Merge commit 'v3.0-rc1' into perf/core

Merge reason: merge in the latest fixes.

Signed-off-by: Ingo Molnar <mingo@elte.hu>

21 files changed, 876 insertions, 733 deletions

diff --git a/kernel/Makefile b/kernel/Makefile
index e9cf19155b46..2d64cfcc8b42 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -61,7 +61,6 @@ obj-$(CONFIG_COMPAT) += compat.o
 obj-$(CONFIG_CGROUPS) += cgroup.o
 obj-$(CONFIG_CGROUP_FREEZER) += cgroup_freezer.o
 obj-$(CONFIG_CPUSETS) += cpuset.o
-obj-$(CONFIG_CGROUP_NS) += ns_cgroup.o
 obj-$(CONFIG_UTS_NS) += utsname.o
 obj-$(CONFIG_USER_NS) += user_namespace.o
 obj-$(CONFIG_PID_NS) += pid_namespace.o
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 909a35510af5..2731d115d725 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -57,6 +57,7 @@
 #include <linux/vmalloc.h> /* TODO: replace with more sophisticated array */
 #include <linux/eventfd.h>
 #include <linux/poll.h>
+#include <linux/flex_array.h> /* used in cgroup_attach_proc */
 
 #include <asm/atomic.h>
 
@@ -1735,6 +1736,76 @@ int cgroup_path(const struct cgroup *cgrp, char *buf, int buflen)
 }
 EXPORT_SYMBOL_GPL(cgroup_path);
 
+/*
+ * cgroup_task_migrate - move a task from one cgroup to another.
+ *
+ * 'guarantee' is set if the caller promises that a new css_set for the task
+ * will already exist. If not set, this function might sleep, and can fail with
+ * -ENOMEM. Otherwise, it can only fail with -ESRCH.
+ */
+static int cgroup_task_migrate(struct cgroup *cgrp, struct cgroup *oldcgrp,
+			       struct task_struct *tsk, bool guarantee)
+{
+	struct css_set *oldcg;
+	struct css_set *newcg;
+
+	/*
+	 * get old css_set. we need to take task_lock and refcount it, because
+	 * an exiting task can change its css_set to init_css_set and drop its
+	 * old one without taking cgroup_mutex.
+	 */
+	task_lock(tsk);
+	oldcg = tsk->cgroups;
+	get_css_set(oldcg);
+	task_unlock(tsk);
+
+	/* locate or allocate a new css_set for this task. */
+	if (guarantee) {
+		/* we know the css_set we want already exists. */
+		struct cgroup_subsys_state *template[CGROUP_SUBSYS_COUNT];
+		read_lock(&css_set_lock);
+		newcg = find_existing_css_set(oldcg, cgrp, template);
+		BUG_ON(!newcg);
+		get_css_set(newcg);
+		read_unlock(&css_set_lock);
+	} else {
+		might_sleep();
+		/* find_css_set will give us newcg already referenced. */
+		newcg = find_css_set(oldcg, cgrp);
+		if (!newcg) {
+			put_css_set(oldcg);
+			return -ENOMEM;
+		}
+	}
+	put_css_set(oldcg);
+
+	/* if PF_EXITING is set, the tsk->cgroups pointer is no longer safe. */
+	task_lock(tsk);
+	if (tsk->flags & PF_EXITING) {
+		task_unlock(tsk);
+		put_css_set(newcg);
+		return -ESRCH;
+	}
+	rcu_assign_pointer(tsk->cgroups, newcg);
+	task_unlock(tsk);
+
+	/* Update the css_set linked lists if we're using them */
+	write_lock(&css_set_lock);
+	if (!list_empty(&tsk->cg_list))
+		list_move(&tsk->cg_list, &newcg->tasks);
+	write_unlock(&css_set_lock);
+
+	/*
+	 * We just gained a reference on oldcg by taking it from the task. As
+	 * trading it for newcg is protected by cgroup_mutex, we're safe to drop
+	 * it here; it will be freed under RCU.
+	 */
+	put_css_set(oldcg);
+
+	set_bit(CGRP_RELEASABLE, &oldcgrp->flags);
+	return 0;
+}
+
 /**
  * cgroup_attach_task - attach task 'tsk' to cgroup 'cgrp'
  * @cgrp: the cgroup the task is attaching to
@@ -1745,11 +1816,9 @@ EXPORT_SYMBOL_GPL(cgroup_path);
  */
 int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk)
 {
-	int retval = 0;
+	int retval;
 	struct cgroup_subsys *ss, *failed_ss = NULL;
 	struct cgroup *oldcgrp;
-	struct css_set *cg;
-	struct css_set *newcg;
 	struct cgroupfs_root *root = cgrp->root;
 
 	/* Nothing to do if the task is already in that cgroup */
@@ -1759,7 +1828,7 @@ int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk)
 
 	for_each_subsys(root, ss) {
 		if (ss->can_attach) {
-			retval = ss->can_attach(ss, cgrp, tsk, false);
+			retval = ss->can_attach(ss, cgrp, tsk);
 			if (retval) {
 				/*
 				 * Remember on which subsystem the can_attach()
@@ -1771,46 +1840,29 @@ int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk)
 				goto out;
 			}
 		}
+		if (ss->can_attach_task) {
+			retval = ss->can_attach_task(cgrp, tsk);
+			if (retval) {
+				failed_ss = ss;
+				goto out;
+			}
+		}
 	}
 
-	task_lock(tsk);
-	cg = tsk->cgroups;
-	get_css_set(cg);
-	task_unlock(tsk);
-	/*
-	 * Locate or allocate a new css_set for this task,
-	 * based on its final set of cgroups
-	 */
-	newcg = find_css_set(cg, cgrp);
-	put_css_set(cg);
-	if (!newcg) {
-		retval = -ENOMEM;
-		goto out;
-	}
-
-	task_lock(tsk);
-	if (tsk->flags & PF_EXITING) {
-		task_unlock(tsk);
-		put_css_set(newcg);
-		retval = -ESRCH;
+	retval = cgroup_task_migrate(cgrp, oldcgrp, tsk, false);
+	if (retval)
 		goto out;
-	}
-	rcu_assign_pointer(tsk->cgroups, newcg);
-	task_unlock(tsk);
-
-	/* Update the css_set linked lists if we're using them */
-	write_lock(&css_set_lock);
-	if (!list_empty(&tsk->cg_list))
-		list_move(&tsk->cg_list, &newcg->tasks);
-	write_unlock(&css_set_lock);
 
 	for_each_subsys(root, ss) {
+		if (ss->pre_attach)
+			ss->pre_attach(cgrp);
+		if (ss->attach_task)
+			ss->attach_task(cgrp, tsk);
 		if (ss->attach)
-			ss->attach(ss, cgrp, oldcgrp, tsk, false);
+			ss->attach(ss, cgrp, oldcgrp, tsk);
 	}
-	set_bit(CGRP_RELEASABLE, &oldcgrp->flags);
+
 	synchronize_rcu();
-	put_css_set(cg);
 
 	/*
 	 * wake up rmdir() waiter. the rmdir should fail since the cgroup
@@ -1829,7 +1881,7 @@ out:
 				 */
 				break;
 			if (ss->cancel_attach)
-				ss->cancel_attach(ss, cgrp, tsk, false);
+				ss->cancel_attach(ss, cgrp, tsk);
 		}
 	}
 	return retval;
@@ -1860,49 +1912,370 @@ int cgroup_attach_task_all(struct task_struct *from, struct task_struct *tsk)
 EXPORT_SYMBOL_GPL(cgroup_attach_task_all);
 
 /*
- * Attach task with pid 'pid' to cgroup 'cgrp'. Call with cgroup_mutex
- * held. May take task_lock of task
+ * cgroup_attach_proc works in two stages, the first of which prefetches all
+ * new css_sets needed (to make sure we have enough memory before committing
+ * to the move) and stores them in a list of entries of the following type.
+ * TODO: possible optimization: use css_set->rcu_head for chaining instead
+ */
+struct cg_list_entry {
+	struct css_set *cg;
+	struct list_head links;
+};
+
+static bool css_set_check_fetched(struct cgroup *cgrp,
+				  struct task_struct *tsk, struct css_set *cg,
+				  struct list_head *newcg_list)
+{
+	struct css_set *newcg;
+	struct cg_list_entry *cg_entry;
+	struct cgroup_subsys_state *template[CGROUP_SUBSYS_COUNT];
+
+	read_lock(&css_set_lock);
+	newcg = find_existing_css_set(cg, cgrp, template);
+	if (newcg)
+		get_css_set(newcg);
+	read_unlock(&css_set_lock);
+
+	/* doesn't exist at all? */
+	if (!newcg)
+		return false;
+	/* see if it's already in the list */
+	list_for_each_entry(cg_entry, newcg_list, links) {
+		if (cg_entry->cg == newcg) {
+			put_css_set(newcg);
+			return true;
+		}
+	}
+
+	/* not found */
+	put_css_set(newcg);
+	return false;
+}
+
+/*
+ * Find the new css_set and store it in the list in preparation for moving the
+ * given task to the given cgroup. Returns 0 or -ENOMEM.
+ */
+static int css_set_prefetch(struct cgroup *cgrp, struct css_set *cg,
+			    struct list_head *newcg_list)
+{
+	struct css_set *newcg;
+	struct cg_list_entry *cg_entry;
+
+	/* ensure a new css_set will exist for this thread */
+	newcg = find_css_set(cg, cgrp);
+	if (!newcg)
+		return -ENOMEM;
+	/* add it to the list */
+	cg_entry = kmalloc(sizeof(struct cg_list_entry), GFP_KERNEL);
+	if (!cg_entry) {
+		put_css_set(newcg);
+		return -ENOMEM;
+	}
+	cg_entry->cg = newcg;
+	list_add(&cg_entry->links, newcg_list);
+	return 0;
+}
+
+/**
+ * cgroup_attach_proc - attach all threads in a threadgroup to a cgroup
+ * @cgrp: the cgroup to attach to
+ * @leader: the threadgroup leader task_struct of the group to be attached
+ *
+ * Call holding cgroup_mutex and the threadgroup_fork_lock of the leader. Will
+ * take task_lock of each thread in leader's threadgroup individually in turn.
+ */
+int cgroup_attach_proc(struct cgroup *cgrp, struct task_struct *leader)
+{
+	int retval, i, group_size;
+	struct cgroup_subsys *ss, *failed_ss = NULL;
+	bool cancel_failed_ss = false;
+	/* guaranteed to be initialized later, but the compiler needs this */
+	struct cgroup *oldcgrp = NULL;
+	struct css_set *oldcg;
+	struct cgroupfs_root *root = cgrp->root;
+	/* threadgroup list cursor and array */
+	struct task_struct *tsk;
+	struct flex_array *group;
+	/*
+	 * we need to make sure we have css_sets for all the tasks we're
+	 * going to move -before- we actually start moving them, so that in
+	 * case we get an ENOMEM we can bail out before making any changes.
+	 */
+	struct list_head newcg_list;
+	struct cg_list_entry *cg_entry, *temp_nobe;
+
+	/*
+	 * step 0: in order to do expensive, possibly blocking operations for
+	 * every thread, we cannot iterate the thread group list, since it needs
+	 * rcu or tasklist locked. instead, build an array of all threads in the
+	 * group - threadgroup_fork_lock prevents new threads from appearing,
+	 * and if threads exit, this will just be an over-estimate.
+	 */
+	group_size = get_nr_threads(leader);
+	/* flex_array supports very large thread-groups better than kmalloc. */
+	group = flex_array_alloc(sizeof(struct task_struct *), group_size,
+				 GFP_KERNEL);
+	if (!group)
+		return -ENOMEM;
+	/* pre-allocate to guarantee space while iterating in rcu read-side. */
+	retval = flex_array_prealloc(group, 0, group_size - 1, GFP_KERNEL);
+	if (retval)
+		goto out_free_group_list;
+
+	/* prevent changes to the threadgroup list while we take a snapshot. */
+	rcu_read_lock();
+	if (!thread_group_leader(leader)) {
+		/*
+		 * a race with de_thread from another thread's exec() may strip
+		 * us of our leadership, making while_each_thread unsafe to use
+		 * on this task. if this happens, there is no choice but to
+		 * throw this task away and try again (from cgroup_procs_write);
+		 * this is "double-double-toil-and-trouble-check locking".
+		 */
+		rcu_read_unlock();
+		retval = -EAGAIN;
+		goto out_free_group_list;
+	}
+	/* take a reference on each task in the group to go in the array. */
+	tsk = leader;
+	i = 0;
+	do {
+		/* as per above, nr_threads may decrease, but not increase. */
+		BUG_ON(i >= group_size);
+		get_task_struct(tsk);
+		/*
+		 * saying GFP_ATOMIC has no effect here because we did prealloc
+		 * earlier, but it's good form to communicate our expectations.
+		 */
+		retval = flex_array_put_ptr(group, i, tsk, GFP_ATOMIC);
+		BUG_ON(retval != 0);
+		i++;
+	} while_each_thread(leader, tsk);
+	/* remember the number of threads in the array for later. */
+	group_size = i;
+	rcu_read_unlock();
+
+	/*
+	 * step 1: check that we can legitimately attach to the cgroup.
+	 */
+	for_each_subsys(root, ss) {
+		if (ss->can_attach) {
+			retval = ss->can_attach(ss, cgrp, leader);
+			if (retval) {
+				failed_ss = ss;
+				goto out_cancel_attach;
+			}
+		}
+		/* a callback to be run on every thread in the threadgroup. */
+		if (ss->can_attach_task) {
+			/* run on each task in the threadgroup. */
+			for (i = 0; i < group_size; i++) {
+				tsk = flex_array_get_ptr(group, i);
+				retval = ss->can_attach_task(cgrp, tsk);
+				if (retval) {
+					failed_ss = ss;
+					cancel_failed_ss = true;
+					goto out_cancel_attach;
+				}
+			}
+		}
+	}
+
+	/*
+	 * step 2: make sure css_sets exist for all threads to be migrated.
+	 * we use find_css_set, which allocates a new one if necessary.
+	 */
+	INIT_LIST_HEAD(&newcg_list);
+	for (i = 0; i < group_size; i++) {
+		tsk = flex_array_get_ptr(group, i);
+		/* nothing to do if this task is already in the cgroup */
+		oldcgrp = task_cgroup_from_root(tsk, root);
+		if (cgrp == oldcgrp)
+			continue;
+		/* get old css_set pointer */
+		task_lock(tsk);
+		if (tsk->flags & PF_EXITING) {
+			/* ignore this task if it's going away */
+			task_unlock(tsk);
+			continue;
+		}
+		oldcg = tsk->cgroups;
+		get_css_set(oldcg);
+		task_unlock(tsk);
+		/* see if the new one for us is already in the list? */
+		if (css_set_check_fetched(cgrp, tsk, oldcg, &newcg_list)) {
+			/* was already there, nothing to do. */
+			put_css_set(oldcg);
+		} else {
+			/* we don't already have it. get new one. */
+			retval = css_set_prefetch(cgrp, oldcg, &newcg_list);
+			put_css_set(oldcg);
+			if (retval)
+				goto out_list_teardown;
+		}
+	}
+
+	/*
+	 * step 3: now that we're guaranteed success wrt the css_sets, proceed
+	 * to move all tasks to the new cgroup, calling ss->attach_task for each
+	 * one along the way. there are no failure cases after here, so this is
+	 * the commit point.
+	 */
+	for_each_subsys(root, ss) {
+		if (ss->pre_attach)
+			ss->pre_attach(cgrp);
+	}
+	for (i = 0; i < group_size; i++) {
+		tsk = flex_array_get_ptr(group, i);
+		/* leave current thread as it is if it's already there */
+		oldcgrp = task_cgroup_from_root(tsk, root);
+		if (cgrp == oldcgrp)
+			continue;
+		/* attach each task to each subsystem */
+		for_each_subsys(root, ss) {
+			if (ss->attach_task)
+				ss->attach_task(cgrp, tsk);
+		}
+		/* if the thread is PF_EXITING, it can just get skipped. */
+		retval = cgroup_task_migrate(cgrp, oldcgrp, tsk, true);
+		BUG_ON(retval != 0 && retval != -ESRCH);
+	}
+	/* nothing is sensitive to fork() after this point. */
+
+	/*
+	 * step 4: do expensive, non-thread-specific subsystem callbacks.
+	 * TODO: if ever a subsystem needs to know the oldcgrp for each task
+	 * being moved, this call will need to be reworked to communicate that.
+	 */
+	for_each_subsys(root, ss) {
+		if (ss->attach)
+			ss->attach(ss, cgrp, oldcgrp, leader);
+	}
+
+	/*
+	 * step 5: success! and cleanup
+	 */
+	synchronize_rcu();
+	cgroup_wakeup_rmdir_waiter(cgrp);
+	retval = 0;
+out_list_teardown:
+	/* clean up the list of prefetched css_sets. */
+	list_for_each_entry_safe(cg_entry, temp_nobe, &newcg_list, links) {
+		list_del(&cg_entry->links);
+		put_css_set(cg_entry->cg);
+		kfree(cg_entry);
+	}
+out_cancel_attach:
+	/* same deal as in cgroup_attach_task */
+	if (retval) {
+		for_each_subsys(root, ss) {
+			if (ss == failed_ss) {
+				if (cancel_failed_ss && ss->cancel_attach)
+					ss->cancel_attach(ss, cgrp, leader);
+				break;
+			}
+			if (ss->cancel_attach)
+				ss->cancel_attach(ss, cgrp, leader);
+		}
+	}
+	/* clean up the array of referenced threads in the group. */
+	for (i = 0; i < group_size; i++) {
+		tsk = flex_array_get_ptr(group, i);
+		put_task_struct(tsk);
+	}
+out_free_group_list:
+	flex_array_free(group);
+	return retval;
+}
+
+/*
+ * Find the task_struct of the task to attach by vpid and pass it along to the
+ * function to attach either it or all tasks in its threadgroup. Will take
+ * cgroup_mutex; may take task_lock of task.
  */
-static int attach_task_by_pid(struct cgroup *cgrp, u64 pid)
+static int attach_task_by_pid(struct cgroup *cgrp, u64 pid, bool threadgroup)
 {
 	struct task_struct *tsk;
 	const struct cred *cred = current_cred(), *tcred;
 	int ret;
 
+	if (!cgroup_lock_live_group(cgrp))
+		return -ENODEV;
+
 	if (pid) {
 		rcu_read_lock();
 		tsk = find_task_by_vpid(pid);
-		if (!tsk || tsk->flags & PF_EXITING) {
+		if (!tsk) {
 			rcu_read_unlock();
+			cgroup_unlock();
+			return -ESRCH;
+		}
+		if (threadgroup) {
+			/*
+			 * RCU protects this access, since tsk was found in the
+			 * tid map. a race with de_thread may cause group_leader
+			 * to stop being the leader, but cgroup_attach_proc will
+			 * detect it later.
+			 */
+			tsk = tsk->group_leader;
+		} else if (tsk->flags & PF_EXITING) {
+			/* optimization for the single-task-only case */
+			rcu_read_unlock();
+			cgroup_unlock();
 			return -ESRCH;
 		}
 
+		/*
+		 * even if we're attaching all tasks in the thread group, we
+		 * only need to check permissions on one of them.
+		 */
 		tcred = __task_cred(tsk);
 		if (cred->euid &&
 		    cred->euid != tcred->uid &&
 		    cred->euid != tcred->suid) {
 			rcu_read_unlock();
+			cgroup_unlock();
 			return -EACCES;
 		}
 		get_task_struct(tsk);
 		rcu_read_unlock();
 	} else {
-		tsk = current;
+		if (threadgroup)
+			tsk = current->group_leader;
+		else
+			tsk = current;
 		get_task_struct(tsk);
 	}
 
-	ret = cgroup_attach_task(cgrp, tsk);
+	if (threadgroup) {
+		threadgroup_fork_write_lock(tsk);
+		ret = cgroup_attach_proc(cgrp, tsk);
+		threadgroup_fork_write_unlock(tsk);
+	} else {
+		ret = cgroup_attach_task(cgrp, tsk);
+	}
 	put_task_struct(tsk);
+	cgroup_unlock();
 	return ret;
 }
 
 static int cgroup_tasks_write(struct cgroup *cgrp, struct cftype *cft, u64 pid)
 {
+	return attach_task_by_pid(cgrp, pid, false);
+}
+
+static int cgroup_procs_write(struct cgroup *cgrp, struct cftype *cft, u64 tgid)
+{
 	int ret;
-	if (!cgroup_lock_live_group(cgrp))
-		return -ENODEV;
-	ret = attach_task_by_pid(cgrp, pid);
-	cgroup_unlock();
+	do {
+		/*
+		 * attach_proc fails with -EAGAIN if threadgroup leadership
+		 * changes in the middle of the operation, in which case we need
+		 * to find the task_struct for the new leader and start over.
+		 */
+		ret = attach_task_by_pid(cgrp, tgid, true);
+	} while (ret == -EAGAIN);
 	return ret;
 }
 
@@ -3259,9 +3632,9 @@ static struct cftype files[] = {
 	{
 		.name = CGROUP_FILE_GENERIC_PREFIX "procs",
 		.open = cgroup_procs_open,
-		/* .write_u64 = cgroup_procs_write, TODO */
+		.write_u64 = cgroup_procs_write,
 		.release = cgroup_pidlist_release,
-		.mode = S_IRUGO,
+		.mode = S_IRUGO | S_IWUSR,
 	},
 	{
 		.name = "notify_on_release",
@@ -4257,122 +4630,6 @@ void cgroup_exit(struct task_struct *tsk, int run_callbacks)
 }
 
 /**
- * cgroup_clone - clone the cgroup the given subsystem is attached to
- * @tsk: the task to be moved
- * @subsys: the given subsystem
- * @nodename: the name for the new cgroup
- *
- * Duplicate the current cgroup in the hierarchy that the given
- * subsystem is attached to, and move this task into the new
- * child.
- */
-int cgroup_clone(struct task_struct *tsk, struct cgroup_subsys *subsys,
-							char *nodename)
-{
-	struct dentry *dentry;
-	int ret = 0;
-	struct cgroup *parent, *child;
-	struct inode *inode;
-	struct css_set *cg;
-	struct cgroupfs_root *root;
-	struct cgroup_subsys *ss;
-
-	/* We shouldn't be called by an unregistered subsystem */
-	BUG_ON(!subsys->active);
-
-	/* First figure out what hierarchy and cgroup we're dealing
-	 * with, and pin them so we can drop cgroup_mutex */
-	mutex_lock(&cgroup_mutex);
- again:
-	root = subsys->root;
-	if (root == &rootnode) {
-		mutex_unlock(&cgroup_mutex);
-		return 0;
-	}
-
-	/* Pin the hierarchy */
-	if (!atomic_inc_not_zero(&root->sb->s_active)) {
-		/* We race with the final deactivate_super() */
-		mutex_unlock(&cgroup_mutex);
-		return 0;
-	}
-
-	/* Keep the cgroup alive */
-	task_lock(tsk);
-	parent = task_cgroup(tsk, subsys->subsys_id);
-	cg = tsk->cgroups;
-	get_css_set(cg);
-	task_unlock(tsk);
-
-	mutex_unlock(&cgroup_mutex);
-
-	/* Now do the VFS work to create a cgroup */
-	inode = parent->dentry->d_inode;
-
-	/* Hold the parent directory mutex across this operation to
-	 * stop anyone else deleting the new cgroup */
-	mutex_lock(&inode->i_mutex);
-	dentry = lookup_one_len(nodename, parent->dentry, strlen(nodename));
-	if (IS_ERR(dentry)) {
-		printk(KERN_INFO
-		       "cgroup: Couldn't allocate dentry for %s: %ld\n", nodename,
-		       PTR_ERR(dentry));
-		ret = PTR_ERR(dentry);
-		goto out_release;
-	}
-
-	/* Create the cgroup directory, which also creates the cgroup */
-	ret = vfs_mkdir(inode, dentry, 0755);
-	child = __d_cgrp(dentry);
-	dput(dentry);
-	if (ret) {
-		printk(KERN_INFO
-		       "Failed to create cgroup %s: %d\n", nodename,
-		       ret);
-		goto out_release;
-	}
-
-	/* The cgroup now exists. Retake cgroup_mutex and check
-	 * that we're still in the same state that we thought we
-	 * were. */
-	mutex_lock(&cgroup_mutex);
-	if ((root != subsys->root) ||
-	    (parent != task_cgroup(tsk, subsys->subsys_id))) {
-		/* Aargh, we raced ... */
-		mutex_unlock(&inode->i_mutex);
-		put_css_set(cg);
-
-		deactivate_super(root->sb);
-		/* The cgroup is still accessible in the VFS, but
-		 * we're not going to try to rmdir() it at this
-		 * point. */
-		printk(KERN_INFO
-		       "Race in cgroup_clone() - leaking cgroup %s\n",
-		       nodename);
-		goto again;
-	}
-
-	/* do any required auto-setup */
-	for_each_subsys(root, ss) {
-		if (ss->post_clone)
-			ss->post_clone(ss, child);
-	}
-
-	/* All seems fine. Finish by moving the task into the new cgroup */
-	ret = cgroup_attach_task(child, tsk);
-	mutex_unlock(&cgroup_mutex);
-
- out_release:
-	mutex_unlock(&inode->i_mutex);
-
-	mutex_lock(&cgroup_mutex);
-	put_css_set(cg);
-	mutex_unlock(&cgroup_mutex);
-	deactivate_super(root->sb);
-	return ret;
-}
-
-/**
  * cgroup_is_descendant - see if @cgrp is a descendant of @task's cgrp
  * @cgrp: the cgroup in question
  * @task: the task in question
diff --git a/kernel/cgroup_freezer.c b/kernel/cgroup_freezer.c
index e7bebb7c6c38..e691818d7e45 100644
--- a/kernel/cgroup_freezer.c
+++ b/kernel/cgroup_freezer.c
@@ -160,7 +160,7 @@ static void freezer_destroy(struct cgroup_subsys *ss,
  */
 static int freezer_can_attach(struct cgroup_subsys *ss,
 			      struct cgroup *new_cgroup,
-			      struct task_struct *task, bool threadgroup)
+			      struct task_struct *task)
 {
 	struct freezer *freezer;
 
@@ -172,26 +172,17 @@ static int freezer_can_attach(struct cgroup_subsys *ss,
 	if (freezer->state != CGROUP_THAWED)
 		return -EBUSY;
 
+	return 0;
+}
+
+static int freezer_can_attach_task(struct cgroup *cgrp, struct task_struct *tsk)
+{
 	rcu_read_lock();
-	if (__cgroup_freezing_or_frozen(task)) {
+	if (__cgroup_freezing_or_frozen(tsk)) {
 		rcu_read_unlock();
 		return -EBUSY;
 	}
 	rcu_read_unlock();
-
-	if (threadgroup) {
-		struct task_struct *c;
-
-		rcu_read_lock();
-		list_for_each_entry_rcu(c, &task->thread_group, thread_group) {
-			if (__cgroup_freezing_or_frozen(c)) {
-				rcu_read_unlock();
-				return -EBUSY;
-			}
-		}
-		rcu_read_unlock();
-	}
-
 	return 0;
 }
 
@@ -390,6 +381,9 @@ struct cgroup_subsys freezer_subsys = {
 	.populate	= freezer_populate,
 	.subsys_id	= freezer_subsys_id,
 	.can_attach	= freezer_can_attach,
+	.can_attach_task = freezer_can_attach_task,
+	.pre_attach	= NULL,
+	.attach_task	= NULL,
 	.attach		= NULL,
 	.fork		= freezer_fork,
 	.exit		= NULL,
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 2bb8c2e98fff..9c9b7545c810 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -1367,14 +1367,10 @@ static int fmeter_getrate(struct fmeter *fmp)
 	return val;
 }
 
-/* Protected by cgroup_lock */
-static cpumask_var_t cpus_attach;
-
 /* Called by cgroups to determine if a cpuset is usable; cgroup_mutex held */
 static int cpuset_can_attach(struct cgroup_subsys *ss, struct cgroup *cont,
-			     struct task_struct *tsk, bool threadgroup)
+			     struct task_struct *tsk)
 {
-	int ret;
 	struct cpuset *cs = cgroup_cs(cont);
 
 	if (cpumask_empty(cs->cpus_allowed) || nodes_empty(cs->mems_allowed))
@@ -1391,29 +1387,42 @@ static int cpuset_can_attach(struct cgroup_subsys *ss, struct cgroup *cont,
 	if (tsk->flags & PF_THREAD_BOUND)
 		return -EINVAL;
 
-	ret = security_task_setscheduler(tsk);
-	if (ret)
-		return ret;
-	if (threadgroup) {
-		struct task_struct *c;
-
-		rcu_read_lock();
-		list_for_each_entry_rcu(c, &tsk->thread_group, thread_group) {
-			ret = security_task_setscheduler(c);
-			if (ret) {
-				rcu_read_unlock();
-				return ret;
-			}
-		}
-		rcu_read_unlock();
-	}
 	return 0;
 }
 
-static void cpuset_attach_task(struct task_struct *tsk, nodemask_t *to,
-			       struct cpuset *cs)
+static int cpuset_can_attach_task(struct cgroup *cgrp, struct task_struct *task)
+{
+	return security_task_setscheduler(task);
+}
+
+/*
+ * Protected by cgroup_lock. The nodemasks must be stored globally because
+ * dynamically allocating them is not allowed in pre_attach, and they must
+ * persist among pre_attach, attach_task, and attach.
+ */
+static cpumask_var_t cpus_attach;
+static nodemask_t cpuset_attach_nodemask_from;
+static nodemask_t cpuset_attach_nodemask_to;
+
+/* Set-up work for before attaching each task. */
+static void cpuset_pre_attach(struct cgroup *cont)
+{
+	struct cpuset *cs = cgroup_cs(cont);
+
+	if (cs == &top_cpuset)
+		cpumask_copy(cpus_attach, cpu_possible_mask);
+	else
+		guarantee_online_cpus(cs, cpus_attach);
+
+	guarantee_online_mems(cs, &cpuset_attach_nodemask_to);
+}
+
+/* Per-thread attachment work. */
+static void cpuset_attach_task(struct cgroup *cont, struct task_struct *tsk)
 {
 	int err;
+	struct cpuset *cs = cgroup_cs(cont);
+
 	/*
 	 * can_attach beforehand should guarantee that this doesn't fail.
 	 * TODO: have a better way to handle failure here
@@ -1421,45 +1430,29 @@ static void cpuset_attach_task(struct task_struct *tsk, nodemask_t *to,
 	err = set_cpus_allowed_ptr(tsk, cpus_attach);
 	WARN_ON_ONCE(err);
 
-	cpuset_change_task_nodemask(tsk, to);
+	cpuset_change_task_nodemask(tsk, &cpuset_attach_nodemask_to);
 	cpuset_update_task_spread_flag(cs, tsk);
-
 }
 
 static void cpuset_attach(struct cgroup_subsys *ss, struct cgroup *cont,
-			  struct cgroup *oldcont, struct task_struct *tsk,
-			  bool threadgroup)
+			  struct cgroup *oldcont, struct task_struct *tsk)
 {
 	struct mm_struct *mm;
 	struct cpuset *cs = cgroup_cs(cont);
 	struct cpuset *oldcs = cgroup_cs(oldcont);
-	static nodemask_t to;		/* protected by cgroup_mutex */
 
-	if (cs == &top_cpuset) {
-		cpumask_copy(cpus_attach, cpu_possible_mask);
-	} else {
-		guarantee_online_cpus(cs, cpus_attach);
-	}
-	guarantee_online_mems(cs, &to);
-
-	/* do per-task migration stuff possibly for each in the threadgroup */
-	cpuset_attach_task(tsk, &to, cs);
-	if (threadgroup) {
-		struct task_struct *c;
-		rcu_read_lock();
-		list_for_each_entry_rcu(c, &tsk->thread_group, thread_group) {
-			cpuset_attach_task(c, &to, cs);
-		}
-		rcu_read_unlock();
-	}
-
-	/* change mm; only needs to be done once even if threadgroup */
-	to = cs->mems_allowed;
+	/*
+	 * Change mm, possibly for multiple threads in a threadgroup. This is
+	 * expensive and may sleep.
+	 */
+	cpuset_attach_nodemask_from = oldcs->mems_allowed;
+	cpuset_attach_nodemask_to = cs->mems_allowed;
 	mm = get_task_mm(tsk);
 	if (mm) {
-		mpol_rebind_mm(mm, &to);
+		mpol_rebind_mm(mm, &cpuset_attach_nodemask_to);
 		if (is_memory_migrate(cs))
-			cpuset_migrate_mm(mm, &oldcs->mems_allowed, &to);
+			cpuset_migrate_mm(mm, &cpuset_attach_nodemask_from,
+					  &cpuset_attach_nodemask_to);
 		mmput(mm);
 	}
 }
@@ -1809,10 +1802,9 @@ static int cpuset_populate(struct cgroup_subsys *ss, struct cgroup *cont)
 }
 
 /*
- * post_clone() is called at the end of cgroup_clone().
- * 'cgroup' was just created automatically as a result of
- * a cgroup_clone(), and the current task is about to
- * be moved into 'cgroup'.
+ * post_clone() is called during cgroup_create() when the
+ * clone_children mount argument was specified.  The cgroup
+ * can not yet have any tasks.
  *
  * Currently we refuse to set up the cgroup - thereby
  * refusing the task to be entered, and as a result refusing
@@ -1911,6 +1903,9 @@ struct cgroup_subsys cpuset_subsys = {
 	.create = cpuset_create,
 	.destroy = cpuset_destroy,
 	.can_attach = cpuset_can_attach,
+	.can_attach_task = cpuset_can_attach_task,
+	.pre_attach = cpuset_pre_attach,
+	.attach_task = cpuset_attach_task,
 	.attach = cpuset_attach,
 	.populate = cpuset_populate,
 	.post_clone = cpuset_post_clone,
@@ -2195,7 +2190,7 @@ int cpuset_cpus_allowed_fallback(struct task_struct *tsk)
 	rcu_read_lock();
 	cs = task_cs(tsk);
 	if (cs)
-		cpumask_copy(&tsk->cpus_allowed, cs->cpus_allowed);
+		do_set_cpus_allowed(tsk, cs->cpus_allowed);
 	rcu_read_unlock();
 
 	/*
@@ -2222,7 +2217,7 @@ int cpuset_cpus_allowed_fallback(struct task_struct *tsk)
 		 * Like above we can temporary set any mask and rely on
 		 * set_cpus_allowed_ptr() as synchronization point.
 		 */
-		cpumask_copy(&tsk->cpus_allowed, cpu_possible_mask);
+		do_set_cpus_allowed(tsk, cpu_possible_mask);
 		cpu = cpumask_any(cpu_active_mask);
 	}
 
diff --git a/kernel/cred.c b/kernel/cred.c
index e12c8af793f8..174fa84eca30 100644
--- a/kernel/cred.c
+++ b/kernel/cred.c
@@ -1,4 +1,4 @@
-/* Task credentials management - see Documentation/credentials.txt
+/* Task credentials management - see Documentation/security/credentials.txt
  *
  * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved.
  * Written by David Howells (dhowells@redhat.com)
diff --git a/kernel/fork.c b/kernel/fork.c
index 8e7e135d0817..0276c30401a0 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -59,7 +59,6 @@
 #include <linux/taskstats_kern.h>
 #include <linux/random.h>
 #include <linux/tty.h>
-#include <linux/proc_fs.h>
 #include <linux/blkdev.h>
 #include <linux/fs_struct.h>
 #include <linux/magic.h>
@@ -485,20 +484,6 @@ static void mm_init_aio(struct mm_struct *mm)
 #endif
 }
 
-int mm_init_cpumask(struct mm_struct *mm, struct mm_struct *oldmm)
-{
-#ifdef CONFIG_CPUMASK_OFFSTACK
-	if (!alloc_cpumask_var(&mm->cpu_vm_mask_var, GFP_KERNEL))
-		return -ENOMEM;
-
-	if (oldmm)
-		cpumask_copy(mm_cpumask(mm), mm_cpumask(oldmm));
-	else
-		memset(mm_cpumask(mm), 0, cpumask_size());
-#endif
-	return 0;
-}
-
 static struct mm_struct * mm_init(struct mm_struct * mm, struct task_struct *p)
 {
 	atomic_set(&mm->mm_users, 1);
@@ -539,17 +524,8 @@ struct mm_struct * mm_alloc(void)
 		return NULL;
 
 	memset(mm, 0, sizeof(*mm));
-	mm = mm_init(mm, current);
-	if (!mm)
-		return NULL;
-
-	if (mm_init_cpumask(mm, NULL)) {
-		mm_free_pgd(mm);
-		free_mm(mm);
-		return NULL;
-	}
-
-	return mm;
+	mm_init_cpumask(mm);
+	return mm_init(mm, current);
 }
 
 /*
@@ -560,7 +536,6 @@ struct mm_struct * mm_alloc(void)
 void __mmdrop(struct mm_struct *mm)
 {
 	BUG_ON(mm == &init_mm);
-	free_cpumask_var(mm->cpu_vm_mask_var);
 	mm_free_pgd(mm);
 	destroy_context(mm);
 	mmu_notifier_mm_destroy(mm);
@@ -597,6 +572,57 @@ void mmput(struct mm_struct *mm)
 }
 EXPORT_SYMBOL_GPL(mmput);
 
+/*
+ * We added or removed a vma mapping the executable. The vmas are only mapped
+ * during exec and are not mapped with the mmap system call.
+ * Callers must hold down_write() on the mm's mmap_sem for these
+ */
+void added_exe_file_vma(struct mm_struct *mm)
+{
+	mm->num_exe_file_vmas++;
+}
+
+void removed_exe_file_vma(struct mm_struct *mm)
+{
+	mm->num_exe_file_vmas--;
+	if ((mm->num_exe_file_vmas == 0) && mm->exe_file){
+		fput(mm->exe_file);
+		mm->exe_file = NULL;
+	}
+
+}
+
+void set_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file)
+{
+	if (new_exe_file)
+		get_file(new_exe_file);
+	if (mm->exe_file)
+		fput(mm->exe_file);
+	mm->exe_file = new_exe_file;
+	mm->num_exe_file_vmas = 0;
+}
+
+struct file *get_mm_exe_file(struct mm_struct *mm)
+{
+	struct file *exe_file;
+
+	/* We need mmap_sem to protect against races with removal of
+	 * VM_EXECUTABLE vmas */
+	down_read(&mm->mmap_sem);
+	exe_file = mm->exe_file;
+	if (exe_file)
+		get_file(exe_file);
+	up_read(&mm->mmap_sem);
+	return exe_file;
+}
+
+static void dup_mm_exe_file(struct mm_struct *oldmm, struct mm_struct *newmm)
+{
+	/* It's safe to write the exe_file pointer without exe_file_lock because
+	 * this is called during fork when the task is not yet in /proc */
+	newmm->exe_file = get_mm_exe_file(oldmm);
+}
+
 /**
  * get_task_mm - acquire a reference to the task's mm
  *
@@ -703,6 +729,7 @@ struct mm_struct *dup_mm(struct task_struct *tsk)
 		goto fail_nomem;
 
 	memcpy(mm, oldmm, sizeof(*mm));
+	mm_init_cpumask(mm);
 
 	/* Initializing for Swap token stuff */
 	mm->token_priority = 0;
@@ -715,9 +742,6 @@ struct mm_struct *dup_mm(struct task_struct *tsk)
 	if (!mm_init(mm, tsk))
 		goto fail_nomem;
 
-	if (mm_init_cpumask(mm, oldmm))
-		goto fail_nocpumask;
-
 	if (init_new_context(tsk, mm))
 		goto fail_nocontext;
 
@@ -744,9 +768,6 @@ fail_nomem:
 	return NULL;
 
 fail_nocontext:
-	free_cpumask_var(mm->cpu_vm_mask_var);
-
-fail_nocpumask:
 	/*
 	 * If init_new_context() failed, we cannot use mmput() to free the mm
 	 * because it calls destroy_context()
@@ -957,6 +978,10 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
 	tty_audit_fork(sig);
 	sched_autogroup_fork(sig);
 
+#ifdef CONFIG_CGROUPS
+	init_rwsem(&sig->threadgroup_fork_lock);
+#endif
+
 	sig->oom_adj = current->signal->oom_adj;
 	sig->oom_score_adj = current->signal->oom_score_adj;
 	sig->oom_score_adj_min = current->signal->oom_score_adj_min;
@@ -1138,6 +1163,8 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	monotonic_to_bootbased(&p->real_start_time);
 	p->io_context = NULL;
 	p->audit_context = NULL;
+	if (clone_flags & CLONE_THREAD)
+		threadgroup_fork_read_lock(current);
 	cgroup_fork(p);
 #ifdef CONFIG_NUMA
 	p->mempolicy = mpol_dup(p->mempolicy);
@@ -1223,12 +1250,6 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	if (clone_flags & CLONE_THREAD)
 		p->tgid = current->tgid;
 
-	if (current->nsproxy != p->nsproxy) {
-		retval = ns_cgroup_clone(p, pid);
-		if (retval)
-			goto bad_fork_free_pid;
-	}
-
 	p->set_child_tid = (clone_flags & CLONE_CHILD_SETTID) ? child_tidptr : NULL;
 	/*
 	 * Clear TID on mm_release()?
@@ -1342,6 +1363,8 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	write_unlock_irq(&tasklist_lock);
 	proc_fork_connector(p);
 	cgroup_post_fork(p);
+	if (clone_flags & CLONE_THREAD)
+		threadgroup_fork_read_unlock(current);
 	perf_event_fork(p);
 	return p;
 
@@ -1380,6 +1403,8 @@ bad_fork_cleanup_policy:
 	mpol_put(p->mempolicy);
 bad_fork_cleanup_cgroup:
 #endif
+	if (clone_flags & CLONE_THREAD)
+		threadgroup_fork_read_unlock(current);
 	cgroup_exit(p, cgroup_callbacks_done);
 	delayacct_tsk_free(p);
 	module_put(task_thread_info(p)->exec_domain->module);
@@ -1537,6 +1562,13 @@ void __init proc_caches_init(void)
 	fs_cachep = kmem_cache_create("fs_cache",
 			sizeof(struct fs_struct), 0,
 			SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_NOTRACK, NULL);
+	/*
+	 * FIXME! The "sizeof(struct mm_struct)" currently includes the
+	 * whole struct cpumask for the OFFSTACK case. We could change
+	 * this to *only* allocate as much of it as required by the
+	 * maximum number of CPU's we can ever have.  The cpumask_allocation
+	 * is at the end of the structure, exactly for that reason.
+	 */
 	mm_cachep = kmem_cache_create("mm_struct",
 			sizeof(struct mm_struct), ARCH_MIN_MMSTRUCT_ALIGN,
 			SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_NOTRACK, NULL);
diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c
index 64e3df6ab1ef..4bd4faa6323a 100644
--- a/kernel/irq/proc.c
+++ b/kernel/irq/proc.c
@@ -352,6 +352,7 @@ void unregister_irq_proc(unsigned int irq, struct irq_desc *desc)
 #ifdef CONFIG_SMP
 	remove_proc_entry("smp_affinity", desc->dir);
 	remove_proc_entry("affinity_hint", desc->dir);
+	remove_proc_entry("smp_affinity_list", desc->dir);
 	remove_proc_entry("node", desc->dir);
 #endif
 	remove_proc_entry("spurious", desc->dir);
diff --git a/kernel/kthread.c b/kernel/kthread.c
index 3b34d2732bce..4ba7cccb4994 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -202,8 +202,8 @@ void kthread_bind(struct task_struct *p, unsigned int cpu)
 		return;
 	}
 
-	p->cpus_allowed = cpumask_of_cpu(cpu);
-	p->rt.nr_cpus_allowed = 1;
+	/* It's safe because the task is inactive. */
+	do_set_cpus_allowed(p, cpumask_of(cpu));
 	p->flags |= PF_THREAD_BOUND;
 }
 EXPORT_SYMBOL(kthread_bind);
diff --git a/kernel/ns_cgroup.c b/kernel/ns_cgroup.c
deleted file mode 100644
index 2c98ad94ba0e..000000000000
--- a/kernel/ns_cgroup.c
+++ /dev/null
@@ -1,118 +0,0 @@
-/*
- * ns_cgroup.c - namespace cgroup subsystem
- *
- * Copyright 2006, 2007 IBM Corp
- */
-
-#include <linux/module.h>
-#include <linux/cgroup.h>
-#include <linux/fs.h>
-#include <linux/proc_fs.h>
-#include <linux/slab.h>
-#include <linux/nsproxy.h>
-
-struct ns_cgroup {
-	struct cgroup_subsys_state css;
-};
-
-struct cgroup_subsys ns_subsys;
-
-static inline struct ns_cgroup *cgroup_to_ns(
-		struct cgroup *cgroup)
-{
-	return container_of(cgroup_subsys_state(cgroup, ns_subsys_id),
-			    struct ns_cgroup, css);
-}
-
-int ns_cgroup_clone(struct task_struct *task, struct pid *pid)
-{
-	char name[PROC_NUMBUF];
-
-	snprintf(name, PROC_NUMBUF, "%d", pid_vnr(pid));
-	return cgroup_clone(task, &ns_subsys, name);
-}
-
-/*
- * Rules:
- *   1. you can only enter a cgroup which is a descendant of your current
- *     cgroup
- *   2. you can only place another process into a cgroup if
- *     a. you have CAP_SYS_ADMIN
- *     b. your cgroup is an ancestor of task's destination cgroup
- *       (hence either you are in the same cgroup as task, or in an
- *        ancestor cgroup thereof)
- */
-static int ns_can_attach(struct cgroup_subsys *ss, struct cgroup *new_cgroup,
-			 struct task_struct *task, bool threadgroup)
-{
-	if (current != task) {
-		if (!capable(CAP_SYS_ADMIN))
-			return -EPERM;
-
-		if (!cgroup_is_descendant(new_cgroup, current))
-			return -EPERM;
-	}
-
-	if (!cgroup_is_descendant(new_cgroup, task))
-		return -EPERM;
-
-	if (threadgroup) {
-		struct task_struct *c;
-		rcu_read_lock();
-		list_for_each_entry_rcu(c, &task->thread_group, thread_group) {
-			if (!cgroup_is_descendant(new_cgroup, c)) {
-				rcu_read_unlock();
-				return -EPERM;
-			}
-		}
-		rcu_read_unlock();
-	}
-
-	return 0;
-}
-
-/*
- * Rules: you can only create a cgroup if
- *     1. you are capable(CAP_SYS_ADMIN)
- *     2. the target cgroup is a descendant of your own cgroup
- */
-static struct cgroup_subsys_state *ns_create(struct cgroup_subsys *ss,
-						struct cgroup *cgroup)
-{
-	struct ns_cgroup *ns_cgroup;
-
-	if (!capable(CAP_SYS_ADMIN))
-		return ERR_PTR(-EPERM);
-	if (!cgroup_is_descendant(cgroup, current))
-		return ERR_PTR(-EPERM);
-	if (test_bit(CGRP_CLONE_CHILDREN, &cgroup->flags)) {
-		printk("ns_cgroup can't be created with parent "
-		       "'clone_children' set.\n");
-		return ERR_PTR(-EINVAL);
-	}
-
-	printk_once("ns_cgroup deprecated: consider using the "
-		    "'clone_children' flag without the ns_cgroup.\n");
-
-	ns_cgroup = kzalloc(sizeof(*ns_cgroup), GFP_KERNEL);
-	if (!ns_cgroup)
-		return ERR_PTR(-ENOMEM);
-	return &ns_cgroup->css;
-}
-
-static void ns_destroy(struct cgroup_subsys *ss,
-			struct cgroup *cgroup)
-{
-	struct ns_cgroup *ns_cgroup;
-
-	ns_cgroup = cgroup_to_ns(cgroup);
-	kfree(ns_cgroup);
-}
-
-struct cgroup_subsys ns_subsys = {
-	.name = "ns",
-	.can_attach = ns_can_attach,
-	.create = ns_create,
-	.destroy  = ns_destroy,
-	.subsys_id = ns_subsys_id,
-};
diff --git a/kernel/nsproxy.c b/kernel/nsproxy.c
index 5424e37673ed..d6a00f3de15d 100644
--- a/kernel/nsproxy.c
+++ b/kernel/nsproxy.c
@@ -201,10 +201,6 @@ int unshare_nsproxy_namespaces(unsigned long unshare_flags,
 		goto out;
 	}
 
-	err = ns_cgroup_clone(current, task_pid(current));
-	if (err)
-		put_nsproxy(*new_nsp);
-
 out:
 	return err;
 }
diff --git a/kernel/pm_qos_params.c b/kernel/pm_qos_params.c
index beb184689af9..6824ca7d4d0c 100644
--- a/kernel/pm_qos_params.c
+++ b/kernel/pm_qos_params.c
@@ -40,6 +40,7 @@
 #include <linux/string.h>
 #include <linux/platform_device.h>
 #include <linux/init.h>
+#include <linux/kernel.h>
 
 #include <linux/uaccess.h>
 
@@ -53,11 +54,17 @@ enum pm_qos_type {
 	PM_QOS_MIN		/* return the smallest value */
 };
 
+/*
+ * Note: The lockless read path depends on the CPU accessing
+ * target_value atomically.  Atomic access is only guaranteed on all CPU
+ * types linux supports for 32 bit quantites
+ */
 struct pm_qos_object {
 	struct plist_head requests;
 	struct blocking_notifier_head *notifiers;
 	struct miscdevice pm_qos_power_miscdev;
 	char *name;
+	s32 target_value;	/* Do not change to 64 bit */
 	s32 default_value;
 	enum pm_qos_type type;
 };
@@ -70,7 +77,8 @@ static struct pm_qos_object cpu_dma_pm_qos = {
 	.requests = PLIST_HEAD_INIT(cpu_dma_pm_qos.requests, pm_qos_lock),
 	.notifiers = &cpu_dma_lat_notifier,
 	.name = "cpu_dma_latency",
-	.default_value = 2000 * USEC_PER_SEC,
+	.target_value = PM_QOS_CPU_DMA_LAT_DEFAULT_VALUE,
+	.default_value = PM_QOS_CPU_DMA_LAT_DEFAULT_VALUE,
 	.type = PM_QOS_MIN,
 };
 
@@ -79,7 +87,8 @@ static struct pm_qos_object network_lat_pm_qos = {
 	.requests = PLIST_HEAD_INIT(network_lat_pm_qos.requests, pm_qos_lock),
 	.notifiers = &network_lat_notifier,
 	.name = "network_latency",
-	.default_value = 2000 * USEC_PER_SEC,
+	.target_value = PM_QOS_NETWORK_LAT_DEFAULT_VALUE,
+	.default_value = PM_QOS_NETWORK_LAT_DEFAULT_VALUE,
 	.type = PM_QOS_MIN
 };
 
@@ -89,7 +98,8 @@ static struct pm_qos_object network_throughput_pm_qos = {
 	.requests = PLIST_HEAD_INIT(network_throughput_pm_qos.requests, pm_qos_lock),
 	.notifiers = &network_throughput_notifier,
 	.name = "network_throughput",
-	.default_value = 0,
+	.target_value = PM_QOS_NETWORK_THROUGHPUT_DEFAULT_VALUE,
+	.default_value = PM_QOS_NETWORK_THROUGHPUT_DEFAULT_VALUE,
 	.type = PM_QOS_MAX,
 };
 
@@ -135,6 +145,16 @@ static inline int pm_qos_get_value(struct pm_qos_object *o)
 	}
 }
 
+static inline s32 pm_qos_read_value(struct pm_qos_object *o)
+{
+	return o->target_value;
+}
+
+static inline void pm_qos_set_value(struct pm_qos_object *o, s32 value)
+{
+	o->target_value = value;
+}
+
 static void update_target(struct pm_qos_object *o, struct plist_node *node,
 			  int del, int value)
 {
@@ -159,6 +179,7 @@ static void update_target(struct pm_qos_object *o, struct plist_node *node,
 		plist_add(node, &o->requests);
 	}
 	curr_value = pm_qos_get_value(o);
+	pm_qos_set_value(o, curr_value);
 	spin_unlock_irqrestore(&pm_qos_lock, flags);
 
 	if (prev_value != curr_value)
@@ -193,18 +214,11 @@ static int find_pm_qos_object_by_minor(int minor)
  * pm_qos_request - returns current system wide qos expectation
  * @pm_qos_class: identification of which qos value is requested
  *
- * This function returns the current target value in an atomic manner.
+ * This function returns the current target value.
  */
 int pm_qos_request(int pm_qos_class)
 {
-	unsigned long flags;
-	int value;
-
-	spin_lock_irqsave(&pm_qos_lock, flags);
-	value = pm_qos_get_value(pm_qos_array[pm_qos_class]);
-	spin_unlock_irqrestore(&pm_qos_lock, flags);
-
-	return value;
+	return pm_qos_read_value(pm_qos_array[pm_qos_class]);
 }
 EXPORT_SYMBOL_GPL(pm_qos_request);
 
@@ -404,24 +418,36 @@ static ssize_t pm_qos_power_write(struct file *filp, const char __user *buf,
 		size_t count, loff_t *f_pos)
 {
 	s32 value;
-	int x;
-	char ascii_value[11];
 	struct pm_qos_request_list *pm_qos_req;
 
 	if (count == sizeof(s32)) {
 		if (copy_from_user(&value, buf, sizeof(s32)))
 			return -EFAULT;
-	} else if (count == 11) { /* len('0x12345678/0') */
-		if (copy_from_user(ascii_value, buf, 11))
+	} else if (count <= 11) { /* ASCII perhaps? */
+		char ascii_value[11];
+		unsigned long int ulval;
+		int ret;
+
+		if (copy_from_user(ascii_value, buf, count))
 			return -EFAULT;
-		if (strlen(ascii_value) != 10)
-			return -EINVAL;
-		x = sscanf(ascii_value, "%x", &value);
-		if (x != 1)
+
+		if (count > 10) {
+			if (ascii_value[10] == '\n')
+				ascii_value[10] = '\0';
+			else
+				return -EINVAL;
+		} else {
+			ascii_value[count] = '\0';
+		}
+		ret = strict_strtoul(ascii_value, 16, &ulval);
+		if (ret) {
+			pr_debug("%s, 0x%lx, 0x%x\n", ascii_value, ulval, ret);
 			return -EINVAL;
-		pr_debug("%s, %d, 0x%x\n", ascii_value, x, value);
-	} else
+		}
+		value = (s32)lower_32_bits(ulval);
+	} else {
 		return -EINVAL;
+	}
 
 	pm_qos_req = filp->private_data;
 	pm_qos_update_request(pm_qos_req, value);
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index f9bec56d8825..8f7b1db1ece1 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -25,7 +25,6 @@
 #include <linux/gfp.h>
 #include <linux/syscore_ops.h>
 #include <scsi/scsi_scan.h>
-#include <asm/suspend.h>
 
 #include "power.h"
 
@@ -55,10 +54,9 @@ static int hibernation_mode = HIBERNATION_SHUTDOWN;
 static const struct platform_hibernation_ops *hibernation_ops;
 
 /**
- * hibernation_set_ops - set the global hibernate operations
- * @ops: the hibernation operations to use in subsequent hibernation transitions
+ * hibernation_set_ops - Set the global hibernate operations.
+ * @ops: Hibernation operations to use in subsequent hibernation transitions.
  */
-
 void hibernation_set_ops(const struct platform_hibernation_ops *ops)
 {
 	if (ops && !(ops->begin && ops->end &&  ops->pre_snapshot
@@ -115,10 +113,9 @@ static int hibernation_test(int level) { return 0; }
 #endif /* !CONFIG_PM_DEBUG */
 
 /**
- *	platform_begin - tell the platform driver that we're starting
- *	hibernation
+ * platform_begin - Call platform to start hibernation.
+ * @platform_mode: Whether or not to use the platform driver.
  */
-
 static int platform_begin(int platform_mode)
 {
 	return (platform_mode && hibernation_ops) ?
@@ -126,10 +123,9 @@ static int platform_begin(int platform_mode)
 }
 
 /**
- *	platform_end - tell the platform driver that we've entered the
- *	working state
+ * platform_end - Call platform to finish transition to the working state.
+ * @platform_mode: Whether or not to use the platform driver.
  */
-
 static void platform_end(int platform_mode)
 {
 	if (platform_mode && hibernation_ops)
@@ -137,8 +133,11 @@ static void platform_end(int platform_mode)
 }
 
 /**
- *	platform_pre_snapshot - prepare the machine for hibernation using the
- *	platform driver if so configured and return an error code if it fails
+ * platform_pre_snapshot - Call platform to prepare the machine for hibernation.
+ * @platform_mode: Whether or not to use the platform driver.
+ *
+ * Use the platform driver to prepare the system for creating a hibernate image,
+ * if so configured, and return an error code if that fails.
  */
 
 static int platform_pre_snapshot(int platform_mode)
@@ -148,10 +147,14 @@ static int platform_pre_snapshot(int platform_mode)
 }
 
 /**
- *	platform_leave - prepare the machine for switching to the normal mode
- *	of operation using the platform driver (called with interrupts disabled)
+ * platform_leave - Call platform to prepare a transition to the working state.
+ * @platform_mode: Whether or not to use the platform driver.
+ *
+ * Use the platform driver prepare to prepare the machine for switching to the
+ * normal mode of operation.
+ *
+ * This routine is called on one CPU with interrupts disabled.
  */
-
 static void platform_leave(int platform_mode)
 {
 	if (platform_mode && hibernation_ops)
@@ -159,10 +162,14 @@ static void platform_leave(int platform_mode)
 }
 
 /**
- *	platform_finish - switch the machine to the normal mode of operation
- *	using the platform driver (must be called after platform_prepare())
+ * platform_finish - Call platform to switch the system to the working state.
+ * @platform_mode: Whether or not to use the platform driver.
+ *
+ * Use the platform driver to switch the machine to the normal mode of
+ * operation.
+ *
+ * This routine must be called after platform_prepare().
  */
-
 static void platform_finish(int platform_mode)
 {
 	if (platform_mode && hibernation_ops)
@@ -170,11 +177,15 @@ static void platform_finish(int platform_mode)
 }
 
 /**
- *	platform_pre_restore - prepare the platform for the restoration from a
- *	hibernation image.  If the restore fails after this function has been
- *	called, platform_restore_cleanup() must be called.
+ * platform_pre_restore - Prepare for hibernate image restoration.
+ * @platform_mode: Whether or not to use the platform driver.
+ *
+ * Use the platform driver to prepare the system for resume from a hibernation
+ * image.
+ *
+ * If the restore fails after this function has been called,
+ * platform_restore_cleanup() must be called.
  */
-
 static int platform_pre_restore(int platform_mode)
 {
 	return (platform_mode && hibernation_ops) ?
@@ -182,12 +193,16 @@ static int platform_pre_restore(int platform_mode)
 }
 
 /**
- *	platform_restore_cleanup - switch the platform to the normal mode of
- *	operation after a failing restore.  If platform_pre_restore() has been
- *	called before the failing restore, this function must be called too,
- *	regardless of the result of platform_pre_restore().
+ * platform_restore_cleanup - Switch to the working state after failing restore.
+ * @platform_mode: Whether or not to use the platform driver.
+ *
+ * Use the platform driver to switch the system to the normal mode of operation
+ * after a failing restore.
+ *
+ * If platform_pre_restore() has been called before the failing restore, this
+ * function must be called too, regardless of the result of
+ * platform_pre_restore().
  */
-
 static void platform_restore_cleanup(int platform_mode)
 {
 	if (platform_mode && hibernation_ops)
@@ -195,10 +210,9 @@ static void platform_restore_cleanup(int platform_mode)
 }
 
 /**
- *	platform_recover - recover the platform from a failure to suspend
- *	devices.
+ * platform_recover - Recover from a failure to suspend devices.
+ * @platform_mode: Whether or not to use the platform driver.
  */
-
 static void platform_recover(int platform_mode)
 {
 	if (platform_mode && hibernation_ops && hibernation_ops->recover)
@@ -206,13 +220,12 @@ static void platform_recover(int platform_mode)
 }
 
 /**
- *	swsusp_show_speed - print the time elapsed between two events.
- *	@start: Starting event.
- *	@stop: Final event.
- *	@nr_pages -	number of pages processed between @start and @stop
- *	@msg -		introductory message to print
+ * swsusp_show_speed - Print time elapsed between two events during hibernation.
+ * @start: Starting event.
+ * @stop: Final event.
+ * @nr_pages: Number of memory pages processed between @start and @stop.
+ * @msg: Additional diagnostic message to print.
  */
-
 void swsusp_show_speed(struct timeval *start, struct timeval *stop,
 			unsigned nr_pages, char *msg)
 {
@@ -235,25 +248,18 @@ void swsusp_show_speed(struct timeval *start, struct timeval *stop,
 }
 
 /**
- *	create_image - freeze devices that need to be frozen with interrupts
- *	off, create the hibernation image and thaw those devices.  Control
- *	reappears in this routine after a restore.
+ * create_image - Create a hibernation image.
+ * @platform_mode: Whether or not to use the platform driver.
+ *
+ * Execute device drivers' .freeze_noirq() callbacks, create a hibernation image
+ * and execute the drivers' .thaw_noirq() callbacks.
+ *
+ * Control reappears in this routine after the subsequent restore.
  */
-
 static int create_image(int platform_mode)
 {
 	int error;
 
-	error = arch_prepare_suspend();
-	if (error)
-		return error;
-
-	/* At this point, dpm_suspend_start() has been called, but *not*
-	 * dpm_suspend_noirq(). We *must* call dpm_suspend_noirq() now.
-	 * Otherwise, drivers for some devices (e.g. interrupt controllers)
-	 * become desynchronized with the actual state of the hardware
-	 * at resume time, and evil weirdness ensues.
-	 */
 	error = dpm_suspend_noirq(PMSG_FREEZE);
 	if (error) {
 		printk(KERN_ERR "PM: Some devices failed to power down, "
@@ -297,9 +303,6 @@ static int create_image(int platform_mode)
 
  Power_up:
 	syscore_resume();
-	/* NOTE:  dpm_resume_noirq() is just a resume() for devices
-	 * that suspended with irqs off ... no overall powerup.
-	 */
 
  Enable_irqs:
 	local_irq_enable();
@@ -317,14 +320,11 @@ static int create_image(int platform_mode)
 }
 
 /**
- *	hibernation_snapshot - quiesce devices and create the hibernation
- *	snapshot image.
- *	@platform_mode - if set, use the platform driver, if available, to
- *			 prepare the platform firmware for the power transition.
+ * hibernation_snapshot - Quiesce devices and create a hibernation image.
+ * @platform_mode: If set, use platform driver to prepare for the transition.
  *
- *	Must be called with pm_mutex held
+ * This routine must be called with pm_mutex held.
  */
-
 int hibernation_snapshot(int platform_mode)
 {
 	pm_message_t msg = PMSG_RECOVER;
@@ -384,13 +384,14 @@ int hibernation_snapshot(int platform_mode)
 }
 
 /**
- *	resume_target_kernel - prepare devices that need to be suspended with
- *	interrupts off, restore the contents of highmem that have not been
- *	restored yet from the image and run the low level code that will restore
- *	the remaining contents of memory and switch to the just restored target
- *	kernel.
+ * resume_target_kernel - Restore system state from a hibernation image.
+ * @platform_mode: Whether or not to use the platform driver.
+ *
+ * Execute device drivers' .freeze_noirq() callbacks, restore the contents of
+ * highmem that have not been restored yet from the image and run the low-level
+ * code that will restore the remaining contents of memory and switch to the
+ * just restored target kernel.
  */
-
 static int resume_target_kernel(bool platform_mode)
 {
 	int error;
@@ -416,24 +417,26 @@ static int resume_target_kernel(bool platform_mode)
 	if (error)
 		goto Enable_irqs;
 
-	/* We'll ignore saved state, but this gets preempt count (etc) right */
 	save_processor_state();
 	error = restore_highmem();
 	if (!error) {
 		error = swsusp_arch_resume();
 		/*
 		 * The code below is only ever reached in case of a failure.
-		 * Otherwise execution continues at place where
-		 * swsusp_arch_suspend() was called
+		 * Otherwise, execution continues at the place where
+		 * swsusp_arch_suspend() was called.
 		 */
 		BUG_ON(!error);
-		/* This call to restore_highmem() undos the previous one */
+		/*
+		 * This call to restore_highmem() reverts the changes made by
+		 * the previous one.
+		 */
 		restore_highmem();
 	}
 	/*
 	 * The only reason why swsusp_arch_resume() can fail is memory being
 	 * very tight, so we have to free it as soon as we can to avoid
-	 * subsequent failures
+	 * subsequent failures.
 	 */
 	swsusp_free();
 	restore_processor_state();
@@ -456,14 +459,12 @@ static int resume_target_kernel(bool platform_mode)
 }
 
 /**
- *	hibernation_restore - quiesce devices and restore the hibernation
- *	snapshot image.  If successful, control returns in hibernation_snaphot()
- *	@platform_mode - if set, use the platform driver, if available, to
- *			 prepare the platform firmware for the transition.
+ * hibernation_restore - Quiesce devices and restore from a hibernation image.
+ * @platform_mode: If set, use platform driver to prepare for the transition.
  *
- *	Must be called with pm_mutex held
+ * This routine must be called with pm_mutex held.  If it is successful, control
+ * reappears in the restored target kernel in hibernation_snaphot().
  */
-
 int hibernation_restore(int platform_mode)
 {
 	int error;
@@ -483,10 +484,8 @@ int hibernation_restore(int platform_mode)
 }
 
 /**
- *	hibernation_platform_enter - enter the hibernation state using the
- *	platform driver (if available)
+ * hibernation_platform_enter - Power off the system using the platform driver.
  */
-
 int hibernation_platform_enter(void)
 {
 	int error;
@@ -557,12 +556,12 @@ int hibernation_platform_enter(void)
 }
 
 /**
- *	power_down - Shut the machine down for hibernation.
+ * power_down - Shut the machine down for hibernation.
  *
- *	Use the platform driver, if configured so; otherwise try
- *	to power off or reboot.
+ * Use the platform driver, if configured, to put the system into the sleep
+ * state corresponding to hibernation, or try to power it off or reboot,
+ * depending on the value of hibernation_mode.
  */
-
 static void power_down(void)
 {
 	switch (hibernation_mode) {
@@ -599,9 +598,8 @@ static int prepare_processes(void)
 }
 
 /**
- *	hibernate - The granpappy of the built-in hibernation management
+ * hibernate - Carry out system hibernation, including saving the image.
  */
-
 int hibernate(void)
 {
 	int error;
@@ -679,17 +677,20 @@ int hibernate(void)
 
 
 /**
- *	software_resume - Resume from a saved image.
+ * software_resume - Resume from a saved hibernation image.
  *
- *	Called as a late_initcall (so all devices are discovered and
- *	initialized), we call swsusp to see if we have a saved image or not.
- *	If so, we quiesce devices, the restore the saved image. We will
- *	return above (in hibernate() ) if everything goes well.
- *	Otherwise, we fail gracefully and return to the normally
- *	scheduled program.
+ * This routine is called as a late initcall, when all devices have been
+ * discovered and initialized already.
  *
+ * The image reading code is called to see if there is a hibernation image
+ * available for reading.  If that is the case, devices are quiesced and the
+ * contents of memory is restored from the saved image.
+ *
+ * If this is successful, control reappears in the restored target kernel in
+ * hibernation_snaphot() which returns to hibernate().  Otherwise, the routine
+ * attempts to recover gracefully and make the kernel return to the normal mode
+ * of operation.
  */
-
 static int software_resume(void)
 {
 	int error;
@@ -819,21 +820,17 @@ static const char * const hibernation_modes[] = {
 	[HIBERNATION_TESTPROC]	= "testproc",
 };
 
-/**
- *	disk - Control hibernation mode
- *
- *	Suspend-to-disk can be handled in several ways. We have a few options
- *	for putting the system to sleep - using the platform driver (e.g. ACPI
- *	or other hibernation_ops), powering off the system or rebooting the
- *	system (for testing) as well as the two test modes.
+/*
+ * /sys/power/disk - Control hibernation mode.
  *
- *	The system can support 'platform', and that is known a priori (and
- *	encoded by the presence of hibernation_ops). However, the user may
- *	choose 'shutdown' or 'reboot' as alternatives, as well as one fo the
- *	test modes, 'test' or 'testproc'.
+ * Hibernation can be handled in several ways.  There are a few different ways
+ * to put the system into the sleep state: using the platform driver (e.g. ACPI
+ * or other hibernation_ops), powering it off or rebooting it (for testing
+ * mostly), or using one of the two available test modes.
  *
- *	show() will display what the mode is currently set to.
- *	store() will accept one of
+ * The sysfs file /sys/power/disk provides an interface for selecting the
+ * hibernation mode to use.  Reading from this file causes the available modes
+ * to be printed.  There are 5 modes that can be supported:
  *
  *	'platform'
  *	'shutdown'
@@ -841,8 +838,14 @@ static const char * const hibernation_modes[] = {
  *	'test'
  *	'testproc'
  *
- *	It will only change to 'platform' if the system
- *	supports it (as determined by having hibernation_ops).
+ * If a platform hibernation driver is in use, 'platform' will be supported
+ * and will be used by default.  Otherwise, 'shutdown' will be used by default.
+ * The selected option (i.e. the one corresponding to the current value of
+ * hibernation_mode) is enclosed by a square bracket.
+ *
+ * To select a given hibernation mode it is necessary to write the mode's
+ * string representation (as returned by reading from /sys/power/disk) back
+ * into /sys/power/disk.
  */
 
 static ssize_t disk_show(struct kobject *kobj, struct kobj_attribute *attr,
@@ -875,7 +878,6 @@ static ssize_t disk_show(struct kobject *kobj, struct kobj_attribute *attr,
 	return buf-start;
 }
 
-
 static ssize_t disk_store(struct kobject *kobj, struct kobj_attribute *attr,
 			  const char *buf, size_t n)
 {
diff --git a/kernel/profile.c b/kernel/profile.c
index 14c9f87b9fc9..961b389fe52f 100644
--- a/kernel/profile.c
+++ b/kernel/profile.c
@@ -303,14 +303,12 @@ static void profile_discard_flip_buffers(void)
 	mutex_unlock(&profile_flip_mutex);
 }
 
-void profile_hits(int type, void *__pc, unsigned int nr_hits)
+static void do_profile_hits(int type, void *__pc, unsigned int nr_hits)
 {
 	unsigned long primary, secondary, flags, pc = (unsigned long)__pc;
 	int i, j, cpu;
 	struct profile_hit *hits;
 
-	if (prof_on != type || !prof_buffer)
-		return;
 	pc = min((pc - (unsigned long)_stext) >> prof_shift, prof_len - 1);
 	i = primary = (pc & (NR_PROFILE_GRP - 1)) << PROFILE_GRPSHIFT;
 	secondary = (~(pc << 1) & (NR_PROFILE_GRP - 1)) << PROFILE_GRPSHIFT;
@@ -417,16 +415,20 @@ out_free:
 #define profile_discard_flip_buffers()	do { } while (0)
 #define profile_cpu_callback		NULL
 
-void profile_hits(int type, void *__pc, unsigned int nr_hits)
+static void do_profile_hits(int type, void *__pc, unsigned int nr_hits)
 {
 	unsigned long pc;
-
-	if (prof_on != type || !prof_buffer)
-		return;
 	pc = ((unsigned long)__pc - (unsigned long)_stext) >> prof_shift;
 	atomic_add(nr_hits, &prof_buffer[min(pc, prof_len - 1)]);
 }
 #endif /* !CONFIG_SMP */
+
+void profile_hits(int type, void *__pc, unsigned int nr_hits)
+{
+	if (prof_on != type || !prof_buffer)
+		return;
+	do_profile_hits(type, __pc, nr_hits);
+}
 EXPORT_SYMBOL_GPL(profile_hits);
 
 void profile_tick(int type)
diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index f07d2f03181a..77a7671dd147 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -36,7 +36,7 @@
 #include <linux/interrupt.h>
 #include <linux/sched.h>
 #include <linux/nmi.h>
-#include <asm/atomic.h>
+#include <linux/atomic.h>
 #include <linux/bitops.h>
 #include <linux/module.h>
 #include <linux/completion.h>
@@ -95,7 +95,6 @@ static DEFINE_PER_CPU(struct task_struct *, rcu_cpu_kthread_task);
 DEFINE_PER_CPU(unsigned int, rcu_cpu_kthread_status);
 DEFINE_PER_CPU(int, rcu_cpu_kthread_cpu);
 DEFINE_PER_CPU(unsigned int, rcu_cpu_kthread_loops);
-static DEFINE_PER_CPU(wait_queue_head_t, rcu_cpu_wq);
 DEFINE_PER_CPU(char, rcu_cpu_has_work);
 static char rcu_kthreads_spawnable;
 
@@ -163,7 +162,7 @@ EXPORT_SYMBOL_GPL(rcu_note_context_switch);
 #ifdef CONFIG_NO_HZ
 DEFINE_PER_CPU(struct rcu_dynticks, rcu_dynticks) = {
 	.dynticks_nesting = 1,
-	.dynticks = 1,
+	.dynticks = ATOMIC_INIT(1),
 };
 #endif /* #ifdef CONFIG_NO_HZ */
 
@@ -322,13 +321,25 @@ void rcu_enter_nohz(void)
 	unsigned long flags;
 	struct rcu_dynticks *rdtp;
 
-	smp_mb(); /* CPUs seeing ++ must see prior RCU read-side crit sects */
 	local_irq_save(flags);
 	rdtp = &__get_cpu_var(rcu_dynticks);
-	rdtp->dynticks++;
-	rdtp->dynticks_nesting--;
-	WARN_ON_ONCE(rdtp->dynticks & 0x1);
+	if (--rdtp->dynticks_nesting) {
+		local_irq_restore(flags);
+		return;
+	}
+	/* CPUs seeing atomic_inc() must see prior RCU read-side crit sects */
+	smp_mb__before_atomic_inc();  /* See above. */
+	atomic_inc(&rdtp->dynticks);
+	smp_mb__after_atomic_inc();  /* Force ordering with next sojourn. */
+	WARN_ON_ONCE(atomic_read(&rdtp->dynticks) & 0x1);
 	local_irq_restore(flags);
+
+	/* If the interrupt queued a callback, get out of dyntick mode. */
+	if (in_irq() &&
+	    (__get_cpu_var(rcu_sched_data).nxtlist ||
+	     __get_cpu_var(rcu_bh_data).nxtlist ||
+	     rcu_preempt_needs_cpu(smp_processor_id())))
+		set_need_resched();
 }
 
 /*
@@ -344,11 +355,16 @@ void rcu_exit_nohz(void)
 
 	local_irq_save(flags);
 	rdtp = &__get_cpu_var(rcu_dynticks);
-	rdtp->dynticks++;
-	rdtp->dynticks_nesting++;
-	WARN_ON_ONCE(!(rdtp->dynticks & 0x1));
+	if (rdtp->dynticks_nesting++) {
+		local_irq_restore(flags);
+		return;
+	}
+	smp_mb__before_atomic_inc();  /* Force ordering w/previous sojourn. */
+	atomic_inc(&rdtp->dynticks);
+	/* CPUs seeing atomic_inc() must see later RCU read-side crit sects */
+	smp_mb__after_atomic_inc();  /* See above. */
+	WARN_ON_ONCE(!(atomic_read(&rdtp->dynticks) & 0x1));
 	local_irq_restore(flags);
-	smp_mb(); /* CPUs seeing ++ must see later RCU read-side crit sects */
 }
 
 /**
@@ -362,11 +378,15 @@ void rcu_nmi_enter(void)
 {
 	struct rcu_dynticks *rdtp = &__get_cpu_var(rcu_dynticks);
 
-	if (rdtp->dynticks & 0x1)
+	if (rdtp->dynticks_nmi_nesting == 0 &&
+	    (atomic_read(&rdtp->dynticks) & 0x1))
 		return;
-	rdtp->dynticks_nmi++;
-	WARN_ON_ONCE(!(rdtp->dynticks_nmi & 0x1));
-	smp_mb(); /* CPUs seeing ++ must see later RCU read-side crit sects */
+	rdtp->dynticks_nmi_nesting++;
+	smp_mb__before_atomic_inc();  /* Force delay from prior write. */
+	atomic_inc(&rdtp->dynticks);
+	/* CPUs seeing atomic_inc() must see later RCU read-side crit sects */
+	smp_mb__after_atomic_inc();  /* See above. */
+	WARN_ON_ONCE(!(atomic_read(&rdtp->dynticks) & 0x1));
 }
 
 /**
@@ -380,11 +400,14 @@ void rcu_nmi_exit(void)
 {
 	struct rcu_dynticks *rdtp = &__get_cpu_var(rcu_dynticks);
 
-	if (rdtp->dynticks & 0x1)
+	if (rdtp->dynticks_nmi_nesting == 0 ||
+	    --rdtp->dynticks_nmi_nesting != 0)
 		return;
-	smp_mb(); /* CPUs seeing ++ must see prior RCU read-side crit sects */
-	rdtp->dynticks_nmi++;
-	WARN_ON_ONCE(rdtp->dynticks_nmi & 0x1);
+	/* CPUs seeing atomic_inc() must see prior RCU read-side crit sects */
+	smp_mb__before_atomic_inc();  /* See above. */
+	atomic_inc(&rdtp->dynticks);
+	smp_mb__after_atomic_inc();  /* Force delay to next write. */
+	WARN_ON_ONCE(atomic_read(&rdtp->dynticks) & 0x1);
 }
 
 /**
@@ -395,13 +418,7 @@ void rcu_nmi_exit(void)
  */
 void rcu_irq_enter(void)
 {
-	struct rcu_dynticks *rdtp = &__get_cpu_var(rcu_dynticks);
-
-	if (rdtp->dynticks_nesting++)
-		return;
-	rdtp->dynticks++;
-	WARN_ON_ONCE(!(rdtp->dynticks & 0x1));
-	smp_mb(); /* CPUs seeing ++ must see later RCU read-side crit sects */
+	rcu_exit_nohz();
 }
 
 /**
@@ -413,18 +430,7 @@ void rcu_irq_enter(void)
  */
 void rcu_irq_exit(void)
 {
-	struct rcu_dynticks *rdtp = &__get_cpu_var(rcu_dynticks);
-
-	if (--rdtp->dynticks_nesting)
-		return;
-	smp_mb(); /* CPUs seeing ++ must see prior RCU read-side crit sects */
-	rdtp->dynticks++;
-	WARN_ON_ONCE(rdtp->dynticks & 0x1);
-
-	/* If the interrupt queued a callback, get out of dyntick mode. */
-	if (__this_cpu_read(rcu_sched_data.nxtlist) ||
-	    __this_cpu_read(rcu_bh_data.nxtlist))
-		set_need_resched();
+	rcu_enter_nohz();
 }
 
 #ifdef CONFIG_SMP
@@ -436,19 +442,8 @@ void rcu_irq_exit(void)
  */
 static int dyntick_save_progress_counter(struct rcu_data *rdp)
 {
-	int ret;
-	int snap;
-	int snap_nmi;
-
-	snap = rdp->dynticks->dynticks;
-	snap_nmi = rdp->dynticks->dynticks_nmi;
-	smp_mb();	/* Order sampling of snap with end of grace period. */
-	rdp->dynticks_snap = snap;
-	rdp->dynticks_nmi_snap = snap_nmi;
-	ret = ((snap & 0x1) == 0) && ((snap_nmi & 0x1) == 0);
-	if (ret)
-		rdp->dynticks_fqs++;
-	return ret;
+	rdp->dynticks_snap = atomic_add_return(0, &rdp->dynticks->dynticks);
+	return 0;
 }
 
 /*
@@ -459,16 +454,11 @@ static int dyntick_save_progress_counter(struct rcu_data *rdp)
  */
 static int rcu_implicit_dynticks_qs(struct rcu_data *rdp)
 {
-	long curr;
-	long curr_nmi;
-	long snap;
-	long snap_nmi;
+	unsigned long curr;
+	unsigned long snap;
 
-	curr = rdp->dynticks->dynticks;
-	snap = rdp->dynticks_snap;
-	curr_nmi = rdp->dynticks->dynticks_nmi;
-	snap_nmi = rdp->dynticks_nmi_snap;
-	smp_mb(); /* force ordering with cpu entering/leaving dynticks. */
+	curr = (unsigned long)atomic_add_return(0, &rdp->dynticks->dynticks);
+	snap = (unsigned long)rdp->dynticks_snap;
 
 	/*
 	 * If the CPU passed through or entered a dynticks idle phase with
@@ -478,8 +468,7 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp)
 	 * read-side critical section that started before the beginning
 	 * of the current RCU grace period.
 	 */
-	if ((curr != snap || (curr & 0x1) == 0) &&
-	    (curr_nmi != snap_nmi || (curr_nmi & 0x1) == 0)) {
+	if ((curr & 0x1) == 0 || ULONG_CMP_GE(curr, snap + 2)) {
 		rdp->dynticks_fqs++;
 		return 1;
 	}
@@ -908,6 +897,12 @@ static void rcu_report_qs_rsp(struct rcu_state *rsp, unsigned long flags)
 	unsigned long gp_duration;
 
 	WARN_ON_ONCE(!rcu_gp_in_progress(rsp));
+
+	/*
+	 * Ensure that all grace-period and pre-grace-period activity
+	 * is seen before the assignment to rsp->completed.
+	 */
+	smp_mb(); /* See above block comment. */
 	gp_duration = jiffies - rsp->gp_start;
 	if (gp_duration > rsp->gp_max)
 		rsp->gp_max = gp_duration;
@@ -1455,25 +1450,11 @@ __rcu_process_callbacks(struct rcu_state *rsp, struct rcu_data *rdp)
  */
 static void rcu_process_callbacks(void)
 {
-	/*
-	 * Memory references from any prior RCU read-side critical sections
-	 * executed by the interrupted code must be seen before any RCU
-	 * grace-period manipulations below.
-	 */
-	smp_mb(); /* See above block comment. */
-
 	__rcu_process_callbacks(&rcu_sched_state,
 				&__get_cpu_var(rcu_sched_data));
 	__rcu_process_callbacks(&rcu_bh_state, &__get_cpu_var(rcu_bh_data));
 	rcu_preempt_process_callbacks();
 
-	/*
-	 * Memory references from any later RCU read-side critical sections
-	 * executed by the interrupted code must be seen after any RCU
-	 * grace-period manipulations above.
-	 */
-	smp_mb(); /* See above block comment. */
-
 	/* If we are last CPU on way to dyntick-idle mode, accelerate it. */
 	rcu_needs_cpu_flush();
 }
@@ -1494,7 +1475,7 @@ static void invoke_rcu_cpu_kthread(void)
 		local_irq_restore(flags);
 		return;
 	}
-	wake_up(&__get_cpu_var(rcu_cpu_wq));
+	wake_up_process(__this_cpu_read(rcu_cpu_kthread_task));
 	local_irq_restore(flags);
 }
 
@@ -1544,13 +1525,10 @@ static void rcu_cpu_kthread_setrt(int cpu, int to_rt)
  */
 static void rcu_cpu_kthread_timer(unsigned long arg)
 {
-	unsigned long flags;
 	struct rcu_data *rdp = per_cpu_ptr(rcu_state->rda, arg);
 	struct rcu_node *rnp = rdp->mynode;
 
-	raw_spin_lock_irqsave(&rnp->lock, flags);
-	rnp->wakemask |= rdp->grpmask;
-	raw_spin_unlock_irqrestore(&rnp->lock, flags);
+	atomic_or(rdp->grpmask, &rnp->wakemask);
 	invoke_rcu_node_kthread(rnp);
 }
 
@@ -1617,14 +1595,12 @@ static int rcu_cpu_kthread(void *arg)
 	unsigned long flags;
 	int spincnt = 0;
 	unsigned int *statusp = &per_cpu(rcu_cpu_kthread_status, cpu);
-	wait_queue_head_t *wqp = &per_cpu(rcu_cpu_wq, cpu);
 	char work;
 	char *workp = &per_cpu(rcu_cpu_has_work, cpu);
 
 	for (;;) {
 		*statusp = RCU_KTHREAD_WAITING;
-		wait_event_interruptible(*wqp,
-					 *workp != 0 || kthread_should_stop());
+		rcu_wait(*workp != 0 || kthread_should_stop());
 		local_bh_disable();
 		if (rcu_cpu_kthread_should_stop(cpu)) {
 			local_bh_enable();
@@ -1672,10 +1648,10 @@ static int __cpuinit rcu_spawn_one_cpu_kthread(int cpu)
 	if (IS_ERR(t))
 		return PTR_ERR(t);
 	kthread_bind(t, cpu);
+	set_task_state(t, TASK_INTERRUPTIBLE);
 	per_cpu(rcu_cpu_kthread_cpu, cpu) = cpu;
 	WARN_ON_ONCE(per_cpu(rcu_cpu_kthread_task, cpu) != NULL);
 	per_cpu(rcu_cpu_kthread_task, cpu) = t;
-	wake_up_process(t);
 	sp.sched_priority = RCU_KTHREAD_PRIO;
 	sched_setscheduler_nocheck(t, SCHED_FIFO, &sp);
 	return 0;
@@ -1698,11 +1674,10 @@ static int rcu_node_kthread(void *arg)
 
 	for (;;) {
 		rnp->node_kthread_status = RCU_KTHREAD_WAITING;
-		wait_event_interruptible(rnp->node_wq, rnp->wakemask != 0);
+		rcu_wait(atomic_read(&rnp->wakemask) != 0);
 		rnp->node_kthread_status = RCU_KTHREAD_RUNNING;
 		raw_spin_lock_irqsave(&rnp->lock, flags);
-		mask = rnp->wakemask;
-		rnp->wakemask = 0;
+		mask = atomic_xchg(&rnp->wakemask, 0);
 		rcu_initiate_boost(rnp, flags); /* releases rnp->lock. */
 		for (cpu = rnp->grplo; cpu <= rnp->grphi; cpu++, mask >>= 1) {
 			if ((mask & 0x1) == 0)
@@ -1781,9 +1756,9 @@ static int __cpuinit rcu_spawn_one_node_kthread(struct rcu_state *rsp,
 		if (IS_ERR(t))
 			return PTR_ERR(t);
 		raw_spin_lock_irqsave(&rnp->lock, flags);
+		set_task_state(t, TASK_INTERRUPTIBLE);
 		rnp->node_kthread_task = t;
 		raw_spin_unlock_irqrestore(&rnp->lock, flags);
-		wake_up_process(t);
 		sp.sched_priority = 99;
 		sched_setscheduler_nocheck(t, SCHED_FIFO, &sp);
 	}
@@ -1800,21 +1775,16 @@ static int __init rcu_spawn_kthreads(void)
 
 	rcu_kthreads_spawnable = 1;
 	for_each_possible_cpu(cpu) {
-		init_waitqueue_head(&per_cpu(rcu_cpu_wq, cpu));
 		per_cpu(rcu_cpu_has_work, cpu) = 0;
 		if (cpu_online(cpu))
 			(void)rcu_spawn_one_cpu_kthread(cpu);
 	}
 	rnp = rcu_get_root(rcu_state);
-	init_waitqueue_head(&rnp->node_wq);
-	rcu_init_boost_waitqueue(rnp);
 	(void)rcu_spawn_one_node_kthread(rcu_state, rnp);
-	if (NUM_RCU_NODES > 1)
-		rcu_for_each_leaf_node(rcu_state, rnp) {
-			init_waitqueue_head(&rnp->node_wq);
-			rcu_init_boost_waitqueue(rnp);
+	if (NUM_RCU_NODES > 1) {
+		rcu_for_each_leaf_node(rcu_state, rnp)
 			(void)rcu_spawn_one_node_kthread(rcu_state, rnp);
-		}
+	}
 	return 0;
 }
 early_initcall(rcu_spawn_kthreads);
diff --git a/kernel/rcutree.h b/kernel/rcutree.h
index 257664815d5d..7b9a08b4aaea 100644
--- a/kernel/rcutree.h
+++ b/kernel/rcutree.h
@@ -84,11 +84,9 @@
  * Dynticks per-CPU state.
  */
 struct rcu_dynticks {
-	int dynticks_nesting;	/* Track nesting level, sort of. */
-	int dynticks;		/* Even value for dynticks-idle, else odd. */
-	int dynticks_nmi;	/* Even value for either dynticks-idle or */
-				/*  not in nmi handler, else odd.  So this */
-				/*  remains even for nmi from irq handler. */
+	int dynticks_nesting;	/* Track irq/process nesting level. */
+	int dynticks_nmi_nesting; /* Track NMI nesting level. */
+	atomic_t dynticks;	/* Even value for dynticks-idle, else odd. */
 };
 
 /* RCU's kthread states for tracing. */
@@ -121,7 +119,9 @@ struct rcu_node {
 				/*  elements that need to drain to allow the */
 				/*  current expedited grace period to */
 				/*  complete (only for TREE_PREEMPT_RCU). */
-	unsigned long wakemask; /* CPUs whose kthread needs to be awakened. */
+	atomic_t wakemask;	/* CPUs whose kthread needs to be awakened. */
+				/*  Since this has meaning only for leaf */
+				/*  rcu_node structures, 32 bits suffices. */
 	unsigned long qsmaskinit;
 				/* Per-GP initial value for qsmask & expmask. */
 	unsigned long grpmask;	/* Mask to apply to parent qsmask. */
@@ -159,9 +159,6 @@ struct rcu_node {
 	struct task_struct *boost_kthread_task;
 				/* kthread that takes care of priority */
 				/*  boosting for this rcu_node structure. */
-	wait_queue_head_t boost_wq;
-				/* Wait queue on which to park the boost */
-				/*  kthread. */
 	unsigned int boost_kthread_status;
 				/* State of boost_kthread_task for tracing. */
 	unsigned long n_tasks_boosted;
@@ -188,9 +185,6 @@ struct rcu_node {
 				/* kthread that takes care of this rcu_node */
 				/*  structure, for example, awakening the */
 				/*  per-CPU kthreads as needed. */
-	wait_queue_head_t node_wq;
-				/* Wait queue on which to park the per-node */
-				/*  kthread. */
 	unsigned int node_kthread_status;
 				/* State of node_kthread_task for tracing. */
 } ____cacheline_internodealigned_in_smp;
@@ -284,7 +278,6 @@ struct rcu_data {
 	/* 3) dynticks interface. */
 	struct rcu_dynticks *dynticks;	/* Shared per-CPU dynticks state. */
 	int dynticks_snap;		/* Per-GP tracking for dynticks. */
-	int dynticks_nmi_snap;		/* Per-GP tracking for dynticks_nmi. */
 #endif /* #ifdef CONFIG_NO_HZ */
 
 	/* 4) reasons this CPU needed to be kicked by force_quiescent_state */
@@ -337,6 +330,16 @@ struct rcu_data {
 						/*  scheduling clock irq */
 						/*  before ratting on them. */
 
+#define rcu_wait(cond)							\
+do {									\
+	for (;;) {							\
+		set_current_state(TASK_INTERRUPTIBLE);			\
+		if (cond)						\
+			break;						\
+		schedule();						\
+	}								\
+	__set_current_state(TASK_RUNNING);				\
+} while (0)
 
 /*
  * RCU global state, including node hierarchy.  This hierarchy is
@@ -446,7 +449,6 @@ static void __cpuinit rcu_preempt_init_percpu_data(int cpu);
 static void rcu_preempt_send_cbs_to_online(void);
 static void __init __rcu_init_preempt(void);
 static void rcu_needs_cpu_flush(void);
-static void __init rcu_init_boost_waitqueue(struct rcu_node *rnp);
 static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags);
 static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp,
 					  cpumask_var_t cm);
diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h
index 3f6559a5f5cd..a767b7dac365 100644
--- a/kernel/rcutree_plugin.h
+++ b/kernel/rcutree_plugin.h
@@ -1196,8 +1196,7 @@ static int rcu_boost_kthread(void *arg)
 
 	for (;;) {
 		rnp->boost_kthread_status = RCU_KTHREAD_WAITING;
-		wait_event_interruptible(rnp->boost_wq, rnp->boost_tasks ||
-							rnp->exp_tasks);
+		rcu_wait(rnp->boost_tasks || rnp->exp_tasks);
 		rnp->boost_kthread_status = RCU_KTHREAD_RUNNING;
 		more2boost = rcu_boost(rnp);
 		if (more2boost)
@@ -1275,14 +1274,6 @@ static void rcu_preempt_boost_start_gp(struct rcu_node *rnp)
 }
 
 /*
- * Initialize the RCU-boost waitqueue.
- */
-static void __init rcu_init_boost_waitqueue(struct rcu_node *rnp)
-{
-	init_waitqueue_head(&rnp->boost_wq);
-}
-
-/*
  * Create an RCU-boost kthread for the specified node if one does not
  * already exist.  We only create this kthread for preemptible RCU.
  * Returns zero if all is well, a negated errno otherwise.
@@ -1304,9 +1295,9 @@ static int __cpuinit rcu_spawn_one_boost_kthread(struct rcu_state *rsp,
 	if (IS_ERR(t))
 		return PTR_ERR(t);
 	raw_spin_lock_irqsave(&rnp->lock, flags);
+	set_task_state(t, TASK_INTERRUPTIBLE);
 	rnp->boost_kthread_task = t;
 	raw_spin_unlock_irqrestore(&rnp->lock, flags);
-	wake_up_process(t);
 	sp.sched_priority = RCU_KTHREAD_PRIO;
 	sched_setscheduler_nocheck(t, SCHED_FIFO, &sp);
 	return 0;
@@ -1328,10 +1319,6 @@ static void rcu_preempt_boost_start_gp(struct rcu_node *rnp)
 {
 }
 
-static void __init rcu_init_boost_waitqueue(struct rcu_node *rnp)
-{
-}
-
 static int __cpuinit rcu_spawn_one_boost_kthread(struct rcu_state *rsp,
 						 struct rcu_node *rnp,
 						 int rnp_index)
@@ -1520,7 +1507,6 @@ int rcu_needs_cpu(int cpu)
 {
 	int c = 0;
 	int snap;
-	int snap_nmi;
 	int thatcpu;
 
 	/* Check for being in the holdoff period. */
@@ -1531,10 +1517,10 @@ int rcu_needs_cpu(int cpu)
 	for_each_online_cpu(thatcpu) {
 		if (thatcpu == cpu)
 			continue;
-		snap = per_cpu(rcu_dynticks, thatcpu).dynticks;
-		snap_nmi = per_cpu(rcu_dynticks, thatcpu).dynticks_nmi;
+		snap = atomic_add_return(0, &per_cpu(rcu_dynticks,
+						     thatcpu).dynticks);
 		smp_mb(); /* Order sampling of snap with end of grace period. */
-		if (((snap & 0x1) != 0) || ((snap_nmi & 0x1) != 0)) {
+		if ((snap & 0x1) != 0) {
 			per_cpu(rcu_dyntick_drain, cpu) = 0;
 			per_cpu(rcu_dyntick_holdoff, cpu) = jiffies - 1;
 			return rcu_needs_cpu_quick_check(cpu);
diff --git a/kernel/rcutree_trace.c b/kernel/rcutree_trace.c
index aa0fd72b4bc7..9678cc3650f5 100644
--- a/kernel/rcutree_trace.c
+++ b/kernel/rcutree_trace.c
@@ -69,10 +69,10 @@ static void print_one_rcu_data(struct seq_file *m, struct rcu_data *rdp)
 		   rdp->passed_quiesc, rdp->passed_quiesc_completed,
 		   rdp->qs_pending);
 #ifdef CONFIG_NO_HZ
-	seq_printf(m, " dt=%d/%d dn=%d df=%lu",
-		   rdp->dynticks->dynticks,
+	seq_printf(m, " dt=%d/%d/%d df=%lu",
+		   atomic_read(&rdp->dynticks->dynticks),
 		   rdp->dynticks->dynticks_nesting,
-		   rdp->dynticks->dynticks_nmi,
+		   rdp->dynticks->dynticks_nmi_nesting,
 		   rdp->dynticks_fqs);
 #endif /* #ifdef CONFIG_NO_HZ */
 	seq_printf(m, " of=%lu ri=%lu", rdp->offline_fqs, rdp->resched_ipi);
@@ -141,9 +141,9 @@ static void print_one_rcu_data_csv(struct seq_file *m, struct rcu_data *rdp)
 		   rdp->qs_pending);
 #ifdef CONFIG_NO_HZ
 	seq_printf(m, ",%d,%d,%d,%lu",
-		   rdp->dynticks->dynticks,
+		   atomic_read(&rdp->dynticks->dynticks),
 		   rdp->dynticks->dynticks_nesting,
-		   rdp->dynticks->dynticks_nmi,
+		   rdp->dynticks->dynticks_nmi_nesting,
 		   rdp->dynticks_fqs);
 #endif /* #ifdef CONFIG_NO_HZ */
 	seq_printf(m, ",%lu,%lu", rdp->offline_fqs, rdp->resched_ipi);
@@ -167,7 +167,7 @@ static int show_rcudata_csv(struct seq_file *m, void *unused)
 {
 	seq_puts(m, "\"CPU\",\"Online?\",\"c\",\"g\",\"pq\",\"pqc\",\"pq\",");
 #ifdef CONFIG_NO_HZ
-	seq_puts(m, "\"dt\",\"dt nesting\",\"dn\",\"df\",");
+	seq_puts(m, "\"dt\",\"dt nesting\",\"dt NMI nesting\",\"df\",");
 #endif /* #ifdef CONFIG_NO_HZ */
 	seq_puts(m, "\"of\",\"ri\",\"ql\",\"b\",\"ci\",\"co\",\"ca\"\n");
 #ifdef CONFIG_TREE_PREEMPT_RCU
diff --git a/kernel/sched.c b/kernel/sched.c
index 2d12893b8b0f..cbb3a0eee58e 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -2573,7 +2573,26 @@ static void ttwu_queue_remote(struct task_struct *p, int cpu)
 	if (!next)
 		smp_send_reschedule(cpu);
 }
-#endif
+
+#ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW
+static int ttwu_activate_remote(struct task_struct *p, int wake_flags)
+{
+	struct rq *rq;
+	int ret = 0;
+
+	rq = __task_rq_lock(p);
+	if (p->on_cpu) {
+		ttwu_activate(rq, p, ENQUEUE_WAKEUP);
+		ttwu_do_wakeup(rq, p, wake_flags);
+		ret = 1;
+	}
+	__task_rq_unlock(rq);
+
+	return ret;
+
+}
+#endif /* __ARCH_WANT_INTERRUPTS_ON_CTXSW */
+#endif /* CONFIG_SMP */
 
 static void ttwu_queue(struct task_struct *p, int cpu)
 {
@@ -2631,17 +2650,17 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 	while (p->on_cpu) {
 #ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW
 		/*
-		 * If called from interrupt context we could have landed in the
-		 * middle of schedule(), in this case we should take care not
-		 * to spin on ->on_cpu if p is current, since that would
-		 * deadlock.
+		 * In case the architecture enables interrupts in
+		 * context_switch(), we cannot busy wait, since that
+		 * would lead to deadlocks when an interrupt hits and
+		 * tries to wake up @prev. So bail and do a complete
+		 * remote wakeup.
 		 */
-		if (p == current) {
-			ttwu_queue(p, cpu);
+		if (ttwu_activate_remote(p, wake_flags))
 			goto stat;
-		}
-#endif
+#else
 		cpu_relax();
+#endif
 	}
 	/*
 	 * Pairs with the smp_wmb() in finish_lock_switch().
@@ -5841,7 +5860,7 @@ void __cpuinit init_idle(struct task_struct *idle, int cpu)
 	idle->state = TASK_RUNNING;
 	idle->se.exec_start = sched_clock();
 
-	cpumask_copy(&idle->cpus_allowed, cpumask_of(cpu));
+	do_set_cpus_allowed(idle, cpumask_of(cpu));
 	/*
 	 * We're having a chicken and egg problem, even though we are
 	 * holding rq->lock, the cpu isn't yet set to this cpu so the
@@ -5929,6 +5948,16 @@ static inline void sched_init_granularity(void)
 }
 
 #ifdef CONFIG_SMP
+void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask)
+{
+	if (p->sched_class && p->sched_class->set_cpus_allowed)
+		p->sched_class->set_cpus_allowed(p, new_mask);
+	else {
+		cpumask_copy(&p->cpus_allowed, new_mask);
+		p->rt.nr_cpus_allowed = cpumask_weight(new_mask);
+	}
+}
+
 /*
  * This is how migration works:
  *
@@ -5974,12 +6003,7 @@ int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask)
 		goto out;
 	}
 
-	if (p->sched_class->set_cpus_allowed)
-		p->sched_class->set_cpus_allowed(p, new_mask);
-	else {
-		cpumask_copy(&p->cpus_allowed, new_mask);
-		p->rt.nr_cpus_allowed = cpumask_weight(new_mask);
-	}
+	do_set_cpus_allowed(p, new_mask);
 
 	/* Can the task run on the task's current CPU? If so, we're done */
 	if (cpumask_test_cpu(task_cpu(p), new_mask))
@@ -8764,42 +8788,10 @@ cpu_cgroup_can_attach_task(struct cgroup *cgrp, struct task_struct *tsk)
 	return 0;
 }
 
-static int
-cpu_cgroup_can_attach(struct cgroup_subsys *ss, struct cgroup *cgrp,
-		      struct task_struct *tsk, bool threadgroup)
-{
-	int retval = cpu_cgroup_can_attach_task(cgrp, tsk);
-	if (retval)
-		return retval;
-	if (threadgroup) {
-		struct task_struct *c;
-		rcu_read_lock();
-		list_for_each_entry_rcu(c, &tsk->thread_group, thread_group) {
-			retval = cpu_cgroup_can_attach_task(cgrp, c);
-			if (retval) {
-				rcu_read_unlock();
-				return retval;
-			}
-		}
-		rcu_read_unlock();
-	}
-	return 0;
-}
-
 static void
-cpu_cgroup_attach(struct cgroup_subsys *ss, struct cgroup *cgrp,
-		  struct cgroup *old_cont, struct task_struct *tsk,
-		  bool threadgroup)
+cpu_cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk)
 {
 	sched_move_task(tsk);
-	if (threadgroup) {
-		struct task_struct *c;
-		rcu_read_lock();
-		list_for_each_entry_rcu(c, &tsk->thread_group, thread_group) {
-			sched_move_task(c);
-		}
-		rcu_read_unlock();
-	}
 }
 
 static void
@@ -8887,8 +8879,8 @@ struct cgroup_subsys cpu_cgroup_subsys = {
 	.name		= "cpu",
 	.create		= cpu_cgroup_create,
 	.destroy	= cpu_cgroup_destroy,
-	.can_attach	= cpu_cgroup_can_attach,
-	.attach		= cpu_cgroup_attach,
+	.can_attach_task = cpu_cgroup_can_attach_task,
+	.attach_task	= cpu_cgroup_attach_task,
 	.exit		= cpu_cgroup_exit,
 	.populate	= cpu_cgroup_populate,
 	.subsys_id	= cpu_cgroup_subsys_id,
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index e32a9b70ee9c..433491c2dc8f 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -1076,8 +1076,6 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 	se->on_rq = 0;
 	update_cfs_load(cfs_rq, 0);
 	account_entity_dequeue(cfs_rq, se);
-	update_min_vruntime(cfs_rq);
-	update_cfs_shares(cfs_rq);
 
 	/*
 	 * Normalize the entity after updating the min_vruntime because the
@@ -1086,6 +1084,9 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 	 */
 	if (!(flags & DEQUEUE_SLEEP))
 		se->vruntime -= cfs_rq->min_vruntime;
+
+	update_min_vruntime(cfs_rq);
+	update_cfs_shares(cfs_rq);
 }
 
 /*
diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c
index 64b2a37c07d0..88725c939e0b 100644
--- a/kernel/sched_rt.c
+++ b/kernel/sched_rt.c
@@ -1263,6 +1263,7 @@ static int find_lowest_rq(struct task_struct *task)
 	if (!cpumask_test_cpu(this_cpu, lowest_mask))
 		this_cpu = -1; /* Skip this_cpu opt if not among lowest */
 
+	rcu_read_lock();
 	for_each_domain(cpu, sd) {
 		if (sd->flags & SD_WAKE_AFFINE) {
 			int best_cpu;
@@ -1272,15 +1273,20 @@ static int find_lowest_rq(struct task_struct *task)
 			 * remote processor.
 			 */
 			if (this_cpu != -1 &&
-			    cpumask_test_cpu(this_cpu, sched_domain_span(sd)))
+			    cpumask_test_cpu(this_cpu, sched_domain_span(sd))) {
+				rcu_read_unlock();
 				return this_cpu;
+			}
 
 			best_cpu = cpumask_first_and(lowest_mask,
 						     sched_domain_span(sd));
-			if (best_cpu < nr_cpu_ids)
+			if (best_cpu < nr_cpu_ids) {
+				rcu_read_unlock();
 				return best_cpu;
+			}
 		}
 	}
+	rcu_read_unlock();
 
 	/*
 	 * And finally, if there were no matches within the domains
diff --git a/kernel/sched_stats.h b/kernel/sched_stats.h
index 48ddf431db0e..331e01bcd026 100644
--- a/kernel/sched_stats.h
+++ b/kernel/sched_stats.h
@@ -37,7 +37,7 @@ static int show_schedstat(struct seq_file *seq, void *v)
 
 #ifdef CONFIG_SMP
 		/* domain-specific stats */
-		preempt_disable();
+		rcu_read_lock();
 		for_each_domain(cpu, sd) {
 			enum cpu_idle_type itype;
 
@@ -64,7 +64,7 @@ static int show_schedstat(struct seq_file *seq, void *v)
 			    sd->ttwu_wake_remote, sd->ttwu_move_affine,
 			    sd->ttwu_move_balance);
 		}
-		preempt_enable();
+		rcu_read_unlock();
 #endif
 	}
 	kfree(mask_str);