Merge commit 'v2.6.34-rc2' into perf/core

Merge reason: Pick up latest perf fixes from upstream.

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

30 files changed, 889 insertions, 189 deletions

diff --git a/kernel/acct.c b/kernel/acct.c
index a6605ca921b6..24f8c81fc48d 100644
--- a/kernel/acct.c
+++ b/kernel/acct.c
@@ -588,16 +588,6 @@ out:
 }
 
 /**
- * acct_init_pacct - initialize a new pacct_struct
- * @pacct: per-process accounting info struct to initialize
- */
-void acct_init_pacct(struct pacct_struct *pacct)
-{
-	memset(pacct, 0, sizeof(struct pacct_struct));
-	pacct->ac_utime = pacct->ac_stime = cputime_zero;
-}
-
-/**
  * acct_collect - collect accounting information into pacct_struct
  * @exitcode: task exit code
  * @group_dead: not 0, if this thread is the last one in the process.
diff --git a/kernel/audit.c b/kernel/audit.c
index 5feed232be9d..78f7f86aa238 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -398,7 +398,7 @@ static void kauditd_send_skb(struct sk_buff *skb)
 	skb_get(skb);
 	err = netlink_unicast(audit_sock, skb, audit_nlk_pid, 0);
 	if (err < 0) {
-		BUG_ON(err != -ECONNREFUSED); /* Shoudn't happen */
+		BUG_ON(err != -ECONNREFUSED); /* Shouldn't happen */
 		printk(KERN_ERR "audit: *NO* daemon at audit_pid=%d\n", audit_pid);
 		audit_log_lost("auditd dissapeared\n");
 		audit_pid = 0;
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 4fd90e129772..ef909a329750 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -4,6 +4,10 @@
  *  Based originally on the cpuset system, extracted by Paul Menage
  *  Copyright (C) 2006 Google, Inc
  *
+ *  Notifications support
+ *  Copyright (C) 2009 Nokia Corporation
+ *  Author: Kirill A. Shutemov
+ *
  *  Copyright notices from the original cpuset code:
  *  --------------------------------------------------
  *  Copyright (C) 2003 BULL SA.
@@ -44,6 +48,7 @@
 #include <linux/string.h>
 #include <linux/sort.h>
 #include <linux/kmod.h>
+#include <linux/module.h>
 #include <linux/delayacct.h>
 #include <linux/cgroupstats.h>
 #include <linux/hash.h>
@@ -52,15 +57,21 @@
 #include <linux/pid_namespace.h>
 #include <linux/idr.h>
 #include <linux/vmalloc.h> /* TODO: replace with more sophisticated array */
+#include <linux/eventfd.h>
+#include <linux/poll.h>
 
 #include <asm/atomic.h>
 
 static DEFINE_MUTEX(cgroup_mutex);
 
-/* Generate an array of cgroup subsystem pointers */
+/*
+ * Generate an array of cgroup subsystem pointers. At boot time, this is
+ * populated up to CGROUP_BUILTIN_SUBSYS_COUNT, and modular subsystems are
+ * registered after that. The mutable section of this array is protected by
+ * cgroup_mutex.
+ */
 #define SUBSYS(_x) &_x ## _subsys,
-
-static struct cgroup_subsys *subsys[] = {
+static struct cgroup_subsys *subsys[CGROUP_SUBSYS_COUNT] = {
 #include <linux/cgroup_subsys.h>
 };
 
@@ -147,6 +158,35 @@ struct css_id {
 	unsigned short stack[0]; /* Array of Length (depth+1) */
 };
 
+/*
+ * cgroup_event represents events which userspace want to recieve.
+ */
+struct cgroup_event {
+	/*
+	 * Cgroup which the event belongs to.
+	 */
+	struct cgroup *cgrp;
+	/*
+	 * Control file which the event associated.
+	 */
+	struct cftype *cft;
+	/*
+	 * eventfd to signal userspace about the event.
+	 */
+	struct eventfd_ctx *eventfd;
+	/*
+	 * Each of these stored in a list by the cgroup.
+	 */
+	struct list_head list;
+	/*
+	 * All fields below needed to unregister event when
+	 * userspace closes eventfd.
+	 */
+	poll_table pt;
+	wait_queue_head_t *wqh;
+	wait_queue_t wait;
+	struct work_struct remove;
+};
 
 /* The list of hierarchy roots */
 
@@ -250,7 +290,8 @@ struct cg_cgroup_link {
 static struct css_set init_css_set;
 static struct cg_cgroup_link init_css_set_link;
 
-static int cgroup_subsys_init_idr(struct cgroup_subsys *ss);
+static int cgroup_init_idr(struct cgroup_subsys *ss,
+			   struct cgroup_subsys_state *css);
 
 /* css_set_lock protects the list of css_set objects, and the
  * chain of tasks off each css_set.  Nests outside task->alloc_lock
@@ -448,8 +489,11 @@ static struct css_set *find_existing_css_set(
 	struct hlist_node *node;
 	struct css_set *cg;
 
-	/* Built the set of subsystem state objects that we want to
-	 * see in the new css_set */
+	/*
+	 * Build the set of subsystem state objects that we want to see in the
+	 * new css_set. while subsystems can change globally, the entries here
+	 * won't change, so no need for locking.
+	 */
 	for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
 		if (root->subsys_bits & (1UL << i)) {
 			/* Subsystem is in this hierarchy. So we want
@@ -696,6 +740,7 @@ void cgroup_lock(void)
 {
 	mutex_lock(&cgroup_mutex);
 }
+EXPORT_SYMBOL_GPL(cgroup_lock);
 
 /**
  * cgroup_unlock - release lock on cgroup changes
@@ -706,6 +751,7 @@ void cgroup_unlock(void)
 {
 	mutex_unlock(&cgroup_mutex);
 }
+EXPORT_SYMBOL_GPL(cgroup_unlock);
 
 /*
  * A couple of forward declarations required, due to cyclic reference loop:
@@ -757,6 +803,7 @@ static int cgroup_call_pre_destroy(struct cgroup *cgrp)
 			if (ret)
 				break;
 		}
+
 	return ret;
 }
 
@@ -884,7 +931,11 @@ void cgroup_release_and_wakeup_rmdir(struct cgroup_subsys_state *css)
 	css_put(css);
 }
 
-
+/*
+ * Call with cgroup_mutex held. Drops reference counts on modules, including
+ * any duplicate ones that parse_cgroupfs_options took. If this function
+ * returns an error, no reference counts are touched.
+ */
 static int rebind_subsystems(struct cgroupfs_root *root,
 			      unsigned long final_bits)
 {
@@ -892,6 +943,8 @@ static int rebind_subsystems(struct cgroupfs_root *root,
 	struct cgroup *cgrp = &root->top_cgroup;
 	int i;
 
+	BUG_ON(!mutex_is_locked(&cgroup_mutex));
+
 	removed_bits = root->actual_subsys_bits & ~final_bits;
 	added_bits = final_bits & ~root->actual_subsys_bits;
 	/* Check that any added subsystems are currently free */
@@ -900,6 +953,12 @@ static int rebind_subsystems(struct cgroupfs_root *root,
 		struct cgroup_subsys *ss = subsys[i];
 		if (!(bit & added_bits))
 			continue;
+		/*
+		 * Nobody should tell us to do a subsys that doesn't exist:
+		 * parse_cgroupfs_options should catch that case and refcounts
+		 * ensure that subsystems won't disappear once selected.
+		 */
+		BUG_ON(ss == NULL);
 		if (ss->root != &rootnode) {
 			/* Subsystem isn't free */
 			return -EBUSY;
@@ -919,6 +978,7 @@ static int rebind_subsystems(struct cgroupfs_root *root,
 		unsigned long bit = 1UL << i;
 		if (bit & added_bits) {
 			/* We're binding this subsystem to this hierarchy */
+			BUG_ON(ss == NULL);
 			BUG_ON(cgrp->subsys[i]);
 			BUG_ON(!dummytop->subsys[i]);
 			BUG_ON(dummytop->subsys[i]->cgroup != dummytop);
@@ -930,8 +990,10 @@ static int rebind_subsystems(struct cgroupfs_root *root,
 			if (ss->bind)
 				ss->bind(ss, cgrp);
 			mutex_unlock(&ss->hierarchy_mutex);
+			/* refcount was already taken, and we're keeping it */
 		} else if (bit & removed_bits) {
 			/* We're removing this subsystem */
+			BUG_ON(ss == NULL);
 			BUG_ON(cgrp->subsys[i] != dummytop->subsys[i]);
 			BUG_ON(cgrp->subsys[i]->cgroup != cgrp);
 			mutex_lock(&ss->hierarchy_mutex);
@@ -942,9 +1004,20 @@ static int rebind_subsystems(struct cgroupfs_root *root,
 			subsys[i]->root = &rootnode;
 			list_move(&ss->sibling, &rootnode.subsys_list);
 			mutex_unlock(&ss->hierarchy_mutex);
+			/* subsystem is now free - drop reference on module */
+			module_put(ss->module);
 		} else if (bit & final_bits) {
 			/* Subsystem state should already exist */
+			BUG_ON(ss == NULL);
 			BUG_ON(!cgrp->subsys[i]);
+			/*
+			 * a refcount was taken, but we already had one, so
+			 * drop the extra reference.
+			 */
+			module_put(ss->module);
+#ifdef CONFIG_MODULE_UNLOAD
+			BUG_ON(ss->module && !module_refcount(ss->module));
+#endif
 		} else {
 			/* Subsystem state shouldn't exist */
 			BUG_ON(cgrp->subsys[i]);
@@ -986,13 +1059,20 @@ struct cgroup_sb_opts {
 
 };
 
-/* Convert a hierarchy specifier into a bitmask of subsystems and
- * flags. */
-static int parse_cgroupfs_options(char *data,
-				     struct cgroup_sb_opts *opts)
+/*
+ * Convert a hierarchy specifier into a bitmask of subsystems and flags. Call
+ * with cgroup_mutex held to protect the subsys[] array. This function takes
+ * refcounts on subsystems to be used, unless it returns error, in which case
+ * no refcounts are taken.
+ */
+static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts)
 {
 	char *token, *o = data ?: "all";
 	unsigned long mask = (unsigned long)-1;
+	int i;
+	bool module_pin_failed = false;
+
+	BUG_ON(!mutex_is_locked(&cgroup_mutex));
 
 #ifdef CONFIG_CPUSETS
 	mask = ~(1UL << cpuset_subsys_id);
@@ -1005,10 +1085,11 @@ static int parse_cgroupfs_options(char *data,
 			return -EINVAL;
 		if (!strcmp(token, "all")) {
 			/* Add all non-disabled subsystems */
-			int i;
 			opts->subsys_bits = 0;
 			for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
 				struct cgroup_subsys *ss = subsys[i];
+				if (ss == NULL)
+					continue;
 				if (!ss->disabled)
 					opts->subsys_bits |= 1ul << i;
 			}
@@ -1026,7 +1107,6 @@ static int parse_cgroupfs_options(char *data,
 			if (!opts->release_agent)
 				return -ENOMEM;
 		} else if (!strncmp(token, "name=", 5)) {
-			int i;
 			const char *name = token + 5;
 			/* Can't specify an empty name */
 			if (!strlen(name))
@@ -1050,9 +1130,10 @@ static int parse_cgroupfs_options(char *data,
 				return -ENOMEM;
 		} else {
 			struct cgroup_subsys *ss;
-			int i;
 			for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
 				ss = subsys[i];
+				if (ss == NULL)
+					continue;
 				if (!strcmp(token, ss->name)) {
 					if (!ss->disabled)
 						set_bit(i, &opts->subsys_bits);
@@ -1087,9 +1168,54 @@ static int parse_cgroupfs_options(char *data,
 	if (!opts->subsys_bits && !opts->name)
 		return -EINVAL;
 
+	/*
+	 * Grab references on all the modules we'll need, so the subsystems
+	 * don't dance around before rebind_subsystems attaches them. This may
+	 * take duplicate reference counts on a subsystem that's already used,
+	 * but rebind_subsystems handles this case.
+	 */
+	for (i = CGROUP_BUILTIN_SUBSYS_COUNT; i < CGROUP_SUBSYS_COUNT; i++) {
+		unsigned long bit = 1UL << i;
+
+		if (!(bit & opts->subsys_bits))
+			continue;
+		if (!try_module_get(subsys[i]->module)) {
+			module_pin_failed = true;
+			break;
+		}
+	}
+	if (module_pin_failed) {
+		/*
+		 * oops, one of the modules was going away. this means that we
+		 * raced with a module_delete call, and to the user this is
+		 * essentially a "subsystem doesn't exist" case.
+		 */
+		for (i--; i >= CGROUP_BUILTIN_SUBSYS_COUNT; i--) {
+			/* drop refcounts only on the ones we took */
+			unsigned long bit = 1UL << i;
+
+			if (!(bit & opts->subsys_bits))
+				continue;
+			module_put(subsys[i]->module);
+		}
+		return -ENOENT;
+	}
+
 	return 0;
 }
 
+static void drop_parsed_module_refcounts(unsigned long subsys_bits)
+{
+	int i;
+	for (i = CGROUP_BUILTIN_SUBSYS_COUNT; i < CGROUP_SUBSYS_COUNT; i++) {
+		unsigned long bit = 1UL << i;
+
+		if (!(bit & subsys_bits))
+			continue;
+		module_put(subsys[i]->module);
+	}
+}
+
 static int cgroup_remount(struct super_block *sb, int *flags, char *data)
 {
 	int ret = 0;
@@ -1106,21 +1232,19 @@ static int cgroup_remount(struct super_block *sb, int *flags, char *data)
 	if (ret)
 		goto out_unlock;
 
-	/* Don't allow flags to change at remount */
-	if (opts.flags != root->flags) {
-		ret = -EINVAL;
-		goto out_unlock;
-	}
-
-	/* Don't allow name to change at remount */
-	if (opts.name && strcmp(opts.name, root->name)) {
+	/* Don't allow flags or name to change at remount */
+	if (opts.flags != root->flags ||
+	    (opts.name && strcmp(opts.name, root->name))) {
 		ret = -EINVAL;
+		drop_parsed_module_refcounts(opts.subsys_bits);
 		goto out_unlock;
 	}
 
 	ret = rebind_subsystems(root, opts.subsys_bits);
-	if (ret)
+	if (ret) {
+		drop_parsed_module_refcounts(opts.subsys_bits);
 		goto out_unlock;
+	}
 
 	/* (re)populate subsystem files */
 	cgroup_populate_dir(cgrp);
@@ -1151,6 +1275,8 @@ static void init_cgroup_housekeeping(struct cgroup *cgrp)
 	INIT_LIST_HEAD(&cgrp->release_list);
 	INIT_LIST_HEAD(&cgrp->pidlists);
 	mutex_init(&cgrp->pidlist_mutex);
+	INIT_LIST_HEAD(&cgrp->event_list);
+	spin_lock_init(&cgrp->event_list_lock);
 }
 
 static void init_cgroup_root(struct cgroupfs_root *root)
@@ -1306,7 +1432,9 @@ static int cgroup_get_sb(struct file_system_type *fs_type,
 	struct cgroupfs_root *new_root;
 
 	/* First find the desired set of subsystems */
+	mutex_lock(&cgroup_mutex);
 	ret = parse_cgroupfs_options(data, &opts);
+	mutex_unlock(&cgroup_mutex);
 	if (ret)
 		goto out_err;
 
@@ -1317,7 +1445,7 @@ static int cgroup_get_sb(struct file_system_type *fs_type,
 	new_root = cgroup_root_from_opts(&opts);
 	if (IS_ERR(new_root)) {
 		ret = PTR_ERR(new_root);
-		goto out_err;
+		goto drop_modules;
 	}
 	opts.new_root = new_root;
 
@@ -1326,7 +1454,7 @@ static int cgroup_get_sb(struct file_system_type *fs_type,
 	if (IS_ERR(sb)) {
 		ret = PTR_ERR(sb);
 		cgroup_drop_root(opts.new_root);
-		goto out_err;
+		goto drop_modules;
 	}
 
 	root = sb->s_fs_info;
@@ -1382,6 +1510,11 @@ static int cgroup_get_sb(struct file_system_type *fs_type,
 			free_cg_links(&tmp_cg_links);
 			goto drop_new_super;
 		}
+		/*
+		 * There must be no failure case after here, since rebinding
+		 * takes care of subsystems' refcounts, which are explicitly
+		 * dropped in the failure exit path.
+		 */
 
 		/* EBUSY should be the only error here */
 		BUG_ON(ret);
@@ -1420,6 +1553,8 @@ static int cgroup_get_sb(struct file_system_type *fs_type,
 		 * any) is not needed
 		 */
 		cgroup_drop_root(opts.new_root);
+		/* no subsys rebinding, so refcounts don't change */
+		drop_parsed_module_refcounts(opts.subsys_bits);
 	}
 
 	simple_set_mnt(mnt, sb);
@@ -1429,6 +1564,8 @@ static int cgroup_get_sb(struct file_system_type *fs_type,
 
  drop_new_super:
 	deactivate_locked_super(sb);
+ drop_modules:
+	drop_parsed_module_refcounts(opts.subsys_bits);
  out_err:
 	kfree(opts.release_agent);
 	kfree(opts.name);
@@ -1542,6 +1679,7 @@ int cgroup_path(const struct cgroup *cgrp, char *buf, int buflen)
 	memmove(buf, start, buf + buflen - start);
 	return 0;
 }
+EXPORT_SYMBOL_GPL(cgroup_path);
 
 /**
  * cgroup_attach_task - attach task 'tsk' to cgroup 'cgrp'
@@ -1554,7 +1692,7 @@ int cgroup_path(const struct cgroup *cgrp, char *buf, int buflen)
 int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk)
 {
 	int retval = 0;
-	struct cgroup_subsys *ss;
+	struct cgroup_subsys *ss, *failed_ss = NULL;
 	struct cgroup *oldcgrp;
 	struct css_set *cg;
 	struct css_set *newcg;
@@ -1568,8 +1706,16 @@ 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);
-			if (retval)
-				return retval;
+			if (retval) {
+				/*
+				 * Remember on which subsystem the can_attach()
+				 * failed, so that we only call cancel_attach()
+				 * against the subsystems whose can_attach()
+				 * succeeded. (See below)
+				 */
+				failed_ss = ss;
+				goto out;
+			}
 		}
 	}
 
@@ -1583,14 +1729,17 @@ int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk)
 	 */
 	newcg = find_css_set(cg, cgrp);
 	put_css_set(cg);
-	if (!newcg)
-		return -ENOMEM;
+	if (!newcg) {
+		retval = -ENOMEM;
+		goto out;
+	}
 
 	task_lock(tsk);
 	if (tsk->flags & PF_EXITING) {
 		task_unlock(tsk);
 		put_css_set(newcg);
-		return -ESRCH;
+		retval = -ESRCH;
+		goto out;
 	}
 	rcu_assign_pointer(tsk->cgroups, newcg);
 	task_unlock(tsk);
@@ -1616,7 +1765,22 @@ int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk)
 	 * is no longer empty.
 	 */
 	cgroup_wakeup_rmdir_waiter(cgrp);
-	return 0;
+out:
+	if (retval) {
+		for_each_subsys(root, ss) {
+			if (ss == failed_ss)
+				/*
+				 * This subsystem was the one that failed the
+				 * can_attach() check earlier, so we don't need
+				 * to call cancel_attach() against it or any
+				 * remaining subsystems.
+				 */
+				break;
+			if (ss->cancel_attach)
+				ss->cancel_attach(ss, cgrp, tsk, false);
+		}
+	}
+	return retval;
 }
 
 /*
@@ -1682,6 +1846,7 @@ bool cgroup_lock_live_group(struct cgroup *cgrp)
 	}
 	return true;
 }
+EXPORT_SYMBOL_GPL(cgroup_lock_live_group);
 
 static int cgroup_release_agent_write(struct cgroup *cgrp, struct cftype *cft,
 				      const char *buffer)
@@ -1950,6 +2115,16 @@ static const struct inode_operations cgroup_dir_inode_operations = {
 	.rename = cgroup_rename,
 };
 
+/*
+ * Check if a file is a control file
+ */
+static inline struct cftype *__file_cft(struct file *file)
+{
+	if (file->f_dentry->d_inode->i_fop != &cgroup_file_operations)
+		return ERR_PTR(-EINVAL);
+	return __d_cft(file->f_dentry);
+}
+
 static int cgroup_create_file(struct dentry *dentry, mode_t mode,
 				struct super_block *sb)
 {
@@ -2069,6 +2244,7 @@ int cgroup_add_file(struct cgroup *cgrp,
 		error = PTR_ERR(dentry);
 	return error;
 }
+EXPORT_SYMBOL_GPL(cgroup_add_file);
 
 int cgroup_add_files(struct cgroup *cgrp,
 			struct cgroup_subsys *subsys,
@@ -2083,6 +2259,7 @@ int cgroup_add_files(struct cgroup *cgrp,
 	}
 	return 0;
 }
+EXPORT_SYMBOL_GPL(cgroup_add_files);
 
 /**
  * cgroup_task_count - count the number of tasks in a cgroup.
@@ -2468,7 +2645,8 @@ static struct cgroup_pidlist *cgroup_pidlist_find(struct cgroup *cgrp,
 {
 	struct cgroup_pidlist *l;
 	/* don't need task_nsproxy() if we're looking at ourself */
-	struct pid_namespace *ns = get_pid_ns(current->nsproxy->pid_ns);
+	struct pid_namespace *ns = current->nsproxy->pid_ns;
+
 	/*
 	 * We can't drop the pidlist_mutex before taking the l->mutex in case
 	 * the last ref-holder is trying to remove l from the list at the same
@@ -2478,8 +2656,6 @@ static struct cgroup_pidlist *cgroup_pidlist_find(struct cgroup *cgrp,
 	mutex_lock(&cgrp->pidlist_mutex);
 	list_for_each_entry(l, &cgrp->pidlists, links) {
 		if (l->key.type == type && l->key.ns == ns) {
-			/* found a matching list - drop the extra refcount */
-			put_pid_ns(ns);
 			/* make sure l doesn't vanish out from under us */
 			down_write(&l->mutex);
 			mutex_unlock(&cgrp->pidlist_mutex);
@@ -2490,13 +2666,12 @@ static struct cgroup_pidlist *cgroup_pidlist_find(struct cgroup *cgrp,
 	l = kmalloc(sizeof(struct cgroup_pidlist), GFP_KERNEL);
 	if (!l) {
 		mutex_unlock(&cgrp->pidlist_mutex);
-		put_pid_ns(ns);
 		return l;
 	}
 	init_rwsem(&l->mutex);
 	down_write(&l->mutex);
 	l->key.type = type;
-	l->key.ns = ns;
+	l->key.ns = get_pid_ns(ns);
 	l->use_count = 0; /* don't increment here */
 	l->list = NULL;
 	l->owner = cgrp;
@@ -2804,6 +2979,174 @@ static int cgroup_write_notify_on_release(struct cgroup *cgrp,
 }
 
 /*
+ * Unregister event and free resources.
+ *
+ * Gets called from workqueue.
+ */
+static void cgroup_event_remove(struct work_struct *work)
+{
+	struct cgroup_event *event = container_of(work, struct cgroup_event,
+			remove);
+	struct cgroup *cgrp = event->cgrp;
+
+	/* TODO: check return code */
+	event->cft->unregister_event(cgrp, event->cft, event->eventfd);
+
+	eventfd_ctx_put(event->eventfd);
+	kfree(event);
+	dput(cgrp->dentry);
+}
+
+/*
+ * Gets called on POLLHUP on eventfd when user closes it.
+ *
+ * Called with wqh->lock held and interrupts disabled.
+ */
+static int cgroup_event_wake(wait_queue_t *wait, unsigned mode,
+		int sync, void *key)
+{
+	struct cgroup_event *event = container_of(wait,
+			struct cgroup_event, wait);
+	struct cgroup *cgrp = event->cgrp;
+	unsigned long flags = (unsigned long)key;
+
+	if (flags & POLLHUP) {
+		remove_wait_queue_locked(event->wqh, &event->wait);
+		spin_lock(&cgrp->event_list_lock);
+		list_del(&event->list);
+		spin_unlock(&cgrp->event_list_lock);
+		/*
+		 * We are in atomic context, but cgroup_event_remove() may
+		 * sleep, so we have to call it in workqueue.
+		 */
+		schedule_work(&event->remove);
+	}
+
+	return 0;
+}
+
+static void cgroup_event_ptable_queue_proc(struct file *file,
+		wait_queue_head_t *wqh, poll_table *pt)
+{
+	struct cgroup_event *event = container_of(pt,
+			struct cgroup_event, pt);
+
+	event->wqh = wqh;
+	add_wait_queue(wqh, &event->wait);
+}
+
+/*
+ * Parse input and register new cgroup event handler.
+ *
+ * Input must be in format '<event_fd> <control_fd> <args>'.
+ * Interpretation of args is defined by control file implementation.
+ */
+static int cgroup_write_event_control(struct cgroup *cgrp, struct cftype *cft,
+				      const char *buffer)
+{
+	struct cgroup_event *event = NULL;
+	unsigned int efd, cfd;
+	struct file *efile = NULL;
+	struct file *cfile = NULL;
+	char *endp;
+	int ret;
+
+	efd = simple_strtoul(buffer, &endp, 10);
+	if (*endp != ' ')
+		return -EINVAL;
+	buffer = endp + 1;
+
+	cfd = simple_strtoul(buffer, &endp, 10);
+	if ((*endp != ' ') && (*endp != '\0'))
+		return -EINVAL;
+	buffer = endp + 1;
+
+	event = kzalloc(sizeof(*event), GFP_KERNEL);
+	if (!event)
+		return -ENOMEM;
+	event->cgrp = cgrp;
+	INIT_LIST_HEAD(&event->list);
+	init_poll_funcptr(&event->pt, cgroup_event_ptable_queue_proc);
+	init_waitqueue_func_entry(&event->wait, cgroup_event_wake);
+	INIT_WORK(&event->remove, cgroup_event_remove);
+
+	efile = eventfd_fget(efd);
+	if (IS_ERR(efile)) {
+		ret = PTR_ERR(efile);
+		goto fail;
+	}
+
+	event->eventfd = eventfd_ctx_fileget(efile);
+	if (IS_ERR(event->eventfd)) {
+		ret = PTR_ERR(event->eventfd);
+		goto fail;
+	}
+
+	cfile = fget(cfd);
+	if (!cfile) {
+		ret = -EBADF;
+		goto fail;
+	}
+
+	/* the process need read permission on control file */
+	ret = file_permission(cfile, MAY_READ);
+	if (ret < 0)
+		goto fail;
+
+	event->cft = __file_cft(cfile);
+	if (IS_ERR(event->cft)) {
+		ret = PTR_ERR(event->cft);
+		goto fail;
+	}
+
+	if (!event->cft->register_event || !event->cft->unregister_event) {
+		ret = -EINVAL;
+		goto fail;
+	}
+
+	ret = event->cft->register_event(cgrp, event->cft,
+			event->eventfd, buffer);
+	if (ret)
+		goto fail;
+
+	if (efile->f_op->poll(efile, &event->pt) & POLLHUP) {
+		event->cft->unregister_event(cgrp, event->cft, event->eventfd);
+		ret = 0;
+		goto fail;
+	}
+
+	/*
+	 * Events should be removed after rmdir of cgroup directory, but before
+	 * destroying subsystem state objects. Let's take reference to cgroup
+	 * directory dentry to do that.
+	 */
+	dget(cgrp->dentry);
+
+	spin_lock(&cgrp->event_list_lock);
+	list_add(&event->list, &cgrp->event_list);
+	spin_unlock(&cgrp->event_list_lock);
+
+	fput(cfile);
+	fput(efile);
+
+	return 0;
+
+fail:
+	if (cfile)
+		fput(cfile);
+
+	if (event && event->eventfd && !IS_ERR(event->eventfd))
+		eventfd_ctx_put(event->eventfd);
+
+	if (!IS_ERR_OR_NULL(efile))
+		fput(efile);
+
+	kfree(event);
+
+	return ret;
+}
+
+/*
  * for the common functions, 'private' gives the type of file
  */
 /* for hysterical raisins, we can't put this on the older files */
@@ -2828,6 +3171,11 @@ static struct cftype files[] = {
 		.read_u64 = cgroup_read_notify_on_release,
 		.write_u64 = cgroup_write_notify_on_release,
 	},
+	{
+		.name = CGROUP_FILE_GENERIC_PREFIX "event_control",
+		.write_string = cgroup_write_event_control,
+		.mode = S_IWUGO,
+	},
 };
 
 static struct cftype cft_release_agent = {
@@ -2892,8 +3240,14 @@ static void cgroup_lock_hierarchy(struct cgroupfs_root *root)
 	/* We need to take each hierarchy_mutex in a consistent order */
 	int i;
 
+	/*
+	 * No worry about a race with rebind_subsystems that might mess up the
+	 * locking order, since both parties are under cgroup_mutex.
+	 */
 	for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
 		struct cgroup_subsys *ss = subsys[i];
+		if (ss == NULL)
+			continue;
 		if (ss->root == root)
 			mutex_lock(&ss->hierarchy_mutex);
 	}
@@ -2905,6 +3259,8 @@ static void cgroup_unlock_hierarchy(struct cgroupfs_root *root)
 
 	for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
 		struct cgroup_subsys *ss = subsys[i];
+		if (ss == NULL)
+			continue;
 		if (ss->root == root)
 			mutex_unlock(&ss->hierarchy_mutex);
 	}
@@ -3028,11 +3384,16 @@ static int cgroup_has_css_refs(struct cgroup *cgrp)
 	 * synchronization other than RCU, and the subsystem linked
 	 * list isn't RCU-safe */
 	int i;
+	/*
+	 * We won't need to lock the subsys array, because the subsystems
+	 * we're concerned about aren't going anywhere since our cgroup root
+	 * has a reference on them.
+	 */
 	for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
 		struct cgroup_subsys *ss = subsys[i];
 		struct cgroup_subsys_state *css;
-		/* Skip subsystems not in this hierarchy */
-		if (ss->root != cgrp->root)
+		/* Skip subsystems not present or not in this hierarchy */
+		if (ss == NULL || ss->root != cgrp->root)
 			continue;
 		css = cgrp->subsys[ss->subsys_id];
 		/* When called from check_for_release() it's possible
@@ -3106,6 +3467,7 @@ static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry)
 	struct dentry *d;
 	struct cgroup *parent;
 	DEFINE_WAIT(wait);
+	struct cgroup_event *event, *tmp;
 	int ret;
 
 	/* the vfs holds both inode->i_mutex already */
@@ -3189,6 +3551,20 @@ again:
 	set_bit(CGRP_RELEASABLE, &parent->flags);
 	check_for_release(parent);
 
+	/*
+	 * Unregister events and notify userspace.
+	 * Notify userspace about cgroup removing only after rmdir of cgroup
+	 * directory to avoid race between userspace and kernelspace
+	 */
+	spin_lock(&cgrp->event_list_lock);
+	list_for_each_entry_safe(event, tmp, &cgrp->event_list, list) {
+		list_del(&event->list);
+		remove_wait_queue(event->wqh, &event->wait);
+		eventfd_signal(event->eventfd, 1);
+		schedule_work(&event->remove);
+	}
+	spin_unlock(&cgrp->event_list_lock);
+
 	mutex_unlock(&cgroup_mutex);
 	return 0;
 }
@@ -3223,7 +3599,196 @@ static void __init cgroup_init_subsys(struct cgroup_subsys *ss)
 	mutex_init(&ss->hierarchy_mutex);
 	lockdep_set_class(&ss->hierarchy_mutex, &ss->subsys_key);
 	ss->active = 1;
+
+	/* this function shouldn't be used with modular subsystems, since they
+	 * need to register a subsys_id, among other things */
+	BUG_ON(ss->module);
+}
+
+/**
+ * cgroup_load_subsys: load and register a modular subsystem at runtime
+ * @ss: the subsystem to load
+ *
+ * This function should be called in a modular subsystem's initcall. If the
+ * subsytem is built as a module, it will be assigned a new subsys_id and set
+ * up for use. If the subsystem is built-in anyway, work is delegated to the
+ * simpler cgroup_init_subsys.
+ */
+int __init_or_module cgroup_load_subsys(struct cgroup_subsys *ss)
+{
+	int i;
+	struct cgroup_subsys_state *css;
+
+	/* check name and function validity */
+	if (ss->name == NULL || strlen(ss->name) > MAX_CGROUP_TYPE_NAMELEN ||
+	    ss->create == NULL || ss->destroy == NULL)
+		return -EINVAL;
+
+	/*
+	 * we don't support callbacks in modular subsystems. this check is
+	 * before the ss->module check for consistency; a subsystem that could
+	 * be a module should still have no callbacks even if the user isn't
+	 * compiling it as one.
+	 */
+	if (ss->fork || ss->exit)
+		return -EINVAL;
+
+	/*
+	 * an optionally modular subsystem is built-in: we want to do nothing,
+	 * since cgroup_init_subsys will have already taken care of it.
+	 */
+	if (ss->module == NULL) {
+		/* a few sanity checks */
+		BUG_ON(ss->subsys_id >= CGROUP_BUILTIN_SUBSYS_COUNT);
+		BUG_ON(subsys[ss->subsys_id] != ss);
+		return 0;
+	}
+
+	/*
+	 * need to register a subsys id before anything else - for example,
+	 * init_cgroup_css needs it.
+	 */
+	mutex_lock(&cgroup_mutex);
+	/* find the first empty slot in the array */
+	for (i = CGROUP_BUILTIN_SUBSYS_COUNT; i < CGROUP_SUBSYS_COUNT; i++) {
+		if (subsys[i] == NULL)
+			break;
+	}
+	if (i == CGROUP_SUBSYS_COUNT) {
+		/* maximum number of subsystems already registered! */
+		mutex_unlock(&cgroup_mutex);
+		return -EBUSY;
+	}
+	/* assign ourselves the subsys_id */
+	ss->subsys_id = i;
+	subsys[i] = ss;
+
+	/*
+	 * no ss->create seems to need anything important in the ss struct, so
+	 * this can happen first (i.e. before the rootnode attachment).
+	 */
+	css = ss->create(ss, dummytop);
+	if (IS_ERR(css)) {
+		/* failure case - need to deassign the subsys[] slot. */
+		subsys[i] = NULL;
+		mutex_unlock(&cgroup_mutex);
+		return PTR_ERR(css);
+	}
+
+	list_add(&ss->sibling, &rootnode.subsys_list);
+	ss->root = &rootnode;
+
+	/* our new subsystem will be attached to the dummy hierarchy. */
+	init_cgroup_css(css, ss, dummytop);
+	/* init_idr must be after init_cgroup_css because it sets css->id. */
+	if (ss->use_id) {
+		int ret = cgroup_init_idr(ss, css);
+		if (ret) {
+			dummytop->subsys[ss->subsys_id] = NULL;
+			ss->destroy(ss, dummytop);
+			subsys[i] = NULL;
+			mutex_unlock(&cgroup_mutex);
+			return ret;
+		}
+	}
+
+	/*
+	 * Now we need to entangle the css into the existing css_sets. unlike
+	 * in cgroup_init_subsys, there are now multiple css_sets, so each one
+	 * will need a new pointer to it; done by iterating the css_set_table.
+	 * furthermore, modifying the existing css_sets will corrupt the hash
+	 * table state, so each changed css_set will need its hash recomputed.
+	 * this is all done under the css_set_lock.
+	 */
+	write_lock(&css_set_lock);
+	for (i = 0; i < CSS_SET_TABLE_SIZE; i++) {
+		struct css_set *cg;
+		struct hlist_node *node, *tmp;
+		struct hlist_head *bucket = &css_set_table[i], *new_bucket;
+
+		hlist_for_each_entry_safe(cg, node, tmp, bucket, hlist) {
+			/* skip entries that we already rehashed */
+			if (cg->subsys[ss->subsys_id])
+				continue;
+			/* remove existing entry */
+			hlist_del(&cg->hlist);
+			/* set new value */
+			cg->subsys[ss->subsys_id] = css;
+			/* recompute hash and restore entry */
+			new_bucket = css_set_hash(cg->subsys);
+			hlist_add_head(&cg->hlist, new_bucket);
+		}
+	}
+	write_unlock(&css_set_lock);
+
+	mutex_init(&ss->hierarchy_mutex);
+	lockdep_set_class(&ss->hierarchy_mutex, &ss->subsys_key);
+	ss->active = 1;
+
+	/* success! */
+	mutex_unlock(&cgroup_mutex);
+	return 0;
 }
+EXPORT_SYMBOL_GPL(cgroup_load_subsys);
+
+/**
+ * cgroup_unload_subsys: unload a modular subsystem
+ * @ss: the subsystem to unload
+ *
+ * This function should be called in a modular subsystem's exitcall. When this
+ * function is invoked, the refcount on the subsystem's module will be 0, so
+ * the subsystem will not be attached to any hierarchy.
+ */
+void cgroup_unload_subsys(struct cgroup_subsys *ss)
+{
+	struct cg_cgroup_link *link;
+	struct hlist_head *hhead;
+
+	BUG_ON(ss->module == NULL);
+
+	/*
+	 * we shouldn't be called if the subsystem is in use, and the use of
+	 * try_module_get in parse_cgroupfs_options should ensure that it
+	 * doesn't start being used while we're killing it off.
+	 */
+	BUG_ON(ss->root != &rootnode);
+
+	mutex_lock(&cgroup_mutex);
+	/* deassign the subsys_id */
+	BUG_ON(ss->subsys_id < CGROUP_BUILTIN_SUBSYS_COUNT);
+	subsys[ss->subsys_id] = NULL;
+
+	/* remove subsystem from rootnode's list of subsystems */
+	list_del(&ss->sibling);
+
+	/*
+	 * disentangle the css from all css_sets attached to the dummytop. as
+	 * in loading, we need to pay our respects to the hashtable gods.
+	 */
+	write_lock(&css_set_lock);
+	list_for_each_entry(link, &dummytop->css_sets, cgrp_link_list) {
+		struct css_set *cg = link->cg;
+
+		hlist_del(&cg->hlist);
+		BUG_ON(!cg->subsys[ss->subsys_id]);
+		cg->subsys[ss->subsys_id] = NULL;
+		hhead = css_set_hash(cg->subsys);
+		hlist_add_head(&cg->hlist, hhead);
+	}
+	write_unlock(&css_set_lock);
+
+	/*
+	 * remove subsystem's css from the dummytop and free it - need to free
+	 * before marking as null because ss->destroy needs the cgrp->subsys
+	 * pointer to find their state. note that this also takes care of
+	 * freeing the css_id.
+	 */
+	ss->destroy(ss, dummytop);
+	dummytop->subsys[ss->subsys_id] = NULL;
+
+	mutex_unlock(&cgroup_mutex);
+}
+EXPORT_SYMBOL_GPL(cgroup_unload_subsys);
 
 /**
  * cgroup_init_early - cgroup initialization at system boot
@@ -3253,7 +3818,8 @@ int __init cgroup_init_early(void)
 	for (i = 0; i < CSS_SET_TABLE_SIZE; i++)
 		INIT_HLIST_HEAD(&css_set_table[i]);
 
-	for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
+	/* at bootup time, we don't worry about modular subsystems */
+	for (i = 0; i < CGROUP_BUILTIN_SUBSYS_COUNT; i++) {
 		struct cgroup_subsys *ss = subsys[i];
 
 		BUG_ON(!ss->name);
@@ -3288,12 +3854,13 @@ int __init cgroup_init(void)
 	if (err)
 		return err;
 
-	for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
+	/* at bootup time, we don't worry about modular subsystems */
+	for (i = 0; i < CGROUP_BUILTIN_SUBSYS_COUNT; i++) {
 		struct cgroup_subsys *ss = subsys[i];
 		if (!ss->early_init)
 			cgroup_init_subsys(ss);
 		if (ss->use_id)
-			cgroup_subsys_init_idr(ss);
+			cgroup_init_idr(ss, init_css_set.subsys[ss->subsys_id]);
 	}
 
 	/* Add init_css_set to the hash table */
@@ -3397,9 +3964,16 @@ static int proc_cgroupstats_show(struct seq_file *m, void *v)
 	int i;
 
 	seq_puts(m, "#subsys_name\thierarchy\tnum_cgroups\tenabled\n");
+	/*
+	 * ideally we don't want subsystems moving around while we do this.
+	 * cgroup_mutex is also necessary to guarantee an atomic snapshot of
+	 * subsys/hierarchy state.
+	 */
 	mutex_lock(&cgroup_mutex);
 	for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
 		struct cgroup_subsys *ss = subsys[i];
+		if (ss == NULL)
+			continue;
 		seq_printf(m, "%s\t%d\t%d\t%d\n",
 			   ss->name, ss->root->hierarchy_id,
 			   ss->root->number_of_cgroups, !ss->disabled);
@@ -3457,7 +4031,12 @@ void cgroup_fork_callbacks(struct task_struct *child)
 {
 	if (need_forkexit_callback) {
 		int i;
-		for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
+		/*
+		 * forkexit callbacks are only supported for builtin
+		 * subsystems, and the builtin section of the subsys array is
+		 * immutable, so we don't need to lock the subsys array here.
+		 */
+		for (i = 0; i < CGROUP_BUILTIN_SUBSYS_COUNT; i++) {
 			struct cgroup_subsys *ss = subsys[i];
 			if (ss->fork)
 				ss->fork(ss, child);
@@ -3526,7 +4105,11 @@ void cgroup_exit(struct task_struct *tsk, int run_callbacks)
 	struct css_set *cg;
 
 	if (run_callbacks && need_forkexit_callback) {
-		for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
+		/*
+		 * modular subsystems can't use callbacks, so no need to lock
+		 * the subsys array
+		 */
+		for (i = 0; i < CGROUP_BUILTIN_SUBSYS_COUNT; i++) {
 			struct cgroup_subsys *ss = subsys[i];
 			if (ss->exit)
 				ss->exit(ss, tsk);
@@ -3720,12 +4303,13 @@ static void check_for_release(struct cgroup *cgrp)
 	}
 }
 
-void __css_put(struct cgroup_subsys_state *css)
+/* Caller must verify that the css is not for root cgroup */
+void __css_put(struct cgroup_subsys_state *css, int count)
 {
 	struct cgroup *cgrp = css->cgroup;
 	int val;
 	rcu_read_lock();
-	val = atomic_dec_return(&css->refcnt);
+	val = atomic_sub_return(count, &css->refcnt);
 	if (val == 1) {
 		if (notify_on_release(cgrp)) {
 			set_bit(CGRP_RELEASABLE, &cgrp->flags);
@@ -3736,6 +4320,7 @@ void __css_put(struct cgroup_subsys_state *css)
 	rcu_read_unlock();
 	WARN_ON_ONCE(val < 1);
 }
+EXPORT_SYMBOL_GPL(__css_put);
 
 /*
  * Notify userspace when a cgroup is released, by running the
@@ -3817,8 +4402,11 @@ static int __init cgroup_disable(char *str)
 	while ((token = strsep(&str, ",")) != NULL) {
 		if (!*token)
 			continue;
-
-		for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
+		/*
+		 * cgroup_disable, being at boot time, can't know about module
+		 * subsystems, so we don't worry about them.
+		 */
+		for (i = 0; i < CGROUP_BUILTIN_SUBSYS_COUNT; i++) {
 			struct cgroup_subsys *ss = subsys[i];
 
 			if (!strcmp(token, ss->name)) {
@@ -3848,6 +4436,7 @@ unsigned short css_id(struct cgroup_subsys_state *css)
 		return cssid->id;
 	return 0;
 }
+EXPORT_SYMBOL_GPL(css_id);
 
 unsigned short css_depth(struct cgroup_subsys_state *css)
 {
@@ -3857,6 +4446,7 @@ unsigned short css_depth(struct cgroup_subsys_state *css)
 		return cssid->depth;
 	return 0;
 }
+EXPORT_SYMBOL_GPL(css_depth);
 
 bool css_is_ancestor(struct cgroup_subsys_state *child,
 		    const struct cgroup_subsys_state *root)
@@ -3893,6 +4483,7 @@ void free_css_id(struct cgroup_subsys *ss, struct cgroup_subsys_state *css)
 	spin_unlock(&ss->id_lock);
 	call_rcu(&id->rcu_head, __free_css_id_cb);
 }
+EXPORT_SYMBOL_GPL(free_css_id);
 
 /*
  * This is called by init or create(). Then, calls to this function are
@@ -3942,15 +4533,14 @@ err_out:
 
 }
 
-static int __init cgroup_subsys_init_idr(struct cgroup_subsys *ss)
+static int __init_or_module cgroup_init_idr(struct cgroup_subsys *ss,
+					    struct cgroup_subsys_state *rootcss)
 {
 	struct css_id *newid;
-	struct cgroup_subsys_state *rootcss;
 
 	spin_lock_init(&ss->id_lock);
 	idr_init(&ss->idr);
 
-	rootcss = init_css_set.subsys[ss->subsys_id];
 	newid = get_new_cssid(ss, 0);
 	if (IS_ERR(newid))
 		return PTR_ERR(newid);
@@ -4010,6 +4600,7 @@ struct cgroup_subsys_state *css_lookup(struct cgroup_subsys *ss, int id)
 
 	return rcu_dereference(cssid->css);
 }
+EXPORT_SYMBOL_GPL(css_lookup);
 
 /**
  * css_get_next - lookup next cgroup under specified hierarchy.
diff --git a/kernel/exit.c b/kernel/exit.c
index ce1e48c2d93d..cce59cb5ee6a 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -87,7 +87,7 @@ static void __exit_signal(struct task_struct *tsk)
 
 	sighand = rcu_dereference_check(tsk->sighand,
 					rcu_read_lock_held() ||
-					lockdep_is_held(&tasklist_lock));
+					lockdep_tasklist_lock_is_held());
 	spin_lock(&sighand->siglock);
 
 	posix_cpu_timers_exit(tsk);
diff --git a/kernel/fork.c b/kernel/fork.c
index b0ec34abc0bb..4799c5f0e6d0 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -86,7 +86,14 @@ int max_threads;		/* tunable limit on nr_threads */
 DEFINE_PER_CPU(unsigned long, process_counts) = 0;
 
 __cacheline_aligned DEFINE_RWLOCK(tasklist_lock);  /* outer */
-EXPORT_SYMBOL_GPL(tasklist_lock);
+
+#ifdef CONFIG_PROVE_RCU
+int lockdep_tasklist_lock_is_held(void)
+{
+	return lockdep_is_held(&tasklist_lock);
+}
+EXPORT_SYMBOL_GPL(lockdep_tasklist_lock_is_held);
+#endif /* #ifdef CONFIG_PROVE_RCU */
 
 int nr_processes(void)
 {
@@ -833,17 +840,6 @@ static void posix_cpu_timers_init_group(struct signal_struct *sig)
 	/* Thread group counters. */
 	thread_group_cputime_init(sig);
 
-	/* Expiration times and increments. */
-	sig->it[CPUCLOCK_PROF].expires = cputime_zero;
-	sig->it[CPUCLOCK_PROF].incr = cputime_zero;
-	sig->it[CPUCLOCK_VIRT].expires = cputime_zero;
-	sig->it[CPUCLOCK_VIRT].incr = cputime_zero;
-
-	/* Cached expiration times. */
-	sig->cputime_expires.prof_exp = cputime_zero;
-	sig->cputime_expires.virt_exp = cputime_zero;
-	sig->cputime_expires.sched_exp = 0;
-
 	cpu_limit = ACCESS_ONCE(sig->rlim[RLIMIT_CPU].rlim_cur);
 	if (cpu_limit != RLIM_INFINITY) {
 		sig->cputime_expires.prof_exp = secs_to_cputime(cpu_limit);
@@ -863,7 +859,7 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
 	if (clone_flags & CLONE_THREAD)
 		return 0;
 
-	sig = kmem_cache_alloc(signal_cachep, GFP_KERNEL);
+	sig = kmem_cache_zalloc(signal_cachep, GFP_KERNEL);
 	tsk->signal = sig;
 	if (!sig)
 		return -ENOMEM;
@@ -871,46 +867,21 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
 	atomic_set(&sig->count, 1);
 	atomic_set(&sig->live, 1);
 	init_waitqueue_head(&sig->wait_chldexit);
-	sig->flags = 0;
 	if (clone_flags & CLONE_NEWPID)
 		sig->flags |= SIGNAL_UNKILLABLE;
-	sig->group_exit_code = 0;
-	sig->group_exit_task = NULL;
-	sig->group_stop_count = 0;
 	sig->curr_target = tsk;
 	init_sigpending(&sig->shared_pending);
 	INIT_LIST_HEAD(&sig->posix_timers);
 
 	hrtimer_init(&sig->real_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-	sig->it_real_incr.tv64 = 0;
 	sig->real_timer.function = it_real_fn;
 
-	sig->leader = 0;	/* session leadership doesn't inherit */
-	sig->tty_old_pgrp = NULL;
-	sig->tty = NULL;
-
-	sig->utime = sig->stime = sig->cutime = sig->cstime = cputime_zero;
-	sig->gtime = cputime_zero;
-	sig->cgtime = cputime_zero;
-#ifndef CONFIG_VIRT_CPU_ACCOUNTING
-	sig->prev_utime = sig->prev_stime = cputime_zero;
-#endif
-	sig->nvcsw = sig->nivcsw = sig->cnvcsw = sig->cnivcsw = 0;
-	sig->min_flt = sig->maj_flt = sig->cmin_flt = sig->cmaj_flt = 0;
-	sig->inblock = sig->oublock = sig->cinblock = sig->coublock = 0;
-	sig->maxrss = sig->cmaxrss = 0;
-	task_io_accounting_init(&sig->ioac);
-	sig->sum_sched_runtime = 0;
-	taskstats_tgid_init(sig);
-
 	task_lock(current->group_leader);
 	memcpy(sig->rlim, current->signal->rlim, sizeof sig->rlim);
 	task_unlock(current->group_leader);
 
 	posix_cpu_timers_init_group(sig);
 
-	acct_init_pacct(&sig->pacct);
-
 	tty_audit_fork(sig);
 
 	sig->oom_adj = current->signal->oom_adj;
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index d70394f12ee9..42ec11b2af8a 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -554,7 +554,7 @@ out:
  *	signal. The occurence is latched into the irq controller hardware
  *	and must be acked in order to be reenabled. After the ack another
  *	interrupt can happen on the same source even before the first one
- *	is handled by the assosiacted event handler. If this happens it
+ *	is handled by the associated event handler. If this happens it
  *	might be necessary to disable (mask) the interrupt depending on the
  *	controller hardware. This requires to reenable the interrupt inside
  *	of the loop which handles the interrupts which have arrived while
diff --git a/kernel/irq/devres.c b/kernel/irq/devres.c
index d06df9c41cba..1ef4ffcdfa55 100644
--- a/kernel/irq/devres.c
+++ b/kernel/irq/devres.c
@@ -42,7 +42,7 @@ static int devm_irq_match(struct device *dev, void *res, void *data)
  *	automatically freed on driver detach.
  *
  *	If an IRQ allocated with this function needs to be freed
- *	separately, dev_free_irq() must be used.
+ *	separately, devm_free_irq() must be used.
  */
 int devm_request_threaded_irq(struct device *dev, unsigned int irq,
 			      irq_handler_t handler, irq_handler_t thread_fn,
@@ -81,7 +81,7 @@ EXPORT_SYMBOL(devm_request_threaded_irq);
  *	Except for the extra @dev argument, this function takes the
  *	same arguments and performs the same function as free_irq().
  *	This function instead of free_irq() should be used to manually
- *	free IRQs allocated with dev_request_irq().
+ *	free IRQs allocated with devm_request_irq().
  */
 void devm_free_irq(struct device *dev, unsigned int irq, void *dev_id)
 {
diff --git a/kernel/ksysfs.c b/kernel/ksysfs.c
index 6b1ccc3f0205..21fe3c426948 100644
--- a/kernel/ksysfs.c
+++ b/kernel/ksysfs.c
@@ -33,7 +33,7 @@ static ssize_t uevent_seqnum_show(struct kobject *kobj,
 }
 KERNEL_ATTR_RO(uevent_seqnum);
 
-/* uevent helper program, used during early boo */
+/* uevent helper program, used during early boot */
 static ssize_t uevent_helper_show(struct kobject *kobj,
 				  struct kobj_attribute *attr, char *buf)
 {
diff --git a/kernel/lockdep.c b/kernel/lockdep.c
index 65b5f5b7c298..c927a549db2c 100644
--- a/kernel/lockdep.c
+++ b/kernel/lockdep.c
@@ -3819,6 +3819,7 @@ void lockdep_rcu_dereference(const char *file, const int line)
 	printk("%s:%d invoked rcu_dereference_check() without protection!\n",
 			file, line);
 	printk("\nother info that might help us debug this:\n\n");
+	printk("\nrcu_scheduler_active = %d, debug_locks = %d\n", rcu_scheduler_active, debug_locks);
 	lockdep_print_held_locks(curr);
 	printk("\nstack backtrace:\n");
 	dump_stack();
diff --git a/kernel/nsproxy.c b/kernel/nsproxy.c
index 09b4ff9711b2..2ab67233ee8f 100644
--- a/kernel/nsproxy.c
+++ b/kernel/nsproxy.c
@@ -24,7 +24,18 @@
 
 static struct kmem_cache *nsproxy_cachep;
 
-struct nsproxy init_nsproxy = INIT_NSPROXY(init_nsproxy);
+struct nsproxy init_nsproxy = {
+	.count	= ATOMIC_INIT(1),
+	.uts_ns	= &init_uts_ns,
+#if defined(CONFIG_POSIX_MQUEUE) || defined(CONFIG_SYSVIPC)
+	.ipc_ns	= &init_ipc_ns,
+#endif
+	.mnt_ns	= NULL,
+	.pid_ns	= &init_pid_ns,
+#ifdef CONFIG_NET
+	.net_ns	= &init_net,
+#endif
+};
 
 static inline struct nsproxy *create_nsproxy(void)
 {
diff --git a/kernel/params.c b/kernel/params.c
index d55a53ec9234..0b30ecd53a52 100644
--- a/kernel/params.c
+++ b/kernel/params.c
@@ -401,8 +401,8 @@ int param_get_string(char *buffer, struct kernel_param *kp)
 }
 
 /* sysfs output in /sys/modules/XYZ/parameters/ */
-#define to_module_attr(n) container_of(n, struct module_attribute, attr);
-#define to_module_kobject(n) container_of(n, struct module_kobject, kobj);
+#define to_module_attr(n) container_of(n, struct module_attribute, attr)
+#define to_module_kobject(n) container_of(n, struct module_kobject, kobj)
 
 extern struct kernel_param __start___param[], __stop___param[];
 
@@ -420,7 +420,7 @@ struct module_param_attrs
 };
 
 #ifdef CONFIG_SYSFS
-#define to_param_attr(n) container_of(n, struct param_attribute, mattr);
+#define to_param_attr(n) container_of(n, struct param_attribute, mattr)
 
 static ssize_t param_attr_show(struct module_attribute *mattr,
 			       struct module *mod, char *buf)
diff --git a/kernel/pid.c b/kernel/pid.c
index 86b296943e5f..aebb30d9c233 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -367,7 +367,9 @@ struct task_struct *pid_task(struct pid *pid, enum pid_type type)
 	struct task_struct *result = NULL;
 	if (pid) {
 		struct hlist_node *first;
-		first = rcu_dereference_check(pid->tasks[type].first, rcu_read_lock_held() || lockdep_is_held(&tasklist_lock));
+		first = rcu_dereference_check(pid->tasks[type].first,
+					      rcu_read_lock_held() ||
+					      lockdep_tasklist_lock_is_held());
 		if (first)
 			result = hlist_entry(first, struct task_struct, pids[(type)].node);
 	}
diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c
index 86b3796b0436..79aac93acf99 100644
--- a/kernel/pid_namespace.c
+++ b/kernel/pid_namespace.c
@@ -161,13 +161,12 @@ void zap_pid_ns_processes(struct pid_namespace *pid_ns)
 		rcu_read_lock();
 
 		/*
-		 * Use force_sig() since it clears SIGNAL_UNKILLABLE ensuring
-		 * any nested-container's init processes don't ignore the
-		 * signal
+		 * Any nested-container's init processes won't ignore the
+		 * SEND_SIG_NOINFO signal, see send_signal()->si_fromuser().
 		 */
 		task = pid_task(find_vpid(nr), PIDTYPE_PID);
 		if (task)
-			force_sig(SIGKILL, task);
+			send_sig_info(SIGKILL, SEND_SIG_NOINFO, task);
 
 		rcu_read_unlock();
 
diff --git a/kernel/rcutree.h b/kernel/rcutree.h
index 1439eb504c22..4a525a30e08e 100644
--- a/kernel/rcutree.h
+++ b/kernel/rcutree.h
@@ -246,12 +246,21 @@ struct rcu_data {
 
 #define RCU_JIFFIES_TILL_FORCE_QS	 3	/* for rsp->jiffies_force_qs */
 #ifdef CONFIG_RCU_CPU_STALL_DETECTOR
-#define RCU_SECONDS_TILL_STALL_CHECK   (10 * HZ)  /* for rsp->jiffies_stall */
-#define RCU_SECONDS_TILL_STALL_RECHECK (30 * HZ)  /* for rsp->jiffies_stall */
-#define RCU_STALL_RAT_DELAY		2	  /* Allow other CPUs time */
-						  /*  to take at least one */
-						  /*  scheduling clock irq */
-						  /*  before ratting on them. */
+
+#ifdef CONFIG_PROVE_RCU
+#define RCU_STALL_DELAY_DELTA	       (5 * HZ)
+#else
+#define RCU_STALL_DELAY_DELTA	       0
+#endif
+
+#define RCU_SECONDS_TILL_STALL_CHECK   (10 * HZ + RCU_STALL_DELAY_DELTA)
+						/* for rsp->jiffies_stall */
+#define RCU_SECONDS_TILL_STALL_RECHECK (30 * HZ + RCU_STALL_DELAY_DELTA)
+						/* for rsp->jiffies_stall */
+#define RCU_STALL_RAT_DELAY		2	/* Allow other CPUs time */
+						/*  to take at least one */
+						/*  scheduling clock irq */
+						/*  before ratting on them. */
 
 #endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
 
diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h
index 464ad2cdee00..79b53bda8943 100644
--- a/kernel/rcutree_plugin.h
+++ b/kernel/rcutree_plugin.h
@@ -1010,6 +1010,10 @@ int rcu_needs_cpu(int cpu)
 	int c = 0;
 	int thatcpu;
 
+	/* Check for being in the holdoff period. */
+	if (per_cpu(rcu_dyntick_holdoff, cpu) == jiffies)
+		return rcu_needs_cpu_quick_check(cpu);
+
 	/* Don't bother unless we are the last non-dyntick-idle CPU. */
 	for_each_cpu_not(thatcpu, nohz_cpu_mask)
 		if (thatcpu != cpu) {
@@ -1041,10 +1045,8 @@ int rcu_needs_cpu(int cpu)
 	}
 
 	/* If RCU callbacks are still pending, RCU still needs this CPU. */
-	if (c) {
+	if (c)
 		raise_softirq(RCU_SOFTIRQ);
-		per_cpu(rcu_dyntick_holdoff, cpu) = jiffies;
-	}
 	return c;
 }
 
diff --git a/kernel/sched.c b/kernel/sched.c
index 150b6988de49..9ab3cd7858d3 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -2359,7 +2359,7 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state,
 {
 	int cpu, orig_cpu, this_cpu, success = 0;
 	unsigned long flags;
-	struct rq *rq, *orig_rq;
+	struct rq *rq;
 
 	if (!sched_feat(SYNC_WAKEUPS))
 		wake_flags &= ~WF_SYNC;
@@ -2367,7 +2367,7 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state,
 	this_cpu = get_cpu();
 
 	smp_wmb();
-	rq = orig_rq = task_rq_lock(p, &flags);
+	rq = task_rq_lock(p, &flags);
 	update_rq_clock(rq);
 	if (!(p->state & state))
 		goto out;
diff --git a/kernel/sched_cpupri.c b/kernel/sched_cpupri.c
index 82095bf2099f..fccf9fbb0d7b 100644
--- a/kernel/sched_cpupri.c
+++ b/kernel/sched_cpupri.c
@@ -56,7 +56,7 @@ static int convert_prio(int prio)
  * @lowest_mask: A mask to fill in with selected CPUs (or NULL)
  *
  * Note: This function returns the recommended CPUs as calculated during the
- * current invokation.  By the time the call returns, the CPUs may have in
+ * current invocation.  By the time the call returns, the CPUs may have in
  * fact changed priorities any number of times.  While not ideal, it is not
  * an issue of correctness since the normal rebalancer logic will correct
  * any discrepancies created by racing against the uncertainty of the current
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 3e1fd96c6cf9..5a5ea2cd924f 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -3476,7 +3476,7 @@ static void run_rebalance_domains(struct softirq_action *h)
 
 static inline int on_null_domain(int cpu)
 {
-	return !rcu_dereference(cpu_rq(cpu)->sd);
+	return !rcu_dereference_sched(cpu_rq(cpu)->sd);
 }
 
 /*
diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c
index 5a6ed1f0990a..b5b920ae2ea7 100644
--- a/kernel/sched_rt.c
+++ b/kernel/sched_rt.c
@@ -1146,7 +1146,12 @@ static struct task_struct *pick_next_highest_task_rt(struct rq *rq, int cpu)
 		if (next && next->prio < idx)
 			continue;
 		list_for_each_entry(rt_se, array->queue + idx, run_list) {
-			struct task_struct *p = rt_task_of(rt_se);
+			struct task_struct *p;
+
+			if (!rt_entity_is_task(rt_se))
+				continue;
+
+			p = rt_task_of(rt_se);
 			if (pick_rt_task(rq, p, cpu)) {
 				next = p;
 				break;
diff --git a/kernel/sys.c b/kernel/sys.c
index 9814e43fb23b..8298878f4f71 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -33,6 +33,7 @@
 #include <linux/task_io_accounting_ops.h>
 #include <linux/seccomp.h>
 #include <linux/cpu.h>
+#include <linux/personality.h>
 #include <linux/ptrace.h>
 #include <linux/fs_struct.h>
 
@@ -1114,6 +1115,15 @@ out:
 
 DECLARE_RWSEM(uts_sem);
 
+#ifdef COMPAT_UTS_MACHINE
+#define override_architecture(name) \
+	(current->personality == PER_LINUX32 && \
+	 copy_to_user(name->machine, COMPAT_UTS_MACHINE, \
+		      sizeof(COMPAT_UTS_MACHINE)))
+#else
+#define override_architecture(name)	0
+#endif
+
 SYSCALL_DEFINE1(newuname, struct new_utsname __user *, name)
 {
 	int errno = 0;
@@ -1122,9 +1132,66 @@ SYSCALL_DEFINE1(newuname, struct new_utsname __user *, name)
 	if (copy_to_user(name, utsname(), sizeof *name))
 		errno = -EFAULT;
 	up_read(&uts_sem);
+
+	if (!errno && override_architecture(name))
+		errno = -EFAULT;
 	return errno;
 }
 
+#ifdef __ARCH_WANT_SYS_OLD_UNAME
+/*
+ * Old cruft
+ */
+SYSCALL_DEFINE1(uname, struct old_utsname __user *, name)
+{
+	int error = 0;
+
+	if (!name)
+		return -EFAULT;
+
+	down_read(&uts_sem);
+	if (copy_to_user(name, utsname(), sizeof(*name)))
+		error = -EFAULT;
+	up_read(&uts_sem);
+
+	if (!error && override_architecture(name))
+		error = -EFAULT;
+	return error;
+}
+
+SYSCALL_DEFINE1(olduname, struct oldold_utsname __user *, name)
+{
+	int error;
+
+	if (!name)
+		return -EFAULT;
+	if (!access_ok(VERIFY_WRITE, name, sizeof(struct oldold_utsname)))
+		return -EFAULT;
+
+	down_read(&uts_sem);
+	error = __copy_to_user(&name->sysname, &utsname()->sysname,
+			       __OLD_UTS_LEN);
+	error |= __put_user(0, name->sysname + __OLD_UTS_LEN);
+	error |= __copy_to_user(&name->nodename, &utsname()->nodename,
+				__OLD_UTS_LEN);
+	error |= __put_user(0, name->nodename + __OLD_UTS_LEN);
+	error |= __copy_to_user(&name->release, &utsname()->release,
+				__OLD_UTS_LEN);
+	error |= __put_user(0, name->release + __OLD_UTS_LEN);
+	error |= __copy_to_user(&name->version, &utsname()->version,
+				__OLD_UTS_LEN);
+	error |= __put_user(0, name->version + __OLD_UTS_LEN);
+	error |= __copy_to_user(&name->machine, &utsname()->machine,
+				__OLD_UTS_LEN);
+	error |= __put_user(0, name->machine + __OLD_UTS_LEN);
+	up_read(&uts_sem);
+
+	if (!error && override_architecture(name))
+		error = -EFAULT;
+	return error ? -EFAULT : 0;
+}
+#endif
+
 SYSCALL_DEFINE2(sethostname, char __user *, name, int, len)
 {
 	int errno;
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index 695384f12a7d..70f2ea758ffe 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -126,6 +126,7 @@ cond_syscall(sys_setreuid16);
 cond_syscall(sys_setuid16);
 cond_syscall(sys_vm86old);
 cond_syscall(sys_vm86);
+cond_syscall(sys_ipc);
 cond_syscall(compat_sys_ipc);
 cond_syscall(compat_sys_sysctl);
 cond_syscall(sys_flock);
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 0ef19c614f6d..8686b0f5fc12 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -23,6 +23,7 @@
 #include <linux/swap.h>
 #include <linux/slab.h>
 #include <linux/sysctl.h>
+#include <linux/signal.h>
 #include <linux/proc_fs.h>
 #include <linux/security.h>
 #include <linux/ctype.h>
@@ -60,13 +61,23 @@
 #include <asm/stacktrace.h>
 #include <asm/io.h>
 #endif
+#ifdef CONFIG_BSD_PROCESS_ACCT
+#include <linux/acct.h>
+#endif
+#ifdef CONFIG_RT_MUTEXES
+#include <linux/rtmutex.h>
+#endif
+#if defined(CONFIG_PROVE_LOCKING) || defined(CONFIG_LOCK_STAT)
+#include <linux/lockdep.h>
+#endif
+#ifdef CONFIG_CHR_DEV_SG
+#include <scsi/sg.h>
+#endif
 
 
 #if defined(CONFIG_SYSCTL)
 
 /* External variables not in a header file. */
-extern int C_A_D;
-extern int print_fatal_signals;
 extern int sysctl_overcommit_memory;
 extern int sysctl_overcommit_ratio;
 extern int sysctl_panic_on_oom;
@@ -88,9 +99,6 @@ extern int sysctl_nr_open_min, sysctl_nr_open_max;
 #ifndef CONFIG_MMU
 extern int sysctl_nr_trim_pages;
 #endif
-#ifdef CONFIG_RCU_TORTURE_TEST
-extern int rcutorture_runnable;
-#endif /* #ifdef CONFIG_RCU_TORTURE_TEST */
 #ifdef CONFIG_BLOCK
 extern int blk_iopoll_enabled;
 #endif
@@ -120,14 +128,6 @@ static int min_percpu_pagelist_fract = 8;
 
 static int ngroups_max = NGROUPS_MAX;
 
-#ifdef CONFIG_MODULES
-extern char modprobe_path[];
-extern int modules_disabled;
-#endif
-#ifdef CONFIG_CHR_DEV_SG
-extern int sg_big_buff;
-#endif
-
 #ifdef CONFIG_SPARC
 #include <asm/system.h>
 #endif
@@ -149,10 +149,6 @@ extern int sysctl_userprocess_debug;
 extern int spin_retry;
 #endif
 
-#ifdef CONFIG_BSD_PROCESS_ACCT
-extern int acct_parm[];
-#endif
-
 #ifdef CONFIG_IA64
 extern int no_unaligned_warning;
 extern int unaligned_dump_stack;
@@ -160,10 +156,6 @@ extern int unaligned_dump_stack;
 
 extern struct ratelimit_state printk_ratelimit_state;
 
-#ifdef CONFIG_RT_MUTEXES
-extern int max_lock_depth;
-#endif
-
 #ifdef CONFIG_PROC_SYSCTL
 static int proc_do_cad_pid(struct ctl_table *table, int write,
 		  void __user *buffer, size_t *lenp, loff_t *ppos);
@@ -202,9 +194,6 @@ extern struct ctl_table epoll_table[];
 int sysctl_legacy_va_layout;
 #endif
 
-extern int prove_locking;
-extern int lock_stat;
-
 /* The default sysctl tables: */
 
 static struct ctl_table root_table[] = {
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index 1f663d23e85e..1f5dde637457 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -592,6 +592,10 @@ static inline void clocksource_select(void) { }
  */
 static int __init clocksource_done_booting(void)
 {
+	mutex_lock(&clocksource_mutex);
+	curr_clocksource = clocksource_default_clock();
+	mutex_unlock(&clocksource_mutex);
+
 	finished_booting = 1;
 
 	/*
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 83783579378f..d9062f5cc0c0 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -27,6 +27,7 @@
 #include <linux/ctype.h>
 #include <linux/list.h>
 #include <linux/hash.h>
+#include <linux/rcupdate.h>
 
 #include <trace/events/sched.h>
 
@@ -84,22 +85,22 @@ ftrace_func_t ftrace_trace_function __read_mostly = ftrace_stub;
 ftrace_func_t __ftrace_trace_function __read_mostly = ftrace_stub;
 ftrace_func_t ftrace_pid_function __read_mostly = ftrace_stub;
 
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-static int ftrace_set_func(unsigned long *array, int *idx, char *buffer);
-#endif
-
+/*
+ * Traverse the ftrace_list, invoking all entries.  The reason that we
+ * can use rcu_dereference_raw() is that elements removed from this list
+ * are simply leaked, so there is no need to interact with a grace-period
+ * mechanism.  The rcu_dereference_raw() calls are needed to handle
+ * concurrent insertions into the ftrace_list.
+ *
+ * Silly Alpha and silly pointer-speculation compiler optimizations!
+ */
 static void ftrace_list_func(unsigned long ip, unsigned long parent_ip)
 {
-	struct ftrace_ops *op = ftrace_list;
-
-	/* in case someone actually ports this to alpha! */
-	read_barrier_depends();
+	struct ftrace_ops *op = rcu_dereference_raw(ftrace_list); /*see above*/
 
 	while (op != &ftrace_list_end) {
-		/* silly alpha */
-		read_barrier_depends();
 		op->func(ip, parent_ip);
-		op = op->next;
+		op = rcu_dereference_raw(op->next); /*see above*/
 	};
 }
 
@@ -154,8 +155,7 @@ static int __register_ftrace_function(struct ftrace_ops *ops)
 	 * the ops->next pointer is valid before another CPU sees
 	 * the ops pointer included into the ftrace_list.
 	 */
-	smp_wmb();
-	ftrace_list = ops;
+	rcu_assign_pointer(ftrace_list, ops);
 
 	if (ftrace_enabled) {
 		ftrace_func_t func;
@@ -2276,6 +2276,8 @@ __setup("ftrace_filter=", set_ftrace_filter);
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 static char ftrace_graph_buf[FTRACE_FILTER_SIZE] __initdata;
+static int ftrace_set_func(unsigned long *array, int *idx, char *buffer);
+
 static int __init set_graph_function(char *str)
 {
 	strlcpy(ftrace_graph_buf, str, FTRACE_FILTER_SIZE);
@@ -3351,6 +3353,7 @@ void ftrace_graph_init_task(struct task_struct *t)
 {
 	/* Make sure we do not use the parent ret_stack */
 	t->ret_stack = NULL;
+	t->curr_ret_stack = -1;
 
 	if (ftrace_graph_active) {
 		struct ftrace_ret_stack *ret_stack;
@@ -3360,7 +3363,6 @@ void ftrace_graph_init_task(struct task_struct *t)
 				GFP_KERNEL);
 		if (!ret_stack)
 			return;
-		t->curr_ret_stack = -1;
 		atomic_set(&t->tracing_graph_pause, 0);
 		atomic_set(&t->trace_overrun, 0);
 		t->ftrace_timestamp = 0;
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 0287f9f52f5a..05a9f83b8819 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -2233,12 +2233,12 @@ ring_buffer_lock_reserve(struct ring_buffer *buffer, unsigned long length)
 	if (ring_buffer_flags != RB_BUFFERS_ON)
 		return NULL;
 
-	if (atomic_read(&buffer->record_disabled))
-		return NULL;
-
 	/* If we are tracing schedule, we don't want to recurse */
 	resched = ftrace_preempt_disable();
 
+	if (atomic_read(&buffer->record_disabled))
+		goto out_nocheck;
+
 	if (trace_recursive_lock())
 		goto out_nocheck;
 
@@ -2470,11 +2470,11 @@ int ring_buffer_write(struct ring_buffer *buffer,
 	if (ring_buffer_flags != RB_BUFFERS_ON)
 		return -EBUSY;
 
-	if (atomic_read(&buffer->record_disabled))
-		return -EBUSY;
-
 	resched = ftrace_preempt_disable();
 
+	if (atomic_read(&buffer->record_disabled))
+		goto out;
+
 	cpu = raw_smp_processor_id();
 
 	if (!cpumask_test_cpu(cpu, buffer->cpumask))
@@ -2542,7 +2542,7 @@ EXPORT_SYMBOL_GPL(ring_buffer_record_disable);
  * @buffer: The ring buffer to enable writes
  *
  * Note, multiple disables will need the same number of enables
- * to truely enable the writing (much like preempt_disable).
+ * to truly enable the writing (much like preempt_disable).
  */
 void ring_buffer_record_enable(struct ring_buffer *buffer)
 {
@@ -2578,7 +2578,7 @@ EXPORT_SYMBOL_GPL(ring_buffer_record_disable_cpu);
  * @cpu: The CPU to enable.
  *
  * Note, multiple disables will need the same number of enables
- * to truely enable the writing (much like preempt_disable).
+ * to truly enable the writing (much like preempt_disable).
  */
 void ring_buffer_record_enable_cpu(struct ring_buffer *buffer, int cpu)
 {
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index ed01fdba4a55..3ec2ee6f6560 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -374,6 +374,21 @@ static int __init set_buf_size(char *str)
 }
 __setup("trace_buf_size=", set_buf_size);
 
+static int __init set_tracing_thresh(char *str)
+{
+	unsigned long threshhold;
+	int ret;
+
+	if (!str)
+		return 0;
+	ret = strict_strtoul(str, 0, &threshhold);
+	if (ret < 0)
+		return 0;
+	tracing_thresh = threshhold * 1000;
+	return 1;
+}
+__setup("tracing_thresh=", set_tracing_thresh);
+
 unsigned long nsecs_to_usecs(unsigned long nsecs)
 {
 	return nsecs / 1000;
@@ -579,9 +594,10 @@ static ssize_t trace_seq_to_buffer(struct trace_seq *s, void *buf, size_t cnt)
 static arch_spinlock_t ftrace_max_lock =
 	(arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED;
 
+unsigned long __read_mostly	tracing_thresh;
+
 #ifdef CONFIG_TRACER_MAX_TRACE
 unsigned long __read_mostly	tracing_max_latency;
-unsigned long __read_mostly	tracing_thresh;
 
 /*
  * Copy the new maximum trace into the separate maximum-trace
@@ -592,7 +608,7 @@ static void
 __update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
 {
 	struct trace_array_cpu *data = tr->data[cpu];
-	struct trace_array_cpu *max_data = tr->data[cpu];
+	struct trace_array_cpu *max_data;
 
 	max_tr.cpu = cpu;
 	max_tr.time_start = data->preempt_timestamp;
@@ -602,7 +618,7 @@ __update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
 	max_data->critical_start = data->critical_start;
 	max_data->critical_end = data->critical_end;
 
-	memcpy(data->comm, tsk->comm, TASK_COMM_LEN);
+	memcpy(max_data->comm, tsk->comm, TASK_COMM_LEN);
 	max_data->pid = tsk->pid;
 	max_data->uid = task_uid(tsk);
 	max_data->nice = tsk->static_prio - 20 - MAX_RT_PRIO;
@@ -824,10 +840,10 @@ out:
 	mutex_unlock(&trace_types_lock);
 }
 
-static void __tracing_reset(struct trace_array *tr, int cpu)
+static void __tracing_reset(struct ring_buffer *buffer, int cpu)
 {
 	ftrace_disable_cpu();
-	ring_buffer_reset_cpu(tr->buffer, cpu);
+	ring_buffer_reset_cpu(buffer, cpu);
 	ftrace_enable_cpu();
 }
 
@@ -839,7 +855,7 @@ void tracing_reset(struct trace_array *tr, int cpu)
 
 	/* Make sure all commits have finished */
 	synchronize_sched();
-	__tracing_reset(tr, cpu);
+	__tracing_reset(buffer, cpu);
 
 	ring_buffer_record_enable(buffer);
 }
@@ -857,7 +873,7 @@ void tracing_reset_online_cpus(struct trace_array *tr)
 	tr->time_start = ftrace_now(tr->cpu);
 
 	for_each_online_cpu(cpu)
-		__tracing_reset(tr, cpu);
+		__tracing_reset(buffer, cpu);
 
 	ring_buffer_record_enable(buffer);
 }
@@ -934,6 +950,8 @@ void tracing_start(void)
 		goto out;
 	}
 
+	/* Prevent the buffers from switching */
+	arch_spin_lock(&ftrace_max_lock);
 
 	buffer = global_trace.buffer;
 	if (buffer)
@@ -943,6 +961,8 @@ void tracing_start(void)
 	if (buffer)
 		ring_buffer_record_enable(buffer);
 
+	arch_spin_unlock(&ftrace_max_lock);
+
 	ftrace_start();
  out:
 	spin_unlock_irqrestore(&tracing_start_lock, flags);
@@ -964,6 +984,9 @@ void tracing_stop(void)
 	if (trace_stop_count++)
 		goto out;
 
+	/* Prevent the buffers from switching */
+	arch_spin_lock(&ftrace_max_lock);
+
 	buffer = global_trace.buffer;
 	if (buffer)
 		ring_buffer_record_disable(buffer);
@@ -972,6 +995,8 @@ void tracing_stop(void)
 	if (buffer)
 		ring_buffer_record_disable(buffer);
 
+	arch_spin_unlock(&ftrace_max_lock);
+
  out:
 	spin_unlock_irqrestore(&tracing_start_lock, flags);
 }
@@ -1259,6 +1284,13 @@ ftrace_trace_userstack(struct ring_buffer *buffer, unsigned long flags, int pc)
 	if (!(trace_flags & TRACE_ITER_USERSTACKTRACE))
 		return;
 
+	/*
+	 * NMIs can not handle page faults, even with fix ups.
+	 * The save user stack can (and often does) fault.
+	 */
+	if (unlikely(in_nmi()))
+		return;
+
 	event = trace_buffer_lock_reserve(buffer, TRACE_USER_STACK,
 					  sizeof(*entry), flags, pc);
 	if (!event)
@@ -1703,6 +1735,7 @@ static void *s_start(struct seq_file *m, loff_t *pos)
 
 		ftrace_enable_cpu();
 
+		iter->leftover = 0;
 		for (p = iter; p && l < *pos; p = s_next(m, p, &l))
 			;
 
@@ -4248,10 +4281,10 @@ static __init int tracer_init_debugfs(void)
 #ifdef CONFIG_TRACER_MAX_TRACE
 	trace_create_file("tracing_max_latency", 0644, d_tracer,
 			&tracing_max_latency, &tracing_max_lat_fops);
+#endif
 
 	trace_create_file("tracing_thresh", 0644, d_tracer,
 			&tracing_thresh, &tracing_max_lat_fops);
-#endif
 
 	trace_create_file("README", 0444, d_tracer,
 			NULL, &tracing_readme_fops);
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index fd05bcaf91b0..2825ef2c0b15 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -396,9 +396,10 @@ extern int process_new_ksym_entry(char *ksymname, int op, unsigned long addr);
 
 extern unsigned long nsecs_to_usecs(unsigned long nsecs);
 
+extern unsigned long tracing_thresh;
+
 #ifdef CONFIG_TRACER_MAX_TRACE
 extern unsigned long tracing_max_latency;
-extern unsigned long tracing_thresh;
 
 void update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu);
 void update_max_tr_single(struct trace_array *tr,
@@ -550,7 +551,7 @@ static inline int ftrace_trace_task(struct task_struct *task)
  * struct trace_parser - servers for reading the user input separated by spaces
  * @cont: set if the input is not complete - no final space char was found
  * @buffer: holds the parsed user input
- * @idx: user input lenght
+ * @idx: user input length
  * @size: buffer size
  */
 struct trace_parser {
diff --git a/kernel/trace/trace_clock.c b/kernel/trace/trace_clock.c
index 84a3a7ba072a..6fbfb8f417b9 100644
--- a/kernel/trace/trace_clock.c
+++ b/kernel/trace/trace_clock.c
@@ -13,6 +13,7 @@
  * Tracer plugins will chose a default from these clocks.
  */
 #include <linux/spinlock.h>
+#include <linux/irqflags.h>
 #include <linux/hardirq.h>
 #include <linux/module.h>
 #include <linux/percpu.h>
diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c
index 7d79a10c3cde..81f691eb3a30 100644
--- a/kernel/trace/trace_event_perf.c
+++ b/kernel/trace/trace_event_perf.c
@@ -142,9 +142,9 @@ __kprobes void *perf_trace_buf_prepare(int size, unsigned short type,
 	cpu = smp_processor_id();
 
 	if (in_nmi())
-		trace_buf = rcu_dereference(perf_trace_buf_nmi);
+		trace_buf = rcu_dereference_sched(perf_trace_buf_nmi);
 	else
-		trace_buf = rcu_dereference(perf_trace_buf);
+		trace_buf = rcu_dereference_sched(perf_trace_buf);
 
 	if (!trace_buf)
 		goto err;
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index 3fc2a575664f..e6989d9b44da 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -237,6 +237,14 @@ int trace_graph_entry(struct ftrace_graph_ent *trace)
 	return ret;
 }
 
+int trace_graph_thresh_entry(struct ftrace_graph_ent *trace)
+{
+	if (tracing_thresh)
+		return 1;
+	else
+		return trace_graph_entry(trace);
+}
+
 static void __trace_graph_return(struct trace_array *tr,
 				struct ftrace_graph_ret *trace,
 				unsigned long flags,
@@ -290,13 +298,26 @@ void set_graph_array(struct trace_array *tr)
 	smp_mb();
 }
 
+void trace_graph_thresh_return(struct ftrace_graph_ret *trace)
+{
+	if (tracing_thresh &&
+	    (trace->rettime - trace->calltime < tracing_thresh))
+		return;
+	else
+		trace_graph_return(trace);
+}
+
 static int graph_trace_init(struct trace_array *tr)
 {
 	int ret;
 
 	set_graph_array(tr);
-	ret = register_ftrace_graph(&trace_graph_return,
-				    &trace_graph_entry);
+	if (tracing_thresh)
+		ret = register_ftrace_graph(&trace_graph_thresh_return,
+					    &trace_graph_thresh_entry);
+	else
+		ret = register_ftrace_graph(&trace_graph_return,
+					    &trace_graph_entry);
 	if (ret)
 		return ret;
 	tracing_start_cmdline_record();
@@ -920,7 +941,7 @@ print_graph_return(struct ftrace_graph_ret *trace, struct trace_seq *s,
 		if (!ret)
 			return TRACE_TYPE_PARTIAL_LINE;
 	} else {
-		ret = trace_seq_printf(s, "} (%ps)\n", (void *)trace->func);
+		ret = trace_seq_printf(s, "} /* %ps */\n", (void *)trace->func);
 		if (!ret)
 			return TRACE_TYPE_PARTIAL_LINE;
 	}