
+	default:
+		return -EINVAL;
+	}
+}
+
+static inline unsigned long
+copy_shmid_from_user(struct shmid64_ds *out, void __user *buf, int version)
+{
+	switch (version) {
+	case IPC_64:
+		if (copy_from_user(out, buf, sizeof(*out)))
+			return -EFAULT;
+		return 0;
+	case IPC_OLD:
+	    {
+		struct shmid_ds tbuf_old;
+
+		if (copy_from_user(&tbuf_old, buf, sizeof(tbuf_old)))
+			return -EFAULT;
+
+		out->shm_perm.uid	= tbuf_old.shm_perm.uid;
+		out->shm_perm.gid	= tbuf_old.shm_perm.gid;
+		out->shm_perm.mode	= tbuf_old.shm_perm.mode;
+
+		return 0;
+	    }
+	default:
+		return -EINVAL;
+	}
+}
+
+static inline unsigned long copy_shminfo_to_user(void __user *buf, struct shminfo64 *in, int version)
+{
+	switch (version) {
+	case IPC_64:
+		return copy_to_user(buf, in, sizeof(*in));
+	case IPC_OLD:
+	    {
+		struct shminfo out;
+
+		if (in->shmmax > INT_MAX)
+			out.shmmax = INT_MAX;
+		else
+			out.shmmax = (int)in->shmmax;
+
+		out.shmmin	= in->shmmin;
+		out.shmmni	= in->shmmni;
+		out.shmseg	= in->shmseg;
+		out.shmall	= in->shmall;
+
+		return copy_to_user(buf, &out, sizeof(out));
+	    }
+	default:
+		return -EINVAL;
+	}
+}
+
+/*
+ * Calculate and add used RSS and swap pages of a shm.
+ * Called with shm_ids.rwsem held as a reader
+ */
+static void shm_add_rss_swap(struct shmid_kernel *shp,
+	unsigned long *rss_add, unsigned long *swp_add)
+{
+	struct inode *inode;
+
+	inode = file_inode(shp->shm_file);
+
+	if (is_file_hugepages(shp->shm_file)) {
+		struct address_space *mapping = inode->i_mapping;
+		struct hstate *h = hstate_file(shp->shm_file);
+		*rss_add += pages_per_huge_page(h) * mapping->nrpages;
+	} else {
+#ifdef CONFIG_SHMEM
+		struct shmem_inode_info *info = SHMEM_I(inode);
+		spin_lock(&info->lock);
+		*rss_add += inode->i_mapping->nrpages;
+		*swp_add += info->swapped;
+		spin_unlock(&info->lock);
+#else
+		*rss_add += inode->i_mapping->nrpages;
+#endif
+	}
+}
+
+/*
+ * Called with shm_ids.rwsem held as a reader
+ */
+static void shm_get_stat(struct ipc_namespace *ns, unsigned long *rss,
+		unsigned long *swp)
+{
+	int next_id;
+	int total, in_use;
+
+	*rss = 0;
+	*swp = 0;
+
+	in_use = shm_ids(ns).in_use;
+
+	for (total = 0, next_id = 0; total < in_use; next_id++) {
+		struct kern_ipc_perm *ipc;
+		struct shmid_kernel *shp;
+
+		ipc = idr_find(&shm_ids(ns).ipcs_idr, next_id);
+		if (ipc == NULL)
+			continue;
+		shp = container_of(ipc, struct shmid_kernel, shm_perm);
+
+		shm_add_rss_swap(shp, rss, swp);
+
+		total++;
+	}
+}
+
+/*
+ * This function handles some shmctl commands which require the rwsem
+ * to be held in write mode.
+ * NOTE: no locks must be held, the rwsem is taken inside this function.
+ */
+static int shmctl_down(struct ipc_namespace *ns, int shmid, int cmd,
+		       struct shmid_ds __user *buf, int version)
+{
+	struct kern_ipc_perm *ipcp;
+	struct shmid64_ds shmid64;
+	struct shmid_kernel *shp;
+	int err;
+
+	if (cmd == IPC_SET) {
+		if (copy_shmid_from_user(&shmid64, buf, version))
+			return -EFAULT;
+	}
+
+	down_write(&shm_ids(ns).rwsem);
+	rcu_read_lock();
+
+	ipcp = ipcctl_pre_down_nolock(ns, &shm_ids(ns), shmid, cmd,
+				      &shmid64.shm_perm, 0);
+	if (IS_ERR(ipcp)) {
+		err = PTR_ERR(ipcp);
+		goto out_unlock1;
+	}
+
+	shp = container_of(ipcp, struct shmid_kernel, shm_perm);
+
+	err = security_shm_shmctl(shp, cmd);
+	if (err)
+		goto out_unlock1;
+
+	switch (cmd) {
+	case IPC_RMID:
+		ipc_lock_object(&shp->shm_perm);
+		/* do_shm_rmid unlocks the ipc object and rcu */
+		do_shm_rmid(ns, ipcp);
+		goto out_up;
+	case IPC_SET:
+		ipc_lock_object(&shp->shm_perm);
+		err = ipc_update_perm(&shmid64.shm_perm, ipcp);
+		if (err)
+			goto out_unlock0;
+		shp->shm_ctim = get_seconds();
+		break;
+	default:
+		err = -EINVAL;
+		goto out_unlock1;
+	}
+
+out_unlock0:
+	ipc_unlock_object(&shp->shm_perm);
+out_unlock1:
+	rcu_read_unlock();
+out_up:
+	up_write(&shm_ids(ns).rwsem);
+	return err;
+}
+
+static int shmctl_nolock(struct ipc_namespace *ns, int shmid,
+			 int cmd, int version, void __user *buf)
+{
+	int err;
+	struct shmid_kernel *shp;
+
+	/* preliminary security checks for *_INFO */
+	if (cmd == IPC_INFO || cmd == SHM_INFO) {
+		err = security_shm_shmctl(NULL, cmd);
+		if (err)
+			return err;
+	}
+
+	switch (cmd) {
+	case IPC_INFO:
+	{
+		struct shminfo64 shminfo;
+
+		memset(&shminfo, 0, sizeof(shminfo));
+		shminfo.shmmni = shminfo.shmseg = ns->shm_ctlmni;
+		shminfo.shmmax = ns->shm_ctlmax;
+		shminfo.shmall = ns->shm_ctlall;
+
+		shminfo.shmmin = SHMMIN;
+		if (copy_shminfo_to_user(buf, &shminfo, version))
+			return -EFAULT;
+
+		down_read(&shm_ids(ns).rwsem);
+		err = ipc_get_maxid(&shm_ids(ns));
+		up_read(&shm_ids(ns).rwsem);
+
+		if (err < 0)
+			err = 0;
+		goto out;
+	}
+	case SHM_INFO:
+	{
+		struct shm_info shm_info;
+
+		memset(&shm_info, 0, sizeof(shm_info));
+		down_read(&shm_ids(ns).rwsem);
+		shm_info.used_ids = shm_ids(ns).in_use;
+		shm_get_stat(ns, &shm_info.shm_rss, &shm_info.shm_swp);
+		shm_info.shm_tot = ns->shm_tot;
+		shm_info.swap_attempts = 0;
+		shm_info.swap_successes = 0;
+		err = ipc_get_maxid(&shm_ids(ns));
+		up_read(&shm_ids(ns).rwsem);
+		if (copy_to_user(buf, &shm_info, sizeof(shm_info))) {
+			err = -EFAULT;
+			goto out;
+		}
+
+		err = err < 0 ? 0 : err;
+		goto out;
+	}
+	case SHM_STAT:
+	case IPC_STAT:
+	{
+		struct shmid64_ds tbuf;
+		int result;
+
+		rcu_read_lock();
+		if (cmd == SHM_STAT) {
+			shp = shm_obtain_object(ns, shmid);
+			if (IS_ERR(shp)) {
+				err = PTR_ERR(shp);
+				goto out_unlock;
+			}
+			result = shp->shm_perm.id;
+		} else {
+			shp = shm_obtain_object_check(ns, shmid);
+			if (IS_ERR(shp)) {
+				err = PTR_ERR(shp);
+				goto out_unlock;
+			}
+			result = 0;
+		}
+
+		err = -EACCES;
+		if (ipcperms(ns, &shp->shm_perm, S_IRUGO))
+			goto out_unlock;
+
+		err = security_shm_shmctl(shp, cmd);
+		if (err)
+			goto out_unlock;
+
+		memset(&tbuf, 0, sizeof(tbuf));
+		kernel_to_ipc64_perm(&shp->shm_perm, &tbuf.shm_perm);
+		tbuf.shm_segsz	= shp->shm_segsz;
+		tbuf.shm_atime	= shp->shm_atim;
+		tbuf.shm_dtime	= shp->shm_dtim;
+		tbuf.shm_ctime	= shp->shm_ctim;
+		tbuf.shm_cpid	= shp->shm_cprid;
+		tbuf.shm_lpid	= shp->shm_lprid;
+		tbuf.shm_nattch	= shp->shm_nattch;
+		rcu_read_unlock();
+
+		if (copy_shmid_to_user(buf, &tbuf, version))
+			err = -EFAULT;
+		else
+			err = result;
+		goto out;
+	}
+	default:
+		return -EINVAL;
+	}
+
+out_unlock:
+	rcu_read_unlock();
+out:
+	return err;
+}
+
+SYSCALL_DEFINE3(shmctl, int, shmid, int, cmd, struct shmid_ds __user *, buf)
+{
+	struct shmid_kernel *shp;
+	int err, version;
+	struct ipc_namespace *ns;
+
+	if (cmd < 0 || shmid < 0)
+		return -EINVAL;
+
+	version = ipc_parse_version(&cmd);
+	ns = current->nsproxy->ipc_ns;
+
+	switch (cmd) {
+	case IPC_INFO:
+	case SHM_INFO:
+	case SHM_STAT:
+	case IPC_STAT:
+		return shmctl_nolock(ns, shmid, cmd, version, buf);
+	case IPC_RMID:
+	case IPC_SET:
+		return shmctl_down(ns, shmid, cmd, buf, version);
+	case SHM_LOCK:
+	case SHM_UNLOCK:
+	{
+		struct file *shm_file;
+
+		rcu_read_lock();
+		shp = shm_obtain_object_check(ns, shmid);
+		if (IS_ERR(shp)) {
+			err = PTR_ERR(shp);
+			goto out_unlock1;
+		}
+
+		audit_ipc_obj(&(shp->shm_perm));
+		err = security_shm_shmctl(shp, cmd);
+		if (err)
+			goto out_unlock1;
+
+		ipc_lock_object(&shp->shm_perm);
+
+		/* check if shm_destroy() is tearing down shp */
+		if (!ipc_valid_object(&shp->shm_perm)) {
+			err = -EIDRM;
+			goto out_unlock0;
+		}
+
+		if (!ns_capable(ns->user_ns, CAP_IPC_LOCK)) {
+			kuid_t euid = current_euid();
+			if (!uid_eq(euid, shp->shm_perm.uid) &&
+			    !uid_eq(euid, shp->shm_perm.cuid)) {
+				err = -EPERM;
+				goto out_unlock0;
+			}
+			if (cmd == SHM_LOCK && !rlimit(RLIMIT_MEMLOCK)) {
+				err = -EPERM;
+				goto out_unlock0;
+			}
+		}
+
+		shm_file = shp->shm_file;
+		if (is_file_hugepages(shm_file))
+			goto out_unlock0;
+
+		if (cmd == SHM_LOCK) {
+			struct user_struct *user = current_user();
+			err = shmem_lock(shm_file, 1, user);
+			if (!err && !(shp->shm_perm.mode & SHM_LOCKED)) {
+				shp->shm_perm.mode |= SHM_LOCKED;
+				shp->mlock_user = user;
+			}
+			goto out_unlock0;
+		}
+
+		/* SHM_UNLOCK */
+		if (!(shp->shm_perm.mode & SHM_LOCKED))
+			goto out_unlock0;
+		shmem_lock(shm_file, 0, shp->mlock_user);
+		shp->shm_perm.mode &= ~SHM_LOCKED;
+		shp->mlock_user = NULL;
+		get_file(shm_file);
+		ipc_unlock_object(&shp->shm_perm);
+		rcu_read_unlock();
+		shmem_unlock_mapping(shm_file->f_mapping);
+
+		fput(shm_file);
+		return err;
+	}
+	default:
+		return -EINVAL;
+	}
+
+out_unlock0:
+	ipc_unlock_object(&shp->shm_perm);
+out_unlock1:
+	rcu_read_unlock();
+	return err;
+}
+
+/*
+ * Fix shmaddr, allocate descriptor, map shm, add attach descriptor to lists.
+ *
+ * NOTE! Despite the name, this is NOT a direct system call entrypoint. The
+ * "raddr" thing points to kernel space, and there has to be a wrapper around
+ * this.
+ */
+long do_shmat(int shmid, char __user *shmaddr, int shmflg, ulong *raddr,
+	      unsigned long shmlba)
+{
+	struct shmid_kernel *shp;
+	unsigned long addr;
+	unsigned long size;
+	struct file *file;
+	int    err;
+	unsigned long flags;
+	unsigned long prot;
+	int acc_mode;
+	struct ipc_namespace *ns;
+	struct shm_file_data *sfd;
+	struct path path;
+	fmode_t f_mode;
+	unsigned long populate = 0;
+
+	err = -EINVAL;
+	if (shmid < 0)
+		goto out;
+	else if ((addr = (ulong)shmaddr)) {
+		if (addr & (shmlba - 1)) {
+			if (shmflg & SHM_RND)
+				addr &= ~(shmlba - 1);	   /* round down */
+			else
+#ifndef __ARCH_FORCE_SHMLBA
+				if (addr & ~PAGE_MASK)
+#endif
+					goto out;
+		}
+		flags = MAP_SHARED | MAP_FIXED;
+	} else {
+		if ((shmflg & SHM_REMAP))
+			goto out;
+
+		flags = MAP_SHARED;
+	}
+
+	if (shmflg & SHM_RDONLY) {
+		prot = PROT_READ;
+		acc_mode = S_IRUGO;
+		f_mode = FMODE_READ;
+	} else {
+		prot = PROT_READ | PROT_WRITE;
+		acc_mode = S_IRUGO | S_IWUGO;
+		f_mode = FMODE_READ | FMODE_WRITE;
+	}
+	if (shmflg & SHM_EXEC) {
+		prot |= PROT_EXEC;
+		acc_mode |= S_IXUGO;
+	}
+
+	/*
+	 * We cannot rely on the fs check since SYSV IPC does have an
+	 * additional creator id...
+	 */
+	ns = current->nsproxy->ipc_ns;
+	rcu_read_lock();
+	shp = shm_obtain_object_check(ns, shmid);
+	if (IS_ERR(shp)) {
+		err = PTR_ERR(shp);
+		goto out_unlock;
+	}
+
+	err = -EACCES;
+	if (ipcperms(ns, &shp->shm_perm, acc_mode))
+		goto out_unlock;
+
+	err = security_shm_shmat(shp, shmaddr, shmflg);
+	if (err)
+		goto out_unlock;
+
+	ipc_lock_object(&shp->shm_perm);
+
+	/* check if shm_destroy() is tearing down shp */
+	if (!ipc_valid_object(&shp->shm_perm)) {
+		ipc_unlock_object(&shp->shm_perm);
+		err = -EIDRM;
+		goto out_unlock;
+	}
+
+	path = shp->shm_file->f_path;
+	path_get(&path);
+	shp->shm_nattch++;
+	size = i_size_read(d_inode(path.dentry));
+	ipc_unlock_object(&shp->shm_perm);
+	rcu_read_unlock();
+
+	err = -ENOMEM;
+	sfd = kzalloc(sizeof(*sfd), GFP_KERNEL);
+	if (!sfd) {
+		path_put(&path);
+		goto out_nattch;
+	}
+
+	file = alloc_file(&path, f_mode,
+			  is_file_hugepages(shp->shm_file) ?
+				&shm_file_operations_huge :
+				&shm_file_operations);
+	err = PTR_ERR(file);
+	if (IS_ERR(file)) {
+		kfree(sfd);
+		path_put(&path);
+		goto out_nattch;
+	}
+
+	file->private_data = sfd;
+	file->f_mapping = shp->shm_file->f_mapping;
+	sfd->id = shp->shm_perm.id;
+	sfd->ns = get_ipc_ns(ns);
+	sfd->file = shp->shm_file;
+	sfd->vm_ops = NULL;
+
+	err = security_mmap_file(file, prot, flags);
+	if (err)
+		goto out_fput;
+
+	down_write(&current->mm->mmap_sem);
+	if (addr && !(shmflg & SHM_REMAP)) {
+		err = -EINVAL;
+		if (addr + size < addr)
+			goto invalid;
+
+		if (find_vma_intersection(current->mm, addr, addr + size))
+			goto invalid;
+	}
+
+	addr = do_mmap_pgoff(file, addr, size, prot, flags, 0, &populate);
+	*raddr = addr;
+	err = 0;
+	if (IS_ERR_VALUE(addr))
+		err = (long)addr;
+invalid:
+	up_write(&current->mm->mmap_sem);
+	if (populate)
+		mm_populate(addr, populate);
+
+out_fput:
+	fput(file);
+
+out_nattch:
+	down_write(&shm_ids(ns).rwsem);
+	shp = shm_lock(ns, shmid);
+	BUG_ON(IS_ERR(shp));
+	shp->shm_nattch--;
+	if (shm_may_destroy(ns, shp))
+		shm_destroy(ns, shp);
+	else
+		shm_unlock(shp);
+	up_write(&shm_ids(ns).rwsem);
+	return err;
+
+out_unlock:
+	rcu_read_unlock();
+out:
+	return err;
+}
+
+SYSCALL_DEFINE3(shmat, int, shmid, char __user *, shmaddr, int, shmflg)
+{
+	unsigned long ret;
+	long err;
+
+	err = do_shmat(shmid, shmaddr, shmflg, &ret, SHMLBA);
+	if (err)
+		return err;
+	force_successful_syscall_return();
+	return (long)ret;
+}
+
+/*
+ * detach and kill segment if marked destroyed.
+ * The work is done in shm_close.
+ */
+SYSCALL_DEFINE1(shmdt, char __user *, shmaddr)
+{
+	struct mm_struct *mm = current->mm;
+	struct vm_area_struct *vma;
+	unsigned long addr = (unsigned long)shmaddr;
+	int retval = -EINVAL;
+#ifdef CONFIG_MMU
+	loff_t size = 0;
+	struct file *file;
+	struct vm_area_struct *next;
+#endif
+
+	if (addr & ~PAGE_MASK)
+		return retval;
+
+	down_write(&mm->mmap_sem);
+
+	/*
+	 * This function tries to be smart and unmap shm segments that
+	 * were modified by partial mlock or munmap calls:
+	 * - It first determines the size of the shm segment that should be
+	 *   unmapped: It searches for a vma that is backed by shm and that
+	 *   started at address shmaddr. It records it's size and then unmaps
+	 *   it.
+	 * - Then it unmaps all shm vmas that started at shmaddr and that
+	 *   are within the initially determined size and that are from the
+	 *   same shm segment from which we determined the size.
+	 * Errors from do_munmap are ignored: the function only fails if
+	 * it's called with invalid parameters or if it's called to unmap
+	 * a part of a vma. Both calls in this function are for full vmas,
+	 * the parameters are directly copied from the vma itself and always
+	 * valid - therefore do_munmap cannot fail. (famous last words?)
+	 */
+	/*
+	 * If it had been mremap()'d, the starting address would not
+	 * match the usual checks anyway. So assume all vma's are
+	 * above the starting address given.
+	 */
+	vma = find_vma(mm, addr);
+
+#ifdef CONFIG_MMU
+	while (vma) {
+		next = vma->vm_next;
+
+		/*
+		 * Check if the starting address would match, i.e. it's
+		 * a fragment created by mprotect() and/or munmap(), or it
+		 * otherwise it starts at this address with no hassles.
+		 */
+		if ((vma->vm_ops == &shm_vm_ops) &&
+			(vma->vm_start - addr)/PAGE_SIZE == vma->vm_pgoff) {
+
+			/*
+			 * Record the file of the shm segment being
+			 * unmapped.  With mremap(), someone could place
+			 * page from another segment but with equal offsets
+			 * in the range we are unmapping.
+			 */
+			file = vma->vm_file;
+			size = i_size_read(file_inode(vma->vm_file));
+			do_munmap(mm, vma->vm_start, vma->vm_end - vma->vm_start);
+			/*
+			 * We discovered the size of the shm segment, so
+			 * break out of here and fall through to the next
+			 * loop that uses the size information to stop
+			 * searching for matching vma's.
+			 */
+			retval = 0;
+			vma = next;
+			break;
+		}
+		vma = next;
+	}
+
+	/*
+	 * We need look no further than the maximum address a fragment
+	 * could possibly have landed at. Also cast things to loff_t to
+	 * prevent overflows and make comparisons vs. equal-width types.
+	 */
+	size = PAGE_ALIGN(size);
+	while (vma && (loff_t)(vma->vm_end - addr) <= size) {
+		next = vma->vm_next;
+
+		/* finding a matching vma now does not alter retval */
+		if ((vma->vm_ops == &shm_vm_ops) &&
+		    ((vma->vm_start - addr)/PAGE_SIZE == vma->vm_pgoff) &&
+		    (vma->vm_file == file))
+			do_munmap(mm, vma->vm_start, vma->vm_end - vma->vm_start);
+		vma = next;
+	}
+
+#else /* CONFIG_MMU */
+	/* under NOMMU conditions, the exact address to be destroyed must be
+	 * given */
+	if (vma && vma->vm_start == addr && vma->vm_ops == &shm_vm_ops) {
+		do_munmap(mm, vma->vm_start, vma->vm_end - vma->vm_start);
+		retval = 0;
+	}
+
+#endif
+
+	up_write(&mm->mmap_sem);
+	return retval;
+}
+
+#ifdef CONFIG_PROC_FS
+static int sysvipc_shm_proc_show(struct seq_file *s, void *it)
+{
+	struct user_namespace *user_ns = seq_user_ns(s);
+	struct shmid_kernel *shp = it;
+	unsigned long rss = 0, swp = 0;
+
+	shm_add_rss_swap(shp, &rss, &swp);
+
+#if BITS_PER_LONG <= 32
+#define SIZE_SPEC "%10lu"
+#else
+#define SIZE_SPEC "%21lu"
+#endif
+
+	seq_printf(s,
+		   "%10d %10d  %4o " SIZE_SPEC " %5u %5u  "
+		   "%5lu %5u %5u %5u %5u %10lu %10lu %10lu "
+		   SIZE_SPEC " " SIZE_SPEC "\n",
+		   shp->shm_perm.key,
+		   shp->shm_perm.id,
+		   shp->shm_perm.mode,
+		   shp->shm_segsz,
+		   shp->shm_cprid,
+		   shp->shm_lprid,
+		   shp->shm_nattch,
+		   from_kuid_munged(user_ns, shp->shm_perm.uid),
+		   from_kgid_munged(user_ns, shp->shm_perm.gid),
+		   from_kuid_munged(user_ns, shp->shm_perm.cuid),
+		   from_kgid_munged(user_ns, shp->shm_perm.cgid),
+		   shp->shm_atim,
+		   shp->shm_dtim,
+		   shp->shm_ctim,
+		   rss * PAGE_SIZE,
+		   swp * PAGE_SIZE);
+
+	return 0;
+}
+#endif
diff --git a/kernel/ipc/syscall.c b/kernel/ipc/syscall.c
new file mode 100644
index 000000000..52429489c
--- /dev/null
+++ b/kernel/ipc/syscall.c
@@ -0,0 +1,99 @@
+/*
+ * sys_ipc() is the old de-multiplexer for the SysV IPC calls.
+ *
+ * This is really horribly ugly, and new architectures should just wire up
+ * the individual syscalls instead.
+ */
+#include <linux/unistd.h>
+
+#ifdef __ARCH_WANT_SYS_IPC
+#include <linux/errno.h>
+#include <linux/ipc.h>
+#include <linux/shm.h>
+#include <linux/syscalls.h>
+#include <linux/uaccess.h>
+
+SYSCALL_DEFINE6(ipc, unsigned int, call, int, first, unsigned long, second,
+		unsigned long, third, void __user *, ptr, long, fifth)
+{
+	int version, ret;
+
+	version = call >> 16; /* hack for backward compatibility */
+	call &= 0xffff;
+
+	switch (call) {
+	case SEMOP:
+		return sys_semtimedop(first, (struct sembuf __user *)ptr,
+				      second, NULL);
+	case SEMTIMEDOP:
+		return sys_semtimedop(first, (struct sembuf __user *)ptr,
+				      second,
+				      (const struct timespec __user *)fifth);
+
+	case SEMGET:
+		return sys_semget(first, second, third);
+	case SEMCTL: {
+		unsigned long arg;
+		if (!ptr)
+			return -EINVAL;
+		if (get_user(arg, (unsigned long __user *) ptr))
+			return -EFAULT;
+		return sys_semctl(first, second, third, arg);
+	}
+
+	case MSGSND:
+		return sys_msgsnd(first, (struct msgbuf __user *) ptr,
+				  second, third);
+	case MSGRCV:
+		switch (version) {
+		case 0: {
+			struct ipc_kludge tmp;
+			if (!ptr)
+				return -EINVAL;
+
+			if (copy_from_user(&tmp,
+					   (struct ipc_kludge __user *) ptr,
+					   sizeof(tmp)))
+				return -EFAULT;
+			return sys_msgrcv(first, tmp.msgp, second,
+					   tmp.msgtyp, third);
+		}
+		default:
+			return sys_msgrcv(first,
+					   (struct msgbuf __user *) ptr,
+					   second, fifth, third);
+		}
+	case MSGGET:
+		return sys_msgget((key_t) first, second);
+	case MSGCTL:
+		return sys_msgctl(first, second, (struct msqid_ds __user *)ptr);
+
+	case SHMAT:
+		switch (version) {
+		default: {
+			unsigned long raddr;
+			ret = do_shmat(first, (char __user *)ptr,
+				       second, &raddr, SHMLBA);
+			if (ret)
+				return ret;
+			return put_user(raddr, (unsigned long __user *) third);
+		}
+		case 1:
+			/*
+			 * This was the entry point for kernel-originating calls
+			 * from iBCS2 in 2.2 days.
+			 */
+			return -EINVAL;
+		}
+	case SHMDT:
+		return sys_shmdt((char __user *)ptr);
+	case SHMGET:
+		return sys_shmget(first, second, third);
+	case SHMCTL:
+		return sys_shmctl(first, second,
+				   (struct shmid_ds __user *) ptr);
+	default:
+		return -ENOSYS;
+	}
+}
+#endif
diff --git a/kernel/ipc/util.c b/kernel/ipc/util.c
new file mode 100644
index 000000000..ff3323ef8
--- /dev/null
+++ b/kernel/ipc/util.c
@@ -0,0 +1,883 @@
+/*
+ * linux/ipc/util.c
+ * Copyright (C) 1992 Krishna Balasubramanian
+ *
+ * Sep 1997 - Call suser() last after "normal" permission checks so we
+ *            get BSD style process accounting right.
+ *            Occurs in several places in the IPC code.
+ *            Chris Evans, <chris@ferret.lmh.ox.ac.uk>
+ * Nov 1999 - ipc helper functions, unified SMP locking
+ *	      Manfred Spraul <manfred@colorfullife.com>
+ * Oct 2002 - One lock per IPC id. RCU ipc_free for lock-free grow_ary().
+ *            Mingming Cao <cmm@us.ibm.com>
+ * Mar 2006 - support for audit of ipc object properties
+ *            Dustin Kirkland <dustin.kirkland@us.ibm.com>
+ * Jun 2006 - namespaces ssupport
+ *            OpenVZ, SWsoft Inc.
+ *            Pavel Emelianov <xemul@openvz.org>
+ *
+ * General sysv ipc locking scheme:
+ *	rcu_read_lock()
+ *          obtain the ipc object (kern_ipc_perm) by looking up the id in an idr
+ *	    tree.
+ *	    - perform initial checks (capabilities, auditing and permission,
+ *	      etc).
+ *	    - perform read-only operations, such as STAT, INFO commands.
+ *	      acquire the ipc lock (kern_ipc_perm.lock) through
+ *	      ipc_lock_object()
+ *		- perform data updates, such as SET, RMID commands and
+ *		  mechanism-specific operations (semop/semtimedop,
+ *		  msgsnd/msgrcv, shmat/shmdt).
+ *	    drop the ipc lock, through ipc_unlock_object().
+ *	rcu_read_unlock()
+ *
+ *  The ids->rwsem must be taken when:
+ *	- creating, removing and iterating the existing entries in ipc
+ *	  identifier sets.
+ *	- iterating through files under /proc/sysvipc/
+ *
+ *  Note that sems have a special fast path that avoids kern_ipc_perm.lock -
+ *  see sem_lock().
+ */
+
+#include <linux/mm.h>
+#include <linux/shm.h>
+#include <linux/init.h>
+#include <linux/msg.h>
+#include <linux/vmalloc.h>
+#include <linux/slab.h>
+#include <linux/notifier.h>
+#include <linux/capability.h>
+#include <linux/highuid.h>
+#include <linux/security.h>
+#include <linux/rcupdate.h>
+#include <linux/workqueue.h>
+#include <linux/seq_file.h>
+#include <linux/proc_fs.h>
+#include <linux/audit.h>
+#include <linux/nsproxy.h>
+#include <linux/rwsem.h>
+#include <linux/memory.h>
+#include <linux/ipc_namespace.h>
+
+#include <asm/unistd.h>
+
+#include "util.h"
+
+struct ipc_proc_iface {
+	const char *path;
+	const char *header;
+	int ids;
+	int (*show)(struct seq_file *, void *);
+};
+
+/**
+ * ipc_init - initialise ipc subsystem
+ *
+ * The various sysv ipc resources (semaphores, messages and shared
+ * memory) are initialised.
+ *
+ * A callback routine is registered into the memory hotplug notifier
+ * chain: since msgmni scales to lowmem this callback routine will be
+ * called upon successful memory add / remove to recompute msmgni.
+ */
+static int __init ipc_init(void)
+{
+	sem_init();
+	msg_init();
+	shm_init();
+	return 0;
+}
+device_initcall(ipc_init);
+
+/**
+ * ipc_init_ids	- initialise ipc identifiers
+ * @ids: ipc identifier set
+ *
+ * Set up the sequence range to use for the ipc identifier range (limited
+ * below IPCMNI) then initialise the ids idr.
+ */
+void ipc_init_ids(struct ipc_ids *ids)
+{
+	ids->in_use = 0;
+	ids->seq = 0;
+	ids->next_id = -1;
+	init_rwsem(&ids->rwsem);
+	idr_init(&ids->ipcs_idr);
+}
+
+#ifdef CONFIG_PROC_FS
+static const struct file_operations sysvipc_proc_fops;
+/**
+ * ipc_init_proc_interface -  create a proc interface for sysipc types using a seq_file interface.
+ * @path: Path in procfs
+ * @header: Banner to be printed at the beginning of the file.
+ * @ids: ipc id table to iterate.
+ * @show: show routine.
+ */
+void __init ipc_init_proc_interface(const char *path, const char *header,
+		int ids, int (*show)(struct seq_file *, void *))
+{
+	struct proc_dir_entry *pde;
+	struct ipc_proc_iface *iface;
+
+	iface = kmalloc(sizeof(*iface), GFP_KERNEL);
+	if (!iface)
+		return;
+	iface->path	= path;
+	iface->header	= header;
+	iface->ids	= ids;
+	iface->show	= show;
+
+	pde = proc_create_data(path,
+			       S_IRUGO,        /* world readable */
+			       NULL,           /* parent dir */
+			       &sysvipc_proc_fops,
+			       iface);
+	if (!pde)
+		kfree(iface);
+}
+#endif
+
+/**
+ * ipc_findkey	- find a key in an ipc identifier set
+ * @ids: ipc identifier set
+ * @key: key to find
+ *
+ * Returns the locked pointer to the ipc structure if found or NULL
+ * otherwise. If key is found ipc points to the owning ipc structure
+ *
+ * Called with ipc_ids.rwsem held.
+ */
+static struct kern_ipc_perm *ipc_findkey(struct ipc_ids *ids, key_t key)
+{
+	struct kern_ipc_perm *ipc;
+	int next_id;
+	int total;
+
+	for (total = 0, next_id = 0; total < ids->in_use; next_id++) {
+		ipc = idr_find(&ids->ipcs_idr, next_id);
+
+		if (ipc == NULL)
+			continue;
+
+		if (ipc->key != key) {
+			total++;
+			continue;
+		}
+
+		rcu_read_lock();
+		ipc_lock_object(ipc);
+		return ipc;
+	}
+
+	return NULL;
+}
+
+/**
+ * ipc_get_maxid - get the last assigned id
+ * @ids: ipc identifier set
+ *
+ * Called with ipc_ids.rwsem held.
+ */
+int ipc_get_maxid(struct ipc_ids *ids)
+{
+	struct kern_ipc_perm *ipc;
+	int max_id = -1;
+	int total, id;
+
+	if (ids->in_use == 0)
+		return -1;
+
+	if (ids->in_use == IPCMNI)
+		return IPCMNI - 1;
+
+	/* Look for the last assigned id */
+	total = 0;
+	for (id = 0; id < IPCMNI && total < ids->in_use; id++) {
+		ipc = idr_find(&ids->ipcs_idr, id);
+		if (ipc != NULL) {
+			max_id = id;
+			total++;
+		}
+	}
+	return max_id;
+}
+
+/**
+ * ipc_addid - add an ipc identifier
+ * @ids: ipc identifier set
+ * @new: new ipc permission set
+ * @size: limit for the number of used ids
+ *
+ * Add an entry 'new' to the ipc ids idr. The permissions object is
+ * initialised and the first free entry is set up and the id assigned
+ * is returned. The 'new' entry is returned in a locked state on success.
+ * On failure the entry is not locked and a negative err-code is returned.
+ *
+ * Called with writer ipc_ids.rwsem held.
+ */
+int ipc_addid(struct ipc_ids *ids, struct kern_ipc_perm *new, int size)
+{
+	kuid_t euid;
+	kgid_t egid;
+	int id;
+	int next_id = ids->next_id;
+
+	if (size > IPCMNI)
+		size = IPCMNI;
+
+	if (ids->in_use >= size)
+		return -ENOSPC;
+
+	idr_preload(GFP_KERNEL);
+
+	spin_lock_init(&new->lock);
+	new->deleted = false;
+	rcu_read_lock();
+	spin_lock(&new->lock);
+
+	id = idr_alloc(&ids->ipcs_idr, new,
+		       (next_id < 0) ? 0 : ipcid_to_idx(next_id), 0,
+		       GFP_NOWAIT);
+	idr_preload_end();
+	if (id < 0) {
+		spin_unlock(&new->lock);
+		rcu_read_unlock();
+		return id;
+	}
+
+	ids->in_use++;
+
+	current_euid_egid(&euid, &egid);
+	new->cuid = new->uid = euid;
+	new->gid = new->cgid = egid;
+
+	if (next_id < 0) {
+		new->seq = ids->seq++;
+		if (ids->seq > IPCID_SEQ_MAX)
+			ids->seq = 0;
+	} else {
+		new->seq = ipcid_to_seqx(next_id);
+		ids->next_id = -1;
+	}
+
+	new->id = ipc_buildid(id, new->seq);
+	return id;
+}
+
+/**
+ * ipcget_new -	create a new ipc object
+ * @ns: ipc namespace
+ * @ids: ipc identifier set
+ * @ops: the actual creation routine to call
+ * @params: its parameters
+ *
+ * This routine is called by sys_msgget, sys_semget() and sys_shmget()
+ * when the key is IPC_PRIVATE.
+ */
+static int ipcget_new(struct ipc_namespace *ns, struct ipc_ids *ids,
+		const struct ipc_ops *ops, struct ipc_params *params)
+{
+	int err;
+
+	down_write(&ids->rwsem);
+	err = ops->getnew(ns, params);
+	up_write(&ids->rwsem);
+	return err;
+}
+
+/**
+ * ipc_check_perms - check security and permissions for an ipc object
+ * @ns: ipc namespace
+ * @ipcp: ipc permission set
+ * @ops: the actual security routine to call
+ * @params: its parameters
+ *
+ * This routine is called by sys_msgget(), sys_semget() and sys_shmget()
+ * when the key is not IPC_PRIVATE and that key already exists in the
+ * ds IDR.
+ *
+ * On success, the ipc id is returned.
+ *
+ * It is called with ipc_ids.rwsem and ipcp->lock held.
+ */
+static int ipc_check_perms(struct ipc_namespace *ns,
+			   struct kern_ipc_perm *ipcp,
+			   const struct ipc_ops *ops,
+			   struct ipc_params *params)
+{
+	int err;
+
+	if (ipcperms(ns, ipcp, params->flg))
+		err = -EACCES;
+	else {
+		err = ops->associate(ipcp, params->flg);
+		if (!err)
+			err = ipcp->id;
+	}
+
+	return err;
+}
+
+/**
+ * ipcget_public - get an ipc object or create a new one
+ * @ns: ipc namespace
+ * @ids: ipc identifier set
+ * @ops: the actual creation routine to call
+ * @params: its parameters
+ *
+ * This routine is called by sys_msgget, sys_semget() and sys_shmget()
+ * when the key is not IPC_PRIVATE.
+ * It adds a new entry if the key is not found and does some permission
+ * / security checkings if the key is found.
+ *
+ * On success, the ipc id is returned.
+ */
+static int ipcget_public(struct ipc_namespace *ns, struct ipc_ids *ids,
+		const struct ipc_ops *ops, struct ipc_params *params)
+{
+	struct kern_ipc_perm *ipcp;
+	int flg = params->flg;
+	int err;
+
+	/*
+	 * Take the lock as a writer since we are potentially going to add
+	 * a new entry + read locks are not "upgradable"
+	 */
+	down_write(&ids->rwsem);
+	ipcp = ipc_findkey(ids, params->key);
+	if (ipcp == NULL) {
+		/* key not used */
+		if (!(flg & IPC_CREAT))
+			err = -ENOENT;
+		else
+			err = ops->getnew(ns, params);
+	} else {
+		/* ipc object has been locked by ipc_findkey() */
+
+		if (flg & IPC_CREAT && flg & IPC_EXCL)
+			err = -EEXIST;
+		else {
+			err = 0;
+			if (ops->more_checks)
+				err = ops->more_checks(ipcp, params);
+			if (!err)
+				/*
+				 * ipc_check_perms returns the IPC id on
+				 * success
+				 */
+				err = ipc_check_perms(ns, ipcp, ops, params);
+		}
+		ipc_unlock(ipcp);
+	}
+	up_write(&ids->rwsem);
+
+	return err;
+}
+
+
+/**
+ * ipc_rmid - remove an ipc identifier
+ * @ids: ipc identifier set
+ * @ipcp: ipc perm structure containing the identifier to remove
+ *
+ * ipc_ids.rwsem (as a writer) and the spinlock for this ID are held
+ * before this function is called, and remain locked on the exit.
+ */
+void ipc_rmid(struct ipc_ids *ids, struct kern_ipc_perm *ipcp)
+{
+	int lid = ipcid_to_idx(ipcp->id);
+
+	idr_remove(&ids->ipcs_idr, lid);
+	ids->in_use--;
+	ipcp->deleted = true;
+}
+
+/**
+ * ipc_alloc -	allocate ipc space
+ * @size: size desired
+ *
+ * Allocate memory from the appropriate pools and return a pointer to it.
+ * NULL is returned if the allocation fails
+ */
+void *ipc_alloc(int size)
+{
+	void *out;
+	if (size > PAGE_SIZE)
+		out = vmalloc(size);
+	else
+		out = kmalloc(size, GFP_KERNEL);
+	return out;
+}
+
+/**
+ * ipc_free - free ipc space
+ * @ptr: pointer returned by ipc_alloc
+ * @size: size of block
+ *
+ * Free a block created with ipc_alloc(). The caller must know the size
+ * used in the allocation call.
+ */
+void ipc_free(void *ptr, int size)
+{
+	if (size > PAGE_SIZE)
+		vfree(ptr);
+	else
+		kfree(ptr);
+}
+
+/**
+ * ipc_rcu_alloc - allocate ipc and rcu space
+ * @size: size desired
+ *
+ * Allocate memory for the rcu header structure +  the object.
+ * Returns the pointer to the object or NULL upon failure.
+ */
+void *ipc_rcu_alloc(int size)
+{
+	/*
+	 * We prepend the allocation with the rcu struct
+	 */
+	struct ipc_rcu *out = ipc_alloc(sizeof(struct ipc_rcu) + size);
+	if (unlikely(!out))
+		return NULL;
+	atomic_set(&out->refcount, 1);
+	return out + 1;
+}
+
+int ipc_rcu_getref(void *ptr)
+{
+	struct ipc_rcu *p = ((struct ipc_rcu *)ptr) - 1;
+
+	return atomic_inc_not_zero(&p->refcount);
+}
+
+void ipc_rcu_putref(void *ptr, void (*func)(struct rcu_head *head))
+{
+	struct ipc_rcu *p = ((struct ipc_rcu *)ptr) - 1;
+
+	if (!atomic_dec_and_test(&p->refcount))
+		return;
+
+	call_rcu(&p->rcu, func);
+}
+
+void ipc_rcu_free(struct rcu_head *head)
+{
+	struct ipc_rcu *p = container_of(head, struct ipc_rcu, rcu);
+
+	if (is_vmalloc_addr(p))
+		vfree(p);
+	else
+		kfree(p);
+}
+
+/**
+ * ipcperms - check ipc permissions
+ * @ns: ipc namespace
+ * @ipcp: ipc permission set
+ * @flag: desired permission set
+ *
+ * Check user, group, other permissions for access
+ * to ipc resources. return 0 if allowed
+ *
+ * @flag will most probably be 0 or S_...UGO from <linux/stat.h>
+ */
+int ipcperms(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp, short flag)
+{
+	kuid_t euid = current_euid();
+	int requested_mode, granted_mode;
+
+	audit_ipc_obj(ipcp);
+	requested_mode = (flag >> 6) | (flag >> 3) | flag;
+	granted_mode = ipcp->mode;
+	if (uid_eq(euid, ipcp->cuid) ||
+	    uid_eq(euid, ipcp->uid))
+		granted_mode >>= 6;
+	else if (in_group_p(ipcp->cgid) || in_group_p(ipcp->gid))
+		granted_mode >>= 3;
+	/* is there some bit set in requested_mode but not in granted_mode? */
+	if ((requested_mode & ~granted_mode & 0007) &&
+	    !ns_capable(ns->user_ns, CAP_IPC_OWNER))
+		return -1;
+
+	return security_ipc_permission(ipcp, flag);
+}
+
+/*
+ * Functions to convert between the kern_ipc_perm structure and the
+ * old/new ipc_perm structures
+ */
+
+/**
+ * kernel_to_ipc64_perm	- convert kernel ipc permissions to user
+ * @in: kernel permissions
+ * @out: new style ipc permissions
+ *
+ * Turn the kernel object @in into a set of permissions descriptions
+ * for returning to userspace (@out).
+ */
+void kernel_to_ipc64_perm(struct kern_ipc_perm *in, struct ipc64_perm *out)
+{
+	out->key	= in->key;
+	out->uid	= from_kuid_munged(current_user_ns(), in->uid);
+	out->gid	= from_kgid_munged(current_user_ns(), in->gid);
+	out->cuid	= from_kuid_munged(current_user_ns(), in->cuid);
+	out->cgid	= from_kgid_munged(current_user_ns(), in->cgid);
+	out->mode	= in->mode;
+	out->seq	= in->seq;
+}
+
+/**
+ * ipc64_perm_to_ipc_perm - convert new ipc permissions to old
+ * @in: new style ipc permissions
+ * @out: old style ipc permissions
+ *
+ * Turn the new style permissions object @in into a compatibility
+ * object and store it into the @out pointer.
+ */
+void ipc64_perm_to_ipc_perm(struct ipc64_perm *in, struct ipc_perm *out)
+{
+	out->key	= in->key;
+	SET_UID(out->uid, in->uid);
+	SET_GID(out->gid, in->gid);
+	SET_UID(out->cuid, in->cuid);
+	SET_GID(out->cgid, in->cgid);
+	out->mode	= in->mode;
+	out->seq	= in->seq;
+}
+
+/**
+ * ipc_obtain_object
+ * @ids: ipc identifier set
+ * @id: ipc id to look for
+ *
+ * Look for an id in the ipc ids idr and return associated ipc object.
+ *
+ * Call inside the RCU critical section.
+ * The ipc object is *not* locked on exit.
+ */
+struct kern_ipc_perm *ipc_obtain_object(struct ipc_ids *ids, int id)
+{
+	struct kern_ipc_perm *out;
+	int lid = ipcid_to_idx(id);
+
+	out = idr_find(&ids->ipcs_idr, lid);
+	if (!out)
+		return ERR_PTR(-EINVAL);
+
+	return out;
+}
+
+/**
+ * ipc_lock - lock an ipc structure without rwsem held
+ * @ids: ipc identifier set
+ * @id: ipc id to look for
+ *
+ * Look for an id in the ipc ids idr and lock the associated ipc object.
+ *
+ * The ipc object is locked on successful exit.
+ */
+struct kern_ipc_perm *ipc_lock(struct ipc_ids *ids, int id)
+{
+	struct kern_ipc_perm *out;
+
+	rcu_read_lock();
+	out = ipc_obtain_object(ids, id);
+	if (IS_ERR(out))
+		goto err1;
+
+	spin_lock(&out->lock);
+
+	/* ipc_rmid() may have already freed the ID while ipc_lock
+	 * was spinning: here verify that the structure is still valid
+	 */
+	if (ipc_valid_object(out))
+		return out;
+
+	spin_unlock(&out->lock);
+	out = ERR_PTR(-EINVAL);
+err1:
+	rcu_read_unlock();
+	return out;
+}
+
+/**
+ * ipc_obtain_object_check
+ * @ids: ipc identifier set
+ * @id: ipc id to look for
+ *
+ * Similar to ipc_obtain_object() but also checks
+ * the ipc object reference counter.
+ *
+ * Call inside the RCU critical section.
+ * The ipc object is *not* locked on exit.
+ */
+struct kern_ipc_perm *ipc_obtain_object_check(struct ipc_ids *ids, int id)
+{
+	struct kern_ipc_perm *out = ipc_obtain_object(ids, id);
+
+	if (IS_ERR(out))
+		goto out;
+
+	if (ipc_checkid(out, id))
+		return ERR_PTR(-EIDRM);
+out:
+	return out;
+}
+
+/**
+ * ipcget - Common sys_*get() code
+ * @ns: namespace
+ * @ids: ipc identifier set
+ * @ops: operations to be called on ipc object creation, permission checks
+ *       and further checks
+ * @params: the parameters needed by the previous operations.
+ *
+ * Common routine called by sys_msgget(), sys_semget() and sys_shmget().
+ */
+int ipcget(struct ipc_namespace *ns, struct ipc_ids *ids,
+			const struct ipc_ops *ops, struct ipc_params *params)
+{
+	if (params->key == IPC_PRIVATE)
+		return ipcget_new(ns, ids, ops, params);
+	else
+		return ipcget_public(ns, ids, ops, params);
+}
+
+/**
+ * ipc_update_perm - update the permissions of an ipc object
+ * @in:  the permission given as input.
+ * @out: the permission of the ipc to set.
+ */
+int ipc_update_perm(struct ipc64_perm *in, struct kern_ipc_perm *out)
+{
+	kuid_t uid = make_kuid(current_user_ns(), in->uid);
+	kgid_t gid = make_kgid(current_user_ns(), in->gid);
+	if (!uid_valid(uid) || !gid_valid(gid))
+		return -EINVAL;
+
+	out->uid = uid;
+	out->gid = gid;
+	out->mode = (out->mode & ~S_IRWXUGO)
+		| (in->mode & S_IRWXUGO);
+
+	return 0;
+}
+
+/**
+ * ipcctl_pre_down_nolock - retrieve an ipc and check permissions for some IPC_XXX cmd
+ * @ns:  ipc namespace
+ * @ids:  the table of ids where to look for the ipc
+ * @id:   the id of the ipc to retrieve
+ * @cmd:  the cmd to check
+ * @perm: the permission to set
+ * @extra_perm: one extra permission parameter used by msq
+ *
+ * This function does some common audit and permissions check for some IPC_XXX
+ * cmd and is called from semctl_down, shmctl_down and msgctl_down.
+ * It must be called without any lock held and
+ *  - retrieves the ipc with the given id in the given table.
+ *  - performs some audit and permission check, depending on the given cmd
+ *  - returns a pointer to the ipc object or otherwise, the corresponding error.
+ *
+ * Call holding the both the rwsem and the rcu read lock.
+ */
+struct kern_ipc_perm *ipcctl_pre_down_nolock(struct ipc_namespace *ns,
+					struct ipc_ids *ids, int id, int cmd,
+					struct ipc64_perm *perm, int extra_perm)
+{
+	kuid_t euid;
+	int err = -EPERM;
+	struct kern_ipc_perm *ipcp;
+
+	ipcp = ipc_obtain_object_check(ids, id);
+	if (IS_ERR(ipcp)) {
+		err = PTR_ERR(ipcp);
+		goto err;
+	}
+
+	audit_ipc_obj(ipcp);
+	if (cmd == IPC_SET)
+		audit_ipc_set_perm(extra_perm, perm->uid,
+				   perm->gid, perm->mode);
+
+	euid = current_euid();
+	if (uid_eq(euid, ipcp->cuid) || uid_eq(euid, ipcp->uid)  ||
+	    ns_capable(ns->user_ns, CAP_SYS_ADMIN))
+		return ipcp; /* successful lookup */
+err:
+	return ERR_PTR(err);
+}
+
+#ifdef CONFIG_ARCH_WANT_IPC_PARSE_VERSION
+
+
+/**
+ * ipc_parse_version - ipc call version
+ * @cmd: pointer to command
+ *
+ * Return IPC_64 for new style IPC and IPC_OLD for old style IPC.
+ * The @cmd value is turned from an encoding command and version into
+ * just the command code.
+ */
+int ipc_parse_version(int *cmd)
+{
+	if (*cmd & IPC_64) {
+		*cmd ^= IPC_64;
+		return IPC_64;
+	} else {
+		return IPC_OLD;
+	}
+}
+
+#endif /* CONFIG_ARCH_WANT_IPC_PARSE_VERSION */
+
+#ifdef CONFIG_PROC_FS
+struct ipc_proc_iter {
+	struct ipc_namespace *ns;
+	struct ipc_proc_iface *iface;
+};
+
+/*
+ * This routine locks the ipc structure found at least at position pos.
+ */
+static struct kern_ipc_perm *sysvipc_find_ipc(struct ipc_ids *ids, loff_t pos,
+					      loff_t *new_pos)
+{
+	struct kern_ipc_perm *ipc;
+	int total, id;
+
+	total = 0;
+	for (id = 0; id < pos && total < ids->in_use; id++) {
+		ipc = idr_find(&ids->ipcs_idr, id);
+		if (ipc != NULL)
+			total++;
+	}
+
+	if (total >= ids->in_use)
+		return NULL;
+
+	for (; pos < IPCMNI; pos++) {
+		ipc = idr_find(&ids->ipcs_idr, pos);
+		if (ipc != NULL) {
+			*new_pos = pos + 1;
+			rcu_read_lock();
+			ipc_lock_object(ipc);
+			return ipc;
+		}
+	}
+
+	/* Out of range - return NULL to terminate iteration */
+	return NULL;
+}
+
+static void *sysvipc_proc_next(struct seq_file *s, void *it, loff_t *pos)
+{
+	struct ipc_proc_iter *iter = s->private;
+	struct ipc_proc_iface *iface = iter->iface;
+	struct kern_ipc_perm *ipc = it;
+
+	/* If we had an ipc id locked before, unlock it */
+	if (ipc && ipc != SEQ_START_TOKEN)
+		ipc_unlock(ipc);
+
+	return sysvipc_find_ipc(&iter->ns->ids[iface->ids], *pos, pos);
+}
+
+/*
+ * File positions: pos 0 -> header, pos n -> ipc id = n - 1.
+ * SeqFile iterator: iterator value locked ipc pointer or SEQ_TOKEN_START.
+ */
+static void *sysvipc_proc_start(struct seq_file *s, loff_t *pos)
+{
+	struct ipc_proc_iter *iter = s->private;
+	struct ipc_proc_iface *iface = iter->iface;
+	struct ipc_ids *ids;
+
+	ids = &iter->ns->ids[iface->ids];
+
+	/*
+	 * Take the lock - this will be released by the corresponding
+	 * call to stop().
+	 */
+	down_read(&ids->rwsem);
+
+	/* pos < 0 is invalid */
+	if (*pos < 0)
+		return NULL;
+
+	/* pos == 0 means header */
+	if (*pos == 0)
+		return SEQ_START_TOKEN;
+
+	/* Find the (pos-1)th ipc */
+	return sysvipc_find_ipc(ids, *pos - 1, pos);
+}
+
+static void sysvipc_proc_stop(struct seq_file *s, void *it)
+{
+	struct kern_ipc_perm *ipc = it;
+	struct ipc_proc_iter *iter = s->private;
+	struct ipc_proc_iface *iface = iter->iface;
+	struct ipc_ids *ids;
+
+	/* If we had a locked structure, release it */
+	if (ipc && ipc != SEQ_START_TOKEN)
+		ipc_unlock(ipc);
+
+	ids = &iter->ns->ids[iface->ids];
+	/* Release the lock we took in start() */
+	up_read(&ids->rwsem);
+}
+
+static int sysvipc_proc_show(struct seq_file *s, void *it)
+{
+	struct ipc_proc_iter *iter = s->private;
+	struct ipc_proc_iface *iface = iter->iface;
+
+	if (it == SEQ_START_TOKEN) {
+		seq_puts(s, iface->header);
+		return 0;
+	}
+
+	return iface->show(s, it);
+}
+
+static const struct seq_operations sysvipc_proc_seqops = {
+	.start = sysvipc_proc_start,
+	.stop  = sysvipc_proc_stop,
+	.next  = sysvipc_proc_next,
+	.show  = sysvipc_proc_show,
+};
+
+static int sysvipc_proc_open(struct inode *inode, struct file *file)
+{
+	struct ipc_proc_iter *iter;
+
+	iter = __seq_open_private(file, &sysvipc_proc_seqops, sizeof(*iter));
+	if (!iter)
+		return -ENOMEM;
+
+	iter->iface = PDE_DATA(inode);
+	iter->ns    = get_ipc_ns(current->nsproxy->ipc_ns);
+
+	return 0;
+}
+
+static int sysvipc_proc_release(struct inode *inode, struct file *file)
+{
+	struct seq_file *seq = file->private_data;
+	struct ipc_proc_iter *iter = seq->private;
+	put_ipc_ns(iter->ns);
+	return seq_release_private(inode, file);
+}
+
+static const struct file_operations sysvipc_proc_fops = {
+	.open    = sysvipc_proc_open,
+	.read    = seq_read,
+	.llseek  = seq_lseek,
+	.release = sysvipc_proc_release,
+};
+#endif /* CONFIG_PROC_FS */
diff --git a/kernel/ipc/util.h b/kernel/ipc/util.h
new file mode 100644
index 000000000..1a5a0fcd0
--- /dev/null
+++ b/kernel/ipc/util.h
@@ -0,0 +1,207 @@
+/*
+ * linux/ipc/util.h
+ * Copyright (C) 1999 Christoph Rohland
+ *
+ * ipc helper functions (c) 1999 Manfred Spraul <manfred@colorfullife.com>
+ * namespaces support.      2006 OpenVZ, SWsoft Inc.
+ *                               Pavel Emelianov <xemul@openvz.org>
+ */
+
+#ifndef _IPC_UTIL_H
+#define _IPC_UTIL_H
+
+#include <linux/unistd.h>
+#include <linux/err.h>
+
+#define SEQ_MULTIPLIER	(IPCMNI)
+
+void sem_init(void);
+void msg_init(void);
+void shm_init(void);
+
+struct ipc_namespace;
+
+#ifdef CONFIG_POSIX_MQUEUE
+extern void mq_clear_sbinfo(struct ipc_namespace *ns);
+extern void mq_put_mnt(struct ipc_namespace *ns);
+#else
+static inline void mq_clear_sbinfo(struct ipc_namespace *ns) { }
+static inline void mq_put_mnt(struct ipc_namespace *ns) { }
+#endif
+
+#ifdef CONFIG_SYSVIPC
+void sem_init_ns(struct ipc_namespace *ns);
+void msg_init_ns(struct ipc_namespace *ns);
+void shm_init_ns(struct ipc_namespace *ns);
+
+void sem_exit_ns(struct ipc_namespace *ns);
+void msg_exit_ns(struct ipc_namespace *ns);
+void shm_exit_ns(struct ipc_namespace *ns);
+#else
+static inline void sem_init_ns(struct ipc_namespace *ns) { }
+static inline void msg_init_ns(struct ipc_namespace *ns) { }
+static inline void shm_init_ns(struct ipc_namespace *ns) { }
+
+static inline void sem_exit_ns(struct ipc_namespace *ns) { }
+static inline void msg_exit_ns(struct ipc_namespace *ns) { }
+static inline void shm_exit_ns(struct ipc_namespace *ns) { }
+#endif
+
+struct ipc_rcu {
+	struct rcu_head rcu;
+	atomic_t refcount;
+} ____cacheline_aligned_in_smp;
+
+#define ipc_rcu_to_struct(p)  ((void *)(p+1))
+
+/*
+ * Structure that holds the parameters needed by the ipc operations
+ * (see after)
+ */
+struct ipc_params {
+	key_t key;
+	int flg;
+	union {
+		size_t size;	/* for shared memories */
+		int nsems;	/* for semaphores */
+	} u;			/* holds the getnew() specific param */
+};
+
+/*
+ * Structure that holds some ipc operations. This structure is used to unify
+ * the calls to sys_msgget(), sys_semget(), sys_shmget()
+ *      . routine to call to create a new ipc object. Can be one of newque,
+ *        newary, newseg
+ *      . routine to call to check permissions for a new ipc object.
+ *        Can be one of security_msg_associate, security_sem_associate,
+ *        security_shm_associate
+ *      . routine to call for an extra check if needed
+ */
+struct ipc_ops {
+	int (*getnew)(struct ipc_namespace *, struct ipc_params *);
+	int (*associate)(struct kern_ipc_perm *, int);
+	int (*more_checks)(struct kern_ipc_perm *, struct ipc_params *);
+};
+
+struct seq_file;
+struct ipc_ids;
+
+void ipc_init_ids(struct ipc_ids *);
+#ifdef CONFIG_PROC_FS
+void __init ipc_init_proc_interface(const char *path, const char *header,
+		int ids, int (*show)(struct seq_file *, void *));
+#else
+#define ipc_init_proc_interface(path, header, ids, show) do {} while (0)
+#endif
+
+#define IPC_SEM_IDS	0
+#define IPC_MSG_IDS	1
+#define IPC_SHM_IDS	2
+
+#define ipcid_to_idx(id) ((id) % SEQ_MULTIPLIER)
+#define ipcid_to_seqx(id) ((id) / SEQ_MULTIPLIER)
+#define IPCID_SEQ_MAX min_t(int, INT_MAX/SEQ_MULTIPLIER, USHRT_MAX)
+
+/* must be called with ids->rwsem acquired for writing */
+int ipc_addid(struct ipc_ids *, struct kern_ipc_perm *, int);
+
+/* must be called with ids->rwsem acquired for reading */
+int ipc_get_maxid(struct ipc_ids *);
+
+/* must be called with both locks acquired. */
+void ipc_rmid(struct ipc_ids *, struct kern_ipc_perm *);
+
+/* must be called with ipcp locked */
+int ipcperms(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp, short flg);
+
+/* for rare, potentially huge allocations.
+ * both function can sleep
+ */
+void *ipc_alloc(int size);
+void ipc_free(void *ptr, int size);
+
+/*
+ * For allocation that need to be freed by RCU.
+ * Objects are reference counted, they start with reference count 1.
+ * getref increases the refcount, the putref call that reduces the recount
+ * to 0 schedules the rcu destruction. Caller must guarantee locking.
+ */
+void *ipc_rcu_alloc(int size);
+int ipc_rcu_getref(void *ptr);
+void ipc_rcu_putref(void *ptr, void (*func)(struct rcu_head *head));
+void ipc_rcu_free(struct rcu_head *head);
+
+struct kern_ipc_perm *ipc_lock(struct ipc_ids *, int);
+struct kern_ipc_perm *ipc_obtain_object(struct ipc_ids *ids, int id);
+
+void kernel_to_ipc64_perm(struct kern_ipc_perm *in, struct ipc64_perm *out);
+void ipc64_perm_to_ipc_perm(struct ipc64_perm *in, struct ipc_perm *out);
+int ipc_update_perm(struct ipc64_perm *in, struct kern_ipc_perm *out);
+struct kern_ipc_perm *ipcctl_pre_down_nolock(struct ipc_namespace *ns,
+					     struct ipc_ids *ids, int id, int cmd,
+					     struct ipc64_perm *perm, int extra_perm);
+
+#ifndef CONFIG_ARCH_WANT_IPC_PARSE_VERSION
+/* On IA-64, we always use the "64-bit version" of the IPC structures.  */
+# define ipc_parse_version(cmd)	IPC_64
+#else
+int ipc_parse_version(int *cmd);
+#endif
+
+extern void free_msg(struct msg_msg *msg);
+extern struct msg_msg *load_msg(const void __user *src, size_t len);
+extern struct msg_msg *copy_msg(struct msg_msg *src, struct msg_msg *dst);
+extern int store_msg(void __user *dest, struct msg_msg *msg, size_t len);
+
+extern void recompute_msgmni(struct ipc_namespace *);
+
+static inline int ipc_buildid(int id, int seq)
+{
+	return SEQ_MULTIPLIER * seq + id;
+}
+
+static inline int ipc_checkid(struct kern_ipc_perm *ipcp, int uid)
+{
+	return uid / SEQ_MULTIPLIER != ipcp->seq;
+}
+
+static inline void ipc_lock_object(struct kern_ipc_perm *perm)
+{
+	spin_lock(&perm->lock);
+}
+
+static inline void ipc_unlock_object(struct kern_ipc_perm *perm)
+{
+	spin_unlock(&perm->lock);
+}
+
+static inline void ipc_assert_locked_object(struct kern_ipc_perm *perm)
+{
+	assert_spin_locked(&perm->lock);
+}
+
+static inline void ipc_unlock(struct kern_ipc_perm *perm)
+{
+	ipc_unlock_object(perm);
+	rcu_read_unlock();
+}
+
+/*
+ * ipc_valid_object() - helper to sort out IPC_RMID races for codepaths
+ * where the respective ipc_ids.rwsem is not being held down.
+ * Checks whether the ipc object is still around or if it's gone already, as
+ * ipc_rmid() may have already freed the ID while the ipc lock was spinning.
+ * Needs to be called with kern_ipc_perm.lock held -- exception made for one
+ * checkpoint case at sys_semtimedop() as noted in code commentary.
+ */
+static inline bool ipc_valid_object(struct kern_ipc_perm *perm)
+{
+	return !perm->deleted;
+}
+
+struct kern_ipc_perm *ipc_obtain_object_check(struct ipc_ids *ids, int id);
+int ipcget(struct ipc_namespace *ns, struct ipc_ids *ids,
+			const struct ipc_ops *ops, struct ipc_params *params);
+void free_ipcs(struct ipc_namespace *ns, struct ipc_ids *ids,
+		void (*free)(struct ipc_namespace *, struct kern_ipc_perm *));
+#endif