7 files changed, 263 insertions, 267 deletions

diff --git a/ipc/ipc_sysctl.c b/ipc/ipc_sysctl.c
index d3497465cc0a..69bc85978ba0 100644
--- a/ipc/ipc_sysctl.c
+++ b/ipc/ipc_sysctl.c
@@ -27,15 +27,17 @@ static void *get_ipc(ctl_table *table)
 }
 
 /*
- * Routine that is called when a tunable has successfully been changed by
- * hand and it has a callback routine registered on the ipc namespace notifier
- * chain: we don't want such tunables to be recomputed anymore upon memory
- * add/remove or ipc namespace creation/removal.
- * They can come back to a recomputable state by being set to a <0 value.
+ * 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 tunable_set_callback(int val)
+static void ipc_auto_callback(int val)
 {
-        if (val >= 0)
+        if (!val)
                 unregister_ipcns_notifier(current->nsproxy->ipc_ns);
         else {
                 /*
@@ -71,7 +73,12 @@ static int proc_ipc_callback_dointvec(ctl_table *table, int write,
         rc = proc_dointvec(&ipc_table, write, filp, buffer, lenp, ppos);
 
         if (write && !rc && lenp_bef == *lenp)
-                tunable_set_callback(*((int *)(ipc_table.data)));
+                /*
+                 * 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;
 }
@@ -87,10 +94,39 @@ static int proc_ipc_doulongvec_minmax(ctl_table *table, int write,
                                         lenp, ppos);
 }
 
+static int proc_ipcauto_dointvec_minmax(ctl_table *table, int write,
+        struct file *filp, 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, filp, 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
@@ -142,14 +178,11 @@ static int sysctl_ipc_registered_data(ctl_table *table, int __user *name,
         rc = sysctl_ipc_data(table, name, nlen, oldval, oldlenp, newval,
                 newlen);
 
-        if (newval && newlen && rc > 0) {
+        if (newval && newlen && rc > 0)
                 /*
                  * Tunable has successfully been changed from userland
                  */
-                int *data = get_ipc(table);
-
-                tunable_set_callback(*data);
-        }
+                unregister_ipcns_notifier(current->nsproxy->ipc_ns);
 
         return rc;
 }
@@ -158,6 +191,9 @@ static int sysctl_ipc_registered_data(ctl_table *table, int __user *name,
 #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,
@@ -222,6 +258,16 @@ static struct ctl_table ipc_kern_table[] = {
                 .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,
+        },
         {}
 };
 
diff --git a/ipc/ipcns_notifier.c b/ipc/ipcns_notifier.c
index 70ff09183f7b..b9b31a4f77e1 100644
--- a/ipc/ipcns_notifier.c
+++ b/ipc/ipcns_notifier.c
@@ -55,25 +55,35 @@ static int ipcns_callback(struct notifier_block *self,
 
 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;
-        return blocking_notifier_chain_register(&ipcns_chain, &ns->ipcns_nb);
+        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;
-        return blocking_notifier_chain_cond_register(&ipcns_chain,
+        rc = blocking_notifier_chain_cond_register(&ipcns_chain,
                                                         &ns->ipcns_nb);
+        if (!rc)
+                ns->auto_msgmni = 1;
+        return rc;
 }
 
-int unregister_ipcns_notifier(struct ipc_namespace *ns)
+void unregister_ipcns_notifier(struct ipc_namespace *ns)
 {
-        return blocking_notifier_chain_unregister(&ipcns_chain,
-                                                &ns->ipcns_nb);
+        blocking_notifier_chain_unregister(&ipcns_chain, &ns->ipcns_nb);
+        ns->auto_msgmni = 0;
 }
 
 int ipcns_notify(unsigned long val)
diff --git a/ipc/mqueue.c b/ipc/mqueue.c
index b3b69fd51330..96fb36cd9874 100644
--- a/ipc/mqueue.c
+++ b/ipc/mqueue.c
@@ -207,7 +207,7 @@ static int mqueue_get_sb(struct file_system_type *fs_type,
         return get_sb_single(fs_type, flags, data, mqueue_fill_super, mnt);
 }
 
-static void init_once(struct kmem_cache *cachep, void *foo)
+static void init_once(void *foo)
 {
         struct mqueue_inode_info *p = (struct mqueue_inode_info *) foo;
 
@@ -314,15 +314,11 @@ static int mqueue_unlink(struct inode *dir, struct dentry *dentry)
 *       through std routines)
 */
 static ssize_t mqueue_read_file(struct file *filp, char __user *u_data,
-                                size_t count, loff_t * off)
+                                size_t count, loff_t *off)
 {
         struct mqueue_inode_info *info = MQUEUE_I(filp->f_path.dentry->d_inode);
         char buffer[FILENT_SIZE];
-        size_t slen;
-        loff_t o;
-
-        if (!count)
-                return 0;
+        ssize_t ret;
 
         spin_lock(&info->lock);
         snprintf(buffer, sizeof(buffer),
@@ -335,21 +331,14 @@ static ssize_t mqueue_read_file(struct file *filp, char __user *u_data,
                         pid_vnr(info->notify_owner));
         spin_unlock(&info->lock);
         buffer[sizeof(buffer)-1] = '\0';
-        slen = strlen(buffer)+1;
-
-        o = *off;
-        if (o > slen)
-                return 0;
-
-        if (o + count > slen)
-                count = slen - o;
 
-        if (copy_to_user(u_data, buffer + o, count))
-                return -EFAULT;
+        ret = simple_read_from_buffer(u_data, count, off, buffer,
+                                strlen(buffer));
+        if (ret <= 0)
+                return ret;
 
-        *off = o + count;
         filp->f_path.dentry->d_inode->i_atime = filp->f_path.dentry->d_inode->i_ctime = CURRENT_TIME;
-        return count;
+        return ret;
 }
 
 static int mqueue_flush_file(struct file *filp, fl_owner_t id)
@@ -649,7 +638,7 @@ static int oflag2acc[O_ACCMODE] = { MAY_READ, MAY_WRITE,
                 return ERR_PTR(-EINVAL);
         }
 
-        if (permission(dentry->d_inode, oflag2acc[oflag & O_ACCMODE], NULL)) {
+        if (inode_permission(dentry->d_inode, oflag2acc[oflag & O_ACCMODE])) {
                 dput(dentry);
                 mntput(mqueue_mnt);
                 return ERR_PTR(-EACCES);
@@ -1054,7 +1043,7 @@ retry:
                         }
 
                         timeo = MAX_SCHEDULE_TIMEOUT;
-                        ret = netlink_attachskb(sock, nc, 0, &timeo, NULL);
+                        ret = netlink_attachskb(sock, nc, &timeo, NULL);
                         if (ret == 1)
                                 goto retry;
                         if (ret) {
diff --git a/ipc/sem.c b/ipc/sem.c
index e9418df5ff3e..bf1bc36cb7ee 100644
--- a/ipc/sem.c
+++ b/ipc/sem.c
@@ -272,9 +272,8 @@ static int newary(struct ipc_namespace *ns, struct ipc_params *params)
         ns->used_sems += nsems;
 
         sma->sem_base = (struct sem *) &sma[1];
-        /* sma->sem_pending = NULL; */
-        sma->sem_pending_last = &sma->sem_pending;
-        /* sma->undo = NULL; */
+        INIT_LIST_HEAD(&sma->sem_pending);
+        INIT_LIST_HEAD(&sma->list_id);
         sma->sem_nsems = nsems;
         sma->sem_ctime = get_seconds();
         sem_unlock(sma);
@@ -331,38 +330,6 @@ asmlinkage long sys_semget(key_t key, int nsems, int semflg)
         return ipcget(ns, &sem_ids(ns), &sem_ops, &sem_params);
 }
 
-/* Manage the doubly linked list sma->sem_pending as a FIFO:
- * insert new queue elements at the tail sma->sem_pending_last.
- */
-static inline void append_to_queue (struct sem_array * sma,
-                                    struct sem_queue * q)
-{
-        *(q->prev = sma->sem_pending_last) = q;
-        *(sma->sem_pending_last = &q->next) = NULL;
-}
-
-static inline void prepend_to_queue (struct sem_array * sma,
-                                     struct sem_queue * q)
-{
-        q->next = sma->sem_pending;
-        *(q->prev = &sma->sem_pending) = q;
-        if (q->next)
-                q->next->prev = &q->next;
-        else /* sma->sem_pending_last == &sma->sem_pending */
-                sma->sem_pending_last = &q->next;
-}
-
-static inline void remove_from_queue (struct sem_array * sma,
-                                      struct sem_queue * q)
-{
-        *(q->prev) = q->next;
-        if (q->next)
-                q->next->prev = q->prev;
-        else /* sma->sem_pending_last == &q->next */
-                sma->sem_pending_last = q->prev;
-        q->prev = NULL; /* mark as removed */
-}
-
 /*
  * 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.
@@ -438,16 +405,15 @@ static void update_queue (struct sem_array * sma)
         int error;
         struct sem_queue * q;
 
-        q = sma->sem_pending;
-        while(q) {
+        q = list_entry(sma->sem_pending.next, struct sem_queue, list);
+        while (&q->list != &sma->sem_pending) {
                 error = try_atomic_semop(sma, q->sops, q->nsops,
                                          q->undo, q->pid);
 
                 /* Does q->sleeper still need to sleep? */
                 if (error <= 0) {
                         struct sem_queue *n;
-                        remove_from_queue(sma,q);
-                        q->status = IN_WAKEUP;
+
                         /*
                          * Continue scanning. The next operation
                          * that must be checked depends on the type of the
@@ -458,11 +424,26 @@ static void update_queue (struct sem_array * sma)
                          *   for semaphore values to become 0.
                          * - if the operation didn't modify the array,
                          *   then just continue.
+                         * The order of list_del() and reading ->next
+                         * is crucial: In the former case, the list_del()
+                         * must be done first [because we might be the
+                         * first entry in ->sem_pending], in the latter
+                         * case the list_del() must be done last
+                         * [because the list is invalid after the list_del()]
                          */
-                        if (q->alter)
-                                n = sma->sem_pending;
-                        else
-                                n = q->next;
+                        if (q->alter) {
+                                list_del(&q->list);
+                                n = list_entry(sma->sem_pending.next,
+                                                struct sem_queue, list);
+                        } else {
+                                n = list_entry(q->list.next, struct sem_queue,
+                                                list);
+                                list_del(&q->list);
+                        }
+
+                        /* wake up the waiting thread */
+                        q->status = IN_WAKEUP;
+
                         wake_up_process(q->sleeper);
                         /* hands-off: q will disappear immediately after
                          * writing q->status.
@@ -471,7 +452,7 @@ static void update_queue (struct sem_array * sma)
                         q->status = error;
                         q = n;
                 } else {
-                        q = q->next;
+                        q = list_entry(q->list.next, struct sem_queue, list);
                 }
         }
 }
@@ -491,7 +472,7 @@ static int count_semncnt (struct sem_array * sma, ushort semnum)
         struct sem_queue * q;
 
         semncnt = 0;
-        for (q = sma->sem_pending; q; q = q->next) {
+        list_for_each_entry(q, &sma->sem_pending, list) {
                 struct sembuf * sops = q->sops;
                 int nsops = q->nsops;
                 int i;
@@ -503,13 +484,14 @@ static int count_semncnt (struct sem_array * sma, ushort semnum)
         }
         return semncnt;
 }
+
 static int count_semzcnt (struct sem_array * sma, ushort semnum)
 {
         int semzcnt;
         struct sem_queue * q;
 
         semzcnt = 0;
-        for (q = sma->sem_pending; q; q = q->next) {
+        list_for_each_entry(q, &sma->sem_pending, list) {
                 struct sembuf * sops = q->sops;
                 int nsops = q->nsops;
                 int i;
@@ -522,35 +504,41 @@ static int count_semzcnt (struct sem_array * sma, ushort semnum)
         return semzcnt;
 }
 
+void free_un(struct rcu_head *head)
+{
+        struct sem_undo *un = container_of(head, struct sem_undo, rcu);
+        kfree(un);
+}
+
 /* Free a semaphore set. freeary() is called with sem_ids.rw_mutex locked
  * as a writer and the spinlock for this semaphore set hold. sem_ids.rw_mutex
  * remains locked on exit.
  */
 static void freeary(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp)
 {
-        struct sem_undo *un;
-        struct sem_queue *q;
+        struct sem_undo *un, *tu;
+        struct sem_queue *q, *tq;
         struct sem_array *sma = container_of(ipcp, struct sem_array, sem_perm);
 
-        /* Invalidate the existing undo structures for this semaphore set.
-         * (They will be freed without any further action in exit_sem()
-         * or during the next semop.)
-         */
-        for (un = sma->undo; un; un = un->id_next)
+        /* Free the existing undo structures for this semaphore set.  */
+        assert_spin_locked(&sma->sem_perm.lock);
+        list_for_each_entry_safe(un, tu, &sma->list_id, list_id) {
+                list_del(&un->list_id);
+                spin_lock(&un->ulp->lock);
                 un->semid = -1;
+                list_del_rcu(&un->list_proc);
+                spin_unlock(&un->ulp->lock);
+                call_rcu(&un->rcu, free_un);
+        }
 
         /* Wake up all pending processes and let them fail with EIDRM. */
-        q = sma->sem_pending;
-        while(q) {
-                struct sem_queue *n;
-                /* lazy remove_from_queue: we are killing the whole queue */
-                q->prev = NULL;
-                n = q->next;
+        list_for_each_entry_safe(q, tq, &sma->sem_pending, list) {
+                list_del(&q->list);
+
                 q->status = IN_WAKEUP;
                 wake_up_process(q->sleeper); /* doesn't sleep */
                 smp_wmb();
                 q->status = -EIDRM;     /* hands-off q */
-                q = n;
         }
 
         /* Remove the semaphore set from the IDR */
@@ -763,9 +751,12 @@ 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];
-                for (un = sma->undo; un; un = un->id_next)
+
+                assert_spin_locked(&sma->sem_perm.lock);
+                list_for_each_entry(un, &sma->list_id, list_id) {
                         for (i = 0; i < nsems; i++)
                                 un->semadj[i] = 0;
+                }
                 sma->sem_ctime = get_seconds();
                 /* maybe some queued-up processes were waiting for this */
                 update_queue(sma);
@@ -797,12 +788,15 @@ static int semctl_main(struct ipc_namespace *ns, int semid, int semnum,
         {
                 int val = arg.val;
                 struct sem_undo *un;
+
                 err = -ERANGE;
                 if (val > SEMVMX || val < 0)
                         goto out_unlock;
 
-                for (un = sma->undo; un; un = un->id_next)
+                assert_spin_locked(&sma->sem_perm.lock);
+                list_for_each_entry(un, &sma->list_id, list_id)
                         un->semadj[semnum] = 0;
+
                 curr->semval = val;
                 curr->sempid = task_tgid_vnr(current);
                 sma->sem_ctime = get_seconds();
@@ -952,6 +946,8 @@ static inline int get_undo_list(struct sem_undo_list **undo_listp)
                         return -ENOMEM;
                 spin_lock_init(&undo_list->lock);
                 atomic_set(&undo_list->refcnt, 1);
+                INIT_LIST_HEAD(&undo_list->list_proc);
+
                 current->sysvsem.undo_list = undo_list;
         }
         *undo_listp = undo_list;
@@ -960,25 +956,27 @@ static inline int get_undo_list(struct sem_undo_list **undo_listp)
 
 static struct sem_undo *lookup_undo(struct sem_undo_list *ulp, int semid)
 {
-        struct sem_undo **last, *un;
+        struct sem_undo *walk;
 
-        last = &ulp->proc_list;
-        un = *last;
-        while(un != NULL) {
-                if(un->semid==semid)
-                        break;
-                if(un->semid==-1) {
-                        *last=un->proc_next;
-                        kfree(un);
-                } else {
-                        last=&un->proc_next;
-                }
-                un=*last;
+        list_for_each_entry_rcu(walk, &ulp->list_proc, list_proc) {
+                if (walk->semid == semid)
+                        return walk;
         }
-        return un;
+        return NULL;
 }
 
-static struct sem_undo *find_undo(struct ipc_namespace *ns, int semid)
+/**
+ * find_alloc_undo - Lookup (and if not present create) undo array
+ * @ns: namespace
+ * @semid: semaphore array id
+ *
+ * The function looks up (and if not present creates) the undo structure.
+ * The size of the undo structure depends on the size of the semaphore
+ * array, thus the alloc path is not that straightforward.
+ * Lifetime-rules: sem_undo is rcu-protected, on success, the function
+ * performs a rcu_read_lock().
+ */
+static struct sem_undo *find_alloc_undo(struct ipc_namespace *ns, int semid)
 {
         struct sem_array *sma;
         struct sem_undo_list *ulp;
@@ -990,13 +988,16 @@ static struct sem_undo *find_undo(struct ipc_namespace *ns, int semid)
         if (error)
                 return ERR_PTR(error);
 
+        rcu_read_lock();
         spin_lock(&ulp->lock);
         un = lookup_undo(ulp, semid);
         spin_unlock(&ulp->lock);
         if (likely(un!=NULL))
                 goto out;
+        rcu_read_unlock();
 
         /* no undo structure around - allocate one. */
+        /* step 1: figure out the size of the semaphore array */
         sma = sem_lock_check(ns, semid);
         if (IS_ERR(sma))
                 return ERR_PTR(PTR_ERR(sma));
@@ -1004,37 +1005,45 @@ static struct sem_undo *find_undo(struct ipc_namespace *ns, int semid)
         nsems = sma->sem_nsems;
         sem_getref_and_unlock(sma);
 
+        /* step 2: allocate new undo structure */
         new = kzalloc(sizeof(struct sem_undo) + sizeof(short)*nsems, GFP_KERNEL);
         if (!new) {
                 sem_putref(sma);
                 return ERR_PTR(-ENOMEM);
         }
-        new->semadj = (short *) &new[1];
-        new->semid = semid;
 
-        spin_lock(&ulp->lock);
-        un = lookup_undo(ulp, semid);
-        if (un) {
-                spin_unlock(&ulp->lock);
-                kfree(new);
-                sem_putref(sma);
-                goto out;
-        }
+        /* step 3: Acquire the lock on semaphore array */
         sem_lock_and_putref(sma);
         if (sma->sem_perm.deleted) {
                 sem_unlock(sma);
-                spin_unlock(&ulp->lock);
                 kfree(new);
                 un = ERR_PTR(-EIDRM);
                 goto out;
         }
-        new->proc_next = ulp->proc_list;
-        ulp->proc_list = new;
-        new->id_next = sma->undo;
-        sma->undo = new;
-        sem_unlock(sma);
+        spin_lock(&ulp->lock);
+
+        /*
+         * step 4: check for races: did someone else allocate the undo struct?
+         */
+        un = lookup_undo(ulp, semid);
+        if (un) {
+                kfree(new);
+                goto success;
+        }
+        /* step 5: initialize & link new undo structure */
+        new->semadj = (short *) &new[1];
+        new->ulp = ulp;
+        new->semid = semid;
+        assert_spin_locked(&ulp->lock);
+        list_add_rcu(&new->list_proc, &ulp->list_proc);
+        assert_spin_locked(&sma->sem_perm.lock);
+        list_add(&new->list_id, &sma->list_id);
         un = new;
+
+success:
         spin_unlock(&ulp->lock);
+        rcu_read_lock();
+        sem_unlock(sma);
 out:
         return un;
 }
@@ -1090,9 +1099,8 @@ asmlinkage long sys_semtimedop(int semid, struct sembuf __user *tsops,
                         alter = 1;
         }
 
-retry_undos:
         if (undos) {
-                un = find_undo(ns, semid);
+                un = find_alloc_undo(ns, semid);
                 if (IS_ERR(un)) {
                         error = PTR_ERR(un);
                         goto out_free;
@@ -1102,19 +1110,37 @@ retry_undos:
 
         sma = sem_lock_check(ns, semid);
         if (IS_ERR(sma)) {
+                if (un)
+                        rcu_read_unlock();
                 error = PTR_ERR(sma);
                 goto out_free;
         }
 
         /*
-         * semid identifiers are not unique - find_undo may have
+         * semid identifiers are not unique - find_alloc_undo may have
          * allocated an undo structure, it was invalidated by an RMID
-         * and now a new array with received the same id. Check and retry.
+         * and now a new array with received the same id. Check and fail.
+         * This case can be detected checking un->semid. The existance of
+         * "un" itself is guaranteed by rcu.
          */
-        if (un && un->semid == -1) {
-                sem_unlock(sma);
-                goto retry_undos;
+        error = -EIDRM;
+        if (un) {
+                if (un->semid == -1) {
+                        rcu_read_unlock();
+                        goto out_unlock_free;
+                } else {
+                        /*
+                         * rcu lock can be released, "un" cannot disappear:
+                         * - sem_lock is acquired, thus IPC_RMID is
+                         *   impossible.
+                         * - exit_sem is impossible, it always operates on
+                         *   current (or a dead task).
+                         */
+
+                        rcu_read_unlock();
+                }
         }
+
         error = -EFBIG;
         if (max >= sma->sem_nsems)
                 goto out_unlock_free;
@@ -1138,17 +1164,15 @@ retry_undos:
          * task into the pending queue and go to sleep.
          */
                 
-        queue.sma = sma;
         queue.sops = sops;
         queue.nsops = nsops;
         queue.undo = un;
         queue.pid = task_tgid_vnr(current);
-        queue.id = semid;
         queue.alter = alter;
         if (alter)
-                append_to_queue(sma ,&queue);
+                list_add_tail(&queue.list, &sma->sem_pending);
         else
-                prepend_to_queue(sma ,&queue);
+                list_add(&queue.list, &sma->sem_pending);
 
         queue.status = -EINTR;
         queue.sleeper = current;
@@ -1174,7 +1198,6 @@ retry_undos:
 
         sma = sem_lock(ns, semid);
         if (IS_ERR(sma)) {
-                BUG_ON(queue.prev != NULL);
                 error = -EIDRM;
                 goto out_free;
         }
@@ -1192,7 +1215,7 @@ retry_undos:
          */
         if (timeout && jiffies_left == 0)
                 error = -EAGAIN;
-        remove_from_queue(sma,&queue);
+        list_del(&queue.list);
         goto out_unlock_free;
 
 out_unlock_free:
@@ -1243,56 +1266,62 @@ int copy_semundo(unsigned long clone_flags, struct task_struct *tsk)
  */
 void exit_sem(struct task_struct *tsk)
 {
-        struct sem_undo_list *undo_list;
-        struct sem_undo *u, **up;
-        struct ipc_namespace *ns;
+        struct sem_undo_list *ulp;
 
-        undo_list = tsk->sysvsem.undo_list;
-        if (!undo_list)
+        ulp = tsk->sysvsem.undo_list;
+        if (!ulp)
                 return;
         tsk->sysvsem.undo_list = NULL;
 
-        if (!atomic_dec_and_test(&undo_list->refcnt))
+        if (!atomic_dec_and_test(&ulp->refcnt))
                 return;
 
-        ns = tsk->nsproxy->ipc_ns;
-        /* There's no need to hold the semundo list lock, as current
-         * is the last task exiting for this undo list.
-         */
-        for (up = &undo_list->proc_list; (u = *up); *up = u->proc_next, kfree(u)) {
+        for (;;) {
                 struct sem_array *sma;
-                int nsems, i;
-                struct sem_undo *un, **unp;
+                struct sem_undo *un;
                 int semid;
-               
-                semid = u->semid;
+                int i;
 
-                if(semid == -1)
-                        continue;
-                sma = sem_lock(ns, semid);
+                rcu_read_lock();
+                un = list_entry(rcu_dereference(ulp->list_proc.next),
+                                        struct sem_undo, list_proc);
+                if (&un->list_proc == &ulp->list_proc)
+                        semid = -1;
+                 else
+                        semid = un->semid;
+                rcu_read_unlock();
+
+                if (semid == -1)
+                        break;
+
+                sma = sem_lock_check(tsk->nsproxy->ipc_ns, un->semid);
+
+                /* exit_sem raced with IPC_RMID, nothing to do */
                 if (IS_ERR(sma))
                         continue;
 
-                if (u->semid == -1)
-                        goto next_entry;
+                un = lookup_undo(ulp, semid);
+                if (un == NULL) {
+                        /* exit_sem raced with IPC_RMID+semget() that created
+                         * exactly the same semid. Nothing to do.
+                         */
+                        sem_unlock(sma);
+                        continue;
+                }
 
-                BUG_ON(sem_checkid(sma, u->semid));
+                /* remove un from the linked lists */
+                assert_spin_locked(&sma->sem_perm.lock);
+                list_del(&un->list_id);
 
-                /* remove u from the sma->undo list */
-                for (unp = &sma->undo; (un = *unp); unp = &un->id_next) {
-                        if (u == un)
-                                goto found;
-                }
-                printk ("exit_sem undo list error id=%d\n", u->semid);
-                goto next_entry;
-found:
-                *unp = un->id_next;
-                /* perform adjustments registered in u */
-                nsems = sma->sem_nsems;
-                for (i = 0; i < nsems; i++) {
+                spin_lock(&ulp->lock);
+                list_del_rcu(&un->list_proc);
+                spin_unlock(&ulp->lock);
+
+                /* perform adjustments registered in un */
+                for (i = 0; i < sma->sem_nsems; i++) {
                         struct sem * semaphore = &sma->sem_base[i];
-                        if (u->semadj[i]) {
-                                semaphore->semval += u->semadj[i];
+                        if (un->semadj[i]) {
+                                semaphore->semval += un->semadj[i];
                                 /*
                                  * Range checks of the new semaphore value,
                                  * not defined by sus:
@@ -1316,10 +1345,11 @@ found:
                 sma->sem_otime = get_seconds();
                 /* maybe some queued-up processes were waiting for this */
                 update_queue(sma);
-next_entry:
                 sem_unlock(sma);
+
+                call_rcu(&un->rcu, free_un);
         }
-        kfree(undo_list);
+        kfree(ulp);
 }
 
 #ifdef CONFIG_PROC_FS
diff --git a/ipc/shm.c b/ipc/shm.c
index 790240cd067f..e77ec698cf40 100644
--- a/ipc/shm.c
+++ b/ipc/shm.c
@@ -112,23 +112,8 @@ void __init shm_init (void)
 }
 
 /*
- * shm_lock_(check_)down routines are called in the paths where the rw_mutex
- * is held to protect access to the idr tree.
- */
-static inline struct shmid_kernel *shm_lock_down(struct ipc_namespace *ns,
-                                                int id)
-{
-        struct kern_ipc_perm *ipcp = ipc_lock_down(&shm_ids(ns), id);
-
-        if (IS_ERR(ipcp))
-                return (struct shmid_kernel *)ipcp;
-
-        return container_of(ipcp, struct shmid_kernel, shm_perm);
-}
-
-/*
  * shm_lock_(check_) routines are called in the paths where the rw_mutex
- * is not held.
+ * is not necessarily held.
  */
 static inline struct shmid_kernel *shm_lock(struct ipc_namespace *ns, int id)
 {
@@ -211,7 +196,7 @@ static void shm_close(struct vm_area_struct *vma)
 
         down_write(&shm_ids(ns).rw_mutex);
         /* remove from the list of attaches of the shm segment */
-        shp = shm_lock_down(ns, sfd->id);
+        shp = shm_lock(ns, sfd->id);
         BUG_ON(IS_ERR(shp));
         shp->shm_lprid = task_tgid_vnr(current);
         shp->shm_dtim = get_seconds();
@@ -577,7 +562,8 @@ static void shm_get_stat(struct ipc_namespace *ns, unsigned long *rss,
 
                 if (is_file_hugepages(shp->shm_file)) {
                         struct address_space *mapping = inode->i_mapping;
-                        *rss += (HPAGE_SIZE/PAGE_SIZE)*mapping->nrpages;
+                        struct hstate *h = hstate_file(shp->shm_file);
+                        *rss += pages_per_huge_page(h) * mapping->nrpages;
                 } else {
                         struct shmem_inode_info *info = SHMEM_I(inode);
                         spin_lock(&info->lock);
@@ -931,7 +917,7 @@ invalid:
 
 out_nattch:
         down_write(&shm_ids(ns).rw_mutex);
-        shp = shm_lock_down(ns, shmid);
+        shp = shm_lock(ns, shmid);
         BUG_ON(IS_ERR(shp));
         shp->shm_nattch--;
         if(shp->shm_nattch == 0 &&
diff --git a/ipc/util.c b/ipc/util.c
index 3339177b336c..49b3ea615dc5 100644
--- a/ipc/util.c
+++ b/ipc/util.c
@@ -688,10 +688,6 @@ void ipc64_perm_to_ipc_perm (struct ipc64_perm *in, struct ipc_perm *out)
  * Look for an id in the ipc ids idr and lock the associated ipc object.
  *
  * The ipc object is locked on exit.
- *
- * This is the routine that should be called when the rw_mutex is not already
- * held, i.e. idr tree not protected: it protects the idr tree in read mode
- * during the idr_find().
  */
 
 struct kern_ipc_perm *ipc_lock(struct ipc_ids *ids, int id)
@@ -699,18 +695,13 @@ struct kern_ipc_perm *ipc_lock(struct ipc_ids *ids, int id)
         struct kern_ipc_perm *out;
         int lid = ipcid_to_idx(id);
 
-        down_read(&ids->rw_mutex);
-
         rcu_read_lock();
         out = idr_find(&ids->ipcs_idr, lid);
         if (out == NULL) {
                 rcu_read_unlock();
-                up_read(&ids->rw_mutex);
                 return ERR_PTR(-EINVAL);
         }
 
-        up_read(&ids->rw_mutex);
-
         spin_lock(&out->lock);
         
         /* ipc_rmid() may have already freed the ID while ipc_lock
@@ -725,56 +716,6 @@ struct kern_ipc_perm *ipc_lock(struct ipc_ids *ids, int id)
         return out;
 }
 
-/**
- * ipc_lock_down - Lock an ipc structure with rw_sem 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.
- *
- * This is the routine that should be called when the rw_mutex is already
- * held, i.e. idr tree protected.
- */
-
-struct kern_ipc_perm *ipc_lock_down(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);
-
-        /*
-         * No need to verify that the structure is still valid since the
-         * rw_mutex is held.
-         */
-        return out;
-}
-
-struct kern_ipc_perm *ipc_lock_check_down(struct ipc_ids *ids, int id)
-{
-        struct kern_ipc_perm *out;
-
-        out = ipc_lock_down(ids, id);
-        if (IS_ERR(out))
-                return out;
-
-        if (ipc_checkid(out, id)) {
-                ipc_unlock(out);
-                return ERR_PTR(-EIDRM);
-        }
-
-        return out;
-}
-
 struct kern_ipc_perm *ipc_lock_check(struct ipc_ids *ids, int id)
 {
         struct kern_ipc_perm *out;
@@ -846,7 +787,7 @@ struct kern_ipc_perm *ipcctl_pre_down(struct ipc_ids *ids, int id, int cmd,
         int err;
 
         down_write(&ids->rw_mutex);
-        ipcp = ipc_lock_check_down(ids, id);
+        ipcp = ipc_lock_check(ids, id);
         if (IS_ERR(ipcp)) {
                 err = PTR_ERR(ipcp);
                 goto out_up;
diff --git a/ipc/util.h b/ipc/util.h
index cdb966aebe07..3646b45a03c9 100644
--- a/ipc/util.h
+++ b/ipc/util.h
@@ -102,11 +102,6 @@ void* ipc_rcu_alloc(int size);
 void ipc_rcu_getref(void *ptr);
 void ipc_rcu_putref(void *ptr);
 
-/*
- * ipc_lock_down: called with rw_mutex held
- * ipc_lock: called without that lock held
- */
-struct kern_ipc_perm *ipc_lock_down(struct ipc_ids *, int);
 struct kern_ipc_perm *ipc_lock(struct ipc_ids *, int);
 
 void kernel_to_ipc64_perm(struct kern_ipc_perm *in, struct ipc64_perm *out);
@@ -155,7 +150,6 @@ static inline void ipc_unlock(struct kern_ipc_perm *perm)
         rcu_read_unlock();
 }
 
-struct kern_ipc_perm *ipc_lock_check_down(struct ipc_ids *ids, int id);
 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);