add idl4k kernel firmware version 1.13.0.105

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 ipcns_notifier.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
+

kernel/ipc/compat.c

@@ -0,0 +1,688 @@
+/*
+ * 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/slab.h>
+#include <linux/syscalls.h>
+
+#include <linux/mutex.h>
+#include <asm/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;
+};
+
+extern int sem_ctls[];
+#define sc_semopm	(sem_ctls[2])
+
+static inline int compat_ipc_parse_version(int *cmd)
+{
+	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;
+}
+
+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 *up)
+{
+	int err;
+	__compat_uid_t u;
+	__compat_gid_t g;
+
+	err  = __put_user(p->key, &up->key);
+	SET_UID(u, p->uid);
+	err |= __put_user(u, &up->uid);
+	SET_GID(g, p->gid);
+	err |= __put_user(g, &up->gid);
+	SET_UID(u, p->cuid);
+	err |= __put_user(u, &up->cuid);
+	SET_GID(g, p->cgid);
+	err |= __put_user(g, &up->cgid);
+	err |= __put_user(p->mode, &up->mode);
+	err |= __put_user(p->seq, &up->seq);
+	return err;
+}
+
+static inline int get_compat_semid64_ds(struct semid64_ds *s64,
+					struct compat_semid64_ds __user *up64)
+{
+	if (!access_ok (VERIFY_READ, up64, sizeof(*up64)))
+		return -EFAULT;
+	return __get_compat_ipc64_perm(&s64->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 *s64,
+					struct compat_semid64_ds __user *up64)
+{
+	int err;
+
+	if (!access_ok (VERIFY_WRITE, up64, sizeof(*up64)))
+		return -EFAULT;
+	err  = __put_compat_ipc64_perm(&s64->sem_perm, &up64->sem_perm);
+	err |= __put_user(s64->sem_otime, &up64->sem_otime);
+	err |= __put_user(s64->sem_ctime, &up64->sem_ctime);
+	err |= __put_user(s64->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;
+}
+
+long compat_sys_semctl(int first, int second, int third, void __user *uptr)
+{
+	union semun fourth;
+	u32 pad;
+	int err, err2;
+	struct semid64_ds s64;
+	struct semid64_ds __user *up64;
+	int version = compat_ipc_parse_version(&third);
+
+	memset(&s64, 0, sizeof(s64));
+
+	if (!uptr)
+		return -EINVAL;
+	if (get_user(pad, (u32 __user *) uptr))
+		return -EFAULT;
+	if ((third & (~IPC_64)) == SETVAL)
+		fourth.val = (int) pad;
+	else
+		fourth.__pad = 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(s64));
+		fourth.__pad = up64;
+		err = sys_semctl(first, second, third, fourth);
+		if (err < 0)
+			break;
+		if (copy_from_user(&s64, up64, sizeof(s64)))
+			err2 = -EFAULT;
+		else if (version == IPC_64)
+			err2 = put_compat_semid64_ds(&s64, compat_ptr(pad));
+		else
+			err2 = put_compat_semid_ds(&s64, compat_ptr(pad));
+		if (err2)
+			err = -EFAULT;
+		break;
+
+	case IPC_SET:
+		if (version == IPC_64) {
+			err = get_compat_semid64_ds(&s64, compat_ptr(pad));
+		} else {
+			err = get_compat_semid_ds(&s64, compat_ptr(pad));
+		}
+		up64 = compat_alloc_user_space(sizeof(s64));
+		if (copy_to_user(up64, &s64, sizeof(s64)))
+			err = -EFAULT;
+		if (err)
+			break;
+
+		fourth.__pad = up64;
+		err = sys_semctl(first, second, third, fourth);
+		break;
+
+	default:
+		err = -EINVAL;
+		break;
+	}
+	return err;
+}
+
+long compat_sys_msgsnd(int first, int second, int third, void __user *uptr)
+{
+	struct compat_msgbuf __user *up = uptr;
+	long type;
+
+	if (first < 0)
+		return -EINVAL;
+	if (second < 0)
+		return -EINVAL;
+
+	if (get_user(type, &up->mtype))
+		return -EFAULT;
+
+	return do_msgsnd(first, type, up->mtext, second, third);
+}
+
+long compat_sys_msgrcv(int first, int second, int msgtyp, int third,
+			   int version, void __user *uptr)
+{
+	struct compat_msgbuf __user *up;
+	long type;
+	int err;
+
+	if (first < 0)
+		return -EINVAL;
+	if (second < 0)
+		return -EINVAL;
+
+	if (!version) {
+		struct compat_ipc_kludge ipck;
+		err = -EINVAL;
+		if (!uptr)
+			goto out;
+		err = -EFAULT;
+		if (copy_from_user (&ipck, uptr, sizeof(ipck)))
+			goto out;
+		uptr = compat_ptr(ipck.msgp);
+		msgtyp = ipck.msgtyp;
+	}
+	up = uptr;
+	err = do_msgrcv(first, &type, up->mtext, second, msgtyp, third);
+	if (err < 0)
+		goto out;
+	if (put_user(type, &up->mtype))
+		err = -EFAULT;
+out:
+	return err;
+}
+
+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;
+}
+
+long compat_sys_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;
+}
+
+long compat_sys_shmat(int first, int second, compat_uptr_t third, int version,
+			void __user *uptr)
+{
+	int err;
+	unsigned long raddr;
+	compat_ulong_t __user *uaddr;
+
+	if (version == 1)
+		return -EINVAL;
+	err = do_shmat(first, uptr, second, &raddr);
+	if (err < 0)
+		return err;
+	uaddr = compat_ptr(third);
+	return put_user(raddr, uaddr);
+}
+
+static inline int get_compat_shmid64_ds(struct shmid64_ds *s64,
+					struct compat_shmid64_ds __user *up64)
+{
+	if (!access_ok(VERIFY_READ, up64, sizeof(*up64)))
+		return -EFAULT;
+	return __get_compat_ipc64_perm(&s64->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 *s64,
+					struct compat_shmid64_ds __user *up64)
+{
+	int err;
+
+	if (!access_ok(VERIFY_WRITE, up64, sizeof(*up64)))
+		return -EFAULT;
+	err  = __put_compat_ipc64_perm(&s64->shm_perm, &up64->shm_perm);
+	err |= __put_user(s64->shm_atime, &up64->shm_atime);
+	err |= __put_user(s64->shm_dtime, &up64->shm_dtime);
+	err |= __put_user(s64->shm_ctime, &up64->shm_ctime);
+	err |= __put_user(s64->shm_segsz, &up64->shm_segsz);
+	err |= __put_user(s64->shm_nattch, &up64->shm_nattch);
+	err |= __put_user(s64->shm_cpid, &up64->shm_cpid);
+	err |= __put_user(s64->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;
+}
+
+long compat_sys_shmctl(int first, int second, void __user *uptr)
+{
+	void __user *p;
+	struct shmid64_ds s64;
+	struct shminfo64 smi;
+	int err, err2;
+	int version = compat_ipc_parse_version(&second);
+
+	memset(&s64, 0, sizeof(s64));
+
+	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(&s64, uptr);
+		} else {
+			err = get_compat_shmid_ds(&s64, uptr);
+		}
+		if (err)
+			break;
+		p = compat_alloc_user_space(sizeof(s64));
+		if (copy_to_user(p, &s64, sizeof(s64)))
+			err = -EFAULT;
+		else
+			err = sys_shmctl(first, second, p);
+		break;
+
+	case IPC_STAT:
+	case SHM_STAT:
+		p = compat_alloc_user_space(sizeof(s64));
+		err = sys_shmctl(first, second, p);
+		if (err < 0)
+			break;
+		if (copy_from_user(&s64, p, sizeof(s64)))
+			err2 = -EFAULT;
+		else if (version == IPC_64)
+			err2 = put_compat_shmid64_ds(&s64, uptr);
+		else
+			err2 = put_compat_shmid_ds(&s64, 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;
+}
+
+long compat_sys_semtimedop(int semid, struct sembuf __user *tsems,
+		unsigned nsops, const struct compat_timespec __user *timeout)
+{
+	struct timespec __user *ts64 = NULL;
+	if (timeout) {
+		struct timespec ts;
+		ts64 = compat_alloc_user_space(sizeof(*ts64));
+		if (get_compat_timespec(&ts, timeout))
+			return -EFAULT;
+		if (copy_to_user(ts64, &ts, sizeof(ts)))
+			return -EFAULT;
+	}
+	return sys_semtimedop(semid, tsems, nsops, ts64);
+}

kernel/ipc/compat_mq.c

@@ -0,0 +1,151 @@
+/*
+ *  ipc/compat_mq.c
+ *    32 bit emulation for POSIX message queue system calls
+ *
+ *    Copyright (C) 2004 IBM Deutschland Entwicklung GmbH, IBM Corporation
+ *    Author: Arnd Bergmann <arnd@arndb.de>
+ */
+
+#include <linux/compat.h>
+#include <linux/fs.h>
+#include <linux/kernel.h>
+#include <linux/mqueue.h>
+#include <linux/syscalls.h>
+
+#include <asm/uaccess.h>
+
+struct compat_mq_attr {
+	compat_long_t mq_flags;      /* message queue flags		     */
+	compat_long_t mq_maxmsg;     /* maximum number of messages	     */
+	compat_long_t mq_msgsize;    /* maximum message size		     */
+	compat_long_t mq_curmsgs;    /* number of messages currently queued  */
+	compat_long_t __reserved[4]; /* ignored for input, zeroed for output */
+};
+
+static inline int get_compat_mq_attr(struct mq_attr *attr,
+			const struct compat_mq_attr __user *uattr)
+{
+	if (!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);
+}
+
+asmlinkage long compat_sys_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);
+}
+
+static int compat_prepare_timeout(struct timespec __user * *p,
+				  const struct compat_timespec __user *u)
+{
+	struct timespec ts;
+	if (!u) {
+		*p = NULL;
+		return 0;
+	}
+	*p = compat_alloc_user_space(sizeof(ts));
+	if (get_compat_timespec(&ts, u) || copy_to_user(*p, &ts, sizeof(ts)))
+		return -EFAULT;
+	return 0;
+}
+
+asmlinkage long compat_sys_mq_timedsend(mqd_t mqdes,
+			const char __user *u_msg_ptr,
+			size_t msg_len, unsigned int msg_prio,
+			const struct compat_timespec __user *u_abs_timeout)
+{
+	struct timespec __user *u_ts;
+
+	if (compat_prepare_timeout(&u_ts, u_abs_timeout))
+		return -EFAULT;
+
+	return sys_mq_timedsend(mqdes, u_msg_ptr, msg_len,
+			msg_prio, u_ts);
+}
+
+asmlinkage ssize_t compat_sys_mq_timedreceive(mqd_t mqdes,
+			char __user *u_msg_ptr,
+			size_t msg_len, unsigned int __user *u_msg_prio,
+			const struct compat_timespec __user *u_abs_timeout)
+{
+	struct timespec __user *u_ts;
+	if (compat_prepare_timeout(&u_ts, u_abs_timeout))
+		return -EFAULT;
+
+	return sys_mq_timedreceive(mqdes, u_msg_ptr, msg_len,
+			u_msg_prio, u_ts);
+}
+
+asmlinkage long compat_sys_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);
+}
+
+asmlinkage long compat_sys_mq_getsetattr(mqd_t mqdes,
+			const struct compat_mq_attr __user *u_mqstat,
+			struct compat_mq_attr __user *u_omqstat)
+{
+	struct mq_attr mqstat;
+	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;
+}

kernel/ipc/ipc_sysctl.c

@@ -0,0 +1,289 @@
+/*
+ *  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(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(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_callback_dointvec(ctl_table *table, int write,
+	void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+	struct ctl_table ipc_table;
+	size_t lenp_bef = *lenp;
+	int rc;
+
+	memcpy(&ipc_table, table, sizeof(ipc_table));
+	ipc_table.data = get_ipc(table);
+
+	rc = proc_dointvec(&ipc_table, write, buffer, lenp, ppos);
+
+	if (write && !rc && lenp_bef == *lenp)
+		/*
+		 * Tunable has successfully been changed by hand. Disable its
+		 * automatic adjustment. This simply requires unregistering
+		 * the notifiers that trigger recalculation.
+		 */
+		unregister_ipcns_notifier(current->nsproxy->ipc_ns);
+
+	return rc;
+}
+
+static int proc_ipc_doulongvec_minmax(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);
+}
+
+/*
+ * Routine that is called when the file "auto_msgmni" has successfully been
+ * written.
+ * Two values are allowed:
+ * 0: unregister msgmni's callback routine from the ipc namespace notifier
+ *    chain. This means that msgmni won't be recomputed anymore upon memory
+ *    add/remove or ipc namespace creation/removal.
+ * 1: register back the callback routine.
+ */
+static void ipc_auto_callback(int val)
+{
+	if (!val)
+		unregister_ipcns_notifier(current->nsproxy->ipc_ns);
+	else {
+		/*
+		 * Re-enable automatic recomputing only if not already
+		 * enabled.
+		 */
+		recompute_msgmni(current->nsproxy->ipc_ns);
+		cond_register_ipcns_notifier(current->nsproxy->ipc_ns);
+	}
+}
+
+static int proc_ipcauto_dointvec_minmax(ctl_table *table, int write,
+	void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+	struct ctl_table ipc_table;
+	size_t lenp_bef = *lenp;
+	int oldval;
+	int rc;
+
+	memcpy(&ipc_table, table, sizeof(ipc_table));
+	ipc_table.data = get_ipc(table);
+	oldval = *((int *)(ipc_table.data));
+
+	rc = proc_dointvec_minmax(&ipc_table, write, buffer, lenp, ppos);
+
+	if (write && !rc && lenp_bef == *lenp) {
+		int newval = *((int *)(ipc_table.data));
+		/*
+		 * The file "auto_msgmni" has correctly been set.
+		 * React by (un)registering the corresponding tunable, if the
+		 * value has changed.
+		 */
+		if (newval != oldval)
+			ipc_auto_callback(newval);
+	}
+
+	return rc;
+}
+
+#else
+#define proc_ipc_doulongvec_minmax NULL
+#define proc_ipc_dointvec	   NULL
+#define proc_ipc_callback_dointvec NULL
+#define proc_ipcauto_dointvec_minmax NULL
+#endif
+
+#ifdef CONFIG_SYSCTL_SYSCALL
+/* The generic sysctl ipc data routine. */
+static int sysctl_ipc_data(ctl_table *table,
+		void __user *oldval, size_t __user *oldlenp,
+		void __user *newval, size_t newlen)
+{
+	size_t len;
+	void *data;
+
+	/* Get out of I don't have a variable */
+	if (!table->data || !table->maxlen)
+		return -ENOTDIR;
+
+	data = get_ipc(table);
+	if (!data)
+		return -ENOTDIR;
+
+	if (oldval && oldlenp) {
+		if (get_user(len, oldlenp))
+			return -EFAULT;
+		if (len) {
+			if (len > table->maxlen)
+				len = table->maxlen;
+			if (copy_to_user(oldval, data, len))
+				return -EFAULT;
+			if (put_user(len, oldlenp))
+				return -EFAULT;
+		}
+	}
+
+	if (newval && newlen) {
+		if (newlen > table->maxlen)
+			newlen = table->maxlen;
+
+		if (copy_from_user(data, newval, newlen))
+			return -EFAULT;
+	}
+	return 1;
+}
+
+static int sysctl_ipc_registered_data(ctl_table *table,
+		void __user *oldval, size_t __user *oldlenp,
+		void __user *newval, size_t newlen)
+{
+	int rc;
+
+	rc = sysctl_ipc_data(table, oldval, oldlenp, newval, newlen);
+
+	if (newval && newlen && rc > 0)
+		/*
+		 * Tunable has successfully been changed from userland
+		 */
+		unregister_ipcns_notifier(current->nsproxy->ipc_ns);
+
+	return rc;
+}
+#else
+#define sysctl_ipc_data NULL
+#define sysctl_ipc_registered_data NULL
+#endif
+
+static int zero;
+static int one = 1;
+
+static struct ctl_table ipc_kern_table[] = {
+	{
+		.ctl_name	= KERN_SHMMAX,
+		.procname	= "shmmax",
+		.data		= &init_ipc_ns.shm_ctlmax,
+		.maxlen		= sizeof (init_ipc_ns.shm_ctlmax),
+		.mode		= 0644,
+		.proc_handler	= proc_ipc_doulongvec_minmax,
+		.strategy	= sysctl_ipc_data,
+	},
+	{
+		.ctl_name	= KERN_SHMALL,
+		.procname	= "shmall",
+		.data		= &init_ipc_ns.shm_ctlall,
+		.maxlen		= sizeof (init_ipc_ns.shm_ctlall),
+		.mode		= 0644,
+		.proc_handler	= proc_ipc_doulongvec_minmax,
+		.strategy	= sysctl_ipc_data,
+	},
+	{
+		.ctl_name	= KERN_SHMMNI,
+		.procname	= "shmmni",
+		.data		= &init_ipc_ns.shm_ctlmni,
+		.maxlen		= sizeof (init_ipc_ns.shm_ctlmni),
+		.mode		= 0644,
+		.proc_handler	= proc_ipc_dointvec,
+		.strategy	= sysctl_ipc_data,
+	},
+	{
+		.ctl_name	= KERN_MSGMAX,
+		.procname	= "msgmax",
+		.data		= &init_ipc_ns.msg_ctlmax,
+		.maxlen		= sizeof (init_ipc_ns.msg_ctlmax),
+		.mode		= 0644,
+		.proc_handler	= proc_ipc_dointvec,
+		.strategy	= sysctl_ipc_data,
+	},
+	{
+		.ctl_name	= KERN_MSGMNI,
+		.procname	= "msgmni",
+		.data		= &init_ipc_ns.msg_ctlmni,
+		.maxlen		= sizeof (init_ipc_ns.msg_ctlmni),
+		.mode		= 0644,
+		.proc_handler	= proc_ipc_callback_dointvec,
+		.strategy	= sysctl_ipc_registered_data,
+	},
+	{
+		.ctl_name	= KERN_MSGMNB,
+		.procname	=  "msgmnb",
+		.data		= &init_ipc_ns.msg_ctlmnb,
+		.maxlen		= sizeof (init_ipc_ns.msg_ctlmnb),
+		.mode		= 0644,
+		.proc_handler	= proc_ipc_dointvec,
+		.strategy	= sysctl_ipc_data,
+	},
+	{
+		.ctl_name	= KERN_SEM,
+		.procname	= "sem",
+		.data		= &init_ipc_ns.sem_ctls,
+		.maxlen		= 4*sizeof (int),
+		.mode		= 0644,
+		.proc_handler	= proc_ipc_dointvec,
+		.strategy	= sysctl_ipc_data,
+	},
+	{
+		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "auto_msgmni",
+		.data		= &init_ipc_ns.auto_msgmni,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_ipcauto_dointvec_minmax,
+		.extra1		= &zero,
+		.extra2		= &one,
+	},
+	{}
+};
+
+static struct ctl_table ipc_root_table[] = {
+	{
+		.ctl_name	= CTL_KERN,
+		.procname	= "kernel",
+		.mode		= 0555,
+		.child		= ipc_kern_table,
+	},
+	{}
+};
+
+static int __init ipc_sysctl_init(void)
+{
+	register_sysctl_table(ipc_root_table);
+	return 0;
+}
+
+__initcall(ipc_sysctl_init);

kernel/ipc/ipcns_notifier.c

@@ -0,0 +1,92 @@
+/*
+ * linux/ipc/ipcns_notifier.c
+ * Copyright (C) 2007 BULL SA. Nadia Derbey
+ *
+ * Notification mechanism for ipc namespaces:
+ * The callback routine registered in the memory chain invokes the ipcns
+ * notifier chain with the IPCNS_MEMCHANGED event.
+ * Each callback routine registered in the ipcns namespace recomputes msgmni
+ * for the owning namespace.
+ */
+
+#include <linux/msg.h>
+#include <linux/rcupdate.h>
+#include <linux/notifier.h>
+#include <linux/nsproxy.h>
+#include <linux/ipc_namespace.h>
+
+#include "util.h"
+
+
+
+static BLOCKING_NOTIFIER_HEAD(ipcns_chain);
+
+
+static int ipcns_callback(struct notifier_block *self,
+				unsigned long action, void *arg)
+{
+	struct ipc_namespace *ns;
+
+	switch (action) {
+	case IPCNS_MEMCHANGED:   /* amount of lowmem has changed */
+	case IPCNS_CREATED:
+	case IPCNS_REMOVED:
+		/*
+		 * It's time to recompute msgmni
+		 */
+		ns = container_of(self, struct ipc_namespace, ipcns_nb);
+		/*
+		 * No need to get a reference on the ns: the 1st job of
+		 * free_ipc_ns() is to unregister the callback routine.
+		 * blocking_notifier_chain_unregister takes the wr lock to do
+		 * it.
+		 * When this callback routine is called the rd lock is held by
+		 * blocking_notifier_call_chain.
+		 * So the ipc ns cannot be freed while we are here.
+		 */
+		recompute_msgmni(ns);
+		break;
+	default:
+		break;
+	}
+
+	return NOTIFY_OK;
+}
+
+int register_ipcns_notifier(struct ipc_namespace *ns)
+{
+	int rc;
+
+	memset(&ns->ipcns_nb, 0, sizeof(ns->ipcns_nb));
+	ns->ipcns_nb.notifier_call = ipcns_callback;
+	ns->ipcns_nb.priority = IPCNS_CALLBACK_PRI;
+	rc = blocking_notifier_chain_register(&ipcns_chain, &ns->ipcns_nb);
+	if (!rc)
+		ns->auto_msgmni = 1;
+	return rc;
+}
+
+int cond_register_ipcns_notifier(struct ipc_namespace *ns)
+{
+	int rc;
+
+	memset(&ns->ipcns_nb, 0, sizeof(ns->ipcns_nb));
+	ns->ipcns_nb.notifier_call = ipcns_callback;
+	ns->ipcns_nb.priority = IPCNS_CALLBACK_PRI;
+	rc = blocking_notifier_chain_cond_register(&ipcns_chain,
+							&ns->ipcns_nb);
+	if (!rc)
+		ns->auto_msgmni = 1;
+	return rc;
+}
+
+void unregister_ipcns_notifier(struct ipc_namespace *ns)
+{
+	blocking_notifier_chain_unregister(&ipcns_chain, &ns->ipcns_nb);
+	ns->auto_msgmni = 0;
+}
+
+int ipcns_notify(unsigned long val)
+{
+	return blocking_notifier_call_chain(&ipcns_chain, val, NULL);
+}

kernel/ipc/mq_sysctl.c

@@ -0,0 +1,116 @@
+/*
+ *  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>
+
+/*
+ * Define the ranges various user-specified maximum values can
+ * be set to.
+ */
+#define MIN_MSGMAX	1		/* min value for msg_max */
+#define MAX_MSGMAX	HARD_MSGMAX	/* max value for msg_max */
+#define MIN_MSGSIZEMAX	128		/* min value for msgsize_max */
+#define MAX_MSGSIZEMAX	(8192*128)	/* max value for msgsize_max */
+
+#ifdef CONFIG_PROC_SYSCTL
+static void *get_mq(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(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(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 = MAX_MSGMAX;
+
+static int msg_maxsize_limit_min = MIN_MSGSIZEMAX;
+static int msg_maxsize_limit_max = MAX_MSGSIZEMAX;
+
+static 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,
+	},
+	{ .ctl_name = 0 }
+};
+
+static ctl_table mq_sysctl_dir[] = {
+	{
+		.procname	= "mqueue",
+		.mode		= 0555,
+		.child		= mq_sysctls,
+	},
+	{ .ctl_name = 0 }
+};
+
+static ctl_table mq_sysctl_root[] = {
+	{
+		.ctl_name	= CTL_FS,
+		.procname	= "fs",
+		.mode		= 0555,
+		.child		= mq_sysctl_dir,
+	},
+	{ .ctl_name = 0 }
+};
+
+struct ctl_table_header *mq_register_sysctl_table(void)
+{
+	return register_sysctl_table(mq_sysctl_root);
+}

kernel/ipc/msg.c

@@ -0,0 +1,945 @@
+/*
+ * 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/slab.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 <asm/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;
+
+	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 msg_ids(ns)	((ns)->ids[IPC_MSG_IDS])
+
+#define msg_unlock(msq)		ipc_unlock(&(msq)->q_perm)
+
+static void freeque(struct ipc_namespace *, struct kern_ipc_perm *);
+static int newque(struct ipc_namespace *, struct ipc_params *);
+#ifdef CONFIG_PROC_FS
+static int sysvipc_msg_proc_show(struct seq_file *s, void *it);
+#endif
+
+/*
+ * Scale msgmni with the available lowmem size: the memory dedicated to msg
+ * queues should occupy at most 1/MSG_MEM_SCALE of lowmem.
+ * Also take into account the number of nsproxies created so far.
+ * This should be done staying within the (MSGMNI , IPCMNI/nr_ipc_ns) range.
+ */
+void recompute_msgmni(struct ipc_namespace *ns)
+{
+	struct sysinfo i;
+	unsigned long allowed;
+	int nb_ns;
+
+	si_meminfo(&i);
+	allowed = (((i.totalram - i.totalhigh) / MSG_MEM_SCALE) * i.mem_unit)
+		/ MSGMNB;
+	nb_ns = atomic_read(&nr_ipc_ns);
+	allowed /= nb_ns;
+
+	if (allowed < MSGMNI) {
+		ns->msg_ctlmni = MSGMNI;
+		return;
+	}
+
+	if (allowed > IPCMNI / nb_ns) {
+		ns->msg_ctlmni = IPCMNI / nb_ns;
+		return;
+	}
+
+	ns->msg_ctlmni = allowed;
+}
+
+void msg_init_ns(struct ipc_namespace *ns)
+{
+	ns->msg_ctlmax = MSGMAX;
+	ns->msg_ctlmnb = MSGMNB;
+
+	recompute_msgmni(ns);
+
+	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
+
+void __init msg_init(void)
+{
+	msg_init_ns(&init_ipc_ns);
+
+	printk(KERN_INFO "msgmni has been set to %d\n",
+		init_ipc_ns.msg_ctlmni);
+
+	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);
+}
+
+/*
+ * msg_lock_(check_) routines are called in the paths where the rw_mutex
+ * is not held.
+ */
+static inline struct msg_queue *msg_lock(struct ipc_namespace *ns, int id)
+{
+	struct kern_ipc_perm *ipcp = ipc_lock(&msg_ids(ns), id);
+
+	if (IS_ERR(ipcp))
+		return (struct msg_queue *)ipcp;
+
+	return container_of(ipcp, struct msg_queue, q_perm);
+}
+
+static inline struct msg_queue *msg_lock_check(struct ipc_namespace *ns,
+						int id)
+{
+	struct kern_ipc_perm *ipcp = ipc_lock_check(&msg_ids(ns), id);
+
+	if (IS_ERR(ipcp))
+		return (struct msg_queue *)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);
+}
+
+/**
+ * newque - Create a new msg queue
+ * @ns: namespace
+ * @params: ptr to the structure that contains the key and msgflg
+ *
+ * Called with msg_ids.rw_mutex 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);
+		return retval;
+	}
+
+	/*
+	 * ipc_addid() locks msq
+	 */
+	id = ipc_addid(&msg_ids(ns), &msq->q_perm, ns->msg_ctlmni);
+	if (id < 0) {
+		security_msg_queue_free(msq);
+		ipc_rcu_putref(msq);
+		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);
+
+	msg_unlock(msq);
+
+	return msq->q_perm.id;
+}
+
+static inline void ss_add(struct msg_queue *msq, struct msg_sender *mss)
+{
+	mss->tsk = current;
+	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 list_head *tmp;
+
+	tmp = h->next;
+	while (tmp != h) {
+		struct msg_sender *mss;
+
+		mss = list_entry(tmp, struct msg_sender, list);
+		tmp = tmp->next;
+		if (kill)
+			mss->list.next = NULL;
+		wake_up_process(mss->tsk);
+	}
+}
+
+static void expunge_all(struct msg_queue *msq, int res)
+{
+	struct list_head *tmp;
+
+	tmp = msq->q_receivers.next;
+	while (tmp != &msq->q_receivers) {
+		struct msg_receiver *msr;
+
+		msr = list_entry(tmp, struct msg_receiver, r_list);
+		tmp = tmp->next;
+		msr->r_msg = NULL;
+		wake_up_process(msr->r_tsk);
+		smp_mb();
+		msr->r_msg = ERR_PTR(res);
+	}
+}
+
+/*
+ * 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.rw_mutex (writer) and the spinlock for this message queue are held
+ * before freeque() is called. msg_ids.rw_mutex remains locked on exit.
+ */
+static void freeque(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp)
+{
+	struct list_head *tmp;
+	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);
+	msg_unlock(msq);
+
+	tmp = msq->q_messages.next;
+	while (tmp != &msq->q_messages) {
+		struct msg_msg *msg = list_entry(tmp, struct msg_msg, m_list);
+
+		tmp = tmp->next;
+		atomic_dec(&ns->msg_hdrs);
+		free_msg(msg);
+	}
+	atomic_sub(msq->q_cbytes, &ns->msg_bytes);
+	security_msg_queue_free(msq);
+	ipc_rcu_putref(msq);
+}
+
+/*
+ * Called with msg_ids.rw_mutex 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;
+	struct ipc_ops msg_ops;
+	struct ipc_params msg_params;
+
+	ns = current->nsproxy->ipc_ns;
+
+	msg_ops.getnew = newque;
+	msg_ops.associate = msg_security;
+	msg_ops.more_checks = NULL;
+
+	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 > USHORT_MAX)
+			out.msg_cbytes	= USHORT_MAX;
+		else
+			out.msg_cbytes	= in->msg_cbytes;
+		out.msg_lcbytes		= in->msg_cbytes;
+
+		if (in->msg_qnum > USHORT_MAX)
+			out.msg_qnum	= USHORT_MAX;
+		else
+			out.msg_qnum	= in->msg_qnum;
+
+		if (in->msg_qbytes > USHORT_MAX)
+			out.msg_qbytes	= USHORT_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 rw_mutex
+ * to be held in write mode.
+ * NOTE: no locks must be held, the rw_mutex 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 msqid64;
+	struct msg_queue *msq;
+	int err;
+
+	if (cmd == IPC_SET) {
+		if (copy_msqid_from_user(&msqid64, buf, version))
+			return -EFAULT;
+	}
+
+	ipcp = ipcctl_pre_down(&msg_ids(ns), msqid, cmd,
+			       &msqid64.msg_perm, msqid64.msg_qbytes);
+	if (IS_ERR(ipcp))
+		return PTR_ERR(ipcp);
+
+	msq = container_of(ipcp, struct msg_queue, q_perm);
+
+	err = security_msg_queue_msgctl(msq, cmd);
+	if (err)
+		goto out_unlock;
+
+	switch (cmd) {
+	case IPC_RMID:
+		freeque(ns, ipcp);
+		goto out_up;
+	case IPC_SET:
+		if (msqid64.msg_qbytes > ns->msg_ctlmnb &&
+		    !capable(CAP_SYS_RESOURCE)) {
+			err = -EPERM;
+			goto out_unlock;
+		}
+
+		msq->q_qbytes = msqid64.msg_qbytes;
+
+		ipc_update_perm(&msqid64.msg_perm, ipcp);
+		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;
+	}
+out_unlock:
+	msg_unlock(msq);
+out_up:
+	up_write(&msg_ids(ns).rw_mutex);
+	return err;
+}
+
+SYSCALL_DEFINE3(msgctl, int, msqid, int, cmd, struct msqid_ds __user *, buf)
+{
+	struct msg_queue *msq;
+	int err, 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:
+	{
+		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).rw_mutex);
+		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).rw_mutex);
+		if (copy_to_user(buf, &msginfo, sizeof(struct msginfo)))
+			return -EFAULT;
+		return (max_id < 0) ? 0 : max_id;
+	}
+	case MSG_STAT:	/* msqid is an index rather than a msg queue id */
+	case IPC_STAT:
+	{
+		struct msqid64_ds tbuf;
+		int success_return;
+
+		if (!buf)
+			return -EFAULT;
+
+		if (cmd == MSG_STAT) {
+			msq = msg_lock(ns, msqid);
+			if (IS_ERR(msq))
+				return PTR_ERR(msq);
+			success_return = msq->q_perm.id;
+		} else {
+			msq = msg_lock_check(ns, msqid);
+			if (IS_ERR(msq))
+				return PTR_ERR(msq);
+			success_return = 0;
+		}
+		err = -EACCES;
+		if (ipcperms(&msq->q_perm, S_IRUGO))
+			goto out_unlock;
+
+		err = security_msg_queue_msgctl(msq, cmd);
+		if (err)
+			goto out_unlock;
+
+		memset(&tbuf, 0, sizeof(tbuf));
+
+		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;
+		msg_unlock(msq);
+		if (copy_msqid_to_user(buf, &tbuf, version))
+			return -EFAULT;
+		return success_return;
+	}
+	case IPC_SET:
+	case IPC_RMID:
+		err = msgctl_down(ns, msqid, cmd, buf, version);
+		return err;
+	default:
+		return  -EINVAL;
+	}
+
+out_unlock:
+	msg_unlock(msq);
+	return err;
+}
+
+static int testmsg(struct msg_msg *msg, long type, int mode)
+{
+	switch(mode)
+	{
+		case SEARCH_ANY:
+			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 list_head *tmp;
+
+	tmp = msq->q_receivers.next;
+	while (tmp != &msq->q_receivers) {
+		struct msg_receiver *msr;
+
+		msr = list_entry(tmp, struct msg_receiver, r_list);
+		tmp = tmp->next;
+		if (testmsg(msg, msr->r_msgtype, msr->r_mode) &&
+		    !security_msg_queue_msgrcv(msq, msg, msr->r_tsk,
+					       msr->r_msgtype, msr->r_mode)) {
+
+			list_del(&msr->r_list);
+			if (msr->r_maxsize < msg->m_ts) {
+				msr->r_msg = NULL;
+				wake_up_process(msr->r_tsk);
+				smp_mb();
+				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);
+				smp_mb();
+				msr->r_msg = msg;
+
+				return 1;
+			}
+		}
+	}
+	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;
+
+	msq = msg_lock_check(ns, msqid);
+	if (IS_ERR(msq)) {
+		err = PTR_ERR(msq);
+		goto out_free;
+	}
+
+	for (;;) {
+		struct msg_sender s;
+
+		err = -EACCES;
+		if (ipcperms(&msq->q_perm, S_IWUGO))
+			goto out_unlock_free;
+
+		err = security_msg_queue_msgsnd(msq, msg, msgflg);
+		if (err)
+			goto out_unlock_free;
+
+		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_unlock_free;
+		}
+		ss_add(msq, &s);
+		ipc_rcu_getref(msq);
+		msg_unlock(msq);
+		schedule();
+
+		ipc_lock_by_ptr(&msq->q_perm);
+		ipc_rcu_putref(msq);
+		if (msq->q_perm.deleted) {
+			err = -EIDRM;
+			goto out_unlock_free;
+		}
+		ss_del(&s);
+
+		if (signal_pending(current)) {
+			err = -ERESTARTNOHAND;
+			goto out_unlock_free;
+		}
+	}
+
+	msq->q_lspid = task_tgid_vnr(current);
+	msq->q_stime = get_seconds();
+
+	if (!pipelined_send(msq, msg)) {
+		/* noone 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_unlock_free:
+	msg_unlock(msq);
+out_free:
+	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)
+{
+	/*
+	 *  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;
+}
+
+long do_msgrcv(int msqid, long *pmtype, void __user *mtext,
+		size_t msgsz, long msgtyp, int msgflg)
+{
+	struct msg_queue *msq;
+	struct msg_msg *msg;
+	int mode;
+	struct ipc_namespace *ns;
+
+	if (msqid < 0 || (long) msgsz < 0)
+		return -EINVAL;
+	mode = convert_mode(&msgtyp, msgflg);
+	ns = current->nsproxy->ipc_ns;
+
+	msq = msg_lock_check(ns, msqid);
+	if (IS_ERR(msq))
+		return PTR_ERR(msq);
+
+	for (;;) {
+		struct msg_receiver msr_d;
+		struct list_head *tmp;
+
+		msg = ERR_PTR(-EACCES);
+		if (ipcperms(&msq->q_perm, S_IRUGO))
+			goto out_unlock;
+
+		msg = ERR_PTR(-EAGAIN);
+		tmp = msq->q_messages.next;
+		while (tmp != &msq->q_messages) {
+			struct msg_msg *walk_msg;
+
+			walk_msg = list_entry(tmp, struct msg_msg, m_list);
+			if (testmsg(walk_msg, msgtyp, mode) &&
+			    !security_msg_queue_msgrcv(msq, walk_msg, current,
+						       msgtyp, mode)) {
+
+				msg = walk_msg;
+				if (mode == SEARCH_LESSEQUAL &&
+						walk_msg->m_type != 1) {
+					msg = walk_msg;
+					msgtyp = walk_msg->m_type - 1;
+				} else {
+					msg = walk_msg;
+					break;
+				}
+			}
+			tmp = tmp->next;
+		}
+		if (!IS_ERR(msg)) {
+			/*
+			 * Found a suitable message.
+			 * Unlink it from the queue.
+			 */
+			if ((msgsz < msg->m_ts) && !(msgflg & MSG_NOERROR)) {
+				msg = ERR_PTR(-E2BIG);
+				goto out_unlock;
+			}
+			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);
+			msg_unlock(msq);
+			break;
+		}
+		/* No message waiting. Wait for a message */
+		if (msgflg & IPC_NOWAIT) {
+			msg = ERR_PTR(-ENOMSG);
+			goto out_unlock;
+		}
+		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 = msgsz;
+		msr_d.r_msg = ERR_PTR(-EAGAIN);
+		current->state = TASK_INTERRUPTIBLE;
+		msg_unlock(msq);
+
+		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
+		 * existance 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 the spin_lock() inside ipc_lock_by_ptr().
+		 */
+		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)) {
+			rcu_read_unlock();
+			break;
+		}
+
+		/* Lockless receive, part 3:
+		 * Acquire the queue spinlock.
+		 */
+		ipc_lock_by_ptr(&msq->q_perm);
+		rcu_read_unlock();
+
+		/* 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_unlock;
+
+		list_del(&msr_d.r_list);
+		if (signal_pending(current)) {
+			msg = ERR_PTR(-ERESTARTNOHAND);
+out_unlock:
+			msg_unlock(msq);
+			break;
+		}
+	}
+	if (IS_ERR(msg))
+		return PTR_ERR(msg);
+
+	msgsz = (msgsz > msg->m_ts) ? msg->m_ts : msgsz;
+	*pmtype = msg->m_type;
+	if (store_msg(mtext, msg, msgsz))
+		msgsz = -EFAULT;
+
+	free_msg(msg);
+
+	return msgsz;
+}
+
+SYSCALL_DEFINE5(msgrcv, int, msqid, struct msgbuf __user *, msgp, size_t, msgsz,
+		long, msgtyp, int, msgflg)
+{
+	long err, mtype;
+
+	err =  do_msgrcv(msqid, &mtype, msgp->mtext, msgsz, msgtyp, msgflg);
+	if (err < 0)
+		goto out;
+
+	if (put_user(mtype, &msgp->mtype))
+		err = -EFAULT;
+out:
+	return err;
+}
+
+#ifdef CONFIG_PROC_FS
+static int sysvipc_msg_proc_show(struct seq_file *s, void *it)
+{
+	struct msg_queue *msq = it;
+
+	return 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,
+			msq->q_perm.uid,
+			msq->q_perm.gid,
+			msq->q_perm.cuid,
+			msq->q_perm.cgid,
+			msq->q_stime,
+			msq->q_rtime,
+			msq->q_ctime);
+}
+#endif

kernel/ipc/msgutil.c

@@ -0,0 +1,146 @@
+/*
+ * 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/ipc_namespace.h>
+#include <asm/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),
+#ifdef CONFIG_POSIX_MQUEUE
+	.mq_queues_max   = DFLT_QUEUESMAX,
+	.mq_msg_max      = DFLT_MSGMAX,
+	.mq_msgsize_max  = DFLT_MSGSIZEMAX,
+#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	(PAGE_SIZE-sizeof(struct msg_msg))
+#define DATALEN_SEG	(PAGE_SIZE-sizeof(struct msg_msgseg))
+
+struct msg_msg *load_msg(const void __user *src, int len)
+{
+	struct msg_msg *msg;
+	struct msg_msgseg **pseg;
+	int err;
+	int alen;
+
+	alen = len;
+	if (alen > DATALEN_MSG)
+		alen = DATALEN_MSG;
+
+	msg = kmalloc(sizeof(*msg) + alen, GFP_KERNEL);
+	if (msg == NULL)
+		return ERR_PTR(-ENOMEM);
+
+	msg->next = NULL;
+	msg->security = NULL;
+
+	if (copy_from_user(msg + 1, src, alen)) {
+		err = -EFAULT;
+		goto out_err;
+	}
+
+	len -= alen;
+	src = ((char __user *)src) + alen;
+	pseg = &msg->next;
+	while (len > 0) {
+		struct msg_msgseg *seg;
+		alen = len;
+		if (alen > DATALEN_SEG)
+			alen = DATALEN_SEG;
+		seg = kmalloc(sizeof(*seg) + alen,
+						 GFP_KERNEL);
+		if (seg == NULL) {
+			err = -ENOMEM;
+			goto out_err;
+		}
+		*pseg = seg;
+		seg->next = NULL;
+		if (copy_from_user(seg + 1, src, alen)) {
+			err = -EFAULT;
+			goto out_err;
+		}
+		pseg = &seg->next;
+		len -= alen;
+		src = ((char __user *)src) + alen;
+	}
+
+	err = security_msg_msg_alloc(msg);
+	if (err)
+		goto out_err;
+
+	return msg;
+
+out_err:
+	free_msg(msg);
+	return ERR_PTR(err);
+}
+
+int store_msg(void __user *dest, struct msg_msg *msg, int len)
+{
+	int alen;
+	struct msg_msgseg *seg;
+
+	alen = len;
+	if (alen > DATALEN_MSG)
+		alen = DATALEN_MSG;
+	if (copy_to_user(dest, msg + 1, alen))
+		return -1;
+
+	len -= alen;
+	dest = ((char __user *)dest) + alen;
+	seg = msg->next;
+	while (len > 0) {
+		alen = len;
+		if (alen > DATALEN_SEG)
+			alen = DATALEN_SEG;
+		if (copy_to_user(dest, seg + 1, alen))
+			return -1;
+		len -= alen;
+		dest = ((char __user *)dest) + alen;
+		seg = seg->next;
+	}
+	return 0;
+}
+
+void free_msg(struct msg_msg *msg)
+{
+	struct msg_msgseg *seg;
+
+	security_msg_msg_free(msg);
+
+	seg = msg->next;
+	kfree(msg);
+	while (seg != NULL) {
+		struct msg_msgseg *tmp = seg->next;
+		kfree(seg);
+		seg = tmp;
+	}
+}

kernel/ipc/namespace.c

@@ -0,0 +1,134 @@
+/*
+ * 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 "util.h"
+
+static struct ipc_namespace *create_ipc_ns(void)
+{
+	struct ipc_namespace *ns;
+	int err;
+
+	ns = kmalloc(sizeof(struct ipc_namespace), GFP_KERNEL);
+	if (ns == NULL)
+		return ERR_PTR(-ENOMEM);
+
+	atomic_set(&ns->count, 1);
+	err = mq_init_ns(ns);
+	if (err) {
+		kfree(ns);
+		return ERR_PTR(err);
+	}
+	atomic_inc(&nr_ipc_ns);
+
+	sem_init_ns(ns);
+	msg_init_ns(ns);
+	shm_init_ns(ns);
+
+	/*
+	 * msgmni has already been computed for the new ipc ns.
+	 * Thus, do the ipcns creation notification before registering that
+	 * new ipcns in the chain.
+	 */
+	ipcns_notify(IPCNS_CREATED);
+	register_ipcns_notifier(ns);
+
+	return ns;
+}
+
+struct ipc_namespace *copy_ipcs(unsigned long flags, struct ipc_namespace *ns)
+{
+	if (!(flags & CLONE_NEWIPC))
+		return get_ipc_ns(ns);
+	return create_ipc_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->rw_mutex);
+
+	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;
+		ipc_lock_by_ptr(perm);
+		free(ns, perm);
+		total++;
+	}
+	up_write(&ids->rw_mutex);
+}
+
+static void free_ipc_ns(struct ipc_namespace *ns)
+{
+	/*
+	 * Unregistering the hotplug notifier at the beginning guarantees
+	 * that the ipc namespace won't be freed while we are inside the
+	 * callback routine. Since the blocking_notifier_chain_XXX routines
+	 * hold a rw lock on the notifier list, unregister_ipcns_notifier()
+	 * won't take the rw lock before blocking_notifier_call_chain() has
+	 * released the rd lock.
+	 */
+	unregister_ipcns_notifier(ns);
+	sem_exit_ns(ns);
+	msg_exit_ns(ns);
+	shm_exit_ns(ns);
+	kfree(ns);
+	atomic_dec(&nr_ipc_ns);
+
+	/*
+	 * Do the ipcns removal notification after decrementing nr_ipc_ns in
+	 * order to have a correct value when recomputing msgmni.
+	 */
+	ipcns_notify(IPCNS_REMOVED);
+}
+
+/*
+ * 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);
+	}
+}

kernel/ipc/util.c

@@ -0,0 +1,993 @@
+/*
+ * 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>
+ */
+
+#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/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 *);
+};
+
+#ifdef CONFIG_MEMORY_HOTPLUG
+
+static void ipc_memory_notifier(struct work_struct *work)
+{
+	ipcns_notify(IPCNS_MEMCHANGED);
+}
+
+static DECLARE_WORK(ipc_memory_wq, ipc_memory_notifier);
+
+
+static int ipc_memory_callback(struct notifier_block *self,
+				unsigned long action, void *arg)
+{
+	switch (action) {
+	case MEM_ONLINE:    /* memory successfully brought online */
+	case MEM_OFFLINE:   /* or offline: it's time to recompute msgmni */
+		/*
+		 * This is done by invoking the ipcns notifier chain with the
+		 * IPC_MEMCHANGED event.
+		 * In order not to keep the lock on the hotplug memory chain
+		 * for too long, queue a work item that will, when waken up,
+		 * activate the ipcns notification chain.
+		 * No need to keep several ipc work items on the queue.
+		 */
+		if (!work_pending(&ipc_memory_wq))
+			schedule_work(&ipc_memory_wq);
+		break;
+	case MEM_GOING_ONLINE:
+	case MEM_GOING_OFFLINE:
+	case MEM_CANCEL_ONLINE:
+	case MEM_CANCEL_OFFLINE:
+	default:
+		break;
+	}
+
+	return NOTIFY_OK;
+}
+
+#endif /* CONFIG_MEMORY_HOTPLUG */
+
+/**
+ *	ipc_init	-	initialise IPC subsystem
+ *
+ *	The various system5 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();
+	hotplug_memory_notifier(ipc_memory_callback, IPC_CALLBACK_PRI);
+	register_ipcns_notifier(&init_ipc_ns);
+	return 0;
+}
+__initcall(ipc_init);
+
+/**
+ *	ipc_init_ids		-	initialise IPC identifiers
+ *	@ids: 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)
+{
+	init_rwsem(&ids->rw_mutex);
+
+	ids->in_use = 0;
+	ids->seq = 0;
+	{
+		int seq_limit = INT_MAX/SEQ_MULTIPLIER;
+		if (seq_limit > USHORT_MAX)
+			ids->seq_max = USHORT_MAX;
+		 else
+		 	ids->seq_max = seq_limit;
+	}
+
+	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: Identifier set
+ *	@key: The key to find
+ *	
+ *	Requires ipc_ids.rw_mutex locked.
+ *	Returns the LOCKED pointer to the ipc structure if found or NULL
+ *	if not.
+ *	If key is found ipc points to the owning ipc structure
+ */
+ 
+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;
+		}
+
+		ipc_lock_by_ptr(ipc);
+		return ipc;
+	}
+
+	return NULL;
+}
+
+/**
+ *	ipc_get_maxid 	-	get the last assigned id
+ *	@ids: IPC identifier set
+ *
+ *	Called with ipc_ids.rw_mutex 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 ipc_ids.rw_mutex held as a writer.
+ */
+ 
+int ipc_addid(struct ipc_ids* ids, struct kern_ipc_perm* new, int size)
+{
+	uid_t euid;
+	gid_t egid;
+	int id, err;
+
+	if (size > IPCMNI)
+		size = IPCMNI;
+
+	if (ids->in_use >= size)
+		return -ENOSPC;
+
+	spin_lock_init(&new->lock);
+	new->deleted = 0;
+	rcu_read_lock();
+	spin_lock(&new->lock);
+
+	err = idr_get_new(&ids->ipcs_idr, new, &id);
+	if (err) {
+		spin_unlock(&new->lock);
+		rcu_read_unlock();
+		return err;
+	}
+
+	ids->in_use++;
+
+	current_euid_egid(&euid, &egid);
+	new->cuid = new->uid = euid;
+	new->gid = new->cgid = egid;
+
+	new->seq = ids->seq++;
+	if(ids->seq > ids->seq_max)
+		ids->seq = 0;
+
+	new->id = ipc_buildid(id, new->seq);
+	return id;
+}
+
+/**
+ *	ipcget_new	-	create a new ipc object
+ *	@ns: namespace
+ *	@ids: IPC identifer 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,
+		struct ipc_ops *ops, struct ipc_params *params)
+{
+	int err;
+retry:
+	err = idr_pre_get(&ids->ipcs_idr, GFP_KERNEL);
+
+	if (!err)
+		return -ENOMEM;
+
+	down_write(&ids->rw_mutex);
+	err = ops->getnew(ns, params);
+	up_write(&ids->rw_mutex);
+
+	if (err == -EAGAIN)
+		goto retry;
+
+	return err;
+}
+
+/**
+ *	ipc_check_perms	-	check security and permissions for an IPC
+ *	@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
+ *      ids IDR.
+ *
+ *	On success, the IPC id is returned.
+ *
+ *	It is called with ipc_ids.rw_mutex and ipcp->lock held.
+ */
+static int ipc_check_perms(struct kern_ipc_perm *ipcp, struct ipc_ops *ops,
+			struct ipc_params *params)
+{
+	int err;
+
+	if (ipcperms(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: namespace
+ *	@ids: IPC identifer 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,
+		struct ipc_ops *ops, struct ipc_params *params)
+{
+	struct kern_ipc_perm *ipcp;
+	int flg = params->flg;
+	int err;
+retry:
+	err = idr_pre_get(&ids->ipcs_idr, GFP_KERNEL);
+
+	/*
+	 * Take the lock as a writer since we are potentially going to add
+	 * a new entry + read locks are not "upgradable"
+	 */
+	down_write(&ids->rw_mutex);
+	ipcp = ipc_findkey(ids, params->key);
+	if (ipcp == NULL) {
+		/* key not used */
+		if (!(flg & IPC_CREAT))
+			err = -ENOENT;
+		else if (!err)
+			err = -ENOMEM;
+		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(ipcp, ops, params);
+		}
+		ipc_unlock(ipcp);
+	}
+	up_write(&ids->rw_mutex);
+
+	if (err == -EAGAIN)
+		goto retry;
+
+	return err;
+}
+
+
+/**
+ *	ipc_rmid	-	remove an IPC identifier
+ *	@ids: IPC identifier set
+ *	@ipcp: ipc perm structure containing the identifier to remove
+ *
+ *	ipc_ids.rw_mutex (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 = 1;
+
+	return;
+}
+
+/**
+ *	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);
+}
+
+/*
+ * rcu allocations:
+ * There are three headers that are prepended to the actual allocation:
+ * - during use: ipc_rcu_hdr.
+ * - during the rcu grace period: ipc_rcu_grace.
+ * - [only if vmalloc]: ipc_rcu_sched.
+ * Their lifetime doesn't overlap, thus the headers share the same memory.
+ * Unlike a normal union, they are right-aligned, thus some container_of
+ * forward/backward casting is necessary:
+ */
+struct ipc_rcu_hdr
+{
+	int refcount;
+	int is_vmalloc;
+	void *data[0];
+};
+
+
+struct ipc_rcu_grace
+{
+	struct rcu_head rcu;
+	/* "void *" makes sure alignment of following data is sane. */
+	void *data[0];
+};
+
+struct ipc_rcu_sched
+{
+	struct work_struct work;
+	/* "void *" makes sure alignment of following data is sane. */
+	void *data[0];
+};
+
+#define HDRLEN_KMALLOC		(sizeof(struct ipc_rcu_grace) > sizeof(struct ipc_rcu_hdr) ? \
+					sizeof(struct ipc_rcu_grace) : sizeof(struct ipc_rcu_hdr))
+#define HDRLEN_VMALLOC		(sizeof(struct ipc_rcu_sched) > HDRLEN_KMALLOC ? \
+					sizeof(struct ipc_rcu_sched) : HDRLEN_KMALLOC)
+
+static inline int rcu_use_vmalloc(int size)
+{
+	/* Too big for a single page? */
+	if (HDRLEN_KMALLOC + size > PAGE_SIZE)
+		return 1;
+	return 0;
+}
+
+/**
+ *	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.
+ *	NULL is returned if the allocation fails. 
+ */
+ 
+void* ipc_rcu_alloc(int size)
+{
+	void* out;
+	/* 
+	 * We prepend the allocation with the rcu struct, and
+	 * workqueue if necessary (for vmalloc). 
+	 */
+	if (rcu_use_vmalloc(size)) {
+		out = vmalloc(HDRLEN_VMALLOC + size);
+		if (out) {
+			out += HDRLEN_VMALLOC;
+			container_of(out, struct ipc_rcu_hdr, data)->is_vmalloc = 1;
+			container_of(out, struct ipc_rcu_hdr, data)->refcount = 1;
+		}
+	} else {
+		out = kmalloc(HDRLEN_KMALLOC + size, GFP_KERNEL);
+		if (out) {
+			out += HDRLEN_KMALLOC;
+			container_of(out, struct ipc_rcu_hdr, data)->is_vmalloc = 0;
+			container_of(out, struct ipc_rcu_hdr, data)->refcount = 1;
+		}
+	}
+
+	return out;
+}
+
+void ipc_rcu_getref(void *ptr)
+{
+	container_of(ptr, struct ipc_rcu_hdr, data)->refcount++;
+}
+
+static void ipc_do_vfree(struct work_struct *work)
+{
+	vfree(container_of(work, struct ipc_rcu_sched, work));
+}
+
+/**
+ * ipc_schedule_free - free ipc + rcu space
+ * @head: RCU callback structure for queued work
+ * 
+ * Since RCU callback function is called in bh,
+ * we need to defer the vfree to schedule_work().
+ */
+static void ipc_schedule_free(struct rcu_head *head)
+{
+	struct ipc_rcu_grace *grace;
+	struct ipc_rcu_sched *sched;
+
+	grace = container_of(head, struct ipc_rcu_grace, rcu);
+	sched = container_of(&(grace->data[0]), struct ipc_rcu_sched,
+				data[0]);
+
+	INIT_WORK(&sched->work, ipc_do_vfree);
+	schedule_work(&sched->work);
+}
+
+/**
+ * ipc_immediate_free - free ipc + rcu space
+ * @head: RCU callback structure that contains pointer to be freed
+ *
+ * Free from the RCU callback context.
+ */
+static void ipc_immediate_free(struct rcu_head *head)
+{
+	struct ipc_rcu_grace *free =
+		container_of(head, struct ipc_rcu_grace, rcu);
+	kfree(free);
+}
+
+void ipc_rcu_putref(void *ptr)
+{
+	if (--container_of(ptr, struct ipc_rcu_hdr, data)->refcount > 0)
+		return;
+
+	if (container_of(ptr, struct ipc_rcu_hdr, data)->is_vmalloc) {
+		call_rcu(&container_of(ptr, struct ipc_rcu_grace, data)->rcu,
+				ipc_schedule_free);
+	} else {
+		call_rcu(&container_of(ptr, struct ipc_rcu_grace, data)->rcu,
+				ipc_immediate_free);
+	}
+}
+
+/**
+ *	ipcperms	-	check IPC permissions
+ *	@ipcp: IPC permission set
+ *	@flag: desired permission set.
+ *
+ *	Check user, group, other permissions for access
+ *	to ipc resources. return 0 if allowed
+ */
+ 
+int ipcperms (struct kern_ipc_perm *ipcp, short flag)
+{	/* flag will most probably be 0 or S_...UGO from <linux/stat.h> */
+	uid_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 (euid == ipcp->cuid ||
+	    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) && 
+	    !capable(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	= in->uid;
+	out->gid	= in->gid;
+	out->cuid	= in->cuid;
+	out->cgid	= 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_lock - Lock an ipc structure without rw_mutex 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 exit.
+ */
+
+struct kern_ipc_perm *ipc_lock(struct ipc_ids *ids, int id)
+{
+	struct kern_ipc_perm *out;
+	int lid = ipcid_to_idx(id);
+
+	rcu_read_lock();
+	out = idr_find(&ids->ipcs_idr, lid);
+	if (out == NULL) {
+		rcu_read_unlock();
+		return ERR_PTR(-EINVAL);
+	}
+
+	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 (out->deleted) {
+		spin_unlock(&out->lock);
+		rcu_read_unlock();
+		return ERR_PTR(-EINVAL);
+	}
+
+	return out;
+}
+
+struct kern_ipc_perm *ipc_lock_check(struct ipc_ids *ids, int id)
+{
+	struct kern_ipc_perm *out;
+
+	out = ipc_lock(ids, id);
+	if (IS_ERR(out))
+		return out;
+
+	if (ipc_checkid(out, id)) {
+		ipc_unlock(out);
+		return ERR_PTR(-EIDRM);
+	}
+
+	return out;
+}
+
+/**
+ * ipcget - Common sys_*get() code
+ * @ns : namsepace
+ * @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,
+			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.
+ * @in:  the permission given as input.
+ * @out: the permission of the ipc to set.
+ */
+void ipc_update_perm(struct ipc64_perm *in, struct kern_ipc_perm *out)
+{
+	out->uid = in->uid;
+	out->gid = in->gid;
+	out->mode = (out->mode & ~S_IRWXUGO)
+		| (in->mode & S_IRWXUGO);
+}
+
+/**
+ * ipcctl_pre_down - retrieve an ipc and check permissions for some IPC_XXX cmd
+ * @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 the ipc with both ipc and rw_mutex locks held in case of success
+ *    or an err-code without any lock held otherwise.
+ */
+struct kern_ipc_perm *ipcctl_pre_down(struct ipc_ids *ids, int id, int cmd,
+				      struct ipc64_perm *perm, int extra_perm)
+{
+	struct kern_ipc_perm *ipcp;
+	uid_t euid;
+	int err;
+
+	down_write(&ids->rw_mutex);
+	ipcp = ipc_lock_check(ids, id);
+	if (IS_ERR(ipcp)) {
+		err = PTR_ERR(ipcp);
+		goto out_up;
+	}
+
+	audit_ipc_obj(ipcp);
+	if (cmd == IPC_SET)
+		audit_ipc_set_perm(extra_perm, perm->uid,
+					 perm->gid, perm->mode);
+
+	euid = current_euid();
+	if (euid == ipcp->cuid ||
+	    euid == ipcp->uid  || capable(CAP_SYS_ADMIN))
+		return ipcp;
+
+	err = -EPERM;
+	ipc_unlock(ipcp);
+out_up:
+	up_write(&ids->rw_mutex);
+	return ERR_PTR(err);
+}
+
+#ifdef __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 /* __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;
+			ipc_lock_by_ptr(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->rw_mutex);
+
+	/* 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->rw_mutex);
+}
+
+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)
+		return seq_puts(s, iface->header);
+
+	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)
+{
+	int ret;
+	struct seq_file *seq;
+	struct ipc_proc_iter *iter;
+
+	ret = -ENOMEM;
+	iter = kmalloc(sizeof(*iter), GFP_KERNEL);
+	if (!iter)
+		goto out;
+
+	ret = seq_open(file, &sysvipc_proc_seqops);
+	if (ret)
+		goto out_kfree;
+
+	seq = file->private_data;
+	seq->private = iter;
+
+	iter->iface = PDE(inode)->data;
+	iter->ns    = get_ipc_ns(current->nsproxy->ipc_ns);
+out:
+	return ret;
+out_kfree:
+	kfree(iter);
+	goto out;
+}
+
+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 */

kernel/ipc/util.h

@@ -0,0 +1,177 @@
+/*
+ * 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
+
+/*
+ * 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)
+
+/* must be called with ids->rw_mutex acquired for writing */
+int ipc_addid(struct ipc_ids *, struct kern_ipc_perm *, int);
+
+/* must be called with ids->rw_mutex 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 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);
+void ipc_rcu_getref(void *ptr);
+void ipc_rcu_putref(void *ptr);
+
+struct kern_ipc_perm *ipc_lock(struct ipc_ids *, int);
+
+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);
+void ipc_update_perm(struct ipc64_perm *in, struct kern_ipc_perm *out);
+struct kern_ipc_perm *ipcctl_pre_down(struct ipc_ids *ids, int id, int cmd,
+				      struct ipc64_perm *perm, int extra_perm);
+
+#ifndef __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, int len);
+extern int store_msg(void __user *dest, struct msg_msg *msg, int len);
+
+extern void recompute_msgmni(struct ipc_namespace *);
+
+static inline int ipc_buildid(int id, int seq)
+{
+	return SEQ_MULTIPLIER * seq + id;
+}
+
+/*
+ * Must be called with ipcp locked
+ */
+static inline int ipc_checkid(struct kern_ipc_perm *ipcp, int uid)
+{
+	if (uid / SEQ_MULTIPLIER != ipcp->seq)
+		return 1;
+	return 0;
+}
+
+static inline void ipc_lock_by_ptr(struct kern_ipc_perm *perm)
+{
+	rcu_read_lock();
+	spin_lock(&perm->lock);
+}
+
+static inline void ipc_unlock(struct kern_ipc_perm *perm)
+{
+	spin_unlock(&perm->lock);
+	rcu_read_unlock();
+}
+
+struct kern_ipc_perm *ipc_lock_check(struct ipc_ids *ids, int id);
+int ipcget(struct ipc_namespace *ns, struct ipc_ids *ids,
+			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