Merge branch 'akpm' (updates from Andrew Morton)

Merge second patch-bomb from Andrew Morton:
 - misc fixes
 - audit stuff
 - fanotify/inotify/dnotify things
 - most of the rest of MM.  The new cache shrinker code from Glauber and
   Dave Chinner probably isn't quite stabilized yet.
 - ptrace
 - ipc
 - partitions
 - reboot cleanups
 - add LZ4 decompressor, use it for kernel compression

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (118 commits)
  lib/scatterlist: error handling in __sg_alloc_table()
  scsi_debug: fix do_device_access() with wrap around range
  crypto: talitos: use sg_pcopy_to_buffer()
  lib/scatterlist: introduce sg_pcopy_from_buffer() and sg_pcopy_to_buffer()
  lib/scatterlist: factor out sg_miter_get_next_page() from sg_miter_next()
  crypto: add lz4 Cryptographic API
  lib: add lz4 compressor module
  arm: add support for LZ4-compressed kernel
  lib: add support for LZ4-compressed kernel
  decompressor: add LZ4 decompressor module
  lib: add weak clz/ctz functions
  reboot: move arch/x86 reboot= handling to generic kernel
  reboot: arm: change reboot_mode to use enum reboot_mode
  reboot: arm: prepare reboot_mode for moving to generic kernel code
  reboot: arm: remove unused restart_mode fields from some arm subarchs
  reboot: unicore32: prepare reboot_mode for moving to generic kernel code
  reboot: x86: prepare reboot_mode for moving to generic kernel code
  reboot: checkpatch.pl the new kernel/reboot.c file
  reboot: move shutdown/reboot related functions to kernel/reboot.c
  reboot: remove -stable friendly PF_THREAD_BOUND define
  ...

6 files changed, 503 insertions, 259 deletions

diff --git a/ipc/mqueue.c b/ipc/mqueue.c
index e4e47f64744..ae1996d3c53 100644
--- a/ipc/mqueue.c
+++ b/ipc/mqueue.c
@@ -823,6 +823,7 @@ SYSCALL_DEFINE4(mq_open, const char __user *, u_name, int, oflag, umode_t, mode,
 				error = ro;
 				goto out;
 			}
+			audit_inode_parent_hidden(name, root);
 			filp = do_create(ipc_ns, root->d_inode,
 						&path, oflag, mode,
 						u_attr ? &attr : NULL);
@@ -868,6 +869,7 @@ SYSCALL_DEFINE1(mq_unlink, const char __user *, u_name)
 	if (IS_ERR(name))
 		return PTR_ERR(name);
 
+	audit_inode_parent_hidden(name, mnt->mnt_root);
 	err = mnt_want_write(mnt);
 	if (err)
 		goto out_name;
diff --git a/ipc/msg.c b/ipc/msg.c
index d0c6d967b39..bd60d7e159e 100644
--- a/ipc/msg.c
+++ b/ipc/msg.c
@@ -141,27 +141,23 @@ void __init msg_init(void)
 				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)
+static inline struct msg_queue *msq_obtain_object(struct ipc_namespace *ns, int id)
 {
-	struct kern_ipc_perm *ipcp = ipc_lock(&msg_ids(ns), id);
+	struct kern_ipc_perm *ipcp = ipc_obtain_object(&msg_ids(ns), id);
 
 	if (IS_ERR(ipcp))
-		return (struct msg_queue *)ipcp;
+		return ERR_CAST(ipcp);
 
 	return container_of(ipcp, struct msg_queue, q_perm);
 }
 
-static inline struct msg_queue *msg_lock_check(struct ipc_namespace *ns,
-						int id)
+static inline struct msg_queue *msq_obtain_object_check(struct ipc_namespace *ns,
+							int id)
 {
-	struct kern_ipc_perm *ipcp = ipc_lock_check(&msg_ids(ns), id);
+	struct kern_ipc_perm *ipcp = ipc_obtain_object_check(&msg_ids(ns), id);
 
 	if (IS_ERR(ipcp))
-		return (struct msg_queue *)ipcp;
+		return ERR_CAST(ipcp);
 
 	return container_of(ipcp, struct msg_queue, q_perm);
 }
@@ -199,9 +195,7 @@ static int newque(struct ipc_namespace *ns, struct ipc_params *params)
 		return retval;
 	}
 
-	/*
-	 * ipc_addid() locks msq
-	 */
+	/* ipc_addid() locks msq upon success. */
 	id = ipc_addid(&msg_ids(ns), &msq->q_perm, ns->msg_ctlmni);
 	if (id < 0) {
 		security_msg_queue_free(msq);
@@ -218,7 +212,8 @@ static int newque(struct ipc_namespace *ns, struct ipc_params *params)
 	INIT_LIST_HEAD(&msq->q_receivers);
 	INIT_LIST_HEAD(&msq->q_senders);
 
-	msg_unlock(msq);
+	ipc_unlock_object(&msq->q_perm);
+	rcu_read_unlock();
 
 	return msq->q_perm.id;
 }
@@ -408,31 +403,39 @@ static int msgctl_down(struct ipc_namespace *ns, int msqid, int cmd,
 			return -EFAULT;
 	}
 
-	ipcp = ipcctl_pre_down(ns, &msg_ids(ns), msqid, cmd,
-			       &msqid64.msg_perm, msqid64.msg_qbytes);
-	if (IS_ERR(ipcp))
-		return PTR_ERR(ipcp);
+	down_write(&msg_ids(ns).rw_mutex);
+	rcu_read_lock();
+
+	ipcp = ipcctl_pre_down_nolock(ns, &msg_ids(ns), msqid, cmd,
+				      &msqid64.msg_perm, msqid64.msg_qbytes);
+	if (IS_ERR(ipcp)) {
+		err = PTR_ERR(ipcp);
+		goto out_unlock1;
+	}
 
 	msq = container_of(ipcp, struct msg_queue, q_perm);
 
 	err = security_msg_queue_msgctl(msq, cmd);
 	if (err)
-		goto out_unlock;
+		goto out_unlock1;
 
 	switch (cmd) {
 	case IPC_RMID:
+		ipc_lock_object(&msq->q_perm);
+		/* freeque unlocks the ipc object and rcu */
 		freeque(ns, ipcp);
 		goto out_up;
 	case IPC_SET:
 		if (msqid64.msg_qbytes > ns->msg_ctlmnb &&
 		    !capable(CAP_SYS_RESOURCE)) {
 			err = -EPERM;
-			goto out_unlock;
+			goto out_unlock1;
 		}
 
+		ipc_lock_object(&msq->q_perm);
 		err = ipc_update_perm(&msqid64.msg_perm, ipcp);
 		if (err)
-			goto out_unlock;
+			goto out_unlock0;
 
 		msq->q_qbytes = msqid64.msg_qbytes;
 
@@ -448,25 +451,23 @@ static int msgctl_down(struct ipc_namespace *ns, int msqid, int cmd,
 		break;
 	default:
 		err = -EINVAL;
+		goto out_unlock1;
 	}
-out_unlock:
-	msg_unlock(msq);
+
+out_unlock0:
+	ipc_unlock_object(&msq->q_perm);
+out_unlock1:
+	rcu_read_unlock();
 out_up:
 	up_write(&msg_ids(ns).rw_mutex);
 	return err;
 }
 
-SYSCALL_DEFINE3(msgctl, int, msqid, int, cmd, struct msqid_ds __user *, buf)
+static int msgctl_nolock(struct ipc_namespace *ns, int msqid,
+			 int cmd, int version, void __user *buf)
 {
+	int err;
 	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:
@@ -477,6 +478,7 @@ SYSCALL_DEFINE3(msgctl, int, msqid, int, cmd, struct msqid_ds __user *, buf)
 
 		if (!buf)
 			return -EFAULT;
+
 		/*
 		 * We must not return kernel stack data.
 		 * due to padding, it's not enough
@@ -508,7 +510,8 @@ SYSCALL_DEFINE3(msgctl, int, msqid, int, cmd, struct msqid_ds __user *, buf)
 			return -EFAULT;
 		return (max_id < 0) ? 0 : max_id;
 	}
-	case MSG_STAT:	/* msqid is an index rather than a msg queue id */
+
+	case MSG_STAT:
 	case IPC_STAT:
 	{
 		struct msqid64_ds tbuf;
@@ -517,17 +520,25 @@ SYSCALL_DEFINE3(msgctl, int, msqid, int, cmd, struct msqid_ds __user *, buf)
 		if (!buf)
 			return -EFAULT;
 
+		memset(&tbuf, 0, sizeof(tbuf));
+
+		rcu_read_lock();
 		if (cmd == MSG_STAT) {
-			msq = msg_lock(ns, msqid);
-			if (IS_ERR(msq))
-				return PTR_ERR(msq);
+			msq = msq_obtain_object(ns, msqid);
+			if (IS_ERR(msq)) {
+				err = PTR_ERR(msq);
+				goto out_unlock;
+			}
 			success_return = msq->q_perm.id;
 		} else {
-			msq = msg_lock_check(ns, msqid);
-			if (IS_ERR(msq))
-				return PTR_ERR(msq);
+			msq = msq_obtain_object_check(ns, msqid);
+			if (IS_ERR(msq)) {
+				err = PTR_ERR(msq);
+				goto out_unlock;
+			}
 			success_return = 0;
 		}
+
 		err = -EACCES;
 		if (ipcperms(ns, &msq->q_perm, S_IRUGO))
 			goto out_unlock;
@@ -536,8 +547,6 @@ SYSCALL_DEFINE3(msgctl, int, msqid, int, cmd, struct msqid_ds __user *, buf)
 		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;
@@ -547,24 +556,48 @@ SYSCALL_DEFINE3(msgctl, int, msqid, int, cmd, struct msqid_ds __user *, buf)
 		tbuf.msg_qbytes = msq->q_qbytes;
 		tbuf.msg_lspid  = msq->q_lspid;
 		tbuf.msg_lrpid  = msq->q_lrpid;
-		msg_unlock(msq);
+		rcu_read_unlock();
+
 		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;
+		return -EINVAL;
 	}
 
+	return err;
 out_unlock:
-	msg_unlock(msq);
+	rcu_read_unlock();
 	return err;
 }
 
+SYSCALL_DEFINE3(msgctl, int, msqid, int, cmd, struct msqid_ds __user *, buf)
+{
+	int version;
+	struct ipc_namespace *ns;
+
+	if (msqid < 0 || cmd < 0)
+		return -EINVAL;
+
+	version = ipc_parse_version(&cmd);
+	ns = current->nsproxy->ipc_ns;
+
+	switch (cmd) {
+	case IPC_INFO:
+	case MSG_INFO:
+	case MSG_STAT:	/* msqid is an index rather than a msg queue id */
+	case IPC_STAT:
+		return msgctl_nolock(ns, msqid, cmd, version, buf);
+	case IPC_SET:
+	case IPC_RMID:
+		return msgctl_down(ns, msqid, cmd, buf, version);
+	default:
+		return  -EINVAL;
+	}
+}
+
 static int testmsg(struct msg_msg *msg, long type, int mode)
 {
 	switch(mode)
@@ -640,10 +673,11 @@ long do_msgsnd(int msqid, long mtype, void __user *mtext,
 	msg->m_type = mtype;
 	msg->m_ts = msgsz;
 
-	msq = msg_lock_check(ns, msqid);
+	rcu_read_lock();
+	msq = msq_obtain_object_check(ns, msqid);
 	if (IS_ERR(msq)) {
 		err = PTR_ERR(msq);
-		goto out_free;
+		goto out_unlock1;
 	}
 
 	for (;;) {
@@ -651,11 +685,11 @@ long do_msgsnd(int msqid, long mtype, void __user *mtext,
 
 		err = -EACCES;
 		if (ipcperms(ns, &msq->q_perm, S_IWUGO))
-			goto out_unlock_free;
+			goto out_unlock1;
 
 		err = security_msg_queue_msgsnd(msq, msg, msgflg);
 		if (err)
-			goto out_unlock_free;
+			goto out_unlock1;
 
 		if (msgsz + msq->q_cbytes <= msq->q_qbytes &&
 				1 + msq->q_qnum <= msq->q_qbytes) {
@@ -665,32 +699,41 @@ long do_msgsnd(int msqid, long mtype, void __user *mtext,
 		/* queue full, wait: */
 		if (msgflg & IPC_NOWAIT) {
 			err = -EAGAIN;
-			goto out_unlock_free;
+			goto out_unlock1;
 		}
+
+		ipc_lock_object(&msq->q_perm);
 		ss_add(msq, &s);
 
 		if (!ipc_rcu_getref(msq)) {
 			err = -EIDRM;
-			goto out_unlock_free;
+			goto out_unlock0;
 		}
 
-		msg_unlock(msq);
+		ipc_unlock_object(&msq->q_perm);
+		rcu_read_unlock();
 		schedule();
 
-		ipc_lock_by_ptr(&msq->q_perm);
+		rcu_read_lock();
+		ipc_lock_object(&msq->q_perm);
+
 		ipc_rcu_putref(msq);
 		if (msq->q_perm.deleted) {
 			err = -EIDRM;
-			goto out_unlock_free;
+			goto out_unlock0;
 		}
+
 		ss_del(&s);
 
 		if (signal_pending(current)) {
 			err = -ERESTARTNOHAND;
-			goto out_unlock_free;
+			goto out_unlock0;
 		}
+
+		ipc_unlock_object(&msq->q_perm);
 	}
 
+	ipc_lock_object(&msq->q_perm);
 	msq->q_lspid = task_tgid_vnr(current);
 	msq->q_stime = get_seconds();
 
@@ -706,9 +749,10 @@ long do_msgsnd(int msqid, long mtype, void __user *mtext,
 	err = 0;
 	msg = NULL;
 
-out_unlock_free:
-	msg_unlock(msq);
-out_free:
+out_unlock0:
+	ipc_unlock_object(&msq->q_perm);
+out_unlock1:
+	rcu_read_unlock();
 	if (msg != NULL)
 		free_msg(msg);
 	return err;
@@ -816,21 +860,19 @@ static struct msg_msg *find_msg(struct msg_queue *msq, long *msgtyp, int mode)
 	return ERR_PTR(-EAGAIN);
 }
 
-
-long do_msgrcv(int msqid, void __user *buf, size_t bufsz, long msgtyp,
-	       int msgflg,
+long do_msgrcv(int msqid, void __user *buf, size_t bufsz, long msgtyp, int msgflg,
 	       long (*msg_handler)(void __user *, struct msg_msg *, size_t))
 {
-	struct msg_queue *msq;
-	struct msg_msg *msg;
 	int mode;
+	struct msg_queue *msq;
 	struct ipc_namespace *ns;
-	struct msg_msg *copy = NULL;
+	struct msg_msg *msg, *copy = NULL;
 
 	ns = current->nsproxy->ipc_ns;
 
 	if (msqid < 0 || (long) bufsz < 0)
 		return -EINVAL;
+
 	if (msgflg & MSG_COPY) {
 		copy = prepare_copy(buf, min_t(size_t, bufsz, ns->msg_ctlmax));
 		if (IS_ERR(copy))
@@ -838,8 +880,10 @@ long do_msgrcv(int msqid, void __user *buf, size_t bufsz, long msgtyp,
 	}
 	mode = convert_mode(&msgtyp, msgflg);
 
-	msq = msg_lock_check(ns, msqid);
+	rcu_read_lock();
+	msq = msq_obtain_object_check(ns, msqid);
 	if (IS_ERR(msq)) {
+		rcu_read_unlock();
 		free_copy(copy);
 		return PTR_ERR(msq);
 	}
@@ -849,10 +893,10 @@ long do_msgrcv(int msqid, void __user *buf, size_t bufsz, long msgtyp,
 
 		msg = ERR_PTR(-EACCES);
 		if (ipcperms(ns, &msq->q_perm, S_IRUGO))
-			goto out_unlock;
+			goto out_unlock1;
 
+		ipc_lock_object(&msq->q_perm);
 		msg = find_msg(msq, &msgtyp, mode);
-
 		if (!IS_ERR(msg)) {
 			/*
 			 * Found a suitable message.
@@ -860,7 +904,7 @@ long do_msgrcv(int msqid, void __user *buf, size_t bufsz, long msgtyp,
 			 */
 			if ((bufsz < msg->m_ts) && !(msgflg & MSG_NOERROR)) {
 				msg = ERR_PTR(-E2BIG);
-				goto out_unlock;
+				goto out_unlock0;
 			}
 			/*
 			 * If we are copying, then do not unlink message and do
@@ -868,8 +912,9 @@ long do_msgrcv(int msqid, void __user *buf, size_t bufsz, long msgtyp,
 			 */
 			if (msgflg & MSG_COPY) {
 				msg = copy_msg(msg, copy);
-				goto out_unlock;
+				goto out_unlock0;
 			}
+
 			list_del(&msg->m_list);
 			msq->q_qnum--;
 			msq->q_rtime = get_seconds();
@@ -878,14 +923,16 @@ long do_msgrcv(int msqid, void __user *buf, size_t bufsz, long msgtyp,
 			atomic_sub(msg->m_ts, &ns->msg_bytes);
 			atomic_dec(&ns->msg_hdrs);
 			ss_wakeup(&msq->q_senders, 0);
-			msg_unlock(msq);
-			break;
+
+			goto out_unlock0;
 		}
+
 		/* No message waiting. Wait for a message */
 		if (msgflg & IPC_NOWAIT) {
 			msg = ERR_PTR(-ENOMSG);
-			goto out_unlock;
+			goto out_unlock0;
 		}
+
 		list_add_tail(&msr_d.r_list, &msq->q_receivers);
 		msr_d.r_tsk = current;
 		msr_d.r_msgtype = msgtyp;
@@ -896,8 +943,9 @@ long do_msgrcv(int msqid, void __user *buf, size_t bufsz, long msgtyp,
 			msr_d.r_maxsize = bufsz;
 		msr_d.r_msg = ERR_PTR(-EAGAIN);
 		current->state = TASK_INTERRUPTIBLE;
-		msg_unlock(msq);
 
+		ipc_unlock_object(&msq->q_perm);
+		rcu_read_unlock();
 		schedule();
 
 		/* Lockless receive, part 1:
@@ -908,7 +956,7 @@ long do_msgrcv(int msqid, void __user *buf, size_t bufsz, long msgtyp,
 		 * 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().
+		 * and acquiring the q_perm.lock in ipc_lock_object().
 		 */
 		rcu_read_lock();
 
@@ -927,32 +975,34 @@ long do_msgrcv(int msqid, void __user *buf, size_t bufsz, long msgtyp,
 		 * If there is a message or an error then accept it without
 		 * locking.
 		 */
-		if (msg != ERR_PTR(-EAGAIN)) {
-			rcu_read_unlock();
-			break;
-		}
+		if (msg != ERR_PTR(-EAGAIN))
+			goto out_unlock1;
 
 		/* Lockless receive, part 3:
 		 * Acquire the queue spinlock.
 		 */
-		ipc_lock_by_ptr(&msq->q_perm);
-		rcu_read_unlock();
+		ipc_lock_object(&msq->q_perm);
 
 		/* Lockless receive, part 4:
 		 * Repeat test after acquiring the spinlock.
 		 */
 		msg = (struct msg_msg*)msr_d.r_msg;
 		if (msg != ERR_PTR(-EAGAIN))
-			goto out_unlock;
+			goto out_unlock0;
 
 		list_del(&msr_d.r_list);
 		if (signal_pending(current)) {
 			msg = ERR_PTR(-ERESTARTNOHAND);
-out_unlock:
-			msg_unlock(msq);
-			break;
+			goto out_unlock0;
 		}
+
+		ipc_unlock_object(&msq->q_perm);
 	}
+
+out_unlock0:
+	ipc_unlock_object(&msq->q_perm);
+out_unlock1:
+	rcu_read_unlock();
 	if (IS_ERR(msg)) {
 		free_copy(copy);
 		return PTR_ERR(msg);
diff --git a/ipc/sem.c b/ipc/sem.c
index 70480a3aa69..41088899783 100644
--- a/ipc/sem.c
+++ b/ipc/sem.c
@@ -95,8 +95,12 @@ struct sem {
 	int	semval;		/* current value */
 	int	sempid;		/* pid of last operation */
 	spinlock_t	lock;	/* spinlock for fine-grained semtimedop */
-	struct list_head sem_pending; /* pending single-sop operations */
-};
+	struct list_head pending_alter; /* pending single-sop operations */
+					/* that alter the semaphore */
+	struct list_head pending_const; /* pending single-sop operations */
+					/* that do not alter the semaphore*/
+	time_t	sem_otime;	/* candidate for sem_otime */
+} ____cacheline_aligned_in_smp;
 
 /* One queue for each sleeping process in the system. */
 struct sem_queue {
@@ -150,12 +154,15 @@ static int sysvipc_sem_proc_show(struct seq_file *s, void *it);
 #define SEMOPM_FAST	64  /* ~ 372 bytes on stack */
 
 /*
- * linked list protection:
+ * Locking:
  *	sem_undo.id_next,
- *	sem_array.sem_pending{,last},
- *	sem_array.sem_undo: sem_lock() for read/write
+ *	sem_array.complex_count,
+ *	sem_array.pending{_alter,_cont},
+ *	sem_array.sem_undo: global sem_lock() for read/write
  *	sem_undo.proc_next: only "current" is allowed to read/write that field.
  *	
+ *	sem_array.sem_base[i].pending_{const,alter}:
+ *		global or semaphore sem_lock() for read/write
  */
 
 #define sc_semmsl	sem_ctls[0]
@@ -189,6 +196,53 @@ void __init sem_init (void)
 				IPC_SEM_IDS, sysvipc_sem_proc_show);
 }
 
+/**
+ * unmerge_queues - unmerge queues, if possible.
+ * @sma: semaphore array
+ *
+ * The function unmerges the wait queues if complex_count is 0.
+ * It must be called prior to dropping the global semaphore array lock.
+ */
+static void unmerge_queues(struct sem_array *sma)
+{
+	struct sem_queue *q, *tq;
+
+	/* complex operations still around? */
+	if (sma->complex_count)
+		return;
+	/*
+	 * We will switch back to simple mode.
+	 * Move all pending operation back into the per-semaphore
+	 * queues.
+	 */
+	list_for_each_entry_safe(q, tq, &sma->pending_alter, list) {
+		struct sem *curr;
+		curr = &sma->sem_base[q->sops[0].sem_num];
+
+		list_add_tail(&q->list, &curr->pending_alter);
+	}
+	INIT_LIST_HEAD(&sma->pending_alter);
+}
+
+/**
+ * merge_queues - Merge single semop queues into global queue
+ * @sma: semaphore array
+ *
+ * This function merges all per-semaphore queues into the global queue.
+ * It is necessary to achieve FIFO ordering for the pending single-sop
+ * operations when a multi-semop operation must sleep.
+ * Only the alter operations must be moved, the const operations can stay.
+ */
+static void merge_queues(struct sem_array *sma)
+{
+	int i;
+	for (i = 0; i < sma->sem_nsems; i++) {
+		struct sem *sem = sma->sem_base + i;
+
+		list_splice_init(&sem->pending_alter, &sma->pending_alter);
+	}
+}
+
 /*
  * If the request contains only one semaphore operation, and there are
  * no complex transactions pending, lock only the semaphore involved.
@@ -246,7 +300,7 @@ static inline int sem_lock(struct sem_array *sma, struct sembuf *sops,
 		 * their critical section while the array lock is held.
 		 */
  lock_array:
-		spin_lock(&sma->sem_perm.lock);
+		ipc_lock_object(&sma->sem_perm);
 		for (i = 0; i < sma->sem_nsems; i++) {
 			struct sem *sem = sma->sem_base + i;
 			spin_unlock_wait(&sem->lock);
@@ -259,7 +313,8 @@ static inline int sem_lock(struct sem_array *sma, struct sembuf *sops,
 static inline void sem_unlock(struct sem_array *sma, int locknum)
 {
 	if (locknum == -1) {
-		spin_unlock(&sma->sem_perm.lock);
+		unmerge_queues(sma);
+		ipc_unlock_object(&sma->sem_perm);
 	} else {
 		struct sem *sem = sma->sem_base + locknum;
 		spin_unlock(&sem->lock);
@@ -337,7 +392,7 @@ static inline void sem_rmid(struct ipc_namespace *ns, struct sem_array *s)
  * Without the check/retry algorithm a lockless wakeup is possible:
  * - queue.status is initialized to -EINTR before blocking.
  * - wakeup is performed by
- *	* unlinking the queue entry from sma->sem_pending
+ *	* unlinking the queue entry from the pending list
  *	* setting queue.status to IN_WAKEUP
  *	  This is the notification for the blocked thread that a
  *	  result value is imminent.
@@ -418,12 +473,14 @@ static int newary(struct ipc_namespace *ns, struct ipc_params *params)
 	sma->sem_base = (struct sem *) &sma[1];
 
 	for (i = 0; i < nsems; i++) {
-		INIT_LIST_HEAD(&sma->sem_base[i].sem_pending);
+		INIT_LIST_HEAD(&sma->sem_base[i].pending_alter);
+		INIT_LIST_HEAD(&sma->sem_base[i].pending_const);
 		spin_lock_init(&sma->sem_base[i].lock);
 	}
 
 	sma->complex_count = 0;
-	INIT_LIST_HEAD(&sma->sem_pending);
+	INIT_LIST_HEAD(&sma->pending_alter);
+	INIT_LIST_HEAD(&sma->pending_const);
 	INIT_LIST_HEAD(&sma->list_id);
 	sma->sem_nsems = nsems;
 	sma->sem_ctime = get_seconds();
@@ -482,12 +539,19 @@ SYSCALL_DEFINE3(semget, key_t, key, int, nsems, int, semflg)
 	return ipcget(ns, &sem_ids(ns), &sem_ops, &sem_params);
 }
 
-/*
- * Determine whether a sequence of semaphore operations would succeed
- * all at once. Return 0 if yes, 1 if need to sleep, else return error code.
+/** perform_atomic_semop - Perform (if possible) a semaphore operation
+ * @sma: semaphore array
+ * @sops: array with operations that should be checked
+ * @nsems: number of sops
+ * @un: undo array
+ * @pid: pid that did the change
+ *
+ * Returns 0 if the operation was possible.
+ * Returns 1 if the operation is impossible, the caller must sleep.
+ * Negative values are error codes.
  */
 
-static int try_atomic_semop (struct sem_array * sma, struct sembuf * sops,
+static int perform_atomic_semop(struct sem_array *sma, struct sembuf *sops,
 			     int nsops, struct sem_undo *un, int pid)
 {
 	int result, sem_op;
@@ -609,60 +673,132 @@ static void unlink_queue(struct sem_array *sma, struct sem_queue *q)
  * update_queue is O(N^2) when it restarts scanning the whole queue of
  * waiting operations. Therefore this function checks if the restart is
  * really necessary. It is called after a previously waiting operation
- * was completed.
+ * modified the array.
+ * Note that wait-for-zero operations are handled without restart.
  */
 static int check_restart(struct sem_array *sma, struct sem_queue *q)
 {
-	struct sem *curr;
-	struct sem_queue *h;
-
-	/* if the operation didn't modify the array, then no restart */
-	if (q->alter == 0)
-		return 0;
-
-	/* pending complex operations are too difficult to analyse */
-	if (sma->complex_count)
+	/* pending complex alter operations are too difficult to analyse */
+	if (!list_empty(&sma->pending_alter))
 		return 1;
 
 	/* we were a sleeping complex operation. Too difficult */
 	if (q->nsops > 1)
 		return 1;
 
-	curr = sma->sem_base + q->sops[0].sem_num;
+	/* It is impossible that someone waits for the new value:
+	 * - complex operations always restart.
+	 * - wait-for-zero are handled seperately.
+	 * - q is a previously sleeping simple operation that
+	 *   altered the array. It must be a decrement, because
+	 *   simple increments never sleep.
+	 * - If there are older (higher priority) decrements
+	 *   in the queue, then they have observed the original
+	 *   semval value and couldn't proceed. The operation
+	 *   decremented to value - thus they won't proceed either.
+	 */
+	return 0;
+}
+
+/**
+ * wake_const_ops(sma, semnum, pt) - Wake up non-alter tasks
+ * @sma: semaphore array.
+ * @semnum: semaphore that was modified.
+ * @pt: list head for the tasks that must be woken up.
+ *
+ * wake_const_ops must be called after a semaphore in a semaphore array
+ * was set to 0. If complex const operations are pending, wake_const_ops must
+ * be called with semnum = -1, as well as with the number of each modified
+ * semaphore.
+ * The tasks that must be woken up are added to @pt. The return code
+ * is stored in q->pid.
+ * The function returns 1 if at least one operation was completed successfully.
+ */
+static int wake_const_ops(struct sem_array *sma, int semnum,
+				struct list_head *pt)
+{
+	struct sem_queue *q;
+	struct list_head *walk;
+	struct list_head *pending_list;
+	int semop_completed = 0;
 
-	/* No-one waits on this queue */
-	if (list_empty(&curr->sem_pending))
-		return 0;
+	if (semnum == -1)
+		pending_list = &sma->pending_const;
+	else
+		pending_list = &sma->sem_base[semnum].pending_const;
+
+	walk = pending_list->next;
+	while (walk != pending_list) {
+		int error;
+
+		q = container_of(walk, struct sem_queue, list);
+		walk = walk->next;
+
+		error = perform_atomic_semop(sma, q->sops, q->nsops,
+						 q->undo, q->pid);
 
-	/* the new semaphore value */
-	if (curr->semval) {
-		/* It is impossible that someone waits for the new value:
-		 * - q is a previously sleeping simple operation that
-		 *   altered the array. It must be a decrement, because
-		 *   simple increments never sleep.
-		 * - The value is not 0, thus wait-for-zero won't proceed.
-		 * - If there are older (higher priority) decrements
-		 *   in the queue, then they have observed the original
-		 *   semval value and couldn't proceed. The operation
-		 *   decremented to value - thus they won't proceed either.
+		if (error <= 0) {
+			/* operation completed, remove from queue & wakeup */
+
+			unlink_queue(sma, q);
+
+			wake_up_sem_queue_prepare(pt, q, error);
+			if (error == 0)
+				semop_completed = 1;
+		}
+	}
+	return semop_completed;
+}
+
+/**
+ * do_smart_wakeup_zero(sma, sops, nsops, pt) - wakeup all wait for zero tasks
+ * @sma: semaphore array
+ * @sops: operations that were performed
+ * @nsops: number of operations
+ * @pt: list head of the tasks that must be woken up.
+ *
+ * do_smart_wakeup_zero() checks all required queue for wait-for-zero
+ * operations, based on the actual changes that were performed on the
+ * semaphore array.
+ * The function returns 1 if at least one operation was completed successfully.
+ */
+static int do_smart_wakeup_zero(struct sem_array *sma, struct sembuf *sops,
+					int nsops, struct list_head *pt)
+{
+	int i;
+	int semop_completed = 0;
+	int got_zero = 0;
+
+	/* first: the per-semaphore queues, if known */
+	if (sops) {
+		for (i = 0; i < nsops; i++) {
+			int num = sops[i].sem_num;
+
+			if (sma->sem_base[num].semval == 0) {
+				got_zero = 1;
+				semop_completed |= wake_const_ops(sma, num, pt);
+			}
+		}
+	} else {
+		/*
+		 * No sops means modified semaphores not known.
+		 * Assume all were changed.
 		 */
-		BUG_ON(q->sops[0].sem_op >= 0);
-		return 0;
+		for (i = 0; i < sma->sem_nsems; i++) {
+			if (sma->sem_base[i].semval == 0) {
+				got_zero = 1;
+				semop_completed |= wake_const_ops(sma, i, pt);
+			}
+		}
 	}
 	/*
-	 * semval is 0. Check if there are wait-for-zero semops.
-	 * They must be the first entries in the per-semaphore queue
+	 * If one of the modified semaphores got 0,
+	 * then check the global queue, too.
 	 */
-	h = list_first_entry(&curr->sem_pending, struct sem_queue, list);
-	BUG_ON(h->nsops != 1);
-	BUG_ON(h->sops[0].sem_num != q->sops[0].sem_num);
-
-	/* Yes, there is a wait-for-zero semop. Restart */
-	if (h->sops[0].sem_op == 0)
-		return 1;
+	if (got_zero)
+		semop_completed |= wake_const_ops(sma, -1, pt);
 
-	/* Again - no-one is waiting for the new value. */
-	return 0;
+	return semop_completed;
 }
 
 
@@ -678,6 +814,8 @@ static int check_restart(struct sem_array *sma, struct sem_queue *q)
  * semaphore.
  * The tasks that must be woken up are added to @pt. The return code
  * is stored in q->pid.
+ * The function internally checks if const operations can now succeed.
+ *
  * The function return 1 if at least one semop was completed successfully.
  */
 static int update_queue(struct sem_array *sma, int semnum, struct list_head *pt)
@@ -688,9 +826,9 @@ static int update_queue(struct sem_array *sma, int semnum, struct list_head *pt)
 	int semop_completed = 0;
 
 	if (semnum == -1)
-		pending_list = &sma->sem_pending;
+		pending_list = &sma->pending_alter;
 	else
-		pending_list = &sma->sem_base[semnum].sem_pending;
+		pending_list = &sma->sem_base[semnum].pending_alter;
 
 again:
 	walk = pending_list->next;
@@ -702,16 +840,15 @@ again:
 
 		/* If we are scanning the single sop, per-semaphore list of
 		 * one semaphore and that semaphore is 0, then it is not
-		 * necessary to scan the "alter" entries: simple increments
+		 * necessary to scan further: simple increments
 		 * that affect only one entry succeed immediately and cannot
 		 * be in the  per semaphore pending queue, and decrements
 		 * cannot be successful if the value is already 0.
 		 */
-		if (semnum != -1 && sma->sem_base[semnum].semval == 0 &&
-				q->alter)
+		if (semnum != -1 && sma->sem_base[semnum].semval == 0)
 			break;
 
-		error = try_atomic_semop(sma, q->sops, q->nsops,
+		error = perform_atomic_semop(sma, q->sops, q->nsops,
 					 q->undo, q->pid);
 
 		/* Does q->sleeper still need to sleep? */
@@ -724,6 +861,7 @@ again:
 			restart = 0;
 		} else {
 			semop_completed = 1;
+			do_smart_wakeup_zero(sma, q->sops, q->nsops, pt);
 			restart = check_restart(sma, q);
 		}
 
@@ -742,8 +880,8 @@ again:
  * @otime: force setting otime
  * @pt: list head of the tasks that must be woken up.
  *
- * do_smart_update() does the required called to update_queue, based on the
- * actual changes that were performed on the semaphore array.
+ * do_smart_update() does the required calls to update_queue and wakeup_zero,
+ * based on the actual changes that were performed on the semaphore array.
  * Note that the function does not do the actual wake-up: the caller is
  * responsible for calling wake_up_sem_queue_do(@pt).
  * It is safe to perform this call after dropping all locks.
@@ -752,49 +890,46 @@ static void do_smart_update(struct sem_array *sma, struct sembuf *sops, int nsop
 			int otime, struct list_head *pt)
 {
 	int i;
-	int progress;
-
-	progress = 1;
-retry_global:
-	if (sma->complex_count) {
-		if (update_queue(sma, -1, pt)) {
-			progress = 1;
-			otime = 1;
-			sops = NULL;
-		}
-	}
-	if (!progress)
-		goto done;
 
-	if (!sops) {
-		/* No semops; something special is going on. */
-		for (i = 0; i < sma->sem_nsems; i++) {
-			if (update_queue(sma, i, pt)) {
-				otime = 1;
-				progress = 1;
-			}
-		}
-		goto done_checkretry;
-	}
+	otime |= do_smart_wakeup_zero(sma, sops, nsops, pt);
 
-	/* Check the semaphores that were modified. */
-	for (i = 0; i < nsops; i++) {
-		if (sops[i].sem_op > 0 ||
-			(sops[i].sem_op < 0 &&
-				sma->sem_base[sops[i].sem_num].semval == 0))
-			if (update_queue(sma, sops[i].sem_num, pt)) {
-				otime = 1;
-				progress = 1;
+	if (!list_empty(&sma->pending_alter)) {
+		/* semaphore array uses the global queue - just process it. */
+		otime |= update_queue(sma, -1, pt);
+	} else {
+		if (!sops) {
+			/*
+			 * No sops, thus the modified semaphores are not
+			 * known. Check all.
+			 */
+			for (i = 0; i < sma->sem_nsems; i++)
+				otime |= update_queue(sma, i, pt);
+		} else {
+			/*
+			 * Check the semaphores that were increased:
+			 * - No complex ops, thus all sleeping ops are
+			 *   decrease.
+			 * - if we decreased the value, then any sleeping
+			 *   semaphore ops wont be able to run: If the
+			 *   previous value was too small, then the new
+			 *   value will be too small, too.
+			 */
+			for (i = 0; i < nsops; i++) {
+				if (sops[i].sem_op > 0) {
+					otime |= update_queue(sma,
+							sops[i].sem_num, pt);
+				}
 			}
+		}
 	}
-done_checkretry:
-	if (progress) {
-		progress = 0;
-		goto retry_global;
+	if (otime) {
+		if (sops == NULL) {
+			sma->sem_base[0].sem_otime = get_seconds();
+		} else {
+			sma->sem_base[sops[0].sem_num].sem_otime =
+								get_seconds();
+		}
 	}
-done:
-	if (otime)
-		sma->sem_otime = get_seconds();
 }
 
 
@@ -813,14 +948,14 @@ static int count_semncnt (struct sem_array * sma, ushort semnum)
 	struct sem_queue * q;
 
 	semncnt = 0;
-	list_for_each_entry(q, &sma->sem_base[semnum].sem_pending, list) {
+	list_for_each_entry(q, &sma->sem_base[semnum].pending_alter, list) {
 		struct sembuf * sops = q->sops;
 		BUG_ON(sops->sem_num != semnum);
 		if ((sops->sem_op < 0) && !(sops->sem_flg & IPC_NOWAIT))
 			semncnt++;
 	}
 
-	list_for_each_entry(q, &sma->sem_pending, list) {
+	list_for_each_entry(q, &sma->pending_alter, list) {
 		struct sembuf * sops = q->sops;
 		int nsops = q->nsops;
 		int i;
@@ -839,14 +974,14 @@ static int count_semzcnt (struct sem_array * sma, ushort semnum)
 	struct sem_queue * q;
 
 	semzcnt = 0;
-	list_for_each_entry(q, &sma->sem_base[semnum].sem_pending, list) {
+	list_for_each_entry(q, &sma->sem_base[semnum].pending_const, list) {
 		struct sembuf * sops = q->sops;
 		BUG_ON(sops->sem_num != semnum);
 		if ((sops->sem_op == 0) && !(sops->sem_flg & IPC_NOWAIT))
 			semzcnt++;
 	}
 
-	list_for_each_entry(q, &sma->sem_pending, list) {
+	list_for_each_entry(q, &sma->pending_const, list) {
 		struct sembuf * sops = q->sops;
 		int nsops = q->nsops;
 		int i;
@@ -872,7 +1007,7 @@ static void freeary(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp)
 	int i;
 
 	/* Free the existing undo structures for this semaphore set.  */
-	assert_spin_locked(&sma->sem_perm.lock);
+	ipc_assert_locked_object(&sma->sem_perm);
 	list_for_each_entry_safe(un, tu, &sma->list_id, list_id) {
 		list_del(&un->list_id);
 		spin_lock(&un->ulp->lock);
@@ -884,13 +1019,22 @@ static void freeary(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp)
 
 	/* Wake up all pending processes and let them fail with EIDRM. */
 	INIT_LIST_HEAD(&tasks);
-	list_for_each_entry_safe(q, tq, &sma->sem_pending, list) {
+	list_for_each_entry_safe(q, tq, &sma->pending_const, list) {
+		unlink_queue(sma, q);
+		wake_up_sem_queue_prepare(&tasks, q, -EIDRM);
+	}
+
+	list_for_each_entry_safe(q, tq, &sma->pending_alter, list) {
 		unlink_queue(sma, q);
 		wake_up_sem_queue_prepare(&tasks, q, -EIDRM);
 	}
 	for (i = 0; i < sma->sem_nsems; i++) {
 		struct sem *sem = sma->sem_base + i;
-		list_for_each_entry_safe(q, tq, &sem->sem_pending, list) {
+		list_for_each_entry_safe(q, tq, &sem->pending_const, list) {
+			unlink_queue(sma, q);
+			wake_up_sem_queue_prepare(&tasks, q, -EIDRM);
+		}
+		list_for_each_entry_safe(q, tq, &sem->pending_alter, list) {
 			unlink_queue(sma, q);
 			wake_up_sem_queue_prepare(&tasks, q, -EIDRM);
 		}
@@ -931,6 +1075,21 @@ static unsigned long copy_semid_to_user(void __user *buf, struct semid64_ds *in,
 	}
 }
 
+static time_t get_semotime(struct sem_array *sma)
+{
+	int i;
+	time_t res;
+
+	res = sma->sem_base[0].sem_otime;
+	for (i = 1; i < sma->sem_nsems; i++) {
+		time_t to = sma->sem_base[i].sem_otime;
+
+		if (to > res)
+			res = to;
+	}
+	return res;
+}
+
 static int semctl_nolock(struct ipc_namespace *ns, int semid,
 			 int cmd, int version, void __user *p)
 {
@@ -1004,9 +1163,9 @@ static int semctl_nolock(struct ipc_namespace *ns, int semid,
 			goto out_unlock;
 
 		kernel_to_ipc64_perm(&sma->sem_perm, &tbuf.sem_perm);
-		tbuf.sem_otime  = sma->sem_otime;
-		tbuf.sem_ctime  = sma->sem_ctime;
-		tbuf.sem_nsems  = sma->sem_nsems;
+		tbuf.sem_otime = get_semotime(sma);
+		tbuf.sem_ctime = sma->sem_ctime;
+		tbuf.sem_nsems = sma->sem_nsems;
 		rcu_read_unlock();
 		if (copy_semid_to_user(p, &tbuf, version))
 			return -EFAULT;
@@ -1070,7 +1229,7 @@ static int semctl_setval(struct ipc_namespace *ns, int semid, int semnum,
 
 	curr = &sma->sem_base[semnum];
 
-	assert_spin_locked(&sma->sem_perm.lock);
+	ipc_assert_locked_object(&sma->sem_perm);
 	list_for_each_entry(un, &sma->list_id, list_id)
 		un->semadj[semnum] = 0;
 
@@ -1199,7 +1358,7 @@ static int semctl_main(struct ipc_namespace *ns, int semid, int semnum,
 		for (i = 0; i < nsems; i++)
 			sma->sem_base[i].semval = sem_io[i];
 
-		assert_spin_locked(&sma->sem_perm.lock);
+		ipc_assert_locked_object(&sma->sem_perm);
 		list_for_each_entry(un, &sma->list_id, list_id) {
 			for (i = 0; i < nsems; i++)
 				un->semadj[i] = 0;
@@ -1289,39 +1448,43 @@ static int semctl_down(struct ipc_namespace *ns, int semid,
 			return -EFAULT;
 	}
 
+	down_write(&sem_ids(ns).rw_mutex);
+	rcu_read_lock();
+
 	ipcp = ipcctl_pre_down_nolock(ns, &sem_ids(ns), semid, cmd,
 				      &semid64.sem_perm, 0);
-	if (IS_ERR(ipcp))
-		return PTR_ERR(ipcp);
+	if (IS_ERR(ipcp)) {
+		err = PTR_ERR(ipcp);
+		goto out_unlock1;
+	}
 
 	sma = container_of(ipcp, struct sem_array, sem_perm);
 
 	err = security_sem_semctl(sma, cmd);
-	if (err) {
-		rcu_read_unlock();
-		goto out_up;
-	}
+	if (err)
+		goto out_unlock1;
 
-	switch(cmd){
+	switch (cmd) {
 	case IPC_RMID:
 		sem_lock(sma, NULL, -1);
+		/* freeary unlocks the ipc object and rcu */
 		freeary(ns, ipcp);
 		goto out_up;
 	case IPC_SET:
 		sem_lock(sma, NULL, -1);
 		err = ipc_update_perm(&semid64.sem_perm, ipcp);
 		if (err)
-			goto out_unlock;
+			goto out_unlock0;
 		sma->sem_ctime = get_seconds();
 		break;
 	default:
-		rcu_read_unlock();
 		err = -EINVAL;
-		goto out_up;
+		goto out_unlock1;
 	}
 
-out_unlock:
+out_unlock0:
 	sem_unlock(sma, -1);
+out_unlock1:
 	rcu_read_unlock();
 out_up:
 	up_write(&sem_ids(ns).rw_mutex);
@@ -1496,7 +1659,7 @@ static struct sem_undo *find_alloc_undo(struct ipc_namespace *ns, int semid)
 	new->semid = semid;
 	assert_spin_locked(&ulp->lock);
 	list_add_rcu(&new->list_proc, &ulp->list_proc);
-	assert_spin_locked(&sma->sem_perm.lock);
+	ipc_assert_locked_object(&sma->sem_perm);
 	list_add(&new->list_id, &sma->list_id);
 	un = new;
 
@@ -1533,7 +1696,6 @@ static int get_queue_result(struct sem_queue *q)
 	return error;
 }
 
-
 SYSCALL_DEFINE4(semtimedop, int, semid, struct sembuf __user *, tsops,
 		unsigned, nsops, const struct timespec __user *, timeout)
 {
@@ -1631,7 +1793,8 @@ SYSCALL_DEFINE4(semtimedop, int, semid, struct sembuf __user *, tsops,
 	if (un && un->semid == -1)
 		goto out_unlock_free;
 
-	error = try_atomic_semop (sma, sops, nsops, un, task_tgid_vnr(current));
+	error = perform_atomic_semop(sma, sops, nsops, un,
+					task_tgid_vnr(current));
 	if (error <= 0) {
 		if (alter && error == 0)
 			do_smart_update(sma, sops, nsops, 1, &tasks);
@@ -1653,15 +1816,27 @@ SYSCALL_DEFINE4(semtimedop, int, semid, struct sembuf __user *, tsops,
 		struct sem *curr;
 		curr = &sma->sem_base[sops->sem_num];
 
-		if (alter)
-			list_add_tail(&queue.list, &curr->sem_pending);
-		else
-			list_add(&queue.list, &curr->sem_pending);
+		if (alter) {
+			if (sma->complex_count) {
+				list_add_tail(&queue.list,
+						&sma->pending_alter);
+			} else {
+
+				list_add_tail(&queue.list,
+						&curr->pending_alter);
+			}
+		} else {
+			list_add_tail(&queue.list, &curr->pending_const);
+		}
 	} else {
+		if (!sma->complex_count)
+			merge_queues(sma);
+
 		if (alter)
-			list_add_tail(&queue.list, &sma->sem_pending);
+			list_add_tail(&queue.list, &sma->pending_alter);
 		else
-			list_add(&queue.list, &sma->sem_pending);
+			list_add_tail(&queue.list, &sma->pending_const);
+
 		sma->complex_count++;
 	}
 
@@ -1833,7 +2008,7 @@ void exit_sem(struct task_struct *tsk)
 		}
 
 		/* remove un from the linked lists */
-		assert_spin_locked(&sma->sem_perm.lock);
+		ipc_assert_locked_object(&sma->sem_perm);
 		list_del(&un->list_id);
 
 		spin_lock(&ulp->lock);
@@ -1882,6 +2057,9 @@ static int sysvipc_sem_proc_show(struct seq_file *s, void *it)
 {
 	struct user_namespace *user_ns = seq_user_ns(s);
 	struct sem_array *sma = it;
+	time_t sem_otime;
+
+	sem_otime = get_semotime(sma);
 
 	return seq_printf(s,
 			  "%10d %10d  %4o %10u %5u %5u %5u %5u %10lu %10lu\n",
@@ -1893,7 +2071,7 @@ static int sysvipc_sem_proc_show(struct seq_file *s, void *it)
 			  from_kgid_munged(user_ns, sma->sem_perm.gid),
 			  from_kuid_munged(user_ns, sma->sem_perm.cuid),
 			  from_kgid_munged(user_ns, sma->sem_perm.cgid),
-			  sma->sem_otime,
+			  sem_otime,
 			  sma->sem_ctime);
 }
 #endif
diff --git a/ipc/shm.c b/ipc/shm.c
index 7e199fa1960..c6b4ad5ce3b 100644
--- a/ipc/shm.c
+++ b/ipc/shm.c
@@ -141,7 +141,7 @@ static inline struct shmid_kernel *shm_lock(struct ipc_namespace *ns, int id)
 static inline void shm_lock_by_ptr(struct shmid_kernel *ipcp)
 {
 	rcu_read_lock();
-	spin_lock(&ipcp->shm_perm.lock);
+	ipc_lock_object(&ipcp->shm_perm);
 }
 
 static inline struct shmid_kernel *shm_lock_check(struct ipc_namespace *ns,
@@ -491,10 +491,10 @@ static int newseg(struct ipc_namespace *ns, struct ipc_params *params)
 
 	sprintf (name, "SYSV%08x", key);
 	if (shmflg & SHM_HUGETLB) {
-		struct hstate *hs = hstate_sizelog((shmflg >> SHM_HUGE_SHIFT)
-						& SHM_HUGE_MASK);
+		struct hstate *hs;
 		size_t hugesize;
 
+		hs = hstate_sizelog((shmflg >> SHM_HUGE_SHIFT) & SHM_HUGE_MASK);
 		if (!hs) {
 			error = -EINVAL;
 			goto no_file;
@@ -535,6 +535,7 @@ static int newseg(struct ipc_namespace *ns, struct ipc_params *params)
 	shp->shm_nattch = 0;
 	shp->shm_file = file;
 	shp->shm_creator = current;
+
 	/*
 	 * shmid gets reported as "inode#" in /proc/pid/maps.
 	 * proc-ps tools use this. Changing this will break them.
@@ -543,7 +544,9 @@ static int newseg(struct ipc_namespace *ns, struct ipc_params *params)
 
 	ns->shm_tot += numpages;
 	error = shp->shm_perm.id;
-	shm_unlock(shp);
+
+	ipc_unlock_object(&shp->shm_perm);
+	rcu_read_unlock();
 	return error;
 
 no_id:
@@ -754,31 +757,42 @@ static int shmctl_down(struct ipc_namespace *ns, int shmid, int cmd,
 			return -EFAULT;
 	}
 
+	down_write(&shm_ids(ns).rw_mutex);
+	rcu_read_lock();
+
 	ipcp = ipcctl_pre_down(ns, &shm_ids(ns), shmid, cmd,
 			       &shmid64.shm_perm, 0);
-	if (IS_ERR(ipcp))
-		return PTR_ERR(ipcp);
+	if (IS_ERR(ipcp)) {
+		err = PTR_ERR(ipcp);
+		/* the ipc lock is not held upon failure */
+		goto out_unlock1;
+	}
 
 	shp = container_of(ipcp, struct shmid_kernel, shm_perm);
 
 	err = security_shm_shmctl(shp, cmd);
 	if (err)
-		goto out_unlock;
+		goto out_unlock0;
+
 	switch (cmd) {
 	case IPC_RMID:
+		/* do_shm_rmid unlocks the ipc object and rcu */
 		do_shm_rmid(ns, ipcp);
 		goto out_up;
 	case IPC_SET:
 		err = ipc_update_perm(&shmid64.shm_perm, ipcp);
 		if (err)
-			goto out_unlock;
+			goto out_unlock0;
 		shp->shm_ctim = get_seconds();
 		break;
 	default:
 		err = -EINVAL;
 	}
-out_unlock:
-	shm_unlock(shp);
+
+out_unlock0:
+	ipc_unlock_object(&shp->shm_perm);
+out_unlock1:
+	rcu_read_unlock();
 out_up:
 	up_write(&shm_ids(ns).rw_mutex);
 	return err;
diff --git a/ipc/util.c b/ipc/util.c
index 809ec5ec812..4704223bfad 100644
--- a/ipc/util.c
+++ b/ipc/util.c
@@ -246,9 +246,8 @@ int ipc_get_maxid(struct ipc_ids *ids)
  *	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.
+ *	Called with writer ipc_ids.rw_mutex held.
  */
- 
 int ipc_addid(struct ipc_ids* ids, struct kern_ipc_perm* new, int size)
 {
 	kuid_t euid;
@@ -469,9 +468,7 @@ void ipc_free(void* ptr, int size)
 struct ipc_rcu {
 	struct rcu_head rcu;
 	atomic_t refcount;
-	/* "void *" makes sure alignment of following data is sane. */
-	void *data[0];
-};
+} ____cacheline_aligned_in_smp;
 
 /**
  *	ipc_rcu_alloc	-	allocate ipc and rcu space 
@@ -489,12 +486,14 @@ void *ipc_rcu_alloc(int size)
 	if (unlikely(!out))
 		return NULL;
 	atomic_set(&out->refcount, 1);
-	return out->data;
+	return out + 1;
 }
 
 int ipc_rcu_getref(void *ptr)
 {
-	return atomic_inc_not_zero(&container_of(ptr, struct ipc_rcu, data)->refcount);
+	struct ipc_rcu *p = ((struct ipc_rcu *)ptr) - 1;
+
+	return atomic_inc_not_zero(&p->refcount);
 }
 
 /**
@@ -508,7 +507,7 @@ static void ipc_schedule_free(struct rcu_head *head)
 
 void ipc_rcu_putref(void *ptr)
 {
-	struct ipc_rcu *p = container_of(ptr, struct ipc_rcu, data);
+	struct ipc_rcu *p = ((struct ipc_rcu *)ptr) - 1;
 
 	if (!atomic_dec_and_test(&p->refcount))
 		return;
@@ -747,8 +746,10 @@ int ipc_update_perm(struct ipc64_perm *in, struct kern_ipc_perm *out)
  * 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
+ *  - returns the ipc with the ipc lock held in case of success
  *    or an err-code without any lock held otherwise.
+ *
+ * Call holding the both the rw_mutex and the rcu read lock.
  */
 struct kern_ipc_perm *ipcctl_pre_down(struct ipc_namespace *ns,
 				      struct ipc_ids *ids, int id, int cmd,
@@ -773,13 +774,10 @@ struct kern_ipc_perm *ipcctl_pre_down_nolock(struct ipc_namespace *ns,
 	int err = -EPERM;
 	struct kern_ipc_perm *ipcp;
 
-	down_write(&ids->rw_mutex);
-	rcu_read_lock();
-
 	ipcp = ipc_obtain_object_check(ids, id);
 	if (IS_ERR(ipcp)) {
 		err = PTR_ERR(ipcp);
-		goto out_up;
+		goto err;
 	}
 
 	audit_ipc_obj(ipcp);
@@ -790,16 +788,8 @@ struct kern_ipc_perm *ipcctl_pre_down_nolock(struct ipc_namespace *ns,
 	euid = current_euid();
 	if (uid_eq(euid, ipcp->cuid) || uid_eq(euid, ipcp->uid)  ||
 	    ns_capable(ns->user_ns, CAP_SYS_ADMIN))
-		return ipcp;
-
-out_up:
-	/*
-	 * Unsuccessful lookup, unlock and return
-	 * the corresponding error.
-	 */
-	rcu_read_unlock();
-	up_write(&ids->rw_mutex);
-
+		return ipcp; /* successful lookup */
+err:
 	return ERR_PTR(err);
 }
 
diff --git a/ipc/util.h b/ipc/util.h
index 2b0bdd5d92c..b6a6a88f300 100644
--- a/ipc/util.h
+++ b/ipc/util.h
@@ -159,21 +159,31 @@ static inline int ipc_checkid(struct kern_ipc_perm *ipcp, int uid)
 	return uid / SEQ_MULTIPLIER != ipcp->seq;
 }
 
-static inline void ipc_lock_by_ptr(struct kern_ipc_perm *perm)
+static inline void ipc_lock_object(struct kern_ipc_perm *perm)
 {
-	rcu_read_lock();
 	spin_lock(&perm->lock);
 }
 
-static inline void ipc_unlock(struct kern_ipc_perm *perm)
+static inline void ipc_unlock_object(struct kern_ipc_perm *perm)
 {
 	spin_unlock(&perm->lock);
-	rcu_read_unlock();
 }
 
-static inline void ipc_lock_object(struct kern_ipc_perm *perm)
+static inline void ipc_assert_locked_object(struct kern_ipc_perm *perm)
 {
-	spin_lock(&perm->lock);
+	assert_spin_locked(&perm->lock);
+}
+
+static inline void ipc_lock_by_ptr(struct kern_ipc_perm *perm)
+{
+	rcu_read_lock();
+	ipc_lock_object(perm);
+}
+
+static inline void ipc_unlock(struct kern_ipc_perm *perm)
+{
+	ipc_unlock_object(perm);
+	rcu_read_unlock();
 }
 
 struct kern_ipc_perm *ipc_lock_check(struct ipc_ids *ids, int id);