Merge commit 'v2.6.34-rc7' into perf/nmi

Merge reason: catch up with latest softlockup detector changes.

125 files changed, 7261 insertions, 4172 deletions

diff --git a/kernel/Makefile b/kernel/Makefile
index 8a5abe53eba..d5c30060ac1 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -10,7 +10,8 @@ obj-y     = sched.o fork.o exec_domain.o panic.o printk.o \
 	    kthread.o wait.o kfifo.o sys_ni.o posix-cpu-timers.o mutex.o \
 	    hrtimer.o rwsem.o nsproxy.o srcu.o semaphore.o \
 	    notifier.o ksysfs.o pm_qos_params.o sched_clock.o cred.o \
-	    async.o
+	    async.o range.o
+obj-$(CONFIG_HAVE_EARLY_RES) += early_res.o
 obj-y += groups.o
 
 ifdef CONFIG_FUNCTION_TRACER
@@ -91,6 +92,9 @@ obj-$(CONFIG_TASK_DELAY_ACCT) += delayacct.o
 obj-$(CONFIG_TASKSTATS) += taskstats.o tsacct.o
 obj-$(CONFIG_TRACEPOINTS) += tracepoint.o
 obj-$(CONFIG_LATENCYTOP) += latencytop.o
+obj-$(CONFIG_BINFMT_ELF) += elfcore.o
+obj-$(CONFIG_COMPAT_BINFMT_ELF) += elfcore.o
+obj-$(CONFIG_BINFMT_ELF_FDPIC) += elfcore.o
 obj-$(CONFIG_FUNCTION_TRACER) += trace/
 obj-$(CONFIG_TRACING) += trace/
 obj-$(CONFIG_X86_DS) += trace/
@@ -101,6 +105,7 @@ obj-$(CONFIG_SLOW_WORK_DEBUG) += slow-work-debugfs.o
 obj-$(CONFIG_PERF_EVENTS) += perf_event.o
 obj-$(CONFIG_HAVE_HW_BREAKPOINT) += hw_breakpoint.o
 obj-$(CONFIG_USER_RETURN_NOTIFIER) += user-return-notifier.o
+obj-$(CONFIG_PADATA) += padata.o
 
 ifneq ($(CONFIG_SCHED_OMIT_FRAME_POINTER),y)
 # According to Alan Modra <alan@linuxcare.com.au>, the -fno-omit-frame-pointer is
diff --git a/kernel/acct.c b/kernel/acct.c
index a6605ca921b..24f8c81fc48 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/async.c b/kernel/async.c
index 27235f5de19..15319d6c18f 100644
--- a/kernel/async.c
+++ b/kernel/async.c
@@ -56,6 +56,7 @@ asynchronous and synchronous parts of the kernel.
 #include <linux/init.h>
 #include <linux/kthread.h>
 #include <linux/delay.h>
+#include <linux/slab.h>
 #include <asm/atomic.h>
 
 static async_cookie_t next_cookie = 1;
diff --git a/kernel/audit.c b/kernel/audit.c
index 5feed232be9..c71bd26631a 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -46,6 +46,7 @@
 #include <asm/atomic.h>
 #include <linux/mm.h>
 #include <linux/module.h>
+#include <linux/slab.h>
 #include <linux/err.h>
 #include <linux/kthread.h>
 
@@ -398,7 +399,7 @@ 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/audit_tree.c b/kernel/audit_tree.c
index 4b05bd9479d..46a57b57a33 100644
--- a/kernel/audit_tree.c
+++ b/kernel/audit_tree.c
@@ -3,6 +3,7 @@
 #include <linux/namei.h>
 #include <linux/mount.h>
 #include <linux/kthread.h>
+#include <linux/slab.h>
 
 struct audit_tree;
 struct audit_chunk;
@@ -548,6 +549,11 @@ int audit_remove_tree_rule(struct audit_krule *rule)
 	return 0;
 }
 
+static int compare_root(struct vfsmount *mnt, void *arg)
+{
+	return mnt->mnt_root->d_inode == arg;
+}
+
 void audit_trim_trees(void)
 {
 	struct list_head cursor;
@@ -559,7 +565,6 @@ void audit_trim_trees(void)
 		struct path path;
 		struct vfsmount *root_mnt;
 		struct node *node;
-		struct list_head list;
 		int err;
 
 		tree = container_of(cursor.next, struct audit_tree, list);
@@ -577,24 +582,16 @@ void audit_trim_trees(void)
 		if (!root_mnt)
 			goto skip_it;
 
-		list_add_tail(&list, &root_mnt->mnt_list);
 		spin_lock(&hash_lock);
 		list_for_each_entry(node, &tree->chunks, list) {
-			struct audit_chunk *chunk = find_chunk(node);
-			struct inode *inode = chunk->watch.inode;
-			struct vfsmount *mnt;
+			struct inode *inode = find_chunk(node)->watch.inode;
 			node->index |= 1U<<31;
-			list_for_each_entry(mnt, &list, mnt_list) {
-				if (mnt->mnt_root->d_inode == inode) {
-					node->index &= ~(1U<<31);
-					break;
-				}
-			}
+			if (iterate_mounts(compare_root, inode, root_mnt))
+				node->index &= ~(1U<<31);
 		}
 		spin_unlock(&hash_lock);
 		trim_marked(tree);
 		put_tree(tree);
-		list_del_init(&list);
 		drop_collected_mounts(root_mnt);
 skip_it:
 		mutex_lock(&audit_filter_mutex);
@@ -603,22 +600,6 @@ skip_it:
 	mutex_unlock(&audit_filter_mutex);
 }
 
-static int is_under(struct vfsmount *mnt, struct dentry *dentry,
-		    struct path *path)
-{
-	if (mnt != path->mnt) {
-		for (;;) {
-			if (mnt->mnt_parent == mnt)
-				return 0;
-			if (mnt->mnt_parent == path->mnt)
-					break;
-			mnt = mnt->mnt_parent;
-		}
-		dentry = mnt->mnt_mountpoint;
-	}
-	return is_subdir(dentry, path->dentry);
-}
-
 int audit_make_tree(struct audit_krule *rule, char *pathname, u32 op)
 {
 
@@ -638,13 +619,17 @@ void audit_put_tree(struct audit_tree *tree)
 	put_tree(tree);
 }
 
+static int tag_mount(struct vfsmount *mnt, void *arg)
+{
+	return tag_chunk(mnt->mnt_root->d_inode, arg);
+}
+
 /* called with audit_filter_mutex */
 int audit_add_tree_rule(struct audit_krule *rule)
 {
 	struct audit_tree *seed = rule->tree, *tree;
 	struct path path;
-	struct vfsmount *mnt, *p;
-	struct list_head list;
+	struct vfsmount *mnt;
 	int err;
 
 	list_for_each_entry(tree, &tree_list, list) {
@@ -670,16 +655,9 @@ int audit_add_tree_rule(struct audit_krule *rule)
 		err = -ENOMEM;
 		goto Err;
 	}
-	list_add_tail(&list, &mnt->mnt_list);
 
 	get_tree(tree);
-	list_for_each_entry(p, &list, mnt_list) {
-		err = tag_chunk(p->mnt_root->d_inode, tree);
-		if (err)
-			break;
-	}
-
-	list_del(&list);
+	err = iterate_mounts(tag_mount, tree, mnt);
 	drop_collected_mounts(mnt);
 
 	if (!err) {
@@ -714,31 +692,23 @@ int audit_tag_tree(char *old, char *new)
 {
 	struct list_head cursor, barrier;
 	int failed = 0;
-	struct path path;
+	struct path path1, path2;
 	struct vfsmount *tagged;
-	struct list_head list;
-	struct vfsmount *mnt;
-	struct dentry *dentry;
 	int err;
 
-	err = kern_path(new, 0, &path);
+	err = kern_path(new, 0, &path2);
 	if (err)
 		return err;
-	tagged = collect_mounts(&path);
-	path_put(&path);
+	tagged = collect_mounts(&path2);
+	path_put(&path2);
 	if (!tagged)
 		return -ENOMEM;
 
-	err = kern_path(old, 0, &path);
+	err = kern_path(old, 0, &path1);
 	if (err) {
 		drop_collected_mounts(tagged);
 		return err;
 	}
-	mnt = mntget(path.mnt);
-	dentry = dget(path.dentry);
-	path_put(&path);
-
-	list_add_tail(&list, &tagged->mnt_list);
 
 	mutex_lock(&audit_filter_mutex);
 	list_add(&barrier, &tree_list);
@@ -746,7 +716,7 @@ int audit_tag_tree(char *old, char *new)
 
 	while (cursor.next != &tree_list) {
 		struct audit_tree *tree;
-		struct vfsmount *p;
+		int good_one = 0;
 
 		tree = container_of(cursor.next, struct audit_tree, list);
 		get_tree(tree);
@@ -754,30 +724,19 @@ int audit_tag_tree(char *old, char *new)
 		list_add(&cursor, &tree->list);
 		mutex_unlock(&audit_filter_mutex);
 
-		err = kern_path(tree->pathname, 0, &path);
-		if (err) {
-			put_tree(tree);
-			mutex_lock(&audit_filter_mutex);
-			continue;
+		err = kern_path(tree->pathname, 0, &path2);
+		if (!err) {
+			good_one = path_is_under(&path1, &path2);
+			path_put(&path2);
 		}
 
-		spin_lock(&vfsmount_lock);
-		if (!is_under(mnt, dentry, &path)) {
-			spin_unlock(&vfsmount_lock);
-			path_put(&path);
+		if (!good_one) {
 			put_tree(tree);
 			mutex_lock(&audit_filter_mutex);
 			continue;
 		}
-		spin_unlock(&vfsmount_lock);
-		path_put(&path);
-
-		list_for_each_entry(p, &list, mnt_list) {
-			failed = tag_chunk(p->mnt_root->d_inode, tree);
-			if (failed)
-				break;
-		}
 
+		failed = iterate_mounts(tag_mount, tree, tagged);
 		if (failed) {
 			put_tree(tree);
 			mutex_lock(&audit_filter_mutex);
@@ -818,10 +777,8 @@ int audit_tag_tree(char *old, char *new)
 	}
 	list_del(&barrier);
 	list_del(&cursor);
-	list_del(&list);
 	mutex_unlock(&audit_filter_mutex);
-	dput(dentry);
-	mntput(mnt);
+	path_put(&path1);
 	drop_collected_mounts(tagged);
 	return failed;
 }
diff --git a/kernel/audit_watch.c b/kernel/audit_watch.c
index cc7e87936cb..8df43696f4b 100644
--- a/kernel/audit_watch.c
+++ b/kernel/audit_watch.c
@@ -27,6 +27,7 @@
 #include <linux/namei.h>
 #include <linux/netlink.h>
 #include <linux/sched.h>
+#include <linux/slab.h>
 #include <linux/inotify.h>
 #include <linux/security.h>
 #include "audit.h"
diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c
index a70604047f3..ce08041f578 100644
--- a/kernel/auditfilter.c
+++ b/kernel/auditfilter.c
@@ -27,6 +27,7 @@
 #include <linux/namei.h>
 #include <linux/netlink.h>
 #include <linux/sched.h>
+#include <linux/slab.h>
 #include <linux/security.h>
 #include "audit.h"
 
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index fc0f928167e..3828ad5fb8f 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -49,6 +49,7 @@
 #include <linux/namei.h>
 #include <linux/mm.h>
 #include <linux/module.h>
+#include <linux/slab.h>
 #include <linux/mount.h>
 #include <linux/socket.h>
 #include <linux/mqueue.h>
@@ -1893,7 +1894,7 @@ static int audit_inc_name_count(struct audit_context *context,
 {
 	if (context->name_count >= AUDIT_NAMES) {
 		if (inode)
-			printk(KERN_DEBUG "name_count maxed, losing inode data: "
+			printk(KERN_DEBUG "audit: name_count maxed, losing inode data: "
 			       "dev=%02x:%02x, inode=%lu\n",
 			       MAJOR(inode->i_sb->s_dev),
 			       MINOR(inode->i_sb->s_dev),
@@ -1988,7 +1989,6 @@ void __audit_inode(const char *name, const struct dentry *dentry)
 
 /**
  * audit_inode_child - collect inode info for created/removed objects
- * @dname: inode's dentry name
  * @dentry: dentry being audited
  * @parent: inode of dentry parent
  *
@@ -2000,13 +2000,14 @@ void __audit_inode(const char *name, const struct dentry *dentry)
  * must be hooked prior, in order to capture the target inode during
  * unsuccessful attempts.
  */
-void __audit_inode_child(const char *dname, const struct dentry *dentry,
+void __audit_inode_child(const struct dentry *dentry,
 			 const struct inode *parent)
 {
 	int idx;
 	struct audit_context *context = current->audit_context;
 	const char *found_parent = NULL, *found_child = NULL;
 	const struct inode *inode = dentry->d_inode;
+	const char *dname = dentry->d_name.name;
 	int dirlen = 0;
 
 	if (!context->in_syscall)
@@ -2014,9 +2015,6 @@ void __audit_inode_child(const char *dname, const struct dentry *dentry,
 
 	if (inode)
 		handle_one(inode);
-	/* determine matching parent */
-	if (!dname)
-		goto add_names;
 
 	/* parent is more likely, look for it first */
 	for (idx = 0; idx < context->name_count; idx++) {
diff --git a/kernel/capability.c b/kernel/capability.c
index 7f876e60521..9e4697e9b27 100644
--- a/kernel/capability.c
+++ b/kernel/capability.c
@@ -135,7 +135,7 @@ static inline int cap_get_target_pid(pid_t pid, kernel_cap_t *pEp,
 	if (pid && (pid != task_pid_vnr(current))) {
 		struct task_struct *target;
 
-		read_lock(&tasklist_lock);
+		rcu_read_lock();
 
 		target = find_task_by_vpid(pid);
 		if (!target)
@@ -143,7 +143,7 @@ static inline int cap_get_target_pid(pid_t pid, kernel_cap_t *pEp,
 		else
 			ret = security_capget(target, pEp, pIp, pPp);
 
-		read_unlock(&tasklist_lock);
+		rcu_read_unlock();
 	} else
 		ret = security_capget(current, pEp, pIp, pPp);
 
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 1fbcc748044..3a53c771e50 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.
@@ -43,6 +47,7 @@
 #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>
@@ -51,15 +56,21 @@
 #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>
 };
 
@@ -146,6 +157,35 @@ 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 */
 
@@ -166,6 +206,20 @@ static DEFINE_SPINLOCK(hierarchy_id_lock);
  */
 static int need_forkexit_callback __read_mostly;
 
+#ifdef CONFIG_PROVE_LOCKING
+int cgroup_lock_is_held(void)
+{
+	return lockdep_is_held(&cgroup_mutex);
+}
+#else /* #ifdef CONFIG_PROVE_LOCKING */
+int cgroup_lock_is_held(void)
+{
+	return mutex_is_locked(&cgroup_mutex);
+}
+#endif /* #else #ifdef CONFIG_PROVE_LOCKING */
+
+EXPORT_SYMBOL_GPL(cgroup_lock_is_held);
+
 /* convenient tests for these bits */
 inline int cgroup_is_removed(const struct cgroup *cgrp)
 {
@@ -235,7 +289,8 @@ 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
@@ -433,8 +488,11 @@ 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
@@ -681,6 +739,7 @@ void cgroup_lock(void)
 {
 	mutex_lock(&cgroup_mutex);
 }
+EXPORT_SYMBOL_GPL(cgroup_lock);
 
 /**
  * cgroup_unlock - release lock on cgroup changes
@@ -691,6 +750,7 @@ void cgroup_unlock(void)
 {
 	mutex_unlock(&cgroup_mutex);
 }
+EXPORT_SYMBOL_GPL(cgroup_unlock);
 
 /*
  * A couple of forward declarations required, due to cyclic reference loop:
@@ -742,6 +802,7 @@ static int cgroup_call_pre_destroy(struct cgroup *cgrp)
 			if (ret)
 				break;
 		}
+
 	return ret;
 }
 
@@ -869,7 +930,11 @@ 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)
 {
@@ -877,6 +942,8 @@ 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 */
@@ -885,6 +952,12 @@ 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;
@@ -904,6 +977,7 @@ 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);
@@ -915,8 +989,10 @@ 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);
@@ -927,9 +1003,20 @@ 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]);
@@ -971,13 +1058,20 @@ 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);
@@ -990,10 +1084,11 @@ 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;
 			}
@@ -1011,7 +1106,6 @@ 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))
@@ -1035,9 +1129,10 @@ 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);
@@ -1072,9 +1167,54 @@ 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;
@@ -1091,21 +1231,19 @@ 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);
@@ -1136,6 +1274,8 @@ 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)
@@ -1291,7 +1431,9 @@ 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;
 
@@ -1302,7 +1444,7 @@ 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;
 
@@ -1311,7 +1453,7 @@ 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;
@@ -1367,6 +1509,11 @@ 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);
@@ -1405,6 +1552,8 @@ 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);
@@ -1414,6 +1563,8 @@ 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);
@@ -1495,7 +1646,9 @@ static inline struct cftype *__d_cft(struct dentry *dentry)
 int cgroup_path(const struct cgroup *cgrp, char *buf, int buflen)
 {
 	char *start;
-	struct dentry *dentry = rcu_dereference(cgrp->dentry);
+	struct dentry *dentry = rcu_dereference_check(cgrp->dentry,
+						      rcu_read_lock_held() ||
+						      cgroup_lock_is_held());
 
 	if (!dentry || cgrp == dummytop) {
 		/*
@@ -1511,13 +1664,17 @@ int cgroup_path(const struct cgroup *cgrp, char *buf, int buflen)
 	*--start = '\0';
 	for (;;) {
 		int len = dentry->d_name.len;
+
 		if ((start -= len) < buf)
 			return -ENAMETOOLONG;
-		memcpy(start, cgrp->dentry->d_name.name, len);
+		memcpy(start, dentry->d_name.name, len);
 		cgrp = cgrp->parent;
 		if (!cgrp)
 			break;
-		dentry = rcu_dereference(cgrp->dentry);
+
+		dentry = rcu_dereference_check(cgrp->dentry,
+					       rcu_read_lock_held() ||
+					       cgroup_lock_is_held());
 		if (!cgrp->parent)
 			continue;
 		if (--start < buf)
@@ -1527,6 +1684,7 @@ 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'
@@ -1539,7 +1697,7 @@ 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;
@@ -1553,8 +1711,16 @@ 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;
+			}
 		}
 	}
 
@@ -1568,14 +1734,17 @@ 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);
@@ -1601,7 +1770,22 @@ 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;
 }
 
 /*
@@ -1667,6 +1851,7 @@ 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)
@@ -1935,6 +2120,16 @@ 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)
 {
@@ -2054,6 +2249,7 @@ 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,
@@ -2068,6 +2264,7 @@ 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.
@@ -2453,7 +2650,8 @@ 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
@@ -2463,8 +2661,6 @@ 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);
@@ -2475,13 +2671,12 @@ 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;
@@ -2789,6 +2984,174 @@ 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 */
@@ -2813,6 +3176,11 @@ 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 = {
@@ -2877,8 +3245,14 @@ 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);
 	}
@@ -2890,6 +3264,8 @@ 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);
 	}
@@ -2936,14 +3312,17 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
 
 	for_each_subsys(root, ss) {
 		struct cgroup_subsys_state *css = ss->create(ss, cgrp);
+
 		if (IS_ERR(css)) {
 			err = PTR_ERR(css);
 			goto err_destroy;
 		}
 		init_cgroup_css(css, ss, cgrp);
-		if (ss->use_id)
-			if (alloc_css_id(ss, parent, cgrp))
+		if (ss->use_id) {
+			err = alloc_css_id(ss, parent, cgrp);
+			if (err)
 				goto err_destroy;
+		}
 		/* At error, ->destroy() callback has to free assigned ID. */
 	}
 
@@ -3010,11 +3389,16 @@ 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
@@ -3088,6 +3472,7 @@ 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 */
@@ -3171,6 +3556,20 @@ 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;
 }
@@ -3205,9 +3604,198 @@ 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
  *
  * Initialize cgroups at system boot, and initialize any
@@ -3235,7 +3823,8 @@ 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);
@@ -3270,12 +3859,13 @@ 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 */
@@ -3379,9 +3969,16 @@ 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);
@@ -3439,7 +4036,12 @@ 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);
@@ -3508,7 +4110,11 @@ 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);
@@ -3702,12 +4308,13 @@ 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);
@@ -3718,6 +4325,7 @@ 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
@@ -3799,8 +4407,11 @@ 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)) {
@@ -3830,6 +4441,7 @@ 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)
 {
@@ -3839,6 +4451,7 @@ 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)
@@ -3875,6 +4488,7 @@ 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
@@ -3924,15 +4538,14 @@ 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);
@@ -3948,13 +4561,13 @@ static int alloc_css_id(struct cgroup_subsys *ss, struct cgroup *parent,
 {
 	int subsys_id, i, depth = 0;
 	struct cgroup_subsys_state *parent_css, *child_css;
-	struct css_id *child_id, *parent_id = NULL;
+	struct css_id *child_id, *parent_id;
 
 	subsys_id = ss->subsys_id;
 	parent_css = parent->subsys[subsys_id];
 	child_css = child->subsys[subsys_id];
-	depth = css_depth(parent_css) + 1;
 	parent_id = parent_css->id;
+	depth = parent_id->depth;
 
 	child_id = get_new_cssid(ss, depth);
 	if (IS_ERR(child_id))
@@ -3992,6 +4605,7 @@ 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/cgroup_freezer.c b/kernel/cgroup_freezer.c
index 59e9ef6aab4..e5c0244962b 100644
--- a/kernel/cgroup_freezer.c
+++ b/kernel/cgroup_freezer.c
@@ -15,6 +15,7 @@
  */
 
 #include <linux/module.h>
+#include <linux/slab.h>
 #include <linux/cgroup.h>
 #include <linux/fs.h>
 #include <linux/uaccess.h>
@@ -47,17 +48,20 @@ static inline struct freezer *task_freezer(struct task_struct *task)
 			    struct freezer, css);
 }
 
-int cgroup_frozen(struct task_struct *task)
+int cgroup_freezing_or_frozen(struct task_struct *task)
 {
 	struct freezer *freezer;
 	enum freezer_state state;
 
 	task_lock(task);
 	freezer = task_freezer(task);
-	state = freezer->state;
+	if (!freezer->css.cgroup->parent)
+		state = CGROUP_THAWED; /* root cgroup can't be frozen */
+	else
+		state = freezer->state;
 	task_unlock(task);
 
-	return state == CGROUP_FROZEN;
+	return (state == CGROUP_FREEZING) || (state == CGROUP_FROZEN);
 }
 
 /*
@@ -201,9 +205,12 @@ static void freezer_fork(struct cgroup_subsys *ss, struct task_struct *task)
 	 * No lock is needed, since the task isn't on tasklist yet,
 	 * so it can't be moved to another cgroup, which means the
 	 * freezer won't be removed and will be valid during this
-	 * function call.
+	 * function call.  Nevertheless, apply RCU read-side critical
+	 * section to suppress RCU lockdep false positives.
 	 */
+	rcu_read_lock();
 	freezer = task_freezer(task);
+	rcu_read_unlock();
 
 	/*
 	 * The root cgroup is non-freezable, so we can skip the
diff --git a/kernel/compat.c b/kernel/compat.c
index f6c204f07ea..7f40e9275fd 100644
--- a/kernel/compat.c
+++ b/kernel/compat.c
@@ -25,6 +25,7 @@
 #include <linux/posix-timers.h>
 #include <linux/times.h>
 #include <linux/ptrace.h>
+#include <linux/gfp.h>
 
 #include <asm/uaccess.h>
 
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 1c8ddd6ee94..25bba73b1be 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -14,6 +14,7 @@
 #include <linux/kthread.h>
 #include <linux/stop_machine.h>
 #include <linux/mutex.h>
+#include <linux/gfp.h>
 
 #ifdef CONFIG_SMP
 /* Serializes the updates to cpu_online_mask, cpu_present_mask */
@@ -151,13 +152,13 @@ static inline void check_for_tasks(int cpu)
 
 	write_lock_irq(&tasklist_lock);
 	for_each_process(p) {
-		if (task_cpu(p) == cpu &&
+		if (task_cpu(p) == cpu && p->state == TASK_RUNNING &&
 		    (!cputime_eq(p->utime, cputime_zero) ||
 		     !cputime_eq(p->stime, cputime_zero)))
-			printk(KERN_WARNING "Task %s (pid = %d) is on cpu %d\
-				(state = %ld, flags = %x) \n",
-				 p->comm, task_pid_nr(p), cpu,
-				 p->state, p->flags);
+			printk(KERN_WARNING "Task %s (pid = %d) is on cpu %d "
+				"(state = %ld, flags = %x)\n",
+				p->comm, task_pid_nr(p), cpu,
+				p->state, p->flags);
 	}
 	write_unlock_irq(&tasklist_lock);
 }
@@ -338,7 +339,7 @@ int __cpuinit cpu_up(unsigned int cpu)
 	if (!cpu_possible(cpu)) {
 		printk(KERN_ERR "can't online cpu %d because it is not "
 			"configured as may-hotadd at boot time\n", cpu);
-#if defined(CONFIG_IA64) || defined(CONFIG_X86_64)
+#if defined(CONFIG_IA64)
 		printk(KERN_ERR "please check additional_cpus= boot "
 				"parameter\n");
 #endif
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index ba401fab459..d10946748ec 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -920,9 +920,6 @@ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs,
  *    call to guarantee_online_mems(), as we know no one is changing
  *    our task's cpuset.
  *
- *    Hold callback_mutex around the two modifications of our tasks
- *    mems_allowed to synchronize with cpuset_mems_allowed().
- *
  *    While the mm_struct we are migrating is typically from some
  *    other task, the task_struct mems_allowed that we are hacking
  *    is for our current task, which must allocate new pages for that
@@ -973,15 +970,20 @@ static void cpuset_change_nodemask(struct task_struct *p,
 	struct cpuset *cs;
 	int migrate;
 	const nodemask_t *oldmem = scan->data;
-	nodemask_t newmems;
+	NODEMASK_ALLOC(nodemask_t, newmems, GFP_KERNEL);
+
+	if (!newmems)
+		return;
 
 	cs = cgroup_cs(scan->cg);
-	guarantee_online_mems(cs, &newmems);
+	guarantee_online_mems(cs, newmems);
 
 	task_lock(p);
-	cpuset_change_task_nodemask(p, &newmems);
+	cpuset_change_task_nodemask(p, newmems);
 	task_unlock(p);
 
+	NODEMASK_FREE(newmems);
+
 	mm = get_task_mm(p);
 	if (!mm)
 		return;
@@ -1051,16 +1053,21 @@ static void update_tasks_nodemask(struct cpuset *cs, const nodemask_t *oldmem,
 static int update_nodemask(struct cpuset *cs, struct cpuset *trialcs,
 			   const char *buf)
 {
-	nodemask_t oldmem;
+	NODEMASK_ALLOC(nodemask_t, oldmem, GFP_KERNEL);
 	int retval;
 	struct ptr_heap heap;
 
+	if (!oldmem)
+		return -ENOMEM;
+
 	/*
 	 * top_cpuset.mems_allowed tracks node_stats[N_HIGH_MEMORY];
 	 * it's read-only
 	 */
-	if (cs == &top_cpuset)
-		return -EACCES;
+	if (cs == &top_cpuset) {
+		retval = -EACCES;
+		goto done;
+	}
 
 	/*
 	 * An empty mems_allowed is ok iff there are no tasks in the cpuset.
@@ -1076,11 +1083,13 @@ static int update_nodemask(struct cpuset *cs, struct cpuset *trialcs,
 			goto done;
 
 		if (!nodes_subset(trialcs->mems_allowed,
-				node_states[N_HIGH_MEMORY]))
-			return -EINVAL;
+				node_states[N_HIGH_MEMORY])) {
+			retval =  -EINVAL;
+			goto done;
+		}
 	}
-	oldmem = cs->mems_allowed;
-	if (nodes_equal(oldmem, trialcs->mems_allowed)) {
+	*oldmem = cs->mems_allowed;
+	if (nodes_equal(*oldmem, trialcs->mems_allowed)) {
 		retval = 0;		/* Too easy - nothing to do */
 		goto done;
 	}
@@ -1096,10 +1105,11 @@ static int update_nodemask(struct cpuset *cs, struct cpuset *trialcs,
 	cs->mems_allowed = trialcs->mems_allowed;
 	mutex_unlock(&callback_mutex);
 
-	update_tasks_nodemask(cs, &oldmem, &heap);
+	update_tasks_nodemask(cs, oldmem, &heap);
 
 	heap_free(&heap);
 done:
+	NODEMASK_FREE(oldmem);
 	return retval;
 }
 
@@ -1384,40 +1394,47 @@ static void cpuset_attach(struct cgroup_subsys *ss, struct cgroup *cont,
 			  struct cgroup *oldcont, struct task_struct *tsk,
 			  bool threadgroup)
 {
-	nodemask_t from, to;
 	struct mm_struct *mm;
 	struct cpuset *cs = cgroup_cs(cont);
 	struct cpuset *oldcs = cgroup_cs(oldcont);
+	NODEMASK_ALLOC(nodemask_t, from, GFP_KERNEL);
+	NODEMASK_ALLOC(nodemask_t, to, GFP_KERNEL);
+
+	if (from == NULL || to == NULL)
+		goto alloc_fail;
 
 	if (cs == &top_cpuset) {
 		cpumask_copy(cpus_attach, cpu_possible_mask);
-		to = node_possible_map;
 	} else {
 		guarantee_online_cpus(cs, cpus_attach);
-		guarantee_online_mems(cs, &to);
 	}
+	guarantee_online_mems(cs, to);
 
 	/* do per-task migration stuff possibly for each in the threadgroup */
-	cpuset_attach_task(tsk, &to, cs);
+	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);
+			cpuset_attach_task(c, to, cs);
 		}
 		rcu_read_unlock();
 	}
 
 	/* change mm; only needs to be done once even if threadgroup */
-	from = oldcs->mems_allowed;
-	to = cs->mems_allowed;
+	*from = oldcs->mems_allowed;
+	*to = cs->mems_allowed;
 	mm = get_task_mm(tsk);
 	if (mm) {
-		mpol_rebind_mm(mm, &to);
+		mpol_rebind_mm(mm, to);
 		if (is_memory_migrate(cs))
-			cpuset_migrate_mm(mm, &from, &to);
+			cpuset_migrate_mm(mm, from, to);
 		mmput(mm);
 	}
+
+alloc_fail:
+	NODEMASK_FREE(from);
+	NODEMASK_FREE(to);
 }
 
 /* The various types of files and directories in a cpuset file system */
@@ -1562,13 +1579,21 @@ static int cpuset_sprintf_cpulist(char *page, struct cpuset *cs)
 
 static int cpuset_sprintf_memlist(char *page, struct cpuset *cs)
 {
-	nodemask_t mask;
+	NODEMASK_ALLOC(nodemask_t, mask, GFP_KERNEL);
+	int retval;
+
+	if (mask == NULL)
+		return -ENOMEM;
 
 	mutex_lock(&callback_mutex);
-	mask = cs->mems_allowed;
+	*mask = cs->mems_allowed;
 	mutex_unlock(&callback_mutex);
 
-	return nodelist_scnprintf(page, PAGE_SIZE, mask);
+	retval = nodelist_scnprintf(page, PAGE_SIZE, *mask);
+
+	NODEMASK_FREE(mask);
+
+	return retval;
 }
 
 static ssize_t cpuset_common_file_read(struct cgroup *cont,
@@ -1997,7 +2022,10 @@ static void scan_for_empty_cpusets(struct cpuset *root)
 	struct cpuset *cp;	/* scans cpusets being updated */
 	struct cpuset *child;	/* scans child cpusets of cp */
 	struct cgroup *cont;
-	nodemask_t oldmems;
+	NODEMASK_ALLOC(nodemask_t, oldmems, GFP_KERNEL);
+
+	if (oldmems == NULL)
+		return;
 
 	list_add_tail((struct list_head *)&root->stack_list, &queue);
 
@@ -2014,7 +2042,7 @@ static void scan_for_empty_cpusets(struct cpuset *root)
 		    nodes_subset(cp->mems_allowed, node_states[N_HIGH_MEMORY]))
 			continue;
 
-		oldmems = cp->mems_allowed;
+		*oldmems = cp->mems_allowed;
 
 		/* Remove offline cpus and mems from this cpuset. */
 		mutex_lock(&callback_mutex);
@@ -2030,9 +2058,10 @@ static void scan_for_empty_cpusets(struct cpuset *root)
 			remove_tasks_in_empty_cpuset(cp);
 		else {
 			update_tasks_cpumask(cp, NULL);
-			update_tasks_nodemask(cp, &oldmems, NULL);
+			update_tasks_nodemask(cp, oldmems, NULL);
 		}
 	}
+	NODEMASK_FREE(oldmems);
 }
 
 /*
@@ -2090,20 +2119,33 @@ static int cpuset_track_online_cpus(struct notifier_block *unused_nb,
 static int cpuset_track_online_nodes(struct notifier_block *self,
 				unsigned long action, void *arg)
 {
+	NODEMASK_ALLOC(nodemask_t, oldmems, GFP_KERNEL);
+
+	if (oldmems == NULL)
+		return NOTIFY_DONE;
+
 	cgroup_lock();
 	switch (action) {
 	case MEM_ONLINE:
-	case MEM_OFFLINE:
+		*oldmems = top_cpuset.mems_allowed;
 		mutex_lock(&callback_mutex);
 		top_cpuset.mems_allowed = node_states[N_HIGH_MEMORY];
 		mutex_unlock(&callback_mutex);
-		if (action == MEM_OFFLINE)
-			scan_for_empty_cpusets(&top_cpuset);
+		update_tasks_nodemask(&top_cpuset, oldmems, NULL);
+		break;
+	case MEM_OFFLINE:
+		/*
+		 * needn't update top_cpuset.mems_allowed explicitly because
+		 * scan_for_empty_cpusets() will update it.
+		 */
+		scan_for_empty_cpusets(&top_cpuset);
 		break;
 	default:
 		break;
 	}
 	cgroup_unlock();
+
+	NODEMASK_FREE(oldmems);
 	return NOTIFY_OK;
 }
 #endif
diff --git a/kernel/cred.c b/kernel/cred.c
index dd76cfe5f5b..62af1816c23 100644
--- a/kernel/cred.c
+++ b/kernel/cred.c
@@ -10,6 +10,7 @@
  */
 #include <linux/module.h>
 #include <linux/cred.h>
+#include <linux/slab.h>
 #include <linux/sched.h>
 #include <linux/key.h>
 #include <linux/keyctl.h>
@@ -224,7 +225,7 @@ struct cred *cred_alloc_blank(void)
 #ifdef CONFIG_KEYS
 	new->tgcred = kzalloc(sizeof(*new->tgcred), GFP_KERNEL);
 	if (!new->tgcred) {
-		kfree(new);
+		kmem_cache_free(cred_jar, new);
 		return NULL;
 	}
 	atomic_set(&new->tgcred->usage, 1);
@@ -364,7 +365,7 @@ struct cred *prepare_usermodehelper_creds(void)
 
 	new = kmem_cache_alloc(cred_jar, GFP_ATOMIC);
 	if (!new)
-		return NULL;
+		goto free_tgcred;
 
 	kdebug("prepare_usermodehelper_creds() alloc %p", new);
 
@@ -398,6 +399,12 @@ struct cred *prepare_usermodehelper_creds(void)
 error:
 	put_cred(new);
 	return NULL;
+
+free_tgcred:
+#ifdef CONFIG_KEYS
+	kfree(tgcred);
+#endif
+	return NULL;
 }
 
 /*
@@ -786,8 +793,6 @@ bool creds_are_invalid(const struct cred *cred)
 {
 	if (cred->magic != CRED_MAGIC)
 		return true;
-	if (atomic_read(&cred->usage) < atomic_read(&cred->subscribers))
-		return true;
 #ifdef CONFIG_SECURITY_SELINUX
 	if (selinux_is_enabled()) {
 		if ((unsigned long) cred->security < PAGE_SIZE)
diff --git a/kernel/early_res.c b/kernel/early_res.c
new file mode 100644
index 00000000000..31aa9332ef3
--- /dev/null
+++ b/kernel/early_res.c
@@ -0,0 +1,584 @@
+/*
+ * early_res, could be used to replace bootmem
+ */
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/init.h>
+#include <linux/bootmem.h>
+#include <linux/mm.h>
+#include <linux/early_res.h>
+
+/*
+ * Early reserved memory areas.
+ */
+/*
+ * need to make sure this one is bigger enough before
+ * find_fw_memmap_area could be used
+ */
+#define MAX_EARLY_RES_X 32
+
+struct early_res {
+	u64 start, end;
+	char name[15];
+	char overlap_ok;
+};
+static struct early_res early_res_x[MAX_EARLY_RES_X] __initdata;
+
+static int max_early_res __initdata = MAX_EARLY_RES_X;
+static struct early_res *early_res __initdata = &early_res_x[0];
+static int early_res_count __initdata;
+
+static int __init find_overlapped_early(u64 start, u64 end)
+{
+	int i;
+	struct early_res *r;
+
+	for (i = 0; i < max_early_res && early_res[i].end; i++) {
+		r = &early_res[i];
+		if (end > r->start && start < r->end)
+			break;
+	}
+
+	return i;
+}
+
+/*
+ * Drop the i-th range from the early reservation map,
+ * by copying any higher ranges down one over it, and
+ * clearing what had been the last slot.
+ */
+static void __init drop_range(int i)
+{
+	int j;
+
+	for (j = i + 1; j < max_early_res && early_res[j].end; j++)
+		;
+
+	memmove(&early_res[i], &early_res[i + 1],
+	       (j - 1 - i) * sizeof(struct early_res));
+
+	early_res[j - 1].end = 0;
+	early_res_count--;
+}
+
+static void __init drop_range_partial(int i, u64 start, u64 end)
+{
+	u64 common_start, common_end;
+	u64 old_start, old_end;
+
+	old_start = early_res[i].start;
+	old_end = early_res[i].end;
+	common_start = max(old_start, start);
+	common_end = min(old_end, end);
+
+	/* no overlap ? */
+	if (common_start >= common_end)
+		return;
+
+	if (old_start < common_start) {
+		/* make head segment */
+		early_res[i].end = common_start;
+		if (old_end > common_end) {
+			char name[15];
+
+			/*
+			 * Save a local copy of the name, since the
+			 * early_res array could get resized inside
+			 * reserve_early_without_check() ->
+			 * __check_and_double_early_res(), which would
+			 * make the current name pointer invalid.
+			 */
+			strncpy(name, early_res[i].name,
+					 sizeof(early_res[i].name) - 1);
+			/* add another for left over on tail */
+			reserve_early_without_check(common_end, old_end, name);
+		}
+		return;
+	} else {
+		if (old_end > common_end) {
+			/* reuse the entry for tail left */
+			early_res[i].start = common_end;
+			return;
+		}
+		/* all covered */
+		drop_range(i);
+	}
+}
+
+/*
+ * Split any existing ranges that:
+ *  1) are marked 'overlap_ok', and
+ *  2) overlap with the stated range [start, end)
+ * into whatever portion (if any) of the existing range is entirely
+ * below or entirely above the stated range.  Drop the portion
+ * of the existing range that overlaps with the stated range,
+ * which will allow the caller of this routine to then add that
+ * stated range without conflicting with any existing range.
+ */
+static void __init drop_overlaps_that_are_ok(u64 start, u64 end)
+{
+	int i;
+	struct early_res *r;
+	u64 lower_start, lower_end;
+	u64 upper_start, upper_end;
+	char name[15];
+
+	for (i = 0; i < max_early_res && early_res[i].end; i++) {
+		r = &early_res[i];
+
+		/* Continue past non-overlapping ranges */
+		if (end <= r->start || start >= r->end)
+			continue;
+
+		/*
+		 * Leave non-ok overlaps as is; let caller
+		 * panic "Overlapping early reservations"
+		 * when it hits this overlap.
+		 */
+		if (!r->overlap_ok)
+			return;
+
+		/*
+		 * We have an ok overlap.  We will drop it from the early
+		 * reservation map, and add back in any non-overlapping
+		 * portions (lower or upper) as separate, overlap_ok,
+		 * non-overlapping ranges.
+		 */
+
+		/* 1. Note any non-overlapping (lower or upper) ranges. */
+		strncpy(name, r->name, sizeof(name) - 1);
+
+		lower_start = lower_end = 0;
+		upper_start = upper_end = 0;
+		if (r->start < start) {
+			lower_start = r->start;
+			lower_end = start;
+		}
+		if (r->end > end) {
+			upper_start = end;
+			upper_end = r->end;
+		}
+
+		/* 2. Drop the original ok overlapping range */
+		drop_range(i);
+
+		i--;		/* resume for-loop on copied down entry */
+
+		/* 3. Add back in any non-overlapping ranges. */
+		if (lower_end)
+			reserve_early_overlap_ok(lower_start, lower_end, name);
+		if (upper_end)
+			reserve_early_overlap_ok(upper_start, upper_end, name);
+	}
+}
+
+static void __init __reserve_early(u64 start, u64 end, char *name,
+						int overlap_ok)
+{
+	int i;
+	struct early_res *r;
+
+	i = find_overlapped_early(start, end);
+	if (i >= max_early_res)
+		panic("Too many early reservations");
+	r = &early_res[i];
+	if (r->end)
+		panic("Overlapping early reservations "
+		      "%llx-%llx %s to %llx-%llx %s\n",
+		      start, end - 1, name ? name : "", r->start,
+		      r->end - 1, r->name);
+	r->start = start;
+	r->end = end;
+	r->overlap_ok = overlap_ok;
+	if (name)
+		strncpy(r->name, name, sizeof(r->name) - 1);
+	early_res_count++;
+}
+
+/*
+ * A few early reservtations come here.
+ *
+ * The 'overlap_ok' in the name of this routine does -not- mean it
+ * is ok for these reservations to overlap an earlier reservation.
+ * Rather it means that it is ok for subsequent reservations to
+ * overlap this one.
+ *
+ * Use this entry point to reserve early ranges when you are doing
+ * so out of "Paranoia", reserving perhaps more memory than you need,
+ * just in case, and don't mind a subsequent overlapping reservation
+ * that is known to be needed.
+ *
+ * The drop_overlaps_that_are_ok() call here isn't really needed.
+ * It would be needed if we had two colliding 'overlap_ok'
+ * reservations, so that the second such would not panic on the
+ * overlap with the first.  We don't have any such as of this
+ * writing, but might as well tolerate such if it happens in
+ * the future.
+ */
+void __init reserve_early_overlap_ok(u64 start, u64 end, char *name)
+{
+	drop_overlaps_that_are_ok(start, end);
+	__reserve_early(start, end, name, 1);
+}
+
+static void __init __check_and_double_early_res(u64 ex_start, u64 ex_end)
+{
+	u64 start, end, size, mem;
+	struct early_res *new;
+
+	/* do we have enough slots left ? */
+	if ((max_early_res - early_res_count) > max(max_early_res/8, 2))
+		return;
+
+	/* double it */
+	mem = -1ULL;
+	size = sizeof(struct early_res) * max_early_res * 2;
+	if (early_res == early_res_x)
+		start = 0;
+	else
+		start = early_res[0].end;
+	end = ex_start;
+	if (start + size < end)
+		mem = find_fw_memmap_area(start, end, size,
+					 sizeof(struct early_res));
+	if (mem == -1ULL) {
+		start = ex_end;
+		end = get_max_mapped();
+		if (start + size < end)
+			mem = find_fw_memmap_area(start, end, size,
+						 sizeof(struct early_res));
+	}
+	if (mem == -1ULL)
+		panic("can not find more space for early_res array");
+
+	new = __va(mem);
+	/* save the first one for own */
+	new[0].start = mem;
+	new[0].end = mem + size;
+	new[0].overlap_ok = 0;
+	/* copy old to new */
+	if (early_res == early_res_x) {
+		memcpy(&new[1], &early_res[0],
+			 sizeof(struct early_res) * max_early_res);
+		memset(&new[max_early_res+1], 0,
+			 sizeof(struct early_res) * (max_early_res - 1));
+		early_res_count++;
+	} else {
+		memcpy(&new[1], &early_res[1],
+			 sizeof(struct early_res) * (max_early_res - 1));
+		memset(&new[max_early_res], 0,
+			 sizeof(struct early_res) * max_early_res);
+	}
+	memset(&early_res[0], 0, sizeof(struct early_res) * max_early_res);
+	early_res = new;
+	max_early_res *= 2;
+	printk(KERN_DEBUG "early_res array is doubled to %d at [%llx - %llx]\n",
+		max_early_res, mem, mem + size - 1);
+}
+
+/*
+ * Most early reservations come here.
+ *
+ * We first have drop_overlaps_that_are_ok() drop any pre-existing
+ * 'overlap_ok' ranges, so that we can then reserve this memory
+ * range without risk of panic'ing on an overlapping overlap_ok
+ * early reservation.
+ */
+void __init reserve_early(u64 start, u64 end, char *name)
+{
+	if (start >= end)
+		return;
+
+	__check_and_double_early_res(start, end);
+
+	drop_overlaps_that_are_ok(start, end);
+	__reserve_early(start, end, name, 0);
+}
+
+void __init reserve_early_without_check(u64 start, u64 end, char *name)
+{
+	struct early_res *r;
+
+	if (start >= end)
+		return;
+
+	__check_and_double_early_res(start, end);
+
+	r = &early_res[early_res_count];
+
+	r->start = start;
+	r->end = end;
+	r->overlap_ok = 0;
+	if (name)
+		strncpy(r->name, name, sizeof(r->name) - 1);
+	early_res_count++;
+}
+
+void __init free_early(u64 start, u64 end)
+{
+	struct early_res *r;
+	int i;
+
+	i = find_overlapped_early(start, end);
+	r = &early_res[i];
+	if (i >= max_early_res || r->end != end || r->start != start)
+		panic("free_early on not reserved area: %llx-%llx!",
+			 start, end - 1);
+
+	drop_range(i);
+}
+
+void __init free_early_partial(u64 start, u64 end)
+{
+	struct early_res *r;
+	int i;
+
+	if (start == end)
+		return;
+
+	if (WARN_ONCE(start > end, "  wrong range [%#llx, %#llx]\n", start, end))
+		return;
+
+try_next:
+	i = find_overlapped_early(start, end);
+	if (i >= max_early_res)
+		return;
+
+	r = &early_res[i];
+	/* hole ? */
+	if (r->end >= end && r->start <= start) {
+		drop_range_partial(i, start, end);
+		return;
+	}
+
+	drop_range_partial(i, start, end);
+	goto try_next;
+}
+
+#ifdef CONFIG_NO_BOOTMEM
+static void __init subtract_early_res(struct range *range, int az)
+{
+	int i, count;
+	u64 final_start, final_end;
+	int idx = 0;
+
+	count  = 0;
+	for (i = 0; i < max_early_res && early_res[i].end; i++)
+		count++;
+
+	/* need to skip first one ?*/
+	if (early_res != early_res_x)
+		idx = 1;
+
+#define DEBUG_PRINT_EARLY_RES 1
+
+#if DEBUG_PRINT_EARLY_RES
+	printk(KERN_INFO "Subtract (%d early reservations)\n", count);
+#endif
+	for (i = idx; i < count; i++) {
+		struct early_res *r = &early_res[i];
+#if DEBUG_PRINT_EARLY_RES
+		printk(KERN_INFO "  #%d [%010llx - %010llx] %15s\n", i,
+			r->start, r->end, r->name);
+#endif
+		final_start = PFN_DOWN(r->start);
+		final_end = PFN_UP(r->end);
+		if (final_start >= final_end)
+			continue;
+		subtract_range(range, az, final_start, final_end);
+	}
+
+}
+
+int __init get_free_all_memory_range(struct range **rangep, int nodeid)
+{
+	int i, count;
+	u64 start = 0, end;
+	u64 size;
+	u64 mem;
+	struct range *range;
+	int nr_range;
+
+	count  = 0;
+	for (i = 0; i < max_early_res && early_res[i].end; i++)
+		count++;
+
+	count *= 2;
+
+	size = sizeof(struct range) * count;
+	end = get_max_mapped();
+#ifdef MAX_DMA32_PFN
+	if (end > (MAX_DMA32_PFN << PAGE_SHIFT))
+		start = MAX_DMA32_PFN << PAGE_SHIFT;
+#endif
+	mem = find_fw_memmap_area(start, end, size, sizeof(struct range));
+	if (mem == -1ULL)
+		panic("can not find more space for range free");
+
+	range = __va(mem);
+	/* use early_node_map[] and early_res to get range array at first */
+	memset(range, 0, size);
+	nr_range = 0;
+
+	/* need to go over early_node_map to find out good range for node */
+	nr_range = add_from_early_node_map(range, count, nr_range, nodeid);
+#ifdef CONFIG_X86_32
+	subtract_range(range, count, max_low_pfn, -1ULL);
+#endif
+	subtract_early_res(range, count);
+	nr_range = clean_sort_range(range, count);
+
+	/* need to clear it ? */
+	if (nodeid == MAX_NUMNODES) {
+		memset(&early_res[0], 0,
+			 sizeof(struct early_res) * max_early_res);
+		early_res = NULL;
+		max_early_res = 0;
+	}
+
+	*rangep = range;
+	return nr_range;
+}
+#else
+void __init early_res_to_bootmem(u64 start, u64 end)
+{
+	int i, count;
+	u64 final_start, final_end;
+	int idx = 0;
+
+	count  = 0;
+	for (i = 0; i < max_early_res && early_res[i].end; i++)
+		count++;
+
+	/* need to skip first one ?*/
+	if (early_res != early_res_x)
+		idx = 1;
+
+	printk(KERN_INFO "(%d/%d early reservations) ==> bootmem [%010llx - %010llx]\n",
+			 count - idx, max_early_res, start, end);
+	for (i = idx; i < count; i++) {
+		struct early_res *r = &early_res[i];
+		printk(KERN_INFO "  #%d [%010llx - %010llx] %16s", i,
+			r->start, r->end, r->name);
+		final_start = max(start, r->start);
+		final_end = min(end, r->end);
+		if (final_start >= final_end) {
+			printk(KERN_CONT "\n");
+			continue;
+		}
+		printk(KERN_CONT " ==> [%010llx - %010llx]\n",
+			final_start, final_end);
+		reserve_bootmem_generic(final_start, final_end - final_start,
+				BOOTMEM_DEFAULT);
+	}
+	/* clear them */
+	memset(&early_res[0], 0, sizeof(struct early_res) * max_early_res);
+	early_res = NULL;
+	max_early_res = 0;
+	early_res_count = 0;
+}
+#endif
+
+/* Check for already reserved areas */
+static inline int __init bad_addr(u64 *addrp, u64 size, u64 align)
+{
+	int i;
+	u64 addr = *addrp;
+	int changed = 0;
+	struct early_res *r;
+again:
+	i = find_overlapped_early(addr, addr + size);
+	r = &early_res[i];
+	if (i < max_early_res && r->end) {
+		*addrp = addr = round_up(r->end, align);
+		changed = 1;
+		goto again;
+	}
+	return changed;
+}
+
+/* Check for already reserved areas */
+static inline int __init bad_addr_size(u64 *addrp, u64 *sizep, u64 align)
+{
+	int i;
+	u64 addr = *addrp, last;
+	u64 size = *sizep;
+	int changed = 0;
+again:
+	last = addr + size;
+	for (i = 0; i < max_early_res && early_res[i].end; i++) {
+		struct early_res *r = &early_res[i];
+		if (last > r->start && addr < r->start) {
+			size = r->start - addr;
+			changed = 1;
+			goto again;
+		}
+		if (last > r->end && addr < r->end) {
+			addr = round_up(r->end, align);
+			size = last - addr;
+			changed = 1;
+			goto again;
+		}
+		if (last <= r->end && addr >= r->start) {
+			(*sizep)++;
+			return 0;
+		}
+	}
+	if (changed) {
+		*addrp = addr;
+		*sizep = size;
+	}
+	return changed;
+}
+
+/*
+ * Find a free area with specified alignment in a specific range.
+ * only with the area.between start to end is active range from early_node_map
+ * so they are good as RAM
+ */
+u64 __init find_early_area(u64 ei_start, u64 ei_last, u64 start, u64 end,
+			 u64 size, u64 align)
+{
+	u64 addr, last;
+
+	addr = round_up(ei_start, align);
+	if (addr < start)
+		addr = round_up(start, align);
+	if (addr >= ei_last)
+		goto out;
+	while (bad_addr(&addr, size, align) && addr+size <= ei_last)
+		;
+	last = addr + size;
+	if (last > ei_last)
+		goto out;
+	if (last > end)
+		goto out;
+
+	return addr;
+
+out:
+	return -1ULL;
+}
+
+u64 __init find_early_area_size(u64 ei_start, u64 ei_last, u64 start,
+			 u64 *sizep, u64 align)
+{
+	u64 addr, last;
+
+	addr = round_up(ei_start, align);
+	if (addr < start)
+		addr = round_up(start, align);
+	if (addr >= ei_last)
+		goto out;
+	*sizep = ei_last - addr;
+	while (bad_addr_size(&addr, sizep, align) && addr + *sizep <= ei_last)
+		;
+	last = addr + *sizep;
+	if (last > ei_last)
+		goto out;
+
+	return addr;
+
+out:
+	return -1ULL;
+}
diff --git a/kernel/elfcore.c b/kernel/elfcore.c
new file mode 100644
index 00000000000..ff915efef66
--- /dev/null
+++ b/kernel/elfcore.c
@@ -0,0 +1,28 @@
+#include <linux/elf.h>
+#include <linux/fs.h>
+#include <linux/mm.h>
+
+#include <asm/elf.h>
+
+
+Elf_Half __weak elf_core_extra_phdrs(void)
+{
+	return 0;
+}
+
+int __weak elf_core_write_extra_phdrs(struct file *file, loff_t offset, size_t *size,
+				      unsigned long limit)
+{
+	return 1;
+}
+
+int __weak elf_core_write_extra_data(struct file *file, size_t *size,
+				     unsigned long limit)
+{
+	return 1;
+}
+
+size_t __weak elf_core_extra_data_size(void)
+{
+	return 0;
+}
diff --git a/kernel/exit.c b/kernel/exit.c
index 546774a31a6..7f2683a10ac 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -85,7 +85,9 @@ static void __exit_signal(struct task_struct *tsk)
 	BUG_ON(!sig);
 	BUG_ON(!atomic_read(&sig->count));
 
-	sighand = rcu_dereference(tsk->sighand);
+	sighand = rcu_dereference_check(tsk->sighand,
+					rcu_read_lock_held() ||
+					lockdep_tasklist_lock_is_held());
 	spin_lock(&sighand->siglock);
 
 	posix_cpu_timers_exit(tsk);
@@ -170,8 +172,10 @@ void release_task(struct task_struct * p)
 repeat:
 	tracehook_prepare_release_task(p);
 	/* don't need to get the RCU readlock here - the process is dead and
-	 * can't be modifying its own credentials */
+	 * can't be modifying its own credentials. But shut RCU-lockdep up */
+	rcu_read_lock();
 	atomic_dec(&__task_cred(p)->user->processes);
+	rcu_read_unlock();
 
 	proc_flush_task(p);
 
@@ -473,9 +477,11 @@ static void close_files(struct files_struct * files)
 	/*
 	 * It is safe to dereference the fd table without RCU or
 	 * ->file_lock because this is the last reference to the
-	 * files structure.
+	 * files structure.  But use RCU to shut RCU-lockdep up.
 	 */
+	rcu_read_lock();
 	fdt = files_fdtable(files);
+	rcu_read_unlock();
 	for (;;) {
 		unsigned long set;
 		i = j * __NFDBITS;
@@ -521,10 +527,12 @@ void put_files_struct(struct files_struct *files)
 		 * at the end of the RCU grace period. Otherwise,
 		 * you can free files immediately.
 		 */
+		rcu_read_lock();
 		fdt = files_fdtable(files);
 		if (fdt != &files->fdtab)
 			kmem_cache_free(files_cachep, files);
 		free_fdtable(fdt);
+		rcu_read_unlock();
 	}
 }
 
@@ -944,7 +952,9 @@ NORET_TYPE void do_exit(long code)
 				preempt_count());
 
 	acct_update_integrals(tsk);
-
+	/* sync mm's RSS info before statistics gathering */
+	if (tsk->mm)
+		sync_mm_rss(tsk, tsk->mm);
 	group_dead = atomic_dec_and_test(&tsk->signal->live);
 	if (group_dead) {
 		hrtimer_cancel(&tsk->signal->real_timer);
@@ -1180,7 +1190,7 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p)
 
 	if (unlikely(wo->wo_flags & WNOWAIT)) {
 		int exit_code = p->exit_code;
-		int why, status;
+		int why;
 
 		get_task_struct(p);
 		read_unlock(&tasklist_lock);
diff --git a/kernel/fork.c b/kernel/fork.c
index 5b2959b3ffc..44b0791b0a2 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -87,6 +87,14 @@ DEFINE_PER_CPU(unsigned long, process_counts) = 0;
 
 __cacheline_aligned DEFINE_RWLOCK(tasklist_lock);  /* outer */
 
+#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)
 {
 	int cpu;
@@ -328,15 +336,17 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
 		if (!tmp)
 			goto fail_nomem;
 		*tmp = *mpnt;
+		INIT_LIST_HEAD(&tmp->anon_vma_chain);
 		pol = mpol_dup(vma_policy(mpnt));
 		retval = PTR_ERR(pol);
 		if (IS_ERR(pol))
 			goto fail_nomem_policy;
 		vma_set_policy(tmp, pol);
+		if (anon_vma_fork(tmp, mpnt))
+			goto fail_nomem_anon_vma_fork;
 		tmp->vm_flags &= ~VM_LOCKED;
 		tmp->vm_mm = mm;
 		tmp->vm_next = NULL;
-		anon_vma_link(tmp);
 		file = tmp->vm_file;
 		if (file) {
 			struct inode *inode = file->f_path.dentry->d_inode;
@@ -391,6 +401,8 @@ out:
 	flush_tlb_mm(oldmm);
 	up_write(&oldmm->mmap_sem);
 	return retval;
+fail_nomem_anon_vma_fork:
+	mpol_put(pol);
 fail_nomem_policy:
 	kmem_cache_free(vm_area_cachep, tmp);
 fail_nomem:
@@ -454,8 +466,7 @@ static struct mm_struct * mm_init(struct mm_struct * mm, struct task_struct *p)
 		(current->mm->flags & MMF_INIT_MASK) : default_dump_filter;
 	mm->core_state = NULL;
 	mm->nr_ptes = 0;
-	set_mm_counter(mm, file_rss, 0);
-	set_mm_counter(mm, anon_rss, 0);
+	memset(&mm->rss_stat, 0, sizeof(mm->rss_stat));
 	spin_lock_init(&mm->page_table_lock);
 	mm->free_area_cache = TASK_UNMAPPED_BASE;
 	mm->cached_hole_size = ~0UL;
@@ -824,23 +835,14 @@ void __cleanup_sighand(struct sighand_struct *sighand)
  */
 static void posix_cpu_timers_init_group(struct signal_struct *sig)
 {
+	unsigned long cpu_limit;
+
 	/* 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;
-
-	if (sig->rlim[RLIMIT_CPU].rlim_cur != RLIM_INFINITY) {
-		sig->cputime_expires.prof_exp =
-			secs_to_cputime(sig->rlim[RLIMIT_CPU].rlim_cur);
+	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);
 		sig->cputimer.running = 1;
 	}
 
@@ -857,7 +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;
@@ -865,46 +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;
@@ -1033,7 +1010,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 #endif
 	retval = -EAGAIN;
 	if (atomic_read(&p->real_cred->user->processes) >=
-			p->signal->rlim[RLIMIT_NPROC].rlim_cur) {
+			task_rlimit(p, RLIMIT_NPROC)) {
 		if (!capable(CAP_SYS_ADMIN) && !capable(CAP_SYS_RESOURCE) &&
 		    p->real_cred->user != INIT_USER)
 			goto bad_fork_free;
@@ -1075,6 +1052,9 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	p->prev_utime = cputime_zero;
 	p->prev_stime = cputime_zero;
 #endif
+#if defined(SPLIT_RSS_COUNTING)
+	memset(&p->rss_stat, 0, sizeof(p->rss_stat));
+#endif
 
 	p->default_timer_slack_ns = current->timer_slack_ns;
 
@@ -1241,21 +1221,6 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	/* Need tasklist lock for parent etc handling! */
 	write_lock_irq(&tasklist_lock);
 
-	/*
-	 * The task hasn't been attached yet, so its cpus_allowed mask will
-	 * not be changed, nor will its assigned CPU.
-	 *
-	 * The cpus_allowed mask of the parent may have changed after it was
-	 * copied first time - so re-copy it here, then check the child's CPU
-	 * to ensure it is on a valid CPU (and if not, just force it back to
-	 * parent's CPU). This avoids alot of nasty races.
-	 */
-	p->cpus_allowed = current->cpus_allowed;
-	p->rt.nr_cpus_allowed = current->rt.nr_cpus_allowed;
-	if (unlikely(!cpu_isset(task_cpu(p), p->cpus_allowed) ||
-			!cpu_online(task_cpu(p))))
-		set_task_cpu(p, smp_processor_id());
-
 	/* CLONE_PARENT re-uses the old parent */
 	if (clone_flags & (CLONE_PARENT|CLONE_THREAD)) {
 		p->real_parent = current->real_parent;
diff --git a/kernel/futex.c b/kernel/futex.c
index d9b3a2228f9..e7a35f1039e 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -530,8 +530,25 @@ lookup_pi_state(u32 uval, struct futex_hash_bucket *hb,
 				return -EINVAL;
 
 			WARN_ON(!atomic_read(&pi_state->refcount));
-			WARN_ON(pid && pi_state->owner &&
-				pi_state->owner->pid != pid);
+
+			/*
+			 * When pi_state->owner is NULL then the owner died
+			 * and another waiter is on the fly. pi_state->owner
+			 * is fixed up by the task which acquires
+			 * pi_state->rt_mutex.
+			 *
+			 * We do not check for pid == 0 which can happen when
+			 * the owner died and robust_list_exit() cleared the
+			 * TID.
+			 */
+			if (pid && pi_state->owner) {
+				/*
+				 * Bail out if user space manipulated the
+				 * futex value.
+				 */
+				if (pid != task_pid_vnr(pi_state->owner))
+					return -EINVAL;
+			}
 
 			atomic_inc(&pi_state->refcount);
 			*ps = pi_state;
@@ -758,6 +775,13 @@ static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_q *this)
 	if (!pi_state)
 		return -EINVAL;
 
+	/*
+	 * If current does not own the pi_state then the futex is
+	 * inconsistent and user space fiddled with the futex value.
+	 */
+	if (pi_state->owner != current)
+		return -EINVAL;
+
 	raw_spin_lock(&pi_state->pi_mutex.wait_lock);
 	new_owner = rt_mutex_next_owner(&pi_state->pi_mutex);
 
@@ -1971,7 +1995,7 @@ retry_private:
 	/* Unqueue and drop the lock */
 	unqueue_me_pi(&q);
 
-	goto out;
+	goto out_put_key;
 
 out_unlock_put_key:
 	queue_unlock(&q, hb);
diff --git a/kernel/futex_compat.c b/kernel/futex_compat.c
index 235716556bf..d49afb2395e 100644
--- a/kernel/futex_compat.c
+++ b/kernel/futex_compat.c
@@ -146,7 +146,7 @@ compat_sys_get_robust_list(int pid, compat_uptr_t __user *head_ptr,
 		struct task_struct *p;
 
 		ret = -ESRCH;
-		read_lock(&tasklist_lock);
+		rcu_read_lock();
 		p = find_task_by_vpid(pid);
 		if (!p)
 			goto err_unlock;
@@ -157,7 +157,7 @@ compat_sys_get_robust_list(int pid, compat_uptr_t __user *head_ptr,
 		    !capable(CAP_SYS_PTRACE))
 			goto err_unlock;
 		head = p->compat_robust_list;
-		read_unlock(&tasklist_lock);
+		rcu_read_unlock();
 	}
 
 	if (put_user(sizeof(*head), len_ptr))
@@ -165,7 +165,7 @@ compat_sys_get_robust_list(int pid, compat_uptr_t __user *head_ptr,
 	return put_user(ptr_to_compat(head), head_ptr);
 
 err_unlock:
-	read_unlock(&tasklist_lock);
+	rcu_read_unlock();
 
 	return ret;
 }
diff --git a/kernel/hw_breakpoint.c b/kernel/hw_breakpoint.c
index c030ae657f2..03808ed342a 100644
--- a/kernel/hw_breakpoint.c
+++ b/kernel/hw_breakpoint.c
@@ -243,38 +243,70 @@ static void toggle_bp_slot(struct perf_event *bp, bool enable)
  *       ((per_cpu(nr_bp_flexible, *) > 1) + max(per_cpu(nr_cpu_bp_pinned, *))
  *            + max(per_cpu(nr_task_bp_pinned, *))) < HBP_NUM
  */
-int reserve_bp_slot(struct perf_event *bp)
+static int __reserve_bp_slot(struct perf_event *bp)
 {
 	struct bp_busy_slots slots = {0};
-	int ret = 0;
-
-	mutex_lock(&nr_bp_mutex);
 
 	fetch_bp_busy_slots(&slots, bp);
 
 	/* Flexible counters need to keep at least one slot */
-	if (slots.pinned + (!!slots.flexible) == HBP_NUM) {
-		ret = -ENOSPC;
-		goto end;
-	}
+	if (slots.pinned + (!!slots.flexible) == HBP_NUM)
+		return -ENOSPC;
 
 	toggle_bp_slot(bp, true);
 
-end:
+	return 0;
+}
+
+int reserve_bp_slot(struct perf_event *bp)
+{
+	int ret;
+
+	mutex_lock(&nr_bp_mutex);
+
+	ret = __reserve_bp_slot(bp);
+
 	mutex_unlock(&nr_bp_mutex);
 
 	return ret;
 }
 
+static void __release_bp_slot(struct perf_event *bp)
+{
+	toggle_bp_slot(bp, false);
+}
+
 void release_bp_slot(struct perf_event *bp)
 {
 	mutex_lock(&nr_bp_mutex);
 
-	toggle_bp_slot(bp, false);
+	__release_bp_slot(bp);
 
 	mutex_unlock(&nr_bp_mutex);
 }
 
+/*
+ * Allow the kernel debugger to reserve breakpoint slots without
+ * taking a lock using the dbg_* variant of for the reserve and
+ * release breakpoint slots.
+ */
+int dbg_reserve_bp_slot(struct perf_event *bp)
+{
+	if (mutex_is_locked(&nr_bp_mutex))
+		return -1;
+
+	return __reserve_bp_slot(bp);
+}
+
+int dbg_release_bp_slot(struct perf_event *bp)
+{
+	if (mutex_is_locked(&nr_bp_mutex))
+		return -1;
+
+	__release_bp_slot(bp);
+
+	return 0;
+}
 
 int register_perf_hw_breakpoint(struct perf_event *bp)
 {
@@ -328,8 +360,8 @@ EXPORT_SYMBOL_GPL(register_user_hw_breakpoint);
 int modify_user_hw_breakpoint(struct perf_event *bp, struct perf_event_attr *attr)
 {
 	u64 old_addr = bp->attr.bp_addr;
+	u64 old_len = bp->attr.bp_len;
 	int old_type = bp->attr.bp_type;
-	int old_len = bp->attr.bp_len;
 	int err = 0;
 
 	perf_event_disable(bp);
@@ -381,17 +413,17 @@ EXPORT_SYMBOL_GPL(unregister_hw_breakpoint);
  *
  * @return a set of per_cpu pointers to perf events
  */
-struct perf_event **
+struct perf_event * __percpu *
 register_wide_hw_breakpoint(struct perf_event_attr *attr,
 			    perf_overflow_handler_t triggered)
 {
-	struct perf_event **cpu_events, **pevent, *bp;
+	struct perf_event * __percpu *cpu_events, **pevent, *bp;
 	long err;
 	int cpu;
 
 	cpu_events = alloc_percpu(typeof(*cpu_events));
 	if (!cpu_events)
-		return ERR_PTR(-ENOMEM);
+		return (void __percpu __force *)ERR_PTR(-ENOMEM);
 
 	get_online_cpus();
 	for_each_online_cpu(cpu) {
@@ -419,7 +451,7 @@ fail:
 	put_online_cpus();
 
 	free_percpu(cpu_events);
-	return ERR_PTR(err);
+	return (void __percpu __force *)ERR_PTR(err);
 }
 EXPORT_SYMBOL_GPL(register_wide_hw_breakpoint);
 
@@ -427,7 +459,7 @@ EXPORT_SYMBOL_GPL(register_wide_hw_breakpoint);
  * unregister_wide_hw_breakpoint - unregister a wide breakpoint in the kernel
  * @cpu_events: the per cpu set of events to unregister
  */
-void unregister_wide_hw_breakpoint(struct perf_event **cpu_events)
+void unregister_wide_hw_breakpoint(struct perf_event * __percpu *cpu_events)
 {
 	int cpu;
 	struct perf_event **pevent;
@@ -457,5 +489,4 @@ struct pmu perf_ops_bp = {
 	.enable		= arch_install_hw_breakpoint,
 	.disable	= arch_uninstall_hw_breakpoint,
 	.read		= hw_breakpoint_pmu_read,
-	.unthrottle	= hw_breakpoint_pmu_unthrottle
 };
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index ecc3fa28f66..b7091d5ca2f 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -18,11 +18,7 @@
 
 #include "internals.h"
 
-/**
- *	dynamic_irq_init - initialize a dynamically allocated irq
- *	@irq:	irq number to initialize
- */
-void dynamic_irq_init(unsigned int irq)
+static void dynamic_irq_init_x(unsigned int irq, bool keep_chip_data)
 {
 	struct irq_desc *desc;
 	unsigned long flags;
@@ -41,7 +37,8 @@ void dynamic_irq_init(unsigned int irq)
 	desc->depth = 1;
 	desc->msi_desc = NULL;
 	desc->handler_data = NULL;
-	desc->chip_data = NULL;
+	if (!keep_chip_data)
+		desc->chip_data = NULL;
 	desc->action = NULL;
 	desc->irq_count = 0;
 	desc->irqs_unhandled = 0;
@@ -55,10 +52,26 @@ void dynamic_irq_init(unsigned int irq)
 }
 
 /**
- *	dynamic_irq_cleanup - cleanup a dynamically allocated irq
+ *	dynamic_irq_init - initialize a dynamically allocated irq
  *	@irq:	irq number to initialize
  */
-void dynamic_irq_cleanup(unsigned int irq)
+void dynamic_irq_init(unsigned int irq)
+{
+	dynamic_irq_init_x(irq, false);
+}
+
+/**
+ *	dynamic_irq_init_keep_chip_data - initialize a dynamically allocated irq
+ *	@irq:	irq number to initialize
+ *
+ *	does not set irq_to_desc(irq)->chip_data to NULL
+ */
+void dynamic_irq_init_keep_chip_data(unsigned int irq)
+{
+	dynamic_irq_init_x(irq, true);
+}
+
+static void dynamic_irq_cleanup_x(unsigned int irq, bool keep_chip_data)
 {
 	struct irq_desc *desc = irq_to_desc(irq);
 	unsigned long flags;
@@ -77,7 +90,8 @@ void dynamic_irq_cleanup(unsigned int irq)
 	}
 	desc->msi_desc = NULL;
 	desc->handler_data = NULL;
-	desc->chip_data = NULL;
+	if (!keep_chip_data)
+		desc->chip_data = NULL;
 	desc->handle_irq = handle_bad_irq;
 	desc->chip = &no_irq_chip;
 	desc->name = NULL;
@@ -85,6 +99,26 @@ void dynamic_irq_cleanup(unsigned int irq)
 	raw_spin_unlock_irqrestore(&desc->lock, flags);
 }
 
+/**
+ *	dynamic_irq_cleanup - cleanup a dynamically allocated irq
+ *	@irq:	irq number to initialize
+ */
+void dynamic_irq_cleanup(unsigned int irq)
+{
+	dynamic_irq_cleanup_x(irq, false);
+}
+
+/**
+ *	dynamic_irq_cleanup_keep_chip_data - cleanup a dynamically allocated irq
+ *	@irq:	irq number to initialize
+ *
+ *	does not set irq_to_desc(irq)->chip_data to NULL
+ */
+void dynamic_irq_cleanup_keep_chip_data(unsigned int irq)
+{
+	dynamic_irq_cleanup_x(irq, true);
+}
+
 
 /**
  *	set_irq_chip - set the irq chip for an irq
@@ -325,6 +359,23 @@ static inline void mask_ack_irq(struct irq_desc *desc, int irq)
 		if (desc->chip->ack)
 			desc->chip->ack(irq);
 	}
+	desc->status |= IRQ_MASKED;
+}
+
+static inline void mask_irq(struct irq_desc *desc, int irq)
+{
+	if (desc->chip->mask) {
+		desc->chip->mask(irq);
+		desc->status |= IRQ_MASKED;
+	}
+}
+
+static inline void unmask_irq(struct irq_desc *desc, int irq)
+{
+	if (desc->chip->unmask) {
+		desc->chip->unmask(irq);
+		desc->status &= ~IRQ_MASKED;
+	}
 }
 
 /*
@@ -450,10 +501,8 @@ handle_level_irq(unsigned int irq, struct irq_desc *desc)
 	raw_spin_lock(&desc->lock);
 	desc->status &= ~IRQ_INPROGRESS;
 
-	if (unlikely(desc->status & IRQ_ONESHOT))
-		desc->status |= IRQ_MASKED;
-	else if (!(desc->status & IRQ_DISABLED) && desc->chip->unmask)
-		desc->chip->unmask(irq);
+	if (!(desc->status & (IRQ_DISABLED | IRQ_ONESHOT)))
+		unmask_irq(desc, irq);
 out_unlock:
 	raw_spin_unlock(&desc->lock);
 }
@@ -490,8 +539,7 @@ handle_fasteoi_irq(unsigned int irq, struct irq_desc *desc)
 	action = desc->action;
 	if (unlikely(!action || (desc->status & IRQ_DISABLED))) {
 		desc->status |= IRQ_PENDING;
-		if (desc->chip->mask)
-			desc->chip->mask(irq);
+		mask_irq(desc, irq);
 		goto out;
 	}
 
@@ -520,7 +568,7 @@ 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
@@ -559,7 +607,7 @@ handle_edge_irq(unsigned int irq, struct irq_desc *desc)
 		irqreturn_t action_ret;
 
 		if (unlikely(!action)) {
-			desc->chip->mask(irq);
+			mask_irq(desc, irq);
 			goto out_unlock;
 		}
 
@@ -571,8 +619,7 @@ handle_edge_irq(unsigned int irq, struct irq_desc *desc)
 		if (unlikely((desc->status &
 			       (IRQ_PENDING | IRQ_MASKED | IRQ_DISABLED)) ==
 			      (IRQ_PENDING | IRQ_MASKED))) {
-			desc->chip->unmask(irq);
-			desc->status &= ~IRQ_MASKED;
+			unmask_irq(desc, irq);
 		}
 
 		desc->status &= ~IRQ_PENDING;
@@ -682,7 +729,7 @@ set_irq_chip_and_handler_name(unsigned int irq, struct irq_chip *chip,
 	__set_irq_handler(irq, handle, 0, name);
 }
 
-void __init set_irq_noprobe(unsigned int irq)
+void set_irq_noprobe(unsigned int irq)
 {
 	struct irq_desc *desc = irq_to_desc(irq);
 	unsigned long flags;
@@ -697,7 +744,7 @@ void __init set_irq_noprobe(unsigned int irq)
 	raw_spin_unlock_irqrestore(&desc->lock, flags);
 }
 
-void __init set_irq_probe(unsigned int irq)
+void set_irq_probe(unsigned int irq)
 {
 	struct irq_desc *desc = irq_to_desc(irq);
 	unsigned long flags;
diff --git a/kernel/irq/devres.c b/kernel/irq/devres.c
index d06df9c41cb..1ef4ffcdfa5 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/irq/handle.c b/kernel/irq/handle.c
index 814940e7f48..76d5a671bfe 100644
--- a/kernel/irq/handle.c
+++ b/kernel/irq/handle.c
@@ -19,7 +19,7 @@
 #include <linux/kernel_stat.h>
 #include <linux/rculist.h>
 #include <linux/hash.h>
-#include <linux/bootmem.h>
+#include <linux/radix-tree.h>
 #include <trace/events/irq.h>
 
 #include "internals.h"
@@ -87,12 +87,8 @@ void __ref init_kstat_irqs(struct irq_desc *desc, int node, int nr)
 {
 	void *ptr;
 
-	if (slab_is_available())
-		ptr = kzalloc_node(nr * sizeof(*desc->kstat_irqs),
-				   GFP_ATOMIC, node);
-	else
-		ptr = alloc_bootmem_node(NODE_DATA(node),
-				nr * sizeof(*desc->kstat_irqs));
+	ptr = kzalloc_node(nr * sizeof(*desc->kstat_irqs),
+			   GFP_ATOMIC, node);
 
 	/*
 	 * don't overwite if can not get new one
@@ -132,7 +128,26 @@ static void init_one_irq_desc(int irq, struct irq_desc *desc, int node)
  */
 DEFINE_RAW_SPINLOCK(sparse_irq_lock);
 
-struct irq_desc **irq_desc_ptrs __read_mostly;
+static RADIX_TREE(irq_desc_tree, GFP_ATOMIC);
+
+static void set_irq_desc(unsigned int irq, struct irq_desc *desc)
+{
+	radix_tree_insert(&irq_desc_tree, irq, desc);
+}
+
+struct irq_desc *irq_to_desc(unsigned int irq)
+{
+	return radix_tree_lookup(&irq_desc_tree, irq);
+}
+
+void replace_irq_desc(unsigned int irq, struct irq_desc *desc)
+{
+	void **ptr;
+
+	ptr = radix_tree_lookup_slot(&irq_desc_tree, irq);
+	if (ptr)
+		radix_tree_replace_slot(ptr, desc);
+}
 
 static struct irq_desc irq_desc_legacy[NR_IRQS_LEGACY] __cacheline_aligned_in_smp = {
 	[0 ... NR_IRQS_LEGACY-1] = {
@@ -164,9 +179,6 @@ int __init early_irq_init(void)
 	legacy_count = ARRAY_SIZE(irq_desc_legacy);
 	node = first_online_node;
 
-	/* allocate irq_desc_ptrs array based on nr_irqs */
-	irq_desc_ptrs = kcalloc(nr_irqs, sizeof(void *), GFP_NOWAIT);
-
 	/* allocate based on nr_cpu_ids */
 	kstat_irqs_legacy = kzalloc_node(NR_IRQS_LEGACY * nr_cpu_ids *
 					  sizeof(int), GFP_NOWAIT, node);
@@ -180,23 +192,12 @@ int __init early_irq_init(void)
 		lockdep_set_class(&desc[i].lock, &irq_desc_lock_class);
 		alloc_desc_masks(&desc[i], node, true);
 		init_desc_masks(&desc[i]);
-		irq_desc_ptrs[i] = desc + i;
+		set_irq_desc(i, &desc[i]);
 	}
 
-	for (i = legacy_count; i < nr_irqs; i++)
-		irq_desc_ptrs[i] = NULL;
-
 	return arch_early_irq_init();
 }
 
-struct irq_desc *irq_to_desc(unsigned int irq)
-{
-	if (irq_desc_ptrs && irq < nr_irqs)
-		return irq_desc_ptrs[irq];
-
-	return NULL;
-}
-
 struct irq_desc * __ref irq_to_desc_alloc_node(unsigned int irq, int node)
 {
 	struct irq_desc *desc;
@@ -208,21 +209,18 @@ struct irq_desc * __ref irq_to_desc_alloc_node(unsigned int irq, int node)
 		return NULL;
 	}
 
-	desc = irq_desc_ptrs[irq];
+	desc = irq_to_desc(irq);
 	if (desc)
 		return desc;
 
 	raw_spin_lock_irqsave(&sparse_irq_lock, flags);
 
 	/* We have to check it to avoid races with another CPU */
-	desc = irq_desc_ptrs[irq];
+	desc = irq_to_desc(irq);
 	if (desc)
 		goto out_unlock;
 
-	if (slab_is_available())
-		desc = kzalloc_node(sizeof(*desc), GFP_ATOMIC, node);
-	else
-		desc = alloc_bootmem_node(NODE_DATA(node), sizeof(*desc));
+	desc = kzalloc_node(sizeof(*desc), GFP_ATOMIC, node);
 
 	printk(KERN_DEBUG "  alloc irq_desc for %d on node %d\n", irq, node);
 	if (!desc) {
@@ -231,7 +229,7 @@ struct irq_desc * __ref irq_to_desc_alloc_node(unsigned int irq, int node)
 	}
 	init_one_irq_desc(irq, desc, node);
 
-	irq_desc_ptrs[irq] = desc;
+	set_irq_desc(irq, desc);
 
 out_unlock:
 	raw_spin_unlock_irqrestore(&sparse_irq_lock, flags);
diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h
index b2821f070a3..c63f3bc88f0 100644
--- a/kernel/irq/internals.h
+++ b/kernel/irq/internals.h
@@ -21,11 +21,7 @@ extern void clear_kstat_irqs(struct irq_desc *desc);
 extern raw_spinlock_t sparse_irq_lock;
 
 #ifdef CONFIG_SPARSE_IRQ
-/* irq_desc_ptrs allocated at boot time */
-extern struct irq_desc **irq_desc_ptrs;
-#else
-/* irq_desc_ptrs is a fixed size array */
-extern struct irq_desc *irq_desc_ptrs[NR_IRQS];
+void replace_irq_desc(unsigned int irq, struct irq_desc *desc);
 #endif
 
 #ifdef CONFIG_PROC_FS
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index eb6078ca60c..704e488730a 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -382,6 +382,7 @@ int can_request_irq(unsigned int irq, unsigned long irqflags)
 {
 	struct irq_desc *desc = irq_to_desc(irq);
 	struct irqaction *action;
+	unsigned long flags;
 
 	if (!desc)
 		return 0;
@@ -389,11 +390,14 @@ int can_request_irq(unsigned int irq, unsigned long irqflags)
 	if (desc->status & IRQ_NOREQUEST)
 		return 0;
 
+	raw_spin_lock_irqsave(&desc->lock, flags);
 	action = desc->action;
 	if (action)
 		if (irqflags & action->flags & IRQF_SHARED)
 			action = NULL;
 
+	raw_spin_unlock_irqrestore(&desc->lock, flags);
+
 	return !action;
 }
 
@@ -483,8 +487,26 @@ static int irq_wait_for_interrupt(struct irqaction *action)
  */
 static void irq_finalize_oneshot(unsigned int irq, struct irq_desc *desc)
 {
+again:
 	chip_bus_lock(irq, desc);
 	raw_spin_lock_irq(&desc->lock);
+
+	/*
+	 * Implausible though it may be we need to protect us against
+	 * the following scenario:
+	 *
+	 * The thread is faster done than the hard interrupt handler
+	 * on the other CPU. If we unmask the irq line then the
+	 * interrupt can come in again and masks the line, leaves due
+	 * to IRQ_INPROGRESS and the irq line is masked forever.
+	 */
+	if (unlikely(desc->status & IRQ_INPROGRESS)) {
+		raw_spin_unlock_irq(&desc->lock);
+		chip_bus_sync_unlock(irq, desc);
+		cpu_relax();
+		goto again;
+	}
+
 	if (!(desc->status & IRQ_DISABLED) && (desc->status & IRQ_MASKED)) {
 		desc->status &= ~IRQ_MASKED;
 		desc->chip->unmask(irq);
@@ -735,6 +757,16 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 		if (new->flags & IRQF_ONESHOT)
 			desc->status |= IRQ_ONESHOT;
 
+		/*
+		 * Force MSI interrupts to run with interrupts
+		 * disabled. The multi vector cards can cause stack
+		 * overflows due to nested interrupts when enough of
+		 * them are directed to a core and fire at the same
+		 * time.
+		 */
+		if (desc->msi_desc)
+			new->flags |= IRQF_DISABLED;
+
 		if (!(desc->status & IRQ_NOAUTOEN)) {
 			desc->depth = 0;
 			desc->status &= ~IRQ_DISABLED;
diff --git a/kernel/irq/numa_migrate.c b/kernel/irq/numa_migrate.c
index 26bac9d8f86..65d3845665a 100644
--- a/kernel/irq/numa_migrate.c
+++ b/kernel/irq/numa_migrate.c
@@ -6,6 +6,7 @@
  */
 
 #include <linux/irq.h>
+#include <linux/slab.h>
 #include <linux/module.h>
 #include <linux/random.h>
 #include <linux/interrupt.h>
@@ -70,7 +71,7 @@ static struct irq_desc *__real_move_irq_desc(struct irq_desc *old_desc,
 	raw_spin_lock_irqsave(&sparse_irq_lock, flags);
 
 	/* We have to check it to avoid races with another CPU */
-	desc = irq_desc_ptrs[irq];
+	desc = irq_to_desc(irq);
 
 	if (desc && old_desc != desc)
 		goto out_unlock;
@@ -90,7 +91,7 @@ static struct irq_desc *__real_move_irq_desc(struct irq_desc *old_desc,
 		goto out_unlock;
 	}
 
-	irq_desc_ptrs[irq] = desc;
+	replace_irq_desc(irq, desc);
 	raw_spin_unlock_irqrestore(&sparse_irq_lock, flags);
 
 	/* free the old one */
diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c
index 6f50eccc79c..7a6eb04ef6b 100644
--- a/kernel/irq/proc.c
+++ b/kernel/irq/proc.c
@@ -7,6 +7,7 @@
  */
 
 #include <linux/irq.h>
+#include <linux/gfp.h>
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
 #include <linux/interrupt.h>
diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c
index 8e5288a8a35..13aff293f4d 100644
--- a/kernel/kallsyms.c
+++ b/kernel/kallsyms.c
@@ -21,6 +21,7 @@
 #include <linux/sched.h>	/* for cond_resched */
 #include <linux/mm.h>
 #include <linux/ctype.h>
+#include <linux/slab.h>
 
 #include <asm/sections.h>
 
diff --git a/kernel/kexec.c b/kernel/kexec.c
index ef077fb7315..87ebe8adc47 100644
--- a/kernel/kexec.c
+++ b/kernel/kexec.c
@@ -41,7 +41,7 @@
 #include <asm/sections.h>
 
 /* Per cpu memory for storing cpu states in case of system crash. */
-note_buf_t* crash_notes;
+note_buf_t __percpu *crash_notes;
 
 /* vmcoreinfo stuff */
 static unsigned char vmcoreinfo_data[VMCOREINFO_BYTES];
diff --git a/kernel/kfifo.c b/kernel/kfifo.c
index 32c5c15d750..35edbe22e9a 100644
--- a/kernel/kfifo.c
+++ b/kernel/kfifo.c
@@ -80,7 +80,7 @@ int kfifo_alloc(struct kfifo *fifo, unsigned int size, gfp_t gfp_mask)
 
 	buffer = kmalloc(size, gfp_mask);
 	if (!buffer) {
-		_kfifo_init(fifo, 0, 0);
+		_kfifo_init(fifo, NULL, 0);
 		return -ENOMEM;
 	}
 
@@ -97,6 +97,7 @@ EXPORT_SYMBOL(kfifo_alloc);
 void kfifo_free(struct kfifo *fifo)
 {
 	kfree(fifo->buffer);
+	_kfifo_init(fifo, NULL, 0);
 }
 EXPORT_SYMBOL(kfifo_free);
 
@@ -349,6 +350,7 @@ EXPORT_SYMBOL(__kfifo_from_user_n);
  * @fifo: the fifo to be used.
  * @from: pointer to the data to be added.
  * @len: the length of the data to be added.
+ * @total: the actual returned data length.
  *
  * This function copies at most @len bytes from the @from into the
  * FIFO depending and returns -EFAULT/0.
@@ -399,7 +401,7 @@ EXPORT_SYMBOL(__kfifo_to_user_n);
  * @fifo: the fifo to be used.
  * @to: where the data must be copied.
  * @len: the size of the destination buffer.
- @ @lenout: pointer to output variable with copied data
+ * @lenout: pointer to output variable with copied data
  *
  * This function copies at most @len bytes from the FIFO into the
  * @to buffer and 0 or -EFAULT.
diff --git a/kernel/kgdb.c b/kernel/kgdb.c
index 2eb517e2351..11f3515ca83 100644
--- a/kernel/kgdb.c
+++ b/kernel/kgdb.c
@@ -69,9 +69,16 @@ struct kgdb_state {
 	struct pt_regs		*linux_regs;
 };
 
+/* Exception state values */
+#define DCPU_WANT_MASTER 0x1 /* Waiting to become a master kgdb cpu */
+#define DCPU_NEXT_MASTER 0x2 /* Transition from one master cpu to another */
+#define DCPU_IS_SLAVE    0x4 /* Slave cpu enter exception */
+#define DCPU_SSTEP       0x8 /* CPU is single stepping */
+
 static struct debuggerinfo_struct {
 	void			*debuggerinfo;
 	struct task_struct	*task;
+	int 			exception_state;
 } kgdb_info[NR_CPUS];
 
 /**
@@ -391,27 +398,22 @@ int kgdb_mem2hex(char *mem, char *buf, int count)
 
 /*
  * Copy the binary array pointed to by buf into mem.  Fix $, #, and
- * 0x7d escaped with 0x7d.  Return a pointer to the character after
- * the last byte written.
+ * 0x7d escaped with 0x7d. Return -EFAULT on failure or 0 on success.
+ * The input buf is overwitten with the result to write to mem.
  */
 static int kgdb_ebin2mem(char *buf, char *mem, int count)
 {
-	int err = 0;
-	char c;
+	int size = 0;
+	char *c = buf;
 
 	while (count-- > 0) {
-		c = *buf++;
-		if (c == 0x7d)
-			c = *buf++ ^ 0x20;
-
-		err = probe_kernel_write(mem, &c, 1);
-		if (err)
-			break;
-
-		mem++;
+		c[size] = *buf++;
+		if (c[size] == 0x7d)
+			c[size] = *buf++ ^ 0x20;
+		size++;
 	}
 
-	return err;
+	return probe_kernel_write(mem, c, size);
 }
 
 /*
@@ -563,46 +565,6 @@ static struct task_struct *getthread(struct pt_regs *regs, int tid)
 }
 
 /*
- * CPU debug state control:
- */
-
-#ifdef CONFIG_SMP
-static void kgdb_wait(struct pt_regs *regs)
-{
-	unsigned long flags;
-	int cpu;
-
-	local_irq_save(flags);
-	cpu = raw_smp_processor_id();
-	kgdb_info[cpu].debuggerinfo = regs;
-	kgdb_info[cpu].task = current;
-	/*
-	 * Make sure the above info reaches the primary CPU before
-	 * our cpu_in_kgdb[] flag setting does:
-	 */
-	smp_wmb();
-	atomic_set(&cpu_in_kgdb[cpu], 1);
-
-	/* Wait till primary CPU is done with debugging */
-	while (atomic_read(&passive_cpu_wait[cpu]))
-		cpu_relax();
-
-	kgdb_info[cpu].debuggerinfo = NULL;
-	kgdb_info[cpu].task = NULL;
-
-	/* fix up hardware debug registers on local cpu */
-	if (arch_kgdb_ops.correct_hw_break)
-		arch_kgdb_ops.correct_hw_break();
-
-	/* Signal the primary CPU that we are done: */
-	atomic_set(&cpu_in_kgdb[cpu], 0);
-	touch_softlockup_watchdog();
-	clocksource_touch_watchdog();
-	local_irq_restore(flags);
-}
-#endif
-
-/*
  * Some architectures need cache flushes when we set/clear a
  * breakpoint:
  */
@@ -1397,34 +1359,13 @@ static int kgdb_reenter_check(struct kgdb_state *ks)
 	return 1;
 }
 
-/*
- * kgdb_handle_exception() - main entry point from a kernel exception
- *
- * Locking hierarchy:
- *	interface locks, if any (begin_session)
- *	kgdb lock (kgdb_active)
- */
-int
-kgdb_handle_exception(int evector, int signo, int ecode, struct pt_regs *regs)
+static int kgdb_cpu_enter(struct kgdb_state *ks, struct pt_regs *regs)
 {
-	struct kgdb_state kgdb_var;
-	struct kgdb_state *ks = &kgdb_var;
 	unsigned long flags;
 	int sstep_tries = 100;
 	int error = 0;
 	int i, cpu;
-
-	ks->cpu			= raw_smp_processor_id();
-	ks->ex_vector		= evector;
-	ks->signo		= signo;
-	ks->ex_vector		= evector;
-	ks->err_code		= ecode;
-	ks->kgdb_usethreadid	= 0;
-	ks->linux_regs		= regs;
-
-	if (kgdb_reenter_check(ks))
-		return 0; /* Ouch, double exception ! */
-
+	int trace_on = 0;
 acquirelock:
 	/*
 	 * Interrupts will be restored by the 'trap return' code, except when
@@ -1432,13 +1373,43 @@ acquirelock:
 	 */
 	local_irq_save(flags);
 
-	cpu = raw_smp_processor_id();
+	cpu = ks->cpu;
+	kgdb_info[cpu].debuggerinfo = regs;
+	kgdb_info[cpu].task = current;
+	/*
+	 * Make sure the above info reaches the primary CPU before
+	 * our cpu_in_kgdb[] flag setting does:
+	 */
+	atomic_inc(&cpu_in_kgdb[cpu]);
 
 	/*
-	 * Acquire the kgdb_active lock:
+	 * CPU will loop if it is a slave or request to become a kgdb
+	 * master cpu and acquire the kgdb_active lock:
 	 */
-	while (atomic_cmpxchg(&kgdb_active, -1, cpu) != -1)
+	while (1) {
+		if (kgdb_info[cpu].exception_state & DCPU_WANT_MASTER) {
+			if (atomic_cmpxchg(&kgdb_active, -1, cpu) == cpu)
+				break;
+		} else if (kgdb_info[cpu].exception_state & DCPU_IS_SLAVE) {
+			if (!atomic_read(&passive_cpu_wait[cpu]))
+				goto return_normal;
+		} else {
+return_normal:
+			/* Return to normal operation by executing any
+			 * hw breakpoint fixup.
+			 */
+			if (arch_kgdb_ops.correct_hw_break)
+				arch_kgdb_ops.correct_hw_break();
+			if (trace_on)
+				tracing_on();
+			atomic_dec(&cpu_in_kgdb[cpu]);
+			touch_softlockup_watchdog_sync();
+			clocksource_touch_watchdog();
+			local_irq_restore(flags);
+			return 0;
+		}
 		cpu_relax();
+	}
 
 	/*
 	 * For single stepping, try to only enter on the processor
@@ -1450,7 +1421,7 @@ acquirelock:
 	    (kgdb_info[cpu].task &&
 	     kgdb_info[cpu].task->pid != kgdb_sstep_pid) && --sstep_tries) {
 		atomic_set(&kgdb_active, -1);
-		touch_softlockup_watchdog();
+		touch_softlockup_watchdog_sync();
 		clocksource_touch_watchdog();
 		local_irq_restore(flags);
 
@@ -1472,9 +1443,6 @@ acquirelock:
 	if (kgdb_io_ops->pre_exception)
 		kgdb_io_ops->pre_exception();
 
-	kgdb_info[ks->cpu].debuggerinfo = ks->linux_regs;
-	kgdb_info[ks->cpu].task = current;
-
 	kgdb_disable_hw_debug(ks->linux_regs);
 
 	/*
@@ -1483,15 +1451,9 @@ acquirelock:
 	 */
 	if (!kgdb_single_step) {
 		for (i = 0; i < NR_CPUS; i++)
-			atomic_set(&passive_cpu_wait[i], 1);
+			atomic_inc(&passive_cpu_wait[i]);
 	}
 
-	/*
-	 * spin_lock code is good enough as a barrier so we don't
-	 * need one here:
-	 */
-	atomic_set(&cpu_in_kgdb[ks->cpu], 1);
-
 #ifdef CONFIG_SMP
 	/* Signal the other CPUs to enter kgdb_wait() */
 	if ((!kgdb_single_step) && kgdb_do_roundup)
@@ -1515,6 +1477,9 @@ acquirelock:
 	kgdb_single_step = 0;
 	kgdb_contthread = current;
 	exception_level = 0;
+	trace_on = tracing_is_on();
+	if (trace_on)
+		tracing_off();
 
 	/* Talk to debugger with gdbserial protocol */
 	error = gdb_serial_stub(ks);
@@ -1523,13 +1488,11 @@ acquirelock:
 	if (kgdb_io_ops->post_exception)
 		kgdb_io_ops->post_exception();
 
-	kgdb_info[ks->cpu].debuggerinfo = NULL;
-	kgdb_info[ks->cpu].task = NULL;
-	atomic_set(&cpu_in_kgdb[ks->cpu], 0);
+	atomic_dec(&cpu_in_kgdb[ks->cpu]);
 
 	if (!kgdb_single_step) {
 		for (i = NR_CPUS-1; i >= 0; i--)
-			atomic_set(&passive_cpu_wait[i], 0);
+			atomic_dec(&passive_cpu_wait[i]);
 		/*
 		 * Wait till all the CPUs have quit
 		 * from the debugger.
@@ -1548,22 +1511,63 @@ kgdb_restore:
 		else
 			kgdb_sstep_pid = 0;
 	}
+	if (trace_on)
+		tracing_on();
 	/* Free kgdb_active */
 	atomic_set(&kgdb_active, -1);
-	touch_softlockup_watchdog();
+	touch_softlockup_watchdog_sync();
 	clocksource_touch_watchdog();
 	local_irq_restore(flags);
 
 	return error;
 }
 
+/*
+ * kgdb_handle_exception() - main entry point from a kernel exception
+ *
+ * Locking hierarchy:
+ *	interface locks, if any (begin_session)
+ *	kgdb lock (kgdb_active)
+ */
+int
+kgdb_handle_exception(int evector, int signo, int ecode, struct pt_regs *regs)
+{
+	struct kgdb_state kgdb_var;
+	struct kgdb_state *ks = &kgdb_var;
+	int ret;
+
+	ks->cpu			= raw_smp_processor_id();
+	ks->ex_vector		= evector;
+	ks->signo		= signo;
+	ks->ex_vector		= evector;
+	ks->err_code		= ecode;
+	ks->kgdb_usethreadid	= 0;
+	ks->linux_regs		= regs;
+
+	if (kgdb_reenter_check(ks))
+		return 0; /* Ouch, double exception ! */
+	kgdb_info[ks->cpu].exception_state |= DCPU_WANT_MASTER;
+	ret = kgdb_cpu_enter(ks, regs);
+	kgdb_info[ks->cpu].exception_state &= ~DCPU_WANT_MASTER;
+	return ret;
+}
+
 int kgdb_nmicallback(int cpu, void *regs)
 {
 #ifdef CONFIG_SMP
+	struct kgdb_state kgdb_var;
+	struct kgdb_state *ks = &kgdb_var;
+
+	memset(ks, 0, sizeof(struct kgdb_state));
+	ks->cpu			= cpu;
+	ks->linux_regs		= regs;
+
 	if (!atomic_read(&cpu_in_kgdb[cpu]) &&
-			atomic_read(&kgdb_active) != cpu &&
-			atomic_read(&cpu_in_kgdb[atomic_read(&kgdb_active)])) {
-		kgdb_wait((struct pt_regs *)regs);
+	    atomic_read(&kgdb_active) != -1 &&
+	    atomic_read(&kgdb_active) != cpu) {
+		kgdb_info[cpu].exception_state |= DCPU_IS_SLAVE;
+		kgdb_cpu_enter(ks, regs);
+		kgdb_info[cpu].exception_state &= ~DCPU_IS_SLAVE;
 		return 0;
 	}
 #endif
@@ -1739,11 +1743,11 @@ EXPORT_SYMBOL_GPL(kgdb_unregister_io_module);
  */
 void kgdb_breakpoint(void)
 {
-	atomic_set(&kgdb_setting_breakpoint, 1);
+	atomic_inc(&kgdb_setting_breakpoint);
 	wmb(); /* Sync point before breakpoint */
 	arch_kgdb_breakpoint();
 	wmb(); /* Sync point after breakpoint */
-	atomic_set(&kgdb_setting_breakpoint, 0);
+	atomic_dec(&kgdb_setting_breakpoint);
 }
 EXPORT_SYMBOL_GPL(kgdb_breakpoint);
 
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index ccec774c716..0ed46f3e51e 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -42,9 +42,11 @@
 #include <linux/freezer.h>
 #include <linux/seq_file.h>
 #include <linux/debugfs.h>
+#include <linux/sysctl.h>
 #include <linux/kdebug.h>
 #include <linux/memory.h>
 #include <linux/ftrace.h>
+#include <linux/cpu.h>
 
 #include <asm-generic/sections.h>
 #include <asm/cacheflush.h>
@@ -105,57 +107,74 @@ static struct kprobe_blackpoint kprobe_blacklist[] = {
  * stepping on the instruction on a vmalloced/kmalloced/data page
  * is a recipe for disaster
  */
-#define INSNS_PER_PAGE	(PAGE_SIZE/(MAX_INSN_SIZE * sizeof(kprobe_opcode_t)))
-
 struct kprobe_insn_page {
 	struct list_head list;
 	kprobe_opcode_t *insns;		/* Page of instruction slots */
-	char slot_used[INSNS_PER_PAGE];
 	int nused;
 	int ngarbage;
+	char slot_used[];
+};
+
+#define KPROBE_INSN_PAGE_SIZE(slots)			\
+	(offsetof(struct kprobe_insn_page, slot_used) +	\
+	 (sizeof(char) * (slots)))
+
+struct kprobe_insn_cache {
+	struct list_head pages;	/* list of kprobe_insn_page */
+	size_t insn_size;	/* size of instruction slot */
+	int nr_garbage;
 };
 
+static int slots_per_page(struct kprobe_insn_cache *c)
+{
+	return PAGE_SIZE/(c->insn_size * sizeof(kprobe_opcode_t));
+}
+
 enum kprobe_slot_state {
 	SLOT_CLEAN = 0,
 	SLOT_DIRTY = 1,
 	SLOT_USED = 2,
 };
 
-static DEFINE_MUTEX(kprobe_insn_mutex);	/* Protects kprobe_insn_pages */
-static LIST_HEAD(kprobe_insn_pages);
-static int kprobe_garbage_slots;
-static int collect_garbage_slots(void);
+static DEFINE_MUTEX(kprobe_insn_mutex);	/* Protects kprobe_insn_slots */
+static struct kprobe_insn_cache kprobe_insn_slots = {
+	.pages = LIST_HEAD_INIT(kprobe_insn_slots.pages),
+	.insn_size = MAX_INSN_SIZE,
+	.nr_garbage = 0,
+};
+static int __kprobes collect_garbage_slots(struct kprobe_insn_cache *c);
 
 /**
  * __get_insn_slot() - Find a slot on an executable page for an instruction.
  * We allocate an executable page if there's no room on existing ones.
  */
-static kprobe_opcode_t __kprobes *__get_insn_slot(void)
+static kprobe_opcode_t __kprobes *__get_insn_slot(struct kprobe_insn_cache *c)
 {
 	struct kprobe_insn_page *kip;
 
  retry:
-	list_for_each_entry(kip, &kprobe_insn_pages, list) {
-		if (kip->nused < INSNS_PER_PAGE) {
+	list_for_each_entry(kip, &c->pages, list) {
+		if (kip->nused < slots_per_page(c)) {
 			int i;
-			for (i = 0; i < INSNS_PER_PAGE; i++) {
+			for (i = 0; i < slots_per_page(c); i++) {
 				if (kip->slot_used[i] == SLOT_CLEAN) {
 					kip->slot_used[i] = SLOT_USED;
 					kip->nused++;
-					return kip->insns + (i * MAX_INSN_SIZE);
+					return kip->insns + (i * c->insn_size);
 				}
 			}
-			/* Surprise!  No unused slots.  Fix kip->nused. */
-			kip->nused = INSNS_PER_PAGE;
+			/* kip->nused is broken. Fix it. */
+			kip->nused = slots_per_page(c);
+			WARN_ON(1);
 		}
 	}
 
 	/* If there are any garbage slots, collect it and try again. */
-	if (kprobe_garbage_slots && collect_garbage_slots() == 0) {
+	if (c->nr_garbage && collect_garbage_slots(c) == 0)
 		goto retry;
-	}
-	/* All out of space.  Need to allocate a new page. Use slot 0. */
-	kip = kmalloc(sizeof(struct kprobe_insn_page), GFP_KERNEL);
+
+	/* All out of space.  Need to allocate a new page. */
+	kip = kmalloc(KPROBE_INSN_PAGE_SIZE(slots_per_page(c)), GFP_KERNEL);
 	if (!kip)
 		return NULL;
 
@@ -170,20 +189,23 @@ static kprobe_opcode_t __kprobes *__get_insn_slot(void)
 		return NULL;
 	}
 	INIT_LIST_HEAD(&kip->list);
-	list_add(&kip->list, &kprobe_insn_pages);
-	memset(kip->slot_used, SLOT_CLEAN, INSNS_PER_PAGE);
+	memset(kip->slot_used, SLOT_CLEAN, slots_per_page(c));
 	kip->slot_used[0] = SLOT_USED;
 	kip->nused = 1;
 	kip->ngarbage = 0;
+	list_add(&kip->list, &c->pages);
 	return kip->insns;
 }
 
+
 kprobe_opcode_t __kprobes *get_insn_slot(void)
 {
-	kprobe_opcode_t *ret;
+	kprobe_opcode_t *ret = NULL;
+
 	mutex_lock(&kprobe_insn_mutex);
-	ret = __get_insn_slot();
+	ret = __get_insn_slot(&kprobe_insn_slots);
 	mutex_unlock(&kprobe_insn_mutex);
+
 	return ret;
 }
 
@@ -199,7 +221,7 @@ static int __kprobes collect_one_slot(struct kprobe_insn_page *kip, int idx)
 		 * so as not to have to set it up again the
 		 * next time somebody inserts a probe.
 		 */
-		if (!list_is_singular(&kprobe_insn_pages)) {
+		if (!list_is_singular(&kip->list)) {
 			list_del(&kip->list);
 			module_free(NULL, kip->insns);
 			kfree(kip);
@@ -209,51 +231,85 @@ static int __kprobes collect_one_slot(struct kprobe_insn_page *kip, int idx)
 	return 0;
 }
 
-static int __kprobes collect_garbage_slots(void)
+static int __kprobes collect_garbage_slots(struct kprobe_insn_cache *c)
 {
 	struct kprobe_insn_page *kip, *next;
 
 	/* Ensure no-one is interrupted on the garbages */
 	synchronize_sched();
 
-	list_for_each_entry_safe(kip, next, &kprobe_insn_pages, list) {
+	list_for_each_entry_safe(kip, next, &c->pages, list) {
 		int i;
 		if (kip->ngarbage == 0)
 			continue;
 		kip->ngarbage = 0;	/* we will collect all garbages */
-		for (i = 0; i < INSNS_PER_PAGE; i++) {
+		for (i = 0; i < slots_per_page(c); i++) {
 			if (kip->slot_used[i] == SLOT_DIRTY &&
 			    collect_one_slot(kip, i))
 				break;
 		}
 	}
-	kprobe_garbage_slots = 0;
+	c->nr_garbage = 0;
 	return 0;
 }
 
-void __kprobes free_insn_slot(kprobe_opcode_t * slot, int dirty)
+static void __kprobes __free_insn_slot(struct kprobe_insn_cache *c,
+				       kprobe_opcode_t *slot, int dirty)
 {
 	struct kprobe_insn_page *kip;
 
-	mutex_lock(&kprobe_insn_mutex);
-	list_for_each_entry(kip, &kprobe_insn_pages, list) {
-		if (kip->insns <= slot &&
-		    slot < kip->insns + (INSNS_PER_PAGE * MAX_INSN_SIZE)) {
-			int i = (slot - kip->insns) / MAX_INSN_SIZE;
+	list_for_each_entry(kip, &c->pages, list) {
+		long idx = ((long)slot - (long)kip->insns) /
+				(c->insn_size * sizeof(kprobe_opcode_t));
+		if (idx >= 0 && idx < slots_per_page(c)) {
+			WARN_ON(kip->slot_used[idx] != SLOT_USED);
 			if (dirty) {
-				kip->slot_used[i] = SLOT_DIRTY;
+				kip->slot_used[idx] = SLOT_DIRTY;
 				kip->ngarbage++;
+				if (++c->nr_garbage > slots_per_page(c))
+					collect_garbage_slots(c);
 			} else
-				collect_one_slot(kip, i);
-			break;
+				collect_one_slot(kip, idx);
+			return;
 		}
 	}
+	/* Could not free this slot. */
+	WARN_ON(1);
+}
 
-	if (dirty && ++kprobe_garbage_slots > INSNS_PER_PAGE)
-		collect_garbage_slots();
-
+void __kprobes free_insn_slot(kprobe_opcode_t * slot, int dirty)
+{
+	mutex_lock(&kprobe_insn_mutex);
+	__free_insn_slot(&kprobe_insn_slots, slot, dirty);
 	mutex_unlock(&kprobe_insn_mutex);
 }
+#ifdef CONFIG_OPTPROBES
+/* For optimized_kprobe buffer */
+static DEFINE_MUTEX(kprobe_optinsn_mutex); /* Protects kprobe_optinsn_slots */
+static struct kprobe_insn_cache kprobe_optinsn_slots = {
+	.pages = LIST_HEAD_INIT(kprobe_optinsn_slots.pages),
+	/* .insn_size is initialized later */
+	.nr_garbage = 0,
+};
+/* Get a slot for optimized_kprobe buffer */
+kprobe_opcode_t __kprobes *get_optinsn_slot(void)
+{
+	kprobe_opcode_t *ret = NULL;
+
+	mutex_lock(&kprobe_optinsn_mutex);
+	ret = __get_insn_slot(&kprobe_optinsn_slots);
+	mutex_unlock(&kprobe_optinsn_mutex);
+
+	return ret;
+}
+
+void __kprobes free_optinsn_slot(kprobe_opcode_t * slot, int dirty)
+{
+	mutex_lock(&kprobe_optinsn_mutex);
+	__free_insn_slot(&kprobe_optinsn_slots, slot, dirty);
+	mutex_unlock(&kprobe_optinsn_mutex);
+}
+#endif
 #endif
 
 /* We have preemption disabled.. so it is safe to use __ versions */
@@ -284,23 +340,401 @@ struct kprobe __kprobes *get_kprobe(void *addr)
 		if (p->addr == addr)
 			return p;
 	}
+
+	return NULL;
+}
+
+static int __kprobes aggr_pre_handler(struct kprobe *p, struct pt_regs *regs);
+
+/* Return true if the kprobe is an aggregator */
+static inline int kprobe_aggrprobe(struct kprobe *p)
+{
+	return p->pre_handler == aggr_pre_handler;
+}
+
+/*
+ * Keep all fields in the kprobe consistent
+ */
+static inline void copy_kprobe(struct kprobe *old_p, struct kprobe *p)
+{
+	memcpy(&p->opcode, &old_p->opcode, sizeof(kprobe_opcode_t));
+	memcpy(&p->ainsn, &old_p->ainsn, sizeof(struct arch_specific_insn));
+}
+
+#ifdef CONFIG_OPTPROBES
+/* NOTE: change this value only with kprobe_mutex held */
+static bool kprobes_allow_optimization;
+
+/*
+ * Call all pre_handler on the list, but ignores its return value.
+ * This must be called from arch-dep optimized caller.
+ */
+void __kprobes opt_pre_handler(struct kprobe *p, struct pt_regs *regs)
+{
+	struct kprobe *kp;
+
+	list_for_each_entry_rcu(kp, &p->list, list) {
+		if (kp->pre_handler && likely(!kprobe_disabled(kp))) {
+			set_kprobe_instance(kp);
+			kp->pre_handler(kp, regs);
+		}
+		reset_kprobe_instance();
+	}
+}
+
+/* Return true(!0) if the kprobe is ready for optimization. */
+static inline int kprobe_optready(struct kprobe *p)
+{
+	struct optimized_kprobe *op;
+
+	if (kprobe_aggrprobe(p)) {
+		op = container_of(p, struct optimized_kprobe, kp);
+		return arch_prepared_optinsn(&op->optinsn);
+	}
+
+	return 0;
+}
+
+/*
+ * Return an optimized kprobe whose optimizing code replaces
+ * instructions including addr (exclude breakpoint).
+ */
+struct kprobe *__kprobes get_optimized_kprobe(unsigned long addr)
+{
+	int i;
+	struct kprobe *p = NULL;
+	struct optimized_kprobe *op;
+
+	/* Don't check i == 0, since that is a breakpoint case. */
+	for (i = 1; !p && i < MAX_OPTIMIZED_LENGTH; i++)
+		p = get_kprobe((void *)(addr - i));
+
+	if (p && kprobe_optready(p)) {
+		op = container_of(p, struct optimized_kprobe, kp);
+		if (arch_within_optimized_kprobe(op, addr))
+			return p;
+	}
+
 	return NULL;
 }
 
+/* Optimization staging list, protected by kprobe_mutex */
+static LIST_HEAD(optimizing_list);
+
+static void kprobe_optimizer(struct work_struct *work);
+static DECLARE_DELAYED_WORK(optimizing_work, kprobe_optimizer);
+#define OPTIMIZE_DELAY 5
+
+/* Kprobe jump optimizer */
+static __kprobes void kprobe_optimizer(struct work_struct *work)
+{
+	struct optimized_kprobe *op, *tmp;
+
+	/* Lock modules while optimizing kprobes */
+	mutex_lock(&module_mutex);
+	mutex_lock(&kprobe_mutex);
+	if (kprobes_all_disarmed || !kprobes_allow_optimization)
+		goto end;
+
+	/*
+	 * Wait for quiesence period to ensure all running interrupts
+	 * are done. Because optprobe may modify multiple instructions
+	 * there is a chance that Nth instruction is interrupted. In that
+	 * case, running interrupt can return to 2nd-Nth byte of jump
+	 * instruction. This wait is for avoiding it.
+	 */
+	synchronize_sched();
+
+	/*
+	 * The optimization/unoptimization refers online_cpus via
+	 * stop_machine() and cpu-hotplug modifies online_cpus.
+	 * And same time, text_mutex will be held in cpu-hotplug and here.
+	 * This combination can cause a deadlock (cpu-hotplug try to lock
+	 * text_mutex but stop_machine can not be done because online_cpus
+	 * has been changed)
+	 * To avoid this deadlock, we need to call get_online_cpus()
+	 * for preventing cpu-hotplug outside of text_mutex locking.
+	 */
+	get_online_cpus();
+	mutex_lock(&text_mutex);
+	list_for_each_entry_safe(op, tmp, &optimizing_list, list) {
+		WARN_ON(kprobe_disabled(&op->kp));
+		if (arch_optimize_kprobe(op) < 0)
+			op->kp.flags &= ~KPROBE_FLAG_OPTIMIZED;
+		list_del_init(&op->list);
+	}
+	mutex_unlock(&text_mutex);
+	put_online_cpus();
+end:
+	mutex_unlock(&kprobe_mutex);
+	mutex_unlock(&module_mutex);
+}
+
+/* Optimize kprobe if p is ready to be optimized */
+static __kprobes void optimize_kprobe(struct kprobe *p)
+{
+	struct optimized_kprobe *op;
+
+	/* Check if the kprobe is disabled or not ready for optimization. */
+	if (!kprobe_optready(p) || !kprobes_allow_optimization ||
+	    (kprobe_disabled(p) || kprobes_all_disarmed))
+		return;
+
+	/* Both of break_handler and post_handler are not supported. */
+	if (p->break_handler || p->post_handler)
+		return;
+
+	op = container_of(p, struct optimized_kprobe, kp);
+
+	/* Check there is no other kprobes at the optimized instructions */
+	if (arch_check_optimized_kprobe(op) < 0)
+		return;
+
+	/* Check if it is already optimized. */
+	if (op->kp.flags & KPROBE_FLAG_OPTIMIZED)
+		return;
+
+	op->kp.flags |= KPROBE_FLAG_OPTIMIZED;
+	list_add(&op->list, &optimizing_list);
+	if (!delayed_work_pending(&optimizing_work))
+		schedule_delayed_work(&optimizing_work, OPTIMIZE_DELAY);
+}
+
+/* Unoptimize a kprobe if p is optimized */
+static __kprobes void unoptimize_kprobe(struct kprobe *p)
+{
+	struct optimized_kprobe *op;
+
+	if ((p->flags & KPROBE_FLAG_OPTIMIZED) && kprobe_aggrprobe(p)) {
+		op = container_of(p, struct optimized_kprobe, kp);
+		if (!list_empty(&op->list))
+			/* Dequeue from the optimization queue */
+			list_del_init(&op->list);
+		else
+			/* Replace jump with break */
+			arch_unoptimize_kprobe(op);
+		op->kp.flags &= ~KPROBE_FLAG_OPTIMIZED;
+	}
+}
+
+/* Remove optimized instructions */
+static void __kprobes kill_optimized_kprobe(struct kprobe *p)
+{
+	struct optimized_kprobe *op;
+
+	op = container_of(p, struct optimized_kprobe, kp);
+	if (!list_empty(&op->list)) {
+		/* Dequeue from the optimization queue */
+		list_del_init(&op->list);
+		op->kp.flags &= ~KPROBE_FLAG_OPTIMIZED;
+	}
+	/* Don't unoptimize, because the target code will be freed. */
+	arch_remove_optimized_kprobe(op);
+}
+
+/* Try to prepare optimized instructions */
+static __kprobes void prepare_optimized_kprobe(struct kprobe *p)
+{
+	struct optimized_kprobe *op;
+
+	op = container_of(p, struct optimized_kprobe, kp);
+	arch_prepare_optimized_kprobe(op);
+}
+
+/* Free optimized instructions and optimized_kprobe */
+static __kprobes void free_aggr_kprobe(struct kprobe *p)
+{
+	struct optimized_kprobe *op;
+
+	op = container_of(p, struct optimized_kprobe, kp);
+	arch_remove_optimized_kprobe(op);
+	kfree(op);
+}
+
+/* Allocate new optimized_kprobe and try to prepare optimized instructions */
+static __kprobes struct kprobe *alloc_aggr_kprobe(struct kprobe *p)
+{
+	struct optimized_kprobe *op;
+
+	op = kzalloc(sizeof(struct optimized_kprobe), GFP_KERNEL);
+	if (!op)
+		return NULL;
+
+	INIT_LIST_HEAD(&op->list);
+	op->kp.addr = p->addr;
+	arch_prepare_optimized_kprobe(op);
+
+	return &op->kp;
+}
+
+static void __kprobes init_aggr_kprobe(struct kprobe *ap, struct kprobe *p);
+
+/*
+ * Prepare an optimized_kprobe and optimize it
+ * NOTE: p must be a normal registered kprobe
+ */
+static __kprobes void try_to_optimize_kprobe(struct kprobe *p)
+{
+	struct kprobe *ap;
+	struct optimized_kprobe *op;
+
+	ap = alloc_aggr_kprobe(p);
+	if (!ap)
+		return;
+
+	op = container_of(ap, struct optimized_kprobe, kp);
+	if (!arch_prepared_optinsn(&op->optinsn)) {
+		/* If failed to setup optimizing, fallback to kprobe */
+		free_aggr_kprobe(ap);
+		return;
+	}
+
+	init_aggr_kprobe(ap, p);
+	optimize_kprobe(ap);
+}
+
+#ifdef CONFIG_SYSCTL
+static void __kprobes optimize_all_kprobes(void)
+{
+	struct hlist_head *head;
+	struct hlist_node *node;
+	struct kprobe *p;
+	unsigned int i;
+
+	/* If optimization is already allowed, just return */
+	if (kprobes_allow_optimization)
+		return;
+
+	kprobes_allow_optimization = true;
+	mutex_lock(&text_mutex);
+	for (i = 0; i < KPROBE_TABLE_SIZE; i++) {
+		head = &kprobe_table[i];
+		hlist_for_each_entry_rcu(p, node, head, hlist)
+			if (!kprobe_disabled(p))
+				optimize_kprobe(p);
+	}
+	mutex_unlock(&text_mutex);
+	printk(KERN_INFO "Kprobes globally optimized\n");
+}
+
+static void __kprobes unoptimize_all_kprobes(void)
+{
+	struct hlist_head *head;
+	struct hlist_node *node;
+	struct kprobe *p;
+	unsigned int i;
+
+	/* If optimization is already prohibited, just return */
+	if (!kprobes_allow_optimization)
+		return;
+
+	kprobes_allow_optimization = false;
+	printk(KERN_INFO "Kprobes globally unoptimized\n");
+	get_online_cpus();	/* For avoiding text_mutex deadlock */
+	mutex_lock(&text_mutex);
+	for (i = 0; i < KPROBE_TABLE_SIZE; i++) {
+		head = &kprobe_table[i];
+		hlist_for_each_entry_rcu(p, node, head, hlist) {
+			if (!kprobe_disabled(p))
+				unoptimize_kprobe(p);
+		}
+	}
+
+	mutex_unlock(&text_mutex);
+	put_online_cpus();
+	/* Allow all currently running kprobes to complete */
+	synchronize_sched();
+}
+
+int sysctl_kprobes_optimization;
+int proc_kprobes_optimization_handler(struct ctl_table *table, int write,
+				      void __user *buffer, size_t *length,
+				      loff_t *ppos)
+{
+	int ret;
+
+	mutex_lock(&kprobe_mutex);
+	sysctl_kprobes_optimization = kprobes_allow_optimization ? 1 : 0;
+	ret = proc_dointvec_minmax(table, write, buffer, length, ppos);
+
+	if (sysctl_kprobes_optimization)
+		optimize_all_kprobes();
+	else
+		unoptimize_all_kprobes();
+	mutex_unlock(&kprobe_mutex);
+
+	return ret;
+}
+#endif /* CONFIG_SYSCTL */
+
+static void __kprobes __arm_kprobe(struct kprobe *p)
+{
+	struct kprobe *old_p;
+
+	/* Check collision with other optimized kprobes */
+	old_p = get_optimized_kprobe((unsigned long)p->addr);
+	if (unlikely(old_p))
+		unoptimize_kprobe(old_p); /* Fallback to unoptimized kprobe */
+
+	arch_arm_kprobe(p);
+	optimize_kprobe(p);	/* Try to optimize (add kprobe to a list) */
+}
+
+static void __kprobes __disarm_kprobe(struct kprobe *p)
+{
+	struct kprobe *old_p;
+
+	unoptimize_kprobe(p);	/* Try to unoptimize */
+	arch_disarm_kprobe(p);
+
+	/* If another kprobe was blocked, optimize it. */
+	old_p = get_optimized_kprobe((unsigned long)p->addr);
+	if (unlikely(old_p))
+		optimize_kprobe(old_p);
+}
+
+#else /* !CONFIG_OPTPROBES */
+
+#define optimize_kprobe(p)			do {} while (0)
+#define unoptimize_kprobe(p)			do {} while (0)
+#define kill_optimized_kprobe(p)		do {} while (0)
+#define prepare_optimized_kprobe(p)		do {} while (0)
+#define try_to_optimize_kprobe(p)		do {} while (0)
+#define __arm_kprobe(p)				arch_arm_kprobe(p)
+#define __disarm_kprobe(p)			arch_disarm_kprobe(p)
+
+static __kprobes void free_aggr_kprobe(struct kprobe *p)
+{
+	kfree(p);
+}
+
+static __kprobes struct kprobe *alloc_aggr_kprobe(struct kprobe *p)
+{
+	return kzalloc(sizeof(struct kprobe), GFP_KERNEL);
+}
+#endif /* CONFIG_OPTPROBES */
+
 /* Arm a kprobe with text_mutex */
 static void __kprobes arm_kprobe(struct kprobe *kp)
 {
+	/*
+	 * Here, since __arm_kprobe() doesn't use stop_machine(),
+	 * this doesn't cause deadlock on text_mutex. So, we don't
+	 * need get_online_cpus().
+	 */
 	mutex_lock(&text_mutex);
-	arch_arm_kprobe(kp);
+	__arm_kprobe(kp);
 	mutex_unlock(&text_mutex);
 }
 
 /* Disarm a kprobe with text_mutex */
 static void __kprobes disarm_kprobe(struct kprobe *kp)
 {
+	get_online_cpus();	/* For avoiding text_mutex deadlock */
 	mutex_lock(&text_mutex);
-	arch_disarm_kprobe(kp);
+	__disarm_kprobe(kp);
 	mutex_unlock(&text_mutex);
+	put_online_cpus();
 }
 
 /*
@@ -369,7 +803,7 @@ static int __kprobes aggr_break_handler(struct kprobe *p, struct pt_regs *regs)
 void __kprobes kprobes_inc_nmissed_count(struct kprobe *p)
 {
 	struct kprobe *kp;
-	if (p->pre_handler != aggr_pre_handler) {
+	if (!kprobe_aggrprobe(p)) {
 		p->nmissed++;
 	} else {
 		list_for_each_entry_rcu(kp, &p->list, list)
@@ -493,21 +927,16 @@ static void __kprobes cleanup_rp_inst(struct kretprobe *rp)
 }
 
 /*
- * Keep all fields in the kprobe consistent
- */
-static inline void copy_kprobe(struct kprobe *old_p, struct kprobe *p)
-{
-	memcpy(&p->opcode, &old_p->opcode, sizeof(kprobe_opcode_t));
-	memcpy(&p->ainsn, &old_p->ainsn, sizeof(struct arch_specific_insn));
-}
-
-/*
 * Add the new probe to ap->list. Fail if this is the
 * second jprobe at the address - two jprobes can't coexist
 */
 static int __kprobes add_new_kprobe(struct kprobe *ap, struct kprobe *p)
 {
 	BUG_ON(kprobe_gone(ap) || kprobe_gone(p));
+
+	if (p->break_handler || p->post_handler)
+		unoptimize_kprobe(ap);	/* Fall back to normal kprobe */
+
 	if (p->break_handler) {
 		if (ap->break_handler)
 			return -EEXIST;
@@ -522,7 +951,7 @@ static int __kprobes add_new_kprobe(struct kprobe *ap, struct kprobe *p)
 		ap->flags &= ~KPROBE_FLAG_DISABLED;
 		if (!kprobes_all_disarmed)
 			/* Arm the breakpoint again. */
-			arm_kprobe(ap);
+			__arm_kprobe(ap);
 	}
 	return 0;
 }
@@ -531,12 +960,13 @@ static int __kprobes add_new_kprobe(struct kprobe *ap, struct kprobe *p)
  * Fill in the required fields of the "manager kprobe". Replace the
  * earlier kprobe in the hlist with the manager kprobe
  */
-static inline void add_aggr_kprobe(struct kprobe *ap, struct kprobe *p)
+static void __kprobes init_aggr_kprobe(struct kprobe *ap, struct kprobe *p)
 {
+	/* Copy p's insn slot to ap */
 	copy_kprobe(p, ap);
 	flush_insn_slot(ap);
 	ap->addr = p->addr;
-	ap->flags = p->flags;
+	ap->flags = p->flags & ~KPROBE_FLAG_OPTIMIZED;
 	ap->pre_handler = aggr_pre_handler;
 	ap->fault_handler = aggr_fault_handler;
 	/* We don't care the kprobe which has gone. */
@@ -546,8 +976,9 @@ static inline void add_aggr_kprobe(struct kprobe *ap, struct kprobe *p)
 		ap->break_handler = aggr_break_handler;
 
 	INIT_LIST_HEAD(&ap->list);
-	list_add_rcu(&p->list, &ap->list);
+	INIT_HLIST_NODE(&ap->hlist);
 
+	list_add_rcu(&p->list, &ap->list);
 	hlist_replace_rcu(&p->hlist, &ap->hlist);
 }
 
@@ -561,12 +992,12 @@ static int __kprobes register_aggr_kprobe(struct kprobe *old_p,
 	int ret = 0;
 	struct kprobe *ap = old_p;
 
-	if (old_p->pre_handler != aggr_pre_handler) {
-		/* If old_p is not an aggr_probe, create new aggr_kprobe. */
-		ap = kzalloc(sizeof(struct kprobe), GFP_KERNEL);
+	if (!kprobe_aggrprobe(old_p)) {
+		/* If old_p is not an aggr_kprobe, create new aggr_kprobe. */
+		ap = alloc_aggr_kprobe(old_p);
 		if (!ap)
 			return -ENOMEM;
-		add_aggr_kprobe(ap, old_p);
+		init_aggr_kprobe(ap, old_p);
 	}
 
 	if (kprobe_gone(ap)) {
@@ -585,6 +1016,9 @@ static int __kprobes register_aggr_kprobe(struct kprobe *old_p,
 			 */
 			return ret;
 
+		/* Prepare optimized instructions if possible. */
+		prepare_optimized_kprobe(ap);
+
 		/*
 		 * Clear gone flag to prevent allocating new slot again, and
 		 * set disabled flag because it is not armed yet.
@@ -593,6 +1027,7 @@ static int __kprobes register_aggr_kprobe(struct kprobe *old_p,
 			    | KPROBE_FLAG_DISABLED;
 	}
 
+	/* Copy ap's insn slot to p */
 	copy_kprobe(ap, p);
 	return add_new_kprobe(ap, p);
 }
@@ -743,27 +1178,34 @@ int __kprobes register_kprobe(struct kprobe *p)
 	p->nmissed = 0;
 	INIT_LIST_HEAD(&p->list);
 	mutex_lock(&kprobe_mutex);
+
+	get_online_cpus();	/* For avoiding text_mutex deadlock. */
+	mutex_lock(&text_mutex);
+
 	old_p = get_kprobe(p->addr);
 	if (old_p) {
+		/* Since this may unoptimize old_p, locking text_mutex. */
 		ret = register_aggr_kprobe(old_p, p);
 		goto out;
 	}
 
-	mutex_lock(&text_mutex);
 	ret = arch_prepare_kprobe(p);
 	if (ret)
-		goto out_unlock_text;
+		goto out;
 
 	INIT_HLIST_NODE(&p->hlist);
 	hlist_add_head_rcu(&p->hlist,
 		       &kprobe_table[hash_ptr(p->addr, KPROBE_HASH_BITS)]);
 
 	if (!kprobes_all_disarmed && !kprobe_disabled(p))
-		arch_arm_kprobe(p);
+		__arm_kprobe(p);
+
+	/* Try to optimize kprobe */
+	try_to_optimize_kprobe(p);
 
-out_unlock_text:
-	mutex_unlock(&text_mutex);
 out:
+	mutex_unlock(&text_mutex);
+	put_online_cpus();
 	mutex_unlock(&kprobe_mutex);
 
 	if (probed_mod)
@@ -785,7 +1227,7 @@ static int __kprobes __unregister_kprobe_top(struct kprobe *p)
 		return -EINVAL;
 
 	if (old_p == p ||
-	    (old_p->pre_handler == aggr_pre_handler &&
+	    (kprobe_aggrprobe(old_p) &&
 	     list_is_singular(&old_p->list))) {
 		/*
 		 * Only probe on the hash list. Disarm only if kprobes are
@@ -793,7 +1235,7 @@ static int __kprobes __unregister_kprobe_top(struct kprobe *p)
 		 * already have been removed. We save on flushing icache.
 		 */
 		if (!kprobes_all_disarmed && !kprobe_disabled(old_p))
-			disarm_kprobe(p);
+			disarm_kprobe(old_p);
 		hlist_del_rcu(&old_p->hlist);
 	} else {
 		if (p->break_handler && !kprobe_gone(p))
@@ -809,8 +1251,13 @@ noclean:
 		list_del_rcu(&p->list);
 		if (!kprobe_disabled(old_p)) {
 			try_to_disable_aggr_kprobe(old_p);
-			if (!kprobes_all_disarmed && kprobe_disabled(old_p))
-				disarm_kprobe(old_p);
+			if (!kprobes_all_disarmed) {
+				if (kprobe_disabled(old_p))
+					disarm_kprobe(old_p);
+				else
+					/* Try to optimize this probe again */
+					optimize_kprobe(old_p);
+			}
 		}
 	}
 	return 0;
@@ -827,7 +1274,7 @@ static void __kprobes __unregister_kprobe_bottom(struct kprobe *p)
 		old_p = list_entry(p->list.next, struct kprobe, list);
 		list_del(&p->list);
 		arch_remove_kprobe(old_p);
-		kfree(old_p);
+		free_aggr_kprobe(old_p);
 	}
 }
 
@@ -1123,7 +1570,7 @@ static void __kprobes kill_kprobe(struct kprobe *p)
 	struct kprobe *kp;
 
 	p->flags |= KPROBE_FLAG_GONE;
-	if (p->pre_handler == aggr_pre_handler) {
+	if (kprobe_aggrprobe(p)) {
 		/*
 		 * If this is an aggr_kprobe, we have to list all the
 		 * chained probes and mark them GONE.
@@ -1132,6 +1579,7 @@ static void __kprobes kill_kprobe(struct kprobe *p)
 			kp->flags |= KPROBE_FLAG_GONE;
 		p->post_handler = NULL;
 		p->break_handler = NULL;
+		kill_optimized_kprobe(p);
 	}
 	/*
 	 * Here, we can remove insn_slot safely, because no thread calls
@@ -1241,6 +1689,15 @@ static int __init init_kprobes(void)
 		}
 	}
 
+#if defined(CONFIG_OPTPROBES)
+#if defined(__ARCH_WANT_KPROBES_INSN_SLOT)
+	/* Init kprobe_optinsn_slots */
+	kprobe_optinsn_slots.insn_size = MAX_OPTINSN_SIZE;
+#endif
+	/* By default, kprobes can be optimized */
+	kprobes_allow_optimization = true;
+#endif
+
 	/* By default, kprobes are armed */
 	kprobes_all_disarmed = false;
 
@@ -1259,7 +1716,7 @@ static int __init init_kprobes(void)
 
 #ifdef CONFIG_DEBUG_FS
 static void __kprobes report_probe(struct seq_file *pi, struct kprobe *p,
-		const char *sym, int offset,char *modname)
+		const char *sym, int offset, char *modname, struct kprobe *pp)
 {
 	char *kprobe_type;
 
@@ -1269,19 +1726,21 @@ static void __kprobes report_probe(struct seq_file *pi, struct kprobe *p,
 		kprobe_type = "j";
 	else
 		kprobe_type = "k";
+
 	if (sym)
-		seq_printf(pi, "%p  %s  %s+0x%x  %s %s%s\n",
+		seq_printf(pi, "%p  %s  %s+0x%x  %s ",
 			p->addr, kprobe_type, sym, offset,
-			(modname ? modname : " "),
-			(kprobe_gone(p) ? "[GONE]" : ""),
-			((kprobe_disabled(p) && !kprobe_gone(p)) ?
-			 "[DISABLED]" : ""));
+			(modname ? modname : " "));
 	else
-		seq_printf(pi, "%p  %s  %p %s%s\n",
-			p->addr, kprobe_type, p->addr,
-			(kprobe_gone(p) ? "[GONE]" : ""),
-			((kprobe_disabled(p) && !kprobe_gone(p)) ?
-			 "[DISABLED]" : ""));
+		seq_printf(pi, "%p  %s  %p ",
+			p->addr, kprobe_type, p->addr);
+
+	if (!pp)
+		pp = p;
+	seq_printf(pi, "%s%s%s\n",
+		(kprobe_gone(p) ? "[GONE]" : ""),
+		((kprobe_disabled(p) && !kprobe_gone(p)) ?  "[DISABLED]" : ""),
+		(kprobe_optimized(pp) ? "[OPTIMIZED]" : ""));
 }
 
 static void __kprobes *kprobe_seq_start(struct seq_file *f, loff_t *pos)
@@ -1317,11 +1776,11 @@ static int __kprobes show_kprobe_addr(struct seq_file *pi, void *v)
 	hlist_for_each_entry_rcu(p, node, head, hlist) {
 		sym = kallsyms_lookup((unsigned long)p->addr, NULL,
 					&offset, &modname, namebuf);
-		if (p->pre_handler == aggr_pre_handler) {
+		if (kprobe_aggrprobe(p)) {
 			list_for_each_entry_rcu(kp, &p->list, list)
-				report_probe(pi, kp, sym, offset, modname);
+				report_probe(pi, kp, sym, offset, modname, p);
 		} else
-			report_probe(pi, p, sym, offset, modname);
+			report_probe(pi, p, sym, offset, modname, NULL);
 	}
 	preempt_enable();
 	return 0;
@@ -1399,12 +1858,13 @@ int __kprobes enable_kprobe(struct kprobe *kp)
 		goto out;
 	}
 
-	if (!kprobes_all_disarmed && kprobe_disabled(p))
-		arm_kprobe(p);
-
-	p->flags &= ~KPROBE_FLAG_DISABLED;
 	if (p != kp)
 		kp->flags &= ~KPROBE_FLAG_DISABLED;
+
+	if (!kprobes_all_disarmed && kprobe_disabled(p)) {
+		p->flags &= ~KPROBE_FLAG_DISABLED;
+		arm_kprobe(p);
+	}
 out:
 	mutex_unlock(&kprobe_mutex);
 	return ret;
@@ -1424,12 +1884,13 @@ static void __kprobes arm_all_kprobes(void)
 	if (!kprobes_all_disarmed)
 		goto already_enabled;
 
+	/* Arming kprobes doesn't optimize kprobe itself */
 	mutex_lock(&text_mutex);
 	for (i = 0; i < KPROBE_TABLE_SIZE; i++) {
 		head = &kprobe_table[i];
 		hlist_for_each_entry_rcu(p, node, head, hlist)
 			if (!kprobe_disabled(p))
-				arch_arm_kprobe(p);
+				__arm_kprobe(p);
 	}
 	mutex_unlock(&text_mutex);
 
@@ -1456,16 +1917,23 @@ static void __kprobes disarm_all_kprobes(void)
 
 	kprobes_all_disarmed = true;
 	printk(KERN_INFO "Kprobes globally disabled\n");
+
+	/*
+	 * Here we call get_online_cpus() for avoiding text_mutex deadlock,
+	 * because disarming may also unoptimize kprobes.
+	 */
+	get_online_cpus();
 	mutex_lock(&text_mutex);
 	for (i = 0; i < KPROBE_TABLE_SIZE; i++) {
 		head = &kprobe_table[i];
 		hlist_for_each_entry_rcu(p, node, head, hlist) {
 			if (!arch_trampoline_kprobe(p) && !kprobe_disabled(p))
-				arch_disarm_kprobe(p);
+				__disarm_kprobe(p);
 		}
 	}
 
 	mutex_unlock(&text_mutex);
+	put_online_cpus();
 	mutex_unlock(&kprobe_mutex);
 	/* Allow all currently running kprobes to complete */
 	synchronize_sched();
diff --git a/kernel/ksysfs.c b/kernel/ksysfs.c
index 3feaf5a7451..21fe3c42694 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)
 {
@@ -197,16 +197,8 @@ static int __init ksysfs_init(void)
 			goto group_exit;
 	}
 
-	/* create the /sys/kernel/uids/ directory */
-	error = uids_sysfs_init();
-	if (error)
-		goto notes_exit;
-
 	return 0;
 
-notes_exit:
-	if (notes_size > 0)
-		sysfs_remove_bin_file(kernel_kobj, &notes_attr);
 group_exit:
 	sysfs_remove_group(kernel_kobj, &kernel_attr_group);
 kset_exit:
diff --git a/kernel/kthread.c b/kernel/kthread.c
index fbb6222fe7e..83911c78017 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -101,7 +101,7 @@ static void create_kthread(struct kthread_create_info *create)
  *
  * Description: This helper function creates and names a kernel
  * thread.  The thread will be stopped: use wake_up_process() to start
- * it.  See also kthread_run(), kthread_create_on_cpu().
+ * it.  See also kthread_run().
  *
  * When woken, the thread will run @threadfn() with @data as its
  * argument. @threadfn() can either call do_exit() directly if it is a
@@ -219,7 +219,7 @@ int kthreadd(void *unused)
 	set_task_comm(tsk, "kthreadd");
 	ignore_signals(tsk);
 	set_cpus_allowed_ptr(tsk, cpu_all_mask);
-	set_mems_allowed(node_possible_map);
+	set_mems_allowed(node_states[N_HIGH_MEMORY]);
 
 	current->flags |= PF_NOFREEZE | PF_FREEZER_NOSIG;
 
diff --git a/kernel/latencytop.c b/kernel/latencytop.c
index ca07c5c0c91..877fb306d41 100644
--- a/kernel/latencytop.c
+++ b/kernel/latencytop.c
@@ -56,7 +56,6 @@
 #include <linux/module.h>
 #include <linux/sched.h>
 #include <linux/list.h>
-#include <linux/slab.h>
 #include <linux/stacktrace.h>
 
 static DEFINE_SPINLOCK(latency_lock);
diff --git a/kernel/lockdep.c b/kernel/lockdep.c
index 5feaddcdbe4..2594e1ce41c 100644
--- a/kernel/lockdep.c
+++ b/kernel/lockdep.c
@@ -43,6 +43,7 @@
 #include <linux/ftrace.h>
 #include <linux/stringify.h>
 #include <linux/bitops.h>
+#include <linux/gfp.h>
 
 #include <asm/sections.h>
 
@@ -582,9 +583,6 @@ static int static_obj(void *obj)
 	unsigned long start = (unsigned long) &_stext,
 		      end   = (unsigned long) &_end,
 		      addr  = (unsigned long) obj;
-#ifdef CONFIG_SMP
-	int i;
-#endif
 
 	/*
 	 * static variable?
@@ -595,24 +593,16 @@ static int static_obj(void *obj)
 	if (arch_is_kernel_data(addr))
 		return 1;
 
-#ifdef CONFIG_SMP
 	/*
-	 * percpu var?
+	 * in-kernel percpu var?
 	 */
-	for_each_possible_cpu(i) {
-		start = (unsigned long) &__per_cpu_start + per_cpu_offset(i);
-		end   = (unsigned long) &__per_cpu_start + PERCPU_ENOUGH_ROOM
-					+ per_cpu_offset(i);
-
-		if ((addr >= start) && (addr < end))
-			return 1;
-	}
-#endif
+	if (is_kernel_percpu_address(addr))
+		return 1;
 
 	/*
-	 * module var?
+	 * module static or percpu var?
 	 */
-	return is_module_address(addr);
+	return is_module_address(addr) || is_module_percpu_address(addr);
 }
 
 /*
@@ -2147,7 +2137,7 @@ check_usage_backwards(struct task_struct *curr, struct held_lock *this,
 		return ret;
 
 	return print_irq_inversion_bug(curr, &root, target_entry,
-					this, 1, irqclass);
+					this, 0, irqclass);
 }
 
 void print_irqtrace_events(struct task_struct *curr)
@@ -3211,8 +3201,6 @@ void lock_acquire(struct lockdep_map *lock, unsigned int subclass,
 {
 	unsigned long flags;
 
-	trace_lock_acquire(lock, subclass, trylock, read, check, nest_lock, ip);
-
 	if (unlikely(current->lockdep_recursion))
 		return;
 
@@ -3220,6 +3208,7 @@ void lock_acquire(struct lockdep_map *lock, unsigned int subclass,
 	check_flags(flags);
 
 	current->lockdep_recursion = 1;
+	trace_lock_acquire(lock, subclass, trylock, read, check, nest_lock, ip);
 	__lock_acquire(lock, subclass, trylock, read, check,
 		       irqs_disabled_flags(flags), nest_lock, ip, 0);
 	current->lockdep_recursion = 0;
@@ -3232,14 +3221,13 @@ void lock_release(struct lockdep_map *lock, int nested,
 {
 	unsigned long flags;
 
-	trace_lock_release(lock, nested, ip);
-
 	if (unlikely(current->lockdep_recursion))
 		return;
 
 	raw_local_irq_save(flags);
 	check_flags(flags);
 	current->lockdep_recursion = 1;
+	trace_lock_release(lock, nested, ip);
 	__lock_release(lock, nested, ip);
 	current->lockdep_recursion = 0;
 	raw_local_irq_restore(flags);
@@ -3413,8 +3401,6 @@ void lock_contended(struct lockdep_map *lock, unsigned long ip)
 {
 	unsigned long flags;
 
-	trace_lock_contended(lock, ip);
-
 	if (unlikely(!lock_stat))
 		return;
 
@@ -3424,6 +3410,7 @@ void lock_contended(struct lockdep_map *lock, unsigned long ip)
 	raw_local_irq_save(flags);
 	check_flags(flags);
 	current->lockdep_recursion = 1;
+	trace_lock_contended(lock, ip);
 	__lock_contended(lock, ip);
 	current->lockdep_recursion = 0;
 	raw_local_irq_restore(flags);
@@ -3809,3 +3796,22 @@ void lockdep_sys_exit(void)
 		lockdep_print_held_locks(curr);
 	}
 }
+
+void lockdep_rcu_dereference(const char *file, const int line)
+{
+	struct task_struct *curr = current;
+
+	if (!debug_locks_off())
+		return;
+	printk("\n===================================================\n");
+	printk(  "[ INFO: suspicious rcu_dereference_check() usage. ]\n");
+	printk(  "---------------------------------------------------\n");
+	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();
+}
+EXPORT_SYMBOL_GPL(lockdep_rcu_dereference);
diff --git a/kernel/module.c b/kernel/module.c
index f82386bd9ee..1016b75b026 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -370,27 +370,33 @@ EXPORT_SYMBOL_GPL(find_module);
 
 #ifdef CONFIG_SMP
 
-static void *percpu_modalloc(unsigned long size, unsigned long align,
-			     const char *name)
+static inline void __percpu *mod_percpu(struct module *mod)
 {
-	void *ptr;
+	return mod->percpu;
+}
 
+static int percpu_modalloc(struct module *mod,
+			   unsigned long size, unsigned long align)
+{
 	if (align > PAGE_SIZE) {
 		printk(KERN_WARNING "%s: per-cpu alignment %li > %li\n",
-		       name, align, PAGE_SIZE);
+		       mod->name, align, PAGE_SIZE);
 		align = PAGE_SIZE;
 	}
 
-	ptr = __alloc_reserved_percpu(size, align);
-	if (!ptr)
+	mod->percpu = __alloc_reserved_percpu(size, align);
+	if (!mod->percpu) {
 		printk(KERN_WARNING
 		       "Could not allocate %lu bytes percpu data\n", size);
-	return ptr;
+		return -ENOMEM;
+	}
+	mod->percpu_size = size;
+	return 0;
 }
 
-static void percpu_modfree(void *freeme)
+static void percpu_modfree(struct module *mod)
 {
-	free_percpu(freeme);
+	free_percpu(mod->percpu);
 }
 
 static unsigned int find_pcpusec(Elf_Ehdr *hdr,
@@ -400,24 +406,62 @@ static unsigned int find_pcpusec(Elf_Ehdr *hdr,
 	return find_sec(hdr, sechdrs, secstrings, ".data.percpu");
 }
 
-static void percpu_modcopy(void *pcpudest, const void *from, unsigned long size)
+static void percpu_modcopy(struct module *mod,
+			   const void *from, unsigned long size)
 {
 	int cpu;
 
 	for_each_possible_cpu(cpu)
-		memcpy(pcpudest + per_cpu_offset(cpu), from, size);
+		memcpy(per_cpu_ptr(mod->percpu, cpu), from, size);
+}
+
+/**
+ * is_module_percpu_address - test whether address is from module static percpu
+ * @addr: address to test
+ *
+ * Test whether @addr belongs to module static percpu area.
+ *
+ * RETURNS:
+ * %true if @addr is from module static percpu area
+ */
+bool is_module_percpu_address(unsigned long addr)
+{
+	struct module *mod;
+	unsigned int cpu;
+
+	preempt_disable();
+
+	list_for_each_entry_rcu(mod, &modules, list) {
+		if (!mod->percpu_size)
+			continue;
+		for_each_possible_cpu(cpu) {
+			void *start = per_cpu_ptr(mod->percpu, cpu);
+
+			if ((void *)addr >= start &&
+			    (void *)addr < start + mod->percpu_size) {
+				preempt_enable();
+				return true;
+			}
+		}
+	}
+
+	preempt_enable();
+	return false;
 }
 
 #else /* ... !CONFIG_SMP */
 
-static inline void *percpu_modalloc(unsigned long size, unsigned long align,
-				    const char *name)
+static inline void __percpu *mod_percpu(struct module *mod)
 {
 	return NULL;
 }
-static inline void percpu_modfree(void *pcpuptr)
+static inline int percpu_modalloc(struct module *mod,
+				  unsigned long size, unsigned long align)
+{
+	return -ENOMEM;
+}
+static inline void percpu_modfree(struct module *mod)
 {
-	BUG();
 }
 static inline unsigned int find_pcpusec(Elf_Ehdr *hdr,
 					Elf_Shdr *sechdrs,
@@ -425,12 +469,16 @@ static inline unsigned int find_pcpusec(Elf_Ehdr *hdr,
 {
 	return 0;
 }
-static inline void percpu_modcopy(void *pcpudst, const void *src,
-				  unsigned long size)
+static inline void percpu_modcopy(struct module *mod,
+				  const void *from, unsigned long size)
 {
 	/* pcpusec should be 0, and size of that section should be 0. */
 	BUG_ON(size != 0);
 }
+bool is_module_percpu_address(unsigned long addr)
+{
+	return false;
+}
 
 #endif /* CONFIG_SMP */
 
@@ -473,10 +521,13 @@ static void module_unload_init(struct module *mod)
 	int cpu;
 
 	INIT_LIST_HEAD(&mod->modules_which_use_me);
-	for_each_possible_cpu(cpu)
-		local_set(__module_ref_addr(mod, cpu), 0);
+	for_each_possible_cpu(cpu) {
+		per_cpu_ptr(mod->refptr, cpu)->incs = 0;
+		per_cpu_ptr(mod->refptr, cpu)->decs = 0;
+	}
+
 	/* Hold reference count during initialization. */
-	local_set(__module_ref_addr(mod, raw_smp_processor_id()), 1);
+	__this_cpu_write(mod->refptr->incs, 1);
 	/* Backwards compatibility macros put refcount during init. */
 	mod->waiter = current;
 }
@@ -615,12 +666,28 @@ static int try_stop_module(struct module *mod, int flags, int *forced)
 
 unsigned int module_refcount(struct module *mod)
 {
-	unsigned int total = 0;
+	unsigned int incs = 0, decs = 0;
 	int cpu;
 
 	for_each_possible_cpu(cpu)
-		total += local_read(__module_ref_addr(mod, cpu));
-	return total;
+		decs += per_cpu_ptr(mod->refptr, cpu)->decs;
+	/*
+	 * ensure the incs are added up after the decs.
+	 * module_put ensures incs are visible before decs with smp_wmb.
+	 *
+	 * This 2-count scheme avoids the situation where the refcount
+	 * for CPU0 is read, then CPU0 increments the module refcount,
+	 * then CPU1 drops that refcount, then the refcount for CPU1 is
+	 * read. We would record a decrement but not its corresponding
+	 * increment so we would see a low count (disaster).
+	 *
+	 * Rare situation? But module_refcount can be preempted, and we
+	 * might be tallying up 4096+ CPUs. So it is not impossible.
+	 */
+	smp_rmb();
+	for_each_possible_cpu(cpu)
+		incs += per_cpu_ptr(mod->refptr, cpu)->incs;
+	return incs - decs;
 }
 EXPORT_SYMBOL(module_refcount);
 
@@ -796,14 +863,16 @@ static struct module_attribute refcnt = {
 void module_put(struct module *module)
 {
 	if (module) {
-		unsigned int cpu = get_cpu();
-		local_dec(__module_ref_addr(module, cpu));
+		preempt_disable();
+		smp_wmb(); /* see comment in module_refcount */
+		__this_cpu_inc(module->refptr->decs);
+
 		trace_module_put(module, _RET_IP_,
-				 local_read(__module_ref_addr(module, cpu)));
+				 __this_cpu_read(module->refptr->decs));
 		/* Maybe they're waiting for us to drop reference? */
 		if (unlikely(!module_is_live(module)))
 			wake_up_process(module->waiter);
-		put_cpu();
+		preempt_enable();
 	}
 }
 EXPORT_SYMBOL(module_put);
@@ -1083,6 +1152,7 @@ static void add_sect_attrs(struct module *mod, unsigned int nsect,
 		if (sattr->name == NULL)
 			goto out;
 		sect_attrs->nsections++;
+		sysfs_attr_init(&sattr->mattr.attr);
 		sattr->mattr.show = module_sect_show;
 		sattr->mattr.store = NULL;
 		sattr->mattr.attr.name = sattr->name;
@@ -1178,6 +1248,7 @@ static void add_notes_attrs(struct module *mod, unsigned int nsect,
 		if (sect_empty(&sechdrs[i]))
 			continue;
 		if (sechdrs[i].sh_type == SHT_NOTE) {
+			sysfs_bin_attr_init(nattr);
 			nattr->attr.name = mod->sect_attrs->attrs[loaded].name;
 			nattr->attr.mode = S_IRUGO;
 			nattr->size = sechdrs[i].sh_size;
@@ -1250,6 +1321,7 @@ int module_add_modinfo_attrs(struct module *mod)
 		if (!attr->test ||
 		    (attr->test && attr->test(mod))) {
 			memcpy(temp_attr, attr, sizeof(*temp_attr));
+			sysfs_attr_init(&temp_attr->attr);
 			error = sysfs_create_file(&mod->mkobj.kobj,&temp_attr->attr);
 			++temp_attr;
 		}
@@ -1395,11 +1467,10 @@ static void free_module(struct module *mod)
 	/* This may be NULL, but that's OK */
 	module_free(mod, mod->module_init);
 	kfree(mod->args);
-	if (mod->percpu)
-		percpu_modfree(mod->percpu);
-#if defined(CONFIG_MODULE_UNLOAD) && defined(CONFIG_SMP)
+	percpu_modfree(mod);
+#if defined(CONFIG_MODULE_UNLOAD)
 	if (mod->refptr)
-		percpu_modfree(mod->refptr);
+		free_percpu(mod->refptr);
 #endif
 	/* Free lock-classes: */
 	lockdep_free_key_range(mod->module_core, mod->core_size);
@@ -1515,7 +1586,7 @@ static int simplify_symbols(Elf_Shdr *sechdrs,
 		default:
 			/* Divert to percpu allocation if a percpu var. */
 			if (sym[i].st_shndx == pcpuindex)
-				secbase = (unsigned long)mod->percpu;
+				secbase = (unsigned long)mod_percpu(mod);
 			else
 				secbase = sechdrs[sym[i].st_shndx].sh_addr;
 			sym[i].st_value += secbase;
@@ -1949,7 +2020,7 @@ static noinline struct module *load_module(void __user *umod,
 	unsigned int modindex, versindex, infoindex, pcpuindex;
 	struct module *mod;
 	long err = 0;
-	void *percpu = NULL, *ptr = NULL; /* Stops spurious gcc warning */
+	void *ptr = NULL; /* Stops spurious gcc warning */
 	unsigned long symoffs, stroffs, *strmap;
 
 	mm_segment_t old_fs;
@@ -2089,15 +2160,11 @@ static noinline struct module *load_module(void __user *umod,
 
 	if (pcpuindex) {
 		/* We have a special allocation for this section. */
-		percpu = percpu_modalloc(sechdrs[pcpuindex].sh_size,
-					 sechdrs[pcpuindex].sh_addralign,
-					 mod->name);
-		if (!percpu) {
-			err = -ENOMEM;
+		err = percpu_modalloc(mod, sechdrs[pcpuindex].sh_size,
+				      sechdrs[pcpuindex].sh_addralign);
+		if (err)
 			goto free_mod;
-		}
 		sechdrs[pcpuindex].sh_flags &= ~(unsigned long)SHF_ALLOC;
-		mod->percpu = percpu;
 	}
 
 	/* Determine total sizes, and put offsets in sh_entsize.  For now
@@ -2162,9 +2229,8 @@ static noinline struct module *load_module(void __user *umod,
 	mod = (void *)sechdrs[modindex].sh_addr;
 	kmemleak_load_module(mod, hdr, sechdrs, secstrings);
 
-#if defined(CONFIG_MODULE_UNLOAD) && defined(CONFIG_SMP)
-	mod->refptr = percpu_modalloc(sizeof(local_t), __alignof__(local_t),
-				      mod->name);
+#if defined(CONFIG_MODULE_UNLOAD)
+	mod->refptr = alloc_percpu(struct module_ref);
 	if (!mod->refptr) {
 		err = -ENOMEM;
 		goto free_init;
@@ -2313,7 +2379,7 @@ static noinline struct module *load_module(void __user *umod,
 	sort_extable(mod->extable, mod->extable + mod->num_exentries);
 
 	/* Finally, copy percpu area over. */
-	percpu_modcopy(mod->percpu, (void *)sechdrs[pcpuindex].sh_addr,
+	percpu_modcopy(mod, (void *)sechdrs[pcpuindex].sh_addr,
 		       sechdrs[pcpuindex].sh_size);
 
 	add_kallsyms(mod, sechdrs, hdr->e_shnum, symindex, strindex,
@@ -2396,8 +2462,8 @@ static noinline struct module *load_module(void __user *umod,
 	kobject_put(&mod->mkobj.kobj);
  free_unload:
 	module_unload_free(mod);
-#if defined(CONFIG_MODULE_UNLOAD) && defined(CONFIG_SMP)
-	percpu_modfree(mod->refptr);
+#if defined(CONFIG_MODULE_UNLOAD)
+	free_percpu(mod->refptr);
  free_init:
 #endif
 	module_free(mod, mod->module_init);
@@ -2405,8 +2471,7 @@ static noinline struct module *load_module(void __user *umod,
 	module_free(mod, mod->module_core);
 	/* mod will be freed with core. Don't access it beyond this line! */
  free_percpu:
-	if (percpu)
-		percpu_modfree(percpu);
+	percpu_modfree(mod);
  free_mod:
 	kfree(args);
 	kfree(strmap);
diff --git a/kernel/notifier.c b/kernel/notifier.c
index acd24e7643e..2488ba7eb56 100644
--- a/kernel/notifier.c
+++ b/kernel/notifier.c
@@ -78,10 +78,10 @@ static int __kprobes notifier_call_chain(struct notifier_block **nl,
 	int ret = NOTIFY_DONE;
 	struct notifier_block *nb, *next_nb;
 
-	nb = rcu_dereference(*nl);
+	nb = rcu_dereference_raw(*nl);
 
 	while (nb && nr_to_call) {
-		next_nb = rcu_dereference(nb->next);
+		next_nb = rcu_dereference_raw(nb->next);
 
 #ifdef CONFIG_DEBUG_NOTIFIERS
 		if (unlikely(!func_ptr_is_kernel_text(nb->notifier_call))) {
@@ -309,7 +309,7 @@ int __blocking_notifier_call_chain(struct blocking_notifier_head *nh,
 	 * racy then it does not matter what the result of the test
 	 * is, we re-check the list after having taken the lock anyway:
 	 */
-	if (rcu_dereference(nh->head)) {
+	if (rcu_dereference_raw(nh->head)) {
 		down_read(&nh->rwsem);
 		ret = notifier_call_chain(&nh->head, val, v, nr_to_call,
 					nr_calls);
diff --git a/kernel/nsproxy.c b/kernel/nsproxy.c
index 09b4ff9711b..f74e6c00e26 100644
--- a/kernel/nsproxy.c
+++ b/kernel/nsproxy.c
@@ -13,6 +13,7 @@
  *             Pavel Emelianov <xemul@openvz.org>
  */
 
+#include <linux/slab.h>
 #include <linux/module.h>
 #include <linux/nsproxy.h>
 #include <linux/init_task.h>
@@ -24,7 +25,18 @@
 
 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/padata.c b/kernel/padata.c
new file mode 100644
index 00000000000..fd03513c732
--- /dev/null
+++ b/kernel/padata.c
@@ -0,0 +1,697 @@
+/*
+ * padata.c - generic interface to process data streams in parallel
+ *
+ * Copyright (C) 2008, 2009 secunet Security Networks AG
+ * Copyright (C) 2008, 2009 Steffen Klassert <steffen.klassert@secunet.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc.,
+ * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
+ */
+
+#include <linux/module.h>
+#include <linux/cpumask.h>
+#include <linux/err.h>
+#include <linux/cpu.h>
+#include <linux/padata.h>
+#include <linux/mutex.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/rcupdate.h>
+
+#define MAX_SEQ_NR INT_MAX - NR_CPUS
+#define MAX_OBJ_NUM 10000 * NR_CPUS
+
+static int padata_index_to_cpu(struct parallel_data *pd, int cpu_index)
+{
+	int cpu, target_cpu;
+
+	target_cpu = cpumask_first(pd->cpumask);
+	for (cpu = 0; cpu < cpu_index; cpu++)
+		target_cpu = cpumask_next(target_cpu, pd->cpumask);
+
+	return target_cpu;
+}
+
+static int padata_cpu_hash(struct padata_priv *padata)
+{
+	int cpu_index;
+	struct parallel_data *pd;
+
+	pd =  padata->pd;
+
+	/*
+	 * Hash the sequence numbers to the cpus by taking
+	 * seq_nr mod. number of cpus in use.
+	 */
+	cpu_index =  padata->seq_nr % cpumask_weight(pd->cpumask);
+
+	return padata_index_to_cpu(pd, cpu_index);
+}
+
+static void padata_parallel_worker(struct work_struct *work)
+{
+	struct padata_queue *queue;
+	struct parallel_data *pd;
+	struct padata_instance *pinst;
+	LIST_HEAD(local_list);
+
+	local_bh_disable();
+	queue = container_of(work, struct padata_queue, pwork);
+	pd = queue->pd;
+	pinst = pd->pinst;
+
+	spin_lock(&queue->parallel.lock);
+	list_replace_init(&queue->parallel.list, &local_list);
+	spin_unlock(&queue->parallel.lock);
+
+	while (!list_empty(&local_list)) {
+		struct padata_priv *padata;
+
+		padata = list_entry(local_list.next,
+				    struct padata_priv, list);
+
+		list_del_init(&padata->list);
+
+		padata->parallel(padata);
+	}
+
+	local_bh_enable();
+}
+
+/*
+ * padata_do_parallel - padata parallelization function
+ *
+ * @pinst: padata instance
+ * @padata: object to be parallelized
+ * @cb_cpu: cpu the serialization callback function will run on,
+ *          must be in the cpumask of padata.
+ *
+ * The parallelization callback function will run with BHs off.
+ * Note: Every object which is parallelized by padata_do_parallel
+ * must be seen by padata_do_serial.
+ */
+int padata_do_parallel(struct padata_instance *pinst,
+		       struct padata_priv *padata, int cb_cpu)
+{
+	int target_cpu, err;
+	struct padata_queue *queue;
+	struct parallel_data *pd;
+
+	rcu_read_lock_bh();
+
+	pd = rcu_dereference(pinst->pd);
+
+	err = 0;
+	if (!(pinst->flags & PADATA_INIT))
+		goto out;
+
+	err =  -EBUSY;
+	if ((pinst->flags & PADATA_RESET))
+		goto out;
+
+	if (atomic_read(&pd->refcnt) >= MAX_OBJ_NUM)
+		goto out;
+
+	err = -EINVAL;
+	if (!cpumask_test_cpu(cb_cpu, pd->cpumask))
+		goto out;
+
+	err = -EINPROGRESS;
+	atomic_inc(&pd->refcnt);
+	padata->pd = pd;
+	padata->cb_cpu = cb_cpu;
+
+	if (unlikely(atomic_read(&pd->seq_nr) == pd->max_seq_nr))
+		atomic_set(&pd->seq_nr, -1);
+
+	padata->seq_nr = atomic_inc_return(&pd->seq_nr);
+
+	target_cpu = padata_cpu_hash(padata);
+	queue = per_cpu_ptr(pd->queue, target_cpu);
+
+	spin_lock(&queue->parallel.lock);
+	list_add_tail(&padata->list, &queue->parallel.list);
+	spin_unlock(&queue->parallel.lock);
+
+	queue_work_on(target_cpu, pinst->wq, &queue->pwork);
+
+out:
+	rcu_read_unlock_bh();
+
+	return err;
+}
+EXPORT_SYMBOL(padata_do_parallel);
+
+static struct padata_priv *padata_get_next(struct parallel_data *pd)
+{
+	int cpu, num_cpus, empty, calc_seq_nr;
+	int seq_nr, next_nr, overrun, next_overrun;
+	struct padata_queue *queue, *next_queue;
+	struct padata_priv *padata;
+	struct padata_list *reorder;
+
+	empty = 0;
+	next_nr = -1;
+	next_overrun = 0;
+	next_queue = NULL;
+
+	num_cpus = cpumask_weight(pd->cpumask);
+
+	for_each_cpu(cpu, pd->cpumask) {
+		queue = per_cpu_ptr(pd->queue, cpu);
+		reorder = &queue->reorder;
+
+		/*
+		 * Calculate the seq_nr of the object that should be
+		 * next in this queue.
+		 */
+		overrun = 0;
+		calc_seq_nr = (atomic_read(&queue->num_obj) * num_cpus)
+			       + queue->cpu_index;
+
+		if (unlikely(calc_seq_nr > pd->max_seq_nr)) {
+			calc_seq_nr = calc_seq_nr - pd->max_seq_nr - 1;
+			overrun = 1;
+		}
+
+		if (!list_empty(&reorder->list)) {
+			padata = list_entry(reorder->list.next,
+					    struct padata_priv, list);
+
+			seq_nr  = padata->seq_nr;
+			BUG_ON(calc_seq_nr != seq_nr);
+		} else {
+			seq_nr = calc_seq_nr;
+			empty++;
+		}
+
+		if (next_nr < 0 || seq_nr < next_nr
+		    || (next_overrun && !overrun)) {
+			next_nr = seq_nr;
+			next_overrun = overrun;
+			next_queue = queue;
+		}
+	}
+
+	padata = NULL;
+
+	if (empty == num_cpus)
+		goto out;
+
+	reorder = &next_queue->reorder;
+
+	if (!list_empty(&reorder->list)) {
+		padata = list_entry(reorder->list.next,
+				    struct padata_priv, list);
+
+		if (unlikely(next_overrun)) {
+			for_each_cpu(cpu, pd->cpumask) {
+				queue = per_cpu_ptr(pd->queue, cpu);
+				atomic_set(&queue->num_obj, 0);
+			}
+		}
+
+		spin_lock(&reorder->lock);
+		list_del_init(&padata->list);
+		atomic_dec(&pd->reorder_objects);
+		spin_unlock(&reorder->lock);
+
+		atomic_inc(&next_queue->num_obj);
+
+		goto out;
+	}
+
+	if (next_nr % num_cpus == next_queue->cpu_index) {
+		padata = ERR_PTR(-ENODATA);
+		goto out;
+	}
+
+	padata = ERR_PTR(-EINPROGRESS);
+out:
+	return padata;
+}
+
+static void padata_reorder(struct parallel_data *pd)
+{
+	struct padata_priv *padata;
+	struct padata_queue *queue;
+	struct padata_instance *pinst = pd->pinst;
+
+try_again:
+	if (!spin_trylock_bh(&pd->lock))
+		goto out;
+
+	while (1) {
+		padata = padata_get_next(pd);
+
+		if (!padata || PTR_ERR(padata) == -EINPROGRESS)
+			break;
+
+		if (PTR_ERR(padata) == -ENODATA) {
+			spin_unlock_bh(&pd->lock);
+			goto out;
+		}
+
+		queue = per_cpu_ptr(pd->queue, padata->cb_cpu);
+
+		spin_lock(&queue->serial.lock);
+		list_add_tail(&padata->list, &queue->serial.list);
+		spin_unlock(&queue->serial.lock);
+
+		queue_work_on(padata->cb_cpu, pinst->wq, &queue->swork);
+	}
+
+	spin_unlock_bh(&pd->lock);
+
+	if (atomic_read(&pd->reorder_objects))
+		goto try_again;
+
+out:
+	return;
+}
+
+static void padata_serial_worker(struct work_struct *work)
+{
+	struct padata_queue *queue;
+	struct parallel_data *pd;
+	LIST_HEAD(local_list);
+
+	local_bh_disable();
+	queue = container_of(work, struct padata_queue, swork);
+	pd = queue->pd;
+
+	spin_lock(&queue->serial.lock);
+	list_replace_init(&queue->serial.list, &local_list);
+	spin_unlock(&queue->serial.lock);
+
+	while (!list_empty(&local_list)) {
+		struct padata_priv *padata;
+
+		padata = list_entry(local_list.next,
+				    struct padata_priv, list);
+
+		list_del_init(&padata->list);
+
+		padata->serial(padata);
+		atomic_dec(&pd->refcnt);
+	}
+	local_bh_enable();
+}
+
+/*
+ * padata_do_serial - padata serialization function
+ *
+ * @padata: object to be serialized.
+ *
+ * padata_do_serial must be called for every parallelized object.
+ * The serialization callback function will run with BHs off.
+ */
+void padata_do_serial(struct padata_priv *padata)
+{
+	int cpu;
+	struct padata_queue *queue;
+	struct parallel_data *pd;
+
+	pd = padata->pd;
+
+	cpu = get_cpu();
+	queue = per_cpu_ptr(pd->queue, cpu);
+
+	spin_lock(&queue->reorder.lock);
+	atomic_inc(&pd->reorder_objects);
+	list_add_tail(&padata->list, &queue->reorder.list);
+	spin_unlock(&queue->reorder.lock);
+
+	put_cpu();
+
+	padata_reorder(pd);
+}
+EXPORT_SYMBOL(padata_do_serial);
+
+static struct parallel_data *padata_alloc_pd(struct padata_instance *pinst,
+					     const struct cpumask *cpumask)
+{
+	int cpu, cpu_index, num_cpus;
+	struct padata_queue *queue;
+	struct parallel_data *pd;
+
+	cpu_index = 0;
+
+	pd = kzalloc(sizeof(struct parallel_data), GFP_KERNEL);
+	if (!pd)
+		goto err;
+
+	pd->queue = alloc_percpu(struct padata_queue);
+	if (!pd->queue)
+		goto err_free_pd;
+
+	if (!alloc_cpumask_var(&pd->cpumask, GFP_KERNEL))
+		goto err_free_queue;
+
+	for_each_possible_cpu(cpu) {
+		queue = per_cpu_ptr(pd->queue, cpu);
+
+		queue->pd = pd;
+
+		if (cpumask_test_cpu(cpu, cpumask)
+		    && cpumask_test_cpu(cpu, cpu_active_mask)) {
+			queue->cpu_index = cpu_index;
+			cpu_index++;
+		} else
+			queue->cpu_index = -1;
+
+		INIT_LIST_HEAD(&queue->reorder.list);
+		INIT_LIST_HEAD(&queue->parallel.list);
+		INIT_LIST_HEAD(&queue->serial.list);
+		spin_lock_init(&queue->reorder.lock);
+		spin_lock_init(&queue->parallel.lock);
+		spin_lock_init(&queue->serial.lock);
+
+		INIT_WORK(&queue->pwork, padata_parallel_worker);
+		INIT_WORK(&queue->swork, padata_serial_worker);
+		atomic_set(&queue->num_obj, 0);
+	}
+
+	cpumask_and(pd->cpumask, cpumask, cpu_active_mask);
+
+	num_cpus = cpumask_weight(pd->cpumask);
+	pd->max_seq_nr = (MAX_SEQ_NR / num_cpus) * num_cpus - 1;
+
+	atomic_set(&pd->seq_nr, -1);
+	atomic_set(&pd->reorder_objects, 0);
+	atomic_set(&pd->refcnt, 0);
+	pd->pinst = pinst;
+	spin_lock_init(&pd->lock);
+
+	return pd;
+
+err_free_queue:
+	free_percpu(pd->queue);
+err_free_pd:
+	kfree(pd);
+err:
+	return NULL;
+}
+
+static void padata_free_pd(struct parallel_data *pd)
+{
+	free_cpumask_var(pd->cpumask);
+	free_percpu(pd->queue);
+	kfree(pd);
+}
+
+static void padata_replace(struct padata_instance *pinst,
+			   struct parallel_data *pd_new)
+{
+	struct parallel_data *pd_old = pinst->pd;
+
+	pinst->flags |= PADATA_RESET;
+
+	rcu_assign_pointer(pinst->pd, pd_new);
+
+	synchronize_rcu();
+
+	while (atomic_read(&pd_old->refcnt) != 0)
+		yield();
+
+	flush_workqueue(pinst->wq);
+
+	padata_free_pd(pd_old);
+
+	pinst->flags &= ~PADATA_RESET;
+}
+
+/*
+ * padata_set_cpumask - set the cpumask that padata should use
+ *
+ * @pinst: padata instance
+ * @cpumask: the cpumask to use
+ */
+int padata_set_cpumask(struct padata_instance *pinst,
+			cpumask_var_t cpumask)
+{
+	struct parallel_data *pd;
+	int err = 0;
+
+	might_sleep();
+
+	mutex_lock(&pinst->lock);
+
+	pd = padata_alloc_pd(pinst, cpumask);
+	if (!pd) {
+		err = -ENOMEM;
+		goto out;
+	}
+
+	cpumask_copy(pinst->cpumask, cpumask);
+
+	padata_replace(pinst, pd);
+
+out:
+	mutex_unlock(&pinst->lock);
+
+	return err;
+}
+EXPORT_SYMBOL(padata_set_cpumask);
+
+static int __padata_add_cpu(struct padata_instance *pinst, int cpu)
+{
+	struct parallel_data *pd;
+
+	if (cpumask_test_cpu(cpu, cpu_active_mask)) {
+		pd = padata_alloc_pd(pinst, pinst->cpumask);
+		if (!pd)
+			return -ENOMEM;
+
+		padata_replace(pinst, pd);
+	}
+
+	return 0;
+}
+
+/*
+ * padata_add_cpu - add a cpu to the padata cpumask
+ *
+ * @pinst: padata instance
+ * @cpu: cpu to add
+ */
+int padata_add_cpu(struct padata_instance *pinst, int cpu)
+{
+	int err;
+
+	might_sleep();
+
+	mutex_lock(&pinst->lock);
+
+	cpumask_set_cpu(cpu, pinst->cpumask);
+	err = __padata_add_cpu(pinst, cpu);
+
+	mutex_unlock(&pinst->lock);
+
+	return err;
+}
+EXPORT_SYMBOL(padata_add_cpu);
+
+static int __padata_remove_cpu(struct padata_instance *pinst, int cpu)
+{
+	struct parallel_data *pd;
+
+	if (cpumask_test_cpu(cpu, cpu_online_mask)) {
+		pd = padata_alloc_pd(pinst, pinst->cpumask);
+		if (!pd)
+			return -ENOMEM;
+
+		padata_replace(pinst, pd);
+	}
+
+	return 0;
+}
+
+/*
+ * padata_remove_cpu - remove a cpu from the padata cpumask
+ *
+ * @pinst: padata instance
+ * @cpu: cpu to remove
+ */
+int padata_remove_cpu(struct padata_instance *pinst, int cpu)
+{
+	int err;
+
+	might_sleep();
+
+	mutex_lock(&pinst->lock);
+
+	cpumask_clear_cpu(cpu, pinst->cpumask);
+	err = __padata_remove_cpu(pinst, cpu);
+
+	mutex_unlock(&pinst->lock);
+
+	return err;
+}
+EXPORT_SYMBOL(padata_remove_cpu);
+
+/*
+ * padata_start - start the parallel processing
+ *
+ * @pinst: padata instance to start
+ */
+void padata_start(struct padata_instance *pinst)
+{
+	might_sleep();
+
+	mutex_lock(&pinst->lock);
+	pinst->flags |= PADATA_INIT;
+	mutex_unlock(&pinst->lock);
+}
+EXPORT_SYMBOL(padata_start);
+
+/*
+ * padata_stop - stop the parallel processing
+ *
+ * @pinst: padata instance to stop
+ */
+void padata_stop(struct padata_instance *pinst)
+{
+	might_sleep();
+
+	mutex_lock(&pinst->lock);
+	pinst->flags &= ~PADATA_INIT;
+	mutex_unlock(&pinst->lock);
+}
+EXPORT_SYMBOL(padata_stop);
+
+static int __cpuinit padata_cpu_callback(struct notifier_block *nfb,
+					 unsigned long action, void *hcpu)
+{
+	int err;
+	struct padata_instance *pinst;
+	int cpu = (unsigned long)hcpu;
+
+	pinst = container_of(nfb, struct padata_instance, cpu_notifier);
+
+	switch (action) {
+	case CPU_ONLINE:
+	case CPU_ONLINE_FROZEN:
+		if (!cpumask_test_cpu(cpu, pinst->cpumask))
+			break;
+		mutex_lock(&pinst->lock);
+		err = __padata_add_cpu(pinst, cpu);
+		mutex_unlock(&pinst->lock);
+		if (err)
+			return NOTIFY_BAD;
+		break;
+
+	case CPU_DOWN_PREPARE:
+	case CPU_DOWN_PREPARE_FROZEN:
+		if (!cpumask_test_cpu(cpu, pinst->cpumask))
+			break;
+		mutex_lock(&pinst->lock);
+		err = __padata_remove_cpu(pinst, cpu);
+		mutex_unlock(&pinst->lock);
+		if (err)
+			return NOTIFY_BAD;
+		break;
+
+	case CPU_UP_CANCELED:
+	case CPU_UP_CANCELED_FROZEN:
+		if (!cpumask_test_cpu(cpu, pinst->cpumask))
+			break;
+		mutex_lock(&pinst->lock);
+		__padata_remove_cpu(pinst, cpu);
+		mutex_unlock(&pinst->lock);
+
+	case CPU_DOWN_FAILED:
+	case CPU_DOWN_FAILED_FROZEN:
+		if (!cpumask_test_cpu(cpu, pinst->cpumask))
+			break;
+		mutex_lock(&pinst->lock);
+		__padata_add_cpu(pinst, cpu);
+		mutex_unlock(&pinst->lock);
+	}
+
+	return NOTIFY_OK;
+}
+
+/*
+ * padata_alloc - allocate and initialize a padata instance
+ *
+ * @cpumask: cpumask that padata uses for parallelization
+ * @wq: workqueue to use for the allocated padata instance
+ */
+struct padata_instance *padata_alloc(const struct cpumask *cpumask,
+				     struct workqueue_struct *wq)
+{
+	int err;
+	struct padata_instance *pinst;
+	struct parallel_data *pd;
+
+	pinst = kzalloc(sizeof(struct padata_instance), GFP_KERNEL);
+	if (!pinst)
+		goto err;
+
+	pd = padata_alloc_pd(pinst, cpumask);
+	if (!pd)
+		goto err_free_inst;
+
+	if (!alloc_cpumask_var(&pinst->cpumask, GFP_KERNEL))
+		goto err_free_pd;
+
+	rcu_assign_pointer(pinst->pd, pd);
+
+	pinst->wq = wq;
+
+	cpumask_copy(pinst->cpumask, cpumask);
+
+	pinst->flags = 0;
+
+	pinst->cpu_notifier.notifier_call = padata_cpu_callback;
+	pinst->cpu_notifier.priority = 0;
+	err = register_hotcpu_notifier(&pinst->cpu_notifier);
+	if (err)
+		goto err_free_cpumask;
+
+	mutex_init(&pinst->lock);
+
+	return pinst;
+
+err_free_cpumask:
+	free_cpumask_var(pinst->cpumask);
+err_free_pd:
+	padata_free_pd(pd);
+err_free_inst:
+	kfree(pinst);
+err:
+	return NULL;
+}
+EXPORT_SYMBOL(padata_alloc);
+
+/*
+ * padata_free - free a padata instance
+ *
+ * @ padata_inst: padata instance to free
+ */
+void padata_free(struct padata_instance *pinst)
+{
+	padata_stop(pinst);
+
+	synchronize_rcu();
+
+	while (atomic_read(&pinst->pd->refcnt) != 0)
+		yield();
+
+	unregister_hotcpu_notifier(&pinst->cpu_notifier);
+	padata_free_pd(pinst->pd);
+	free_cpumask_var(pinst->cpumask);
+	kfree(pinst);
+}
+EXPORT_SYMBOL(padata_free);
diff --git a/kernel/panic.c b/kernel/panic.c
index c787333282b..13d966b4c14 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -36,15 +36,36 @@ ATOMIC_NOTIFIER_HEAD(panic_notifier_list);
 
 EXPORT_SYMBOL(panic_notifier_list);
 
-static long no_blink(long time)
-{
-	return 0;
-}
-
 /* Returns how long it waited in ms */
 long (*panic_blink)(long time);
 EXPORT_SYMBOL(panic_blink);
 
+static void panic_blink_one_second(void)
+{
+	static long i = 0, end;
+
+	if (panic_blink) {
+		end = i + MSEC_PER_SEC;
+
+		while (i < end) {
+			i += panic_blink(i);
+			mdelay(1);
+			i++;
+		}
+	} else {
+		/*
+		 * When running under a hypervisor a small mdelay may get
+		 * rounded up to the hypervisor timeslice. For example, with
+		 * a 1ms in 10ms hypervisor timeslice we might inflate a
+		 * mdelay(1) loop by 10x.
+		 *
+		 * If we have nothing to blink, spin on 1 second calls to
+		 * mdelay to avoid this.
+		 */
+		mdelay(MSEC_PER_SEC);
+	}
+}
+
 /**
  *	panic - halt the system
  *	@fmt: The text string to print
@@ -95,9 +116,6 @@ NORET_TYPE void panic(const char * fmt, ...)
 
 	bust_spinlocks(0);
 
-	if (!panic_blink)
-		panic_blink = no_blink;
-
 	if (panic_timeout > 0) {
 		/*
 		 * Delay timeout seconds before rebooting the machine.
@@ -105,11 +123,9 @@ NORET_TYPE void panic(const char * fmt, ...)
 		 */
 		printk(KERN_EMERG "Rebooting in %d seconds..", panic_timeout);
 
-		for (i = 0; i < panic_timeout*1000; ) {
+		for (i = 0; i < panic_timeout; i++) {
 			touch_nmi_watchdog();
-			i += panic_blink(i);
-			mdelay(1);
-			i++;
+			panic_blink_one_second();
 		}
 		/*
 		 * This will not be a clean reboot, with everything
@@ -135,11 +151,9 @@ NORET_TYPE void panic(const char * fmt, ...)
 	}
 #endif
 	local_irq_enable();
-	for (i = 0; ; ) {
+	while (1) {
 		touch_softlockup_watchdog();
-		i += panic_blink(i);
-		mdelay(1);
-		i++;
+		panic_blink_one_second();
 	}
 }
 
diff --git a/kernel/params.c b/kernel/params.c
index cf1b6918312..0b30ecd53a5 100644
--- a/kernel/params.c
+++ b/kernel/params.c
@@ -24,7 +24,6 @@
 #include <linux/err.h>
 #include <linux/slab.h>
 #include <linux/ctype.h>
-#include <linux/string.h>
 
 #if 0
 #define DEBUGP printk
@@ -402,8 +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[];
 
@@ -421,7 +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)
@@ -517,6 +516,7 @@ static __modinit int add_sysfs_param(struct module_kobject *mk,
 	new->grp.attrs = attrs;
 
 	/* Tack new one on the end. */
+	sysfs_attr_init(&new->attrs[num].mattr.attr);
 	new->attrs[num].param = kp;
 	new->attrs[num].mattr.show = param_attr_show;
 	new->attrs[num].mattr.store = param_attr_store;
@@ -723,7 +723,7 @@ static ssize_t module_attr_store(struct kobject *kobj,
 	return ret;
 }
 
-static struct sysfs_ops module_sysfs_ops = {
+static const struct sysfs_ops module_sysfs_ops = {
 	.show = module_attr_show,
 	.store = module_attr_store,
 };
@@ -737,7 +737,7 @@ static int uevent_filter(struct kset *kset, struct kobject *kobj)
 	return 0;
 }
 
-static struct kset_uevent_ops module_uevent_ops = {
+static const struct kset_uevent_ops module_uevent_ops = {
 	.filter = uevent_filter,
 };
 
diff --git a/kernel/perf_event.c b/kernel/perf_event.c
index 087025fe3ba..3d1552d3c12 100644
--- a/kernel/perf_event.c
+++ b/kernel/perf_event.c
@@ -15,6 +15,7 @@
 #include <linux/smp.h>
 #include <linux/file.h>
 #include <linux/poll.h>
+#include <linux/slab.h>
 #include <linux/sysfs.h>
 #include <linux/dcache.h>
 #include <linux/percpu.h>
@@ -56,21 +57,6 @@ static atomic_t nr_task_events __read_mostly;
  */
 int sysctl_perf_event_paranoid __read_mostly = 1;
 
-static inline bool perf_paranoid_tracepoint_raw(void)
-{
-	return sysctl_perf_event_paranoid > -1;
-}
-
-static inline bool perf_paranoid_cpu(void)
-{
-	return sysctl_perf_event_paranoid > 0;
-}
-
-static inline bool perf_paranoid_kernel(void)
-{
-	return sysctl_perf_event_paranoid > 1;
-}
-
 int sysctl_perf_event_mlock __read_mostly = 512; /* 'free' kb per user */
 
 /*
@@ -96,13 +82,10 @@ extern __weak const struct pmu *hw_perf_event_init(struct perf_event *event)
 void __weak hw_perf_disable(void)		{ barrier(); }
 void __weak hw_perf_enable(void)		{ barrier(); }
 
-void __weak hw_perf_event_setup(int cpu)	{ barrier(); }
-void __weak hw_perf_event_setup_online(int cpu)	{ barrier(); }
-
 int __weak
 hw_perf_group_sched_in(struct perf_event *group_leader,
 	       struct perf_cpu_context *cpuctx,
-	       struct perf_event_context *ctx, int cpu)
+	       struct perf_event_context *ctx)
 {
 	return 0;
 }
@@ -111,25 +94,15 @@ void __weak perf_event_print_debug(void)	{ }
 
 static DEFINE_PER_CPU(int, perf_disable_count);
 
-void __perf_disable(void)
-{
-	__get_cpu_var(perf_disable_count)++;
-}
-
-bool __perf_enable(void)
-{
-	return !--__get_cpu_var(perf_disable_count);
-}
-
 void perf_disable(void)
 {
-	__perf_disable();
-	hw_perf_disable();
+	if (!__get_cpu_var(perf_disable_count)++)
+		hw_perf_disable();
 }
 
 void perf_enable(void)
 {
-	if (__perf_enable())
+	if (!--__get_cpu_var(perf_disable_count))
 		hw_perf_enable();
 }
 
@@ -248,7 +221,7 @@ static void perf_unpin_context(struct perf_event_context *ctx)
 
 static inline u64 perf_clock(void)
 {
-	return cpu_clock(smp_processor_id());
+	return cpu_clock(raw_smp_processor_id());
 }
 
 /*
@@ -632,14 +605,13 @@ void perf_event_disable(struct perf_event *event)
 static int
 event_sched_in(struct perf_event *event,
 		 struct perf_cpu_context *cpuctx,
-		 struct perf_event_context *ctx,
-		 int cpu)
+		 struct perf_event_context *ctx)
 {
 	if (event->state <= PERF_EVENT_STATE_OFF)
 		return 0;
 
 	event->state = PERF_EVENT_STATE_ACTIVE;
-	event->oncpu = cpu;	/* TODO: put 'cpu' into cpuctx->cpu */
+	event->oncpu = smp_processor_id();
 	/*
 	 * The new state must be visible before we turn it on in the hardware:
 	 */
@@ -666,8 +638,7 @@ event_sched_in(struct perf_event *event,
 static int
 group_sched_in(struct perf_event *group_event,
 	       struct perf_cpu_context *cpuctx,
-	       struct perf_event_context *ctx,
-	       int cpu)
+	       struct perf_event_context *ctx)
 {
 	struct perf_event *event, *partial_group;
 	int ret;
@@ -675,18 +646,18 @@ group_sched_in(struct perf_event *group_event,
 	if (group_event->state == PERF_EVENT_STATE_OFF)
 		return 0;
 
-	ret = hw_perf_group_sched_in(group_event, cpuctx, ctx, cpu);
+	ret = hw_perf_group_sched_in(group_event, cpuctx, ctx);
 	if (ret)
 		return ret < 0 ? ret : 0;
 
-	if (event_sched_in(group_event, cpuctx, ctx, cpu))
+	if (event_sched_in(group_event, cpuctx, ctx))
 		return -EAGAIN;
 
 	/*
 	 * Schedule in siblings as one group (if any):
 	 */
 	list_for_each_entry(event, &group_event->sibling_list, group_entry) {
-		if (event_sched_in(event, cpuctx, ctx, cpu)) {
+		if (event_sched_in(event, cpuctx, ctx)) {
 			partial_group = event;
 			goto group_error;
 		}
@@ -760,7 +731,6 @@ static void __perf_install_in_context(void *info)
 	struct perf_event *event = info;
 	struct perf_event_context *ctx = event->ctx;
 	struct perf_event *leader = event->group_leader;
-	int cpu = smp_processor_id();
 	int err;
 
 	/*
@@ -807,7 +777,7 @@ static void __perf_install_in_context(void *info)
 	if (!group_can_go_on(event, cpuctx, 1))
 		err = -EEXIST;
 	else
-		err = event_sched_in(event, cpuctx, ctx, cpu);
+		err = event_sched_in(event, cpuctx, ctx);
 
 	if (err) {
 		/*
@@ -949,11 +919,9 @@ static void __perf_event_enable(void *info)
 	} else {
 		perf_disable();
 		if (event == leader)
-			err = group_sched_in(event, cpuctx, ctx,
-					     smp_processor_id());
+			err = group_sched_in(event, cpuctx, ctx);
 		else
-			err = event_sched_in(event, cpuctx, ctx,
-					       smp_processor_id());
+			err = event_sched_in(event, cpuctx, ctx);
 		perf_enable();
 	}
 
@@ -1197,11 +1165,9 @@ void perf_event_task_sched_out(struct task_struct *task,
 	struct perf_event_context *ctx = task->perf_event_ctxp;
 	struct perf_event_context *next_ctx;
 	struct perf_event_context *parent;
-	struct pt_regs *regs;
 	int do_switch = 1;
 
-	regs = task_pt_regs(task);
-	perf_sw_event(PERF_COUNT_SW_CONTEXT_SWITCHES, 1, 1, regs, 0);
+	perf_sw_event(PERF_COUNT_SW_CONTEXT_SWITCHES, 1, 1, NULL, 0);
 
 	if (likely(!ctx || !cpuctx->task_ctx))
 		return;
@@ -1280,19 +1246,18 @@ static void cpu_ctx_sched_out(struct perf_cpu_context *cpuctx,
 
 static void
 ctx_pinned_sched_in(struct perf_event_context *ctx,
-		    struct perf_cpu_context *cpuctx,
-		    int cpu)
+		    struct perf_cpu_context *cpuctx)
 {
 	struct perf_event *event;
 
 	list_for_each_entry(event, &ctx->pinned_groups, group_entry) {
 		if (event->state <= PERF_EVENT_STATE_OFF)
 			continue;
-		if (event->cpu != -1 && event->cpu != cpu)
+		if (event->cpu != -1 && event->cpu != smp_processor_id())
 			continue;
 
 		if (group_can_go_on(event, cpuctx, 1))
-			group_sched_in(event, cpuctx, ctx, cpu);
+			group_sched_in(event, cpuctx, ctx);
 
 		/*
 		 * If this pinned group hasn't been scheduled,
@@ -1307,8 +1272,7 @@ ctx_pinned_sched_in(struct perf_event_context *ctx,
 
 static void
 ctx_flexible_sched_in(struct perf_event_context *ctx,
-		      struct perf_cpu_context *cpuctx,
-		      int cpu)
+		      struct perf_cpu_context *cpuctx)
 {
 	struct perf_event *event;
 	int can_add_hw = 1;
@@ -1321,11 +1285,11 @@ ctx_flexible_sched_in(struct perf_event_context *ctx,
 		 * Listen to the 'cpu' scheduling filter constraint
 		 * of events:
 		 */
-		if (event->cpu != -1 && event->cpu != cpu)
+		if (event->cpu != -1 && event->cpu != smp_processor_id())
 			continue;
 
 		if (group_can_go_on(event, cpuctx, can_add_hw))
-			if (group_sched_in(event, cpuctx, ctx, cpu))
+			if (group_sched_in(event, cpuctx, ctx))
 				can_add_hw = 0;
 	}
 }
@@ -1335,8 +1299,6 @@ ctx_sched_in(struct perf_event_context *ctx,
 	     struct perf_cpu_context *cpuctx,
 	     enum event_type_t event_type)
 {
-	int cpu = smp_processor_id();
-
 	raw_spin_lock(&ctx->lock);
 	ctx->is_active = 1;
 	if (likely(!ctx->nr_events))
@@ -1351,11 +1313,11 @@ ctx_sched_in(struct perf_event_context *ctx,
 	 * in order to give them the best chance of going on.
 	 */
 	if (event_type & EVENT_PINNED)
-		ctx_pinned_sched_in(ctx, cpuctx, cpu);
+		ctx_pinned_sched_in(ctx, cpuctx);
 
 	/* Then walk through the lower prio flexible groups */
 	if (event_type & EVENT_FLEXIBLE)
-		ctx_flexible_sched_in(ctx, cpuctx, cpu);
+		ctx_flexible_sched_in(ctx, cpuctx);
 
 	perf_enable();
  out:
@@ -1493,6 +1455,22 @@ do {					\
 	return div64_u64(dividend, divisor);
 }
 
+static void perf_event_stop(struct perf_event *event)
+{
+	if (!event->pmu->stop)
+		return event->pmu->disable(event);
+
+	return event->pmu->stop(event);
+}
+
+static int perf_event_start(struct perf_event *event)
+{
+	if (!event->pmu->start)
+		return event->pmu->enable(event);
+
+	return event->pmu->start(event);
+}
+
 static void perf_adjust_period(struct perf_event *event, u64 nsec, u64 count)
 {
 	struct hw_perf_event *hwc = &event->hw;
@@ -1513,9 +1491,9 @@ static void perf_adjust_period(struct perf_event *event, u64 nsec, u64 count)
 
 	if (atomic64_read(&hwc->period_left) > 8*sample_period) {
 		perf_disable();
-		event->pmu->disable(event);
+		perf_event_stop(event);
 		atomic64_set(&hwc->period_left, 0);
-		event->pmu->enable(event);
+		perf_event_start(event);
 		perf_enable();
 	}
 }
@@ -1545,12 +1523,15 @@ static void perf_ctx_adjust_freq(struct perf_event_context *ctx)
 		 */
 		if (interrupts == MAX_INTERRUPTS) {
 			perf_log_throttle(event, 1);
+			perf_disable();
 			event->pmu->unthrottle(event);
+			perf_enable();
 		}
 
 		if (!event->attr.freq || !event->attr.sample_freq)
 			continue;
 
+		perf_disable();
 		event->pmu->read(event);
 		now = atomic64_read(&event->count);
 		delta = now - hwc->freq_count_stamp;
@@ -1558,6 +1539,7 @@ static void perf_ctx_adjust_freq(struct perf_event_context *ctx)
 
 		if (delta > 0)
 			perf_adjust_period(event, TICK_NSEC, delta);
+		perf_enable();
 	}
 	raw_spin_unlock(&ctx->lock);
 }
@@ -1567,9 +1549,6 @@ static void perf_ctx_adjust_freq(struct perf_event_context *ctx)
  */
 static void rotate_ctx(struct perf_event_context *ctx)
 {
-	if (!ctx->nr_events)
-		return;
-
 	raw_spin_lock(&ctx->lock);
 
 	/* Rotate the first entry last of non-pinned groups */
@@ -1582,19 +1561,28 @@ void perf_event_task_tick(struct task_struct *curr)
 {
 	struct perf_cpu_context *cpuctx;
 	struct perf_event_context *ctx;
+	int rotate = 0;
 
 	if (!atomic_read(&nr_events))
 		return;
 
 	cpuctx = &__get_cpu_var(perf_cpu_context);
-	ctx = curr->perf_event_ctxp;
+	if (cpuctx->ctx.nr_events &&
+	    cpuctx->ctx.nr_events != cpuctx->ctx.nr_active)
+		rotate = 1;
 
-	perf_disable();
+	ctx = curr->perf_event_ctxp;
+	if (ctx && ctx->nr_events && ctx->nr_events != ctx->nr_active)
+		rotate = 1;
 
 	perf_ctx_adjust_freq(&cpuctx->ctx);
 	if (ctx)
 		perf_ctx_adjust_freq(ctx);
 
+	if (!rotate)
+		return;
+
+	perf_disable();
 	cpu_ctx_sched_out(cpuctx, EVENT_FLEXIBLE);
 	if (ctx)
 		task_ctx_sched_out(ctx, EVENT_FLEXIBLE);
@@ -1606,7 +1594,6 @@ void perf_event_task_tick(struct task_struct *curr)
 	cpu_ctx_sched_in(cpuctx, EVENT_FLEXIBLE);
 	if (ctx)
 		task_ctx_sched_in(curr, EVENT_FLEXIBLE);
-
 	perf_enable();
 }
 
@@ -2602,7 +2589,7 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma)
 	if (user_locked > user_lock_limit)
 		extra = user_locked - user_lock_limit;
 
-	lock_limit = current->signal->rlim[RLIMIT_MEMLOCK].rlim_cur;
+	lock_limit = rlimit(RLIMIT_MEMLOCK);
 	lock_limit >>= PAGE_SHIFT;
 	locked = vma->vm_mm->locked_vm + extra;
 
@@ -2798,6 +2785,12 @@ __weak struct perf_callchain_entry *perf_callchain(struct pt_regs *regs)
 	return NULL;
 }
 
+__weak
+void perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned long ip, int skip)
+{
+}
+
+
 /*
  * Output
  */
@@ -3383,15 +3376,23 @@ static void perf_event_task_output(struct perf_event *event,
 				     struct perf_task_event *task_event)
 {
 	struct perf_output_handle handle;
-	int size;
 	struct task_struct *task = task_event->task;
-	int ret;
+	unsigned long flags;
+	int size, ret;
+
+	/*
+	 * If this CPU attempts to acquire an rq lock held by a CPU spinning
+	 * in perf_output_lock() from interrupt context, it's game over.
+	 */
+	local_irq_save(flags);
 
 	size  = task_event->event_id.header.size;
 	ret = perf_output_begin(&handle, event, size, 0, 0);
 
-	if (ret)
+	if (ret) {
+		local_irq_restore(flags);
 		return;
+	}
 
 	task_event->event_id.pid = perf_event_pid(event, task);
 	task_event->event_id.ppid = perf_event_pid(event, current);
@@ -3399,16 +3400,15 @@ static void perf_event_task_output(struct perf_event *event,
 	task_event->event_id.tid = perf_event_tid(event, task);
 	task_event->event_id.ptid = perf_event_tid(event, current);
 
-	task_event->event_id.time = perf_clock();
-
 	perf_output_put(&handle, task_event->event_id);
 
 	perf_output_end(&handle);
+	local_irq_restore(flags);
 }
 
 static int perf_event_task_match(struct perf_event *event)
 {
-	if (event->state != PERF_EVENT_STATE_ACTIVE)
+	if (event->state < PERF_EVENT_STATE_INACTIVE)
 		return 0;
 
 	if (event->cpu != -1 && event->cpu != smp_processor_id())
@@ -3440,7 +3440,7 @@ static void perf_event_task_event(struct perf_task_event *task_event)
 	cpuctx = &get_cpu_var(perf_cpu_context);
 	perf_event_task_ctx(&cpuctx->ctx, task_event);
 	if (!ctx)
-		ctx = rcu_dereference(task_event->task->perf_event_ctxp);
+		ctx = rcu_dereference(current->perf_event_ctxp);
 	if (ctx)
 		perf_event_task_ctx(ctx, task_event);
 	put_cpu_var(perf_cpu_context);
@@ -3471,6 +3471,7 @@ static void perf_event_task(struct task_struct *task,
 			/* .ppid */
 			/* .tid  */
 			/* .ptid */
+			.time = perf_clock(),
 		},
 	};
 
@@ -3520,7 +3521,7 @@ static void perf_event_comm_output(struct perf_event *event,
 
 static int perf_event_comm_match(struct perf_event *event)
 {
-	if (event->state != PERF_EVENT_STATE_ACTIVE)
+	if (event->state < PERF_EVENT_STATE_INACTIVE)
 		return 0;
 
 	if (event->cpu != -1 && event->cpu != smp_processor_id())
@@ -3640,7 +3641,7 @@ static void perf_event_mmap_output(struct perf_event *event,
 static int perf_event_mmap_match(struct perf_event *event,
 				   struct perf_mmap_event *mmap_event)
 {
-	if (event->state != PERF_EVENT_STATE_ACTIVE)
+	if (event->state < PERF_EVENT_STATE_INACTIVE)
 		return 0;
 
 	if (event->cpu != -1 && event->cpu != smp_processor_id())
@@ -3749,7 +3750,7 @@ void __perf_event_mmap(struct vm_area_struct *vma)
 			/* .tid */
 			.start  = vma->vm_start,
 			.len    = vma->vm_end - vma->vm_start,
-			.pgoff  = vma->vm_pgoff,
+			.pgoff  = (u64)vma->vm_pgoff << PAGE_SHIFT,
 		},
 	};
 
@@ -4116,8 +4117,7 @@ void __perf_sw_event(u32 event_id, u64 nr, int nmi,
 	if (rctx < 0)
 		return;
 
-	data.addr = addr;
-	data.raw  = NULL;
+	perf_sample_data_init(&data, addr);
 
 	do_perf_sw_event(PERF_TYPE_SOFTWARE, event_id, nr, nmi, &data, regs);
 
@@ -4162,11 +4162,10 @@ static enum hrtimer_restart perf_swevent_hrtimer(struct hrtimer *hrtimer)
 	struct perf_event *event;
 	u64 period;
 
-	event	= container_of(hrtimer, struct perf_event, hw.hrtimer);
+	event = container_of(hrtimer, struct perf_event, hw.hrtimer);
 	event->pmu->read(event);
 
-	data.addr = 0;
-	data.raw = NULL;
+	perf_sample_data_init(&data, 0);
 	data.period = event->hw.last_period;
 	regs = get_irq_regs();
 	/*
@@ -4328,26 +4327,20 @@ static const struct pmu perf_ops_task_clock = {
 #ifdef CONFIG_EVENT_TRACING
 
 void perf_tp_event(int event_id, u64 addr, u64 count, void *record,
-			  int entry_size)
+		   int entry_size, struct pt_regs *regs)
 {
+	struct perf_sample_data data;
 	struct perf_raw_record raw = {
 		.size = entry_size,
 		.data = record,
 	};
 
-	struct perf_sample_data data = {
-		.addr = addr,
-		.raw = &raw,
-	};
-
-	struct pt_regs *regs = get_irq_regs();
-
-	if (!regs)
-		regs = task_pt_regs(current);
+	perf_sample_data_init(&data, addr);
+	data.raw = &raw;
 
 	/* Trace events already protected against recursion */
 	do_perf_sw_event(PERF_TYPE_TRACEPOINT, event_id, count, 1,
-				&data, regs);
+			 &data, regs);
 }
 EXPORT_SYMBOL_GPL(perf_tp_event);
 
@@ -4363,7 +4356,7 @@ static int perf_tp_event_match(struct perf_event *event,
 
 static void tp_perf_event_destroy(struct perf_event *event)
 {
-	ftrace_profile_disable(event->attr.config);
+	perf_trace_disable(event->attr.config);
 }
 
 static const struct pmu *tp_perf_event_init(struct perf_event *event)
@@ -4377,7 +4370,7 @@ static const struct pmu *tp_perf_event_init(struct perf_event *event)
 			!capable(CAP_SYS_ADMIN))
 		return ERR_PTR(-EPERM);
 
-	if (ftrace_profile_enable(event->attr.config))
+	if (perf_trace_enable(event->attr.config))
 		return NULL;
 
 	event->destroy = tp_perf_event_destroy;
@@ -4456,8 +4449,7 @@ void perf_bp_event(struct perf_event *bp, void *data)
 	struct perf_sample_data sample;
 	struct pt_regs *regs = data;
 
-	sample.raw = NULL;
-	sample.addr = bp->attr.bp_addr;
+	perf_sample_data_init(&sample, bp->attr.bp_addr);
 
 	if (!perf_exclude_event(bp, regs))
 		perf_swevent_add(bp, 1, 1, &sample, regs);
@@ -4720,7 +4712,7 @@ static int perf_copy_attr(struct perf_event_attr __user *uattr,
 	if (attr->type >= PERF_TYPE_MAX)
 		return -EINVAL;
 
-	if (attr->__reserved_1 || attr->__reserved_2)
+	if (attr->__reserved_1)
 		return -EINVAL;
 
 	if (attr->sample_type & ~(PERF_SAMPLE_MAX-1))
@@ -4905,7 +4897,7 @@ err_fput_free_put_context:
 
 err_free_put_context:
 	if (err < 0)
-		kfree(event);
+		free_event(event);
 
 err_put_context:
 	if (err < 0)
@@ -5385,18 +5377,26 @@ int perf_event_init_task(struct task_struct *child)
 	return ret;
 }
 
+static void __init perf_event_init_all_cpus(void)
+{
+	int cpu;
+	struct perf_cpu_context *cpuctx;
+
+	for_each_possible_cpu(cpu) {
+		cpuctx = &per_cpu(perf_cpu_context, cpu);
+		__perf_event_init_context(&cpuctx->ctx, NULL);
+	}
+}
+
 static void __cpuinit perf_event_init_cpu(int cpu)
 {
 	struct perf_cpu_context *cpuctx;
 
 	cpuctx = &per_cpu(perf_cpu_context, cpu);
-	__perf_event_init_context(&cpuctx->ctx, NULL);
 
 	spin_lock(&perf_resource_lock);
 	cpuctx->max_pertask = perf_max_events - perf_reserved_percpu;
 	spin_unlock(&perf_resource_lock);
-
-	hw_perf_event_setup(cpu);
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
@@ -5436,11 +5436,6 @@ perf_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu)
 		perf_event_init_cpu(cpu);
 		break;
 
-	case CPU_ONLINE:
-	case CPU_ONLINE_FROZEN:
-		hw_perf_event_setup_online(cpu);
-		break;
-
 	case CPU_DOWN_PREPARE:
 	case CPU_DOWN_PREPARE_FROZEN:
 		perf_event_exit_cpu(cpu);
@@ -5463,6 +5458,7 @@ static struct notifier_block __cpuinitdata perf_cpu_nb = {
 
 void __init perf_event_init(void)
 {
+	perf_event_init_all_cpus();
 	perf_cpu_notify(&perf_cpu_nb, (unsigned long)CPU_UP_PREPARE,
 			(void *)(long)smp_processor_id());
 	perf_cpu_notify(&perf_cpu_nb, (unsigned long)CPU_ONLINE,
@@ -5470,13 +5466,16 @@ void __init perf_event_init(void)
 	register_cpu_notifier(&perf_cpu_nb);
 }
 
-static ssize_t perf_show_reserve_percpu(struct sysdev_class *class, char *buf)
+static ssize_t perf_show_reserve_percpu(struct sysdev_class *class,
+					struct sysdev_class_attribute *attr,
+					char *buf)
 {
 	return sprintf(buf, "%d\n", perf_reserved_percpu);
 }
 
 static ssize_t
 perf_set_reserve_percpu(struct sysdev_class *class,
+			struct sysdev_class_attribute *attr,
 			const char *buf,
 			size_t count)
 {
@@ -5505,13 +5504,17 @@ perf_set_reserve_percpu(struct sysdev_class *class,
 	return count;
 }
 
-static ssize_t perf_show_overcommit(struct sysdev_class *class, char *buf)
+static ssize_t perf_show_overcommit(struct sysdev_class *class,
+				    struct sysdev_class_attribute *attr,
+				    char *buf)
 {
 	return sprintf(buf, "%d\n", perf_overcommit);
 }
 
 static ssize_t
-perf_set_overcommit(struct sysdev_class *class, const char *buf, size_t count)
+perf_set_overcommit(struct sysdev_class *class,
+		    struct sysdev_class_attribute *attr,
+		    const char *buf, size_t count)
 {
 	unsigned long val;
 	int err;
diff --git a/kernel/pid.c b/kernel/pid.c
index 2e17c9c92cb..aebb30d9c23 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(pid->tasks[type].first);
+		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);
 	}
@@ -376,7 +378,7 @@ struct task_struct *pid_task(struct pid *pid, enum pid_type type)
 EXPORT_SYMBOL(pid_task);
 
 /*
- * Must be called under rcu_read_lock() or with tasklist_lock read-held.
+ * Must be called under rcu_read_lock().
  */
 struct task_struct *find_task_by_pid_ns(pid_t nr, struct pid_namespace *ns)
 {
diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c
index 86b3796b043..a5aff94e1f0 100644
--- a/kernel/pid_namespace.c
+++ b/kernel/pid_namespace.c
@@ -13,6 +13,7 @@
 #include <linux/syscalls.h>
 #include <linux/err.h>
 #include <linux/acct.h>
+#include <linux/slab.h>
 
 #define BITS_PER_PAGE		(PAGE_SIZE*8)
 
@@ -161,13 +162,12 @@ 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/posix-cpu-timers.c b/kernel/posix-cpu-timers.c
index 438ff452351..bc7704b3a44 100644
--- a/kernel/posix-cpu-timers.c
+++ b/kernel/posix-cpu-timers.c
@@ -982,6 +982,7 @@ static void check_thread_timers(struct task_struct *tsk,
 	int maxfire;
 	struct list_head *timers = tsk->cpu_timers;
 	struct signal_struct *const sig = tsk->signal;
+	unsigned long soft;
 
 	maxfire = 20;
 	tsk->cputime_expires.prof_exp = cputime_zero;
@@ -1030,9 +1031,10 @@ static void check_thread_timers(struct task_struct *tsk,
 	/*
 	 * Check for the special case thread timers.
 	 */
-	if (sig->rlim[RLIMIT_RTTIME].rlim_cur != RLIM_INFINITY) {
-		unsigned long hard = sig->rlim[RLIMIT_RTTIME].rlim_max;
-		unsigned long *soft = &sig->rlim[RLIMIT_RTTIME].rlim_cur;
+	soft = ACCESS_ONCE(sig->rlim[RLIMIT_RTTIME].rlim_cur);
+	if (soft != RLIM_INFINITY) {
+		unsigned long hard =
+			ACCESS_ONCE(sig->rlim[RLIMIT_RTTIME].rlim_max);
 
 		if (hard != RLIM_INFINITY &&
 		    tsk->rt.timeout > DIV_ROUND_UP(hard, USEC_PER_SEC/HZ)) {
@@ -1043,14 +1045,13 @@ static void check_thread_timers(struct task_struct *tsk,
 			__group_send_sig_info(SIGKILL, SEND_SIG_PRIV, tsk);
 			return;
 		}
-		if (tsk->rt.timeout > DIV_ROUND_UP(*soft, USEC_PER_SEC/HZ)) {
+		if (tsk->rt.timeout > DIV_ROUND_UP(soft, USEC_PER_SEC/HZ)) {
 			/*
 			 * At the soft limit, send a SIGXCPU every second.
 			 */
-			if (sig->rlim[RLIMIT_RTTIME].rlim_cur
-			    < sig->rlim[RLIMIT_RTTIME].rlim_max) {
-				sig->rlim[RLIMIT_RTTIME].rlim_cur +=
-								USEC_PER_SEC;
+			if (soft < hard) {
+				soft += USEC_PER_SEC;
+				sig->rlim[RLIMIT_RTTIME].rlim_cur = soft;
 			}
 			printk(KERN_INFO
 				"RT Watchdog Timeout: %s[%d]\n",
@@ -1060,9 +1061,9 @@ static void check_thread_timers(struct task_struct *tsk,
 	}
 }
 
-static void stop_process_timers(struct task_struct *tsk)
+static void stop_process_timers(struct signal_struct *sig)
 {
-	struct thread_group_cputimer *cputimer = &tsk->signal->cputimer;
+	struct thread_group_cputimer *cputimer = &sig->cputimer;
 	unsigned long flags;
 
 	if (!cputimer->running)
@@ -1071,6 +1072,10 @@ static void stop_process_timers(struct task_struct *tsk)
 	spin_lock_irqsave(&cputimer->lock, flags);
 	cputimer->running = 0;
 	spin_unlock_irqrestore(&cputimer->lock, flags);
+
+	sig->cputime_expires.prof_exp = cputime_zero;
+	sig->cputime_expires.virt_exp = cputime_zero;
+	sig->cputime_expires.sched_exp = 0;
 }
 
 static u32 onecputick;
@@ -1121,6 +1126,7 @@ static void check_process_timers(struct task_struct *tsk,
 	unsigned long long sum_sched_runtime, sched_expires;
 	struct list_head *timers = sig->cpu_timers;
 	struct task_cputime cputime;
+	unsigned long soft;
 
 	/*
 	 * Don't sample the current process CPU clocks if there are no timers.
@@ -1131,7 +1137,7 @@ static void check_process_timers(struct task_struct *tsk,
 	    list_empty(&timers[CPUCLOCK_VIRT]) &&
 	    cputime_eq(sig->it[CPUCLOCK_VIRT].expires, cputime_zero) &&
 	    list_empty(&timers[CPUCLOCK_SCHED])) {
-		stop_process_timers(tsk);
+		stop_process_timers(sig);
 		return;
 	}
 
@@ -1193,11 +1199,13 @@ static void check_process_timers(struct task_struct *tsk,
 			 SIGPROF);
 	check_cpu_itimer(tsk, &sig->it[CPUCLOCK_VIRT], &virt_expires, utime,
 			 SIGVTALRM);
-
-	if (sig->rlim[RLIMIT_CPU].rlim_cur != RLIM_INFINITY) {
+	soft = ACCESS_ONCE(sig->rlim[RLIMIT_CPU].rlim_cur);
+	if (soft != RLIM_INFINITY) {
 		unsigned long psecs = cputime_to_secs(ptime);
+		unsigned long hard =
+			ACCESS_ONCE(sig->rlim[RLIMIT_CPU].rlim_max);
 		cputime_t x;
-		if (psecs >= sig->rlim[RLIMIT_CPU].rlim_max) {
+		if (psecs >= hard) {
 			/*
 			 * At the hard limit, we just die.
 			 * No need to calculate anything else now.
@@ -1205,17 +1213,17 @@ static void check_process_timers(struct task_struct *tsk,
 			__group_send_sig_info(SIGKILL, SEND_SIG_PRIV, tsk);
 			return;
 		}
-		if (psecs >= sig->rlim[RLIMIT_CPU].rlim_cur) {
+		if (psecs >= soft) {
 			/*
 			 * At the soft limit, send a SIGXCPU every second.
 			 */
 			__group_send_sig_info(SIGXCPU, SEND_SIG_PRIV, tsk);
-			if (sig->rlim[RLIMIT_CPU].rlim_cur
-			    < sig->rlim[RLIMIT_CPU].rlim_max) {
-				sig->rlim[RLIMIT_CPU].rlim_cur++;
+			if (soft < hard) {
+				soft++;
+				sig->rlim[RLIMIT_CPU].rlim_cur = soft;
 			}
 		}
-		x = secs_to_cputime(sig->rlim[RLIMIT_CPU].rlim_cur);
+		x = secs_to_cputime(soft);
 		if (cputime_eq(prof_expires, cputime_zero) ||
 		    cputime_lt(x, prof_expires)) {
 			prof_expires = x;
diff --git a/kernel/posix-timers.c b/kernel/posix-timers.c
index 495440779ce..00d1fda58ab 100644
--- a/kernel/posix-timers.c
+++ b/kernel/posix-timers.c
@@ -256,7 +256,7 @@ static int posix_get_monotonic_coarse(clockid_t which_clock,
 	return 0;
 }
 
-int posix_get_coarse_res(const clockid_t which_clock, struct timespec *tp)
+static int posix_get_coarse_res(const clockid_t which_clock, struct timespec *tp)
 {
 	*tp = ktime_to_timespec(KTIME_LOW_RES);
 	return 0;
diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig
index 91e09d3b2eb..5c36ea9d55d 100644
--- a/kernel/power/Kconfig
+++ b/kernel/power/Kconfig
@@ -27,6 +27,15 @@ config PM_DEBUG
 	code. This is helpful when debugging and reporting PM bugs, like
 	suspend support.
 
+config PM_ADVANCED_DEBUG
+	bool "Extra PM attributes in sysfs for low-level debugging/testing"
+	depends on PM_DEBUG
+	default n
+	---help---
+	Add extra sysfs attributes allowing one to access some Power Management
+	fields of device objects from user space.  If you are not a kernel
+	developer interested in debugging/testing Power Management, say "no".
+
 config PM_VERBOSE
 	bool "Verbose Power Management debugging"
 	depends on PM_DEBUG
@@ -85,6 +94,11 @@ config PM_SLEEP
 	depends on SUSPEND || HIBERNATION || XEN_SAVE_RESTORE
 	default y
 
+config PM_SLEEP_ADVANCED_DEBUG
+	bool
+	depends on PM_ADVANCED_DEBUG
+	default n
+
 config SUSPEND
 	bool "Suspend to RAM and standby"
 	depends on PM && ARCH_SUSPEND_POSSIBLE
@@ -222,3 +236,8 @@ config PM_RUNTIME
 	  and the bus type drivers of the buses the devices are on are
 	  responsible for the actual handling of the autosuspend requests and
 	  wake-up events.
+
+config PM_OPS
+	bool
+	depends on PM_SLEEP || PM_RUNTIME
+	default y
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index bbfe472d752..aa9e916da4d 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -22,6 +22,7 @@
 #include <linux/console.h>
 #include <linux/cpu.h>
 #include <linux/freezer.h>
+#include <linux/gfp.h>
 #include <scsi/scsi_scan.h>
 #include <asm/suspend.h>
 
@@ -323,6 +324,7 @@ static int create_image(int platform_mode)
 int hibernation_snapshot(int platform_mode)
 {
 	int error;
+	gfp_t saved_mask;
 
 	error = platform_begin(platform_mode);
 	if (error)
@@ -334,6 +336,7 @@ int hibernation_snapshot(int platform_mode)
 		goto Close;
 
 	suspend_console();
+	saved_mask = clear_gfp_allowed_mask(GFP_IOFS);
 	error = dpm_suspend_start(PMSG_FREEZE);
 	if (error)
 		goto Recover_platform;
@@ -351,6 +354,7 @@ int hibernation_snapshot(int platform_mode)
 
 	dpm_resume_end(in_suspend ?
 		(error ? PMSG_RECOVER : PMSG_THAW) : PMSG_RESTORE);
+	set_gfp_allowed_mask(saved_mask);
 	resume_console();
  Close:
 	platform_end(platform_mode);
@@ -445,14 +449,17 @@ static int resume_target_kernel(bool platform_mode)
 int hibernation_restore(int platform_mode)
 {
 	int error;
+	gfp_t saved_mask;
 
 	pm_prepare_console();
 	suspend_console();
+	saved_mask = clear_gfp_allowed_mask(GFP_IOFS);
 	error = dpm_suspend_start(PMSG_QUIESCE);
 	if (!error) {
 		error = resume_target_kernel(platform_mode);
 		dpm_resume_end(PMSG_RECOVER);
 	}
+	set_gfp_allowed_mask(saved_mask);
 	resume_console();
 	pm_restore_console();
 	return error;
@@ -466,6 +473,7 @@ int hibernation_restore(int platform_mode)
 int hibernation_platform_enter(void)
 {
 	int error;
+	gfp_t saved_mask;
 
 	if (!hibernation_ops)
 		return -ENOSYS;
@@ -481,6 +489,7 @@ int hibernation_platform_enter(void)
 
 	entering_platform_hibernation = true;
 	suspend_console();
+	saved_mask = clear_gfp_allowed_mask(GFP_IOFS);
 	error = dpm_suspend_start(PMSG_HIBERNATE);
 	if (error) {
 		if (hibernation_ops->recover)
@@ -518,6 +527,7 @@ int hibernation_platform_enter(void)
  Resume_devices:
 	entering_platform_hibernation = false;
 	dpm_resume_end(PMSG_RESTORE);
+	set_gfp_allowed_mask(saved_mask);
 	resume_console();
 
  Close:
diff --git a/kernel/power/hibernate_nvs.c b/kernel/power/hibernate_nvs.c
index 39ac698ef83..fdcad9ed5a7 100644
--- a/kernel/power/hibernate_nvs.c
+++ b/kernel/power/hibernate_nvs.c
@@ -10,6 +10,7 @@
 #include <linux/kernel.h>
 #include <linux/list.h>
 #include <linux/mm.h>
+#include <linux/slab.h>
 #include <linux/suspend.h>
 
 /*
diff --git a/kernel/power/main.c b/kernel/power/main.c
index 0998c713905..b58800b21fc 100644
--- a/kernel/power/main.c
+++ b/kernel/power/main.c
@@ -44,6 +44,32 @@ int pm_notifier_call_chain(unsigned long val)
 			== NOTIFY_BAD) ? -EINVAL : 0;
 }
 
+/* If set, devices may be suspended and resumed asynchronously. */
+int pm_async_enabled = 1;
+
+static ssize_t pm_async_show(struct kobject *kobj, struct kobj_attribute *attr,
+			     char *buf)
+{
+	return sprintf(buf, "%d\n", pm_async_enabled);
+}
+
+static ssize_t pm_async_store(struct kobject *kobj, struct kobj_attribute *attr,
+			      const char *buf, size_t n)
+{
+	unsigned long val;
+
+	if (strict_strtoul(buf, 10, &val))
+		return -EINVAL;
+
+	if (val > 1)
+		return -EINVAL;
+
+	pm_async_enabled = val;
+	return n;
+}
+
+power_attr(pm_async);
+
 #ifdef CONFIG_PM_DEBUG
 int pm_test_level = TEST_NONE;
 
@@ -208,9 +234,12 @@ static struct attribute * g[] = {
 #ifdef CONFIG_PM_TRACE
 	&pm_trace_attr.attr,
 #endif
-#if defined(CONFIG_PM_SLEEP) && defined(CONFIG_PM_DEBUG)
+#ifdef CONFIG_PM_SLEEP
+	&pm_async_attr.attr,
+#ifdef CONFIG_PM_DEBUG
 	&pm_test_attr.attr,
 #endif
+#endif
 	NULL,
 };
 
diff --git a/kernel/power/process.c b/kernel/power/process.c
index 5ade1bdcf36..71ae29052ab 100644
--- a/kernel/power/process.c
+++ b/kernel/power/process.c
@@ -88,12 +88,11 @@ static int try_to_freeze_tasks(bool sig_only)
 		printk(KERN_ERR "Freezing of tasks failed after %d.%02d seconds "
 				"(%d tasks refusing to freeze):\n",
 				elapsed_csecs / 100, elapsed_csecs % 100, todo);
-		show_state();
 		read_lock(&tasklist_lock);
 		do_each_thread(g, p) {
 			task_lock(p);
 			if (freezing(p) && !freezer_should_skip(p))
-				printk(KERN_ERR " %s\n", p->comm);
+				sched_show_task(p);
 			cancel_freezing(p);
 			task_unlock(p);
 		} while_each_thread(g, p);
@@ -145,7 +144,7 @@ static void thaw_tasks(bool nosig_only)
 		if (nosig_only && should_send_signal(p))
 			continue;
 
-		if (cgroup_frozen(p))
+		if (cgroup_freezing_or_frozen(p))
 			continue;
 
 		thaw_process(p);
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index 36cb168e433..be861c26dda 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -26,6 +26,7 @@
 #include <linux/console.h>
 #include <linux/highmem.h>
 #include <linux/list.h>
+#include <linux/slab.h>
 
 #include <asm/uaccess.h>
 #include <asm/mmu_context.h>
@@ -1181,7 +1182,7 @@ static void free_unnecessary_pages(void)
 
 	memory_bm_position_reset(&copy_bm);
 
-	while (to_free_normal > 0 && to_free_highmem > 0) {
+	while (to_free_normal > 0 || to_free_highmem > 0) {
 		unsigned long pfn = memory_bm_next_pfn(&copy_bm);
 		struct page *page = pfn_to_page(pfn);
 
@@ -1500,7 +1501,7 @@ asmlinkage int swsusp_save(void)
 {
 	unsigned int nr_pages, nr_highmem;
 
-	printk(KERN_INFO "PM: Creating hibernation image: \n");
+	printk(KERN_INFO "PM: Creating hibernation image:\n");
 
 	drain_local_pages(NULL);
 	nr_pages = count_data_pages();
diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
index 6f10dfc2d3e..56e7dbb8b99 100644
--- a/kernel/power/suspend.c
+++ b/kernel/power/suspend.c
@@ -15,6 +15,7 @@
 #include <linux/console.h>
 #include <linux/cpu.h>
 #include <linux/syscalls.h>
+#include <linux/gfp.h>
 
 #include "power.h"
 
@@ -189,6 +190,7 @@ static int suspend_enter(suspend_state_t state)
 int suspend_devices_and_enter(suspend_state_t state)
 {
 	int error;
+	gfp_t saved_mask;
 
 	if (!suspend_ops)
 		return -ENOSYS;
@@ -199,6 +201,7 @@ int suspend_devices_and_enter(suspend_state_t state)
 			goto Close;
 	}
 	suspend_console();
+	saved_mask = clear_gfp_allowed_mask(GFP_IOFS);
 	suspend_test_start();
 	error = dpm_suspend_start(PMSG_SUSPEND);
 	if (error) {
@@ -215,6 +218,7 @@ int suspend_devices_and_enter(suspend_state_t state)
 	suspend_test_start();
 	dpm_resume_end(PMSG_RESUME);
 	suspend_test_finish("resume devices");
+	set_gfp_allowed_mask(saved_mask);
 	resume_console();
  Close:
 	if (suspend_ops->end)
diff --git a/kernel/power/swap.c b/kernel/power/swap.c
index 09b2b0ae9e9..66824d71983 100644
--- a/kernel/power/swap.c
+++ b/kernel/power/swap.c
@@ -23,6 +23,7 @@
 #include <linux/swap.h>
 #include <linux/swapops.h>
 #include <linux/pm.h>
+#include <linux/slab.h>
 
 #include "power.h"
 
@@ -657,10 +658,6 @@ int swsusp_read(unsigned int *flags_p)
 	struct swsusp_info *header;
 
 	*flags_p = swsusp_header->flags;
-	if (IS_ERR(resume_bdev)) {
-		pr_debug("PM: Image device not initialised\n");
-		return PTR_ERR(resume_bdev);
-	}
 
 	memset(&snapshot, 0, sizeof(struct snapshot_handle));
 	error = snapshot_write_next(&snapshot, PAGE_SIZE);
diff --git a/kernel/power/swsusp.c b/kernel/power/swsusp.c
deleted file mode 100644
index 5b3601bd189..00000000000
--- a/kernel/power/swsusp.c
+++ /dev/null
@@ -1,58 +0,0 @@
-/*
- * linux/kernel/power/swsusp.c
- *
- * This file provides code to write suspend image to swap and read it back.
- *
- * Copyright (C) 1998-2001 Gabor Kuti <seasons@fornax.hu>
- * Copyright (C) 1998,2001-2005 Pavel Machek <pavel@suse.cz>
- *
- * This file is released under the GPLv2.
- *
- * I'd like to thank the following people for their work:
- *
- * Pavel Machek <pavel@ucw.cz>:
- * Modifications, defectiveness pointing, being with me at the very beginning,
- * suspend to swap space, stop all tasks. Port to 2.4.18-ac and 2.5.17.
- *
- * Steve Doddi <dirk@loth.demon.co.uk>:
- * Support the possibility of hardware state restoring.
- *
- * Raph <grey.havens@earthling.net>:
- * Support for preserving states of network devices and virtual console
- * (including X and svgatextmode)
- *
- * Kurt Garloff <garloff@suse.de>:
- * Straightened the critical function in order to prevent compilers from
- * playing tricks with local variables.
- *
- * Andreas Mohr <a.mohr@mailto.de>
- *
- * Alex Badea <vampire@go.ro>:
- * Fixed runaway init
- *
- * Rafael J. Wysocki <rjw@sisk.pl>
- * Reworked the freeing of memory and the handling of swap
- *
- * More state savers are welcome. Especially for the scsi layer...
- *
- * For TODOs,FIXMEs also look in Documentation/power/swsusp.txt
- */
-
-#include <linux/mm.h>
-#include <linux/suspend.h>
-#include <linux/spinlock.h>
-#include <linux/kernel.h>
-#include <linux/major.h>
-#include <linux/swap.h>
-#include <linux/pm.h>
-#include <linux/swapops.h>
-#include <linux/bootmem.h>
-#include <linux/syscalls.h>
-#include <linux/highmem.h>
-#include <linux/time.h>
-#include <linux/rbtree.h>
-#include <linux/io.h>
-
-#include "power.h"
-
-int in_suspend __nosavedata = 0;
diff --git a/kernel/power/user.c b/kernel/power/user.c
index bf0014d6a5f..a8c96212bc1 100644
--- a/kernel/power/user.c
+++ b/kernel/power/user.c
@@ -195,6 +195,15 @@ static ssize_t snapshot_write(struct file *filp, const char __user *buf,
 	return res;
 }
 
+static void snapshot_deprecated_ioctl(unsigned int cmd)
+{
+	if (printk_ratelimit())
+		printk(KERN_NOTICE "%pf: ioctl '%.8x' is deprecated and will "
+				"be removed soon, update your suspend-to-disk "
+				"utilities\n",
+				__builtin_return_address(0), cmd);
+}
+
 static long snapshot_ioctl(struct file *filp, unsigned int cmd,
 							unsigned long arg)
 {
@@ -246,8 +255,9 @@ static long snapshot_ioctl(struct file *filp, unsigned int cmd,
 		data->frozen = 0;
 		break;
 
-	case SNAPSHOT_CREATE_IMAGE:
 	case SNAPSHOT_ATOMIC_SNAPSHOT:
+		snapshot_deprecated_ioctl(cmd);
+	case SNAPSHOT_CREATE_IMAGE:
 		if (data->mode != O_RDONLY || !data->frozen  || data->ready) {
 			error = -EPERM;
 			break;
@@ -275,8 +285,9 @@ static long snapshot_ioctl(struct file *filp, unsigned int cmd,
 		data->ready = 0;
 		break;
 
-	case SNAPSHOT_PREF_IMAGE_SIZE:
 	case SNAPSHOT_SET_IMAGE_SIZE:
+		snapshot_deprecated_ioctl(cmd);
+	case SNAPSHOT_PREF_IMAGE_SIZE:
 		image_size = arg;
 		break;
 
@@ -290,15 +301,17 @@ static long snapshot_ioctl(struct file *filp, unsigned int cmd,
 		error = put_user(size, (loff_t __user *)arg);
 		break;
 
-	case SNAPSHOT_AVAIL_SWAP_SIZE:
 	case SNAPSHOT_AVAIL_SWAP:
+		snapshot_deprecated_ioctl(cmd);
+	case SNAPSHOT_AVAIL_SWAP_SIZE:
 		size = count_swap_pages(data->swap, 1);
 		size <<= PAGE_SHIFT;
 		error = put_user(size, (loff_t __user *)arg);
 		break;
 
-	case SNAPSHOT_ALLOC_SWAP_PAGE:
 	case SNAPSHOT_GET_SWAP_PAGE:
+		snapshot_deprecated_ioctl(cmd);
+	case SNAPSHOT_ALLOC_SWAP_PAGE:
 		if (data->swap < 0 || data->swap >= MAX_SWAPFILES) {
 			error = -ENODEV;
 			break;
@@ -321,6 +334,7 @@ static long snapshot_ioctl(struct file *filp, unsigned int cmd,
 		break;
 
 	case SNAPSHOT_SET_SWAP_FILE: /* This ioctl is deprecated */
+		snapshot_deprecated_ioctl(cmd);
 		if (!swsusp_swap_in_use()) {
 			/*
 			 * User space encodes device types as two-byte values,
@@ -362,6 +376,7 @@ static long snapshot_ioctl(struct file *filp, unsigned int cmd,
 		break;
 
 	case SNAPSHOT_PMOPS: /* This ioctl is deprecated */
+		snapshot_deprecated_ioctl(cmd);
 		error = -EINVAL;
 
 		switch (arg) {
@@ -405,7 +420,7 @@ static long snapshot_ioctl(struct file *filp, unsigned int cmd,
 			 * User space encodes device types as two-byte values,
 			 * so we need to recode them
 			 */
-			swdev = old_decode_dev(swap_area.dev);
+			swdev = new_decode_dev(swap_area.dev);
 			if (swdev) {
 				offset = swap_area.offset;
 				data->swap = swap_type_of(swdev, offset, NULL);
diff --git a/kernel/printk.c b/kernel/printk.c
index 1751c456b71..75077ad0b53 100644
--- a/kernel/printk.c
+++ b/kernel/printk.c
@@ -35,6 +35,7 @@
 #include <linux/kexec.h>
 #include <linux/ratelimit.h>
 #include <linux/kmsg_dump.h>
+#include <linux/syslog.h>
 
 #include <asm/uaccess.h>
 
@@ -69,8 +70,6 @@ int console_printk[4] = {
 	DEFAULT_CONSOLE_LOGLEVEL,	/* default_console_loglevel */
 };
 
-static int saved_console_loglevel = -1;
-
 /*
  * Low level drivers may need that to know if they can schedule in
  * their unblank() callback or not. So let's export it.
@@ -145,6 +144,7 @@ static char __log_buf[__LOG_BUF_LEN];
 static char *log_buf = __log_buf;
 static int log_buf_len = __LOG_BUF_LEN;
 static unsigned logged_chars; /* Number of chars produced since last read+clear operation */
+static int saved_console_loglevel = -1;
 
 #ifdef CONFIG_KEXEC
 /*
@@ -258,38 +258,23 @@ static inline void boot_delay_msec(void)
 }
 #endif
 
-/*
- * Commands to do_syslog:
- *
- * 	0 -- Close the log.  Currently a NOP.
- * 	1 -- Open the log. Currently a NOP.
- * 	2 -- Read from the log.
- * 	3 -- Read all messages remaining in the ring buffer.
- * 	4 -- Read and clear all messages remaining in the ring buffer
- * 	5 -- Clear ring buffer.
- * 	6 -- Disable printk's to console
- * 	7 -- Enable printk's to console
- *	8 -- Set level of messages printed to console
- *	9 -- Return number of unread characters in the log buffer
- *     10 -- Return size of the log buffer
- */
-int do_syslog(int type, char __user *buf, int len)
+int do_syslog(int type, char __user *buf, int len, bool from_file)
 {
 	unsigned i, j, limit, count;
 	int do_clear = 0;
 	char c;
 	int error = 0;
 
-	error = security_syslog(type);
+	error = security_syslog(type, from_file);
 	if (error)
 		return error;
 
 	switch (type) {
-	case 0:		/* Close log */
+	case SYSLOG_ACTION_CLOSE:	/* Close log */
 		break;
-	case 1:		/* Open log */
+	case SYSLOG_ACTION_OPEN:	/* Open log */
 		break;
-	case 2:		/* Read from log */
+	case SYSLOG_ACTION_READ:	/* Read from log */
 		error = -EINVAL;
 		if (!buf || len < 0)
 			goto out;
@@ -320,10 +305,12 @@ int do_syslog(int type, char __user *buf, int len)
 		if (!error)
 			error = i;
 		break;
-	case 4:		/* Read/clear last kernel messages */
+	/* Read/clear last kernel messages */
+	case SYSLOG_ACTION_READ_CLEAR:
 		do_clear = 1;
 		/* FALL THRU */
-	case 3:		/* Read last kernel messages */
+	/* Read last kernel messages */
+	case SYSLOG_ACTION_READ_ALL:
 		error = -EINVAL;
 		if (!buf || len < 0)
 			goto out;
@@ -376,21 +363,25 @@ int do_syslog(int type, char __user *buf, int len)
 			}
 		}
 		break;
-	case 5:		/* Clear ring buffer */
+	/* Clear ring buffer */
+	case SYSLOG_ACTION_CLEAR:
 		logged_chars = 0;
 		break;
-	case 6:		/* Disable logging to console */
+	/* Disable logging to console */
+	case SYSLOG_ACTION_CONSOLE_OFF:
 		if (saved_console_loglevel == -1)
 			saved_console_loglevel = console_loglevel;
 		console_loglevel = minimum_console_loglevel;
 		break;
-	case 7:		/* Enable logging to console */
+	/* Enable logging to console */
+	case SYSLOG_ACTION_CONSOLE_ON:
 		if (saved_console_loglevel != -1) {
 			console_loglevel = saved_console_loglevel;
 			saved_console_loglevel = -1;
 		}
 		break;
-	case 8:		/* Set level of messages printed to console */
+	/* Set level of messages printed to console */
+	case SYSLOG_ACTION_CONSOLE_LEVEL:
 		error = -EINVAL;
 		if (len < 1 || len > 8)
 			goto out;
@@ -401,10 +392,12 @@ int do_syslog(int type, char __user *buf, int len)
 		saved_console_loglevel = -1;
 		error = 0;
 		break;
-	case 9:		/* Number of chars in the log buffer */
+	/* Number of chars in the log buffer */
+	case SYSLOG_ACTION_SIZE_UNREAD:
 		error = log_end - log_start;
 		break;
-	case 10:	/* Size of the log buffer */
+	/* Size of the log buffer */
+	case SYSLOG_ACTION_SIZE_BUFFER:
 		error = log_buf_len;
 		break;
 	default:
@@ -417,7 +410,7 @@ out:
 
 SYSCALL_DEFINE3(syslog, int, type, char __user *, buf, int, len)
 {
-	return do_syslog(type, buf, len);
+	return do_syslog(type, buf, len, SYSLOG_FROM_CALL);
 }
 
 /*
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 23bd09cd042..42ad8ae729a 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -22,6 +22,7 @@
 #include <linux/pid_namespace.h>
 #include <linux/syscalls.h>
 #include <linux/uaccess.h>
+#include <linux/regset.h>
 
 
 /*
@@ -511,6 +512,47 @@ static int ptrace_resume(struct task_struct *child, long request, long data)
 	return 0;
 }
 
+#ifdef CONFIG_HAVE_ARCH_TRACEHOOK
+
+static const struct user_regset *
+find_regset(const struct user_regset_view *view, unsigned int type)
+{
+	const struct user_regset *regset;
+	int n;
+
+	for (n = 0; n < view->n; ++n) {
+		regset = view->regsets + n;
+		if (regset->core_note_type == type)
+			return regset;
+	}
+
+	return NULL;
+}
+
+static int ptrace_regset(struct task_struct *task, int req, unsigned int type,
+			 struct iovec *kiov)
+{
+	const struct user_regset_view *view = task_user_regset_view(task);
+	const struct user_regset *regset = find_regset(view, type);
+	int regset_no;
+
+	if (!regset || (kiov->iov_len % regset->size) != 0)
+		return -EINVAL;
+
+	regset_no = regset - view->regsets;
+	kiov->iov_len = min(kiov->iov_len,
+			    (__kernel_size_t) (regset->n * regset->size));
+
+	if (req == PTRACE_GETREGSET)
+		return copy_regset_to_user(task, view, regset_no, 0,
+					   kiov->iov_len, kiov->iov_base);
+	else
+		return copy_regset_from_user(task, view, regset_no, 0,
+					     kiov->iov_len, kiov->iov_base);
+}
+
+#endif
+
 int ptrace_request(struct task_struct *child, long request,
 		   long addr, long data)
 {
@@ -573,6 +615,26 @@ int ptrace_request(struct task_struct *child, long request,
 			return 0;
 		return ptrace_resume(child, request, SIGKILL);
 
+#ifdef CONFIG_HAVE_ARCH_TRACEHOOK
+	case PTRACE_GETREGSET:
+	case PTRACE_SETREGSET:
+	{
+		struct iovec kiov;
+		struct iovec __user *uiov = (struct iovec __user *) data;
+
+		if (!access_ok(VERIFY_WRITE, uiov, sizeof(*uiov)))
+			return -EFAULT;
+
+		if (__get_user(kiov.iov_base, &uiov->iov_base) ||
+		    __get_user(kiov.iov_len, &uiov->iov_len))
+			return -EFAULT;
+
+		ret = ptrace_regset(child, request, addr, &kiov);
+		if (!ret)
+			ret = __put_user(kiov.iov_len, &uiov->iov_len);
+		break;
+	}
+#endif
 	default:
 		break;
 	}
@@ -711,6 +773,32 @@ int compat_ptrace_request(struct task_struct *child, compat_long_t request,
 		else
 			ret = ptrace_setsiginfo(child, &siginfo);
 		break;
+#ifdef CONFIG_HAVE_ARCH_TRACEHOOK
+	case PTRACE_GETREGSET:
+	case PTRACE_SETREGSET:
+	{
+		struct iovec kiov;
+		struct compat_iovec __user *uiov =
+			(struct compat_iovec __user *) datap;
+		compat_uptr_t ptr;
+		compat_size_t len;
+
+		if (!access_ok(VERIFY_WRITE, uiov, sizeof(*uiov)))
+			return -EFAULT;
+
+		if (__get_user(ptr, &uiov->iov_base) ||
+		    __get_user(len, &uiov->iov_len))
+			return -EFAULT;
+
+		kiov.iov_base = compat_ptr(ptr);
+		kiov.iov_len = len;
+
+		ret = ptrace_regset(child, request, addr, &kiov);
+		if (!ret)
+			ret = __put_user(kiov.iov_len, &uiov->iov_len);
+		break;
+	}
+#endif
 
 	default:
 		ret = ptrace_request(child, request, addr, data);
diff --git a/kernel/range.c b/kernel/range.c
new file mode 100644
index 00000000000..74e2e611492
--- /dev/null
+++ b/kernel/range.c
@@ -0,0 +1,163 @@
+/*
+ * Range add and subtract
+ */
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/sort.h>
+
+#include <linux/range.h>
+
+#ifndef ARRAY_SIZE
+#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))
+#endif
+
+int add_range(struct range *range, int az, int nr_range, u64 start, u64 end)
+{
+	if (start >= end)
+		return nr_range;
+
+	/* Out of slots: */
+	if (nr_range >= az)
+		return nr_range;
+
+	range[nr_range].start = start;
+	range[nr_range].end = end;
+
+	nr_range++;
+
+	return nr_range;
+}
+
+int add_range_with_merge(struct range *range, int az, int nr_range,
+		     u64 start, u64 end)
+{
+	int i;
+
+	if (start >= end)
+		return nr_range;
+
+	/* Try to merge it with old one: */
+	for (i = 0; i < nr_range; i++) {
+		u64 final_start, final_end;
+		u64 common_start, common_end;
+
+		if (!range[i].end)
+			continue;
+
+		common_start = max(range[i].start, start);
+		common_end = min(range[i].end, end);
+		if (common_start > common_end)
+			continue;
+
+		final_start = min(range[i].start, start);
+		final_end = max(range[i].end, end);
+
+		range[i].start = final_start;
+		range[i].end =  final_end;
+		return nr_range;
+	}
+
+	/* Need to add it: */
+	return add_range(range, az, nr_range, start, end);
+}
+
+void subtract_range(struct range *range, int az, u64 start, u64 end)
+{
+	int i, j;
+
+	if (start >= end)
+		return;
+
+	for (j = 0; j < az; j++) {
+		if (!range[j].end)
+			continue;
+
+		if (start <= range[j].start && end >= range[j].end) {
+			range[j].start = 0;
+			range[j].end = 0;
+			continue;
+		}
+
+		if (start <= range[j].start && end < range[j].end &&
+		    range[j].start < end) {
+			range[j].start = end;
+			continue;
+		}
+
+
+		if (start > range[j].start && end >= range[j].end &&
+		    range[j].end > start) {
+			range[j].end = start;
+			continue;
+		}
+
+		if (start > range[j].start && end < range[j].end) {
+			/* Find the new spare: */
+			for (i = 0; i < az; i++) {
+				if (range[i].end == 0)
+					break;
+			}
+			if (i < az) {
+				range[i].end = range[j].end;
+				range[i].start = end;
+			} else {
+				printk(KERN_ERR "run of slot in ranges\n");
+			}
+			range[j].end = start;
+			continue;
+		}
+	}
+}
+
+static int cmp_range(const void *x1, const void *x2)
+{
+	const struct range *r1 = x1;
+	const struct range *r2 = x2;
+	s64 start1, start2;
+
+	start1 = r1->start;
+	start2 = r2->start;
+
+	return start1 - start2;
+}
+
+int clean_sort_range(struct range *range, int az)
+{
+	int i, j, k = az - 1, nr_range = 0;
+
+	for (i = 0; i < k; i++) {
+		if (range[i].end)
+			continue;
+		for (j = k; j > i; j--) {
+			if (range[j].end) {
+				k = j;
+				break;
+			}
+		}
+		if (j == i)
+			break;
+		range[i].start = range[k].start;
+		range[i].end   = range[k].end;
+		range[k].start = 0;
+		range[k].end   = 0;
+		k--;
+	}
+	/* count it */
+	for (i = 0; i < az; i++) {
+		if (!range[i].end) {
+			nr_range = i;
+			break;
+		}
+	}
+
+	/* sort them */
+	sort(range, nr_range, sizeof(struct range), cmp_range, NULL);
+
+	return nr_range;
+}
+
+void sort_range(struct range *range, int nr_range)
+{
+	/* sort them */
+	sort(range, nr_range, sizeof(struct range), cmp_range, NULL);
+}
diff --git a/kernel/rcupdate.c b/kernel/rcupdate.c
index 9b7fd472387..49d808e833b 100644
--- a/kernel/rcupdate.c
+++ b/kernel/rcupdate.c
@@ -44,14 +44,73 @@
 #include <linux/cpu.h>
 #include <linux/mutex.h>
 #include <linux/module.h>
+#include <linux/kernel_stat.h>
+#include <linux/hardirq.h>
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 static struct lock_class_key rcu_lock_key;
 struct lockdep_map rcu_lock_map =
 	STATIC_LOCKDEP_MAP_INIT("rcu_read_lock", &rcu_lock_key);
 EXPORT_SYMBOL_GPL(rcu_lock_map);
+
+static struct lock_class_key rcu_bh_lock_key;
+struct lockdep_map rcu_bh_lock_map =
+	STATIC_LOCKDEP_MAP_INIT("rcu_read_lock_bh", &rcu_bh_lock_key);
+EXPORT_SYMBOL_GPL(rcu_bh_lock_map);
+
+static struct lock_class_key rcu_sched_lock_key;
+struct lockdep_map rcu_sched_lock_map =
+	STATIC_LOCKDEP_MAP_INIT("rcu_read_lock_sched", &rcu_sched_lock_key);
+EXPORT_SYMBOL_GPL(rcu_sched_lock_map);
 #endif
 
+int rcu_scheduler_active __read_mostly;
+EXPORT_SYMBOL_GPL(rcu_scheduler_active);
+
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+
+int debug_lockdep_rcu_enabled(void)
+{
+	return rcu_scheduler_active && debug_locks &&
+	       current->lockdep_recursion == 0;
+}
+EXPORT_SYMBOL_GPL(debug_lockdep_rcu_enabled);
+
+/**
+ * rcu_read_lock_bh_held - might we be in RCU-bh read-side critical section?
+ *
+ * Check for bottom half being disabled, which covers both the
+ * CONFIG_PROVE_RCU and not cases.  Note that if someone uses
+ * rcu_read_lock_bh(), but then later enables BH, lockdep (if enabled)
+ * will show the situation.
+ *
+ * Check debug_lockdep_rcu_enabled() to prevent false positives during boot.
+ */
+int rcu_read_lock_bh_held(void)
+{
+	if (!debug_lockdep_rcu_enabled())
+		return 1;
+	return in_softirq();
+}
+EXPORT_SYMBOL_GPL(rcu_read_lock_bh_held);
+
+#endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
+
+/*
+ * This function is invoked towards the end of the scheduler's initialization
+ * process.  Before this is called, the idle task might contain
+ * RCU read-side critical sections (during which time, this idle
+ * task is booting the system).  After this function is called, the
+ * idle tasks are prohibited from containing RCU read-side critical
+ * sections.
+ */
+void rcu_scheduler_starting(void)
+{
+	WARN_ON(num_online_cpus() != 1);
+	WARN_ON(nr_context_switches() > 0);
+	rcu_scheduler_active = 1;
+}
+
 /*
  * Awaken the corresponding synchronize_rcu() instance now that a
  * grace period has elapsed.
@@ -63,3 +122,14 @@ void wakeme_after_rcu(struct rcu_head  *head)
 	rcu = container_of(head, struct rcu_synchronize, head);
 	complete(&rcu->completion);
 }
+
+#ifdef CONFIG_PROVE_RCU
+/*
+ * wrapper function to avoid #include problems.
+ */
+int rcu_my_thread_group_empty(void)
+{
+	return thread_group_empty(current);
+}
+EXPORT_SYMBOL_GPL(rcu_my_thread_group_empty);
+#endif /* #ifdef CONFIG_PROVE_RCU */
diff --git a/kernel/rcutorture.c b/kernel/rcutorture.c
index 9bb52177af0..58df55bf83e 100644
--- a/kernel/rcutorture.c
+++ b/kernel/rcutorture.c
@@ -61,6 +61,9 @@ static int test_no_idle_hz;	/* Test RCU's support for tickless idle CPUs. */
 static int shuffle_interval = 3; /* Interval between shuffles (in sec)*/
 static int stutter = 5;		/* Start/stop testing interval (in sec) */
 static int irqreader = 1;	/* RCU readers from irq (timers). */
+static int fqs_duration = 0;	/* Duration of bursts (us), 0 to disable. */
+static int fqs_holdoff = 0;	/* Hold time within burst (us). */
+static int fqs_stutter = 3;	/* Wait time between bursts (s). */
 static char *torture_type = "rcu"; /* What RCU implementation to torture. */
 
 module_param(nreaders, int, 0444);
@@ -79,6 +82,12 @@ module_param(stutter, int, 0444);
 MODULE_PARM_DESC(stutter, "Number of seconds to run/halt test");
 module_param(irqreader, int, 0444);
 MODULE_PARM_DESC(irqreader, "Allow RCU readers from irq handlers");
+module_param(fqs_duration, int, 0444);
+MODULE_PARM_DESC(fqs_duration, "Duration of fqs bursts (us)");
+module_param(fqs_holdoff, int, 0444);
+MODULE_PARM_DESC(fqs_holdoff, "Holdoff time within fqs bursts (us)");
+module_param(fqs_stutter, int, 0444);
+MODULE_PARM_DESC(fqs_stutter, "Wait time between fqs bursts (s)");
 module_param(torture_type, charp, 0444);
 MODULE_PARM_DESC(torture_type, "Type of RCU to torture (rcu, rcu_bh, srcu)");
 
@@ -99,6 +108,7 @@ static struct task_struct **reader_tasks;
 static struct task_struct *stats_task;
 static struct task_struct *shuffler_task;
 static struct task_struct *stutter_task;
+static struct task_struct *fqs_task;
 
 #define RCU_TORTURE_PIPE_LEN 10
 
@@ -263,6 +273,7 @@ struct rcu_torture_ops {
 	void (*deferred_free)(struct rcu_torture *p);
 	void (*sync)(void);
 	void (*cb_barrier)(void);
+	void (*fqs)(void);
 	int (*stats)(char *page);
 	int irq_capable;
 	char *name;
@@ -347,6 +358,7 @@ static struct rcu_torture_ops rcu_ops = {
 	.deferred_free	= rcu_torture_deferred_free,
 	.sync		= synchronize_rcu,
 	.cb_barrier	= rcu_barrier,
+	.fqs		= rcu_force_quiescent_state,
 	.stats		= NULL,
 	.irq_capable	= 1,
 	.name		= "rcu"
@@ -388,6 +400,7 @@ static struct rcu_torture_ops rcu_sync_ops = {
 	.deferred_free	= rcu_sync_torture_deferred_free,
 	.sync		= synchronize_rcu,
 	.cb_barrier	= NULL,
+	.fqs		= rcu_force_quiescent_state,
 	.stats		= NULL,
 	.irq_capable	= 1,
 	.name		= "rcu_sync"
@@ -403,6 +416,7 @@ static struct rcu_torture_ops rcu_expedited_ops = {
 	.deferred_free	= rcu_sync_torture_deferred_free,
 	.sync		= synchronize_rcu_expedited,
 	.cb_barrier	= NULL,
+	.fqs		= rcu_force_quiescent_state,
 	.stats		= NULL,
 	.irq_capable	= 1,
 	.name		= "rcu_expedited"
@@ -465,6 +479,7 @@ static struct rcu_torture_ops rcu_bh_ops = {
 	.deferred_free	= rcu_bh_torture_deferred_free,
 	.sync		= rcu_bh_torture_synchronize,
 	.cb_barrier	= rcu_barrier_bh,
+	.fqs		= rcu_bh_force_quiescent_state,
 	.stats		= NULL,
 	.irq_capable	= 1,
 	.name		= "rcu_bh"
@@ -480,6 +495,7 @@ static struct rcu_torture_ops rcu_bh_sync_ops = {
 	.deferred_free	= rcu_sync_torture_deferred_free,
 	.sync		= rcu_bh_torture_synchronize,
 	.cb_barrier	= NULL,
+	.fqs		= rcu_bh_force_quiescent_state,
 	.stats		= NULL,
 	.irq_capable	= 1,
 	.name		= "rcu_bh_sync"
@@ -621,6 +637,7 @@ static struct rcu_torture_ops sched_ops = {
 	.deferred_free	= rcu_sched_torture_deferred_free,
 	.sync		= sched_torture_synchronize,
 	.cb_barrier	= rcu_barrier_sched,
+	.fqs		= rcu_sched_force_quiescent_state,
 	.stats		= NULL,
 	.irq_capable	= 1,
 	.name		= "sched"
@@ -636,6 +653,7 @@ static struct rcu_torture_ops sched_sync_ops = {
 	.deferred_free	= rcu_sync_torture_deferred_free,
 	.sync		= sched_torture_synchronize,
 	.cb_barrier	= NULL,
+	.fqs		= rcu_sched_force_quiescent_state,
 	.stats		= NULL,
 	.name		= "sched_sync"
 };
@@ -650,12 +668,45 @@ static struct rcu_torture_ops sched_expedited_ops = {
 	.deferred_free	= rcu_sync_torture_deferred_free,
 	.sync		= synchronize_sched_expedited,
 	.cb_barrier	= NULL,
+	.fqs		= rcu_sched_force_quiescent_state,
 	.stats		= rcu_expedited_torture_stats,
 	.irq_capable	= 1,
 	.name		= "sched_expedited"
 };
 
 /*
+ * RCU torture force-quiescent-state kthread.  Repeatedly induces
+ * bursts of calls to force_quiescent_state(), increasing the probability
+ * of occurrence of some important types of race conditions.
+ */
+static int
+rcu_torture_fqs(void *arg)
+{
+	unsigned long fqs_resume_time;
+	int fqs_burst_remaining;
+
+	VERBOSE_PRINTK_STRING("rcu_torture_fqs task started");
+	do {
+		fqs_resume_time = jiffies + fqs_stutter * HZ;
+		while (jiffies - fqs_resume_time > LONG_MAX) {
+			schedule_timeout_interruptible(1);
+		}
+		fqs_burst_remaining = fqs_duration;
+		while (fqs_burst_remaining > 0) {
+			cur_ops->fqs();
+			udelay(fqs_holdoff);
+			fqs_burst_remaining -= fqs_holdoff;
+		}
+		rcu_stutter_wait("rcu_torture_fqs");
+	} while (!kthread_should_stop() && fullstop == FULLSTOP_DONTSTOP);
+	VERBOSE_PRINTK_STRING("rcu_torture_fqs task stopping");
+	rcutorture_shutdown_absorb("rcu_torture_fqs");
+	while (!kthread_should_stop())
+		schedule_timeout_uninterruptible(1);
+	return 0;
+}
+
+/*
  * RCU torture writer kthread.  Repeatedly substitutes a new structure
  * for that pointed to by rcu_torture_current, freeing the old structure
  * after a series of grace periods (the "pipeline").
@@ -745,7 +796,11 @@ static void rcu_torture_timer(unsigned long unused)
 
 	idx = cur_ops->readlock();
 	completed = cur_ops->completed();
-	p = rcu_dereference(rcu_torture_current);
+	p = rcu_dereference_check(rcu_torture_current,
+				  rcu_read_lock_held() ||
+				  rcu_read_lock_bh_held() ||
+				  rcu_read_lock_sched_held() ||
+				  srcu_read_lock_held(&srcu_ctl));
 	if (p == NULL) {
 		/* Leave because rcu_torture_writer is not yet underway */
 		cur_ops->readunlock(idx);
@@ -763,13 +818,13 @@ static void rcu_torture_timer(unsigned long unused)
 		/* Should not happen, but... */
 		pipe_count = RCU_TORTURE_PIPE_LEN;
 	}
-	__this_cpu_inc(per_cpu_var(rcu_torture_count)[pipe_count]);
+	__this_cpu_inc(rcu_torture_count[pipe_count]);
 	completed = cur_ops->completed() - completed;
 	if (completed > RCU_TORTURE_PIPE_LEN) {
 		/* Should not happen, but... */
 		completed = RCU_TORTURE_PIPE_LEN;
 	}
-	__this_cpu_inc(per_cpu_var(rcu_torture_batch)[completed]);
+	__this_cpu_inc(rcu_torture_batch[completed]);
 	preempt_enable();
 	cur_ops->readunlock(idx);
 }
@@ -798,11 +853,15 @@ rcu_torture_reader(void *arg)
 	do {
 		if (irqreader && cur_ops->irq_capable) {
 			if (!timer_pending(&t))
-				mod_timer(&t, 1);
+				mod_timer(&t, jiffies + 1);
 		}
 		idx = cur_ops->readlock();
 		completed = cur_ops->completed();
-		p = rcu_dereference(rcu_torture_current);
+		p = rcu_dereference_check(rcu_torture_current,
+					  rcu_read_lock_held() ||
+					  rcu_read_lock_bh_held() ||
+					  rcu_read_lock_sched_held() ||
+					  srcu_read_lock_held(&srcu_ctl));
 		if (p == NULL) {
 			/* Wait for rcu_torture_writer to get underway */
 			cur_ops->readunlock(idx);
@@ -818,13 +877,13 @@ rcu_torture_reader(void *arg)
 			/* Should not happen, but... */
 			pipe_count = RCU_TORTURE_PIPE_LEN;
 		}
-		__this_cpu_inc(per_cpu_var(rcu_torture_count)[pipe_count]);
+		__this_cpu_inc(rcu_torture_count[pipe_count]);
 		completed = cur_ops->completed() - completed;
 		if (completed > RCU_TORTURE_PIPE_LEN) {
 			/* Should not happen, but... */
 			completed = RCU_TORTURE_PIPE_LEN;
 		}
-		__this_cpu_inc(per_cpu_var(rcu_torture_batch)[completed]);
+		__this_cpu_inc(rcu_torture_batch[completed]);
 		preempt_enable();
 		cur_ops->readunlock(idx);
 		schedule();
@@ -1030,10 +1089,11 @@ rcu_torture_print_module_parms(char *tag)
 	printk(KERN_ALERT "%s" TORTURE_FLAG
 		"--- %s: nreaders=%d nfakewriters=%d "
 		"stat_interval=%d verbose=%d test_no_idle_hz=%d "
-		"shuffle_interval=%d stutter=%d irqreader=%d\n",
+		"shuffle_interval=%d stutter=%d irqreader=%d "
+		"fqs_duration=%d fqs_holdoff=%d fqs_stutter=%d\n",
 		torture_type, tag, nrealreaders, nfakewriters,
 		stat_interval, verbose, test_no_idle_hz, shuffle_interval,
-		stutter, irqreader);
+		stutter, irqreader, fqs_duration, fqs_holdoff, fqs_stutter);
 }
 
 static struct notifier_block rcutorture_nb = {
@@ -1109,6 +1169,12 @@ rcu_torture_cleanup(void)
 	}
 	stats_task = NULL;
 
+	if (fqs_task) {
+		VERBOSE_PRINTK_STRING("Stopping rcu_torture_fqs task");
+		kthread_stop(fqs_task);
+	}
+	fqs_task = NULL;
+
 	/* Wait for all RCU callbacks to fire.  */
 
 	if (cur_ops->cb_barrier != NULL)
@@ -1154,6 +1220,11 @@ rcu_torture_init(void)
 		mutex_unlock(&fullstop_mutex);
 		return -EINVAL;
 	}
+	if (cur_ops->fqs == NULL && fqs_duration != 0) {
+		printk(KERN_ALERT "rcu-torture: ->fqs NULL and non-zero "
+				  "fqs_duration, fqs disabled.\n");
+		fqs_duration = 0;
+	}
 	if (cur_ops->init)
 		cur_ops->init(); /* no "goto unwind" prior to this point!!! */
 
@@ -1282,6 +1353,19 @@ rcu_torture_init(void)
 			goto unwind;
 		}
 	}
+	if (fqs_duration < 0)
+		fqs_duration = 0;
+	if (fqs_duration) {
+		/* Create the stutter thread */
+		fqs_task = kthread_run(rcu_torture_fqs, NULL,
+				       "rcu_torture_fqs");
+		if (IS_ERR(fqs_task)) {
+			firsterr = PTR_ERR(fqs_task);
+			VERBOSE_PRINTK_ERRSTRING("Failed to create fqs");
+			fqs_task = NULL;
+			goto unwind;
+		}
+	}
 	register_reboot_notifier(&rcutorture_nb);
 	mutex_unlock(&fullstop_mutex);
 	return 0;
diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index 53ae9598f79..3ec8160fc75 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -46,7 +46,6 @@
 #include <linux/cpu.h>
 #include <linux/mutex.h>
 #include <linux/time.h>
-#include <linux/kernel_stat.h>
 
 #include "rcutree.h"
 
@@ -66,11 +65,11 @@ static struct lock_class_key rcu_node_class[NUM_RCU_LVLS];
 	.signaled = RCU_GP_IDLE, \
 	.gpnum = -300, \
 	.completed = -300, \
-	.onofflock = __SPIN_LOCK_UNLOCKED(&name.onofflock), \
+	.onofflock = __RAW_SPIN_LOCK_UNLOCKED(&name.onofflock), \
 	.orphan_cbs_list = NULL, \
 	.orphan_cbs_tail = &name.orphan_cbs_list, \
 	.orphan_qlen = 0, \
-	.fqslock = __SPIN_LOCK_UNLOCKED(&name.fqslock), \
+	.fqslock = __RAW_SPIN_LOCK_UNLOCKED(&name.fqslock), \
 	.n_force_qs = 0, \
 	.n_force_qs_ngp = 0, \
 }
@@ -81,9 +80,6 @@ DEFINE_PER_CPU(struct rcu_data, rcu_sched_data);
 struct rcu_state rcu_bh_state = RCU_STATE_INITIALIZER(rcu_bh_state);
 DEFINE_PER_CPU(struct rcu_data, rcu_bh_data);
 
-static int rcu_scheduler_active __read_mostly;
-
-
 /*
  * Return true if an RCU grace period is in progress.  The ACCESS_ONCE()s
  * permit this function to be invoked without holding the root rcu_node
@@ -157,6 +153,24 @@ long rcu_batches_completed_bh(void)
 EXPORT_SYMBOL_GPL(rcu_batches_completed_bh);
 
 /*
+ * Force a quiescent state for RCU BH.
+ */
+void rcu_bh_force_quiescent_state(void)
+{
+	force_quiescent_state(&rcu_bh_state, 0);
+}
+EXPORT_SYMBOL_GPL(rcu_bh_force_quiescent_state);
+
+/*
+ * Force a quiescent state for RCU-sched.
+ */
+void rcu_sched_force_quiescent_state(void)
+{
+	force_quiescent_state(&rcu_sched_state, 0);
+}
+EXPORT_SYMBOL_GPL(rcu_sched_force_quiescent_state);
+
+/*
  * Does the CPU have callbacks ready to be invoked?
  */
 static int
@@ -439,10 +453,10 @@ static void print_other_cpu_stall(struct rcu_state *rsp)
 
 	/* Only let one CPU complain about others per time interval. */
 
-	spin_lock_irqsave(&rnp->lock, flags);
+	raw_spin_lock_irqsave(&rnp->lock, flags);
 	delta = jiffies - rsp->jiffies_stall;
 	if (delta < RCU_STALL_RAT_DELAY || !rcu_gp_in_progress(rsp)) {
-		spin_unlock_irqrestore(&rnp->lock, flags);
+		raw_spin_unlock_irqrestore(&rnp->lock, flags);
 		return;
 	}
 	rsp->jiffies_stall = jiffies + RCU_SECONDS_TILL_STALL_RECHECK;
@@ -452,13 +466,15 @@ static void print_other_cpu_stall(struct rcu_state *rsp)
 	 * due to CPU offlining.
 	 */
 	rcu_print_task_stall(rnp);
-	spin_unlock_irqrestore(&rnp->lock, flags);
+	raw_spin_unlock_irqrestore(&rnp->lock, flags);
 
 	/* OK, time to rat on our buddy... */
 
 	printk(KERN_ERR "INFO: RCU detected CPU stalls:");
 	rcu_for_each_leaf_node(rsp, rnp) {
+		raw_spin_lock_irqsave(&rnp->lock, flags);
 		rcu_print_task_stall(rnp);
+		raw_spin_unlock_irqrestore(&rnp->lock, flags);
 		if (rnp->qsmask == 0)
 			continue;
 		for (cpu = 0; cpu <= rnp->grphi - rnp->grplo; cpu++)
@@ -469,6 +485,10 @@ static void print_other_cpu_stall(struct rcu_state *rsp)
 	       smp_processor_id(), (long)(jiffies - rsp->gp_start));
 	trigger_all_cpu_backtrace();
 
+	/* If so configured, complain about tasks blocking the grace period. */
+
+	rcu_print_detail_task_stall(rsp);
+
 	force_quiescent_state(rsp, 0);  /* Kick them all. */
 }
 
@@ -481,11 +501,11 @@ static void print_cpu_stall(struct rcu_state *rsp)
 			smp_processor_id(), jiffies - rsp->gp_start);
 	trigger_all_cpu_backtrace();
 
-	spin_lock_irqsave(&rnp->lock, flags);
-	if ((long)(jiffies - rsp->jiffies_stall) >= 0)
+	raw_spin_lock_irqsave(&rnp->lock, flags);
+	if (ULONG_CMP_GE(jiffies, rsp->jiffies_stall))
 		rsp->jiffies_stall =
 			jiffies + RCU_SECONDS_TILL_STALL_RECHECK;
-	spin_unlock_irqrestore(&rnp->lock, flags);
+	raw_spin_unlock_irqrestore(&rnp->lock, flags);
 
 	set_need_resched();  /* kick ourselves to get things going. */
 }
@@ -545,12 +565,12 @@ static void note_new_gpnum(struct rcu_state *rsp, struct rcu_data *rdp)
 	local_irq_save(flags);
 	rnp = rdp->mynode;
 	if (rdp->gpnum == ACCESS_ONCE(rnp->gpnum) || /* outside lock. */
-	    !spin_trylock(&rnp->lock)) { /* irqs already off, retry later. */
+	    !raw_spin_trylock(&rnp->lock)) { /* irqs already off, so later. */
 		local_irq_restore(flags);
 		return;
 	}
 	__note_new_gpnum(rsp, rnp, rdp);
-	spin_unlock_irqrestore(&rnp->lock, flags);
+	raw_spin_unlock_irqrestore(&rnp->lock, flags);
 }
 
 /*
@@ -609,12 +629,12 @@ rcu_process_gp_end(struct rcu_state *rsp, struct rcu_data *rdp)
 	local_irq_save(flags);
 	rnp = rdp->mynode;
 	if (rdp->completed == ACCESS_ONCE(rnp->completed) || /* outside lock. */
-	    !spin_trylock(&rnp->lock)) { /* irqs already off, retry later. */
+	    !raw_spin_trylock(&rnp->lock)) { /* irqs already off, so later. */
 		local_irq_restore(flags);
 		return;
 	}
 	__rcu_process_gp_end(rsp, rnp, rdp);
-	spin_unlock_irqrestore(&rnp->lock, flags);
+	raw_spin_unlock_irqrestore(&rnp->lock, flags);
 }
 
 /*
@@ -659,12 +679,14 @@ rcu_start_gp(struct rcu_state *rsp, unsigned long flags)
 	struct rcu_data *rdp = rsp->rda[smp_processor_id()];
 	struct rcu_node *rnp = rcu_get_root(rsp);
 
-	if (!cpu_needs_another_gp(rsp, rdp)) {
+	if (!cpu_needs_another_gp(rsp, rdp) || rsp->fqs_active) {
+		if (cpu_needs_another_gp(rsp, rdp))
+			rsp->fqs_need_gp = 1;
 		if (rnp->completed == rsp->completed) {
-			spin_unlock_irqrestore(&rnp->lock, flags);
+			raw_spin_unlock_irqrestore(&rnp->lock, flags);
 			return;
 		}
-		spin_unlock(&rnp->lock);	 /* irqs remain disabled. */
+		raw_spin_unlock(&rnp->lock);	 /* irqs remain disabled. */
 
 		/*
 		 * Propagate new ->completed value to rcu_node structures
@@ -672,9 +694,9 @@ rcu_start_gp(struct rcu_state *rsp, unsigned long flags)
 		 * of the next grace period to process their callbacks.
 		 */
 		rcu_for_each_node_breadth_first(rsp, rnp) {
-			spin_lock(&rnp->lock);	 /* irqs already disabled. */
+			raw_spin_lock(&rnp->lock); /* irqs already disabled. */
 			rnp->completed = rsp->completed;
-			spin_unlock(&rnp->lock); /* irqs remain disabled. */
+			raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */
 		}
 		local_irq_restore(flags);
 		return;
@@ -695,15 +717,15 @@ rcu_start_gp(struct rcu_state *rsp, unsigned long flags)
 		rnp->completed = rsp->completed;
 		rsp->signaled = RCU_SIGNAL_INIT; /* force_quiescent_state OK. */
 		rcu_start_gp_per_cpu(rsp, rnp, rdp);
-		spin_unlock_irqrestore(&rnp->lock, flags);
+		raw_spin_unlock_irqrestore(&rnp->lock, flags);
 		return;
 	}
 
-	spin_unlock(&rnp->lock);  /* leave irqs disabled. */
+	raw_spin_unlock(&rnp->lock);  /* leave irqs disabled. */
 
 
 	/* Exclude any concurrent CPU-hotplug operations. */
-	spin_lock(&rsp->onofflock);  /* irqs already disabled. */
+	raw_spin_lock(&rsp->onofflock);  /* irqs already disabled. */
 
 	/*
 	 * Set the quiescent-state-needed bits in all the rcu_node
@@ -723,21 +745,21 @@ rcu_start_gp(struct rcu_state *rsp, unsigned long flags)
 	 * irqs disabled.
 	 */
 	rcu_for_each_node_breadth_first(rsp, rnp) {
-		spin_lock(&rnp->lock);		/* irqs already disabled. */
+		raw_spin_lock(&rnp->lock);	/* irqs already disabled. */
 		rcu_preempt_check_blocked_tasks(rnp);
 		rnp->qsmask = rnp->qsmaskinit;
 		rnp->gpnum = rsp->gpnum;
 		rnp->completed = rsp->completed;
 		if (rnp == rdp->mynode)
 			rcu_start_gp_per_cpu(rsp, rnp, rdp);
-		spin_unlock(&rnp->lock);	/* irqs remain disabled. */
+		raw_spin_unlock(&rnp->lock);	/* irqs remain disabled. */
 	}
 
 	rnp = rcu_get_root(rsp);
-	spin_lock(&rnp->lock);			/* irqs already disabled. */
+	raw_spin_lock(&rnp->lock);		/* irqs already disabled. */
 	rsp->signaled = RCU_SIGNAL_INIT; /* force_quiescent_state now OK. */
-	spin_unlock(&rnp->lock);		/* irqs remain disabled. */
-	spin_unlock_irqrestore(&rsp->onofflock, flags);
+	raw_spin_unlock(&rnp->lock);		/* irqs remain disabled. */
+	raw_spin_unlock_irqrestore(&rsp->onofflock, flags);
 }
 
 /*
@@ -776,14 +798,14 @@ rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp,
 		if (!(rnp->qsmask & mask)) {
 
 			/* Our bit has already been cleared, so done. */
-			spin_unlock_irqrestore(&rnp->lock, flags);
+			raw_spin_unlock_irqrestore(&rnp->lock, flags);
 			return;
 		}
 		rnp->qsmask &= ~mask;
 		if (rnp->qsmask != 0 || rcu_preempted_readers(rnp)) {
 
 			/* Other bits still set at this level, so done. */
-			spin_unlock_irqrestore(&rnp->lock, flags);
+			raw_spin_unlock_irqrestore(&rnp->lock, flags);
 			return;
 		}
 		mask = rnp->grpmask;
@@ -793,10 +815,10 @@ rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp,
 
 			break;
 		}
-		spin_unlock_irqrestore(&rnp->lock, flags);
+		raw_spin_unlock_irqrestore(&rnp->lock, flags);
 		rnp_c = rnp;
 		rnp = rnp->parent;
-		spin_lock_irqsave(&rnp->lock, flags);
+		raw_spin_lock_irqsave(&rnp->lock, flags);
 		WARN_ON_ONCE(rnp_c->qsmask);
 	}
 
@@ -825,7 +847,7 @@ rcu_report_qs_rdp(int cpu, struct rcu_state *rsp, struct rcu_data *rdp, long las
 	struct rcu_node *rnp;
 
 	rnp = rdp->mynode;
-	spin_lock_irqsave(&rnp->lock, flags);
+	raw_spin_lock_irqsave(&rnp->lock, flags);
 	if (lastcomp != rnp->completed) {
 
 		/*
@@ -837,12 +859,12 @@ rcu_report_qs_rdp(int cpu, struct rcu_state *rsp, struct rcu_data *rdp, long las
 		 * race occurred.
 		 */
 		rdp->passed_quiesc = 0;	/* try again later! */
-		spin_unlock_irqrestore(&rnp->lock, flags);
+		raw_spin_unlock_irqrestore(&rnp->lock, flags);
 		return;
 	}
 	mask = rdp->grpmask;
 	if ((rnp->qsmask & mask) == 0) {
-		spin_unlock_irqrestore(&rnp->lock, flags);
+		raw_spin_unlock_irqrestore(&rnp->lock, flags);
 	} else {
 		rdp->qs_pending = 0;
 
@@ -906,7 +928,7 @@ static void rcu_send_cbs_to_orphanage(struct rcu_state *rsp)
 
 	if (rdp->nxtlist == NULL)
 		return;  /* irqs disabled, so comparison is stable. */
-	spin_lock(&rsp->onofflock);  /* irqs already disabled. */
+	raw_spin_lock(&rsp->onofflock);  /* irqs already disabled. */
 	*rsp->orphan_cbs_tail = rdp->nxtlist;
 	rsp->orphan_cbs_tail = rdp->nxttail[RCU_NEXT_TAIL];
 	rdp->nxtlist = NULL;
@@ -914,7 +936,7 @@ static void rcu_send_cbs_to_orphanage(struct rcu_state *rsp)
 		rdp->nxttail[i] = &rdp->nxtlist;
 	rsp->orphan_qlen += rdp->qlen;
 	rdp->qlen = 0;
-	spin_unlock(&rsp->onofflock);  /* irqs remain disabled. */
+	raw_spin_unlock(&rsp->onofflock);  /* irqs remain disabled. */
 }
 
 /*
@@ -925,10 +947,10 @@ static void rcu_adopt_orphan_cbs(struct rcu_state *rsp)
 	unsigned long flags;
 	struct rcu_data *rdp;
 
-	spin_lock_irqsave(&rsp->onofflock, flags);
+	raw_spin_lock_irqsave(&rsp->onofflock, flags);
 	rdp = rsp->rda[smp_processor_id()];
 	if (rsp->orphan_cbs_list == NULL) {
-		spin_unlock_irqrestore(&rsp->onofflock, flags);
+		raw_spin_unlock_irqrestore(&rsp->onofflock, flags);
 		return;
 	}
 	*rdp->nxttail[RCU_NEXT_TAIL] = rsp->orphan_cbs_list;
@@ -937,7 +959,7 @@ static void rcu_adopt_orphan_cbs(struct rcu_state *rsp)
 	rsp->orphan_cbs_list = NULL;
 	rsp->orphan_cbs_tail = &rsp->orphan_cbs_list;
 	rsp->orphan_qlen = 0;
-	spin_unlock_irqrestore(&rsp->onofflock, flags);
+	raw_spin_unlock_irqrestore(&rsp->onofflock, flags);
 }
 
 /*
@@ -953,23 +975,23 @@ static void __rcu_offline_cpu(int cpu, struct rcu_state *rsp)
 	struct rcu_node *rnp;
 
 	/* Exclude any attempts to start a new grace period. */
-	spin_lock_irqsave(&rsp->onofflock, flags);
+	raw_spin_lock_irqsave(&rsp->onofflock, flags);
 
 	/* Remove the outgoing CPU from the masks in the rcu_node hierarchy. */
 	rnp = rdp->mynode;	/* this is the outgoing CPU's rnp. */
 	mask = rdp->grpmask;	/* rnp->grplo is constant. */
 	do {
-		spin_lock(&rnp->lock);		/* irqs already disabled. */
+		raw_spin_lock(&rnp->lock);	/* irqs already disabled. */
 		rnp->qsmaskinit &= ~mask;
 		if (rnp->qsmaskinit != 0) {
 			if (rnp != rdp->mynode)
-				spin_unlock(&rnp->lock); /* irqs remain disabled. */
+				raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */
 			break;
 		}
 		if (rnp == rdp->mynode)
 			need_report = rcu_preempt_offline_tasks(rsp, rnp, rdp);
 		else
-			spin_unlock(&rnp->lock); /* irqs remain disabled. */
+			raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */
 		mask = rnp->grpmask;
 		rnp = rnp->parent;
 	} while (rnp != NULL);
@@ -980,12 +1002,12 @@ static void __rcu_offline_cpu(int cpu, struct rcu_state *rsp)
 	 * because invoking rcu_report_unblock_qs_rnp() with ->onofflock
 	 * held leads to deadlock.
 	 */
-	spin_unlock(&rsp->onofflock); /* irqs remain disabled. */
+	raw_spin_unlock(&rsp->onofflock); /* irqs remain disabled. */
 	rnp = rdp->mynode;
 	if (need_report & RCU_OFL_TASKS_NORM_GP)
 		rcu_report_unblock_qs_rnp(rnp, flags);
 	else
-		spin_unlock_irqrestore(&rnp->lock, flags);
+		raw_spin_unlock_irqrestore(&rnp->lock, flags);
 	if (need_report & RCU_OFL_TASKS_EXP_GP)
 		rcu_report_exp_rnp(rsp, rnp);
 
@@ -1144,11 +1166,9 @@ void rcu_check_callbacks(int cpu, int user)
 /*
  * Scan the leaf rcu_node structures, processing dyntick state for any that
  * have not yet encountered a quiescent state, using the function specified.
- * Returns 1 if the current grace period ends while scanning (possibly
- * because we made it end).
+ * The caller must have suppressed start of new grace periods.
  */
-static int rcu_process_dyntick(struct rcu_state *rsp, long lastcomp,
-			       int (*f)(struct rcu_data *))
+static void force_qs_rnp(struct rcu_state *rsp, int (*f)(struct rcu_data *))
 {
 	unsigned long bit;
 	int cpu;
@@ -1158,13 +1178,13 @@ static int rcu_process_dyntick(struct rcu_state *rsp, long lastcomp,
 
 	rcu_for_each_leaf_node(rsp, rnp) {
 		mask = 0;
-		spin_lock_irqsave(&rnp->lock, flags);
-		if (rnp->completed != lastcomp) {
-			spin_unlock_irqrestore(&rnp->lock, flags);
-			return 1;
+		raw_spin_lock_irqsave(&rnp->lock, flags);
+		if (!rcu_gp_in_progress(rsp)) {
+			raw_spin_unlock_irqrestore(&rnp->lock, flags);
+			return;
 		}
 		if (rnp->qsmask == 0) {
-			spin_unlock_irqrestore(&rnp->lock, flags);
+			raw_spin_unlock_irqrestore(&rnp->lock, flags);
 			continue;
 		}
 		cpu = rnp->grplo;
@@ -1173,15 +1193,14 @@ static int rcu_process_dyntick(struct rcu_state *rsp, long lastcomp,
 			if ((rnp->qsmask & bit) != 0 && f(rsp->rda[cpu]))
 				mask |= bit;
 		}
-		if (mask != 0 && rnp->completed == lastcomp) {
+		if (mask != 0) {
 
 			/* rcu_report_qs_rnp() releases rnp->lock. */
 			rcu_report_qs_rnp(mask, rsp, rnp, flags);
 			continue;
 		}
-		spin_unlock_irqrestore(&rnp->lock, flags);
+		raw_spin_unlock_irqrestore(&rnp->lock, flags);
 	}
-	return 0;
 }
 
 /*
@@ -1191,32 +1210,26 @@ static int rcu_process_dyntick(struct rcu_state *rsp, long lastcomp,
 static void force_quiescent_state(struct rcu_state *rsp, int relaxed)
 {
 	unsigned long flags;
-	long lastcomp;
 	struct rcu_node *rnp = rcu_get_root(rsp);
-	u8 signaled;
-	u8 forcenow;
 
 	if (!rcu_gp_in_progress(rsp))
 		return;  /* No grace period in progress, nothing to force. */
-	if (!spin_trylock_irqsave(&rsp->fqslock, flags)) {
+	if (!raw_spin_trylock_irqsave(&rsp->fqslock, flags)) {
 		rsp->n_force_qs_lh++; /* Inexact, can lose counts.  Tough! */
 		return;	/* Someone else is already on the job. */
 	}
-	if (relaxed &&
-	    (long)(rsp->jiffies_force_qs - jiffies) >= 0)
-		goto unlock_ret; /* no emergency and done recently. */
+	if (relaxed && ULONG_CMP_GE(rsp->jiffies_force_qs, jiffies))
+		goto unlock_fqs_ret; /* no emergency and done recently. */
 	rsp->n_force_qs++;
-	spin_lock(&rnp->lock);
-	lastcomp = rsp->gpnum - 1;
-	signaled = rsp->signaled;
+	raw_spin_lock(&rnp->lock);  /* irqs already disabled */
 	rsp->jiffies_force_qs = jiffies + RCU_JIFFIES_TILL_FORCE_QS;
 	if(!rcu_gp_in_progress(rsp)) {
 		rsp->n_force_qs_ngp++;
-		spin_unlock(&rnp->lock);
-		goto unlock_ret;  /* no GP in progress, time updated. */
+		raw_spin_unlock(&rnp->lock);  /* irqs remain disabled */
+		goto unlock_fqs_ret;  /* no GP in progress, time updated. */
 	}
-	spin_unlock(&rnp->lock);
-	switch (signaled) {
+	rsp->fqs_active = 1;
+	switch (rsp->signaled) {
 	case RCU_GP_IDLE:
 	case RCU_GP_INIT:
 
@@ -1224,45 +1237,38 @@ static void force_quiescent_state(struct rcu_state *rsp, int relaxed)
 
 	case RCU_SAVE_DYNTICK:
 
+		raw_spin_unlock(&rnp->lock);  /* irqs remain disabled */
 		if (RCU_SIGNAL_INIT != RCU_SAVE_DYNTICK)
 			break; /* So gcc recognizes the dead code. */
 
 		/* Record dyntick-idle state. */
-		if (rcu_process_dyntick(rsp, lastcomp,
-					dyntick_save_progress_counter))
-			goto unlock_ret;
-		/* fall into next case. */
-
-	case RCU_SAVE_COMPLETED:
-
-		/* Update state, record completion counter. */
-		forcenow = 0;
-		spin_lock(&rnp->lock);
-		if (lastcomp + 1 == rsp->gpnum &&
-		    lastcomp == rsp->completed &&
-		    rsp->signaled == signaled) {
+		force_qs_rnp(rsp, dyntick_save_progress_counter);
+		raw_spin_lock(&rnp->lock);  /* irqs already disabled */
+		if (rcu_gp_in_progress(rsp))
 			rsp->signaled = RCU_FORCE_QS;
-			rsp->completed_fqs = lastcomp;
-			forcenow = signaled == RCU_SAVE_COMPLETED;
-		}
-		spin_unlock(&rnp->lock);
-		if (!forcenow)
-			break;
-		/* fall into next case. */
+		break;
 
 	case RCU_FORCE_QS:
 
 		/* Check dyntick-idle state, send IPI to laggarts. */
-		if (rcu_process_dyntick(rsp, rsp->completed_fqs,
-					rcu_implicit_dynticks_qs))
-			goto unlock_ret;
+		raw_spin_unlock(&rnp->lock);  /* irqs remain disabled */
+		force_qs_rnp(rsp, rcu_implicit_dynticks_qs);
 
 		/* Leave state in case more forcing is required. */
 
+		raw_spin_lock(&rnp->lock);  /* irqs already disabled */
 		break;
 	}
-unlock_ret:
-	spin_unlock_irqrestore(&rsp->fqslock, flags);
+	rsp->fqs_active = 0;
+	if (rsp->fqs_need_gp) {
+		raw_spin_unlock(&rsp->fqslock); /* irqs remain disabled */
+		rsp->fqs_need_gp = 0;
+		rcu_start_gp(rsp, flags); /* releases rnp->lock */
+		return;
+	}
+	raw_spin_unlock(&rnp->lock);  /* irqs remain disabled */
+unlock_fqs_ret:
+	raw_spin_unlock_irqrestore(&rsp->fqslock, flags);
 }
 
 #else /* #ifdef CONFIG_SMP */
@@ -1290,7 +1296,7 @@ __rcu_process_callbacks(struct rcu_state *rsp, struct rcu_data *rdp)
 	 * If an RCU GP has gone long enough, go check for dyntick
 	 * idle CPUs and, if needed, send resched IPIs.
 	 */
-	if ((long)(ACCESS_ONCE(rsp->jiffies_force_qs) - jiffies) < 0)
+	if (ULONG_CMP_LT(ACCESS_ONCE(rsp->jiffies_force_qs), jiffies))
 		force_quiescent_state(rsp, 1);
 
 	/*
@@ -1304,7 +1310,7 @@ __rcu_process_callbacks(struct rcu_state *rsp, struct rcu_data *rdp)
 
 	/* Does this CPU require a not-yet-started grace period? */
 	if (cpu_needs_another_gp(rsp, rdp)) {
-		spin_lock_irqsave(&rcu_get_root(rsp)->lock, flags);
+		raw_spin_lock_irqsave(&rcu_get_root(rsp)->lock, flags);
 		rcu_start_gp(rsp, flags);  /* releases above lock */
 	}
 
@@ -1335,6 +1341,9 @@ static void rcu_process_callbacks(struct softirq_action *unused)
 	 * 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();
 }
 
 static void
@@ -1369,7 +1378,7 @@ __call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu),
 		unsigned long nestflag;
 		struct rcu_node *rnp_root = rcu_get_root(rsp);
 
-		spin_lock_irqsave(&rnp_root->lock, nestflag);
+		raw_spin_lock_irqsave(&rnp_root->lock, nestflag);
 		rcu_start_gp(rsp, nestflag);  /* releases rnp_root->lock. */
 	}
 
@@ -1387,7 +1396,7 @@ __call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu),
 			force_quiescent_state(rsp, 0);
 		rdp->n_force_qs_snap = rsp->n_force_qs;
 		rdp->qlen_last_fqs_check = rdp->qlen;
-	} else if ((long)(ACCESS_ONCE(rsp->jiffies_force_qs) - jiffies) < 0)
+	} else if (ULONG_CMP_LT(ACCESS_ONCE(rsp->jiffies_force_qs), jiffies))
 		force_quiescent_state(rsp, 1);
 	local_irq_restore(flags);
 }
@@ -1520,7 +1529,7 @@ static int __rcu_pending(struct rcu_state *rsp, struct rcu_data *rdp)
 
 	/* Has an RCU GP gone long enough to send resched IPIs &c? */
 	if (rcu_gp_in_progress(rsp) &&
-	    ((long)(ACCESS_ONCE(rsp->jiffies_force_qs) - jiffies) < 0)) {
+	    ULONG_CMP_LT(ACCESS_ONCE(rsp->jiffies_force_qs), jiffies)) {
 		rdp->n_rp_need_fqs++;
 		return 1;
 	}
@@ -1545,10 +1554,9 @@ static int rcu_pending(int cpu)
 /*
  * Check to see if any future RCU-related work will need to be done
  * by the current CPU, even if none need be done immediately, returning
- * 1 if so.  This function is part of the RCU implementation; it is -not-
- * an exported member of the RCU API.
+ * 1 if so.
  */
-int rcu_needs_cpu(int cpu)
+static int rcu_needs_cpu_quick_check(int cpu)
 {
 	/* RCU callbacks either ready or pending? */
 	return per_cpu(rcu_sched_data, cpu).nxtlist ||
@@ -1556,21 +1564,6 @@ int rcu_needs_cpu(int cpu)
 	       rcu_preempt_needs_cpu(cpu);
 }
 
-/*
- * This function is invoked towards the end of the scheduler's initialization
- * process.  Before this is called, the idle task might contain
- * RCU read-side critical sections (during which time, this idle
- * task is booting the system).  After this function is called, the
- * idle tasks are prohibited from containing RCU read-side critical
- * sections.
- */
-void rcu_scheduler_starting(void)
-{
-	WARN_ON(num_online_cpus() != 1);
-	WARN_ON(nr_context_switches() > 0);
-	rcu_scheduler_active = 1;
-}
-
 static DEFINE_PER_CPU(struct rcu_head, rcu_barrier_head) = {NULL};
 static atomic_t rcu_barrier_cpu_count;
 static DEFINE_MUTEX(rcu_barrier_mutex);
@@ -1659,7 +1652,7 @@ rcu_boot_init_percpu_data(int cpu, struct rcu_state *rsp)
 	struct rcu_node *rnp = rcu_get_root(rsp);
 
 	/* Set up local state, ensuring consistent view of global state. */
-	spin_lock_irqsave(&rnp->lock, flags);
+	raw_spin_lock_irqsave(&rnp->lock, flags);
 	rdp->grpmask = 1UL << (cpu - rdp->mynode->grplo);
 	rdp->nxtlist = NULL;
 	for (i = 0; i < RCU_NEXT_SIZE; i++)
@@ -1669,7 +1662,7 @@ rcu_boot_init_percpu_data(int cpu, struct rcu_state *rsp)
 	rdp->dynticks = &per_cpu(rcu_dynticks, cpu);
 #endif /* #ifdef CONFIG_NO_HZ */
 	rdp->cpu = cpu;
-	spin_unlock_irqrestore(&rnp->lock, flags);
+	raw_spin_unlock_irqrestore(&rnp->lock, flags);
 }
 
 /*
@@ -1687,7 +1680,7 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp, int preemptable)
 	struct rcu_node *rnp = rcu_get_root(rsp);
 
 	/* Set up local state, ensuring consistent view of global state. */
-	spin_lock_irqsave(&rnp->lock, flags);
+	raw_spin_lock_irqsave(&rnp->lock, flags);
 	rdp->passed_quiesc = 0;  /* We could be racing with new GP, */
 	rdp->qs_pending = 1;	 /*  so set up to respond to current GP. */
 	rdp->beenonline = 1;	 /* We have now been online. */
@@ -1695,7 +1688,7 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp, int preemptable)
 	rdp->qlen_last_fqs_check = 0;
 	rdp->n_force_qs_snap = rsp->n_force_qs;
 	rdp->blimit = blimit;
-	spin_unlock(&rnp->lock);		/* irqs remain disabled. */
+	raw_spin_unlock(&rnp->lock);		/* irqs remain disabled. */
 
 	/*
 	 * A new grace period might start here.  If so, we won't be part
@@ -1703,14 +1696,14 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp, int preemptable)
 	 */
 
 	/* Exclude any attempts to start a new GP on large systems. */
-	spin_lock(&rsp->onofflock);		/* irqs already disabled. */
+	raw_spin_lock(&rsp->onofflock);		/* irqs already disabled. */
 
 	/* Add CPU to rcu_node bitmasks. */
 	rnp = rdp->mynode;
 	mask = rdp->grpmask;
 	do {
 		/* Exclude any attempts to start a new GP on small systems. */
-		spin_lock(&rnp->lock);	/* irqs already disabled. */
+		raw_spin_lock(&rnp->lock);	/* irqs already disabled. */
 		rnp->qsmaskinit |= mask;
 		mask = rnp->grpmask;
 		if (rnp == rdp->mynode) {
@@ -1718,11 +1711,11 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp, int preemptable)
 			rdp->completed = rnp->completed;
 			rdp->passed_quiesc_completed = rnp->completed - 1;
 		}
-		spin_unlock(&rnp->lock); /* irqs already disabled. */
+		raw_spin_unlock(&rnp->lock); /* irqs already disabled. */
 		rnp = rnp->parent;
 	} while (rnp != NULL && !(rnp->qsmaskinit & mask));
 
-	spin_unlock_irqrestore(&rsp->onofflock, flags);
+	raw_spin_unlock_irqrestore(&rsp->onofflock, flags);
 }
 
 static void __cpuinit rcu_online_cpu(int cpu)
@@ -1806,11 +1799,17 @@ static void __init rcu_init_levelspread(struct rcu_state *rsp)
  */
 static void __init rcu_init_one(struct rcu_state *rsp)
 {
+	static char *buf[] = { "rcu_node_level_0",
+			       "rcu_node_level_1",
+			       "rcu_node_level_2",
+			       "rcu_node_level_3" };  /* Match MAX_RCU_LVLS */
 	int cpustride = 1;
 	int i;
 	int j;
 	struct rcu_node *rnp;
 
+	BUILD_BUG_ON(MAX_RCU_LVLS > ARRAY_SIZE(buf));  /* Fix buf[] init! */
+
 	/* Initialize the level-tracking arrays. */
 
 	for (i = 1; i < NUM_RCU_LVLS; i++)
@@ -1823,8 +1822,9 @@ static void __init rcu_init_one(struct rcu_state *rsp)
 		cpustride *= rsp->levelspread[i];
 		rnp = rsp->level[i];
 		for (j = 0; j < rsp->levelcnt[i]; j++, rnp++) {
-			spin_lock_init(&rnp->lock);
-			lockdep_set_class(&rnp->lock, &rcu_node_class[i]);
+			raw_spin_lock_init(&rnp->lock);
+			lockdep_set_class_and_name(&rnp->lock,
+						   &rcu_node_class[i], buf[i]);
 			rnp->gpnum = 0;
 			rnp->qsmask = 0;
 			rnp->qsmaskinit = 0;
@@ -1876,7 +1876,7 @@ do { \
 
 void __init rcu_init(void)
 {
-	int i;
+	int cpu;
 
 	rcu_bootup_announce();
 #ifdef CONFIG_RCU_CPU_STALL_DETECTOR
@@ -1896,8 +1896,8 @@ void __init rcu_init(void)
 	 * or the scheduler are operational.
 	 */
 	cpu_notifier(rcu_cpu_notify, 0);
-	for_each_online_cpu(i)
-		rcu_cpu_notify(NULL, CPU_UP_PREPARE, (void *)(long)i);
+	for_each_online_cpu(cpu)
+		rcu_cpu_notify(NULL, CPU_UP_PREPARE, (void *)(long)cpu);
 }
 
 #include "rcutree_plugin.h"
diff --git a/kernel/rcutree.h b/kernel/rcutree.h
index d2a0046f63b..4a525a30e08 100644
--- a/kernel/rcutree.h
+++ b/kernel/rcutree.h
@@ -90,12 +90,12 @@ struct rcu_dynticks {
  * Definition for node within the RCU grace-period-detection hierarchy.
  */
 struct rcu_node {
-	spinlock_t lock;	/* Root rcu_node's lock protects some */
+	raw_spinlock_t lock;	/* Root rcu_node's lock protects some */
 				/*  rcu_state fields as well as following. */
-	long	gpnum;		/* Current grace period for this node. */
+	unsigned long gpnum;	/* Current grace period for this node. */
 				/*  This will either be equal to or one */
 				/*  behind the root rcu_node's gpnum. */
-	long	completed;	/* Last grace period completed for this node. */
+	unsigned long completed; /* Last GP completed for this node. */
 				/*  This will either be equal to or one */
 				/*  behind the root rcu_node's gpnum. */
 	unsigned long qsmask;	/* CPUs or groups that need to switch in */
@@ -161,11 +161,11 @@ struct rcu_node {
 /* Per-CPU data for read-copy update. */
 struct rcu_data {
 	/* 1) quiescent-state and grace-period handling : */
-	long		completed;	/* Track rsp->completed gp number */
+	unsigned long	completed;	/* Track rsp->completed gp number */
 					/*  in order to detect GP end. */
-	long		gpnum;		/* Highest gp number that this CPU */
+	unsigned long	gpnum;		/* Highest gp number that this CPU */
 					/*  is aware of having started. */
-	long		passed_quiesc_completed;
+	unsigned long	passed_quiesc_completed;
 					/* Value of completed at time of qs. */
 	bool		passed_quiesc;	/* User-mode/idle loop etc. */
 	bool		qs_pending;	/* Core waits for quiesc state. */
@@ -221,14 +221,14 @@ struct rcu_data {
 	unsigned long resched_ipi;	/* Sent a resched IPI. */
 
 	/* 5) __rcu_pending() statistics. */
-	long n_rcu_pending;		/* rcu_pending() calls since boot. */
-	long n_rp_qs_pending;
-	long n_rp_cb_ready;
-	long n_rp_cpu_needs_gp;
-	long n_rp_gp_completed;
-	long n_rp_gp_started;
-	long n_rp_need_fqs;
-	long n_rp_need_nothing;
+	unsigned long n_rcu_pending;	/* rcu_pending() calls since boot. */
+	unsigned long n_rp_qs_pending;
+	unsigned long n_rp_cb_ready;
+	unsigned long n_rp_cpu_needs_gp;
+	unsigned long n_rp_gp_completed;
+	unsigned long n_rp_gp_started;
+	unsigned long n_rp_need_fqs;
+	unsigned long n_rp_need_nothing;
 
 	int cpu;
 };
@@ -237,25 +237,36 @@ struct rcu_data {
 #define RCU_GP_IDLE		0	/* No grace period in progress. */
 #define RCU_GP_INIT		1	/* Grace period being initialized. */
 #define RCU_SAVE_DYNTICK	2	/* Need to scan dyntick state. */
-#define RCU_SAVE_COMPLETED	3	/* Need to save rsp->completed. */
-#define RCU_FORCE_QS		4	/* Need to force quiescent state. */
+#define RCU_FORCE_QS		3	/* Need to force quiescent state. */
 #ifdef CONFIG_NO_HZ
 #define RCU_SIGNAL_INIT		RCU_SAVE_DYNTICK
 #else /* #ifdef CONFIG_NO_HZ */
-#define RCU_SIGNAL_INIT		RCU_SAVE_COMPLETED
+#define RCU_SIGNAL_INIT		RCU_FORCE_QS
 #endif /* #else #ifdef CONFIG_NO_HZ */
 
 #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 */
 
+#define ULONG_CMP_GE(a, b)	(ULONG_MAX / 2 >= (a) - (b))
+#define ULONG_CMP_LT(a, b)	(ULONG_MAX / 2 < (a) - (b))
+
 /*
  * RCU global state, including node hierarchy.  This hierarchy is
  * represented in "heap" form in a dense array.  The root (first level)
@@ -277,12 +288,19 @@ struct rcu_state {
 
 	u8	signaled ____cacheline_internodealigned_in_smp;
 						/* Force QS state. */
-	long	gpnum;				/* Current gp number. */
-	long	completed;			/* # of last completed gp. */
+	u8	fqs_active;			/* force_quiescent_state() */
+						/*  is running. */
+	u8	fqs_need_gp;			/* A CPU was prevented from */
+						/*  starting a new grace */
+						/*  period because */
+						/*  force_quiescent_state() */
+						/*  was running. */
+	unsigned long gpnum;			/* Current gp number. */
+	unsigned long completed;		/* # of last completed gp. */
 
 	/* End of fields guarded by root rcu_node's lock. */
 
-	spinlock_t onofflock;			/* exclude on/offline and */
+	raw_spinlock_t onofflock;		/* exclude on/offline and */
 						/*  starting new GP.  Also */
 						/*  protects the following */
 						/*  orphan_cbs fields. */
@@ -292,10 +310,8 @@ struct rcu_state {
 						/*  going offline. */
 	struct rcu_head **orphan_cbs_tail;	/* And tail pointer. */
 	long orphan_qlen;			/* Number of orphaned cbs. */
-	spinlock_t fqslock;			/* Only one task forcing */
+	raw_spinlock_t fqslock;			/* Only one task forcing */
 						/*  quiescent states. */
-	long	completed_fqs;			/* Value of completed @ snap. */
-						/*  Protected by fqslock. */
 	unsigned long jiffies_force_qs;		/* Time at which to invoke */
 						/*  force_quiescent_state(). */
 	unsigned long n_force_qs;		/* Number of calls to */
@@ -319,8 +335,6 @@ struct rcu_state {
 #define RCU_OFL_TASKS_EXP_GP	0x2		/* Tasks blocking expedited */
 						/*  GP were moved to root. */
 
-#ifdef RCU_TREE_NONCORE
-
 /*
  * RCU implementation internal declarations:
  */
@@ -335,7 +349,7 @@ extern struct rcu_state rcu_preempt_state;
 DECLARE_PER_CPU(struct rcu_data, rcu_preempt_data);
 #endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */
 
-#else /* #ifdef RCU_TREE_NONCORE */
+#ifndef RCU_TREE_NONCORE
 
 /* Forward declarations for rcutree_plugin.h */
 static void rcu_bootup_announce(void);
@@ -347,6 +361,7 @@ static void rcu_report_unblock_qs_rnp(struct rcu_node *rnp,
 				      unsigned long flags);
 #endif /* #ifdef CONFIG_HOTPLUG_CPU */
 #ifdef CONFIG_RCU_CPU_STALL_DETECTOR
+static void rcu_print_detail_task_stall(struct rcu_state *rsp);
 static void rcu_print_task_stall(struct rcu_node *rnp);
 #endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
 static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp);
@@ -367,5 +382,6 @@ static int rcu_preempt_needs_cpu(int cpu);
 static void __cpuinit rcu_preempt_init_percpu_data(int cpu);
 static void rcu_preempt_send_cbs_to_orphanage(void);
 static void __init __rcu_init_preempt(void);
+static void rcu_needs_cpu_flush(void);
 
-#endif /* #else #ifdef RCU_TREE_NONCORE */
+#endif /* #ifndef RCU_TREE_NONCORE */
diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h
index 37fbccdf41d..79b53bda894 100644
--- a/kernel/rcutree_plugin.h
+++ b/kernel/rcutree_plugin.h
@@ -62,6 +62,15 @@ long rcu_batches_completed(void)
 EXPORT_SYMBOL_GPL(rcu_batches_completed);
 
 /*
+ * Force a quiescent state for preemptible RCU.
+ */
+void rcu_force_quiescent_state(void)
+{
+	force_quiescent_state(&rcu_preempt_state, 0);
+}
+EXPORT_SYMBOL_GPL(rcu_force_quiescent_state);
+
+/*
  * Record a preemptable-RCU quiescent state for the specified CPU.  Note
  * that this just means that the task currently running on the CPU is
  * not in a quiescent state.  There might be any number of tasks blocked
@@ -102,7 +111,7 @@ static void rcu_preempt_note_context_switch(int cpu)
 		/* Possibly blocking in an RCU read-side critical section. */
 		rdp = rcu_preempt_state.rda[cpu];
 		rnp = rdp->mynode;
-		spin_lock_irqsave(&rnp->lock, flags);
+		raw_spin_lock_irqsave(&rnp->lock, flags);
 		t->rcu_read_unlock_special |= RCU_READ_UNLOCK_BLOCKED;
 		t->rcu_blocked_node = rnp;
 
@@ -123,7 +132,7 @@ static void rcu_preempt_note_context_switch(int cpu)
 		WARN_ON_ONCE(!list_empty(&t->rcu_node_entry));
 		phase = (rnp->gpnum + !(rnp->qsmask & rdp->grpmask)) & 0x1;
 		list_add(&t->rcu_node_entry, &rnp->blocked_tasks[phase]);
-		spin_unlock_irqrestore(&rnp->lock, flags);
+		raw_spin_unlock_irqrestore(&rnp->lock, flags);
 	}
 
 	/*
@@ -180,7 +189,7 @@ static void rcu_report_unblock_qs_rnp(struct rcu_node *rnp, unsigned long flags)
 	struct rcu_node *rnp_p;
 
 	if (rnp->qsmask != 0 || rcu_preempted_readers(rnp)) {
-		spin_unlock_irqrestore(&rnp->lock, flags);
+		raw_spin_unlock_irqrestore(&rnp->lock, flags);
 		return;  /* Still need more quiescent states! */
 	}
 
@@ -197,8 +206,8 @@ static void rcu_report_unblock_qs_rnp(struct rcu_node *rnp, unsigned long flags)
 
 	/* Report up the rest of the hierarchy. */
 	mask = rnp->grpmask;
-	spin_unlock(&rnp->lock);	/* irqs remain disabled. */
-	spin_lock(&rnp_p->lock);	/* irqs already disabled. */
+	raw_spin_unlock(&rnp->lock);	/* irqs remain disabled. */
+	raw_spin_lock(&rnp_p->lock);	/* irqs already disabled. */
 	rcu_report_qs_rnp(mask, &rcu_preempt_state, rnp_p, flags);
 }
 
@@ -248,10 +257,10 @@ static void rcu_read_unlock_special(struct task_struct *t)
 		 */
 		for (;;) {
 			rnp = t->rcu_blocked_node;
-			spin_lock(&rnp->lock);  /* irqs already disabled. */
+			raw_spin_lock(&rnp->lock);  /* irqs already disabled. */
 			if (rnp == t->rcu_blocked_node)
 				break;
-			spin_unlock(&rnp->lock);  /* irqs remain disabled. */
+			raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */
 		}
 		empty = !rcu_preempted_readers(rnp);
 		empty_exp = !rcu_preempted_readers_exp(rnp);
@@ -265,7 +274,7 @@ static void rcu_read_unlock_special(struct task_struct *t)
 		 * Note that rcu_report_unblock_qs_rnp() releases rnp->lock.
 		 */
 		if (empty)
-			spin_unlock_irqrestore(&rnp->lock, flags);
+			raw_spin_unlock_irqrestore(&rnp->lock, flags);
 		else
 			rcu_report_unblock_qs_rnp(rnp, flags);
 
@@ -295,29 +304,73 @@ void __rcu_read_unlock(void)
 	if (--ACCESS_ONCE(t->rcu_read_lock_nesting) == 0 &&
 	    unlikely(ACCESS_ONCE(t->rcu_read_unlock_special)))
 		rcu_read_unlock_special(t);
+#ifdef CONFIG_PROVE_LOCKING
+	WARN_ON_ONCE(ACCESS_ONCE(t->rcu_read_lock_nesting) < 0);
+#endif /* #ifdef CONFIG_PROVE_LOCKING */
 }
 EXPORT_SYMBOL_GPL(__rcu_read_unlock);
 
 #ifdef CONFIG_RCU_CPU_STALL_DETECTOR
 
+#ifdef CONFIG_RCU_CPU_STALL_VERBOSE
+
+/*
+ * Dump detailed information for all tasks blocking the current RCU
+ * grace period on the specified rcu_node structure.
+ */
+static void rcu_print_detail_task_stall_rnp(struct rcu_node *rnp)
+{
+	unsigned long flags;
+	struct list_head *lp;
+	int phase;
+	struct task_struct *t;
+
+	if (rcu_preempted_readers(rnp)) {
+		raw_spin_lock_irqsave(&rnp->lock, flags);
+		phase = rnp->gpnum & 0x1;
+		lp = &rnp->blocked_tasks[phase];
+		list_for_each_entry(t, lp, rcu_node_entry)
+			sched_show_task(t);
+		raw_spin_unlock_irqrestore(&rnp->lock, flags);
+	}
+}
+
+/*
+ * Dump detailed information for all tasks blocking the current RCU
+ * grace period.
+ */
+static void rcu_print_detail_task_stall(struct rcu_state *rsp)
+{
+	struct rcu_node *rnp = rcu_get_root(rsp);
+
+	rcu_print_detail_task_stall_rnp(rnp);
+	rcu_for_each_leaf_node(rsp, rnp)
+		rcu_print_detail_task_stall_rnp(rnp);
+}
+
+#else /* #ifdef CONFIG_RCU_CPU_STALL_VERBOSE */
+
+static void rcu_print_detail_task_stall(struct rcu_state *rsp)
+{
+}
+
+#endif /* #else #ifdef CONFIG_RCU_CPU_STALL_VERBOSE */
+
 /*
  * Scan the current list of tasks blocked within RCU read-side critical
  * sections, printing out the tid of each.
  */
 static void rcu_print_task_stall(struct rcu_node *rnp)
 {
-	unsigned long flags;
 	struct list_head *lp;
 	int phase;
 	struct task_struct *t;
 
 	if (rcu_preempted_readers(rnp)) {
-		spin_lock_irqsave(&rnp->lock, flags);
 		phase = rnp->gpnum & 0x1;
 		lp = &rnp->blocked_tasks[phase];
 		list_for_each_entry(t, lp, rcu_node_entry)
 			printk(" P%d", t->pid);
-		spin_unlock_irqrestore(&rnp->lock, flags);
 	}
 }
 
@@ -388,11 +441,11 @@ static int rcu_preempt_offline_tasks(struct rcu_state *rsp,
 		lp_root = &rnp_root->blocked_tasks[i];
 		while (!list_empty(lp)) {
 			tp = list_entry(lp->next, typeof(*tp), rcu_node_entry);
-			spin_lock(&rnp_root->lock); /* irqs already disabled */
+			raw_spin_lock(&rnp_root->lock); /* irqs already disabled */
 			list_del(&tp->rcu_node_entry);
 			tp->rcu_blocked_node = rnp_root;
 			list_add(&tp->rcu_node_entry, lp_root);
-			spin_unlock(&rnp_root->lock); /* irqs remain disabled */
+			raw_spin_unlock(&rnp_root->lock); /* irqs remain disabled */
 		}
 	}
 	return retval;
@@ -516,7 +569,7 @@ static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp)
 	unsigned long flags;
 	unsigned long mask;
 
-	spin_lock_irqsave(&rnp->lock, flags);
+	raw_spin_lock_irqsave(&rnp->lock, flags);
 	for (;;) {
 		if (!sync_rcu_preempt_exp_done(rnp))
 			break;
@@ -525,12 +578,12 @@ static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp)
 			break;
 		}
 		mask = rnp->grpmask;
-		spin_unlock(&rnp->lock); /* irqs remain disabled */
+		raw_spin_unlock(&rnp->lock); /* irqs remain disabled */
 		rnp = rnp->parent;
-		spin_lock(&rnp->lock); /* irqs already disabled */
+		raw_spin_lock(&rnp->lock); /* irqs already disabled */
 		rnp->expmask &= ~mask;
 	}
-	spin_unlock_irqrestore(&rnp->lock, flags);
+	raw_spin_unlock_irqrestore(&rnp->lock, flags);
 }
 
 /*
@@ -545,11 +598,11 @@ sync_rcu_preempt_exp_init(struct rcu_state *rsp, struct rcu_node *rnp)
 {
 	int must_wait;
 
-	spin_lock(&rnp->lock); /* irqs already disabled */
+	raw_spin_lock(&rnp->lock); /* irqs already disabled */
 	list_splice_init(&rnp->blocked_tasks[0], &rnp->blocked_tasks[2]);
 	list_splice_init(&rnp->blocked_tasks[1], &rnp->blocked_tasks[3]);
 	must_wait = rcu_preempted_readers_exp(rnp);
-	spin_unlock(&rnp->lock); /* irqs remain disabled */
+	raw_spin_unlock(&rnp->lock); /* irqs remain disabled */
 	if (!must_wait)
 		rcu_report_exp_rnp(rsp, rnp);
 }
@@ -594,13 +647,13 @@ void synchronize_rcu_expedited(void)
 	/* force all RCU readers onto blocked_tasks[]. */
 	synchronize_sched_expedited();
 
-	spin_lock_irqsave(&rsp->onofflock, flags);
+	raw_spin_lock_irqsave(&rsp->onofflock, flags);
 
 	/* Initialize ->expmask for all non-leaf rcu_node structures. */
 	rcu_for_each_nonleaf_node_breadth_first(rsp, rnp) {
-		spin_lock(&rnp->lock); /* irqs already disabled. */
+		raw_spin_lock(&rnp->lock); /* irqs already disabled. */
 		rnp->expmask = rnp->qsmaskinit;
-		spin_unlock(&rnp->lock); /* irqs remain disabled. */
+		raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */
 	}
 
 	/* Snapshot current state of ->blocked_tasks[] lists. */
@@ -609,7 +662,7 @@ void synchronize_rcu_expedited(void)
 	if (NUM_RCU_NODES > 1)
 		sync_rcu_preempt_exp_init(rsp, rcu_get_root(rsp));
 
-	spin_unlock_irqrestore(&rsp->onofflock, flags);
+	raw_spin_unlock_irqrestore(&rsp->onofflock, flags);
 
 	/* Wait for snapshotted ->blocked_tasks[] lists to drain. */
 	rnp = rcu_get_root(rsp);
@@ -713,6 +766,16 @@ long rcu_batches_completed(void)
 EXPORT_SYMBOL_GPL(rcu_batches_completed);
 
 /*
+ * Force a quiescent state for RCU, which, because there is no preemptible
+ * RCU, becomes the same as rcu-sched.
+ */
+void rcu_force_quiescent_state(void)
+{
+	rcu_sched_force_quiescent_state();
+}
+EXPORT_SYMBOL_GPL(rcu_force_quiescent_state);
+
+/*
  * Because preemptable RCU does not exist, we never have to check for
  * CPUs being in quiescent states.
  */
@@ -734,7 +797,7 @@ static int rcu_preempted_readers(struct rcu_node *rnp)
 /* Because preemptible RCU does not exist, no quieting of tasks. */
 static void rcu_report_unblock_qs_rnp(struct rcu_node *rnp, unsigned long flags)
 {
-	spin_unlock_irqrestore(&rnp->lock, flags);
+	raw_spin_unlock_irqrestore(&rnp->lock, flags);
 }
 
 #endif /* #ifdef CONFIG_HOTPLUG_CPU */
@@ -745,6 +808,14 @@ static void rcu_report_unblock_qs_rnp(struct rcu_node *rnp, unsigned long flags)
  * Because preemptable RCU does not exist, we never have to check for
  * tasks blocked within RCU read-side critical sections.
  */
+static void rcu_print_detail_task_stall(struct rcu_state *rsp)
+{
+}
+
+/*
+ * Because preemptable RCU does not exist, we never have to check for
+ * tasks blocked within RCU read-side critical sections.
+ */
 static void rcu_print_task_stall(struct rcu_node *rnp)
 {
 }
@@ -884,3 +955,115 @@ static void __init __rcu_init_preempt(void)
 }
 
 #endif /* #else #ifdef CONFIG_TREE_PREEMPT_RCU */
+
+#if !defined(CONFIG_RCU_FAST_NO_HZ)
+
+/*
+ * Check to see if any future RCU-related work will need to be done
+ * by the current CPU, even if none need be done immediately, returning
+ * 1 if so.  This function is part of the RCU implementation; it is -not-
+ * an exported member of the RCU API.
+ *
+ * Because we have preemptible RCU, just check whether this CPU needs
+ * any flavor of RCU.  Do not chew up lots of CPU cycles with preemption
+ * disabled in a most-likely vain attempt to cause RCU not to need this CPU.
+ */
+int rcu_needs_cpu(int cpu)
+{
+	return rcu_needs_cpu_quick_check(cpu);
+}
+
+/*
+ * Check to see if we need to continue a callback-flush operations to
+ * allow the last CPU to enter dyntick-idle mode.  But fast dyntick-idle
+ * entry is not configured, so we never do need to.
+ */
+static void rcu_needs_cpu_flush(void)
+{
+}
+
+#else /* #if !defined(CONFIG_RCU_FAST_NO_HZ) */
+
+#define RCU_NEEDS_CPU_FLUSHES 5
+static DEFINE_PER_CPU(int, rcu_dyntick_drain);
+static DEFINE_PER_CPU(unsigned long, rcu_dyntick_holdoff);
+
+/*
+ * Check to see if any future RCU-related work will need to be done
+ * by the current CPU, even if none need be done immediately, returning
+ * 1 if so.  This function is part of the RCU implementation; it is -not-
+ * an exported member of the RCU API.
+ *
+ * Because we are not supporting preemptible RCU, attempt to accelerate
+ * any current grace periods so that RCU no longer needs this CPU, but
+ * only if all other CPUs are already in dynticks-idle mode.  This will
+ * allow the CPU cores to be powered down immediately, as opposed to after
+ * waiting many milliseconds for grace periods to elapse.
+ *
+ * Because it is not legal to invoke rcu_process_callbacks() with irqs
+ * disabled, we do one pass of force_quiescent_state(), then do a
+ * raise_softirq() to cause rcu_process_callbacks() to be invoked later.
+ * The per-cpu rcu_dyntick_drain variable controls the sequencing.
+ */
+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) {
+			per_cpu(rcu_dyntick_drain, cpu) = 0;
+			per_cpu(rcu_dyntick_holdoff, cpu) = jiffies - 1;
+			return rcu_needs_cpu_quick_check(cpu);
+		}
+
+	/* Check and update the rcu_dyntick_drain sequencing. */
+	if (per_cpu(rcu_dyntick_drain, cpu) <= 0) {
+		/* First time through, initialize the counter. */
+		per_cpu(rcu_dyntick_drain, cpu) = RCU_NEEDS_CPU_FLUSHES;
+	} else if (--per_cpu(rcu_dyntick_drain, cpu) <= 0) {
+		/* We have hit the limit, so time to give up. */
+		per_cpu(rcu_dyntick_holdoff, cpu) = jiffies;
+		return rcu_needs_cpu_quick_check(cpu);
+	}
+
+	/* Do one step pushing remaining RCU callbacks through. */
+	if (per_cpu(rcu_sched_data, cpu).nxtlist) {
+		rcu_sched_qs(cpu);
+		force_quiescent_state(&rcu_sched_state, 0);
+		c = c || per_cpu(rcu_sched_data, cpu).nxtlist;
+	}
+	if (per_cpu(rcu_bh_data, cpu).nxtlist) {
+		rcu_bh_qs(cpu);
+		force_quiescent_state(&rcu_bh_state, 0);
+		c = c || per_cpu(rcu_bh_data, cpu).nxtlist;
+	}
+
+	/* If RCU callbacks are still pending, RCU still needs this CPU. */
+	if (c)
+		raise_softirq(RCU_SOFTIRQ);
+	return c;
+}
+
+/*
+ * Check to see if we need to continue a callback-flush operations to
+ * allow the last CPU to enter dyntick-idle mode.
+ */
+static void rcu_needs_cpu_flush(void)
+{
+	int cpu = smp_processor_id();
+	unsigned long flags;
+
+	if (per_cpu(rcu_dyntick_drain, cpu) <= 0)
+		return;
+	local_irq_save(flags);
+	(void)rcu_needs_cpu(cpu);
+	local_irq_restore(flags);
+}
+
+#endif /* #else #if !defined(CONFIG_RCU_FAST_NO_HZ) */
diff --git a/kernel/rcutree_trace.c b/kernel/rcutree_trace.c
index 9d2c88423b3..d45db2e35d2 100644
--- a/kernel/rcutree_trace.c
+++ b/kernel/rcutree_trace.c
@@ -50,7 +50,7 @@ static void print_one_rcu_data(struct seq_file *m, struct rcu_data *rdp)
 {
 	if (!rdp->beenonline)
 		return;
-	seq_printf(m, "%3d%cc=%ld g=%ld pq=%d pqc=%ld qp=%d",
+	seq_printf(m, "%3d%cc=%lu g=%lu pq=%d pqc=%lu qp=%d",
 		   rdp->cpu,
 		   cpu_is_offline(rdp->cpu) ? '!' : ' ',
 		   rdp->completed, rdp->gpnum,
@@ -105,7 +105,7 @@ static void print_one_rcu_data_csv(struct seq_file *m, struct rcu_data *rdp)
 {
 	if (!rdp->beenonline)
 		return;
-	seq_printf(m, "%d,%s,%ld,%ld,%d,%ld,%d",
+	seq_printf(m, "%d,%s,%lu,%lu,%d,%lu,%d",
 		   rdp->cpu,
 		   cpu_is_offline(rdp->cpu) ? "\"N\"" : "\"Y\"",
 		   rdp->completed, rdp->gpnum,
@@ -155,13 +155,13 @@ static const struct file_operations rcudata_csv_fops = {
 
 static void print_one_rcu_state(struct seq_file *m, struct rcu_state *rsp)
 {
-	long gpnum;
+	unsigned long gpnum;
 	int level = 0;
 	int phase;
 	struct rcu_node *rnp;
 
 	gpnum = rsp->gpnum;
-	seq_printf(m, "c=%ld g=%ld s=%d jfq=%ld j=%x "
+	seq_printf(m, "c=%lu g=%lu s=%d jfq=%ld j=%x "
 		      "nfqs=%lu/nfqsng=%lu(%lu) fqlh=%lu oqlen=%ld\n",
 		   rsp->completed, gpnum, rsp->signaled,
 		   (long)(rsp->jiffies_force_qs - jiffies),
@@ -215,12 +215,12 @@ static const struct file_operations rcuhier_fops = {
 static int show_rcugp(struct seq_file *m, void *unused)
 {
 #ifdef CONFIG_TREE_PREEMPT_RCU
-	seq_printf(m, "rcu_preempt: completed=%ld  gpnum=%ld\n",
+	seq_printf(m, "rcu_preempt: completed=%ld  gpnum=%lu\n",
 		   rcu_preempt_state.completed, rcu_preempt_state.gpnum);
 #endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */
-	seq_printf(m, "rcu_sched: completed=%ld  gpnum=%ld\n",
+	seq_printf(m, "rcu_sched: completed=%ld  gpnum=%lu\n",
 		   rcu_sched_state.completed, rcu_sched_state.gpnum);
-	seq_printf(m, "rcu_bh: completed=%ld  gpnum=%ld\n",
+	seq_printf(m, "rcu_bh: completed=%ld  gpnum=%lu\n",
 		   rcu_bh_state.completed, rcu_bh_state.gpnum);
 	return 0;
 }
diff --git a/kernel/relay.c b/kernel/relay.c
index c705a41b4ba..3d97f282161 100644
--- a/kernel/relay.c
+++ b/kernel/relay.c
@@ -1215,14 +1215,14 @@ static void relay_page_release(struct splice_pipe_desc *spd, unsigned int i)
 /*
  *	subbuf_splice_actor - splice up to one subbuf's worth of data
  */
-static int subbuf_splice_actor(struct file *in,
+static ssize_t subbuf_splice_actor(struct file *in,
 			       loff_t *ppos,
 			       struct pipe_inode_info *pipe,
 			       size_t len,
 			       unsigned int flags,
 			       int *nonpad_ret)
 {
-	unsigned int pidx, poff, total_len, subbuf_pages, nr_pages, ret;
+	unsigned int pidx, poff, total_len, subbuf_pages, nr_pages;
 	struct rchan_buf *rbuf = in->private_data;
 	unsigned int subbuf_size = rbuf->chan->subbuf_size;
 	uint64_t pos = (uint64_t) *ppos;
@@ -1241,6 +1241,7 @@ static int subbuf_splice_actor(struct file *in,
 		.ops = &relay_pipe_buf_ops,
 		.spd_release = relay_page_release,
 	};
+	ssize_t ret;
 
 	if (rbuf->subbufs_produced == rbuf->subbufs_consumed)
 		return 0;
diff --git a/kernel/res_counter.c b/kernel/res_counter.c
index bcdabf37c40..c7eaa37a768 100644
--- a/kernel/res_counter.c
+++ b/kernel/res_counter.c
@@ -10,7 +10,6 @@
 #include <linux/types.h>
 #include <linux/parser.h>
 #include <linux/fs.h>
-#include <linux/slab.h>
 #include <linux/res_counter.h>
 #include <linux/uaccess.h>
 #include <linux/mm.h>
diff --git a/kernel/resource.c b/kernel/resource.c
index af96c1e4b54..9c358e26353 100644
--- a/kernel/resource.c
+++ b/kernel/resource.c
@@ -188,20 +188,65 @@ static int __release_resource(struct resource *old)
 	return -EINVAL;
 }
 
+static void __release_child_resources(struct resource *r)
+{
+	struct resource *tmp, *p;
+	resource_size_t size;
+
+	p = r->child;
+	r->child = NULL;
+	while (p) {
+		tmp = p;
+		p = p->sibling;
+
+		tmp->parent = NULL;
+		tmp->sibling = NULL;
+		__release_child_resources(tmp);
+
+		printk(KERN_DEBUG "release child resource %pR\n", tmp);
+		/* need to restore size, and keep flags */
+		size = resource_size(tmp);
+		tmp->start = 0;
+		tmp->end = size - 1;
+	}
+}
+
+void release_child_resources(struct resource *r)
+{
+	write_lock(&resource_lock);
+	__release_child_resources(r);
+	write_unlock(&resource_lock);
+}
+
 /**
- * request_resource - request and reserve an I/O or memory resource
+ * request_resource_conflict - request and reserve an I/O or memory resource
  * @root: root resource descriptor
  * @new: resource descriptor desired by caller
  *
- * Returns 0 for success, negative error code on error.
+ * Returns 0 for success, conflict resource on error.
  */
-int request_resource(struct resource *root, struct resource *new)
+struct resource *request_resource_conflict(struct resource *root, struct resource *new)
 {
 	struct resource *conflict;
 
 	write_lock(&resource_lock);
 	conflict = __request_resource(root, new);
 	write_unlock(&resource_lock);
+	return conflict;
+}
+
+/**
+ * request_resource - request and reserve an I/O or memory resource
+ * @root: root resource descriptor
+ * @new: resource descriptor desired by caller
+ *
+ * Returns 0 for success, negative error code on error.
+ */
+int request_resource(struct resource *root, struct resource *new)
+{
+	struct resource *conflict;
+
+	conflict = request_resource_conflict(root, new);
 	return conflict ? -EBUSY : 0;
 }
 
@@ -274,7 +319,7 @@ int walk_system_ram_range(unsigned long start_pfn, unsigned long nr_pages,
 		void *arg, int (*func)(unsigned long, unsigned long, void *))
 {
 	struct resource res;
-	unsigned long pfn, len;
+	unsigned long pfn, end_pfn;
 	u64 orig_end;
 	int ret = -1;
 
@@ -284,9 +329,10 @@ int walk_system_ram_range(unsigned long start_pfn, unsigned long nr_pages,
 	orig_end = res.end;
 	while ((res.start < res.end) &&
 		(find_next_system_ram(&res, "System RAM") >= 0)) {
-		pfn = (unsigned long)(res.start >> PAGE_SHIFT);
-		len = (unsigned long)((res.end + 1 - res.start) >> PAGE_SHIFT);
-		ret = (*func)(pfn, len, arg);
+		pfn = (res.start + PAGE_SIZE - 1) >> PAGE_SHIFT;
+		end_pfn = (res.end + 1) >> PAGE_SHIFT;
+		if (end_pfn > pfn)
+			ret = (*func)(pfn, end_pfn - pfn, arg);
 		if (ret)
 			break;
 		res.start = res.end + 1;
@@ -297,14 +343,29 @@ int walk_system_ram_range(unsigned long start_pfn, unsigned long nr_pages,
 
 #endif
 
+static int __is_ram(unsigned long pfn, unsigned long nr_pages, void *arg)
+{
+	return 1;
+}
+/*
+ * This generic page_is_ram() returns true if specified address is
+ * registered as "System RAM" in iomem_resource list.
+ */
+int __weak page_is_ram(unsigned long pfn)
+{
+	return walk_system_ram_range(pfn, 1, NULL, __is_ram) == 1;
+}
+
 /*
  * Find empty slot in the resource tree given range and alignment.
  */
 static int find_resource(struct resource *root, struct resource *new,
 			 resource_size_t size, resource_size_t min,
 			 resource_size_t max, resource_size_t align,
-			 void (*alignf)(void *, struct resource *,
-					resource_size_t, resource_size_t),
+			 resource_size_t (*alignf)(void *,
+						   const struct resource *,
+						   resource_size_t,
+						   resource_size_t),
 			 void *alignf_data)
 {
 	struct resource *this = root->child;
@@ -330,7 +391,7 @@ static int find_resource(struct resource *root, struct resource *new,
 			tmp.end = max;
 		tmp.start = ALIGN(tmp.start, align);
 		if (alignf)
-			alignf(alignf_data, &tmp, size, align);
+			tmp.start = alignf(alignf_data, &tmp, size, align);
 		if (tmp.start < tmp.end && tmp.end - tmp.start >= size - 1) {
 			new->start = tmp.start;
 			new->end = tmp.start + size - 1;
@@ -358,8 +419,10 @@ static int find_resource(struct resource *root, struct resource *new,
 int allocate_resource(struct resource *root, struct resource *new,
 		      resource_size_t size, resource_size_t min,
 		      resource_size_t max, resource_size_t align,
-		      void (*alignf)(void *, struct resource *,
-				     resource_size_t, resource_size_t),
+		      resource_size_t (*alignf)(void *,
+						const struct resource *,
+						resource_size_t,
+						resource_size_t),
 		      void *alignf_data)
 {
 	int err;
@@ -426,25 +489,40 @@ static struct resource * __insert_resource(struct resource *parent, struct resou
 }
 
 /**
- * insert_resource - Inserts a resource in the resource tree
+ * insert_resource_conflict - Inserts resource in the resource tree
  * @parent: parent of the new resource
  * @new: new resource to insert
  *
- * Returns 0 on success, -EBUSY if the resource can't be inserted.
+ * Returns 0 on success, conflict resource if the resource can't be inserted.
  *
- * This function is equivalent to request_resource when no conflict
+ * This function is equivalent to request_resource_conflict when no conflict
  * happens. If a conflict happens, and the conflicting resources
  * entirely fit within the range of the new resource, then the new
  * resource is inserted and the conflicting resources become children of
  * the new resource.
  */
-int insert_resource(struct resource *parent, struct resource *new)
+struct resource *insert_resource_conflict(struct resource *parent, struct resource *new)
 {
 	struct resource *conflict;
 
 	write_lock(&resource_lock);
 	conflict = __insert_resource(parent, new);
 	write_unlock(&resource_lock);
+	return conflict;
+}
+
+/**
+ * insert_resource - Inserts a resource in the resource tree
+ * @parent: parent of the new resource
+ * @new: new resource to insert
+ *
+ * Returns 0 on success, -EBUSY if the resource can't be inserted.
+ */
+int insert_resource(struct resource *parent, struct resource *new)
+{
+	struct resource *conflict;
+
+	conflict = insert_resource_conflict(parent, new);
 	return conflict ? -EBUSY : 0;
 }
 
diff --git a/kernel/sched.c b/kernel/sched.c
index 7266b912139..3c2a54f70ff 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -71,6 +71,7 @@
 #include <linux/debugfs.h>
 #include <linux/ctype.h>
 #include <linux/ftrace.h>
+#include <linux/slab.h>
 
 #include <asm/tlb.h>
 #include <asm/irq_regs.h>
@@ -233,7 +234,7 @@ static void destroy_rt_bandwidth(struct rt_bandwidth *rt_b)
  */
 static DEFINE_MUTEX(sched_domains_mutex);
 
-#ifdef CONFIG_GROUP_SCHED
+#ifdef CONFIG_CGROUP_SCHED
 
 #include <linux/cgroup.h>
 
@@ -243,13 +244,7 @@ static LIST_HEAD(task_groups);
 
 /* task group related information */
 struct task_group {
-#ifdef CONFIG_CGROUP_SCHED
 	struct cgroup_subsys_state css;
-#endif
-
-#ifdef CONFIG_USER_SCHED
-	uid_t uid;
-#endif
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
 	/* schedulable entities of this group on each cpu */
@@ -274,35 +269,7 @@ struct task_group {
 	struct list_head children;
 };
 
-#ifdef CONFIG_USER_SCHED
-
-/* Helper function to pass uid information to create_sched_user() */
-void set_tg_uid(struct user_struct *user)
-{
-	user->tg->uid = user->uid;
-}
-
-/*
- * Root task group.
- *	Every UID task group (including init_task_group aka UID-0) will
- *	be a child to this group.
- */
-struct task_group root_task_group;
-
-#ifdef CONFIG_FAIR_GROUP_SCHED
-/* Default task group's sched entity on each cpu */
-static DEFINE_PER_CPU(struct sched_entity, init_sched_entity);
-/* Default task group's cfs_rq on each cpu */
-static DEFINE_PER_CPU_SHARED_ALIGNED(struct cfs_rq, init_tg_cfs_rq);
-#endif /* CONFIG_FAIR_GROUP_SCHED */
-
-#ifdef CONFIG_RT_GROUP_SCHED
-static DEFINE_PER_CPU(struct sched_rt_entity, init_sched_rt_entity);
-static DEFINE_PER_CPU_SHARED_ALIGNED(struct rt_rq, init_rt_rq_var);
-#endif /* CONFIG_RT_GROUP_SCHED */
-#else /* !CONFIG_USER_SCHED */
 #define root_task_group init_task_group
-#endif /* CONFIG_USER_SCHED */
 
 /* task_group_lock serializes add/remove of task groups and also changes to
  * a task group's cpu shares.
@@ -318,11 +285,7 @@ static int root_task_group_empty(void)
 }
 #endif
 
-#ifdef CONFIG_USER_SCHED
-# define INIT_TASK_GROUP_LOAD	(2*NICE_0_LOAD)
-#else /* !CONFIG_USER_SCHED */
 # define INIT_TASK_GROUP_LOAD	NICE_0_LOAD
-#endif /* CONFIG_USER_SCHED */
 
 /*
  * A weight of 0 or 1 can cause arithmetics problems.
@@ -348,11 +311,7 @@ static inline struct task_group *task_group(struct task_struct *p)
 {
 	struct task_group *tg;
 
-#ifdef CONFIG_USER_SCHED
-	rcu_read_lock();
-	tg = __task_cred(p)->user->tg;
-	rcu_read_unlock();
-#elif defined(CONFIG_CGROUP_SCHED)
+#ifdef CONFIG_CGROUP_SCHED
 	tg = container_of(task_subsys_state(p, cpu_cgroup_subsys_id),
 				struct task_group, css);
 #else
@@ -364,6 +323,15 @@ static inline struct task_group *task_group(struct task_struct *p)
 /* Change a task's cfs_rq and parent entity if it moves across CPUs/groups */
 static inline void set_task_rq(struct task_struct *p, unsigned int cpu)
 {
+	/*
+	 * Strictly speaking this rcu_read_lock() is not needed since the
+	 * task_group is tied to the cgroup, which in turn can never go away
+	 * as long as there are tasks attached to it.
+	 *
+	 * However since task_group() uses task_subsys_state() which is an
+	 * rcu_dereference() user, this quiets CONFIG_PROVE_RCU.
+	 */
+	rcu_read_lock();
 #ifdef CONFIG_FAIR_GROUP_SCHED
 	p->se.cfs_rq = task_group(p)->cfs_rq[cpu];
 	p->se.parent = task_group(p)->se[cpu];
@@ -373,6 +341,7 @@ static inline void set_task_rq(struct task_struct *p, unsigned int cpu)
 	p->rt.rt_rq  = task_group(p)->rt_rq[cpu];
 	p->rt.parent = task_group(p)->rt_se[cpu];
 #endif
+	rcu_read_unlock();
 }
 
 #else
@@ -383,7 +352,7 @@ static inline struct task_group *task_group(struct task_struct *p)
 	return NULL;
 }
 
-#endif	/* CONFIG_GROUP_SCHED */
+#endif	/* CONFIG_CGROUP_SCHED */
 
 /* CFS-related fields in a runqueue */
 struct cfs_rq {
@@ -478,7 +447,6 @@ struct rt_rq {
 	struct rq *rq;
 	struct list_head leaf_rt_rq_list;
 	struct task_group *tg;
-	struct sched_rt_entity *rt_se;
 #endif
 };
 
@@ -645,6 +613,11 @@ static inline int cpu_of(struct rq *rq)
 #endif
 }
 
+#define rcu_dereference_check_sched_domain(p) \
+	rcu_dereference_check((p), \
+			      rcu_read_lock_sched_held() || \
+			      lockdep_is_held(&sched_domains_mutex))
+
 /*
  * The domain tree (rq->sd) is protected by RCU's quiescent state transition.
  * See detach_destroy_domains: synchronize_sched for details.
@@ -653,7 +626,7 @@ static inline int cpu_of(struct rq *rq)
  * preempt-disabled sections.
  */
 #define for_each_domain(cpu, __sd) \
-	for (__sd = rcu_dereference(cpu_rq(cpu)->sd); __sd; __sd = __sd->parent)
+	for (__sd = rcu_dereference_check_sched_domain(cpu_rq(cpu)->sd); __sd; __sd = __sd->parent)
 
 #define cpu_rq(cpu)		(&per_cpu(runqueues, (cpu)))
 #define this_rq()		(&__get_cpu_var(runqueues))
@@ -941,16 +914,33 @@ static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev)
 #endif /* __ARCH_WANT_UNLOCKED_CTXSW */
 
 /*
+ * Check whether the task is waking, we use this to synchronize against
+ * ttwu() so that task_cpu() reports a stable number.
+ *
+ * We need to make an exception for PF_STARTING tasks because the fork
+ * path might require task_rq_lock() to work, eg. it can call
+ * set_cpus_allowed_ptr() from the cpuset clone_ns code.
+ */
+static inline int task_is_waking(struct task_struct *p)
+{
+	return unlikely((p->state == TASK_WAKING) && !(p->flags & PF_STARTING));
+}
+
+/*
  * __task_rq_lock - lock the runqueue a given task resides on.
  * Must be called interrupts disabled.
  */
 static inline struct rq *__task_rq_lock(struct task_struct *p)
 	__acquires(rq->lock)
 {
+	struct rq *rq;
+
 	for (;;) {
-		struct rq *rq = task_rq(p);
+		while (task_is_waking(p))
+			cpu_relax();
+		rq = task_rq(p);
 		raw_spin_lock(&rq->lock);
-		if (likely(rq == task_rq(p)))
+		if (likely(rq == task_rq(p) && !task_is_waking(p)))
 			return rq;
 		raw_spin_unlock(&rq->lock);
 	}
@@ -967,10 +957,12 @@ static struct rq *task_rq_lock(struct task_struct *p, unsigned long *flags)
 	struct rq *rq;
 
 	for (;;) {
+		while (task_is_waking(p))
+			cpu_relax();
 		local_irq_save(*flags);
 		rq = task_rq(p);
 		raw_spin_lock(&rq->lock);
-		if (likely(rq == task_rq(p)))
+		if (likely(rq == task_rq(p) && !task_is_waking(p)))
 			return rq;
 		raw_spin_unlock_irqrestore(&rq->lock, *flags);
 	}
@@ -1390,32 +1382,6 @@ static const u32 prio_to_wmult[40] = {
  /*  15 */ 119304647, 148102320, 186737708, 238609294, 286331153,
 };
 
-static void activate_task(struct rq *rq, struct task_struct *p, int wakeup);
-
-/*
- * runqueue iterator, to support SMP load-balancing between different
- * scheduling classes, without having to expose their internal data
- * structures to the load-balancing proper:
- */
-struct rq_iterator {
-	void *arg;
-	struct task_struct *(*start)(void *);
-	struct task_struct *(*next)(void *);
-};
-
-#ifdef CONFIG_SMP
-static unsigned long
-balance_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest,
-	      unsigned long max_load_move, struct sched_domain *sd,
-	      enum cpu_idle_type idle, int *all_pinned,
-	      int *this_best_prio, struct rq_iterator *iterator);
-
-static int
-iter_move_one_task(struct rq *this_rq, int this_cpu, struct rq *busiest,
-		   struct sched_domain *sd, enum cpu_idle_type idle,
-		   struct rq_iterator *iterator);
-#endif
-
 /* Time spent by the tasks of the cpu accounting group executing in ... */
 enum cpuacct_stat_index {
 	CPUACCT_STAT_USER,	/* ... user mode */
@@ -1531,7 +1497,7 @@ static unsigned long target_load(int cpu, int type)
 
 static struct sched_group *group_of(int cpu)
 {
-	struct sched_domain *sd = rcu_dereference(cpu_rq(cpu)->sd);
+	struct sched_domain *sd = rcu_dereference_sched(cpu_rq(cpu)->sd);
 
 	if (!sd)
 		return NULL;
@@ -1566,7 +1532,7 @@ static unsigned long cpu_avg_load_per_task(int cpu)
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
 
-static __read_mostly unsigned long *update_shares_data;
+static __read_mostly unsigned long __percpu *update_shares_data;
 
 static void __set_se_shares(struct sched_entity *se, unsigned long shares);
 
@@ -1701,16 +1667,6 @@ static void update_shares(struct sched_domain *sd)
 	}
 }
 
-static void update_shares_locked(struct rq *rq, struct sched_domain *sd)
-{
-	if (root_task_group_empty())
-		return;
-
-	raw_spin_unlock(&rq->lock);
-	update_shares(sd);
-	raw_spin_lock(&rq->lock);
-}
-
 static void update_h_load(long cpu)
 {
 	if (root_task_group_empty())
@@ -1725,10 +1681,6 @@ static inline void update_shares(struct sched_domain *sd)
 {
 }
 
-static inline void update_shares_locked(struct rq *rq, struct sched_domain *sd)
-{
-}
-
 #endif
 
 #ifdef CONFIG_PREEMPT
@@ -1805,6 +1757,51 @@ static inline void double_unlock_balance(struct rq *this_rq, struct rq *busiest)
 	raw_spin_unlock(&busiest->lock);
 	lock_set_subclass(&this_rq->lock.dep_map, 0, _RET_IP_);
 }
+
+/*
+ * double_rq_lock - safely lock two runqueues
+ *
+ * Note this does not disable interrupts like task_rq_lock,
+ * you need to do so manually before calling.
+ */
+static void double_rq_lock(struct rq *rq1, struct rq *rq2)
+	__acquires(rq1->lock)
+	__acquires(rq2->lock)
+{
+	BUG_ON(!irqs_disabled());
+	if (rq1 == rq2) {
+		raw_spin_lock(&rq1->lock);
+		__acquire(rq2->lock);	/* Fake it out ;) */
+	} else {
+		if (rq1 < rq2) {
+			raw_spin_lock(&rq1->lock);
+			raw_spin_lock_nested(&rq2->lock, SINGLE_DEPTH_NESTING);
+		} else {
+			raw_spin_lock(&rq2->lock);
+			raw_spin_lock_nested(&rq1->lock, SINGLE_DEPTH_NESTING);
+		}
+	}
+	update_rq_clock(rq1);
+	update_rq_clock(rq2);
+}
+
+/*
+ * double_rq_unlock - safely unlock two runqueues
+ *
+ * Note this does not restore interrupts like task_rq_unlock,
+ * you need to do so manually after calling.
+ */
+static void double_rq_unlock(struct rq *rq1, struct rq *rq2)
+	__releases(rq1->lock)
+	__releases(rq2->lock)
+{
+	raw_spin_unlock(&rq1->lock);
+	if (rq1 != rq2)
+		raw_spin_unlock(&rq2->lock);
+	else
+		__release(rq2->lock);
+}
+
 #endif
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
@@ -1834,18 +1831,14 @@ static inline void __set_task_cpu(struct task_struct *p, unsigned int cpu)
 #endif
 }
 
-#include "sched_stats.h"
-#include "sched_idletask.c"
-#include "sched_fair.c"
-#include "sched_rt.c"
-#ifdef CONFIG_SCHED_DEBUG
-# include "sched_debug.c"
-#endif
+static const struct sched_class rt_sched_class;
 
 #define sched_class_highest (&rt_sched_class)
 #define for_each_class(class) \
    for (class = sched_class_highest; class; class = class->next)
 
+#include "sched_stats.h"
+
 static void inc_nr_running(struct rq *rq)
 {
 	rq->nr_running++;
@@ -1883,13 +1876,14 @@ static void update_avg(u64 *avg, u64 sample)
 	*avg += diff >> 3;
 }
 
-static void enqueue_task(struct rq *rq, struct task_struct *p, int wakeup)
+static void
+enqueue_task(struct rq *rq, struct task_struct *p, int wakeup, bool head)
 {
 	if (wakeup)
 		p->se.start_runtime = p->se.sum_exec_runtime;
 
 	sched_info_queued(p);
-	p->sched_class->enqueue_task(rq, p, wakeup);
+	p->sched_class->enqueue_task(rq, p, wakeup, head);
 	p->se.on_rq = 1;
 }
 
@@ -1912,6 +1906,37 @@ static void dequeue_task(struct rq *rq, struct task_struct *p, int sleep)
 }
 
 /*
+ * activate_task - move a task to the runqueue.
+ */
+static void activate_task(struct rq *rq, struct task_struct *p, int wakeup)
+{
+	if (task_contributes_to_load(p))
+		rq->nr_uninterruptible--;
+
+	enqueue_task(rq, p, wakeup, false);
+	inc_nr_running(rq);
+}
+
+/*
+ * deactivate_task - remove a task from the runqueue.
+ */
+static void deactivate_task(struct rq *rq, struct task_struct *p, int sleep)
+{
+	if (task_contributes_to_load(p))
+		rq->nr_uninterruptible++;
+
+	dequeue_task(rq, p, sleep);
+	dec_nr_running(rq);
+}
+
+#include "sched_idletask.c"
+#include "sched_fair.c"
+#include "sched_rt.c"
+#ifdef CONFIG_SCHED_DEBUG
+# include "sched_debug.c"
+#endif
+
+/*
  * __normal_prio - return the priority that is based on the static prio
  */
 static inline int __normal_prio(struct task_struct *p)
@@ -1957,30 +1982,6 @@ static int effective_prio(struct task_struct *p)
 	return p->prio;
 }
 
-/*
- * activate_task - move a task to the runqueue.
- */
-static void activate_task(struct rq *rq, struct task_struct *p, int wakeup)
-{
-	if (task_contributes_to_load(p))
-		rq->nr_uninterruptible--;
-
-	enqueue_task(rq, p, wakeup);
-	inc_nr_running(rq);
-}
-
-/*
- * deactivate_task - remove a task from the runqueue.
- */
-static void deactivate_task(struct rq *rq, struct task_struct *p, int sleep)
-{
-	if (task_contributes_to_load(p))
-		rq->nr_uninterruptible++;
-
-	dequeue_task(rq, p, sleep);
-	dec_nr_running(rq);
-}
-
 /**
  * task_curr - is this task currently executing on a CPU?
  * @p: the task in question.
@@ -2320,14 +2321,12 @@ static int select_fallback_rq(int cpu, struct task_struct *p)
 }
 
 /*
- * Called from:
- *
- *  - fork, @p is stable because it isn't on the tasklist yet
+ * Gets called from 3 sites (exec, fork, wakeup), since it is called without
+ * holding rq->lock we need to ensure ->cpus_allowed is stable, this is done
+ * by:
  *
- *  - exec, @p is unstable, retry loop
- *
- *  - wake-up, we serialize ->cpus_allowed against TASK_WAKING so
- *             we should be good.
+ *  exec:           is unstable, retry loop
+ *  fork & wake-up: serialize ->cpus_allowed against TASK_WAKING
  */
 static inline
 int select_task_rq(struct task_struct *p, int sd_flags, int wake_flags)
@@ -2371,7 +2370,7 @@ 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;
@@ -2379,7 +2378,7 @@ 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;
@@ -2410,14 +2409,27 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state,
 	__task_rq_unlock(rq);
 
 	cpu = select_task_rq(p, SD_BALANCE_WAKE, wake_flags);
-	if (cpu != orig_cpu)
+	if (cpu != orig_cpu) {
+		/*
+		 * Since we migrate the task without holding any rq->lock,
+		 * we need to be careful with task_rq_lock(), since that
+		 * might end up locking an invalid rq.
+		 */
 		set_task_cpu(p, cpu);
+	}
 
-	rq = __task_rq_lock(p);
+	rq = cpu_rq(cpu);
+	raw_spin_lock(&rq->lock);
 	update_rq_clock(rq);
 
+	/*
+	 * We migrated the task without holding either rq->lock, however
+	 * since the task is not on the task list itself, nobody else
+	 * will try and migrate the task, hence the rq should match the
+	 * cpu we just moved it to.
+	 */
+	WARN_ON(task_cpu(p) != cpu);
 	WARN_ON(p->state != TASK_WAKING);
-	cpu = task_cpu(p);
 
 #ifdef CONFIG_SCHEDSTATS
 	schedstat_inc(rq, ttwu_count);
@@ -2620,9 +2632,6 @@ void sched_fork(struct task_struct *p, int clone_flags)
 	if (p->sched_class->task_fork)
 		p->sched_class->task_fork(p);
 
-#ifdef CONFIG_SMP
-	cpu = select_task_rq(p, SD_BALANCE_FORK, 0);
-#endif
 	set_task_cpu(p, cpu);
 
 #if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT)
@@ -2652,8 +2661,29 @@ void wake_up_new_task(struct task_struct *p, unsigned long clone_flags)
 {
 	unsigned long flags;
 	struct rq *rq;
+	int cpu __maybe_unused = get_cpu();
+
+#ifdef CONFIG_SMP
+	/*
+	 * Fork balancing, do it here and not earlier because:
+	 *  - cpus_allowed can change in the fork path
+	 *  - any previously selected cpu might disappear through hotplug
+	 *
+	 * We still have TASK_WAKING but PF_STARTING is gone now, meaning
+	 * ->cpus_allowed is stable, we have preemption disabled, meaning
+	 * cpu_online_mask is stable.
+	 */
+	cpu = select_task_rq(p, SD_BALANCE_FORK, 0);
+	set_task_cpu(p, cpu);
+#endif
+
+	/*
+	 * Since the task is not on the rq and we still have TASK_WAKING set
+	 * nobody else will migrate this task.
+	 */
+	rq = cpu_rq(cpu);
+	raw_spin_lock_irqsave(&rq->lock, flags);
 
-	rq = task_rq_lock(p, &flags);
 	BUG_ON(p->state != TASK_WAKING);
 	p->state = TASK_RUNNING;
 	update_rq_clock(rq);
@@ -2665,6 +2695,7 @@ void wake_up_new_task(struct task_struct *p, unsigned long clone_flags)
 		p->sched_class->task_woken(rq, p);
 #endif
 	task_rq_unlock(rq, &flags);
+	put_cpu();
 }
 
 #ifdef CONFIG_PREEMPT_NOTIFIERS
@@ -3094,50 +3125,6 @@ static void update_cpu_load(struct rq *this_rq)
 #ifdef CONFIG_SMP
 
 /*
- * double_rq_lock - safely lock two runqueues
- *
- * Note this does not disable interrupts like task_rq_lock,
- * you need to do so manually before calling.
- */
-static void double_rq_lock(struct rq *rq1, struct rq *rq2)
-	__acquires(rq1->lock)
-	__acquires(rq2->lock)
-{
-	BUG_ON(!irqs_disabled());
-	if (rq1 == rq2) {
-		raw_spin_lock(&rq1->lock);
-		__acquire(rq2->lock);	/* Fake it out ;) */
-	} else {
-		if (rq1 < rq2) {
-			raw_spin_lock(&rq1->lock);
-			raw_spin_lock_nested(&rq2->lock, SINGLE_DEPTH_NESTING);
-		} else {
-			raw_spin_lock(&rq2->lock);
-			raw_spin_lock_nested(&rq1->lock, SINGLE_DEPTH_NESTING);
-		}
-	}
-	update_rq_clock(rq1);
-	update_rq_clock(rq2);
-}
-
-/*
- * double_rq_unlock - safely unlock two runqueues
- *
- * Note this does not restore interrupts like task_rq_unlock,
- * you need to do so manually after calling.
- */
-static void double_rq_unlock(struct rq *rq1, struct rq *rq2)
-	__releases(rq1->lock)
-	__releases(rq2->lock)
-{
-	raw_spin_unlock(&rq1->lock);
-	if (rq1 != rq2)
-		raw_spin_unlock(&rq2->lock);
-	else
-		__release(rq2->lock);
-}
-
-/*
  * sched_exec - execve() is a valuable balancing opportunity, because at
  * this point the task has the smallest effective memory and cache footprint.
  */
@@ -3185,1771 +3172,6 @@ again:
 	task_rq_unlock(rq, &flags);
 }
 
-/*
- * pull_task - move a task from a remote runqueue to the local runqueue.
- * Both runqueues must be locked.
- */
-static void pull_task(struct rq *src_rq, struct task_struct *p,
-		      struct rq *this_rq, int this_cpu)
-{
-	deactivate_task(src_rq, p, 0);
-	set_task_cpu(p, this_cpu);
-	activate_task(this_rq, p, 0);
-	check_preempt_curr(this_rq, p, 0);
-}
-
-/*
- * can_migrate_task - may task p from runqueue rq be migrated to this_cpu?
- */
-static
-int can_migrate_task(struct task_struct *p, struct rq *rq, int this_cpu,
-		     struct sched_domain *sd, enum cpu_idle_type idle,
-		     int *all_pinned)
-{
-	int tsk_cache_hot = 0;
-	/*
-	 * We do not migrate tasks that are:
-	 * 1) running (obviously), or
-	 * 2) cannot be migrated to this CPU due to cpus_allowed, or
-	 * 3) are cache-hot on their current CPU.
-	 */
-	if (!cpumask_test_cpu(this_cpu, &p->cpus_allowed)) {
-		schedstat_inc(p, se.nr_failed_migrations_affine);
-		return 0;
-	}
-	*all_pinned = 0;
-
-	if (task_running(rq, p)) {
-		schedstat_inc(p, se.nr_failed_migrations_running);
-		return 0;
-	}
-
-	/*
-	 * Aggressive migration if:
-	 * 1) task is cache cold, or
-	 * 2) too many balance attempts have failed.
-	 */
-
-	tsk_cache_hot = task_hot(p, rq->clock, sd);
-	if (!tsk_cache_hot ||
-		sd->nr_balance_failed > sd->cache_nice_tries) {
-#ifdef CONFIG_SCHEDSTATS
-		if (tsk_cache_hot) {
-			schedstat_inc(sd, lb_hot_gained[idle]);
-			schedstat_inc(p, se.nr_forced_migrations);
-		}
-#endif
-		return 1;
-	}
-
-	if (tsk_cache_hot) {
-		schedstat_inc(p, se.nr_failed_migrations_hot);
-		return 0;
-	}
-	return 1;
-}
-
-static unsigned long
-balance_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest,
-	      unsigned long max_load_move, struct sched_domain *sd,
-	      enum cpu_idle_type idle, int *all_pinned,
-	      int *this_best_prio, struct rq_iterator *iterator)
-{
-	int loops = 0, pulled = 0, pinned = 0;
-	struct task_struct *p;
-	long rem_load_move = max_load_move;
-
-	if (max_load_move == 0)
-		goto out;
-
-	pinned = 1;
-
-	/*
-	 * Start the load-balancing iterator:
-	 */
-	p = iterator->start(iterator->arg);
-next:
-	if (!p || loops++ > sysctl_sched_nr_migrate)
-		goto out;
-
-	if ((p->se.load.weight >> 1) > rem_load_move ||
-	    !can_migrate_task(p, busiest, this_cpu, sd, idle, &pinned)) {
-		p = iterator->next(iterator->arg);
-		goto next;
-	}
-
-	pull_task(busiest, p, this_rq, this_cpu);
-	pulled++;
-	rem_load_move -= p->se.load.weight;
-
-#ifdef CONFIG_PREEMPT
-	/*
-	 * NEWIDLE balancing is a source of latency, so preemptible kernels
-	 * will stop after the first task is pulled to minimize the critical
-	 * section.
-	 */
-	if (idle == CPU_NEWLY_IDLE)
-		goto out;
-#endif
-
-	/*
-	 * We only want to steal up to the prescribed amount of weighted load.
-	 */
-	if (rem_load_move > 0) {
-		if (p->prio < *this_best_prio)
-			*this_best_prio = p->prio;
-		p = iterator->next(iterator->arg);
-		goto next;
-	}
-out:
-	/*
-	 * Right now, this is one of only two places pull_task() is called,
-	 * so we can safely collect pull_task() stats here rather than
-	 * inside pull_task().
-	 */
-	schedstat_add(sd, lb_gained[idle], pulled);
-
-	if (all_pinned)
-		*all_pinned = pinned;
-
-	return max_load_move - rem_load_move;
-}
-
-/*
- * move_tasks tries to move up to max_load_move weighted load from busiest to
- * this_rq, as part of a balancing operation within domain "sd".
- * Returns 1 if successful and 0 otherwise.
- *
- * Called with both runqueues locked.
- */
-static int move_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest,
-		      unsigned long max_load_move,
-		      struct sched_domain *sd, enum cpu_idle_type idle,
-		      int *all_pinned)
-{
-	const struct sched_class *class = sched_class_highest;
-	unsigned long total_load_moved = 0;
-	int this_best_prio = this_rq->curr->prio;
-
-	do {
-		total_load_moved +=
-			class->load_balance(this_rq, this_cpu, busiest,
-				max_load_move - total_load_moved,
-				sd, idle, all_pinned, &this_best_prio);
-		class = class->next;
-
-#ifdef CONFIG_PREEMPT
-		/*
-		 * NEWIDLE balancing is a source of latency, so preemptible
-		 * kernels will stop after the first task is pulled to minimize
-		 * the critical section.
-		 */
-		if (idle == CPU_NEWLY_IDLE && this_rq->nr_running)
-			break;
-#endif
-	} while (class && max_load_move > total_load_moved);
-
-	return total_load_moved > 0;
-}
-
-static int
-iter_move_one_task(struct rq *this_rq, int this_cpu, struct rq *busiest,
-		   struct sched_domain *sd, enum cpu_idle_type idle,
-		   struct rq_iterator *iterator)
-{
-	struct task_struct *p = iterator->start(iterator->arg);
-	int pinned = 0;
-
-	while (p) {
-		if (can_migrate_task(p, busiest, this_cpu, sd, idle, &pinned)) {
-			pull_task(busiest, p, this_rq, this_cpu);
-			/*
-			 * Right now, this is only the second place pull_task()
-			 * is called, so we can safely collect pull_task()
-			 * stats here rather than inside pull_task().
-			 */
-			schedstat_inc(sd, lb_gained[idle]);
-
-			return 1;
-		}
-		p = iterator->next(iterator->arg);
-	}
-
-	return 0;
-}
-
-/*
- * move_one_task tries to move exactly one task from busiest to this_rq, as
- * part of active balancing operations within "domain".
- * Returns 1 if successful and 0 otherwise.
- *
- * Called with both runqueues locked.
- */
-static int move_one_task(struct rq *this_rq, int this_cpu, struct rq *busiest,
-			 struct sched_domain *sd, enum cpu_idle_type idle)
-{
-	const struct sched_class *class;
-
-	for_each_class(class) {
-		if (class->move_one_task(this_rq, this_cpu, busiest, sd, idle))
-			return 1;
-	}
-
-	return 0;
-}
-/********** Helpers for find_busiest_group ************************/
-/*
- * sd_lb_stats - Structure to store the statistics of a sched_domain
- * 		during load balancing.
- */
-struct sd_lb_stats {
-	struct sched_group *busiest; /* Busiest group in this sd */
-	struct sched_group *this;  /* Local group in this sd */
-	unsigned long total_load;  /* Total load of all groups in sd */
-	unsigned long total_pwr;   /*	Total power of all groups in sd */
-	unsigned long avg_load;	   /* Average load across all groups in sd */
-
-	/** Statistics of this group */
-	unsigned long this_load;
-	unsigned long this_load_per_task;
-	unsigned long this_nr_running;
-
-	/* Statistics of the busiest group */
-	unsigned long max_load;
-	unsigned long busiest_load_per_task;
-	unsigned long busiest_nr_running;
-
-	int group_imb; /* Is there imbalance in this sd */
-#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT)
-	int power_savings_balance; /* Is powersave balance needed for this sd */
-	struct sched_group *group_min; /* Least loaded group in sd */
-	struct sched_group *group_leader; /* Group which relieves group_min */
-	unsigned long min_load_per_task; /* load_per_task in group_min */
-	unsigned long leader_nr_running; /* Nr running of group_leader */
-	unsigned long min_nr_running; /* Nr running of group_min */
-#endif
-};
-
-/*
- * sg_lb_stats - stats of a sched_group required for load_balancing
- */
-struct sg_lb_stats {
-	unsigned long avg_load; /*Avg load across the CPUs of the group */
-	unsigned long group_load; /* Total load over the CPUs of the group */
-	unsigned long sum_nr_running; /* Nr tasks running in the group */
-	unsigned long sum_weighted_load; /* Weighted load of group's tasks */
-	unsigned long group_capacity;
-	int group_imb; /* Is there an imbalance in the group ? */
-};
-
-/**
- * group_first_cpu - Returns the first cpu in the cpumask of a sched_group.
- * @group: The group whose first cpu is to be returned.
- */
-static inline unsigned int group_first_cpu(struct sched_group *group)
-{
-	return cpumask_first(sched_group_cpus(group));
-}
-
-/**
- * get_sd_load_idx - Obtain the load index for a given sched domain.
- * @sd: The sched_domain whose load_idx is to be obtained.
- * @idle: The Idle status of the CPU for whose sd load_icx is obtained.
- */
-static inline int get_sd_load_idx(struct sched_domain *sd,
-					enum cpu_idle_type idle)
-{
-	int load_idx;
-
-	switch (idle) {
-	case CPU_NOT_IDLE:
-		load_idx = sd->busy_idx;
-		break;
-
-	case CPU_NEWLY_IDLE:
-		load_idx = sd->newidle_idx;
-		break;
-	default:
-		load_idx = sd->idle_idx;
-		break;
-	}
-
-	return load_idx;
-}
-
-
-#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT)
-/**
- * init_sd_power_savings_stats - Initialize power savings statistics for
- * the given sched_domain, during load balancing.
- *
- * @sd: Sched domain whose power-savings statistics are to be initialized.
- * @sds: Variable containing the statistics for sd.
- * @idle: Idle status of the CPU at which we're performing load-balancing.
- */
-static inline void init_sd_power_savings_stats(struct sched_domain *sd,
-	struct sd_lb_stats *sds, enum cpu_idle_type idle)
-{
-	/*
-	 * Busy processors will not participate in power savings
-	 * balance.
-	 */
-	if (idle == CPU_NOT_IDLE || !(sd->flags & SD_POWERSAVINGS_BALANCE))
-		sds->power_savings_balance = 0;
-	else {
-		sds->power_savings_balance = 1;
-		sds->min_nr_running = ULONG_MAX;
-		sds->leader_nr_running = 0;
-	}
-}
-
-/**
- * update_sd_power_savings_stats - Update the power saving stats for a
- * sched_domain while performing load balancing.
- *
- * @group: sched_group belonging to the sched_domain under consideration.
- * @sds: Variable containing the statistics of the sched_domain
- * @local_group: Does group contain the CPU for which we're performing
- * 		load balancing ?
- * @sgs: Variable containing the statistics of the group.
- */
-static inline void update_sd_power_savings_stats(struct sched_group *group,
-	struct sd_lb_stats *sds, int local_group, struct sg_lb_stats *sgs)
-{
-
-	if (!sds->power_savings_balance)
-		return;
-
-	/*
-	 * If the local group is idle or completely loaded
-	 * no need to do power savings balance at this domain
-	 */
-	if (local_group && (sds->this_nr_running >= sgs->group_capacity ||
-				!sds->this_nr_running))
-		sds->power_savings_balance = 0;
-
-	/*
-	 * If a group is already running at full capacity or idle,
-	 * don't include that group in power savings calculations
-	 */
-	if (!sds->power_savings_balance ||
-		sgs->sum_nr_running >= sgs->group_capacity ||
-		!sgs->sum_nr_running)
-		return;
-
-	/*
-	 * Calculate the group which has the least non-idle load.
-	 * This is the group from where we need to pick up the load
-	 * for saving power
-	 */
-	if ((sgs->sum_nr_running < sds->min_nr_running) ||
-	    (sgs->sum_nr_running == sds->min_nr_running &&
-	     group_first_cpu(group) > group_first_cpu(sds->group_min))) {
-		sds->group_min = group;
-		sds->min_nr_running = sgs->sum_nr_running;
-		sds->min_load_per_task = sgs->sum_weighted_load /
-						sgs->sum_nr_running;
-	}
-
-	/*
-	 * Calculate the group which is almost near its
-	 * capacity but still has some space to pick up some load
-	 * from other group and save more power
-	 */
-	if (sgs->sum_nr_running + 1 > sgs->group_capacity)
-		return;
-
-	if (sgs->sum_nr_running > sds->leader_nr_running ||
-	    (sgs->sum_nr_running == sds->leader_nr_running &&
-	     group_first_cpu(group) < group_first_cpu(sds->group_leader))) {
-		sds->group_leader = group;
-		sds->leader_nr_running = sgs->sum_nr_running;
-	}
-}
-
-/**
- * check_power_save_busiest_group - see if there is potential for some power-savings balance
- * @sds: Variable containing the statistics of the sched_domain
- *	under consideration.
- * @this_cpu: Cpu at which we're currently performing load-balancing.
- * @imbalance: Variable to store the imbalance.
- *
- * Description:
- * Check if we have potential to perform some power-savings balance.
- * If yes, set the busiest group to be the least loaded group in the
- * sched_domain, so that it's CPUs can be put to idle.
- *
- * Returns 1 if there is potential to perform power-savings balance.
- * Else returns 0.
- */
-static inline int check_power_save_busiest_group(struct sd_lb_stats *sds,
-					int this_cpu, unsigned long *imbalance)
-{
-	if (!sds->power_savings_balance)
-		return 0;
-
-	if (sds->this != sds->group_leader ||
-			sds->group_leader == sds->group_min)
-		return 0;
-
-	*imbalance = sds->min_load_per_task;
-	sds->busiest = sds->group_min;
-
-	return 1;
-
-}
-#else /* CONFIG_SCHED_MC || CONFIG_SCHED_SMT */
-static inline void init_sd_power_savings_stats(struct sched_domain *sd,
-	struct sd_lb_stats *sds, enum cpu_idle_type idle)
-{
-	return;
-}
-
-static inline void update_sd_power_savings_stats(struct sched_group *group,
-	struct sd_lb_stats *sds, int local_group, struct sg_lb_stats *sgs)
-{
-	return;
-}
-
-static inline int check_power_save_busiest_group(struct sd_lb_stats *sds,
-					int this_cpu, unsigned long *imbalance)
-{
-	return 0;
-}
-#endif /* CONFIG_SCHED_MC || CONFIG_SCHED_SMT */
-
-
-unsigned long default_scale_freq_power(struct sched_domain *sd, int cpu)
-{
-	return SCHED_LOAD_SCALE;
-}
-
-unsigned long __weak arch_scale_freq_power(struct sched_domain *sd, int cpu)
-{
-	return default_scale_freq_power(sd, cpu);
-}
-
-unsigned long default_scale_smt_power(struct sched_domain *sd, int cpu)
-{
-	unsigned long weight = cpumask_weight(sched_domain_span(sd));
-	unsigned long smt_gain = sd->smt_gain;
-
-	smt_gain /= weight;
-
-	return smt_gain;
-}
-
-unsigned long __weak arch_scale_smt_power(struct sched_domain *sd, int cpu)
-{
-	return default_scale_smt_power(sd, cpu);
-}
-
-unsigned long scale_rt_power(int cpu)
-{
-	struct rq *rq = cpu_rq(cpu);
-	u64 total, available;
-
-	sched_avg_update(rq);
-
-	total = sched_avg_period() + (rq->clock - rq->age_stamp);
-	available = total - rq->rt_avg;
-
-	if (unlikely((s64)total < SCHED_LOAD_SCALE))
-		total = SCHED_LOAD_SCALE;
-
-	total >>= SCHED_LOAD_SHIFT;
-
-	return div_u64(available, total);
-}
-
-static void update_cpu_power(struct sched_domain *sd, int cpu)
-{
-	unsigned long weight = cpumask_weight(sched_domain_span(sd));
-	unsigned long power = SCHED_LOAD_SCALE;
-	struct sched_group *sdg = sd->groups;
-
-	if (sched_feat(ARCH_POWER))
-		power *= arch_scale_freq_power(sd, cpu);
-	else
-		power *= default_scale_freq_power(sd, cpu);
-
-	power >>= SCHED_LOAD_SHIFT;
-
-	if ((sd->flags & SD_SHARE_CPUPOWER) && weight > 1) {
-		if (sched_feat(ARCH_POWER))
-			power *= arch_scale_smt_power(sd, cpu);
-		else
-			power *= default_scale_smt_power(sd, cpu);
-
-		power >>= SCHED_LOAD_SHIFT;
-	}
-
-	power *= scale_rt_power(cpu);
-	power >>= SCHED_LOAD_SHIFT;
-
-	if (!power)
-		power = 1;
-
-	sdg->cpu_power = power;
-}
-
-static void update_group_power(struct sched_domain *sd, int cpu)
-{
-	struct sched_domain *child = sd->child;
-	struct sched_group *group, *sdg = sd->groups;
-	unsigned long power;
-
-	if (!child) {
-		update_cpu_power(sd, cpu);
-		return;
-	}
-
-	power = 0;
-
-	group = child->groups;
-	do {
-		power += group->cpu_power;
-		group = group->next;
-	} while (group != child->groups);
-
-	sdg->cpu_power = power;
-}
-
-/**
- * update_sg_lb_stats - Update sched_group's statistics for load balancing.
- * @sd: The sched_domain whose statistics are to be updated.
- * @group: sched_group whose statistics are to be updated.
- * @this_cpu: Cpu for which load balance is currently performed.
- * @idle: Idle status of this_cpu
- * @load_idx: Load index of sched_domain of this_cpu for load calc.
- * @sd_idle: Idle status of the sched_domain containing group.
- * @local_group: Does group contain this_cpu.
- * @cpus: Set of cpus considered for load balancing.
- * @balance: Should we balance.
- * @sgs: variable to hold the statistics for this group.
- */
-static inline void update_sg_lb_stats(struct sched_domain *sd,
-			struct sched_group *group, int this_cpu,
-			enum cpu_idle_type idle, int load_idx, int *sd_idle,
-			int local_group, const struct cpumask *cpus,
-			int *balance, struct sg_lb_stats *sgs)
-{
-	unsigned long load, max_cpu_load, min_cpu_load;
-	int i;
-	unsigned int balance_cpu = -1, first_idle_cpu = 0;
-	unsigned long sum_avg_load_per_task;
-	unsigned long avg_load_per_task;
-
-	if (local_group) {
-		balance_cpu = group_first_cpu(group);
-		if (balance_cpu == this_cpu)
-			update_group_power(sd, this_cpu);
-	}
-
-	/* Tally up the load of all CPUs in the group */
-	sum_avg_load_per_task = avg_load_per_task = 0;
-	max_cpu_load = 0;
-	min_cpu_load = ~0UL;
-
-	for_each_cpu_and(i, sched_group_cpus(group), cpus) {
-		struct rq *rq = cpu_rq(i);
-
-		if (*sd_idle && rq->nr_running)
-			*sd_idle = 0;
-
-		/* Bias balancing toward cpus of our domain */
-		if (local_group) {
-			if (idle_cpu(i) && !first_idle_cpu) {
-				first_idle_cpu = 1;
-				balance_cpu = i;
-			}
-
-			load = target_load(i, load_idx);
-		} else {
-			load = source_load(i, load_idx);
-			if (load > max_cpu_load)
-				max_cpu_load = load;
-			if (min_cpu_load > load)
-				min_cpu_load = load;
-		}
-
-		sgs->group_load += load;
-		sgs->sum_nr_running += rq->nr_running;
-		sgs->sum_weighted_load += weighted_cpuload(i);
-
-		sum_avg_load_per_task += cpu_avg_load_per_task(i);
-	}
-
-	/*
-	 * First idle cpu or the first cpu(busiest) in this sched group
-	 * is eligible for doing load balancing at this and above
-	 * domains. In the newly idle case, we will allow all the cpu's
-	 * to do the newly idle load balance.
-	 */
-	if (idle != CPU_NEWLY_IDLE && local_group &&
-	    balance_cpu != this_cpu && balance) {
-		*balance = 0;
-		return;
-	}
-
-	/* Adjust by relative CPU power of the group */
-	sgs->avg_load = (sgs->group_load * SCHED_LOAD_SCALE) / group->cpu_power;
-
-
-	/*
-	 * Consider the group unbalanced when the imbalance is larger
-	 * than the average weight of two tasks.
-	 *
-	 * APZ: with cgroup the avg task weight can vary wildly and
-	 *      might not be a suitable number - should we keep a
-	 *      normalized nr_running number somewhere that negates
-	 *      the hierarchy?
-	 */
-	avg_load_per_task = (sum_avg_load_per_task * SCHED_LOAD_SCALE) /
-		group->cpu_power;
-
-	if ((max_cpu_load - min_cpu_load) > 2*avg_load_per_task)
-		sgs->group_imb = 1;
-
-	sgs->group_capacity =
-		DIV_ROUND_CLOSEST(group->cpu_power, SCHED_LOAD_SCALE);
-}
-
-/**
- * update_sd_lb_stats - Update sched_group's statistics for load balancing.
- * @sd: sched_domain whose statistics are to be updated.
- * @this_cpu: Cpu for which load balance is currently performed.
- * @idle: Idle status of this_cpu
- * @sd_idle: Idle status of the sched_domain containing group.
- * @cpus: Set of cpus considered for load balancing.
- * @balance: Should we balance.
- * @sds: variable to hold the statistics for this sched_domain.
- */
-static inline void update_sd_lb_stats(struct sched_domain *sd, int this_cpu,
-			enum cpu_idle_type idle, int *sd_idle,
-			const struct cpumask *cpus, int *balance,
-			struct sd_lb_stats *sds)
-{
-	struct sched_domain *child = sd->child;
-	struct sched_group *group = sd->groups;
-	struct sg_lb_stats sgs;
-	int load_idx, prefer_sibling = 0;
-
-	if (child && child->flags & SD_PREFER_SIBLING)
-		prefer_sibling = 1;
-
-	init_sd_power_savings_stats(sd, sds, idle);
-	load_idx = get_sd_load_idx(sd, idle);
-
-	do {
-		int local_group;
-
-		local_group = cpumask_test_cpu(this_cpu,
-					       sched_group_cpus(group));
-		memset(&sgs, 0, sizeof(sgs));
-		update_sg_lb_stats(sd, group, this_cpu, idle, load_idx, sd_idle,
-				local_group, cpus, balance, &sgs);
-
-		if (local_group && balance && !(*balance))
-			return;
-
-		sds->total_load += sgs.group_load;
-		sds->total_pwr += group->cpu_power;
-
-		/*
-		 * In case the child domain prefers tasks go to siblings
-		 * first, lower the group capacity to one so that we'll try
-		 * and move all the excess tasks away.
-		 */
-		if (prefer_sibling)
-			sgs.group_capacity = min(sgs.group_capacity, 1UL);
-
-		if (local_group) {
-			sds->this_load = sgs.avg_load;
-			sds->this = group;
-			sds->this_nr_running = sgs.sum_nr_running;
-			sds->this_load_per_task = sgs.sum_weighted_load;
-		} else if (sgs.avg_load > sds->max_load &&
-			   (sgs.sum_nr_running > sgs.group_capacity ||
-				sgs.group_imb)) {
-			sds->max_load = sgs.avg_load;
-			sds->busiest = group;
-			sds->busiest_nr_running = sgs.sum_nr_running;
-			sds->busiest_load_per_task = sgs.sum_weighted_load;
-			sds->group_imb = sgs.group_imb;
-		}
-
-		update_sd_power_savings_stats(group, sds, local_group, &sgs);
-		group = group->next;
-	} while (group != sd->groups);
-}
-
-/**
- * fix_small_imbalance - Calculate the minor imbalance that exists
- *			amongst the groups of a sched_domain, during
- *			load balancing.
- * @sds: Statistics of the sched_domain whose imbalance is to be calculated.
- * @this_cpu: The cpu at whose sched_domain we're performing load-balance.
- * @imbalance: Variable to store the imbalance.
- */
-static inline void fix_small_imbalance(struct sd_lb_stats *sds,
-				int this_cpu, unsigned long *imbalance)
-{
-	unsigned long tmp, pwr_now = 0, pwr_move = 0;
-	unsigned int imbn = 2;
-
-	if (sds->this_nr_running) {
-		sds->this_load_per_task /= sds->this_nr_running;
-		if (sds->busiest_load_per_task >
-				sds->this_load_per_task)
-			imbn = 1;
-	} else
-		sds->this_load_per_task =
-			cpu_avg_load_per_task(this_cpu);
-
-	if (sds->max_load - sds->this_load + sds->busiest_load_per_task >=
-			sds->busiest_load_per_task * imbn) {
-		*imbalance = sds->busiest_load_per_task;
-		return;
-	}
-
-	/*
-	 * OK, we don't have enough imbalance to justify moving tasks,
-	 * however we may be able to increase total CPU power used by
-	 * moving them.
-	 */
-
-	pwr_now += sds->busiest->cpu_power *
-			min(sds->busiest_load_per_task, sds->max_load);
-	pwr_now += sds->this->cpu_power *
-			min(sds->this_load_per_task, sds->this_load);
-	pwr_now /= SCHED_LOAD_SCALE;
-
-	/* Amount of load we'd subtract */
-	tmp = (sds->busiest_load_per_task * SCHED_LOAD_SCALE) /
-		sds->busiest->cpu_power;
-	if (sds->max_load > tmp)
-		pwr_move += sds->busiest->cpu_power *
-			min(sds->busiest_load_per_task, sds->max_load - tmp);
-
-	/* Amount of load we'd add */
-	if (sds->max_load * sds->busiest->cpu_power <
-		sds->busiest_load_per_task * SCHED_LOAD_SCALE)
-		tmp = (sds->max_load * sds->busiest->cpu_power) /
-			sds->this->cpu_power;
-	else
-		tmp = (sds->busiest_load_per_task * SCHED_LOAD_SCALE) /
-			sds->this->cpu_power;
-	pwr_move += sds->this->cpu_power *
-			min(sds->this_load_per_task, sds->this_load + tmp);
-	pwr_move /= SCHED_LOAD_SCALE;
-
-	/* Move if we gain throughput */
-	if (pwr_move > pwr_now)
-		*imbalance = sds->busiest_load_per_task;
-}
-
-/**
- * calculate_imbalance - Calculate the amount of imbalance present within the
- *			 groups of a given sched_domain during load balance.
- * @sds: statistics of the sched_domain whose imbalance is to be calculated.
- * @this_cpu: Cpu for which currently load balance is being performed.
- * @imbalance: The variable to store the imbalance.
- */
-static inline void calculate_imbalance(struct sd_lb_stats *sds, int this_cpu,
-		unsigned long *imbalance)
-{
-	unsigned long max_pull;
-	/*
-	 * In the presence of smp nice balancing, certain scenarios can have
-	 * max load less than avg load(as we skip the groups at or below
-	 * its cpu_power, while calculating max_load..)
-	 */
-	if (sds->max_load < sds->avg_load) {
-		*imbalance = 0;
-		return fix_small_imbalance(sds, this_cpu, imbalance);
-	}
-
-	/* Don't want to pull so many tasks that a group would go idle */
-	max_pull = min(sds->max_load - sds->avg_load,
-			sds->max_load - sds->busiest_load_per_task);
-
-	/* How much load to actually move to equalise the imbalance */
-	*imbalance = min(max_pull * sds->busiest->cpu_power,
-		(sds->avg_load - sds->this_load) * sds->this->cpu_power)
-			/ SCHED_LOAD_SCALE;
-
-	/*
-	 * if *imbalance is less than the average load per runnable task
-	 * there is no gaurantee that any tasks will be moved so we'll have
-	 * a think about bumping its value to force at least one task to be
-	 * moved
-	 */
-	if (*imbalance < sds->busiest_load_per_task)
-		return fix_small_imbalance(sds, this_cpu, imbalance);
-
-}
-/******* find_busiest_group() helpers end here *********************/
-
-/**
- * find_busiest_group - Returns the busiest group within the sched_domain
- * if there is an imbalance. If there isn't an imbalance, and
- * the user has opted for power-savings, it returns a group whose
- * CPUs can be put to idle by rebalancing those tasks elsewhere, if
- * such a group exists.
- *
- * Also calculates the amount of weighted load which should be moved
- * to restore balance.
- *
- * @sd: The sched_domain whose busiest group is to be returned.
- * @this_cpu: The cpu for which load balancing is currently being performed.
- * @imbalance: Variable which stores amount of weighted load which should
- *		be moved to restore balance/put a group to idle.
- * @idle: The idle status of this_cpu.
- * @sd_idle: The idleness of sd
- * @cpus: The set of CPUs under consideration for load-balancing.
- * @balance: Pointer to a variable indicating if this_cpu
- *	is the appropriate cpu to perform load balancing at this_level.
- *
- * Returns:	- the busiest group if imbalance exists.
- *		- If no imbalance and user has opted for power-savings balance,
- *		   return the least loaded group whose CPUs can be
- *		   put to idle by rebalancing its tasks onto our group.
- */
-static struct sched_group *
-find_busiest_group(struct sched_domain *sd, int this_cpu,
-		   unsigned long *imbalance, enum cpu_idle_type idle,
-		   int *sd_idle, const struct cpumask *cpus, int *balance)
-{
-	struct sd_lb_stats sds;
-
-	memset(&sds, 0, sizeof(sds));
-
-	/*
-	 * Compute the various statistics relavent for load balancing at
-	 * this level.
-	 */
-	update_sd_lb_stats(sd, this_cpu, idle, sd_idle, cpus,
-					balance, &sds);
-
-	/* Cases where imbalance does not exist from POV of this_cpu */
-	/* 1) this_cpu is not the appropriate cpu to perform load balancing
-	 *    at this level.
-	 * 2) There is no busy sibling group to pull from.
-	 * 3) This group is the busiest group.
-	 * 4) This group is more busy than the avg busieness at this
-	 *    sched_domain.
-	 * 5) The imbalance is within the specified limit.
-	 * 6) Any rebalance would lead to ping-pong
-	 */
-	if (balance && !(*balance))
-		goto ret;
-
-	if (!sds.busiest || sds.busiest_nr_running == 0)
-		goto out_balanced;
-
-	if (sds.this_load >= sds.max_load)
-		goto out_balanced;
-
-	sds.avg_load = (SCHED_LOAD_SCALE * sds.total_load) / sds.total_pwr;
-
-	if (sds.this_load >= sds.avg_load)
-		goto out_balanced;
-
-	if (100 * sds.max_load <= sd->imbalance_pct * sds.this_load)
-		goto out_balanced;
-
-	sds.busiest_load_per_task /= sds.busiest_nr_running;
-	if (sds.group_imb)
-		sds.busiest_load_per_task =
-			min(sds.busiest_load_per_task, sds.avg_load);
-
-	/*
-	 * We're trying to get all the cpus to the average_load, so we don't
-	 * want to push ourselves above the average load, nor do we wish to
-	 * reduce the max loaded cpu below the average load, as either of these
-	 * actions would just result in more rebalancing later, and ping-pong
-	 * tasks around. Thus we look for the minimum possible imbalance.
-	 * Negative imbalances (*we* are more loaded than anyone else) will
-	 * be counted as no imbalance for these purposes -- we can't fix that
-	 * by pulling tasks to us. Be careful of negative numbers as they'll
-	 * appear as very large values with unsigned longs.
-	 */
-	if (sds.max_load <= sds.busiest_load_per_task)
-		goto out_balanced;
-
-	/* Looks like there is an imbalance. Compute it */
-	calculate_imbalance(&sds, this_cpu, imbalance);
-	return sds.busiest;
-
-out_balanced:
-	/*
-	 * There is no obvious imbalance. But check if we can do some balancing
-	 * to save power.
-	 */
-	if (check_power_save_busiest_group(&sds, this_cpu, imbalance))
-		return sds.busiest;
-ret:
-	*imbalance = 0;
-	return NULL;
-}
-
-/*
- * find_busiest_queue - find the busiest runqueue among the cpus in group.
- */
-static struct rq *
-find_busiest_queue(struct sched_group *group, enum cpu_idle_type idle,
-		   unsigned long imbalance, const struct cpumask *cpus)
-{
-	struct rq *busiest = NULL, *rq;
-	unsigned long max_load = 0;
-	int i;
-
-	for_each_cpu(i, sched_group_cpus(group)) {
-		unsigned long power = power_of(i);
-		unsigned long capacity = DIV_ROUND_CLOSEST(power, SCHED_LOAD_SCALE);
-		unsigned long wl;
-
-		if (!cpumask_test_cpu(i, cpus))
-			continue;
-
-		rq = cpu_rq(i);
-		wl = weighted_cpuload(i) * SCHED_LOAD_SCALE;
-		wl /= power;
-
-		if (capacity && rq->nr_running == 1 && wl > imbalance)
-			continue;
-
-		if (wl > max_load) {
-			max_load = wl;
-			busiest = rq;
-		}
-	}
-
-	return busiest;
-}
-
-/*
- * Max backoff if we encounter pinned tasks. Pretty arbitrary value, but
- * so long as it is large enough.
- */
-#define MAX_PINNED_INTERVAL	512
-
-/* Working cpumask for load_balance and load_balance_newidle. */
-static DEFINE_PER_CPU(cpumask_var_t, load_balance_tmpmask);
-
-/*
- * Check this_cpu to ensure it is balanced within domain. Attempt to move
- * tasks if there is an imbalance.
- */
-static int load_balance(int this_cpu, struct rq *this_rq,
-			struct sched_domain *sd, enum cpu_idle_type idle,
-			int *balance)
-{
-	int ld_moved, all_pinned = 0, active_balance = 0, sd_idle = 0;
-	struct sched_group *group;
-	unsigned long imbalance;
-	struct rq *busiest;
-	unsigned long flags;
-	struct cpumask *cpus = __get_cpu_var(load_balance_tmpmask);
-
-	cpumask_copy(cpus, cpu_active_mask);
-
-	/*
-	 * When power savings policy is enabled for the parent domain, idle
-	 * sibling can pick up load irrespective of busy siblings. In this case,
-	 * let the state of idle sibling percolate up as CPU_IDLE, instead of
-	 * portraying it as CPU_NOT_IDLE.
-	 */
-	if (idle != CPU_NOT_IDLE && sd->flags & SD_SHARE_CPUPOWER &&
-	    !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE))
-		sd_idle = 1;
-
-	schedstat_inc(sd, lb_count[idle]);
-
-redo:
-	update_shares(sd);
-	group = find_busiest_group(sd, this_cpu, &imbalance, idle, &sd_idle,
-				   cpus, balance);
-
-	if (*balance == 0)
-		goto out_balanced;
-
-	if (!group) {
-		schedstat_inc(sd, lb_nobusyg[idle]);
-		goto out_balanced;
-	}
-
-	busiest = find_busiest_queue(group, idle, imbalance, cpus);
-	if (!busiest) {
-		schedstat_inc(sd, lb_nobusyq[idle]);
-		goto out_balanced;
-	}
-
-	BUG_ON(busiest == this_rq);
-
-	schedstat_add(sd, lb_imbalance[idle], imbalance);
-
-	ld_moved = 0;
-	if (busiest->nr_running > 1) {
-		/*
-		 * Attempt to move tasks. If find_busiest_group has found
-		 * an imbalance but busiest->nr_running <= 1, the group is
-		 * still unbalanced. ld_moved simply stays zero, so it is
-		 * correctly treated as an imbalance.
-		 */
-		local_irq_save(flags);
-		double_rq_lock(this_rq, busiest);
-		ld_moved = move_tasks(this_rq, this_cpu, busiest,
-				      imbalance, sd, idle, &all_pinned);
-		double_rq_unlock(this_rq, busiest);
-		local_irq_restore(flags);
-
-		/*
-		 * some other cpu did the load balance for us.
-		 */
-		if (ld_moved && this_cpu != smp_processor_id())
-			resched_cpu(this_cpu);
-
-		/* All tasks on this runqueue were pinned by CPU affinity */
-		if (unlikely(all_pinned)) {
-			cpumask_clear_cpu(cpu_of(busiest), cpus);
-			if (!cpumask_empty(cpus))
-				goto redo;
-			goto out_balanced;
-		}
-	}
-
-	if (!ld_moved) {
-		schedstat_inc(sd, lb_failed[idle]);
-		sd->nr_balance_failed++;
-
-		if (unlikely(sd->nr_balance_failed > sd->cache_nice_tries+2)) {
-
-			raw_spin_lock_irqsave(&busiest->lock, flags);
-
-			/* don't kick the migration_thread, if the curr
-			 * task on busiest cpu can't be moved to this_cpu
-			 */
-			if (!cpumask_test_cpu(this_cpu,
-					      &busiest->curr->cpus_allowed)) {
-				raw_spin_unlock_irqrestore(&busiest->lock,
-							    flags);
-				all_pinned = 1;
-				goto out_one_pinned;
-			}
-
-			if (!busiest->active_balance) {
-				busiest->active_balance = 1;
-				busiest->push_cpu = this_cpu;
-				active_balance = 1;
-			}
-			raw_spin_unlock_irqrestore(&busiest->lock, flags);
-			if (active_balance)
-				wake_up_process(busiest->migration_thread);
-
-			/*
-			 * We've kicked active balancing, reset the failure
-			 * counter.
-			 */
-			sd->nr_balance_failed = sd->cache_nice_tries+1;
-		}
-	} else
-		sd->nr_balance_failed = 0;
-
-	if (likely(!active_balance)) {
-		/* We were unbalanced, so reset the balancing interval */
-		sd->balance_interval = sd->min_interval;
-	} else {
-		/*
-		 * If we've begun active balancing, start to back off. This
-		 * case may not be covered by the all_pinned logic if there
-		 * is only 1 task on the busy runqueue (because we don't call
-		 * move_tasks).
-		 */
-		if (sd->balance_interval < sd->max_interval)
-			sd->balance_interval *= 2;
-	}
-
-	if (!ld_moved && !sd_idle && sd->flags & SD_SHARE_CPUPOWER &&
-	    !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE))
-		ld_moved = -1;
-
-	goto out;
-
-out_balanced:
-	schedstat_inc(sd, lb_balanced[idle]);
-
-	sd->nr_balance_failed = 0;
-
-out_one_pinned:
-	/* tune up the balancing interval */
-	if ((all_pinned && sd->balance_interval < MAX_PINNED_INTERVAL) ||
-			(sd->balance_interval < sd->max_interval))
-		sd->balance_interval *= 2;
-
-	if (!sd_idle && sd->flags & SD_SHARE_CPUPOWER &&
-	    !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE))
-		ld_moved = -1;
-	else
-		ld_moved = 0;
-out:
-	if (ld_moved)
-		update_shares(sd);
-	return ld_moved;
-}
-
-/*
- * Check this_cpu to ensure it is balanced within domain. Attempt to move
- * tasks if there is an imbalance.
- *
- * Called from schedule when this_rq is about to become idle (CPU_NEWLY_IDLE).
- * this_rq is locked.
- */
-static int
-load_balance_newidle(int this_cpu, struct rq *this_rq, struct sched_domain *sd)
-{
-	struct sched_group *group;
-	struct rq *busiest = NULL;
-	unsigned long imbalance;
-	int ld_moved = 0;
-	int sd_idle = 0;
-	int all_pinned = 0;
-	struct cpumask *cpus = __get_cpu_var(load_balance_tmpmask);
-
-	cpumask_copy(cpus, cpu_active_mask);
-
-	/*
-	 * When power savings policy is enabled for the parent domain, idle
-	 * sibling can pick up load irrespective of busy siblings. In this case,
-	 * let the state of idle sibling percolate up as IDLE, instead of
-	 * portraying it as CPU_NOT_IDLE.
-	 */
-	if (sd->flags & SD_SHARE_CPUPOWER &&
-	    !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE))
-		sd_idle = 1;
-
-	schedstat_inc(sd, lb_count[CPU_NEWLY_IDLE]);
-redo:
-	update_shares_locked(this_rq, sd);
-	group = find_busiest_group(sd, this_cpu, &imbalance, CPU_NEWLY_IDLE,
-				   &sd_idle, cpus, NULL);
-	if (!group) {
-		schedstat_inc(sd, lb_nobusyg[CPU_NEWLY_IDLE]);
-		goto out_balanced;
-	}
-
-	busiest = find_busiest_queue(group, CPU_NEWLY_IDLE, imbalance, cpus);
-	if (!busiest) {
-		schedstat_inc(sd, lb_nobusyq[CPU_NEWLY_IDLE]);
-		goto out_balanced;
-	}
-
-	BUG_ON(busiest == this_rq);
-
-	schedstat_add(sd, lb_imbalance[CPU_NEWLY_IDLE], imbalance);
-
-	ld_moved = 0;
-	if (busiest->nr_running > 1) {
-		/* Attempt to move tasks */
-		double_lock_balance(this_rq, busiest);
-		/* this_rq->clock is already updated */
-		update_rq_clock(busiest);
-		ld_moved = move_tasks(this_rq, this_cpu, busiest,
-					imbalance, sd, CPU_NEWLY_IDLE,
-					&all_pinned);
-		double_unlock_balance(this_rq, busiest);
-
-		if (unlikely(all_pinned)) {
-			cpumask_clear_cpu(cpu_of(busiest), cpus);
-			if (!cpumask_empty(cpus))
-				goto redo;
-		}
-	}
-
-	if (!ld_moved) {
-		int active_balance = 0;
-
-		schedstat_inc(sd, lb_failed[CPU_NEWLY_IDLE]);
-		if (!sd_idle && sd->flags & SD_SHARE_CPUPOWER &&
-		    !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE))
-			return -1;
-
-		if (sched_mc_power_savings < POWERSAVINGS_BALANCE_WAKEUP)
-			return -1;
-
-		if (sd->nr_balance_failed++ < 2)
-			return -1;
-
-		/*
-		 * The only task running in a non-idle cpu can be moved to this
-		 * cpu in an attempt to completely freeup the other CPU
-		 * package. The same method used to move task in load_balance()
-		 * have been extended for load_balance_newidle() to speedup
-		 * consolidation at sched_mc=POWERSAVINGS_BALANCE_WAKEUP (2)
-		 *
-		 * The package power saving logic comes from
-		 * find_busiest_group().  If there are no imbalance, then
-		 * f_b_g() will return NULL.  However when sched_mc={1,2} then
-		 * f_b_g() will select a group from which a running task may be
-		 * pulled to this cpu in order to make the other package idle.
-		 * If there is no opportunity to make a package idle and if
-		 * there are no imbalance, then f_b_g() will return NULL and no
-		 * action will be taken in load_balance_newidle().
-		 *
-		 * Under normal task pull operation due to imbalance, there
-		 * will be more than one task in the source run queue and
-		 * move_tasks() will succeed.  ld_moved will be true and this
-		 * active balance code will not be triggered.
-		 */
-
-		/* Lock busiest in correct order while this_rq is held */
-		double_lock_balance(this_rq, busiest);
-
-		/*
-		 * don't kick the migration_thread, if the curr
-		 * task on busiest cpu can't be moved to this_cpu
-		 */
-		if (!cpumask_test_cpu(this_cpu, &busiest->curr->cpus_allowed)) {
-			double_unlock_balance(this_rq, busiest);
-			all_pinned = 1;
-			return ld_moved;
-		}
-
-		if (!busiest->active_balance) {
-			busiest->active_balance = 1;
-			busiest->push_cpu = this_cpu;
-			active_balance = 1;
-		}
-
-		double_unlock_balance(this_rq, busiest);
-		/*
-		 * Should not call ttwu while holding a rq->lock
-		 */
-		raw_spin_unlock(&this_rq->lock);
-		if (active_balance)
-			wake_up_process(busiest->migration_thread);
-		raw_spin_lock(&this_rq->lock);
-
-	} else
-		sd->nr_balance_failed = 0;
-
-	update_shares_locked(this_rq, sd);
-	return ld_moved;
-
-out_balanced:
-	schedstat_inc(sd, lb_balanced[CPU_NEWLY_IDLE]);
-	if (!sd_idle && sd->flags & SD_SHARE_CPUPOWER &&
-	    !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE))
-		return -1;
-	sd->nr_balance_failed = 0;
-
-	return 0;
-}
-
-/*
- * idle_balance is called by schedule() if this_cpu is about to become
- * idle. Attempts to pull tasks from other CPUs.
- */
-static void idle_balance(int this_cpu, struct rq *this_rq)
-{
-	struct sched_domain *sd;
-	int pulled_task = 0;
-	unsigned long next_balance = jiffies + HZ;
-
-	this_rq->idle_stamp = this_rq->clock;
-
-	if (this_rq->avg_idle < sysctl_sched_migration_cost)
-		return;
-
-	for_each_domain(this_cpu, sd) {
-		unsigned long interval;
-
-		if (!(sd->flags & SD_LOAD_BALANCE))
-			continue;
-
-		if (sd->flags & SD_BALANCE_NEWIDLE)
-			/* If we've pulled tasks over stop searching: */
-			pulled_task = load_balance_newidle(this_cpu, this_rq,
-							   sd);
-
-		interval = msecs_to_jiffies(sd->balance_interval);
-		if (time_after(next_balance, sd->last_balance + interval))
-			next_balance = sd->last_balance + interval;
-		if (pulled_task) {
-			this_rq->idle_stamp = 0;
-			break;
-		}
-	}
-	if (pulled_task || time_after(jiffies, this_rq->next_balance)) {
-		/*
-		 * We are going idle. next_balance may be set based on
-		 * a busy processor. So reset next_balance.
-		 */
-		this_rq->next_balance = next_balance;
-	}
-}
-
-/*
- * active_load_balance is run by migration threads. It pushes running tasks
- * off the busiest CPU onto idle CPUs. It requires at least 1 task to be
- * running on each physical CPU where possible, and avoids physical /
- * logical imbalances.
- *
- * Called with busiest_rq locked.
- */
-static void active_load_balance(struct rq *busiest_rq, int busiest_cpu)
-{
-	int target_cpu = busiest_rq->push_cpu;
-	struct sched_domain *sd;
-	struct rq *target_rq;
-
-	/* Is there any task to move? */
-	if (busiest_rq->nr_running <= 1)
-		return;
-
-	target_rq = cpu_rq(target_cpu);
-
-	/*
-	 * This condition is "impossible", if it occurs
-	 * we need to fix it. Originally reported by
-	 * Bjorn Helgaas on a 128-cpu setup.
-	 */
-	BUG_ON(busiest_rq == target_rq);
-
-	/* move a task from busiest_rq to target_rq */
-	double_lock_balance(busiest_rq, target_rq);
-	update_rq_clock(busiest_rq);
-	update_rq_clock(target_rq);
-
-	/* Search for an sd spanning us and the target CPU. */
-	for_each_domain(target_cpu, sd) {
-		if ((sd->flags & SD_LOAD_BALANCE) &&
-		    cpumask_test_cpu(busiest_cpu, sched_domain_span(sd)))
-				break;
-	}
-
-	if (likely(sd)) {
-		schedstat_inc(sd, alb_count);
-
-		if (move_one_task(target_rq, target_cpu, busiest_rq,
-				  sd, CPU_IDLE))
-			schedstat_inc(sd, alb_pushed);
-		else
-			schedstat_inc(sd, alb_failed);
-	}
-	double_unlock_balance(busiest_rq, target_rq);
-}
-
-#ifdef CONFIG_NO_HZ
-static struct {
-	atomic_t load_balancer;
-	cpumask_var_t cpu_mask;
-	cpumask_var_t ilb_grp_nohz_mask;
-} nohz ____cacheline_aligned = {
-	.load_balancer = ATOMIC_INIT(-1),
-};
-
-int get_nohz_load_balancer(void)
-{
-	return atomic_read(&nohz.load_balancer);
-}
-
-#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT)
-/**
- * lowest_flag_domain - Return lowest sched_domain containing flag.
- * @cpu:	The cpu whose lowest level of sched domain is to
- *		be returned.
- * @flag:	The flag to check for the lowest sched_domain
- *		for the given cpu.
- *
- * Returns the lowest sched_domain of a cpu which contains the given flag.
- */
-static inline struct sched_domain *lowest_flag_domain(int cpu, int flag)
-{
-	struct sched_domain *sd;
-
-	for_each_domain(cpu, sd)
-		if (sd && (sd->flags & flag))
-			break;
-
-	return sd;
-}
-
-/**
- * for_each_flag_domain - Iterates over sched_domains containing the flag.
- * @cpu:	The cpu whose domains we're iterating over.
- * @sd:		variable holding the value of the power_savings_sd
- *		for cpu.
- * @flag:	The flag to filter the sched_domains to be iterated.
- *
- * Iterates over all the scheduler domains for a given cpu that has the 'flag'
- * set, starting from the lowest sched_domain to the highest.
- */
-#define for_each_flag_domain(cpu, sd, flag) \
-	for (sd = lowest_flag_domain(cpu, flag); \
-		(sd && (sd->flags & flag)); sd = sd->parent)
-
-/**
- * is_semi_idle_group - Checks if the given sched_group is semi-idle.
- * @ilb_group:	group to be checked for semi-idleness
- *
- * Returns:	1 if the group is semi-idle. 0 otherwise.
- *
- * We define a sched_group to be semi idle if it has atleast one idle-CPU
- * and atleast one non-idle CPU. This helper function checks if the given
- * sched_group is semi-idle or not.
- */
-static inline int is_semi_idle_group(struct sched_group *ilb_group)
-{
-	cpumask_and(nohz.ilb_grp_nohz_mask, nohz.cpu_mask,
-					sched_group_cpus(ilb_group));
-
-	/*
-	 * A sched_group is semi-idle when it has atleast one busy cpu
-	 * and atleast one idle cpu.
-	 */
-	if (cpumask_empty(nohz.ilb_grp_nohz_mask))
-		return 0;
-
-	if (cpumask_equal(nohz.ilb_grp_nohz_mask, sched_group_cpus(ilb_group)))
-		return 0;
-
-	return 1;
-}
-/**
- * find_new_ilb - Finds the optimum idle load balancer for nomination.
- * @cpu:	The cpu which is nominating a new idle_load_balancer.
- *
- * Returns:	Returns the id of the idle load balancer if it exists,
- *		Else, returns >= nr_cpu_ids.
- *
- * This algorithm picks the idle load balancer such that it belongs to a
- * semi-idle powersavings sched_domain. The idea is to try and avoid
- * completely idle packages/cores just for the purpose of idle load balancing
- * when there are other idle cpu's which are better suited for that job.
- */
-static int find_new_ilb(int cpu)
-{
-	struct sched_domain *sd;
-	struct sched_group *ilb_group;
-
-	/*
-	 * Have idle load balancer selection from semi-idle packages only
-	 * when power-aware load balancing is enabled
-	 */
-	if (!(sched_smt_power_savings || sched_mc_power_savings))
-		goto out_done;
-
-	/*
-	 * Optimize for the case when we have no idle CPUs or only one
-	 * idle CPU. Don't walk the sched_domain hierarchy in such cases
-	 */
-	if (cpumask_weight(nohz.cpu_mask) < 2)
-		goto out_done;
-
-	for_each_flag_domain(cpu, sd, SD_POWERSAVINGS_BALANCE) {
-		ilb_group = sd->groups;
-
-		do {
-			if (is_semi_idle_group(ilb_group))
-				return cpumask_first(nohz.ilb_grp_nohz_mask);
-
-			ilb_group = ilb_group->next;
-
-		} while (ilb_group != sd->groups);
-	}
-
-out_done:
-	return cpumask_first(nohz.cpu_mask);
-}
-#else /*  (CONFIG_SCHED_MC || CONFIG_SCHED_SMT) */
-static inline int find_new_ilb(int call_cpu)
-{
-	return cpumask_first(nohz.cpu_mask);
-}
-#endif
-
-/*
- * This routine will try to nominate the ilb (idle load balancing)
- * owner among the cpus whose ticks are stopped. ilb owner will do the idle
- * load balancing on behalf of all those cpus. If all the cpus in the system
- * go into this tickless mode, then there will be no ilb owner (as there is
- * no need for one) and all the cpus will sleep till the next wakeup event
- * arrives...
- *
- * For the ilb owner, tick is not stopped. And this tick will be used
- * for idle load balancing. ilb owner will still be part of
- * nohz.cpu_mask..
- *
- * While stopping the tick, this cpu will become the ilb owner if there
- * is no other owner. And will be the owner till that cpu becomes busy
- * or if all cpus in the system stop their ticks at which point
- * there is no need for ilb owner.
- *
- * When the ilb owner becomes busy, it nominates another owner, during the
- * next busy scheduler_tick()
- */
-int select_nohz_load_balancer(int stop_tick)
-{
-	int cpu = smp_processor_id();
-
-	if (stop_tick) {
-		cpu_rq(cpu)->in_nohz_recently = 1;
-
-		if (!cpu_active(cpu)) {
-			if (atomic_read(&nohz.load_balancer) != cpu)
-				return 0;
-
-			/*
-			 * If we are going offline and still the leader,
-			 * give up!
-			 */
-			if (atomic_cmpxchg(&nohz.load_balancer, cpu, -1) != cpu)
-				BUG();
-
-			return 0;
-		}
-
-		cpumask_set_cpu(cpu, nohz.cpu_mask);
-
-		/* time for ilb owner also to sleep */
-		if (cpumask_weight(nohz.cpu_mask) == num_active_cpus()) {
-			if (atomic_read(&nohz.load_balancer) == cpu)
-				atomic_set(&nohz.load_balancer, -1);
-			return 0;
-		}
-
-		if (atomic_read(&nohz.load_balancer) == -1) {
-			/* make me the ilb owner */
-			if (atomic_cmpxchg(&nohz.load_balancer, -1, cpu) == -1)
-				return 1;
-		} else if (atomic_read(&nohz.load_balancer) == cpu) {
-			int new_ilb;
-
-			if (!(sched_smt_power_savings ||
-						sched_mc_power_savings))
-				return 1;
-			/*
-			 * Check to see if there is a more power-efficient
-			 * ilb.
-			 */
-			new_ilb = find_new_ilb(cpu);
-			if (new_ilb < nr_cpu_ids && new_ilb != cpu) {
-				atomic_set(&nohz.load_balancer, -1);
-				resched_cpu(new_ilb);
-				return 0;
-			}
-			return 1;
-		}
-	} else {
-		if (!cpumask_test_cpu(cpu, nohz.cpu_mask))
-			return 0;
-
-		cpumask_clear_cpu(cpu, nohz.cpu_mask);
-
-		if (atomic_read(&nohz.load_balancer) == cpu)
-			if (atomic_cmpxchg(&nohz.load_balancer, cpu, -1) != cpu)
-				BUG();
-	}
-	return 0;
-}
-#endif
-
-static DEFINE_SPINLOCK(balancing);
-
-/*
- * It checks each scheduling domain to see if it is due to be balanced,
- * and initiates a balancing operation if so.
- *
- * Balancing parameters are set up in arch_init_sched_domains.
- */
-static void rebalance_domains(int cpu, enum cpu_idle_type idle)
-{
-	int balance = 1;
-	struct rq *rq = cpu_rq(cpu);
-	unsigned long interval;
-	struct sched_domain *sd;
-	/* Earliest time when we have to do rebalance again */
-	unsigned long next_balance = jiffies + 60*HZ;
-	int update_next_balance = 0;
-	int need_serialize;
-
-	for_each_domain(cpu, sd) {
-		if (!(sd->flags & SD_LOAD_BALANCE))
-			continue;
-
-		interval = sd->balance_interval;
-		if (idle != CPU_IDLE)
-			interval *= sd->busy_factor;
-
-		/* scale ms to jiffies */
-		interval = msecs_to_jiffies(interval);
-		if (unlikely(!interval))
-			interval = 1;
-		if (interval > HZ*NR_CPUS/10)
-			interval = HZ*NR_CPUS/10;
-
-		need_serialize = sd->flags & SD_SERIALIZE;
-
-		if (need_serialize) {
-			if (!spin_trylock(&balancing))
-				goto out;
-		}
-
-		if (time_after_eq(jiffies, sd->last_balance + interval)) {
-			if (load_balance(cpu, rq, sd, idle, &balance)) {
-				/*
-				 * We've pulled tasks over so either we're no
-				 * longer idle, or one of our SMT siblings is
-				 * not idle.
-				 */
-				idle = CPU_NOT_IDLE;
-			}
-			sd->last_balance = jiffies;
-		}
-		if (need_serialize)
-			spin_unlock(&balancing);
-out:
-		if (time_after(next_balance, sd->last_balance + interval)) {
-			next_balance = sd->last_balance + interval;
-			update_next_balance = 1;
-		}
-
-		/*
-		 * Stop the load balance at this level. There is another
-		 * CPU in our sched group which is doing load balancing more
-		 * actively.
-		 */
-		if (!balance)
-			break;
-	}
-
-	/*
-	 * next_balance will be updated only when there is a need.
-	 * When the cpu is attached to null domain for ex, it will not be
-	 * updated.
-	 */
-	if (likely(update_next_balance))
-		rq->next_balance = next_balance;
-}
-
-/*
- * run_rebalance_domains is triggered when needed from the scheduler tick.
- * In CONFIG_NO_HZ case, the idle load balance owner will do the
- * rebalancing for all the cpus for whom scheduler ticks are stopped.
- */
-static void run_rebalance_domains(struct softirq_action *h)
-{
-	int this_cpu = smp_processor_id();
-	struct rq *this_rq = cpu_rq(this_cpu);
-	enum cpu_idle_type idle = this_rq->idle_at_tick ?
-						CPU_IDLE : CPU_NOT_IDLE;
-
-	rebalance_domains(this_cpu, idle);
-
-#ifdef CONFIG_NO_HZ
-	/*
-	 * If this cpu is the owner for idle load balancing, then do the
-	 * balancing on behalf of the other idle cpus whose ticks are
-	 * stopped.
-	 */
-	if (this_rq->idle_at_tick &&
-	    atomic_read(&nohz.load_balancer) == this_cpu) {
-		struct rq *rq;
-		int balance_cpu;
-
-		for_each_cpu(balance_cpu, nohz.cpu_mask) {
-			if (balance_cpu == this_cpu)
-				continue;
-
-			/*
-			 * If this cpu gets work to do, stop the load balancing
-			 * work being done for other cpus. Next load
-			 * balancing owner will pick it up.
-			 */
-			if (need_resched())
-				break;
-
-			rebalance_domains(balance_cpu, CPU_IDLE);
-
-			rq = cpu_rq(balance_cpu);
-			if (time_after(this_rq->next_balance, rq->next_balance))
-				this_rq->next_balance = rq->next_balance;
-		}
-	}
-#endif
-}
-
-static inline int on_null_domain(int cpu)
-{
-	return !rcu_dereference(cpu_rq(cpu)->sd);
-}
-
-/*
- * Trigger the SCHED_SOFTIRQ if it is time to do periodic load balancing.
- *
- * In case of CONFIG_NO_HZ, this is the place where we nominate a new
- * idle load balancing owner or decide to stop the periodic load balancing,
- * if the whole system is idle.
- */
-static inline void trigger_load_balance(struct rq *rq, int cpu)
-{
-#ifdef CONFIG_NO_HZ
-	/*
-	 * If we were in the nohz mode recently and busy at the current
-	 * scheduler tick, then check if we need to nominate new idle
-	 * load balancer.
-	 */
-	if (rq->in_nohz_recently && !rq->idle_at_tick) {
-		rq->in_nohz_recently = 0;
-
-		if (atomic_read(&nohz.load_balancer) == cpu) {
-			cpumask_clear_cpu(cpu, nohz.cpu_mask);
-			atomic_set(&nohz.load_balancer, -1);
-		}
-
-		if (atomic_read(&nohz.load_balancer) == -1) {
-			int ilb = find_new_ilb(cpu);
-
-			if (ilb < nr_cpu_ids)
-				resched_cpu(ilb);
-		}
-	}
-
-	/*
-	 * If this cpu is idle and doing idle load balancing for all the
-	 * cpus with ticks stopped, is it time for that to stop?
-	 */
-	if (rq->idle_at_tick && atomic_read(&nohz.load_balancer) == cpu &&
-	    cpumask_weight(nohz.cpu_mask) == num_online_cpus()) {
-		resched_cpu(cpu);
-		return;
-	}
-
-	/*
-	 * If this cpu is idle and the idle load balancing is done by
-	 * someone else, then no need raise the SCHED_SOFTIRQ
-	 */
-	if (rq->idle_at_tick && atomic_read(&nohz.load_balancer) != cpu &&
-	    cpumask_test_cpu(cpu, nohz.cpu_mask))
-		return;
-#endif
-	/* Don't need to rebalance while attached to NULL domain */
-	if (time_after_eq(jiffies, rq->next_balance) &&
-	    likely(!on_null_domain(cpu)))
-		raise_softirq(SCHED_SOFTIRQ);
-}
-
-#else	/* CONFIG_SMP */
-
-/*
- * on UP we do not need to balance between CPUs:
- */
-static inline void idle_balance(int cpu, struct rq *rq)
-{
-}
-
 #endif
 
 DEFINE_PER_CPU(struct kernel_stat, kstat);
@@ -5568,7 +3790,7 @@ int mutex_spin_on_owner(struct mutex *lock, struct thread_info *owner)
 	 * the mutex owner just released it and exited.
 	 */
 	if (probe_kernel_address(&owner->cpu, cpu))
-		goto out;
+		return 0;
 #else
 	cpu = owner->cpu;
 #endif
@@ -5578,14 +3800,14 @@ int mutex_spin_on_owner(struct mutex *lock, struct thread_info *owner)
 	 * the cpu field may no longer be valid.
 	 */
 	if (cpu >= nr_cpumask_bits)
-		goto out;
+		return 0;
 
 	/*
 	 * We need to validate that we can do a
 	 * get_cpu() and that we have the percpu area.
 	 */
 	if (!cpu_online(cpu))
-		goto out;
+		return 0;
 
 	rq = cpu_rq(cpu);
 
@@ -5604,7 +3826,7 @@ int mutex_spin_on_owner(struct mutex *lock, struct thread_info *owner)
 
 		cpu_relax();
 	}
-out:
+
 	return 1;
 }
 #endif
@@ -6049,7 +4271,7 @@ void rt_mutex_setprio(struct task_struct *p, int prio)
 	unsigned long flags;
 	int oldprio, on_rq, running;
 	struct rq *rq;
-	const struct sched_class *prev_class = p->sched_class;
+	const struct sched_class *prev_class;
 
 	BUG_ON(prio < 0 || prio > MAX_PRIO);
 
@@ -6057,6 +4279,7 @@ void rt_mutex_setprio(struct task_struct *p, int prio)
 	update_rq_clock(rq);
 
 	oldprio = p->prio;
+	prev_class = p->sched_class;
 	on_rq = p->se.on_rq;
 	running = task_current(rq, p);
 	if (on_rq)
@@ -6074,7 +4297,7 @@ void rt_mutex_setprio(struct task_struct *p, int prio)
 	if (running)
 		p->sched_class->set_curr_task(rq);
 	if (on_rq) {
-		enqueue_task(rq, p, 0);
+		enqueue_task(rq, p, 0, oldprio < prio);
 
 		check_class_changed(rq, p, prev_class, oldprio, running);
 	}
@@ -6118,7 +4341,7 @@ void set_user_nice(struct task_struct *p, long nice)
 	delta = p->prio - old_prio;
 
 	if (on_rq) {
-		enqueue_task(rq, p, 0);
+		enqueue_task(rq, p, 0, false);
 		/*
 		 * If the task increased its priority or is running and
 		 * lowered its priority, then reschedule its CPU:
@@ -6141,7 +4364,7 @@ int can_nice(const struct task_struct *p, const int nice)
 	/* convert nice value [19,-20] to rlimit style value [1,40] */
 	int nice_rlim = 20 - nice;
 
-	return (nice_rlim <= p->signal->rlim[RLIMIT_NICE].rlim_cur ||
+	return (nice_rlim <= task_rlimit(p, RLIMIT_NICE) ||
 		capable(CAP_SYS_NICE));
 }
 
@@ -6276,7 +4499,7 @@ static int __sched_setscheduler(struct task_struct *p, int policy,
 {
 	int retval, oldprio, oldpolicy = -1, on_rq, running;
 	unsigned long flags;
-	const struct sched_class *prev_class = p->sched_class;
+	const struct sched_class *prev_class;
 	struct rq *rq;
 	int reset_on_fork;
 
@@ -6318,7 +4541,7 @@ recheck:
 
 			if (!lock_task_sighand(p, &flags))
 				return -ESRCH;
-			rlim_rtprio = p->signal->rlim[RLIMIT_RTPRIO].rlim_cur;
+			rlim_rtprio = task_rlimit(p, RLIMIT_RTPRIO);
 			unlock_task_sighand(p, &flags);
 
 			/* can't set/change the rt policy */
@@ -6390,6 +4613,7 @@ recheck:
 	p->sched_reset_on_fork = reset_on_fork;
 
 	oldprio = p->prio;
+	prev_class = p->sched_class;
 	__setscheduler(rq, p, policy, param->sched_priority);
 
 	if (running)
@@ -6689,7 +4913,9 @@ SYSCALL_DEFINE3(sched_getaffinity, pid_t, pid, unsigned int, len,
 	int ret;
 	cpumask_var_t mask;
 
-	if (len < cpumask_size())
+	if ((len * BITS_PER_BYTE) < nr_cpu_ids)
+		return -EINVAL;
+	if (len & (sizeof(unsigned long)-1))
 		return -EINVAL;
 
 	if (!alloc_cpumask_var(&mask, GFP_KERNEL))
@@ -6697,10 +4923,12 @@ SYSCALL_DEFINE3(sched_getaffinity, pid_t, pid, unsigned int, len,
 
 	ret = sched_getaffinity(pid, mask);
 	if (ret == 0) {
-		if (copy_to_user(user_mask_ptr, mask, cpumask_size()))
+		size_t retlen = min_t(size_t, len, cpumask_size());
+
+		if (copy_to_user(user_mask_ptr, mask, retlen))
 			ret = -EFAULT;
 		else
-			ret = cpumask_size();
+			ret = retlen;
 	}
 	free_cpumask_var(mask);
 
@@ -7140,23 +5368,8 @@ int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask)
 	struct rq *rq;
 	int ret = 0;
 
-	/*
-	 * Since we rely on wake-ups to migrate sleeping tasks, don't change
-	 * the ->cpus_allowed mask from under waking tasks, which would be
-	 * possible when we change rq->lock in ttwu(), so synchronize against
-	 * TASK_WAKING to avoid that.
-	 */
-again:
-	while (p->state == TASK_WAKING)
-		cpu_relax();
-
 	rq = task_rq_lock(p, &flags);
 
-	if (p->state == TASK_WAKING) {
-		task_rq_unlock(rq, &flags);
-		goto again;
-	}
-
 	if (!cpumask_intersects(new_mask, cpu_active_mask)) {
 		ret = -EINVAL;
 		goto out;
@@ -7185,7 +5398,7 @@ again:
 
 		get_task_struct(mt);
 		task_rq_unlock(rq, &flags);
-		wake_up_process(rq->migration_thread);
+		wake_up_process(mt);
 		put_task_struct(mt);
 		wait_for_completion(&req.done);
 		tlb_migrate_finish(p->mm);
@@ -9208,11 +7421,13 @@ static ssize_t sched_power_savings_store(const char *buf, size_t count, int smt)
 
 #ifdef CONFIG_SCHED_MC
 static ssize_t sched_mc_power_savings_show(struct sysdev_class *class,
+					   struct sysdev_class_attribute *attr,
 					   char *page)
 {
 	return sprintf(page, "%u\n", sched_mc_power_savings);
 }
 static ssize_t sched_mc_power_savings_store(struct sysdev_class *class,
+					    struct sysdev_class_attribute *attr,
 					    const char *buf, size_t count)
 {
 	return sched_power_savings_store(buf, count, 0);
@@ -9224,11 +7439,13 @@ static SYSDEV_CLASS_ATTR(sched_mc_power_savings, 0644,
 
 #ifdef CONFIG_SCHED_SMT
 static ssize_t sched_smt_power_savings_show(struct sysdev_class *dev,
+					    struct sysdev_class_attribute *attr,
 					    char *page)
 {
 	return sprintf(page, "%u\n", sched_smt_power_savings);
 }
 static ssize_t sched_smt_power_savings_store(struct sysdev_class *dev,
+					     struct sysdev_class_attribute *attr,
 					     const char *buf, size_t count)
 {
 	return sched_power_savings_store(buf, count, 1);
@@ -9443,7 +7660,6 @@ static void init_tg_rt_entry(struct task_group *tg, struct rt_rq *rt_rq,
 	tg->rt_rq[cpu] = rt_rq;
 	init_rt_rq(rt_rq, rq);
 	rt_rq->tg = tg;
-	rt_rq->rt_se = rt_se;
 	rt_rq->rt_runtime = tg->rt_bandwidth.rt_runtime;
 	if (add)
 		list_add(&rt_rq->leaf_rt_rq_list, &rq->leaf_rt_rq_list);
@@ -9474,9 +7690,6 @@ void __init sched_init(void)
 #ifdef CONFIG_RT_GROUP_SCHED
 	alloc_size += 2 * nr_cpu_ids * sizeof(void **);
 #endif
-#ifdef CONFIG_USER_SCHED
-	alloc_size *= 2;
-#endif
 #ifdef CONFIG_CPUMASK_OFFSTACK
 	alloc_size += num_possible_cpus() * cpumask_size();
 #endif
@@ -9490,13 +7703,6 @@ void __init sched_init(void)
 		init_task_group.cfs_rq = (struct cfs_rq **)ptr;
 		ptr += nr_cpu_ids * sizeof(void **);
 
-#ifdef CONFIG_USER_SCHED
-		root_task_group.se = (struct sched_entity **)ptr;
-		ptr += nr_cpu_ids * sizeof(void **);
-
-		root_task_group.cfs_rq = (struct cfs_rq **)ptr;
-		ptr += nr_cpu_ids * sizeof(void **);
-#endif /* CONFIG_USER_SCHED */
 #endif /* CONFIG_FAIR_GROUP_SCHED */
 #ifdef CONFIG_RT_GROUP_SCHED
 		init_task_group.rt_se = (struct sched_rt_entity **)ptr;
@@ -9505,13 +7711,6 @@ void __init sched_init(void)
 		init_task_group.rt_rq = (struct rt_rq **)ptr;
 		ptr += nr_cpu_ids * sizeof(void **);
 
-#ifdef CONFIG_USER_SCHED
-		root_task_group.rt_se = (struct sched_rt_entity **)ptr;
-		ptr += nr_cpu_ids * sizeof(void **);
-
-		root_task_group.rt_rq = (struct rt_rq **)ptr;
-		ptr += nr_cpu_ids * sizeof(void **);
-#endif /* CONFIG_USER_SCHED */
 #endif /* CONFIG_RT_GROUP_SCHED */
 #ifdef CONFIG_CPUMASK_OFFSTACK
 		for_each_possible_cpu(i) {
@@ -9531,22 +7730,13 @@ void __init sched_init(void)
 #ifdef CONFIG_RT_GROUP_SCHED
 	init_rt_bandwidth(&init_task_group.rt_bandwidth,
 			global_rt_period(), global_rt_runtime());
-#ifdef CONFIG_USER_SCHED
-	init_rt_bandwidth(&root_task_group.rt_bandwidth,
-			global_rt_period(), RUNTIME_INF);
-#endif /* CONFIG_USER_SCHED */
 #endif /* CONFIG_RT_GROUP_SCHED */
 
-#ifdef CONFIG_GROUP_SCHED
+#ifdef CONFIG_CGROUP_SCHED
 	list_add(&init_task_group.list, &task_groups);
 	INIT_LIST_HEAD(&init_task_group.children);
 
-#ifdef CONFIG_USER_SCHED
-	INIT_LIST_HEAD(&root_task_group.children);
-	init_task_group.parent = &root_task_group;
-	list_add(&init_task_group.siblings, &root_task_group.children);
-#endif /* CONFIG_USER_SCHED */
-#endif /* CONFIG_GROUP_SCHED */
+#endif /* CONFIG_CGROUP_SCHED */
 
 #if defined CONFIG_FAIR_GROUP_SCHED && defined CONFIG_SMP
 	update_shares_data = __alloc_percpu(nr_cpu_ids * sizeof(unsigned long),
@@ -9586,25 +7776,6 @@ void __init sched_init(void)
 		 * directly in rq->cfs (i.e init_task_group->se[] = NULL).
 		 */
 		init_tg_cfs_entry(&init_task_group, &rq->cfs, NULL, i, 1, NULL);
-#elif defined CONFIG_USER_SCHED
-		root_task_group.shares = NICE_0_LOAD;
-		init_tg_cfs_entry(&root_task_group, &rq->cfs, NULL, i, 0, NULL);
-		/*
-		 * In case of task-groups formed thr' the user id of tasks,
-		 * init_task_group represents tasks belonging to root user.
-		 * Hence it forms a sibling of all subsequent groups formed.
-		 * In this case, init_task_group gets only a fraction of overall
-		 * system cpu resource, based on the weight assigned to root
-		 * user's cpu share (INIT_TASK_GROUP_LOAD). This is accomplished
-		 * by letting tasks of init_task_group sit in a separate cfs_rq
-		 * (init_tg_cfs_rq) and having one entity represent this group of
-		 * tasks in rq->cfs (i.e init_task_group->se[] != NULL).
-		 */
-		init_tg_cfs_entry(&init_task_group,
-				&per_cpu(init_tg_cfs_rq, i),
-				&per_cpu(init_sched_entity, i), i, 1,
-				root_task_group.se[i]);
-
 #endif
 #endif /* CONFIG_FAIR_GROUP_SCHED */
 
@@ -9613,12 +7784,6 @@ void __init sched_init(void)
 		INIT_LIST_HEAD(&rq->leaf_rt_rq_list);
 #ifdef CONFIG_CGROUP_SCHED
 		init_tg_rt_entry(&init_task_group, &rq->rt, NULL, i, 1, NULL);
-#elif defined CONFIG_USER_SCHED
-		init_tg_rt_entry(&root_task_group, &rq->rt, NULL, i, 0, NULL);
-		init_tg_rt_entry(&init_task_group,
-				&per_cpu(init_rt_rq_var, i),
-				&per_cpu(init_sched_rt_entity, i), i, 1,
-				root_task_group.rt_se[i]);
 #endif
 #endif
 
@@ -9703,7 +7868,7 @@ static inline int preempt_count_equals(int preempt_offset)
 	return (nested == PREEMPT_INATOMIC_BASE + preempt_offset);
 }
 
-void __might_sleep(char *file, int line, int preempt_offset)
+void __might_sleep(const char *file, int line, int preempt_offset)
 {
 #ifdef in_atomic
 	static unsigned long prev_jiffy;	/* ratelimiting */
@@ -10014,7 +8179,7 @@ static inline void unregister_rt_sched_group(struct task_group *tg, int cpu)
 }
 #endif /* CONFIG_RT_GROUP_SCHED */
 
-#ifdef CONFIG_GROUP_SCHED
+#ifdef CONFIG_CGROUP_SCHED
 static void free_sched_group(struct task_group *tg)
 {
 	free_fair_sched_group(tg);
@@ -10119,11 +8284,11 @@ void sched_move_task(struct task_struct *tsk)
 	if (unlikely(running))
 		tsk->sched_class->set_curr_task(rq);
 	if (on_rq)
-		enqueue_task(rq, tsk, 0);
+		enqueue_task(rq, tsk, 0, false);
 
 	task_rq_unlock(rq, &flags);
 }
-#endif /* CONFIG_GROUP_SCHED */
+#endif /* CONFIG_CGROUP_SCHED */
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
 static void __set_se_shares(struct sched_entity *se, unsigned long shares)
@@ -10265,13 +8430,6 @@ static int tg_schedulable(struct task_group *tg, void *data)
 		runtime = d->rt_runtime;
 	}
 
-#ifdef CONFIG_USER_SCHED
-	if (tg == &root_task_group) {
-		period = global_rt_period();
-		runtime = global_rt_runtime();
-	}
-#endif
-
 	/*
 	 * Cannot have more runtime than the period.
 	 */
@@ -10674,7 +8832,7 @@ struct cgroup_subsys cpu_cgroup_subsys = {
 struct cpuacct {
 	struct cgroup_subsys_state css;
 	/* cpuusage holds pointer to a u64-type object on every cpu */
-	u64 *cpuusage;
+	u64 __percpu *cpuusage;
 	struct percpu_counter cpustat[CPUACCT_STAT_NSTATS];
 	struct cpuacct *parent;
 };
@@ -10891,12 +9049,30 @@ static void cpuacct_charge(struct task_struct *tsk, u64 cputime)
 }
 
 /*
+ * When CONFIG_VIRT_CPU_ACCOUNTING is enabled one jiffy can be very large
+ * in cputime_t units. As a result, cpuacct_update_stats calls
+ * percpu_counter_add with values large enough to always overflow the
+ * per cpu batch limit causing bad SMP scalability.
+ *
+ * To fix this we scale percpu_counter_batch by cputime_one_jiffy so we
+ * batch the same amount of time with CONFIG_VIRT_CPU_ACCOUNTING disabled
+ * and enabled. We cap it at INT_MAX which is the largest allowed batch value.
+ */
+#ifdef CONFIG_SMP
+#define CPUACCT_BATCH	\
+	min_t(long, percpu_counter_batch * cputime_one_jiffy, INT_MAX)
+#else
+#define CPUACCT_BATCH	0
+#endif
+
+/*
  * Charge the system/user time to the task's accounting group.
  */
 static void cpuacct_update_stats(struct task_struct *tsk,
 		enum cpuacct_stat_index idx, cputime_t val)
 {
 	struct cpuacct *ca;
+	int batch = CPUACCT_BATCH;
 
 	if (unlikely(!cpuacct_subsys.active))
 		return;
@@ -10905,7 +9081,7 @@ static void cpuacct_update_stats(struct task_struct *tsk,
 	ca = task_ca(tsk);
 
 	do {
-		percpu_counter_add(&ca->cpustat[idx], val);
+		__percpu_counter_add(&ca->cpustat[idx], val, batch);
 		ca = ca->parent;
 	} while (ca);
 	rcu_read_unlock();
diff --git a/kernel/sched_cpupri.c b/kernel/sched_cpupri.c
index 597b33099df..e6871cb3fc8 100644
--- a/kernel/sched_cpupri.c
+++ b/kernel/sched_cpupri.c
@@ -27,6 +27,7 @@
  *  of the License.
  */
 
+#include <linux/gfp.h>
 #include "sched_cpupri.h"
 
 /* Convert between a 140 based task->prio, and our 102 based cpupri */
@@ -47,9 +48,7 @@ static int convert_prio(int prio)
 }
 
 #define for_each_cpupri_active(array, idx)                    \
-  for (idx = find_first_bit(array, CPUPRI_NR_PRIORITIES);     \
-       idx < CPUPRI_NR_PRIORITIES;                            \
-       idx = find_next_bit(array, CPUPRI_NR_PRIORITIES, idx+1))
+	for_each_set_bit(idx, array, CPUPRI_NR_PRIORITIES)
 
 /**
  * cpupri_find - find the best (lowest-pri) CPU in the system
@@ -58,7 +57,7 @@ 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_debug.c b/kernel/sched_debug.c
index 67f95aada4b..19be00ba612 100644
--- a/kernel/sched_debug.c
+++ b/kernel/sched_debug.c
@@ -114,7 +114,9 @@ print_task(struct seq_file *m, struct rq *rq, struct task_struct *p)
 	{
 		char path[64];
 
+		rcu_read_lock();
 		cgroup_path(task_group(p)->css.cgroup, path, sizeof(path));
+		rcu_read_unlock();
 		SEQ_printf(m, " %s", path);
 	}
 #endif
@@ -518,8 +520,4 @@ void proc_sched_set_task(struct task_struct *p)
 	p->se.nr_wakeups_idle			= 0;
 	p->sched_info.bkl_count			= 0;
 #endif
-	p->se.sum_exec_runtime			= 0;
-	p->se.prev_sum_exec_runtime		= 0;
-	p->nvcsw				= 0;
-	p->nivcsw				= 0;
 }
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 8fe7ee81c55..5a5ea2cd924 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -1053,7 +1053,8 @@ static inline void hrtick_update(struct rq *rq)
  * increased. Here we update the fair scheduling stats and
  * then put the task into the rbtree:
  */
-static void enqueue_task_fair(struct rq *rq, struct task_struct *p, int wakeup)
+static void
+enqueue_task_fair(struct rq *rq, struct task_struct *p, int wakeup, bool head)
 {
 	struct cfs_rq *cfs_rq;
 	struct sched_entity *se = &p->se;
@@ -1815,57 +1816,164 @@ static void put_prev_task_fair(struct rq *rq, struct task_struct *prev)
  */
 
 /*
- * Load-balancing iterator. Note: while the runqueue stays locked
- * during the whole iteration, the current task might be
- * dequeued so the iterator has to be dequeue-safe. Here we
- * achieve that by always pre-iterating before returning
- * the current task:
+ * pull_task - move a task from a remote runqueue to the local runqueue.
+ * Both runqueues must be locked.
  */
-static struct task_struct *
-__load_balance_iterator(struct cfs_rq *cfs_rq, struct list_head *next)
+static void pull_task(struct rq *src_rq, struct task_struct *p,
+		      struct rq *this_rq, int this_cpu)
 {
-	struct task_struct *p = NULL;
-	struct sched_entity *se;
+	deactivate_task(src_rq, p, 0);
+	set_task_cpu(p, this_cpu);
+	activate_task(this_rq, p, 0);
+	check_preempt_curr(this_rq, p, 0);
+}
 
-	if (next == &cfs_rq->tasks)
-		return NULL;
+/*
+ * can_migrate_task - may task p from runqueue rq be migrated to this_cpu?
+ */
+static
+int can_migrate_task(struct task_struct *p, struct rq *rq, int this_cpu,
+		     struct sched_domain *sd, enum cpu_idle_type idle,
+		     int *all_pinned)
+{
+	int tsk_cache_hot = 0;
+	/*
+	 * We do not migrate tasks that are:
+	 * 1) running (obviously), or
+	 * 2) cannot be migrated to this CPU due to cpus_allowed, or
+	 * 3) are cache-hot on their current CPU.
+	 */
+	if (!cpumask_test_cpu(this_cpu, &p->cpus_allowed)) {
+		schedstat_inc(p, se.nr_failed_migrations_affine);
+		return 0;
+	}
+	*all_pinned = 0;
 
-	se = list_entry(next, struct sched_entity, group_node);
-	p = task_of(se);
-	cfs_rq->balance_iterator = next->next;
+	if (task_running(rq, p)) {
+		schedstat_inc(p, se.nr_failed_migrations_running);
+		return 0;
+	}
 
-	return p;
-}
+	/*
+	 * Aggressive migration if:
+	 * 1) task is cache cold, or
+	 * 2) too many balance attempts have failed.
+	 */
 
-static struct task_struct *load_balance_start_fair(void *arg)
-{
-	struct cfs_rq *cfs_rq = arg;
+	tsk_cache_hot = task_hot(p, rq->clock, sd);
+	if (!tsk_cache_hot ||
+		sd->nr_balance_failed > sd->cache_nice_tries) {
+#ifdef CONFIG_SCHEDSTATS
+		if (tsk_cache_hot) {
+			schedstat_inc(sd, lb_hot_gained[idle]);
+			schedstat_inc(p, se.nr_forced_migrations);
+		}
+#endif
+		return 1;
+	}
 
-	return __load_balance_iterator(cfs_rq, cfs_rq->tasks.next);
+	if (tsk_cache_hot) {
+		schedstat_inc(p, se.nr_failed_migrations_hot);
+		return 0;
+	}
+	return 1;
 }
 
-static struct task_struct *load_balance_next_fair(void *arg)
+/*
+ * move_one_task tries to move exactly one task from busiest to this_rq, as
+ * part of active balancing operations within "domain".
+ * Returns 1 if successful and 0 otherwise.
+ *
+ * Called with both runqueues locked.
+ */
+static int
+move_one_task(struct rq *this_rq, int this_cpu, struct rq *busiest,
+	      struct sched_domain *sd, enum cpu_idle_type idle)
 {
-	struct cfs_rq *cfs_rq = arg;
+	struct task_struct *p, *n;
+	struct cfs_rq *cfs_rq;
+	int pinned = 0;
+
+	for_each_leaf_cfs_rq(busiest, cfs_rq) {
+		list_for_each_entry_safe(p, n, &cfs_rq->tasks, se.group_node) {
+
+			if (!can_migrate_task(p, busiest, this_cpu,
+						sd, idle, &pinned))
+				continue;
 
-	return __load_balance_iterator(cfs_rq, cfs_rq->balance_iterator);
+			pull_task(busiest, p, this_rq, this_cpu);
+			/*
+			 * Right now, this is only the second place pull_task()
+			 * is called, so we can safely collect pull_task()
+			 * stats here rather than inside pull_task().
+			 */
+			schedstat_inc(sd, lb_gained[idle]);
+			return 1;
+		}
+	}
+
+	return 0;
 }
 
 static unsigned long
-__load_balance_fair(struct rq *this_rq, int this_cpu, struct rq *busiest,
-		unsigned long max_load_move, struct sched_domain *sd,
-		enum cpu_idle_type idle, int *all_pinned, int *this_best_prio,
-		struct cfs_rq *cfs_rq)
+balance_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest,
+	      unsigned long max_load_move, struct sched_domain *sd,
+	      enum cpu_idle_type idle, int *all_pinned,
+	      int *this_best_prio, struct cfs_rq *busiest_cfs_rq)
 {
-	struct rq_iterator cfs_rq_iterator;
+	int loops = 0, pulled = 0, pinned = 0;
+	long rem_load_move = max_load_move;
+	struct task_struct *p, *n;
 
-	cfs_rq_iterator.start = load_balance_start_fair;
-	cfs_rq_iterator.next = load_balance_next_fair;
-	cfs_rq_iterator.arg = cfs_rq;
+	if (max_load_move == 0)
+		goto out;
 
-	return balance_tasks(this_rq, this_cpu, busiest,
-			max_load_move, sd, idle, all_pinned,
-			this_best_prio, &cfs_rq_iterator);
+	pinned = 1;
+
+	list_for_each_entry_safe(p, n, &busiest_cfs_rq->tasks, se.group_node) {
+		if (loops++ > sysctl_sched_nr_migrate)
+			break;
+
+		if ((p->se.load.weight >> 1) > rem_load_move ||
+		    !can_migrate_task(p, busiest, this_cpu, sd, idle, &pinned))
+			continue;
+
+		pull_task(busiest, p, this_rq, this_cpu);
+		pulled++;
+		rem_load_move -= p->se.load.weight;
+
+#ifdef CONFIG_PREEMPT
+		/*
+		 * NEWIDLE balancing is a source of latency, so preemptible
+		 * kernels will stop after the first task is pulled to minimize
+		 * the critical section.
+		 */
+		if (idle == CPU_NEWLY_IDLE)
+			break;
+#endif
+
+		/*
+		 * We only want to steal up to the prescribed amount of
+		 * weighted load.
+		 */
+		if (rem_load_move <= 0)
+			break;
+
+		if (p->prio < *this_best_prio)
+			*this_best_prio = p->prio;
+	}
+out:
+	/*
+	 * Right now, this is one of only two places pull_task() is called,
+	 * so we can safely collect pull_task() stats here rather than
+	 * inside pull_task().
+	 */
+	schedstat_add(sd, lb_gained[idle], pulled);
+
+	if (all_pinned)
+		*all_pinned = pinned;
+
+	return max_load_move - rem_load_move;
 }
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
@@ -1897,9 +2005,9 @@ load_balance_fair(struct rq *this_rq, int this_cpu, struct rq *busiest,
 		rem_load = (u64)rem_load_move * busiest_weight;
 		rem_load = div_u64(rem_load, busiest_h_load + 1);
 
-		moved_load = __load_balance_fair(this_rq, this_cpu, busiest,
+		moved_load = balance_tasks(this_rq, this_cpu, busiest,
 				rem_load, sd, idle, all_pinned, this_best_prio,
-				tg->cfs_rq[busiest_cpu]);
+				busiest_cfs_rq);
 
 		if (!moved_load)
 			continue;
@@ -1922,35 +2030,1509 @@ load_balance_fair(struct rq *this_rq, int this_cpu, struct rq *busiest,
 		  struct sched_domain *sd, enum cpu_idle_type idle,
 		  int *all_pinned, int *this_best_prio)
 {
-	return __load_balance_fair(this_rq, this_cpu, busiest,
+	return balance_tasks(this_rq, this_cpu, busiest,
 			max_load_move, sd, idle, all_pinned,
 			this_best_prio, &busiest->cfs);
 }
 #endif
 
-static int
-move_one_task_fair(struct rq *this_rq, int this_cpu, struct rq *busiest,
-		   struct sched_domain *sd, enum cpu_idle_type idle)
+/*
+ * move_tasks tries to move up to max_load_move weighted load from busiest to
+ * this_rq, as part of a balancing operation within domain "sd".
+ * Returns 1 if successful and 0 otherwise.
+ *
+ * Called with both runqueues locked.
+ */
+static int move_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest,
+		      unsigned long max_load_move,
+		      struct sched_domain *sd, enum cpu_idle_type idle,
+		      int *all_pinned)
 {
-	struct cfs_rq *busy_cfs_rq;
-	struct rq_iterator cfs_rq_iterator;
+	unsigned long total_load_moved = 0, load_moved;
+	int this_best_prio = this_rq->curr->prio;
 
-	cfs_rq_iterator.start = load_balance_start_fair;
-	cfs_rq_iterator.next = load_balance_next_fair;
+	do {
+		load_moved = load_balance_fair(this_rq, this_cpu, busiest,
+				max_load_move - total_load_moved,
+				sd, idle, all_pinned, &this_best_prio);
 
-	for_each_leaf_cfs_rq(busiest, busy_cfs_rq) {
+		total_load_moved += load_moved;
+
+#ifdef CONFIG_PREEMPT
 		/*
-		 * pass busy_cfs_rq argument into
-		 * load_balance_[start|next]_fair iterators
+		 * NEWIDLE balancing is a source of latency, so preemptible
+		 * kernels will stop after the first task is pulled to minimize
+		 * the critical section.
 		 */
-		cfs_rq_iterator.arg = busy_cfs_rq;
-		if (iter_move_one_task(this_rq, this_cpu, busiest, sd, idle,
-				       &cfs_rq_iterator))
-		    return 1;
+		if (idle == CPU_NEWLY_IDLE && this_rq->nr_running)
+			break;
+
+		if (raw_spin_is_contended(&this_rq->lock) ||
+				raw_spin_is_contended(&busiest->lock))
+			break;
+#endif
+	} while (load_moved && max_load_move > total_load_moved);
+
+	return total_load_moved > 0;
+}
+
+/********** Helpers for find_busiest_group ************************/
+/*
+ * sd_lb_stats - Structure to store the statistics of a sched_domain
+ * 		during load balancing.
+ */
+struct sd_lb_stats {
+	struct sched_group *busiest; /* Busiest group in this sd */
+	struct sched_group *this;  /* Local group in this sd */
+	unsigned long total_load;  /* Total load of all groups in sd */
+	unsigned long total_pwr;   /*	Total power of all groups in sd */
+	unsigned long avg_load;	   /* Average load across all groups in sd */
+
+	/** Statistics of this group */
+	unsigned long this_load;
+	unsigned long this_load_per_task;
+	unsigned long this_nr_running;
+
+	/* Statistics of the busiest group */
+	unsigned long max_load;
+	unsigned long busiest_load_per_task;
+	unsigned long busiest_nr_running;
+	unsigned long busiest_group_capacity;
+
+	int group_imb; /* Is there imbalance in this sd */
+#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT)
+	int power_savings_balance; /* Is powersave balance needed for this sd */
+	struct sched_group *group_min; /* Least loaded group in sd */
+	struct sched_group *group_leader; /* Group which relieves group_min */
+	unsigned long min_load_per_task; /* load_per_task in group_min */
+	unsigned long leader_nr_running; /* Nr running of group_leader */
+	unsigned long min_nr_running; /* Nr running of group_min */
+#endif
+};
+
+/*
+ * sg_lb_stats - stats of a sched_group required for load_balancing
+ */
+struct sg_lb_stats {
+	unsigned long avg_load; /*Avg load across the CPUs of the group */
+	unsigned long group_load; /* Total load over the CPUs of the group */
+	unsigned long sum_nr_running; /* Nr tasks running in the group */
+	unsigned long sum_weighted_load; /* Weighted load of group's tasks */
+	unsigned long group_capacity;
+	int group_imb; /* Is there an imbalance in the group ? */
+};
+
+/**
+ * group_first_cpu - Returns the first cpu in the cpumask of a sched_group.
+ * @group: The group whose first cpu is to be returned.
+ */
+static inline unsigned int group_first_cpu(struct sched_group *group)
+{
+	return cpumask_first(sched_group_cpus(group));
+}
+
+/**
+ * get_sd_load_idx - Obtain the load index for a given sched domain.
+ * @sd: The sched_domain whose load_idx is to be obtained.
+ * @idle: The Idle status of the CPU for whose sd load_icx is obtained.
+ */
+static inline int get_sd_load_idx(struct sched_domain *sd,
+					enum cpu_idle_type idle)
+{
+	int load_idx;
+
+	switch (idle) {
+	case CPU_NOT_IDLE:
+		load_idx = sd->busy_idx;
+		break;
+
+	case CPU_NEWLY_IDLE:
+		load_idx = sd->newidle_idx;
+		break;
+	default:
+		load_idx = sd->idle_idx;
+		break;
 	}
 
+	return load_idx;
+}
+
+
+#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT)
+/**
+ * init_sd_power_savings_stats - Initialize power savings statistics for
+ * the given sched_domain, during load balancing.
+ *
+ * @sd: Sched domain whose power-savings statistics are to be initialized.
+ * @sds: Variable containing the statistics for sd.
+ * @idle: Idle status of the CPU at which we're performing load-balancing.
+ */
+static inline void init_sd_power_savings_stats(struct sched_domain *sd,
+	struct sd_lb_stats *sds, enum cpu_idle_type idle)
+{
+	/*
+	 * Busy processors will not participate in power savings
+	 * balance.
+	 */
+	if (idle == CPU_NOT_IDLE || !(sd->flags & SD_POWERSAVINGS_BALANCE))
+		sds->power_savings_balance = 0;
+	else {
+		sds->power_savings_balance = 1;
+		sds->min_nr_running = ULONG_MAX;
+		sds->leader_nr_running = 0;
+	}
+}
+
+/**
+ * update_sd_power_savings_stats - Update the power saving stats for a
+ * sched_domain while performing load balancing.
+ *
+ * @group: sched_group belonging to the sched_domain under consideration.
+ * @sds: Variable containing the statistics of the sched_domain
+ * @local_group: Does group contain the CPU for which we're performing
+ * 		load balancing ?
+ * @sgs: Variable containing the statistics of the group.
+ */
+static inline void update_sd_power_savings_stats(struct sched_group *group,
+	struct sd_lb_stats *sds, int local_group, struct sg_lb_stats *sgs)
+{
+
+	if (!sds->power_savings_balance)
+		return;
+
+	/*
+	 * If the local group is idle or completely loaded
+	 * no need to do power savings balance at this domain
+	 */
+	if (local_group && (sds->this_nr_running >= sgs->group_capacity ||
+				!sds->this_nr_running))
+		sds->power_savings_balance = 0;
+
+	/*
+	 * If a group is already running at full capacity or idle,
+	 * don't include that group in power savings calculations
+	 */
+	if (!sds->power_savings_balance ||
+		sgs->sum_nr_running >= sgs->group_capacity ||
+		!sgs->sum_nr_running)
+		return;
+
+	/*
+	 * Calculate the group which has the least non-idle load.
+	 * This is the group from where we need to pick up the load
+	 * for saving power
+	 */
+	if ((sgs->sum_nr_running < sds->min_nr_running) ||
+	    (sgs->sum_nr_running == sds->min_nr_running &&
+	     group_first_cpu(group) > group_first_cpu(sds->group_min))) {
+		sds->group_min = group;
+		sds->min_nr_running = sgs->sum_nr_running;
+		sds->min_load_per_task = sgs->sum_weighted_load /
+						sgs->sum_nr_running;
+	}
+
+	/*
+	 * Calculate the group which is almost near its
+	 * capacity but still has some space to pick up some load
+	 * from other group and save more power
+	 */
+	if (sgs->sum_nr_running + 1 > sgs->group_capacity)
+		return;
+
+	if (sgs->sum_nr_running > sds->leader_nr_running ||
+	    (sgs->sum_nr_running == sds->leader_nr_running &&
+	     group_first_cpu(group) < group_first_cpu(sds->group_leader))) {
+		sds->group_leader = group;
+		sds->leader_nr_running = sgs->sum_nr_running;
+	}
+}
+
+/**
+ * check_power_save_busiest_group - see if there is potential for some power-savings balance
+ * @sds: Variable containing the statistics of the sched_domain
+ *	under consideration.
+ * @this_cpu: Cpu at which we're currently performing load-balancing.
+ * @imbalance: Variable to store the imbalance.
+ *
+ * Description:
+ * Check if we have potential to perform some power-savings balance.
+ * If yes, set the busiest group to be the least loaded group in the
+ * sched_domain, so that it's CPUs can be put to idle.
+ *
+ * Returns 1 if there is potential to perform power-savings balance.
+ * Else returns 0.
+ */
+static inline int check_power_save_busiest_group(struct sd_lb_stats *sds,
+					int this_cpu, unsigned long *imbalance)
+{
+	if (!sds->power_savings_balance)
+		return 0;
+
+	if (sds->this != sds->group_leader ||
+			sds->group_leader == sds->group_min)
+		return 0;
+
+	*imbalance = sds->min_load_per_task;
+	sds->busiest = sds->group_min;
+
+	return 1;
+
+}
+#else /* CONFIG_SCHED_MC || CONFIG_SCHED_SMT */
+static inline void init_sd_power_savings_stats(struct sched_domain *sd,
+	struct sd_lb_stats *sds, enum cpu_idle_type idle)
+{
+	return;
+}
+
+static inline void update_sd_power_savings_stats(struct sched_group *group,
+	struct sd_lb_stats *sds, int local_group, struct sg_lb_stats *sgs)
+{
+	return;
+}
+
+static inline int check_power_save_busiest_group(struct sd_lb_stats *sds,
+					int this_cpu, unsigned long *imbalance)
+{
 	return 0;
 }
+#endif /* CONFIG_SCHED_MC || CONFIG_SCHED_SMT */
+
+
+unsigned long default_scale_freq_power(struct sched_domain *sd, int cpu)
+{
+	return SCHED_LOAD_SCALE;
+}
+
+unsigned long __weak arch_scale_freq_power(struct sched_domain *sd, int cpu)
+{
+	return default_scale_freq_power(sd, cpu);
+}
+
+unsigned long default_scale_smt_power(struct sched_domain *sd, int cpu)
+{
+	unsigned long weight = cpumask_weight(sched_domain_span(sd));
+	unsigned long smt_gain = sd->smt_gain;
+
+	smt_gain /= weight;
+
+	return smt_gain;
+}
+
+unsigned long __weak arch_scale_smt_power(struct sched_domain *sd, int cpu)
+{
+	return default_scale_smt_power(sd, cpu);
+}
+
+unsigned long scale_rt_power(int cpu)
+{
+	struct rq *rq = cpu_rq(cpu);
+	u64 total, available;
+
+	sched_avg_update(rq);
+
+	total = sched_avg_period() + (rq->clock - rq->age_stamp);
+	available = total - rq->rt_avg;
+
+	if (unlikely((s64)total < SCHED_LOAD_SCALE))
+		total = SCHED_LOAD_SCALE;
+
+	total >>= SCHED_LOAD_SHIFT;
+
+	return div_u64(available, total);
+}
+
+static void update_cpu_power(struct sched_domain *sd, int cpu)
+{
+	unsigned long weight = cpumask_weight(sched_domain_span(sd));
+	unsigned long power = SCHED_LOAD_SCALE;
+	struct sched_group *sdg = sd->groups;
+
+	if (sched_feat(ARCH_POWER))
+		power *= arch_scale_freq_power(sd, cpu);
+	else
+		power *= default_scale_freq_power(sd, cpu);
+
+	power >>= SCHED_LOAD_SHIFT;
+
+	if ((sd->flags & SD_SHARE_CPUPOWER) && weight > 1) {
+		if (sched_feat(ARCH_POWER))
+			power *= arch_scale_smt_power(sd, cpu);
+		else
+			power *= default_scale_smt_power(sd, cpu);
+
+		power >>= SCHED_LOAD_SHIFT;
+	}
+
+	power *= scale_rt_power(cpu);
+	power >>= SCHED_LOAD_SHIFT;
+
+	if (!power)
+		power = 1;
+
+	sdg->cpu_power = power;
+}
+
+static void update_group_power(struct sched_domain *sd, int cpu)
+{
+	struct sched_domain *child = sd->child;
+	struct sched_group *group, *sdg = sd->groups;
+	unsigned long power;
+
+	if (!child) {
+		update_cpu_power(sd, cpu);
+		return;
+	}
+
+	power = 0;
+
+	group = child->groups;
+	do {
+		power += group->cpu_power;
+		group = group->next;
+	} while (group != child->groups);
+
+	sdg->cpu_power = power;
+}
+
+/**
+ * update_sg_lb_stats - Update sched_group's statistics for load balancing.
+ * @sd: The sched_domain whose statistics are to be updated.
+ * @group: sched_group whose statistics are to be updated.
+ * @this_cpu: Cpu for which load balance is currently performed.
+ * @idle: Idle status of this_cpu
+ * @load_idx: Load index of sched_domain of this_cpu for load calc.
+ * @sd_idle: Idle status of the sched_domain containing group.
+ * @local_group: Does group contain this_cpu.
+ * @cpus: Set of cpus considered for load balancing.
+ * @balance: Should we balance.
+ * @sgs: variable to hold the statistics for this group.
+ */
+static inline void update_sg_lb_stats(struct sched_domain *sd,
+			struct sched_group *group, int this_cpu,
+			enum cpu_idle_type idle, int load_idx, int *sd_idle,
+			int local_group, const struct cpumask *cpus,
+			int *balance, struct sg_lb_stats *sgs)
+{
+	unsigned long load, max_cpu_load, min_cpu_load;
+	int i;
+	unsigned int balance_cpu = -1, first_idle_cpu = 0;
+	unsigned long avg_load_per_task = 0;
+
+	if (local_group)
+		balance_cpu = group_first_cpu(group);
+
+	/* Tally up the load of all CPUs in the group */
+	max_cpu_load = 0;
+	min_cpu_load = ~0UL;
+
+	for_each_cpu_and(i, sched_group_cpus(group), cpus) {
+		struct rq *rq = cpu_rq(i);
+
+		if (*sd_idle && rq->nr_running)
+			*sd_idle = 0;
+
+		/* Bias balancing toward cpus of our domain */
+		if (local_group) {
+			if (idle_cpu(i) && !first_idle_cpu) {
+				first_idle_cpu = 1;
+				balance_cpu = i;
+			}
+
+			load = target_load(i, load_idx);
+		} else {
+			load = source_load(i, load_idx);
+			if (load > max_cpu_load)
+				max_cpu_load = load;
+			if (min_cpu_load > load)
+				min_cpu_load = load;
+		}
+
+		sgs->group_load += load;
+		sgs->sum_nr_running += rq->nr_running;
+		sgs->sum_weighted_load += weighted_cpuload(i);
+
+	}
+
+	/*
+	 * First idle cpu or the first cpu(busiest) in this sched group
+	 * is eligible for doing load balancing at this and above
+	 * domains. In the newly idle case, we will allow all the cpu's
+	 * to do the newly idle load balance.
+	 */
+	if (idle != CPU_NEWLY_IDLE && local_group &&
+	    balance_cpu != this_cpu) {
+		*balance = 0;
+		return;
+	}
+
+	update_group_power(sd, this_cpu);
+
+	/* Adjust by relative CPU power of the group */
+	sgs->avg_load = (sgs->group_load * SCHED_LOAD_SCALE) / group->cpu_power;
+
+	/*
+	 * Consider the group unbalanced when the imbalance is larger
+	 * than the average weight of two tasks.
+	 *
+	 * APZ: with cgroup the avg task weight can vary wildly and
+	 *      might not be a suitable number - should we keep a
+	 *      normalized nr_running number somewhere that negates
+	 *      the hierarchy?
+	 */
+	if (sgs->sum_nr_running)
+		avg_load_per_task = sgs->sum_weighted_load / sgs->sum_nr_running;
+
+	if ((max_cpu_load - min_cpu_load) > 2*avg_load_per_task)
+		sgs->group_imb = 1;
+
+	sgs->group_capacity =
+		DIV_ROUND_CLOSEST(group->cpu_power, SCHED_LOAD_SCALE);
+}
+
+/**
+ * update_sd_lb_stats - Update sched_group's statistics for load balancing.
+ * @sd: sched_domain whose statistics are to be updated.
+ * @this_cpu: Cpu for which load balance is currently performed.
+ * @idle: Idle status of this_cpu
+ * @sd_idle: Idle status of the sched_domain containing group.
+ * @cpus: Set of cpus considered for load balancing.
+ * @balance: Should we balance.
+ * @sds: variable to hold the statistics for this sched_domain.
+ */
+static inline void update_sd_lb_stats(struct sched_domain *sd, int this_cpu,
+			enum cpu_idle_type idle, int *sd_idle,
+			const struct cpumask *cpus, int *balance,
+			struct sd_lb_stats *sds)
+{
+	struct sched_domain *child = sd->child;
+	struct sched_group *group = sd->groups;
+	struct sg_lb_stats sgs;
+	int load_idx, prefer_sibling = 0;
+
+	if (child && child->flags & SD_PREFER_SIBLING)
+		prefer_sibling = 1;
+
+	init_sd_power_savings_stats(sd, sds, idle);
+	load_idx = get_sd_load_idx(sd, idle);
+
+	do {
+		int local_group;
+
+		local_group = cpumask_test_cpu(this_cpu,
+					       sched_group_cpus(group));
+		memset(&sgs, 0, sizeof(sgs));
+		update_sg_lb_stats(sd, group, this_cpu, idle, load_idx, sd_idle,
+				local_group, cpus, balance, &sgs);
+
+		if (local_group && !(*balance))
+			return;
+
+		sds->total_load += sgs.group_load;
+		sds->total_pwr += group->cpu_power;
+
+		/*
+		 * In case the child domain prefers tasks go to siblings
+		 * first, lower the group capacity to one so that we'll try
+		 * and move all the excess tasks away.
+		 */
+		if (prefer_sibling)
+			sgs.group_capacity = min(sgs.group_capacity, 1UL);
+
+		if (local_group) {
+			sds->this_load = sgs.avg_load;
+			sds->this = group;
+			sds->this_nr_running = sgs.sum_nr_running;
+			sds->this_load_per_task = sgs.sum_weighted_load;
+		} else if (sgs.avg_load > sds->max_load &&
+			   (sgs.sum_nr_running > sgs.group_capacity ||
+				sgs.group_imb)) {
+			sds->max_load = sgs.avg_load;
+			sds->busiest = group;
+			sds->busiest_nr_running = sgs.sum_nr_running;
+			sds->busiest_group_capacity = sgs.group_capacity;
+			sds->busiest_load_per_task = sgs.sum_weighted_load;
+			sds->group_imb = sgs.group_imb;
+		}
+
+		update_sd_power_savings_stats(group, sds, local_group, &sgs);
+		group = group->next;
+	} while (group != sd->groups);
+}
+
+/**
+ * fix_small_imbalance - Calculate the minor imbalance that exists
+ *			amongst the groups of a sched_domain, during
+ *			load balancing.
+ * @sds: Statistics of the sched_domain whose imbalance is to be calculated.
+ * @this_cpu: The cpu at whose sched_domain we're performing load-balance.
+ * @imbalance: Variable to store the imbalance.
+ */
+static inline void fix_small_imbalance(struct sd_lb_stats *sds,
+				int this_cpu, unsigned long *imbalance)
+{
+	unsigned long tmp, pwr_now = 0, pwr_move = 0;
+	unsigned int imbn = 2;
+	unsigned long scaled_busy_load_per_task;
+
+	if (sds->this_nr_running) {
+		sds->this_load_per_task /= sds->this_nr_running;
+		if (sds->busiest_load_per_task >
+				sds->this_load_per_task)
+			imbn = 1;
+	} else
+		sds->this_load_per_task =
+			cpu_avg_load_per_task(this_cpu);
+
+	scaled_busy_load_per_task = sds->busiest_load_per_task
+						 * SCHED_LOAD_SCALE;
+	scaled_busy_load_per_task /= sds->busiest->cpu_power;
+
+	if (sds->max_load - sds->this_load + scaled_busy_load_per_task >=
+			(scaled_busy_load_per_task * imbn)) {
+		*imbalance = sds->busiest_load_per_task;
+		return;
+	}
+
+	/*
+	 * OK, we don't have enough imbalance to justify moving tasks,
+	 * however we may be able to increase total CPU power used by
+	 * moving them.
+	 */
+
+	pwr_now += sds->busiest->cpu_power *
+			min(sds->busiest_load_per_task, sds->max_load);
+	pwr_now += sds->this->cpu_power *
+			min(sds->this_load_per_task, sds->this_load);
+	pwr_now /= SCHED_LOAD_SCALE;
+
+	/* Amount of load we'd subtract */
+	tmp = (sds->busiest_load_per_task * SCHED_LOAD_SCALE) /
+		sds->busiest->cpu_power;
+	if (sds->max_load > tmp)
+		pwr_move += sds->busiest->cpu_power *
+			min(sds->busiest_load_per_task, sds->max_load - tmp);
+
+	/* Amount of load we'd add */
+	if (sds->max_load * sds->busiest->cpu_power <
+		sds->busiest_load_per_task * SCHED_LOAD_SCALE)
+		tmp = (sds->max_load * sds->busiest->cpu_power) /
+			sds->this->cpu_power;
+	else
+		tmp = (sds->busiest_load_per_task * SCHED_LOAD_SCALE) /
+			sds->this->cpu_power;
+	pwr_move += sds->this->cpu_power *
+			min(sds->this_load_per_task, sds->this_load + tmp);
+	pwr_move /= SCHED_LOAD_SCALE;
+
+	/* Move if we gain throughput */
+	if (pwr_move > pwr_now)
+		*imbalance = sds->busiest_load_per_task;
+}
+
+/**
+ * calculate_imbalance - Calculate the amount of imbalance present within the
+ *			 groups of a given sched_domain during load balance.
+ * @sds: statistics of the sched_domain whose imbalance is to be calculated.
+ * @this_cpu: Cpu for which currently load balance is being performed.
+ * @imbalance: The variable to store the imbalance.
+ */
+static inline void calculate_imbalance(struct sd_lb_stats *sds, int this_cpu,
+		unsigned long *imbalance)
+{
+	unsigned long max_pull, load_above_capacity = ~0UL;
+
+	sds->busiest_load_per_task /= sds->busiest_nr_running;
+	if (sds->group_imb) {
+		sds->busiest_load_per_task =
+			min(sds->busiest_load_per_task, sds->avg_load);
+	}
+
+	/*
+	 * In the presence of smp nice balancing, certain scenarios can have
+	 * max load less than avg load(as we skip the groups at or below
+	 * its cpu_power, while calculating max_load..)
+	 */
+	if (sds->max_load < sds->avg_load) {
+		*imbalance = 0;
+		return fix_small_imbalance(sds, this_cpu, imbalance);
+	}
+
+	if (!sds->group_imb) {
+		/*
+		 * Don't want to pull so many tasks that a group would go idle.
+		 */
+		load_above_capacity = (sds->busiest_nr_running -
+						sds->busiest_group_capacity);
+
+		load_above_capacity *= (SCHED_LOAD_SCALE * SCHED_LOAD_SCALE);
+
+		load_above_capacity /= sds->busiest->cpu_power;
+	}
+
+	/*
+	 * We're trying to get all the cpus to the average_load, so we don't
+	 * want to push ourselves above the average load, nor do we wish to
+	 * reduce the max loaded cpu below the average load. At the same time,
+	 * we also don't want to reduce the group load below the group capacity
+	 * (so that we can implement power-savings policies etc). Thus we look
+	 * for the minimum possible imbalance.
+	 * Be careful of negative numbers as they'll appear as very large values
+	 * with unsigned longs.
+	 */
+	max_pull = min(sds->max_load - sds->avg_load, load_above_capacity);
+
+	/* How much load to actually move to equalise the imbalance */
+	*imbalance = min(max_pull * sds->busiest->cpu_power,
+		(sds->avg_load - sds->this_load) * sds->this->cpu_power)
+			/ SCHED_LOAD_SCALE;
+
+	/*
+	 * if *imbalance is less than the average load per runnable task
+	 * there is no gaurantee that any tasks will be moved so we'll have
+	 * a think about bumping its value to force at least one task to be
+	 * moved
+	 */
+	if (*imbalance < sds->busiest_load_per_task)
+		return fix_small_imbalance(sds, this_cpu, imbalance);
+
+}
+/******* find_busiest_group() helpers end here *********************/
+
+/**
+ * find_busiest_group - Returns the busiest group within the sched_domain
+ * if there is an imbalance. If there isn't an imbalance, and
+ * the user has opted for power-savings, it returns a group whose
+ * CPUs can be put to idle by rebalancing those tasks elsewhere, if
+ * such a group exists.
+ *
+ * Also calculates the amount of weighted load which should be moved
+ * to restore balance.
+ *
+ * @sd: The sched_domain whose busiest group is to be returned.
+ * @this_cpu: The cpu for which load balancing is currently being performed.
+ * @imbalance: Variable which stores amount of weighted load which should
+ *		be moved to restore balance/put a group to idle.
+ * @idle: The idle status of this_cpu.
+ * @sd_idle: The idleness of sd
+ * @cpus: The set of CPUs under consideration for load-balancing.
+ * @balance: Pointer to a variable indicating if this_cpu
+ *	is the appropriate cpu to perform load balancing at this_level.
+ *
+ * Returns:	- the busiest group if imbalance exists.
+ *		- If no imbalance and user has opted for power-savings balance,
+ *		   return the least loaded group whose CPUs can be
+ *		   put to idle by rebalancing its tasks onto our group.
+ */
+static struct sched_group *
+find_busiest_group(struct sched_domain *sd, int this_cpu,
+		   unsigned long *imbalance, enum cpu_idle_type idle,
+		   int *sd_idle, const struct cpumask *cpus, int *balance)
+{
+	struct sd_lb_stats sds;
+
+	memset(&sds, 0, sizeof(sds));
+
+	/*
+	 * Compute the various statistics relavent for load balancing at
+	 * this level.
+	 */
+	update_sd_lb_stats(sd, this_cpu, idle, sd_idle, cpus,
+					balance, &sds);
+
+	/* Cases where imbalance does not exist from POV of this_cpu */
+	/* 1) this_cpu is not the appropriate cpu to perform load balancing
+	 *    at this level.
+	 * 2) There is no busy sibling group to pull from.
+	 * 3) This group is the busiest group.
+	 * 4) This group is more busy than the avg busieness at this
+	 *    sched_domain.
+	 * 5) The imbalance is within the specified limit.
+	 */
+	if (!(*balance))
+		goto ret;
+
+	if (!sds.busiest || sds.busiest_nr_running == 0)
+		goto out_balanced;
+
+	if (sds.this_load >= sds.max_load)
+		goto out_balanced;
+
+	sds.avg_load = (SCHED_LOAD_SCALE * sds.total_load) / sds.total_pwr;
+
+	if (sds.this_load >= sds.avg_load)
+		goto out_balanced;
+
+	if (100 * sds.max_load <= sd->imbalance_pct * sds.this_load)
+		goto out_balanced;
+
+	/* Looks like there is an imbalance. Compute it */
+	calculate_imbalance(&sds, this_cpu, imbalance);
+	return sds.busiest;
+
+out_balanced:
+	/*
+	 * There is no obvious imbalance. But check if we can do some balancing
+	 * to save power.
+	 */
+	if (check_power_save_busiest_group(&sds, this_cpu, imbalance))
+		return sds.busiest;
+ret:
+	*imbalance = 0;
+	return NULL;
+}
+
+/*
+ * find_busiest_queue - find the busiest runqueue among the cpus in group.
+ */
+static struct rq *
+find_busiest_queue(struct sched_group *group, enum cpu_idle_type idle,
+		   unsigned long imbalance, const struct cpumask *cpus)
+{
+	struct rq *busiest = NULL, *rq;
+	unsigned long max_load = 0;
+	int i;
+
+	for_each_cpu(i, sched_group_cpus(group)) {
+		unsigned long power = power_of(i);
+		unsigned long capacity = DIV_ROUND_CLOSEST(power, SCHED_LOAD_SCALE);
+		unsigned long wl;
+
+		if (!cpumask_test_cpu(i, cpus))
+			continue;
+
+		rq = cpu_rq(i);
+		wl = weighted_cpuload(i);
+
+		/*
+		 * When comparing with imbalance, use weighted_cpuload()
+		 * which is not scaled with the cpu power.
+		 */
+		if (capacity && rq->nr_running == 1 && wl > imbalance)
+			continue;
+
+		/*
+		 * For the load comparisons with the other cpu's, consider
+		 * the weighted_cpuload() scaled with the cpu power, so that
+		 * the load can be moved away from the cpu that is potentially
+		 * running at a lower capacity.
+		 */
+		wl = (wl * SCHED_LOAD_SCALE) / power;
+
+		if (wl > max_load) {
+			max_load = wl;
+			busiest = rq;
+		}
+	}
+
+	return busiest;
+}
+
+/*
+ * Max backoff if we encounter pinned tasks. Pretty arbitrary value, but
+ * so long as it is large enough.
+ */
+#define MAX_PINNED_INTERVAL	512
+
+/* Working cpumask for load_balance and load_balance_newidle. */
+static DEFINE_PER_CPU(cpumask_var_t, load_balance_tmpmask);
+
+static int need_active_balance(struct sched_domain *sd, int sd_idle, int idle)
+{
+	if (idle == CPU_NEWLY_IDLE) {
+		/*
+		 * The only task running in a non-idle cpu can be moved to this
+		 * cpu in an attempt to completely freeup the other CPU
+		 * package.
+		 *
+		 * The package power saving logic comes from
+		 * find_busiest_group(). If there are no imbalance, then
+		 * f_b_g() will return NULL. However when sched_mc={1,2} then
+		 * f_b_g() will select a group from which a running task may be
+		 * pulled to this cpu in order to make the other package idle.
+		 * If there is no opportunity to make a package idle and if
+		 * there are no imbalance, then f_b_g() will return NULL and no
+		 * action will be taken in load_balance_newidle().
+		 *
+		 * Under normal task pull operation due to imbalance, there
+		 * will be more than one task in the source run queue and
+		 * move_tasks() will succeed.  ld_moved will be true and this
+		 * active balance code will not be triggered.
+		 */
+		if (!sd_idle && sd->flags & SD_SHARE_CPUPOWER &&
+		    !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE))
+			return 0;
+
+		if (sched_mc_power_savings < POWERSAVINGS_BALANCE_WAKEUP)
+			return 0;
+	}
+
+	return unlikely(sd->nr_balance_failed > sd->cache_nice_tries+2);
+}
+
+/*
+ * Check this_cpu to ensure it is balanced within domain. Attempt to move
+ * tasks if there is an imbalance.
+ */
+static int load_balance(int this_cpu, struct rq *this_rq,
+			struct sched_domain *sd, enum cpu_idle_type idle,
+			int *balance)
+{
+	int ld_moved, all_pinned = 0, active_balance = 0, sd_idle = 0;
+	struct sched_group *group;
+	unsigned long imbalance;
+	struct rq *busiest;
+	unsigned long flags;
+	struct cpumask *cpus = __get_cpu_var(load_balance_tmpmask);
+
+	cpumask_copy(cpus, cpu_active_mask);
+
+	/*
+	 * When power savings policy is enabled for the parent domain, idle
+	 * sibling can pick up load irrespective of busy siblings. In this case,
+	 * let the state of idle sibling percolate up as CPU_IDLE, instead of
+	 * portraying it as CPU_NOT_IDLE.
+	 */
+	if (idle != CPU_NOT_IDLE && sd->flags & SD_SHARE_CPUPOWER &&
+	    !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE))
+		sd_idle = 1;
+
+	schedstat_inc(sd, lb_count[idle]);
+
+redo:
+	update_shares(sd);
+	group = find_busiest_group(sd, this_cpu, &imbalance, idle, &sd_idle,
+				   cpus, balance);
+
+	if (*balance == 0)
+		goto out_balanced;
+
+	if (!group) {
+		schedstat_inc(sd, lb_nobusyg[idle]);
+		goto out_balanced;
+	}
+
+	busiest = find_busiest_queue(group, idle, imbalance, cpus);
+	if (!busiest) {
+		schedstat_inc(sd, lb_nobusyq[idle]);
+		goto out_balanced;
+	}
+
+	BUG_ON(busiest == this_rq);
+
+	schedstat_add(sd, lb_imbalance[idle], imbalance);
+
+	ld_moved = 0;
+	if (busiest->nr_running > 1) {
+		/*
+		 * Attempt to move tasks. If find_busiest_group has found
+		 * an imbalance but busiest->nr_running <= 1, the group is
+		 * still unbalanced. ld_moved simply stays zero, so it is
+		 * correctly treated as an imbalance.
+		 */
+		local_irq_save(flags);
+		double_rq_lock(this_rq, busiest);
+		ld_moved = move_tasks(this_rq, this_cpu, busiest,
+				      imbalance, sd, idle, &all_pinned);
+		double_rq_unlock(this_rq, busiest);
+		local_irq_restore(flags);
+
+		/*
+		 * some other cpu did the load balance for us.
+		 */
+		if (ld_moved && this_cpu != smp_processor_id())
+			resched_cpu(this_cpu);
+
+		/* All tasks on this runqueue were pinned by CPU affinity */
+		if (unlikely(all_pinned)) {
+			cpumask_clear_cpu(cpu_of(busiest), cpus);
+			if (!cpumask_empty(cpus))
+				goto redo;
+			goto out_balanced;
+		}
+	}
+
+	if (!ld_moved) {
+		schedstat_inc(sd, lb_failed[idle]);
+		sd->nr_balance_failed++;
+
+		if (need_active_balance(sd, sd_idle, idle)) {
+			raw_spin_lock_irqsave(&busiest->lock, flags);
+
+			/* don't kick the migration_thread, if the curr
+			 * task on busiest cpu can't be moved to this_cpu
+			 */
+			if (!cpumask_test_cpu(this_cpu,
+					      &busiest->curr->cpus_allowed)) {
+				raw_spin_unlock_irqrestore(&busiest->lock,
+							    flags);
+				all_pinned = 1;
+				goto out_one_pinned;
+			}
+
+			if (!busiest->active_balance) {
+				busiest->active_balance = 1;
+				busiest->push_cpu = this_cpu;
+				active_balance = 1;
+			}
+			raw_spin_unlock_irqrestore(&busiest->lock, flags);
+			if (active_balance)
+				wake_up_process(busiest->migration_thread);
+
+			/*
+			 * We've kicked active balancing, reset the failure
+			 * counter.
+			 */
+			sd->nr_balance_failed = sd->cache_nice_tries+1;
+		}
+	} else
+		sd->nr_balance_failed = 0;
+
+	if (likely(!active_balance)) {
+		/* We were unbalanced, so reset the balancing interval */
+		sd->balance_interval = sd->min_interval;
+	} else {
+		/*
+		 * If we've begun active balancing, start to back off. This
+		 * case may not be covered by the all_pinned logic if there
+		 * is only 1 task on the busy runqueue (because we don't call
+		 * move_tasks).
+		 */
+		if (sd->balance_interval < sd->max_interval)
+			sd->balance_interval *= 2;
+	}
+
+	if (!ld_moved && !sd_idle && sd->flags & SD_SHARE_CPUPOWER &&
+	    !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE))
+		ld_moved = -1;
+
+	goto out;
+
+out_balanced:
+	schedstat_inc(sd, lb_balanced[idle]);
+
+	sd->nr_balance_failed = 0;
+
+out_one_pinned:
+	/* tune up the balancing interval */
+	if ((all_pinned && sd->balance_interval < MAX_PINNED_INTERVAL) ||
+			(sd->balance_interval < sd->max_interval))
+		sd->balance_interval *= 2;
+
+	if (!sd_idle && sd->flags & SD_SHARE_CPUPOWER &&
+	    !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE))
+		ld_moved = -1;
+	else
+		ld_moved = 0;
+out:
+	if (ld_moved)
+		update_shares(sd);
+	return ld_moved;
+}
+
+/*
+ * idle_balance is called by schedule() if this_cpu is about to become
+ * idle. Attempts to pull tasks from other CPUs.
+ */
+static void idle_balance(int this_cpu, struct rq *this_rq)
+{
+	struct sched_domain *sd;
+	int pulled_task = 0;
+	unsigned long next_balance = jiffies + HZ;
+
+	this_rq->idle_stamp = this_rq->clock;
+
+	if (this_rq->avg_idle < sysctl_sched_migration_cost)
+		return;
+
+	/*
+	 * Drop the rq->lock, but keep IRQ/preempt disabled.
+	 */
+	raw_spin_unlock(&this_rq->lock);
+
+	for_each_domain(this_cpu, sd) {
+		unsigned long interval;
+		int balance = 1;
+
+		if (!(sd->flags & SD_LOAD_BALANCE))
+			continue;
+
+		if (sd->flags & SD_BALANCE_NEWIDLE) {
+			/* If we've pulled tasks over stop searching: */
+			pulled_task = load_balance(this_cpu, this_rq,
+						   sd, CPU_NEWLY_IDLE, &balance);
+		}
+
+		interval = msecs_to_jiffies(sd->balance_interval);
+		if (time_after(next_balance, sd->last_balance + interval))
+			next_balance = sd->last_balance + interval;
+		if (pulled_task) {
+			this_rq->idle_stamp = 0;
+			break;
+		}
+	}
+
+	raw_spin_lock(&this_rq->lock);
+
+	if (pulled_task || time_after(jiffies, this_rq->next_balance)) {
+		/*
+		 * We are going idle. next_balance may be set based on
+		 * a busy processor. So reset next_balance.
+		 */
+		this_rq->next_balance = next_balance;
+	}
+}
+
+/*
+ * active_load_balance is run by migration threads. It pushes running tasks
+ * off the busiest CPU onto idle CPUs. It requires at least 1 task to be
+ * running on each physical CPU where possible, and avoids physical /
+ * logical imbalances.
+ *
+ * Called with busiest_rq locked.
+ */
+static void active_load_balance(struct rq *busiest_rq, int busiest_cpu)
+{
+	int target_cpu = busiest_rq->push_cpu;
+	struct sched_domain *sd;
+	struct rq *target_rq;
+
+	/* Is there any task to move? */
+	if (busiest_rq->nr_running <= 1)
+		return;
+
+	target_rq = cpu_rq(target_cpu);
+
+	/*
+	 * This condition is "impossible", if it occurs
+	 * we need to fix it. Originally reported by
+	 * Bjorn Helgaas on a 128-cpu setup.
+	 */
+	BUG_ON(busiest_rq == target_rq);
+
+	/* move a task from busiest_rq to target_rq */
+	double_lock_balance(busiest_rq, target_rq);
+	update_rq_clock(busiest_rq);
+	update_rq_clock(target_rq);
+
+	/* Search for an sd spanning us and the target CPU. */
+	for_each_domain(target_cpu, sd) {
+		if ((sd->flags & SD_LOAD_BALANCE) &&
+		    cpumask_test_cpu(busiest_cpu, sched_domain_span(sd)))
+				break;
+	}
+
+	if (likely(sd)) {
+		schedstat_inc(sd, alb_count);
+
+		if (move_one_task(target_rq, target_cpu, busiest_rq,
+				  sd, CPU_IDLE))
+			schedstat_inc(sd, alb_pushed);
+		else
+			schedstat_inc(sd, alb_failed);
+	}
+	double_unlock_balance(busiest_rq, target_rq);
+}
+
+#ifdef CONFIG_NO_HZ
+static struct {
+	atomic_t load_balancer;
+	cpumask_var_t cpu_mask;
+	cpumask_var_t ilb_grp_nohz_mask;
+} nohz ____cacheline_aligned = {
+	.load_balancer = ATOMIC_INIT(-1),
+};
+
+int get_nohz_load_balancer(void)
+{
+	return atomic_read(&nohz.load_balancer);
+}
+
+#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT)
+/**
+ * lowest_flag_domain - Return lowest sched_domain containing flag.
+ * @cpu:	The cpu whose lowest level of sched domain is to
+ *		be returned.
+ * @flag:	The flag to check for the lowest sched_domain
+ *		for the given cpu.
+ *
+ * Returns the lowest sched_domain of a cpu which contains the given flag.
+ */
+static inline struct sched_domain *lowest_flag_domain(int cpu, int flag)
+{
+	struct sched_domain *sd;
+
+	for_each_domain(cpu, sd)
+		if (sd && (sd->flags & flag))
+			break;
+
+	return sd;
+}
+
+/**
+ * for_each_flag_domain - Iterates over sched_domains containing the flag.
+ * @cpu:	The cpu whose domains we're iterating over.
+ * @sd:		variable holding the value of the power_savings_sd
+ *		for cpu.
+ * @flag:	The flag to filter the sched_domains to be iterated.
+ *
+ * Iterates over all the scheduler domains for a given cpu that has the 'flag'
+ * set, starting from the lowest sched_domain to the highest.
+ */
+#define for_each_flag_domain(cpu, sd, flag) \
+	for (sd = lowest_flag_domain(cpu, flag); \
+		(sd && (sd->flags & flag)); sd = sd->parent)
+
+/**
+ * is_semi_idle_group - Checks if the given sched_group is semi-idle.
+ * @ilb_group:	group to be checked for semi-idleness
+ *
+ * Returns:	1 if the group is semi-idle. 0 otherwise.
+ *
+ * We define a sched_group to be semi idle if it has atleast one idle-CPU
+ * and atleast one non-idle CPU. This helper function checks if the given
+ * sched_group is semi-idle or not.
+ */
+static inline int is_semi_idle_group(struct sched_group *ilb_group)
+{
+	cpumask_and(nohz.ilb_grp_nohz_mask, nohz.cpu_mask,
+					sched_group_cpus(ilb_group));
+
+	/*
+	 * A sched_group is semi-idle when it has atleast one busy cpu
+	 * and atleast one idle cpu.
+	 */
+	if (cpumask_empty(nohz.ilb_grp_nohz_mask))
+		return 0;
+
+	if (cpumask_equal(nohz.ilb_grp_nohz_mask, sched_group_cpus(ilb_group)))
+		return 0;
+
+	return 1;
+}
+/**
+ * find_new_ilb - Finds the optimum idle load balancer for nomination.
+ * @cpu:	The cpu which is nominating a new idle_load_balancer.
+ *
+ * Returns:	Returns the id of the idle load balancer if it exists,
+ *		Else, returns >= nr_cpu_ids.
+ *
+ * This algorithm picks the idle load balancer such that it belongs to a
+ * semi-idle powersavings sched_domain. The idea is to try and avoid
+ * completely idle packages/cores just for the purpose of idle load balancing
+ * when there are other idle cpu's which are better suited for that job.
+ */
+static int find_new_ilb(int cpu)
+{
+	struct sched_domain *sd;
+	struct sched_group *ilb_group;
+
+	/*
+	 * Have idle load balancer selection from semi-idle packages only
+	 * when power-aware load balancing is enabled
+	 */
+	if (!(sched_smt_power_savings || sched_mc_power_savings))
+		goto out_done;
+
+	/*
+	 * Optimize for the case when we have no idle CPUs or only one
+	 * idle CPU. Don't walk the sched_domain hierarchy in such cases
+	 */
+	if (cpumask_weight(nohz.cpu_mask) < 2)
+		goto out_done;
+
+	for_each_flag_domain(cpu, sd, SD_POWERSAVINGS_BALANCE) {
+		ilb_group = sd->groups;
+
+		do {
+			if (is_semi_idle_group(ilb_group))
+				return cpumask_first(nohz.ilb_grp_nohz_mask);
+
+			ilb_group = ilb_group->next;
+
+		} while (ilb_group != sd->groups);
+	}
+
+out_done:
+	return cpumask_first(nohz.cpu_mask);
+}
+#else /*  (CONFIG_SCHED_MC || CONFIG_SCHED_SMT) */
+static inline int find_new_ilb(int call_cpu)
+{
+	return cpumask_first(nohz.cpu_mask);
+}
+#endif
+
+/*
+ * This routine will try to nominate the ilb (idle load balancing)
+ * owner among the cpus whose ticks are stopped. ilb owner will do the idle
+ * load balancing on behalf of all those cpus. If all the cpus in the system
+ * go into this tickless mode, then there will be no ilb owner (as there is
+ * no need for one) and all the cpus will sleep till the next wakeup event
+ * arrives...
+ *
+ * For the ilb owner, tick is not stopped. And this tick will be used
+ * for idle load balancing. ilb owner will still be part of
+ * nohz.cpu_mask..
+ *
+ * While stopping the tick, this cpu will become the ilb owner if there
+ * is no other owner. And will be the owner till that cpu becomes busy
+ * or if all cpus in the system stop their ticks at which point
+ * there is no need for ilb owner.
+ *
+ * When the ilb owner becomes busy, it nominates another owner, during the
+ * next busy scheduler_tick()
+ */
+int select_nohz_load_balancer(int stop_tick)
+{
+	int cpu = smp_processor_id();
+
+	if (stop_tick) {
+		cpu_rq(cpu)->in_nohz_recently = 1;
+
+		if (!cpu_active(cpu)) {
+			if (atomic_read(&nohz.load_balancer) != cpu)
+				return 0;
+
+			/*
+			 * If we are going offline and still the leader,
+			 * give up!
+			 */
+			if (atomic_cmpxchg(&nohz.load_balancer, cpu, -1) != cpu)
+				BUG();
+
+			return 0;
+		}
+
+		cpumask_set_cpu(cpu, nohz.cpu_mask);
+
+		/* time for ilb owner also to sleep */
+		if (cpumask_weight(nohz.cpu_mask) == num_active_cpus()) {
+			if (atomic_read(&nohz.load_balancer) == cpu)
+				atomic_set(&nohz.load_balancer, -1);
+			return 0;
+		}
+
+		if (atomic_read(&nohz.load_balancer) == -1) {
+			/* make me the ilb owner */
+			if (atomic_cmpxchg(&nohz.load_balancer, -1, cpu) == -1)
+				return 1;
+		} else if (atomic_read(&nohz.load_balancer) == cpu) {
+			int new_ilb;
+
+			if (!(sched_smt_power_savings ||
+						sched_mc_power_savings))
+				return 1;
+			/*
+			 * Check to see if there is a more power-efficient
+			 * ilb.
+			 */
+			new_ilb = find_new_ilb(cpu);
+			if (new_ilb < nr_cpu_ids && new_ilb != cpu) {
+				atomic_set(&nohz.load_balancer, -1);
+				resched_cpu(new_ilb);
+				return 0;
+			}
+			return 1;
+		}
+	} else {
+		if (!cpumask_test_cpu(cpu, nohz.cpu_mask))
+			return 0;
+
+		cpumask_clear_cpu(cpu, nohz.cpu_mask);
+
+		if (atomic_read(&nohz.load_balancer) == cpu)
+			if (atomic_cmpxchg(&nohz.load_balancer, cpu, -1) != cpu)
+				BUG();
+	}
+	return 0;
+}
+#endif
+
+static DEFINE_SPINLOCK(balancing);
+
+/*
+ * It checks each scheduling domain to see if it is due to be balanced,
+ * and initiates a balancing operation if so.
+ *
+ * Balancing parameters are set up in arch_init_sched_domains.
+ */
+static void rebalance_domains(int cpu, enum cpu_idle_type idle)
+{
+	int balance = 1;
+	struct rq *rq = cpu_rq(cpu);
+	unsigned long interval;
+	struct sched_domain *sd;
+	/* Earliest time when we have to do rebalance again */
+	unsigned long next_balance = jiffies + 60*HZ;
+	int update_next_balance = 0;
+	int need_serialize;
+
+	for_each_domain(cpu, sd) {
+		if (!(sd->flags & SD_LOAD_BALANCE))
+			continue;
+
+		interval = sd->balance_interval;
+		if (idle != CPU_IDLE)
+			interval *= sd->busy_factor;
+
+		/* scale ms to jiffies */
+		interval = msecs_to_jiffies(interval);
+		if (unlikely(!interval))
+			interval = 1;
+		if (interval > HZ*NR_CPUS/10)
+			interval = HZ*NR_CPUS/10;
+
+		need_serialize = sd->flags & SD_SERIALIZE;
+
+		if (need_serialize) {
+			if (!spin_trylock(&balancing))
+				goto out;
+		}
+
+		if (time_after_eq(jiffies, sd->last_balance + interval)) {
+			if (load_balance(cpu, rq, sd, idle, &balance)) {
+				/*
+				 * We've pulled tasks over so either we're no
+				 * longer idle, or one of our SMT siblings is
+				 * not idle.
+				 */
+				idle = CPU_NOT_IDLE;
+			}
+			sd->last_balance = jiffies;
+		}
+		if (need_serialize)
+			spin_unlock(&balancing);
+out:
+		if (time_after(next_balance, sd->last_balance + interval)) {
+			next_balance = sd->last_balance + interval;
+			update_next_balance = 1;
+		}
+
+		/*
+		 * Stop the load balance at this level. There is another
+		 * CPU in our sched group which is doing load balancing more
+		 * actively.
+		 */
+		if (!balance)
+			break;
+	}
+
+	/*
+	 * next_balance will be updated only when there is a need.
+	 * When the cpu is attached to null domain for ex, it will not be
+	 * updated.
+	 */
+	if (likely(update_next_balance))
+		rq->next_balance = next_balance;
+}
+
+/*
+ * run_rebalance_domains is triggered when needed from the scheduler tick.
+ * In CONFIG_NO_HZ case, the idle load balance owner will do the
+ * rebalancing for all the cpus for whom scheduler ticks are stopped.
+ */
+static void run_rebalance_domains(struct softirq_action *h)
+{
+	int this_cpu = smp_processor_id();
+	struct rq *this_rq = cpu_rq(this_cpu);
+	enum cpu_idle_type idle = this_rq->idle_at_tick ?
+						CPU_IDLE : CPU_NOT_IDLE;
+
+	rebalance_domains(this_cpu, idle);
+
+#ifdef CONFIG_NO_HZ
+	/*
+	 * If this cpu is the owner for idle load balancing, then do the
+	 * balancing on behalf of the other idle cpus whose ticks are
+	 * stopped.
+	 */
+	if (this_rq->idle_at_tick &&
+	    atomic_read(&nohz.load_balancer) == this_cpu) {
+		struct rq *rq;
+		int balance_cpu;
+
+		for_each_cpu(balance_cpu, nohz.cpu_mask) {
+			if (balance_cpu == this_cpu)
+				continue;
+
+			/*
+			 * If this cpu gets work to do, stop the load balancing
+			 * work being done for other cpus. Next load
+			 * balancing owner will pick it up.
+			 */
+			if (need_resched())
+				break;
+
+			rebalance_domains(balance_cpu, CPU_IDLE);
+
+			rq = cpu_rq(balance_cpu);
+			if (time_after(this_rq->next_balance, rq->next_balance))
+				this_rq->next_balance = rq->next_balance;
+		}
+	}
+#endif
+}
+
+static inline int on_null_domain(int cpu)
+{
+	return !rcu_dereference_sched(cpu_rq(cpu)->sd);
+}
+
+/*
+ * Trigger the SCHED_SOFTIRQ if it is time to do periodic load balancing.
+ *
+ * In case of CONFIG_NO_HZ, this is the place where we nominate a new
+ * idle load balancing owner or decide to stop the periodic load balancing,
+ * if the whole system is idle.
+ */
+static inline void trigger_load_balance(struct rq *rq, int cpu)
+{
+#ifdef CONFIG_NO_HZ
+	/*
+	 * If we were in the nohz mode recently and busy at the current
+	 * scheduler tick, then check if we need to nominate new idle
+	 * load balancer.
+	 */
+	if (rq->in_nohz_recently && !rq->idle_at_tick) {
+		rq->in_nohz_recently = 0;
+
+		if (atomic_read(&nohz.load_balancer) == cpu) {
+			cpumask_clear_cpu(cpu, nohz.cpu_mask);
+			atomic_set(&nohz.load_balancer, -1);
+		}
+
+		if (atomic_read(&nohz.load_balancer) == -1) {
+			int ilb = find_new_ilb(cpu);
+
+			if (ilb < nr_cpu_ids)
+				resched_cpu(ilb);
+		}
+	}
+
+	/*
+	 * If this cpu is idle and doing idle load balancing for all the
+	 * cpus with ticks stopped, is it time for that to stop?
+	 */
+	if (rq->idle_at_tick && atomic_read(&nohz.load_balancer) == cpu &&
+	    cpumask_weight(nohz.cpu_mask) == num_online_cpus()) {
+		resched_cpu(cpu);
+		return;
+	}
+
+	/*
+	 * If this cpu is idle and the idle load balancing is done by
+	 * someone else, then no need raise the SCHED_SOFTIRQ
+	 */
+	if (rq->idle_at_tick && atomic_read(&nohz.load_balancer) != cpu &&
+	    cpumask_test_cpu(cpu, nohz.cpu_mask))
+		return;
+#endif
+	/* Don't need to rebalance while attached to NULL domain */
+	if (time_after_eq(jiffies, rq->next_balance) &&
+	    likely(!on_null_domain(cpu)))
+		raise_softirq(SCHED_SOFTIRQ);
+}
 
 static void rq_online_fair(struct rq *rq)
 {
@@ -1962,6 +3544,15 @@ static void rq_offline_fair(struct rq *rq)
 	update_sysctl();
 }
 
+#else	/* CONFIG_SMP */
+
+/*
+ * on UP we do not need to balance between CPUs:
+ */
+static inline void idle_balance(int cpu, struct rq *rq)
+{
+}
+
 #endif /* CONFIG_SMP */
 
 /*
@@ -2076,7 +3667,7 @@ static void moved_group_fair(struct task_struct *p, int on_rq)
 }
 #endif
 
-unsigned int get_rr_interval_fair(struct rq *rq, struct task_struct *task)
+static unsigned int get_rr_interval_fair(struct rq *rq, struct task_struct *task)
 {
 	struct sched_entity *se = &task->se;
 	unsigned int rr_interval = 0;
@@ -2108,8 +3699,6 @@ static const struct sched_class fair_sched_class = {
 #ifdef CONFIG_SMP
 	.select_task_rq		= select_task_rq_fair,
 
-	.load_balance		= load_balance_fair,
-	.move_one_task		= move_one_task_fair,
 	.rq_online		= rq_online_fair,
 	.rq_offline		= rq_offline_fair,
 
diff --git a/kernel/sched_idletask.c b/kernel/sched_idletask.c
index 5f93b570d38..a8a6d8a5094 100644
--- a/kernel/sched_idletask.c
+++ b/kernel/sched_idletask.c
@@ -44,24 +44,6 @@ static void put_prev_task_idle(struct rq *rq, struct task_struct *prev)
 {
 }
 
-#ifdef CONFIG_SMP
-static unsigned long
-load_balance_idle(struct rq *this_rq, int this_cpu, struct rq *busiest,
-		  unsigned long max_load_move,
-		  struct sched_domain *sd, enum cpu_idle_type idle,
-		  int *all_pinned, int *this_best_prio)
-{
-	return 0;
-}
-
-static int
-move_one_task_idle(struct rq *this_rq, int this_cpu, struct rq *busiest,
-		   struct sched_domain *sd, enum cpu_idle_type idle)
-{
-	return 0;
-}
-#endif
-
 static void task_tick_idle(struct rq *rq, struct task_struct *curr, int queued)
 {
 }
@@ -97,7 +79,7 @@ static void prio_changed_idle(struct rq *rq, struct task_struct *p,
 		check_preempt_curr(rq, p, 0);
 }
 
-unsigned int get_rr_interval_idle(struct rq *rq, struct task_struct *task)
+static unsigned int get_rr_interval_idle(struct rq *rq, struct task_struct *task)
 {
 	return 0;
 }
@@ -119,9 +101,6 @@ static const struct sched_class idle_sched_class = {
 
 #ifdef CONFIG_SMP
 	.select_task_rq		= select_task_rq_idle,
-
-	.load_balance		= load_balance_idle,
-	.move_one_task		= move_one_task_idle,
 #endif
 
 	.set_curr_task          = set_curr_task_idle,
diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c
index f48328ac216..b5b920ae2ea 100644
--- a/kernel/sched_rt.c
+++ b/kernel/sched_rt.c
@@ -194,17 +194,20 @@ static inline struct rt_rq *group_rt_rq(struct sched_rt_entity *rt_se)
 	return rt_se->my_q;
 }
 
-static void enqueue_rt_entity(struct sched_rt_entity *rt_se);
+static void enqueue_rt_entity(struct sched_rt_entity *rt_se, bool head);
 static void dequeue_rt_entity(struct sched_rt_entity *rt_se);
 
 static void sched_rt_rq_enqueue(struct rt_rq *rt_rq)
 {
+	int this_cpu = smp_processor_id();
 	struct task_struct *curr = rq_of_rt_rq(rt_rq)->curr;
-	struct sched_rt_entity *rt_se = rt_rq->rt_se;
+	struct sched_rt_entity *rt_se;
+
+	rt_se = rt_rq->tg->rt_se[this_cpu];
 
 	if (rt_rq->rt_nr_running) {
 		if (rt_se && !on_rt_rq(rt_se))
-			enqueue_rt_entity(rt_se);
+			enqueue_rt_entity(rt_se, false);
 		if (rt_rq->highest_prio.curr < curr->prio)
 			resched_task(curr);
 	}
@@ -212,7 +215,10 @@ static void sched_rt_rq_enqueue(struct rt_rq *rt_rq)
 
 static void sched_rt_rq_dequeue(struct rt_rq *rt_rq)
 {
-	struct sched_rt_entity *rt_se = rt_rq->rt_se;
+	int this_cpu = smp_processor_id();
+	struct sched_rt_entity *rt_se;
+
+	rt_se = rt_rq->tg->rt_se[this_cpu];
 
 	if (rt_se && on_rt_rq(rt_se))
 		dequeue_rt_entity(rt_se);
@@ -803,7 +809,7 @@ void dec_rt_tasks(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
 	dec_rt_group(rt_se, rt_rq);
 }
 
-static void __enqueue_rt_entity(struct sched_rt_entity *rt_se)
+static void __enqueue_rt_entity(struct sched_rt_entity *rt_se, bool head)
 {
 	struct rt_rq *rt_rq = rt_rq_of_se(rt_se);
 	struct rt_prio_array *array = &rt_rq->active;
@@ -819,7 +825,10 @@ static void __enqueue_rt_entity(struct sched_rt_entity *rt_se)
 	if (group_rq && (rt_rq_throttled(group_rq) || !group_rq->rt_nr_running))
 		return;
 
-	list_add_tail(&rt_se->run_list, queue);
+	if (head)
+		list_add(&rt_se->run_list, queue);
+	else
+		list_add_tail(&rt_se->run_list, queue);
 	__set_bit(rt_se_prio(rt_se), array->bitmap);
 
 	inc_rt_tasks(rt_se, rt_rq);
@@ -856,11 +865,11 @@ static void dequeue_rt_stack(struct sched_rt_entity *rt_se)
 	}
 }
 
-static void enqueue_rt_entity(struct sched_rt_entity *rt_se)
+static void enqueue_rt_entity(struct sched_rt_entity *rt_se, bool head)
 {
 	dequeue_rt_stack(rt_se);
 	for_each_sched_rt_entity(rt_se)
-		__enqueue_rt_entity(rt_se);
+		__enqueue_rt_entity(rt_se, head);
 }
 
 static void dequeue_rt_entity(struct sched_rt_entity *rt_se)
@@ -871,21 +880,22 @@ static void dequeue_rt_entity(struct sched_rt_entity *rt_se)
 		struct rt_rq *rt_rq = group_rt_rq(rt_se);
 
 		if (rt_rq && rt_rq->rt_nr_running)
-			__enqueue_rt_entity(rt_se);
+			__enqueue_rt_entity(rt_se, false);
 	}
 }
 
 /*
  * Adding/removing a task to/from a priority array:
  */
-static void enqueue_task_rt(struct rq *rq, struct task_struct *p, int wakeup)
+static void
+enqueue_task_rt(struct rq *rq, struct task_struct *p, int wakeup, bool head)
 {
 	struct sched_rt_entity *rt_se = &p->rt;
 
 	if (wakeup)
 		rt_se->timeout = 0;
 
-	enqueue_rt_entity(rt_se);
+	enqueue_rt_entity(rt_se, head);
 
 	if (!task_current(rq, p) && p->rt.nr_cpus_allowed > 1)
 		enqueue_pushable_task(rq, p);
@@ -1136,7 +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;
@@ -1481,24 +1496,6 @@ static void task_woken_rt(struct rq *rq, struct task_struct *p)
 		push_rt_tasks(rq);
 }
 
-static unsigned long
-load_balance_rt(struct rq *this_rq, int this_cpu, struct rq *busiest,
-		unsigned long max_load_move,
-		struct sched_domain *sd, enum cpu_idle_type idle,
-		int *all_pinned, int *this_best_prio)
-{
-	/* don't touch RT tasks */
-	return 0;
-}
-
-static int
-move_one_task_rt(struct rq *this_rq, int this_cpu, struct rq *busiest,
-		 struct sched_domain *sd, enum cpu_idle_type idle)
-{
-	/* don't touch RT tasks */
-	return 0;
-}
-
 static void set_cpus_allowed_rt(struct task_struct *p,
 				const struct cpumask *new_mask)
 {
@@ -1670,8 +1667,9 @@ static void watchdog(struct rq *rq, struct task_struct *p)
 	if (!p->signal)
 		return;
 
-	soft = p->signal->rlim[RLIMIT_RTTIME].rlim_cur;
-	hard = p->signal->rlim[RLIMIT_RTTIME].rlim_max;
+	/* max may change after cur was read, this will be fixed next tick */
+	soft = task_rlimit(p, RLIMIT_RTTIME);
+	hard = task_rlimit_max(p, RLIMIT_RTTIME);
 
 	if (soft != RLIM_INFINITY) {
 		unsigned long next;
@@ -1721,7 +1719,7 @@ static void set_curr_task_rt(struct rq *rq)
 	dequeue_pushable_task(rq, p);
 }
 
-unsigned int get_rr_interval_rt(struct rq *rq, struct task_struct *task)
+static unsigned int get_rr_interval_rt(struct rq *rq, struct task_struct *task)
 {
 	/*
 	 * Time slice is 0 for SCHED_FIFO tasks
@@ -1746,8 +1744,6 @@ static const struct sched_class rt_sched_class = {
 #ifdef CONFIG_SMP
 	.select_task_rq		= select_task_rq_rt,
 
-	.load_balance		= load_balance_rt,
-	.move_one_task		= move_one_task_rt,
 	.set_cpus_allowed       = set_cpus_allowed_rt,
 	.rq_online              = rq_online_rt,
 	.rq_offline             = rq_offline_rt,
diff --git a/kernel/signal.c b/kernel/signal.c
index 934ae5e687b..dbd7fe073c5 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -159,6 +159,10 @@ void recalc_sigpending(void)
 
 /* Given the mask, find the first available signal that should be serviced. */
 
+#define SYNCHRONOUS_MASK \
+	(sigmask(SIGSEGV) | sigmask(SIGBUS) | sigmask(SIGILL) | \
+	 sigmask(SIGTRAP) | sigmask(SIGFPE))
+
 int next_signal(struct sigpending *pending, sigset_t *mask)
 {
 	unsigned long i, *s, *m, x;
@@ -166,26 +170,39 @@ int next_signal(struct sigpending *pending, sigset_t *mask)
 
 	s = pending->signal.sig;
 	m = mask->sig;
+
+	/*
+	 * Handle the first word specially: it contains the
+	 * synchronous signals that need to be dequeued first.
+	 */
+	x = *s &~ *m;
+	if (x) {
+		if (x & SYNCHRONOUS_MASK)
+			x &= SYNCHRONOUS_MASK;
+		sig = ffz(~x) + 1;
+		return sig;
+	}
+
 	switch (_NSIG_WORDS) {
 	default:
-		for (i = 0; i < _NSIG_WORDS; ++i, ++s, ++m)
-			if ((x = *s &~ *m) != 0) {
-				sig = ffz(~x) + i*_NSIG_BPW + 1;
-				break;
-			}
+		for (i = 1; i < _NSIG_WORDS; ++i) {
+			x = *++s &~ *++m;
+			if (!x)
+				continue;
+			sig = ffz(~x) + i*_NSIG_BPW + 1;
+			break;
+		}
 		break;
 
-	case 2: if ((x = s[0] &~ m[0]) != 0)
-			sig = 1;
-		else if ((x = s[1] &~ m[1]) != 0)
-			sig = _NSIG_BPW + 1;
-		else
+	case 2:
+		x = s[1] &~ m[1];
+		if (!x)
 			break;
-		sig += ffz(~x);
+		sig = ffz(~x) + _NSIG_BPW + 1;
 		break;
 
-	case 1: if ((x = *s &~ *m) != 0)
-			sig = ffz(~x) + 1;
+	case 1:
+		/* Nothing to do */
 		break;
 	}
 
@@ -228,7 +245,7 @@ __sigqueue_alloc(int sig, struct task_struct *t, gfp_t flags, int override_rlimi
 
 	if (override_rlimit ||
 	    atomic_read(&user->sigpending) <=
-			t->signal->rlim[RLIMIT_SIGPENDING].rlim_cur) {
+			task_rlimit(t, RLIMIT_SIGPENDING)) {
 		q = kmem_cache_alloc(sigqueue_cachep, flags);
 	} else {
 		print_dropped_signal(sig);
diff --git a/kernel/slow-work.c b/kernel/slow-work.c
index 7494bbf5a27..7d3f4fa9ef4 100644
--- a/kernel/slow-work.c
+++ b/kernel/slow-work.c
@@ -637,7 +637,7 @@ int delayed_slow_work_enqueue(struct delayed_slow_work *dwork,
 			goto cancelled;
 
 		/* the timer holds a reference whilst it is pending */
-		ret = work->ops->get_ref(work);
+		ret = slow_work_get_ref(work);
 		if (ret < 0)
 			goto cant_get_ref;
 
diff --git a/kernel/slow-work.h b/kernel/slow-work.h
index 321f3c59d73..a29ebd1ef41 100644
--- a/kernel/slow-work.h
+++ b/kernel/slow-work.h
@@ -43,28 +43,28 @@ extern void slow_work_new_thread_desc(struct slow_work *, struct seq_file *);
  */
 static inline void slow_work_set_thread_pid(int id, pid_t pid)
 {
-#ifdef CONFIG_SLOW_WORK_PROC
+#ifdef CONFIG_SLOW_WORK_DEBUG
 	slow_work_pids[id] = pid;
 #endif
 }
 
 static inline void slow_work_mark_time(struct slow_work *work)
 {
-#ifdef CONFIG_SLOW_WORK_PROC
+#ifdef CONFIG_SLOW_WORK_DEBUG
 	work->mark = CURRENT_TIME;
 #endif
 }
 
 static inline void slow_work_begin_exec(int id, struct slow_work *work)
 {
-#ifdef CONFIG_SLOW_WORK_PROC
+#ifdef CONFIG_SLOW_WORK_DEBUG
 	slow_work_execs[id] = work;
 #endif
 }
 
 static inline void slow_work_end_exec(int id, struct slow_work *work)
 {
-#ifdef CONFIG_SLOW_WORK_PROC
+#ifdef CONFIG_SLOW_WORK_DEBUG
 	write_lock(&slow_work_execs_lock);
 	slow_work_execs[id] = NULL;
 	write_unlock(&slow_work_execs_lock);
diff --git a/kernel/smp.c b/kernel/smp.c
index f1040842244..3fc69733618 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -9,11 +9,10 @@
 #include <linux/module.h>
 #include <linux/percpu.h>
 #include <linux/init.h>
+#include <linux/gfp.h>
 #include <linux/smp.h>
 #include <linux/cpu.h>
 
-static DEFINE_PER_CPU(struct call_single_queue, call_single_queue);
-
 static struct {
 	struct list_head	queue;
 	raw_spinlock_t		lock;
@@ -33,12 +32,14 @@ struct call_function_data {
 	cpumask_var_t		cpumask;
 };
 
+static DEFINE_PER_CPU_SHARED_ALIGNED(struct call_function_data, cfd_data);
+
 struct call_single_queue {
 	struct list_head	list;
 	raw_spinlock_t		lock;
 };
 
-static DEFINE_PER_CPU(struct call_function_data, cfd_data);
+static DEFINE_PER_CPU_SHARED_ALIGNED(struct call_single_queue, call_single_queue);
 
 static int
 hotplug_cfd(struct notifier_block *nfb, unsigned long action, void *hcpu)
@@ -256,7 +257,7 @@ void generic_smp_call_function_single_interrupt(void)
 	}
 }
 
-static DEFINE_PER_CPU(struct call_single_data, csd_data);
+static DEFINE_PER_CPU_SHARED_ALIGNED(struct call_single_data, csd_data);
 
 /*
  * smp_call_function_single - Run a function on a specific CPU
diff --git a/kernel/softirq.c b/kernel/softirq.c
index a09502e2ef7..7c1a67ef027 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -500,22 +500,17 @@ EXPORT_SYMBOL(tasklet_kill);
  */
 
 /*
- * The trampoline is called when the hrtimer expires. If this is
- * called from the hrtimer interrupt then we schedule the tasklet as
- * the timer callback function expects to run in softirq context. If
- * it's called in softirq context anyway (i.e. high resolution timers
- * disabled) then the hrtimer callback is called right away.
+ * The trampoline is called when the hrtimer expires. It schedules a tasklet
+ * to run __tasklet_hrtimer_trampoline() which in turn will call the intended
+ * hrtimer callback, but from softirq context.
  */
 static enum hrtimer_restart __hrtimer_tasklet_trampoline(struct hrtimer *timer)
 {
 	struct tasklet_hrtimer *ttimer =
 		container_of(timer, struct tasklet_hrtimer, timer);
 
-	if (hrtimer_is_hres_active(timer)) {
-		tasklet_hi_schedule(&ttimer->tasklet);
-		return HRTIMER_NORESTART;
-	}
-	return ttimer->function(timer);
+	tasklet_hi_schedule(&ttimer->tasklet);
+	return HRTIMER_NORESTART;
 }
 
 /*
diff --git a/kernel/softlockup.c b/kernel/softlockup.c
index d22579087e2..4b493f67dcb 100644
--- a/kernel/softlockup.c
+++ b/kernel/softlockup.c
@@ -25,6 +25,7 @@ static DEFINE_SPINLOCK(print_lock);
 static DEFINE_PER_CPU(unsigned long, softlockup_touch_ts); /* touch timestamp */
 static DEFINE_PER_CPU(unsigned long, softlockup_print_ts); /* print timestamp */
 static DEFINE_PER_CPU(struct task_struct *, softlockup_watchdog);
+static DEFINE_PER_CPU(bool, softlock_touch_sync);
 
 static int __read_mostly did_panic;
 int __read_mostly softlockup_thresh = 60;
@@ -79,6 +80,12 @@ void touch_softlockup_watchdog(void)
 }
 EXPORT_SYMBOL(touch_softlockup_watchdog);
 
+void touch_softlockup_watchdog_sync(void)
+{
+	__raw_get_cpu_var(softlock_touch_sync) = true;
+	__raw_get_cpu_var(softlockup_touch_ts) = 0;
+}
+
 void touch_all_softlockup_watchdogs(void)
 {
 	int cpu;
@@ -118,6 +125,14 @@ void softlockup_tick(void)
 	}
 
 	if (touch_ts == 0) {
+		if (unlikely(per_cpu(softlock_touch_sync, this_cpu))) {
+			/*
+			 * If the time stamp was touched atomically
+			 * make sure the scheduler tick is up to date.
+			 */
+			per_cpu(softlock_touch_sync, this_cpu) = false;
+			sched_clock_tick();
+		}
 		__touch_softlockup_watchdog();
 		return;
 	}
@@ -140,11 +155,11 @@ void softlockup_tick(void)
 	 * Wake up the high-prio watchdog task twice per
 	 * threshold timespan.
 	 */
-	if (now > touch_ts + softlockup_thresh/2)
+	if (time_after(now - softlockup_thresh/2, touch_ts))
 		wake_up_process(per_cpu(softlockup_watchdog, this_cpu));
 
 	/* Warn about unreasonable delays: */
-	if (now <= (touch_ts + softlockup_thresh))
+	if (time_before_eq(now - softlockup_thresh, touch_ts))
 		return;
 
 	per_cpu(softlockup_print_ts, this_cpu) = touch_ts;
diff --git a/kernel/srcu.c b/kernel/srcu.c
index 818d7d9aa03..2980da3fd50 100644
--- a/kernel/srcu.c
+++ b/kernel/srcu.c
@@ -30,10 +30,33 @@
 #include <linux/preempt.h>
 #include <linux/rcupdate.h>
 #include <linux/sched.h>
-#include <linux/slab.h>
 #include <linux/smp.h>
 #include <linux/srcu.h>
 
+static int init_srcu_struct_fields(struct srcu_struct *sp)
+{
+	sp->completed = 0;
+	mutex_init(&sp->mutex);
+	sp->per_cpu_ref = alloc_percpu(struct srcu_struct_array);
+	return sp->per_cpu_ref ? 0 : -ENOMEM;
+}
+
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+
+int __init_srcu_struct(struct srcu_struct *sp, const char *name,
+		       struct lock_class_key *key)
+{
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+	/* Don't re-initialize a lock while it is held. */
+	debug_check_no_locks_freed((void *)sp, sizeof(*sp));
+	lockdep_init_map(&sp->dep_map, name, key, 0);
+#endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
+	return init_srcu_struct_fields(sp);
+}
+EXPORT_SYMBOL_GPL(__init_srcu_struct);
+
+#else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
+
 /**
  * init_srcu_struct - initialize a sleep-RCU structure
  * @sp: structure to initialize.
@@ -44,13 +67,12 @@
  */
 int init_srcu_struct(struct srcu_struct *sp)
 {
-	sp->completed = 0;
-	mutex_init(&sp->mutex);
-	sp->per_cpu_ref = alloc_percpu(struct srcu_struct_array);
-	return (sp->per_cpu_ref ? 0 : -ENOMEM);
+	return init_srcu_struct_fields(sp);
 }
 EXPORT_SYMBOL_GPL(init_srcu_struct);
 
+#endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */
+
 /*
  * srcu_readers_active_idx -- returns approximate number of readers
  *	active on the specified rank of per-CPU counters.
@@ -100,15 +122,12 @@ void cleanup_srcu_struct(struct srcu_struct *sp)
 }
 EXPORT_SYMBOL_GPL(cleanup_srcu_struct);
 
-/**
- * srcu_read_lock - register a new reader for an SRCU-protected structure.
- * @sp: srcu_struct in which to register the new reader.
- *
+/*
  * Counts the new reader in the appropriate per-CPU element of the
  * srcu_struct.  Must be called from process context.
  * Returns an index that must be passed to the matching srcu_read_unlock().
  */
-int srcu_read_lock(struct srcu_struct *sp)
+int __srcu_read_lock(struct srcu_struct *sp)
 {
 	int idx;
 
@@ -120,31 +139,27 @@ int srcu_read_lock(struct srcu_struct *sp)
 	preempt_enable();
 	return idx;
 }
-EXPORT_SYMBOL_GPL(srcu_read_lock);
+EXPORT_SYMBOL_GPL(__srcu_read_lock);
 
-/**
- * srcu_read_unlock - unregister a old reader from an SRCU-protected structure.
- * @sp: srcu_struct in which to unregister the old reader.
- * @idx: return value from corresponding srcu_read_lock().
- *
+/*
  * Removes the count for the old reader from the appropriate per-CPU
  * element of the srcu_struct.  Note that this may well be a different
  * CPU than that which was incremented by the corresponding srcu_read_lock().
  * Must be called from process context.
  */
-void srcu_read_unlock(struct srcu_struct *sp, int idx)
+void __srcu_read_unlock(struct srcu_struct *sp, int idx)
 {
 	preempt_disable();
 	srcu_barrier();  /* ensure compiler won't misorder critical section. */
 	per_cpu_ptr(sp->per_cpu_ref, smp_processor_id())->c[idx]--;
 	preempt_enable();
 }
-EXPORT_SYMBOL_GPL(srcu_read_unlock);
+EXPORT_SYMBOL_GPL(__srcu_read_unlock);
 
 /*
  * Helper function for synchronize_srcu() and synchronize_srcu_expedited().
  */
-void __synchronize_srcu(struct srcu_struct *sp, void (*sync_func)(void))
+static void __synchronize_srcu(struct srcu_struct *sp, void (*sync_func)(void))
 {
 	int idx;
 
diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c
index 912823e2a11..9bb9fb1bd79 100644
--- a/kernel/stop_machine.c
+++ b/kernel/stop_machine.c
@@ -45,7 +45,7 @@ static int refcount;
 static struct workqueue_struct *stop_machine_wq;
 static struct stop_machine_data active, idle;
 static const struct cpumask *active_cpus;
-static void *stop_machine_work;
+static void __percpu *stop_machine_work;
 
 static void set_state(enum stopmachine_state newstate)
 {
diff --git a/kernel/sys.c b/kernel/sys.c
index 26a6b73a6b8..7cb426a5896 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -33,8 +33,10 @@
 #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>
+#include <linux/gfp.h>
 
 #include <linux/compat.h>
 #include <linux/syscalls.h>
@@ -222,6 +224,7 @@ SYSCALL_DEFINE2(getpriority, int, which, int, who)
 	if (which > PRIO_USER || which < PRIO_PROCESS)
 		return -EINVAL;
 
+	rcu_read_lock();
 	read_lock(&tasklist_lock);
 	switch (which) {
 		case PRIO_PROCESS:
@@ -267,6 +270,7 @@ SYSCALL_DEFINE2(getpriority, int, which, int, who)
 	}
 out_unlock:
 	read_unlock(&tasklist_lock);
+	rcu_read_unlock();
 
 	return retval;
 }
@@ -569,13 +573,7 @@ static int set_user(struct cred *new)
 	if (!new_user)
 		return -EAGAIN;
 
-	if (!task_can_switch_user(new_user, current)) {
-		free_uid(new_user);
-		return -EINVAL;
-	}
-
-	if (atomic_read(&new_user->processes) >=
-				current->signal->rlim[RLIMIT_NPROC].rlim_cur &&
+	if (atomic_read(&new_user->processes) >= rlimit(RLIMIT_NPROC) &&
 			new_user != INIT_USER) {
 		free_uid(new_user);
 		return -EAGAIN;
@@ -1118,6 +1116,15 @@ out:
 
 DECLARE_RWSEM(uts_sem);
 
+#ifdef COMPAT_UTS_MACHINE
+#define override_architecture(name) \
+	(personality(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;
@@ -1126,9 +1133,66 @@ 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 695384f12a7..70f2ea758ff 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 ac72c9e6bd9..a38af430f0d 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>
@@ -50,6 +51,7 @@
 #include <linux/ftrace.h>
 #include <linux/slow-work.h>
 #include <linux/perf_event.h>
+#include <linux/kprobes.h>
 
 #include <asm/uaccess.h>
 #include <asm/processor.h>
@@ -59,6 +61,18 @@
 #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
 
 #ifdef CONFIG_NMI_WATCHDOG
 #include <linux/nmi.h>
@@ -68,8 +82,6 @@
 #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;
@@ -91,9 +103,6 @@ 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
@@ -123,14 +132,6 @@ 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
@@ -152,10 +153,6 @@ 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;
@@ -163,10 +160,6 @@ 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);
@@ -205,9 +198,6 @@ 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[] = {
@@ -1454,7 +1444,7 @@ static struct ctl_table fs_table[] = {
 };
 
 static struct ctl_table debug_table[] = {
-#if defined(CONFIG_X86) || defined(CONFIG_PPC)
+#if defined(CONFIG_X86) || defined(CONFIG_PPC) || defined(CONFIG_SPARC)
 	{
 		.procname	= "exception-trace",
 		.data		= &show_unhandled_signals,
@@ -1463,6 +1453,17 @@ static struct ctl_table debug_table[] = {
 		.proc_handler	= proc_dointvec
 	},
 #endif
+#if defined(CONFIG_OPTPROBES)
+	{
+		.procname	= "kprobes-optimization",
+		.data		= &sysctl_kprobes_optimization,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_kprobes_optimization_handler,
+		.extra1		= &zero,
+		.extra2		= &one,
+	},
+#endif
 	{ }
 };
 
diff --git a/kernel/sysctl_binary.c b/kernel/sysctl_binary.c
index 8f5d16e0707..59030570f5c 100644
--- a/kernel/sysctl_binary.c
+++ b/kernel/sysctl_binary.c
@@ -13,6 +13,7 @@
 #include <linux/file.h>
 #include <linux/ctype.h>
 #include <linux/netdevice.h>
+#include <linux/slab.h>
 
 #ifdef CONFIG_SYSCTL_SYSCALL
 
@@ -1331,7 +1332,7 @@ static ssize_t binary_sysctl(const int *name, int nlen,
 	ssize_t result;
 	char *pathname;
 	int flags;
-	int acc_mode, fmode;
+	int acc_mode;
 
 	pathname = sysctl_getname(name, nlen, &table);
 	result = PTR_ERR(pathname);
@@ -1342,15 +1343,12 @@ static ssize_t binary_sysctl(const int *name, int nlen,
 	if (oldval && oldlen && newval && newlen) {
 		flags = O_RDWR;
 		acc_mode = MAY_READ | MAY_WRITE;
-		fmode = FMODE_READ | FMODE_WRITE;
 	} else if (newval && newlen) {
 		flags = O_WRONLY;
 		acc_mode = MAY_WRITE;
-		fmode = FMODE_WRITE;
 	} else if (oldval && oldlen) {
 		flags = O_RDONLY;
 		acc_mode = MAY_READ;
-		fmode = FMODE_READ;
 	} else {
 		result = 0;
 		goto out_putname;
@@ -1361,7 +1359,7 @@ static ssize_t binary_sysctl(const int *name, int nlen,
 	if (result)
 		goto out_putname;
 
-	result = may_open(&nd.path, acc_mode, fmode);
+	result = may_open(&nd.path, acc_mode, flags);
 	if (result)
 		goto out_putpath;
 
diff --git a/kernel/taskstats.c b/kernel/taskstats.c
index ea8384d3caa..11281d5792b 100644
--- a/kernel/taskstats.c
+++ b/kernel/taskstats.c
@@ -22,6 +22,7 @@
 #include <linux/delayacct.h>
 #include <linux/cpumask.h>
 #include <linux/percpu.h>
+#include <linux/slab.h>
 #include <linux/cgroupstats.h>
 #include <linux/cgroup.h>
 #include <linux/fs.h>
@@ -46,15 +47,13 @@ static struct genl_family family = {
 	.maxattr	= TASKSTATS_CMD_ATTR_MAX,
 };
 
-static struct nla_policy taskstats_cmd_get_policy[TASKSTATS_CMD_ATTR_MAX+1]
-__read_mostly = {
+static const struct nla_policy taskstats_cmd_get_policy[TASKSTATS_CMD_ATTR_MAX+1] = {
 	[TASKSTATS_CMD_ATTR_PID]  = { .type = NLA_U32 },
 	[TASKSTATS_CMD_ATTR_TGID] = { .type = NLA_U32 },
 	[TASKSTATS_CMD_ATTR_REGISTER_CPUMASK] = { .type = NLA_STRING },
 	[TASKSTATS_CMD_ATTR_DEREGISTER_CPUMASK] = { .type = NLA_STRING },};
 
-static struct nla_policy
-cgroupstats_cmd_get_policy[CGROUPSTATS_CMD_ATTR_MAX+1] __read_mostly = {
+static const struct nla_policy cgroupstats_cmd_get_policy[CGROUPSTATS_CMD_ATTR_MAX+1] = {
 	[CGROUPSTATS_CMD_ATTR_FD] = { .type = NLA_U32 },
 };
 
diff --git a/kernel/time.c b/kernel/time.c
index 804798005d1..656dccfe1cb 100644
--- a/kernel/time.c
+++ b/kernel/time.c
@@ -35,7 +35,6 @@
 #include <linux/syscalls.h>
 #include <linux/security.h>
 #include <linux/fs.h>
-#include <linux/slab.h>
 #include <linux/math64.h>
 #include <linux/ptrace.h>
 
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index e85c23404d3..1f5dde63745 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -343,7 +343,19 @@ static void clocksource_resume_watchdog(void)
 {
 	unsigned long flags;
 
-	spin_lock_irqsave(&watchdog_lock, flags);
+	/*
+	 * We use trylock here to avoid a potential dead lock when
+	 * kgdb calls this code after the kernel has been stopped with
+	 * watchdog_lock held. When watchdog_lock is held we just
+	 * return and accept, that the watchdog might trigger and mark
+	 * the monitored clock source (usually TSC) unstable.
+	 *
+	 * This does not affect the other caller clocksource_resume()
+	 * because at this point the kernel is UP, interrupts are
+	 * disabled and nothing can hold watchdog_lock.
+	 */
+	if (!spin_trylock_irqsave(&watchdog_lock, flags))
+		return;
 	clocksource_reset_watchdog();
 	spin_unlock_irqrestore(&watchdog_lock, flags);
 }
@@ -441,6 +453,18 @@ static inline int clocksource_watchdog_kthread(void *data) { return 0; }
 #endif /* CONFIG_CLOCKSOURCE_WATCHDOG */
 
 /**
+ * clocksource_suspend - suspend the clocksource(s)
+ */
+void clocksource_suspend(void)
+{
+	struct clocksource *cs;
+
+	list_for_each_entry_reverse(cs, &clocksource_list, list)
+		if (cs->suspend)
+			cs->suspend(cs);
+}
+
+/**
  * clocksource_resume - resume the clocksource(s)
  */
 void clocksource_resume(void)
@@ -449,7 +473,7 @@ void clocksource_resume(void)
 
 	list_for_each_entry(cs, &clocksource_list, list)
 		if (cs->resume)
-			cs->resume();
+			cs->resume(cs);
 
 	clocksource_resume_watchdog();
 }
@@ -458,8 +482,8 @@ void clocksource_resume(void)
  * clocksource_touch_watchdog - Update watchdog
  *
  * Update the watchdog after exception contexts such as kgdb so as not
- * to incorrectly trip the watchdog.
- *
+ * to incorrectly trip the watchdog. This might fail when the kernel
+ * was stopped in code which holds watchdog_lock.
  */
 void clocksource_touch_watchdog(void)
 {
@@ -568,6 +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/time/ntp.c b/kernel/time/ntp.c
index 4800f933910..7c0f180d6e9 100644
--- a/kernel/time/ntp.c
+++ b/kernel/time/ntp.c
@@ -58,10 +58,10 @@ static s64			time_offset;
 static long			time_constant = 2;
 
 /* maximum error (usecs):						*/
-long				time_maxerror = NTP_PHASE_LIMIT;
+static long			time_maxerror = NTP_PHASE_LIMIT;
 
 /* estimated error (usecs):						*/
-long				time_esterror = NTP_PHASE_LIMIT;
+static long			time_esterror = NTP_PHASE_LIMIT;
 
 /* frequency offset (scaled nsecs/secs):				*/
 static s64			time_freq;
@@ -142,11 +142,11 @@ static void ntp_update_offset(long offset)
 	 * Select how the frequency is to be controlled
 	 * and in which mode (PLL or FLL).
 	 */
-	secs = xtime.tv_sec - time_reftime;
+	secs = get_seconds() - time_reftime;
 	if (unlikely(time_status & STA_FREQHOLD))
 		secs = 0;
 
-	time_reftime = xtime.tv_sec;
+	time_reftime = get_seconds();
 
 	offset64    = offset;
 	freq_adj    = (offset64 * secs) <<
@@ -368,7 +368,7 @@ static inline void process_adj_status(struct timex *txc, struct timespec *ts)
 	 * reference time to current time.
 	 */
 	if (!(time_status & STA_PLL) && (txc->status & STA_PLL))
-		time_reftime = xtime.tv_sec;
+		time_reftime = get_seconds();
 
 	/* only set allowed bits */
 	time_status &= STA_RONLY;
diff --git a/kernel/time/tick-oneshot.c b/kernel/time/tick-oneshot.c
index 0a8a213016f..aada0e52680 100644
--- a/kernel/time/tick-oneshot.c
+++ b/kernel/time/tick-oneshot.c
@@ -22,6 +22,29 @@
 
 #include "tick-internal.h"
 
+/* Limit min_delta to a jiffie */
+#define MIN_DELTA_LIMIT		(NSEC_PER_SEC / HZ)
+
+static int tick_increase_min_delta(struct clock_event_device *dev)
+{
+	/* Nothing to do if we already reached the limit */
+	if (dev->min_delta_ns >= MIN_DELTA_LIMIT)
+		return -ETIME;
+
+	if (dev->min_delta_ns < 5000)
+		dev->min_delta_ns = 5000;
+	else
+		dev->min_delta_ns += dev->min_delta_ns >> 1;
+
+	if (dev->min_delta_ns > MIN_DELTA_LIMIT)
+		dev->min_delta_ns = MIN_DELTA_LIMIT;
+
+	printk(KERN_WARNING "CE: %s increased min_delta_ns to %llu nsec\n",
+	       dev->name ? dev->name : "?",
+	       (unsigned long long) dev->min_delta_ns);
+	return 0;
+}
+
 /**
  * tick_program_event internal worker function
  */
@@ -37,23 +60,28 @@ int tick_dev_program_event(struct clock_event_device *dev, ktime_t expires,
 		if (!ret || !force)
 			return ret;
 
+		dev->retries++;
 		/*
-		 * We tried 2 times to program the device with the given
-		 * min_delta_ns. If that's not working then we double it
+		 * We tried 3 times to program the device with the given
+		 * min_delta_ns. If that's not working then we increase it
 		 * and emit a warning.
 		 */
 		if (++i > 2) {
 			/* Increase the min. delta and try again */
-			if (!dev->min_delta_ns)
-				dev->min_delta_ns = 5000;
-			else
-				dev->min_delta_ns += dev->min_delta_ns >> 1;
-
-			printk(KERN_WARNING
-			       "CE: %s increasing min_delta_ns to %llu nsec\n",
-			       dev->name ? dev->name : "?",
-			       (unsigned long long) dev->min_delta_ns << 1);
-
+			if (tick_increase_min_delta(dev)) {
+				/*
+				 * Get out of the loop if min_delta_ns
+				 * hit the limit already. That's
+				 * better than staying here forever.
+				 *
+				 * We clear next_event so we have a
+				 * chance that the box survives.
+				 */
+				printk(KERN_WARNING
+				       "CE: Reprogramming failure. Giving up\n");
+				dev->next_event.tv64 = KTIME_MAX;
+				return -ETIME;
+			}
 			i = 0;
 		}
 
diff --git a/kernel/time/timecompare.c b/kernel/time/timecompare.c
index 12f5c55090b..ac38fbb176c 100644
--- a/kernel/time/timecompare.c
+++ b/kernel/time/timecompare.c
@@ -19,6 +19,7 @@
 
 #include <linux/timecompare.h>
 #include <linux/module.h>
+#include <linux/slab.h>
 #include <linux/math64.h>
 
 /*
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 7faaa32fbf4..39f6177fafa 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -622,6 +622,7 @@ static int timekeeping_suspend(struct sys_device *dev, pm_message_t state)
 	write_sequnlock_irqrestore(&xtime_lock, flags);
 
 	clockevents_notify(CLOCK_EVT_NOTIFY_SUSPEND, NULL);
+	clocksource_suspend();
 
 	return 0;
 }
@@ -817,7 +818,8 @@ void update_wall_time(void)
 	shift = min(shift, maxshift);
 	while (offset >= timekeeper.cycle_interval) {
 		offset = logarithmic_accumulation(offset, shift);
-		shift--;
+		if(offset < timekeeper.cycle_interval<<shift)
+			shift--;
 	}
 
 	/* correct the clock when NTP error is too big */
@@ -880,6 +882,7 @@ void getboottime(struct timespec *ts)
 
 	set_normalized_timespec(ts, -boottime.tv_sec, -boottime.tv_nsec);
 }
+EXPORT_SYMBOL_GPL(getboottime);
 
 /**
  * monotonic_to_bootbased - Convert the monotonic time to boot based.
@@ -889,6 +892,7 @@ void monotonic_to_bootbased(struct timespec *ts)
 {
 	*ts = timespec_add_safe(*ts, total_sleep_time);
 }
+EXPORT_SYMBOL_GPL(monotonic_to_bootbased);
 
 unsigned long get_seconds(void)
 {
diff --git a/kernel/time/timer_list.c b/kernel/time/timer_list.c
index bdfb8dd1050..1a4a7dd7877 100644
--- a/kernel/time/timer_list.c
+++ b/kernel/time/timer_list.c
@@ -228,6 +228,7 @@ print_tickdevice(struct seq_file *m, struct tick_device *td, int cpu)
 	SEQ_printf(m, " event_handler:  ");
 	print_name_offset(m, dev->event_handler);
 	SEQ_printf(m, "\n");
+	SEQ_printf(m, " retries:        %lu\n", dev->retries);
 }
 
 static void timer_list_show_tickdevices(struct seq_file *m)
@@ -257,7 +258,7 @@ static int timer_list_show(struct seq_file *m, void *v)
 	u64 now = ktime_to_ns(ktime_get());
 	int cpu;
 
-	SEQ_printf(m, "Timer List Version: v0.5\n");
+	SEQ_printf(m, "Timer List Version: v0.6\n");
 	SEQ_printf(m, "HRTIMER_MAX_CLOCK_BASES: %d\n", HRTIMER_MAX_CLOCK_BASES);
 	SEQ_printf(m, "now at %Ld nsecs\n", (unsigned long long)now);
 
diff --git a/kernel/timer.c b/kernel/timer.c
index c61a7949387..aeb6a54f277 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -39,6 +39,7 @@
 #include <linux/kallsyms.h>
 #include <linux/perf_event.h>
 #include <linux/sched.h>
+#include <linux/slab.h>
 
 #include <asm/uaccess.h>
 #include <asm/unistd.h>
@@ -880,6 +881,7 @@ int try_to_del_timer_sync(struct timer_list *timer)
 	if (base->running_timer == timer)
 		goto out;
 
+	timer_stats_timer_clear_start_info(timer);
 	ret = 0;
 	if (timer_pending(timer)) {
 		detach_timer(timer, 1);
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 6c22d8a2f28..13e13d428cd 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -27,9 +27,7 @@ config HAVE_FUNCTION_GRAPH_TRACER
 config HAVE_FUNCTION_GRAPH_FP_TEST
 	bool
 	help
-	 An arch may pass in a unique value (frame pointer) to both the
-	 entering and exiting of a function. On exit, the value is compared
-	 and if it does not match, then it will panic the kernel.
+	  See Documentation/trace/ftrace-design.txt
 
 config HAVE_FUNCTION_TRACE_MCOUNT_TEST
 	bool
@@ -330,15 +328,6 @@ config BRANCH_TRACER
 
 	  Say N if unsure.
 
-config POWER_TRACER
-	bool "Trace power consumption behavior"
-	depends on X86
-	select GENERIC_TRACER
-	help
-	  This tracer helps developers to analyze and optimize the kernel's
-	  power management decisions, specifically the C-state and P-state
-	  behavior.
-
 config KSYM_TRACER
 	bool "Trace read and write access on kernel memory locations"
 	depends on HAVE_HW_BREAKPOINT
@@ -451,7 +440,7 @@ config BLK_DEV_IO_TRACE
 
 config KPROBE_EVENT
 	depends on KPROBES
-	depends on X86
+	depends on HAVE_REGS_AND_STACK_ACCESS_API
 	bool "Enable kprobes-based dynamic events"
 	select TRACING
 	default y
diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile
index d00c6fe23f5..78edc649003 100644
--- a/kernel/trace/Makefile
+++ b/kernel/trace/Makefile
@@ -52,7 +52,7 @@ obj-$(CONFIG_EVENT_TRACING) += trace_events.o
 obj-$(CONFIG_EVENT_TRACING) += trace_export.o
 obj-$(CONFIG_FTRACE_SYSCALLS) += trace_syscalls.o
 ifeq ($(CONFIG_PERF_EVENTS),y)
-obj-$(CONFIG_EVENT_TRACING) += trace_event_profile.o
+obj-$(CONFIG_EVENT_TRACING) += trace_event_perf.o
 endif
 obj-$(CONFIG_EVENT_TRACING) += trace_events_filter.o
 obj-$(CONFIG_KPROBE_EVENT) += trace_kprobe.o
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index d9d6206e0b1..b3bc91a3f51 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -21,6 +21,7 @@
 #include <linux/percpu.h>
 #include <linux/init.h>
 #include <linux/mutex.h>
+#include <linux/slab.h>
 #include <linux/debugfs.h>
 #include <linux/smp_lock.h>
 #include <linux/time.h>
@@ -540,9 +541,10 @@ int blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
 	if (ret)
 		return ret;
 
-	if (copy_to_user(arg, &buts, sizeof(buts)))
+	if (copy_to_user(arg, &buts, sizeof(buts))) {
+		blk_trace_remove(q);
 		return -EFAULT;
-
+	}
 	return 0;
 }
 EXPORT_SYMBOL_GPL(blk_trace_setup);
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 1904797f4a8..2404b59b309 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -24,9 +24,11 @@
 #include <linux/uaccess.h>
 #include <linux/ftrace.h>
 #include <linux/sysctl.h>
+#include <linux/slab.h>
 #include <linux/ctype.h>
 #include <linux/list.h>
 #include <linux/hash.h>
+#include <linux/rcupdate.h>
 
 #include <trace/events/sched.h>
 
@@ -84,22 +86,22 @@ 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 +156,7 @@ 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 +2277,8 @@ __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);
@@ -2402,6 +2405,7 @@ static const struct file_operations ftrace_notrace_fops = {
 static DEFINE_MUTEX(graph_lock);
 
 int ftrace_graph_count;
+int ftrace_graph_filter_enabled;
 unsigned long ftrace_graph_funcs[FTRACE_GRAPH_MAX_FUNCS] __read_mostly;
 
 static void *
@@ -2424,7 +2428,7 @@ static void *g_start(struct seq_file *m, loff_t *pos)
 	mutex_lock(&graph_lock);
 
 	/* Nothing, tell g_show to print all functions are enabled */
-	if (!ftrace_graph_count && !*pos)
+	if (!ftrace_graph_filter_enabled && !*pos)
 		return (void *)1;
 
 	return __g_next(m, pos);
@@ -2470,6 +2474,7 @@ ftrace_graph_open(struct inode *inode, struct file *file)
 	mutex_lock(&graph_lock);
 	if ((file->f_mode & FMODE_WRITE) &&
 	    (file->f_flags & O_TRUNC)) {
+		ftrace_graph_filter_enabled = 0;
 		ftrace_graph_count = 0;
 		memset(ftrace_graph_funcs, 0, sizeof(ftrace_graph_funcs));
 	}
@@ -2495,7 +2500,7 @@ ftrace_set_func(unsigned long *array, int *idx, char *buffer)
 	struct dyn_ftrace *rec;
 	struct ftrace_page *pg;
 	int search_len;
-	int found = 0;
+	int fail = 1;
 	int type, not;
 	char *search;
 	bool exists;
@@ -2506,37 +2511,51 @@ ftrace_set_func(unsigned long *array, int *idx, char *buffer)
 
 	/* decode regex */
 	type = filter_parse_regex(buffer, strlen(buffer), &search, &not);
-	if (not)
-		return -EINVAL;
+	if (!not && *idx >= FTRACE_GRAPH_MAX_FUNCS)
+		return -EBUSY;
 
 	search_len = strlen(search);
 
 	mutex_lock(&ftrace_lock);
 	do_for_each_ftrace_rec(pg, rec) {
 
-		if (*idx >= FTRACE_GRAPH_MAX_FUNCS)
-			break;
-
 		if (rec->flags & (FTRACE_FL_FAILED | FTRACE_FL_FREE))
 			continue;
 
 		if (ftrace_match_record(rec, search, search_len, type)) {
-			/* ensure it is not already in the array */
+			/* if it is in the array */
 			exists = false;
-			for (i = 0; i < *idx; i++)
+			for (i = 0; i < *idx; i++) {
 				if (array[i] == rec->ip) {
 					exists = true;
 					break;
 				}
-			if (!exists)
-				array[(*idx)++] = rec->ip;
-			found = 1;
+			}
+
+			if (!not) {
+				fail = 0;
+				if (!exists) {
+					array[(*idx)++] = rec->ip;
+					if (*idx >= FTRACE_GRAPH_MAX_FUNCS)
+						goto out;
+				}
+			} else {
+				if (exists) {
+					array[i] = array[--(*idx)];
+					array[*idx] = 0;
+					fail = 0;
+				}
+			}
 		}
 	} while_for_each_ftrace_rec();
-
+out:
 	mutex_unlock(&ftrace_lock);
 
-	return found ? 0 : -EINVAL;
+	if (fail)
+		return -EINVAL;
+
+	ftrace_graph_filter_enabled = 1;
+	return 0;
 }
 
 static ssize_t
@@ -2546,16 +2565,11 @@ ftrace_graph_write(struct file *file, const char __user *ubuf,
 	struct trace_parser parser;
 	ssize_t read, ret;
 
-	if (!cnt || cnt < 0)
+	if (!cnt)
 		return 0;
 
 	mutex_lock(&graph_lock);
 
-	if (ftrace_graph_count >= FTRACE_GRAPH_MAX_FUNCS) {
-		ret = -EBUSY;
-		goto out_unlock;
-	}
-
 	if (trace_parser_get_init(&parser, FTRACE_BUFF_MAX)) {
 		ret = -ENOMEM;
 		goto out_unlock;
@@ -3340,6 +3354,7 @@ 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;
@@ -3349,7 +3364,6 @@ 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/power-traces.c b/kernel/trace/power-traces.c
index 9f4f565b01e..a22582a0616 100644
--- a/kernel/trace/power-traces.c
+++ b/kernel/trace/power-traces.c
@@ -9,7 +9,6 @@
 #include <linux/workqueue.h>
 #include <linux/sched.h>
 #include <linux/module.h>
-#include <linux/slab.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/power.h>
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index edefe3b2801..41ca394feb2 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -14,12 +14,14 @@
 #include <linux/module.h>
 #include <linux/percpu.h>
 #include <linux/mutex.h>
+#include <linux/slab.h>
 #include <linux/init.h>
 #include <linux/hash.h>
 #include <linux/list.h>
 #include <linux/cpu.h>
 #include <linux/fs.h>
 
+#include <asm/local.h>
 #include "trace.h"
 
 /*
@@ -206,6 +208,14 @@ EXPORT_SYMBOL_GPL(tracing_is_on);
 #define RB_MAX_SMALL_DATA	(RB_ALIGNMENT * RINGBUF_TYPE_DATA_TYPE_LEN_MAX)
 #define RB_EVNT_MIN_SIZE	8U	/* two 32bit words */
 
+#if !defined(CONFIG_64BIT) || defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)
+# define RB_FORCE_8BYTE_ALIGNMENT	0
+# define RB_ARCH_ALIGNMENT		RB_ALIGNMENT
+#else
+# define RB_FORCE_8BYTE_ALIGNMENT	1
+# define RB_ARCH_ALIGNMENT		8U
+#endif
+
 /* define RINGBUF_TYPE_DATA for 'case RINGBUF_TYPE_DATA:' */
 #define RINGBUF_TYPE_DATA 0 ... RINGBUF_TYPE_DATA_TYPE_LEN_MAX
 
@@ -464,6 +474,8 @@ struct ring_buffer_iter {
 	struct ring_buffer_per_cpu	*cpu_buffer;
 	unsigned long			head;
 	struct buffer_page		*head_page;
+	struct buffer_page		*cache_reader_page;
+	unsigned long			cache_read;
 	u64				read_stamp;
 };
 
@@ -1198,18 +1210,19 @@ rb_remove_pages(struct ring_buffer_per_cpu *cpu_buffer, unsigned nr_pages)
 
 	for (i = 0; i < nr_pages; i++) {
 		if (RB_WARN_ON(cpu_buffer, list_empty(cpu_buffer->pages)))
-			return;
+			goto out;
 		p = cpu_buffer->pages->next;
 		bpage = list_entry(p, struct buffer_page, list);
 		list_del_init(&bpage->list);
 		free_buffer_page(bpage);
 	}
 	if (RB_WARN_ON(cpu_buffer, list_empty(cpu_buffer->pages)))
-		return;
+		goto out;
 
 	rb_reset_cpu(cpu_buffer);
 	rb_check_pages(cpu_buffer);
 
+out:
 	spin_unlock_irq(&cpu_buffer->reader_lock);
 }
 
@@ -1226,7 +1239,7 @@ rb_insert_pages(struct ring_buffer_per_cpu *cpu_buffer,
 
 	for (i = 0; i < nr_pages; i++) {
 		if (RB_WARN_ON(cpu_buffer, list_empty(pages)))
-			return;
+			goto out;
 		p = pages->next;
 		bpage = list_entry(p, struct buffer_page, list);
 		list_del_init(&bpage->list);
@@ -1235,6 +1248,7 @@ rb_insert_pages(struct ring_buffer_per_cpu *cpu_buffer,
 	rb_reset_cpu(cpu_buffer);
 	rb_check_pages(cpu_buffer);
 
+out:
 	spin_unlock_irq(&cpu_buffer->reader_lock);
 }
 
@@ -1544,7 +1558,7 @@ rb_update_event(struct ring_buffer_event *event,
 
 	case 0:
 		length -= RB_EVNT_HDR_SIZE;
-		if (length > RB_MAX_SMALL_DATA)
+		if (length > RB_MAX_SMALL_DATA || RB_FORCE_8BYTE_ALIGNMENT)
 			event->array[0] = length;
 		else
 			event->type_len = DIV_ROUND_UP(length, RB_ALIGNMENT);
@@ -1719,11 +1733,11 @@ static unsigned rb_calculate_event_length(unsigned length)
 	if (!length)
 		length = 1;
 
-	if (length > RB_MAX_SMALL_DATA)
+	if (length > RB_MAX_SMALL_DATA || RB_FORCE_8BYTE_ALIGNMENT)
 		length += sizeof(event.array[0]);
 
 	length += RB_EVNT_HDR_SIZE;
-	length = ALIGN(length, RB_ALIGNMENT);
+	length = ALIGN(length, RB_ARCH_ALIGNMENT);
 
 	return length;
 }
@@ -2230,12 +2244,12 @@ 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;
 
@@ -2467,11 +2481,11 @@ 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))
@@ -2539,7 +2553,7 @@ 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)
 {
@@ -2575,7 +2589,7 @@ 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)
 {
@@ -2716,6 +2730,8 @@ static void rb_iter_reset(struct ring_buffer_iter *iter)
 		iter->read_stamp = cpu_buffer->read_stamp;
 	else
 		iter->read_stamp = iter->head_page->page->time_stamp;
+	iter->cache_reader_page = cpu_buffer->reader_page;
+	iter->cache_read = cpu_buffer->read;
 }
 
 /**
@@ -3060,13 +3076,22 @@ rb_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
 	struct ring_buffer_event *event;
 	int nr_loops = 0;
 
-	if (ring_buffer_iter_empty(iter))
-		return NULL;
-
 	cpu_buffer = iter->cpu_buffer;
 	buffer = cpu_buffer->buffer;
 
+	/*
+	 * Check if someone performed a consuming read to
+	 * the buffer. A consuming read invalidates the iterator
+	 * and we need to reset the iterator in this case.
+	 */
+	if (unlikely(iter->cache_read != cpu_buffer->read ||
+		     iter->cache_reader_page != cpu_buffer->reader_page))
+		rb_iter_reset(iter);
+
  again:
+	if (ring_buffer_iter_empty(iter))
+		return NULL;
+
 	/*
 	 * We repeat when a timestamp is encountered.
 	 * We can get multiple timestamps by nested interrupts or also
@@ -3081,6 +3106,11 @@ rb_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
 	if (rb_per_cpu_empty(cpu_buffer))
 		return NULL;
 
+	if (iter->head >= local_read(&iter->head_page->page->commit)) {
+		rb_inc_iter(iter);
+		goto again;
+	}
+
 	event = rb_iter_head_event(iter);
 
 	switch (event->type_len) {
diff --git a/kernel/trace/ring_buffer_benchmark.c b/kernel/trace/ring_buffer_benchmark.c
index b2477caf09c..df74c798225 100644
--- a/kernel/trace/ring_buffer_benchmark.c
+++ b/kernel/trace/ring_buffer_benchmark.c
@@ -8,6 +8,7 @@
 #include <linux/kthread.h>
 #include <linux/module.h>
 #include <linux/time.h>
+#include <asm/local.h>
 
 struct rb_page {
 	u64		ts;
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 0df1b0f2cb9..44f916a0406 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -32,10 +32,11 @@
 #include <linux/splice.h>
 #include <linux/kdebug.h>
 #include <linux/string.h>
+#include <linux/rwsem.h>
+#include <linux/slab.h>
 #include <linux/ctype.h>
 #include <linux/init.h>
 #include <linux/poll.h>
-#include <linux/gfp.h>
 #include <linux/fs.h>
 
 #include "trace.h"
@@ -91,20 +92,17 @@ DEFINE_PER_CPU(int, ftrace_cpu_disabled);
 static inline void ftrace_disable_cpu(void)
 {
 	preempt_disable();
-	__this_cpu_inc(per_cpu_var(ftrace_cpu_disabled));
+	__this_cpu_inc(ftrace_cpu_disabled);
 }
 
 static inline void ftrace_enable_cpu(void)
 {
-	__this_cpu_dec(per_cpu_var(ftrace_cpu_disabled));
+	__this_cpu_dec(ftrace_cpu_disabled);
 	preempt_enable();
 }
 
 static cpumask_var_t __read_mostly	tracing_buffer_mask;
 
-/* Define which cpu buffers are currently read in trace_pipe */
-static cpumask_var_t			tracing_reader_cpumask;
-
 #define for_each_tracing_cpu(cpu)	\
 	for_each_cpu(cpu, tracing_buffer_mask)
 
@@ -243,12 +241,91 @@ static struct tracer		*current_trace __read_mostly;
 
 /*
  * trace_types_lock is used to protect the trace_types list.
- * This lock is also used to keep user access serialized.
- * Accesses from userspace will grab this lock while userspace
- * activities happen inside the kernel.
  */
 static DEFINE_MUTEX(trace_types_lock);
 
+/*
+ * serialize the access of the ring buffer
+ *
+ * ring buffer serializes readers, but it is low level protection.
+ * The validity of the events (which returns by ring_buffer_peek() ..etc)
+ * are not protected by ring buffer.
+ *
+ * The content of events may become garbage if we allow other process consumes
+ * these events concurrently:
+ *   A) the page of the consumed events may become a normal page
+ *      (not reader page) in ring buffer, and this page will be rewrited
+ *      by events producer.
+ *   B) The page of the consumed events may become a page for splice_read,
+ *      and this page will be returned to system.
+ *
+ * These primitives allow multi process access to different cpu ring buffer
+ * concurrently.
+ *
+ * These primitives don't distinguish read-only and read-consume access.
+ * Multi read-only access are also serialized.
+ */
+
+#ifdef CONFIG_SMP
+static DECLARE_RWSEM(all_cpu_access_lock);
+static DEFINE_PER_CPU(struct mutex, cpu_access_lock);
+
+static inline void trace_access_lock(int cpu)
+{
+	if (cpu == TRACE_PIPE_ALL_CPU) {
+		/* gain it for accessing the whole ring buffer. */
+		down_write(&all_cpu_access_lock);
+	} else {
+		/* gain it for accessing a cpu ring buffer. */
+
+		/* Firstly block other trace_access_lock(TRACE_PIPE_ALL_CPU). */
+		down_read(&all_cpu_access_lock);
+
+		/* Secondly block other access to this @cpu ring buffer. */
+		mutex_lock(&per_cpu(cpu_access_lock, cpu));
+	}
+}
+
+static inline void trace_access_unlock(int cpu)
+{
+	if (cpu == TRACE_PIPE_ALL_CPU) {
+		up_write(&all_cpu_access_lock);
+	} else {
+		mutex_unlock(&per_cpu(cpu_access_lock, cpu));
+		up_read(&all_cpu_access_lock);
+	}
+}
+
+static inline void trace_access_lock_init(void)
+{
+	int cpu;
+
+	for_each_possible_cpu(cpu)
+		mutex_init(&per_cpu(cpu_access_lock, cpu));
+}
+
+#else
+
+static DEFINE_MUTEX(access_lock);
+
+static inline void trace_access_lock(int cpu)
+{
+	(void)cpu;
+	mutex_lock(&access_lock);
+}
+
+static inline void trace_access_unlock(int cpu)
+{
+	(void)cpu;
+	mutex_unlock(&access_lock);
+}
+
+static inline void trace_access_lock_init(void)
+{
+}
+
+#endif
+
 /* trace_wait is a waitqueue for tasks blocked on trace_poll */
 static DECLARE_WAIT_QUEUE_HEAD(trace_wait);
 
@@ -297,6 +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;
@@ -502,9 +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
@@ -515,7 +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;
@@ -525,7 +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;
@@ -747,10 +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();
 }
 
@@ -762,7 +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);
 }
@@ -780,7 +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);
 }
@@ -857,6 +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)
@@ -866,6 +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);
@@ -887,6 +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);
@@ -895,6 +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);
 }
@@ -951,6 +1053,11 @@ void trace_find_cmdline(int pid, char comm[])
 		return;
 	}
 
+	if (WARN_ON_ONCE(pid < 0)) {
+		strcpy(comm, "<XXX>");
+		return;
+	}
+
 	if (pid > PID_MAX_DEFAULT) {
 		strcpy(comm, "<...>");
 		return;
@@ -1084,7 +1191,7 @@ trace_function(struct trace_array *tr,
 	struct ftrace_entry *entry;
 
 	/* If we are reading the ring buffer, don't trace */
-	if (unlikely(__this_cpu_read(per_cpu_var(ftrace_cpu_disabled))))
+	if (unlikely(__this_cpu_read(ftrace_cpu_disabled)))
 		return;
 
 	event = trace_buffer_lock_reserve(buffer, TRACE_FN, sizeof(*entry),
@@ -1177,6 +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)
@@ -1315,8 +1429,10 @@ int trace_vbprintk(unsigned long ip, const char *fmt, va_list args)
 	entry->fmt			= fmt;
 
 	memcpy(entry->buf, trace_buf, sizeof(u32) * len);
-	if (!filter_check_discard(call, entry, buffer, event))
+	if (!filter_check_discard(call, entry, buffer, event)) {
 		ring_buffer_unlock_commit(buffer, event);
+		ftrace_trace_stack(buffer, flags, 6, pc);
+	}
 
 out_unlock:
 	arch_spin_unlock(&trace_buf_lock);
@@ -1389,8 +1505,10 @@ int trace_array_vprintk(struct trace_array *tr,
 
 	memcpy(&entry->buf, trace_buf, len);
 	entry->buf[len] = '\0';
-	if (!filter_check_discard(call, entry, buffer, event))
+	if (!filter_check_discard(call, entry, buffer, event)) {
 		ring_buffer_unlock_commit(buffer, event);
+		ftrace_trace_stack(buffer, irq_flags, 6, pc);
+	}
 
  out_unlock:
 	arch_spin_unlock(&trace_buf_lock);
@@ -1580,12 +1698,6 @@ static void tracing_iter_reset(struct trace_iterator *iter, int cpu)
 }
 
 /*
- * No necessary locking here. The worst thing which can
- * happen is loosing events consumed at the same time
- * by a trace_pipe reader.
- * Other than that, we don't risk to crash the ring buffer
- * because it serializes the readers.
- *
  * The current tracer is copied to avoid a global locking
  * all around.
  */
@@ -1623,6 +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))
 			;
 
@@ -1640,12 +1753,16 @@ static void *s_start(struct seq_file *m, loff_t *pos)
 	}
 
 	trace_event_read_lock();
+	trace_access_lock(cpu_file);
 	return p;
 }
 
 static void s_stop(struct seq_file *m, void *p)
 {
+	struct trace_iterator *iter = m->private;
+
 	atomic_dec(&trace_record_cmdline_disabled);
+	trace_access_unlock(iter->cpu_file);
 	trace_event_read_unlock();
 }
 
@@ -2836,22 +2953,6 @@ static int tracing_open_pipe(struct inode *inode, struct file *filp)
 
 	mutex_lock(&trace_types_lock);
 
-	/* We only allow one reader per cpu */
-	if (cpu_file == TRACE_PIPE_ALL_CPU) {
-		if (!cpumask_empty(tracing_reader_cpumask)) {
-			ret = -EBUSY;
-			goto out;
-		}
-		cpumask_setall(tracing_reader_cpumask);
-	} else {
-		if (!cpumask_test_cpu(cpu_file, tracing_reader_cpumask))
-			cpumask_set_cpu(cpu_file, tracing_reader_cpumask);
-		else {
-			ret = -EBUSY;
-			goto out;
-		}
-	}
-
 	/* create a buffer to store the information to pass to userspace */
 	iter = kzalloc(sizeof(*iter), GFP_KERNEL);
 	if (!iter) {
@@ -2907,12 +3008,6 @@ static int tracing_release_pipe(struct inode *inode, struct file *file)
 
 	mutex_lock(&trace_types_lock);
 
-	if (iter->cpu_file == TRACE_PIPE_ALL_CPU)
-		cpumask_clear(tracing_reader_cpumask);
-	else
-		cpumask_clear_cpu(iter->cpu_file, tracing_reader_cpumask);
-
-
 	if (iter->trace->pipe_close)
 		iter->trace->pipe_close(iter);
 
@@ -3074,6 +3169,7 @@ waitagain:
 	iter->pos = -1;
 
 	trace_event_read_lock();
+	trace_access_lock(iter->cpu_file);
 	while (find_next_entry_inc(iter) != NULL) {
 		enum print_line_t ret;
 		int len = iter->seq.len;
@@ -3090,6 +3186,7 @@ waitagain:
 		if (iter->seq.len >= cnt)
 			break;
 	}
+	trace_access_unlock(iter->cpu_file);
 	trace_event_read_unlock();
 
 	/* Now copy what we have to the user */
@@ -3215,6 +3312,7 @@ static ssize_t tracing_splice_read_pipe(struct file *filp,
 	}
 
 	trace_event_read_lock();
+	trace_access_lock(iter->cpu_file);
 
 	/* Fill as many pages as possible. */
 	for (i = 0, rem = len; i < PIPE_BUFFERS && rem; i++) {
@@ -3238,6 +3336,7 @@ static ssize_t tracing_splice_read_pipe(struct file *filp,
 		trace_seq_init(&iter->seq);
 	}
 
+	trace_access_unlock(iter->cpu_file);
 	trace_event_read_unlock();
 	mutex_unlock(&iter->mutex);
 
@@ -3539,10 +3638,12 @@ tracing_buffers_read(struct file *filp, char __user *ubuf,
 
 	info->read = 0;
 
+	trace_access_lock(info->cpu);
 	ret = ring_buffer_read_page(info->tr->buffer,
 				    &info->spare,
 				    count,
 				    info->cpu, 0);
+	trace_access_unlock(info->cpu);
 	if (ret < 0)
 		return 0;
 
@@ -3670,6 +3771,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
 		len &= PAGE_MASK;
 	}
 
+	trace_access_lock(info->cpu);
 	entries = ring_buffer_entries_cpu(info->tr->buffer, info->cpu);
 
 	for (i = 0; i < PIPE_BUFFERS && len && entries; i++, len -= PAGE_SIZE) {
@@ -3717,6 +3819,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
 		entries = ring_buffer_entries_cpu(info->tr->buffer, info->cpu);
 	}
 
+	trace_access_unlock(info->cpu);
 	spd.nr_pages = i;
 
 	/* did we read anything? */
@@ -4153,6 +4256,8 @@ static __init int tracer_init_debugfs(void)
 	struct dentry *d_tracer;
 	int cpu;
 
+	trace_access_lock_init();
+
 	d_tracer = tracing_init_dentry();
 
 	trace_create_file("tracing_enabled", 0644, d_tracer,
@@ -4176,10 +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);
@@ -4387,9 +4492,6 @@ __init static int tracer_alloc_buffers(void)
 	if (!alloc_cpumask_var(&tracing_cpumask, GFP_KERNEL))
 		goto out_free_buffer_mask;
 
-	if (!zalloc_cpumask_var(&tracing_reader_cpumask, GFP_KERNEL))
-		goto out_free_tracing_cpumask;
-
 	/* To save memory, keep the ring buffer size to its minimum */
 	if (ring_buffer_expanded)
 		ring_buf_size = trace_buf_size;
@@ -4447,8 +4549,6 @@ __init static int tracer_alloc_buffers(void)
 	return 0;
 
 out_free_cpumask:
-	free_cpumask_var(tracing_reader_cpumask);
-out_free_tracing_cpumask:
 	free_cpumask_var(tracing_cpumask);
 out_free_buffer_mask:
 	free_cpumask_var(tracing_buffer_mask);
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 4df6a77eb19..2825ef2c0b1 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,
@@ -497,6 +498,7 @@ trace_print_graph_duration(unsigned long long duration, struct trace_seq *s);
 #ifdef CONFIG_DYNAMIC_FTRACE
 /* TODO: make this variable */
 #define FTRACE_GRAPH_MAX_FUNCS		32
+extern int ftrace_graph_filter_enabled;
 extern int ftrace_graph_count;
 extern unsigned long ftrace_graph_funcs[FTRACE_GRAPH_MAX_FUNCS];
 
@@ -504,7 +506,7 @@ static inline int ftrace_graph_addr(unsigned long addr)
 {
 	int i;
 
-	if (!ftrace_graph_count || test_tsk_trace_graph(current))
+	if (!ftrace_graph_filter_enabled)
 		return 1;
 
 	for (i = 0; i < ftrace_graph_count; i++) {
@@ -549,7 +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 {
@@ -791,7 +793,8 @@ extern const char *__stop___trace_bprintk_fmt[];
 
 #undef FTRACE_ENTRY
 #define FTRACE_ENTRY(call, struct_name, id, tstruct, print)		\
-	extern struct ftrace_event_call event_##call;
+	extern struct ftrace_event_call					\
+	__attribute__((__aligned__(4))) event_##call;
 #undef FTRACE_ENTRY_DUP
 #define FTRACE_ENTRY_DUP(call, struct_name, id, tstruct, print)		\
 	FTRACE_ENTRY(call, struct_name, id, PARAMS(tstruct), PARAMS(print))
diff --git a/kernel/trace/trace_branch.c b/kernel/trace/trace_branch.c
index 4a194f08f88..b9bc4d47017 100644
--- a/kernel/trace/trace_branch.c
+++ b/kernel/trace/trace_branch.c
@@ -307,8 +307,23 @@ static int annotated_branch_stat_cmp(void *p1, void *p2)
 		return -1;
 	if (percent_a > percent_b)
 		return 1;
-	else
-		return 0;
+
+	if (a->incorrect < b->incorrect)
+		return -1;
+	if (a->incorrect > b->incorrect)
+		return 1;
+
+	/*
+	 * Since the above shows worse (incorrect) cases
+	 * first, we continue that by showing best (correct)
+	 * cases last.
+	 */
+	if (a->correct > b->correct)
+		return -1;
+	if (a->correct < b->correct)
+		return 1;
+
+	return 0;
 }
 
 static struct tracer_stat annotated_branch_stats = {
diff --git a/kernel/trace/trace_clock.c b/kernel/trace/trace_clock.c
index 84a3a7ba072..9d589d8dcd1 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>
@@ -83,7 +84,7 @@ u64 notrace trace_clock_global(void)
 	int this_cpu;
 	u64 now;
 
-	raw_local_irq_save(flags);
+	local_irq_save(flags);
 
 	this_cpu = raw_smp_processor_id();
 	now = cpu_clock(this_cpu);
@@ -109,7 +110,7 @@ u64 notrace trace_clock_global(void)
 	arch_spin_unlock(&trace_clock_struct.lock);
 
  out:
-	raw_local_irq_restore(flags);
+	local_irq_restore(flags);
 
 	return now;
 }
diff --git a/kernel/trace/trace_event_profile.c b/kernel/trace/trace_event_perf.c
index f0d69300507..0565bb42566 100644
--- a/kernel/trace/trace_event_profile.c
+++ b/kernel/trace/trace_event_perf.c
@@ -1,32 +1,41 @@
 /*
- * trace event based perf counter profiling
+ * trace event based perf event profiling/tracing
  *
  * Copyright (C) 2009 Red Hat Inc, Peter Zijlstra <pzijlstr@redhat.com>
- *
+ * Copyright (C) 2009-2010 Frederic Weisbecker <fweisbec@gmail.com>
  */
 
 #include <linux/module.h>
 #include <linux/kprobes.h>
 #include "trace.h"
 
+DEFINE_PER_CPU(struct pt_regs, perf_trace_regs);
+EXPORT_PER_CPU_SYMBOL_GPL(perf_trace_regs);
+
+EXPORT_SYMBOL_GPL(perf_arch_fetch_caller_regs);
 
 static char *perf_trace_buf;
 static char *perf_trace_buf_nmi;
 
-typedef typeof(char [FTRACE_MAX_PROFILE_SIZE]) perf_trace_t ;
+/*
+ * Force it to be aligned to unsigned long to avoid misaligned accesses
+ * suprises
+ */
+typedef typeof(unsigned long [PERF_MAX_TRACE_SIZE / sizeof(unsigned long)])
+	perf_trace_t;
 
 /* Count the events in use (per event id, not per instance) */
-static int	total_profile_count;
+static int	total_ref_count;
 
-static int ftrace_profile_enable_event(struct ftrace_event_call *event)
+static int perf_trace_event_enable(struct ftrace_event_call *event)
 {
 	char *buf;
 	int ret = -ENOMEM;
 
-	if (event->profile_count++ > 0)
+	if (event->perf_refcount++ > 0)
 		return 0;
 
-	if (!total_profile_count) {
+	if (!total_ref_count) {
 		buf = (char *)alloc_percpu(perf_trace_t);
 		if (!buf)
 			goto fail_buf;
@@ -40,35 +49,35 @@ static int ftrace_profile_enable_event(struct ftrace_event_call *event)
 		rcu_assign_pointer(perf_trace_buf_nmi, buf);
 	}
 
-	ret = event->profile_enable(event);
+	ret = event->perf_event_enable(event);
 	if (!ret) {
-		total_profile_count++;
+		total_ref_count++;
 		return 0;
 	}
 
 fail_buf_nmi:
-	if (!total_profile_count) {
+	if (!total_ref_count) {
 		free_percpu(perf_trace_buf_nmi);
 		free_percpu(perf_trace_buf);
 		perf_trace_buf_nmi = NULL;
 		perf_trace_buf = NULL;
 	}
 fail_buf:
-	event->profile_count--;
+	event->perf_refcount--;
 
 	return ret;
 }
 
-int ftrace_profile_enable(int event_id)
+int perf_trace_enable(int event_id)
 {
 	struct ftrace_event_call *event;
 	int ret = -EINVAL;
 
 	mutex_lock(&event_mutex);
 	list_for_each_entry(event, &ftrace_events, list) {
-		if (event->id == event_id && event->profile_enable &&
+		if (event->id == event_id && event->perf_event_enable &&
 		    try_module_get(event->mod)) {
-			ret = ftrace_profile_enable_event(event);
+			ret = perf_trace_event_enable(event);
 			break;
 		}
 	}
@@ -77,16 +86,16 @@ int ftrace_profile_enable(int event_id)
 	return ret;
 }
 
-static void ftrace_profile_disable_event(struct ftrace_event_call *event)
+static void perf_trace_event_disable(struct ftrace_event_call *event)
 {
 	char *buf, *nmi_buf;
 
-	if (--event->profile_count > 0)
+	if (--event->perf_refcount > 0)
 		return;
 
-	event->profile_disable(event);
+	event->perf_event_disable(event);
 
-	if (!--total_profile_count) {
+	if (!--total_ref_count) {
 		buf = perf_trace_buf;
 		rcu_assign_pointer(perf_trace_buf, NULL);
 
@@ -104,14 +113,14 @@ static void ftrace_profile_disable_event(struct ftrace_event_call *event)
 	}
 }
 
-void ftrace_profile_disable(int event_id)
+void perf_trace_disable(int event_id)
 {
 	struct ftrace_event_call *event;
 
 	mutex_lock(&event_mutex);
 	list_for_each_entry(event, &ftrace_events, list) {
 		if (event->id == event_id) {
-			ftrace_profile_disable_event(event);
+			perf_trace_event_disable(event);
 			module_put(event->mod);
 			break;
 		}
@@ -119,13 +128,15 @@ void ftrace_profile_disable(int event_id)
 	mutex_unlock(&event_mutex);
 }
 
-__kprobes void *ftrace_perf_buf_prepare(int size, unsigned short type,
-					int *rctxp, unsigned long *irq_flags)
+__kprobes void *perf_trace_buf_prepare(int size, unsigned short type,
+				       int *rctxp, unsigned long *irq_flags)
 {
 	struct trace_entry *entry;
 	char *trace_buf, *raw_data;
 	int pc, cpu;
 
+	BUILD_BUG_ON(PERF_MAX_TRACE_SIZE % sizeof(unsigned long));
+
 	pc = preempt_count();
 
 	/* Protect the per cpu buffer, begin the rcu read side */
@@ -138,9 +149,9 @@ __kprobes void *ftrace_perf_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;
@@ -148,7 +159,7 @@ __kprobes void *ftrace_perf_buf_prepare(int size, unsigned short type,
 	raw_data = per_cpu_ptr(trace_buf, cpu);
 
 	/* zero the dead bytes from align to not leak stack to user */
-	*(u64 *)(&raw_data[size - sizeof(u64)]) = 0ULL;
+	memset(&raw_data[size - sizeof(u64)], 0, sizeof(u64));
 
 	entry = (struct trace_entry *)raw_data;
 	tracing_generic_entry_update(entry, *irq_flags, pc);
@@ -161,4 +172,4 @@ err_recursion:
 	local_irq_restore(*irq_flags);
 	return NULL;
 }
-EXPORT_SYMBOL_GPL(ftrace_perf_buf_prepare);
+EXPORT_SYMBOL_GPL(perf_trace_buf_prepare);
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 189b09baf4f..c697c704334 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -15,6 +15,7 @@
 #include <linux/uaccess.h>
 #include <linux/module.h>
 #include <linux/ctype.h>
+#include <linux/slab.h>
 #include <linux/delay.h>
 
 #include <asm/setup.h>
@@ -60,10 +61,8 @@ int trace_define_field(struct ftrace_event_call *call, const char *type,
 	return 0;
 
 err:
-	if (field) {
+	if (field)
 		kfree(field->name);
-		kfree(field->type);
-	}
 	kfree(field);
 
 	return -ENOMEM;
@@ -520,41 +519,16 @@ out:
 	return ret;
 }
 
-extern char *__bad_type_size(void);
-
-#undef FIELD
-#define FIELD(type, name)						\
-	sizeof(type) != sizeof(field.name) ? __bad_type_size() :	\
-	#type, "common_" #name, offsetof(typeof(field), name),		\
-		sizeof(field.name), is_signed_type(type)
-
-static int trace_write_header(struct trace_seq *s)
-{
-	struct trace_entry field;
-
-	/* struct trace_entry */
-	return trace_seq_printf(s,
-			"\tfield:%s %s;\toffset:%zu;\tsize:%zu;\tsigned:%u;\n"
-			"\tfield:%s %s;\toffset:%zu;\tsize:%zu;\tsigned:%u;\n"
-			"\tfield:%s %s;\toffset:%zu;\tsize:%zu;\tsigned:%u;\n"
-			"\tfield:%s %s;\toffset:%zu;\tsize:%zu;\tsigned:%u;\n"
-			"\tfield:%s %s;\toffset:%zu;\tsize:%zu;\tsigned:%u;\n"
-			"\n",
-			FIELD(unsigned short, type),
-			FIELD(unsigned char, flags),
-			FIELD(unsigned char, preempt_count),
-			FIELD(int, pid),
-			FIELD(int, lock_depth));
-}
-
 static ssize_t
 event_format_read(struct file *filp, char __user *ubuf, size_t cnt,
 		  loff_t *ppos)
 {
 	struct ftrace_event_call *call = filp->private_data;
+	struct ftrace_event_field *field;
 	struct trace_seq *s;
+	int common_field_count = 5;
 	char *buf;
-	int r;
+	int r = 0;
 
 	if (*ppos)
 		return 0;
@@ -565,14 +539,48 @@ event_format_read(struct file *filp, char __user *ubuf, size_t cnt,
 
 	trace_seq_init(s);
 
-	/* If any of the first writes fail, so will the show_format. */
-
 	trace_seq_printf(s, "name: %s\n", call->name);
 	trace_seq_printf(s, "ID: %d\n", call->id);
 	trace_seq_printf(s, "format:\n");
-	trace_write_header(s);
 
-	r = call->show_format(call, s);
+	list_for_each_entry_reverse(field, &call->fields, link) {
+		/*
+		 * Smartly shows the array type(except dynamic array).
+		 * Normal:
+		 *	field:TYPE VAR
+		 * If TYPE := TYPE[LEN], it is shown:
+		 *	field:TYPE VAR[LEN]
+		 */
+		const char *array_descriptor = strchr(field->type, '[');
+
+		if (!strncmp(field->type, "__data_loc", 10))
+			array_descriptor = NULL;
+
+		if (!array_descriptor) {
+			r = trace_seq_printf(s, "\tfield:%s %s;\toffset:%u;"
+					"\tsize:%u;\tsigned:%d;\n",
+					field->type, field->name, field->offset,
+					field->size, !!field->is_signed);
+		} else {
+			r = trace_seq_printf(s, "\tfield:%.*s %s%s;\toffset:%u;"
+					"\tsize:%u;\tsigned:%d;\n",
+					(int)(array_descriptor - field->type),
+					field->type, field->name,
+					array_descriptor, field->offset,
+					field->size, !!field->is_signed);
+		}
+
+		if (--common_field_count == 0)
+			r = trace_seq_printf(s, "\n");
+
+		if (!r)
+			break;
+	}
+
+	if (r)
+		r = trace_seq_printf(s, "\nprint fmt: %s\n",
+				call->print_fmt);
+
 	if (!r) {
 		/*
 		 * ug!  The format output is bigger than a PAGE!!
@@ -931,7 +939,7 @@ event_create_dir(struct ftrace_event_call *call, struct dentry *d_events,
 		trace_create_file("enable", 0644, call->dir, call,
 				  enable);
 
-	if (call->id && call->profile_enable)
+	if (call->id && call->perf_event_enable)
 		trace_create_file("id", 0444, call->dir, call,
 		 		  id);
 
@@ -948,10 +956,6 @@ event_create_dir(struct ftrace_event_call *call, struct dentry *d_events,
 				  filter);
 	}
 
-	/* A trace may not want to export its format */
-	if (!call->show_format)
-		return 0;
-
 	trace_create_file("format", 0444, call->dir, call,
 			  format);
 
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index 4615f62a04f..88c0b6dbd7f 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -22,6 +22,7 @@
 #include <linux/ctype.h>
 #include <linux/mutex.h>
 #include <linux/perf_event.h>
+#include <linux/slab.h>
 
 #include "trace.h"
 #include "trace_output.h"
diff --git a/kernel/trace/trace_export.c b/kernel/trace/trace_export.c
index d4fa5dc1ee4..e091f64ba6c 100644
--- a/kernel/trace/trace_export.c
+++ b/kernel/trace/trace_export.c
@@ -62,78 +62,6 @@ static void __always_unused ____ftrace_check_##name(void)	\
 
 #include "trace_entries.h"
 
-
-#undef __field
-#define __field(type, item)						\
-	ret = trace_seq_printf(s, "\tfield:" #type " " #item ";\t"	\
-			       "offset:%zu;\tsize:%zu;\tsigned:%u;\n",	\
-			       offsetof(typeof(field), item),		\
-			       sizeof(field.item), is_signed_type(type)); \
-	if (!ret)							\
-		return 0;
-
-#undef __field_desc
-#define __field_desc(type, container, item)				\
-	ret = trace_seq_printf(s, "\tfield:" #type " " #item ";\t"	\
-			       "offset:%zu;\tsize:%zu;\tsigned:%u;\n",	\
-			       offsetof(typeof(field), container.item),	\
-			       sizeof(field.container.item),		\
-			       is_signed_type(type));			\
-	if (!ret)							\
-		return 0;
-
-#undef __array
-#define __array(type, item, len)					\
-	ret = trace_seq_printf(s, "\tfield:" #type " " #item "[" #len "];\t" \
-			       "offset:%zu;\tsize:%zu;\tsigned:%u;\n",	\
-			       offsetof(typeof(field), item),		\
-			       sizeof(field.item), is_signed_type(type)); \
-	if (!ret)							\
-		return 0;
-
-#undef __array_desc
-#define __array_desc(type, container, item, len)			\
-	ret = trace_seq_printf(s, "\tfield:" #type " " #item "[" #len "];\t" \
-			       "offset:%zu;\tsize:%zu;\tsigned:%u;\n",	\
-			       offsetof(typeof(field), container.item),	\
-			       sizeof(field.container.item),		\
-			       is_signed_type(type));			\
-	if (!ret)							\
-		return 0;
-
-#undef __dynamic_array
-#define __dynamic_array(type, item)					\
-	ret = trace_seq_printf(s, "\tfield:" #type " " #item ";\t"	\
-			       "offset:%zu;\tsize:0;\tsigned:%u;\n",	\
-			       offsetof(typeof(field), item),		\
-			       is_signed_type(type));			\
-	if (!ret)							\
-		return 0;
-
-#undef F_printk
-#define F_printk(fmt, args...) "%s, %s\n", #fmt, __stringify(args)
-
-#undef __entry
-#define __entry REC
-
-#undef FTRACE_ENTRY
-#define FTRACE_ENTRY(name, struct_name, id, tstruct, print)		\
-static int								\
-ftrace_format_##name(struct ftrace_event_call *unused,			\
-		     struct trace_seq *s)				\
-{									\
-	struct struct_name field __attribute__((unused));		\
-	int ret = 0;							\
-									\
-	tstruct;							\
-									\
-	trace_seq_printf(s, "\nprint fmt: " print);			\
-									\
-	return ret;							\
-}
-
-#include "trace_entries.h"
-
 #undef __field
 #define __field(type, item)						\
 	ret = trace_define_field(event_call, #type, #item,		\
@@ -175,7 +103,12 @@ ftrace_format_##name(struct ftrace_event_call *unused,			\
 		return ret;
 
 #undef __dynamic_array
-#define __dynamic_array(type, item)
+#define __dynamic_array(type, item)					\
+	ret = trace_define_field(event_call, #type, #item,		\
+				 offsetof(typeof(field), item),		\
+				 0, is_signed_type(type), FILTER_OTHER);\
+	if (ret)							\
+		return ret;
 
 #undef FTRACE_ENTRY
 #define FTRACE_ENTRY(name, struct_name, id, tstruct, print)		\
@@ -198,6 +131,9 @@ static int ftrace_raw_init_event(struct ftrace_event_call *call)
 	return 0;
 }
 
+#undef __entry
+#define __entry REC
+
 #undef __field
 #define __field(type, item)
 
@@ -213,6 +149,9 @@ static int ftrace_raw_init_event(struct ftrace_event_call *call)
 #undef __dynamic_array
 #define __dynamic_array(type, item)
 
+#undef F_printk
+#define F_printk(fmt, args...) #fmt ", "  __stringify(args)
+
 #undef FTRACE_ENTRY
 #define FTRACE_ENTRY(call, struct_name, type, tstruct, print)		\
 									\
@@ -223,7 +162,7 @@ __attribute__((section("_ftrace_events"))) event_##call = {		\
 	.id			= type,					\
 	.system			= __stringify(TRACE_SYSTEM),		\
 	.raw_init		= ftrace_raw_init_event,		\
-	.show_format		= ftrace_format_##call,			\
+	.print_fmt		= print,				\
 	.define_fields		= ftrace_define_fields_##call,		\
 };									\
 
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index b1342c5d37c..9aed1a5cf55 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -9,6 +9,7 @@
 #include <linux/debugfs.h>
 #include <linux/uaccess.h>
 #include <linux/ftrace.h>
+#include <linux/slab.h>
 #include <linux/fs.h>
 
 #include "trace.h"
@@ -18,6 +19,7 @@ struct fgraph_cpu_data {
 	pid_t		last_pid;
 	int		depth;
 	int		ignore;
+	unsigned long	enter_funcs[FTRACE_RETFUNC_DEPTH];
 };
 
 struct fgraph_data {
@@ -187,7 +189,7 @@ static int __trace_graph_entry(struct trace_array *tr,
 	struct ring_buffer *buffer = tr->buffer;
 	struct ftrace_graph_ent_entry *entry;
 
-	if (unlikely(__this_cpu_read(per_cpu_var(ftrace_cpu_disabled))))
+	if (unlikely(__this_cpu_read(ftrace_cpu_disabled)))
 		return 0;
 
 	event = trace_buffer_lock_reserve(buffer, TRACE_GRAPH_ENT,
@@ -212,13 +214,11 @@ int trace_graph_entry(struct ftrace_graph_ent *trace)
 	int cpu;
 	int pc;
 
-	if (unlikely(!tr))
-		return 0;
-
 	if (!ftrace_trace_task(current))
 		return 0;
 
-	if (!ftrace_graph_addr(trace->func))
+	/* trace it when it is-nested-in or is a function enabled. */
+	if (!(trace->depth || ftrace_graph_addr(trace->func)))
 		return 0;
 
 	local_irq_save(flags);
@@ -231,9 +231,6 @@ int trace_graph_entry(struct ftrace_graph_ent *trace)
 	} else {
 		ret = 0;
 	}
-	/* Only do the atomic if it is not already set */
-	if (!test_tsk_trace_graph(current))
-		set_tsk_trace_graph(current);
 
 	atomic_dec(&data->disabled);
 	local_irq_restore(flags);
@@ -241,6 +238,14 @@ 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,
@@ -251,7 +256,7 @@ static void __trace_graph_return(struct trace_array *tr,
 	struct ring_buffer *buffer = tr->buffer;
 	struct ftrace_graph_ret_entry *entry;
 
-	if (unlikely(__this_cpu_read(per_cpu_var(ftrace_cpu_disabled))))
+	if (unlikely(__this_cpu_read(ftrace_cpu_disabled)))
 		return;
 
 	event = trace_buffer_lock_reserve(buffer, TRACE_GRAPH_RET,
@@ -281,19 +286,39 @@ void trace_graph_return(struct ftrace_graph_ret *trace)
 		pc = preempt_count();
 		__trace_graph_return(tr, trace, flags, pc);
 	}
-	if (!trace->depth)
-		clear_tsk_trace_graph(current);
 	atomic_dec(&data->disabled);
 	local_irq_restore(flags);
 }
 
+void set_graph_array(struct trace_array *tr)
+{
+	graph_array = tr;
+
+	/* Make graph_array visible before we start tracing */
+
+	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;
 
-	graph_array = tr;
-	ret = register_ftrace_graph(&trace_graph_return,
-				    &trace_graph_entry);
+	set_graph_array(tr);
+	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();
@@ -301,11 +326,6 @@ static int graph_trace_init(struct trace_array *tr)
 	return 0;
 }
 
-void set_graph_array(struct trace_array *tr)
-{
-	graph_array = tr;
-}
-
 static void graph_trace_reset(struct trace_array *tr)
 {
 	tracing_stop_cmdline_record();
@@ -673,15 +693,21 @@ print_graph_entry_leaf(struct trace_iterator *iter,
 	duration = graph_ret->rettime - graph_ret->calltime;
 
 	if (data) {
+		struct fgraph_cpu_data *cpu_data;
 		int cpu = iter->cpu;
-		int *depth = &(per_cpu_ptr(data->cpu_data, cpu)->depth);
+
+		cpu_data = per_cpu_ptr(data->cpu_data, cpu);
 
 		/*
 		 * Comments display at + 1 to depth. Since
 		 * this is a leaf function, keep the comments
 		 * equal to this depth.
 		 */
-		*depth = call->depth - 1;
+		cpu_data->depth = call->depth - 1;
+
+		/* No need to keep this function around for this depth */
+		if (call->depth < FTRACE_RETFUNC_DEPTH)
+			cpu_data->enter_funcs[call->depth] = 0;
 	}
 
 	/* Overhead */
@@ -721,10 +747,15 @@ print_graph_entry_nested(struct trace_iterator *iter,
 	int i;
 
 	if (data) {
+		struct fgraph_cpu_data *cpu_data;
 		int cpu = iter->cpu;
-		int *depth = &(per_cpu_ptr(data->cpu_data, cpu)->depth);
 
-		*depth = call->depth;
+		cpu_data = per_cpu_ptr(data->cpu_data, cpu);
+		cpu_data->depth = call->depth;
+
+		/* Save this function pointer to see if the exit matches */
+		if (call->depth < FTRACE_RETFUNC_DEPTH)
+			cpu_data->enter_funcs[call->depth] = call->func;
 	}
 
 	/* No overhead */
@@ -854,19 +885,28 @@ print_graph_return(struct ftrace_graph_ret *trace, struct trace_seq *s,
 	struct fgraph_data *data = iter->private;
 	pid_t pid = ent->pid;
 	int cpu = iter->cpu;
+	int func_match = 1;
 	int ret;
 	int i;
 
 	if (data) {
+		struct fgraph_cpu_data *cpu_data;
 		int cpu = iter->cpu;
-		int *depth = &(per_cpu_ptr(data->cpu_data, cpu)->depth);
+
+		cpu_data = per_cpu_ptr(data->cpu_data, cpu);
 
 		/*
 		 * Comments display at + 1 to depth. This is the
 		 * return from a function, we now want the comments
 		 * to display at the same level of the bracket.
 		 */
-		*depth = trace->depth - 1;
+		cpu_data->depth = trace->depth - 1;
+
+		if (trace->depth < FTRACE_RETFUNC_DEPTH) {
+			if (cpu_data->enter_funcs[trace->depth] != trace->func)
+				func_match = 0;
+			cpu_data->enter_funcs[trace->depth] = 0;
+		}
 	}
 
 	if (print_graph_prologue(iter, s, 0, 0))
@@ -891,9 +931,21 @@ print_graph_return(struct ftrace_graph_ret *trace, struct trace_seq *s,
 			return TRACE_TYPE_PARTIAL_LINE;
 	}
 
-	ret = trace_seq_printf(s, "}\n");
-	if (!ret)
-		return TRACE_TYPE_PARTIAL_LINE;
+	/*
+	 * If the return function does not have a matching entry,
+	 * then the entry was lost. Instead of just printing
+	 * the '}' and letting the user guess what function this
+	 * belongs to, write out the function name.
+	 */
+	if (func_match) {
+		ret = trace_seq_printf(s, "}\n");
+		if (!ret)
+			return TRACE_TYPE_PARTIAL_LINE;
+	} else {
+		ret = trace_seq_printf(s, "} /* %ps */\n", (void *)trace->func);
+		if (!ret)
+			return TRACE_TYPE_PARTIAL_LINE;
+	}
 
 	/* Overrun */
 	if (tracer_flags.val & TRACE_GRAPH_PRINT_OVERRUN) {
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 6178abf3637..1251e367bae 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -635,12 +635,12 @@ static int create_trace_probe(int argc, char **argv)
 			event = strchr(group, '/') + 1;
 			event[-1] = '\0';
 			if (strlen(group) == 0) {
-				pr_info("Group name is not specifiled\n");
+				pr_info("Group name is not specified\n");
 				return -EINVAL;
 			}
 		}
 		if (strlen(event) == 0) {
-			pr_info("Event name is not specifiled\n");
+			pr_info("Event name is not specified\n");
 			return -EINVAL;
 		}
 	}
@@ -673,7 +673,7 @@ static int create_trace_probe(int argc, char **argv)
 			return -EINVAL;
 		}
 		/* an address specified */
-		ret = strict_strtoul(&argv[0][2], 0, (unsigned long *)&addr);
+		ret = strict_strtoul(&argv[1][0], 0, (unsigned long *)&addr);
 		if (ret) {
 			pr_info("Failed to parse address.\n");
 			return ret;
@@ -1155,86 +1155,66 @@ static int kretprobe_event_define_fields(struct ftrace_event_call *event_call)
 	return 0;
 }
 
-static int __probe_event_show_format(struct trace_seq *s,
-				     struct trace_probe *tp, const char *fmt,
-				     const char *arg)
+static int __set_print_fmt(struct trace_probe *tp, char *buf, int len)
 {
 	int i;
+	int pos = 0;
 
-	/* Show format */
-	if (!trace_seq_printf(s, "\nprint fmt: \"%s", fmt))
-		return 0;
+	const char *fmt, *arg;
 
-	for (i = 0; i < tp->nr_args; i++)
-		if (!trace_seq_printf(s, " %s=%%lx", tp->args[i].name))
-			return 0;
+	if (!probe_is_return(tp)) {
+		fmt = "(%lx)";
+		arg = "REC->" FIELD_STRING_IP;
+	} else {
+		fmt = "(%lx <- %lx)";
+		arg = "REC->" FIELD_STRING_FUNC ", REC->" FIELD_STRING_RETIP;
+	}
 
-	if (!trace_seq_printf(s, "\", %s", arg))
-		return 0;
+	/* When len=0, we just calculate the needed length */
+#define LEN_OR_ZERO (len ? len - pos : 0)
 
-	for (i = 0; i < tp->nr_args; i++)
-		if (!trace_seq_printf(s, ", REC->%s", tp->args[i].name))
-			return 0;
+	pos += snprintf(buf + pos, LEN_OR_ZERO, "\"%s", fmt);
 
-	return trace_seq_puts(s, "\n");
-}
+	for (i = 0; i < tp->nr_args; i++) {
+		pos += snprintf(buf + pos, LEN_OR_ZERO, " %s=%%lx",
+				tp->args[i].name);
+	}
 
-#undef SHOW_FIELD
-#define SHOW_FIELD(type, item, name)					\
-	do {								\
-		ret = trace_seq_printf(s, "\tfield:" #type " %s;\t"	\
-				"offset:%u;\tsize:%u;\tsigned:%d;\n", name,\
-				(unsigned int)offsetof(typeof(field), item),\
-				(unsigned int)sizeof(type),		\
-				is_signed_type(type));			\
-		if (!ret)						\
-			return 0;					\
-	} while (0)
+	pos += snprintf(buf + pos, LEN_OR_ZERO, "\", %s", arg);
 
-static int kprobe_event_show_format(struct ftrace_event_call *call,
-				    struct trace_seq *s)
-{
-	struct kprobe_trace_entry field __attribute__((unused));
-	int ret, i;
-	struct trace_probe *tp = (struct trace_probe *)call->data;
-
-	SHOW_FIELD(unsigned long, ip, FIELD_STRING_IP);
-	SHOW_FIELD(int, nargs, FIELD_STRING_NARGS);
+	for (i = 0; i < tp->nr_args; i++) {
+		pos += snprintf(buf + pos, LEN_OR_ZERO, ", REC->%s",
+				tp->args[i].name);
+	}
 
-	/* Show fields */
-	for (i = 0; i < tp->nr_args; i++)
-		SHOW_FIELD(unsigned long, args[i], tp->args[i].name);
-	trace_seq_puts(s, "\n");
+#undef LEN_OR_ZERO
 
-	return __probe_event_show_format(s, tp, "(%lx)",
-					 "REC->" FIELD_STRING_IP);
+	/* return the length of print_fmt */
+	return pos;
 }
 
-static int kretprobe_event_show_format(struct ftrace_event_call *call,
-				       struct trace_seq *s)
+static int set_print_fmt(struct trace_probe *tp)
 {
-	struct kretprobe_trace_entry field __attribute__((unused));
-	int ret, i;
-	struct trace_probe *tp = (struct trace_probe *)call->data;
+	int len;
+	char *print_fmt;
 
-	SHOW_FIELD(unsigned long, func, FIELD_STRING_FUNC);
-	SHOW_FIELD(unsigned long, ret_ip, FIELD_STRING_RETIP);
-	SHOW_FIELD(int, nargs, FIELD_STRING_NARGS);
+	/* First: called with 0 length to calculate the needed length */
+	len = __set_print_fmt(tp, NULL, 0);
+	print_fmt = kmalloc(len + 1, GFP_KERNEL);
+	if (!print_fmt)
+		return -ENOMEM;
 
-	/* Show fields */
-	for (i = 0; i < tp->nr_args; i++)
-		SHOW_FIELD(unsigned long, args[i], tp->args[i].name);
-	trace_seq_puts(s, "\n");
+	/* Second: actually write the @print_fmt */
+	__set_print_fmt(tp, print_fmt, len + 1);
+	tp->call.print_fmt = print_fmt;
 
-	return __probe_event_show_format(s, tp, "(%lx <- %lx)",
-					 "REC->" FIELD_STRING_FUNC
-					 ", REC->" FIELD_STRING_RETIP);
+	return 0;
 }
 
 #ifdef CONFIG_PERF_EVENTS
 
 /* Kprobe profile handler */
-static __kprobes void kprobe_profile_func(struct kprobe *kp,
+static __kprobes void kprobe_perf_func(struct kprobe *kp,
 					 struct pt_regs *regs)
 {
 	struct trace_probe *tp = container_of(kp, struct trace_probe, rp.kp);
@@ -1247,11 +1227,11 @@ static __kprobes void kprobe_profile_func(struct kprobe *kp,
 	__size = SIZEOF_KPROBE_TRACE_ENTRY(tp->nr_args);
 	size = ALIGN(__size + sizeof(u32), sizeof(u64));
 	size -= sizeof(u32);
-	if (WARN_ONCE(size > FTRACE_MAX_PROFILE_SIZE,
+	if (WARN_ONCE(size > PERF_MAX_TRACE_SIZE,
 		     "profile buffer not large enough"))
 		return;
 
-	entry = ftrace_perf_buf_prepare(size, call->id, &rctx, &irq_flags);
+	entry = perf_trace_buf_prepare(size, call->id, &rctx, &irq_flags);
 	if (!entry)
 		return;
 
@@ -1260,11 +1240,11 @@ static __kprobes void kprobe_profile_func(struct kprobe *kp,
 	for (i = 0; i < tp->nr_args; i++)
 		entry->args[i] = call_fetch(&tp->args[i].fetch, regs);
 
-	ftrace_perf_buf_submit(entry, size, rctx, entry->ip, 1, irq_flags);
+	perf_trace_buf_submit(entry, size, rctx, entry->ip, 1, irq_flags, regs);
 }
 
 /* Kretprobe profile handler */
-static __kprobes void kretprobe_profile_func(struct kretprobe_instance *ri,
+static __kprobes void kretprobe_perf_func(struct kretprobe_instance *ri,
 					    struct pt_regs *regs)
 {
 	struct trace_probe *tp = container_of(ri->rp, struct trace_probe, rp);
@@ -1277,11 +1257,11 @@ static __kprobes void kretprobe_profile_func(struct kretprobe_instance *ri,
 	__size = SIZEOF_KRETPROBE_TRACE_ENTRY(tp->nr_args);
 	size = ALIGN(__size + sizeof(u32), sizeof(u64));
 	size -= sizeof(u32);
-	if (WARN_ONCE(size > FTRACE_MAX_PROFILE_SIZE,
+	if (WARN_ONCE(size > PERF_MAX_TRACE_SIZE,
 		     "profile buffer not large enough"))
 		return;
 
-	entry = ftrace_perf_buf_prepare(size, call->id, &rctx, &irq_flags);
+	entry = perf_trace_buf_prepare(size, call->id, &rctx, &irq_flags);
 	if (!entry)
 		return;
 
@@ -1291,10 +1271,11 @@ static __kprobes void kretprobe_profile_func(struct kretprobe_instance *ri,
 	for (i = 0; i < tp->nr_args; i++)
 		entry->args[i] = call_fetch(&tp->args[i].fetch, regs);
 
-	ftrace_perf_buf_submit(entry, size, rctx, entry->ret_ip, 1, irq_flags);
+	perf_trace_buf_submit(entry, size, rctx, entry->ret_ip, 1,
+			       irq_flags, regs);
 }
 
-static int probe_profile_enable(struct ftrace_event_call *call)
+static int probe_perf_enable(struct ftrace_event_call *call)
 {
 	struct trace_probe *tp = (struct trace_probe *)call->data;
 
@@ -1306,7 +1287,7 @@ static int probe_profile_enable(struct ftrace_event_call *call)
 		return enable_kprobe(&tp->rp.kp);
 }
 
-static void probe_profile_disable(struct ftrace_event_call *call)
+static void probe_perf_disable(struct ftrace_event_call *call)
 {
 	struct trace_probe *tp = (struct trace_probe *)call->data;
 
@@ -1331,7 +1312,7 @@ int kprobe_dispatcher(struct kprobe *kp, struct pt_regs *regs)
 		kprobe_trace_func(kp, regs);
 #ifdef CONFIG_PERF_EVENTS
 	if (tp->flags & TP_FLAG_PROFILE)
-		kprobe_profile_func(kp, regs);
+		kprobe_perf_func(kp, regs);
 #endif
 	return 0;	/* We don't tweek kernel, so just return 0 */
 }
@@ -1345,7 +1326,7 @@ int kretprobe_dispatcher(struct kretprobe_instance *ri, struct pt_regs *regs)
 		kretprobe_trace_func(ri, regs);
 #ifdef CONFIG_PERF_EVENTS
 	if (tp->flags & TP_FLAG_PROFILE)
-		kretprobe_profile_func(ri, regs);
+		kretprobe_perf_func(ri, regs);
 #endif
 	return 0;	/* We don't tweek kernel, so just return 0 */
 }
@@ -1359,30 +1340,33 @@ static int register_probe_event(struct trace_probe *tp)
 	if (probe_is_return(tp)) {
 		tp->event.trace = print_kretprobe_event;
 		call->raw_init = probe_event_raw_init;
-		call->show_format = kretprobe_event_show_format;
 		call->define_fields = kretprobe_event_define_fields;
 	} else {
 		tp->event.trace = print_kprobe_event;
 		call->raw_init = probe_event_raw_init;
-		call->show_format = kprobe_event_show_format;
 		call->define_fields = kprobe_event_define_fields;
 	}
+	if (set_print_fmt(tp) < 0)
+		return -ENOMEM;
 	call->event = &tp->event;
 	call->id = register_ftrace_event(&tp->event);
-	if (!call->id)
+	if (!call->id) {
+		kfree(call->print_fmt);
 		return -ENODEV;
+	}
 	call->enabled = 0;
 	call->regfunc = probe_event_enable;
 	call->unregfunc = probe_event_disable;
 
 #ifdef CONFIG_PERF_EVENTS
-	call->profile_enable = probe_profile_enable;
-	call->profile_disable = probe_profile_disable;
+	call->perf_event_enable = probe_perf_enable;
+	call->perf_event_disable = probe_perf_disable;
 #endif
 	call->data = tp;
 	ret = trace_add_event_call(call);
 	if (ret) {
 		pr_info("Failed to register kprobe event: %s\n", call->name);
+		kfree(call->print_fmt);
 		unregister_ftrace_event(&tp->event);
 	}
 	return ret;
@@ -1392,6 +1376,7 @@ static void unregister_probe_event(struct trace_probe *tp)
 {
 	/* tp->event is unregistered in trace_remove_event_call() */
 	trace_remove_event_call(&tp->call);
+	kfree(tp->call.print_fmt);
 }
 
 /* Make a debugfs interface for controling probe points */
diff --git a/kernel/trace/trace_ksym.c b/kernel/trace/trace_ksym.c
index 94103cdcf9d..d59cd687947 100644
--- a/kernel/trace/trace_ksym.c
+++ b/kernel/trace/trace_ksym.c
@@ -23,6 +23,7 @@
 #include <linux/debugfs.h>
 #include <linux/ftrace.h>
 #include <linux/module.h>
+#include <linux/slab.h>
 #include <linux/fs.h>
 
 #include "trace_output.h"
diff --git a/kernel/trace/trace_mmiotrace.c b/kernel/trace/trace_mmiotrace.c
index 0acd834659e..017fa376505 100644
--- a/kernel/trace/trace_mmiotrace.c
+++ b/kernel/trace/trace_mmiotrace.c
@@ -9,6 +9,7 @@
 #include <linux/kernel.h>
 #include <linux/mmiotrace.h>
 #include <linux/pci.h>
+#include <linux/slab.h>
 #include <linux/time.h>
 
 #include <asm/atomic.h>
diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c
index 280fea470d6..81003b4d617 100644
--- a/kernel/trace/trace_selftest.c
+++ b/kernel/trace/trace_selftest.c
@@ -3,6 +3,7 @@
 #include <linux/stringify.h>
 #include <linux/kthread.h>
 #include <linux/delay.h>
+#include <linux/slab.h>
 
 static inline int trace_valid_entry(struct trace_entry *entry)
 {
diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
index 678a5120ee3..f4bc9b27de5 100644
--- a/kernel/trace/trace_stack.c
+++ b/kernel/trace/trace_stack.c
@@ -157,6 +157,7 @@ stack_max_size_write(struct file *filp, const char __user *ubuf,
 	unsigned long val, flags;
 	char buf[64];
 	int ret;
+	int cpu;
 
 	if (count >= sizeof(buf))
 		return -EINVAL;
@@ -171,9 +172,20 @@ stack_max_size_write(struct file *filp, const char __user *ubuf,
 		return ret;
 
 	local_irq_save(flags);
+
+	/*
+	 * In case we trace inside arch_spin_lock() or after (NMI),
+	 * we will cause circular lock, so we also need to increase
+	 * the percpu trace_active here.
+	 */
+	cpu = smp_processor_id();
+	per_cpu(trace_active, cpu)++;
+
 	arch_spin_lock(&max_stack_lock);
 	*ptr = val;
 	arch_spin_unlock(&max_stack_lock);
+
+	per_cpu(trace_active, cpu)--;
 	local_irq_restore(flags);
 
 	return count;
@@ -206,7 +218,13 @@ t_next(struct seq_file *m, void *v, loff_t *pos)
 
 static void *t_start(struct seq_file *m, loff_t *pos)
 {
+	int cpu;
+
 	local_irq_disable();
+
+	cpu = smp_processor_id();
+	per_cpu(trace_active, cpu)++;
+
 	arch_spin_lock(&max_stack_lock);
 
 	if (*pos == 0)
@@ -217,7 +235,13 @@ static void *t_start(struct seq_file *m, loff_t *pos)
 
 static void t_stop(struct seq_file *m, void *p)
 {
+	int cpu;
+
 	arch_spin_unlock(&max_stack_lock);
+
+	cpu = smp_processor_id();
+	per_cpu(trace_active, cpu)--;
+
 	local_irq_enable();
 }
 
diff --git a/kernel/trace/trace_stat.c b/kernel/trace/trace_stat.c
index a4bb239eb98..96cffb269e7 100644
--- a/kernel/trace/trace_stat.c
+++ b/kernel/trace/trace_stat.c
@@ -10,6 +10,7 @@
 
 
 #include <linux/list.h>
+#include <linux/slab.h>
 #include <linux/rbtree.h>
 #include <linux/debugfs.h>
 #include "trace_stat.h"
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index 4e332b9e449..4d6d711717f 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -1,5 +1,6 @@
 #include <trace/syscall.h>
 #include <trace/events/syscalls.h>
+#include <linux/slab.h>
 #include <linux/kernel.h>
 #include <linux/ftrace.h>
 #include <linux/perf_event.h>
@@ -143,70 +144,65 @@ extern char *__bad_type_size(void);
 		#type, #name, offsetof(typeof(trace), name),		\
 		sizeof(trace.name), is_signed_type(type)
 
-int syscall_enter_format(struct ftrace_event_call *call, struct trace_seq *s)
+static
+int  __set_enter_print_fmt(struct syscall_metadata *entry, char *buf, int len)
 {
 	int i;
-	int ret;
-	struct syscall_metadata *entry = call->data;
-	struct syscall_trace_enter trace;
-	int offset = offsetof(struct syscall_trace_enter, args);
+	int pos = 0;
 
-	ret = trace_seq_printf(s, "\tfield:%s %s;\toffset:%zu;\tsize:%zu;"
-			       "\tsigned:%u;\n",
-			       SYSCALL_FIELD(int, nr));
-	if (!ret)
-		return 0;
+	/* When len=0, we just calculate the needed length */
+#define LEN_OR_ZERO (len ? len - pos : 0)
 
+	pos += snprintf(buf + pos, LEN_OR_ZERO, "\"");
 	for (i = 0; i < entry->nb_args; i++) {
-		ret = trace_seq_printf(s, "\tfield:%s %s;", entry->types[i],
-				        entry->args[i]);
-		if (!ret)
-			return 0;
-		ret = trace_seq_printf(s, "\toffset:%d;\tsize:%zu;"
-				       "\tsigned:%u;\n", offset,
-				       sizeof(unsigned long),
-				       is_signed_type(unsigned long));
-		if (!ret)
-			return 0;
-		offset += sizeof(unsigned long);
+		pos += snprintf(buf + pos, LEN_OR_ZERO, "%s: 0x%%0%zulx%s",
+				entry->args[i], sizeof(unsigned long),
+				i == entry->nb_args - 1 ? "" : ", ");
 	}
+	pos += snprintf(buf + pos, LEN_OR_ZERO, "\"");
 
-	trace_seq_puts(s, "\nprint fmt: \"");
 	for (i = 0; i < entry->nb_args; i++) {
-		ret = trace_seq_printf(s, "%s: 0x%%0%zulx%s", entry->args[i],
-				        sizeof(unsigned long),
-					i == entry->nb_args - 1 ? "" : ", ");
-		if (!ret)
-			return 0;
+		pos += snprintf(buf + pos, LEN_OR_ZERO,
+				", ((unsigned long)(REC->%s))", entry->args[i]);
 	}
-	trace_seq_putc(s, '"');
 
-	for (i = 0; i < entry->nb_args; i++) {
-		ret = trace_seq_printf(s, ", ((unsigned long)(REC->%s))",
-				       entry->args[i]);
-		if (!ret)
-			return 0;
-	}
+#undef LEN_OR_ZERO
 
-	return trace_seq_putc(s, '\n');
+	/* return the length of print_fmt */
+	return pos;
 }
 
-int syscall_exit_format(struct ftrace_event_call *call, struct trace_seq *s)
+static int set_syscall_print_fmt(struct ftrace_event_call *call)
 {
-	int ret;
-	struct syscall_trace_exit trace;
+	char *print_fmt;
+	int len;
+	struct syscall_metadata *entry = call->data;
 
-	ret = trace_seq_printf(s,
-			       "\tfield:%s %s;\toffset:%zu;\tsize:%zu;"
-			       "\tsigned:%u;\n"
-			       "\tfield:%s %s;\toffset:%zu;\tsize:%zu;"
-			       "\tsigned:%u;\n",
-			       SYSCALL_FIELD(int, nr),
-			       SYSCALL_FIELD(long, ret));
-	if (!ret)
+	if (entry->enter_event != call) {
+		call->print_fmt = "\"0x%lx\", REC->ret";
 		return 0;
+	}
 
-	return trace_seq_printf(s, "\nprint fmt: \"0x%%lx\", REC->ret\n");
+	/* First: called with 0 length to calculate the needed length */
+	len = __set_enter_print_fmt(entry, NULL, 0);
+
+	print_fmt = kmalloc(len + 1, GFP_KERNEL);
+	if (!print_fmt)
+		return -ENOMEM;
+
+	/* Second: actually write the @print_fmt */
+	__set_enter_print_fmt(entry, print_fmt, len + 1);
+	call->print_fmt = print_fmt;
+
+	return 0;
+}
+
+static void free_syscall_print_fmt(struct ftrace_event_call *call)
+{
+	struct syscall_metadata *entry = call->data;
+
+	if (entry->enter_event == call)
+		kfree(call->print_fmt);
 }
 
 int syscall_enter_define_fields(struct ftrace_event_call *call)
@@ -386,12 +382,22 @@ int init_syscall_trace(struct ftrace_event_call *call)
 {
 	int id;
 
-	id = register_ftrace_event(call->event);
-	if (!id)
-		return -ENODEV;
-	call->id = id;
-	INIT_LIST_HEAD(&call->fields);
-	return 0;
+	if (set_syscall_print_fmt(call) < 0)
+		return -ENOMEM;
+
+	id = trace_event_raw_init(call);
+
+	if (id < 0) {
+		free_syscall_print_fmt(call);
+		return id;
+	}
+
+	return id;
+}
+
+unsigned long __init arch_syscall_addr(int nr)
+{
+	return (unsigned long)sys_call_table[nr];
 }
 
 int __init init_ftrace_syscalls(void)
@@ -423,12 +429,12 @@ core_initcall(init_ftrace_syscalls);
 
 #ifdef CONFIG_PERF_EVENTS
 
-static DECLARE_BITMAP(enabled_prof_enter_syscalls, NR_syscalls);
-static DECLARE_BITMAP(enabled_prof_exit_syscalls, NR_syscalls);
-static int sys_prof_refcount_enter;
-static int sys_prof_refcount_exit;
+static DECLARE_BITMAP(enabled_perf_enter_syscalls, NR_syscalls);
+static DECLARE_BITMAP(enabled_perf_exit_syscalls, NR_syscalls);
+static int sys_perf_refcount_enter;
+static int sys_perf_refcount_exit;
 
-static void prof_syscall_enter(struct pt_regs *regs, long id)
+static void perf_syscall_enter(struct pt_regs *regs, long id)
 {
 	struct syscall_metadata *sys_data;
 	struct syscall_trace_enter *rec;
@@ -438,7 +444,7 @@ static void prof_syscall_enter(struct pt_regs *regs, long id)
 	int size;
 
 	syscall_nr = syscall_get_nr(current, regs);
-	if (!test_bit(syscall_nr, enabled_prof_enter_syscalls))
+	if (!test_bit(syscall_nr, enabled_perf_enter_syscalls))
 		return;
 
 	sys_data = syscall_nr_to_meta(syscall_nr);
@@ -450,11 +456,11 @@ static void prof_syscall_enter(struct pt_regs *regs, long id)
 	size = ALIGN(size + sizeof(u32), sizeof(u64));
 	size -= sizeof(u32);
 
-	if (WARN_ONCE(size > FTRACE_MAX_PROFILE_SIZE,
-		      "profile buffer not large enough"))
+	if (WARN_ONCE(size > PERF_MAX_TRACE_SIZE,
+		      "perf buffer not large enough"))
 		return;
 
-	rec = (struct syscall_trace_enter *)ftrace_perf_buf_prepare(size,
+	rec = (struct syscall_trace_enter *)perf_trace_buf_prepare(size,
 				sys_data->enter_event->id, &rctx, &flags);
 	if (!rec)
 		return;
@@ -462,10 +468,10 @@ static void prof_syscall_enter(struct pt_regs *regs, long id)
 	rec->nr = syscall_nr;
 	syscall_get_arguments(current, regs, 0, sys_data->nb_args,
 			       (unsigned long *)&rec->args);
-	ftrace_perf_buf_submit(rec, size, rctx, 0, 1, flags);
+	perf_trace_buf_submit(rec, size, rctx, 0, 1, flags, regs);
 }
 
-int prof_sysenter_enable(struct ftrace_event_call *call)
+int perf_sysenter_enable(struct ftrace_event_call *call)
 {
 	int ret = 0;
 	int num;
@@ -473,34 +479,34 @@ int prof_sysenter_enable(struct ftrace_event_call *call)
 	num = ((struct syscall_metadata *)call->data)->syscall_nr;
 
 	mutex_lock(&syscall_trace_lock);
-	if (!sys_prof_refcount_enter)
-		ret = register_trace_sys_enter(prof_syscall_enter);
+	if (!sys_perf_refcount_enter)
+		ret = register_trace_sys_enter(perf_syscall_enter);
 	if (ret) {
 		pr_info("event trace: Could not activate"
 				"syscall entry trace point");
 	} else {
-		set_bit(num, enabled_prof_enter_syscalls);
-		sys_prof_refcount_enter++;
+		set_bit(num, enabled_perf_enter_syscalls);
+		sys_perf_refcount_enter++;
 	}
 	mutex_unlock(&syscall_trace_lock);
 	return ret;
 }
 
-void prof_sysenter_disable(struct ftrace_event_call *call)
+void perf_sysenter_disable(struct ftrace_event_call *call)
 {
 	int num;
 
 	num = ((struct syscall_metadata *)call->data)->syscall_nr;
 
 	mutex_lock(&syscall_trace_lock);
-	sys_prof_refcount_enter--;
-	clear_bit(num, enabled_prof_enter_syscalls);
-	if (!sys_prof_refcount_enter)
-		unregister_trace_sys_enter(prof_syscall_enter);
+	sys_perf_refcount_enter--;
+	clear_bit(num, enabled_perf_enter_syscalls);
+	if (!sys_perf_refcount_enter)
+		unregister_trace_sys_enter(perf_syscall_enter);
 	mutex_unlock(&syscall_trace_lock);
 }
 
-static void prof_syscall_exit(struct pt_regs *regs, long ret)
+static void perf_syscall_exit(struct pt_regs *regs, long ret)
 {
 	struct syscall_metadata *sys_data;
 	struct syscall_trace_exit *rec;
@@ -510,7 +516,7 @@ static void prof_syscall_exit(struct pt_regs *regs, long ret)
 	int size;
 
 	syscall_nr = syscall_get_nr(current, regs);
-	if (!test_bit(syscall_nr, enabled_prof_exit_syscalls))
+	if (!test_bit(syscall_nr, enabled_perf_exit_syscalls))
 		return;
 
 	sys_data = syscall_nr_to_meta(syscall_nr);
@@ -525,11 +531,11 @@ static void prof_syscall_exit(struct pt_regs *regs, long ret)
 	 * Impossible, but be paranoid with the future
 	 * How to put this check outside runtime?
 	 */
-	if (WARN_ONCE(size > FTRACE_MAX_PROFILE_SIZE,
-		"exit event has grown above profile buffer size"))
+	if (WARN_ONCE(size > PERF_MAX_TRACE_SIZE,
+		"exit event has grown above perf buffer size"))
 		return;
 
-	rec = (struct syscall_trace_exit *)ftrace_perf_buf_prepare(size,
+	rec = (struct syscall_trace_exit *)perf_trace_buf_prepare(size,
 				sys_data->exit_event->id, &rctx, &flags);
 	if (!rec)
 		return;
@@ -537,10 +543,10 @@ static void prof_syscall_exit(struct pt_regs *regs, long ret)
 	rec->nr = syscall_nr;
 	rec->ret = syscall_get_return_value(current, regs);
 
-	ftrace_perf_buf_submit(rec, size, rctx, 0, 1, flags);
+	perf_trace_buf_submit(rec, size, rctx, 0, 1, flags, regs);
 }
 
-int prof_sysexit_enable(struct ftrace_event_call *call)
+int perf_sysexit_enable(struct ftrace_event_call *call)
 {
 	int ret = 0;
 	int num;
@@ -548,30 +554,30 @@ int prof_sysexit_enable(struct ftrace_event_call *call)
 	num = ((struct syscall_metadata *)call->data)->syscall_nr;
 
 	mutex_lock(&syscall_trace_lock);
-	if (!sys_prof_refcount_exit)
-		ret = register_trace_sys_exit(prof_syscall_exit);
+	if (!sys_perf_refcount_exit)
+		ret = register_trace_sys_exit(perf_syscall_exit);
 	if (ret) {
 		pr_info("event trace: Could not activate"
-				"syscall entry trace point");
+				"syscall exit trace point");
 	} else {
-		set_bit(num, enabled_prof_exit_syscalls);
-		sys_prof_refcount_exit++;
+		set_bit(num, enabled_perf_exit_syscalls);
+		sys_perf_refcount_exit++;
 	}
 	mutex_unlock(&syscall_trace_lock);
 	return ret;
 }
 
-void prof_sysexit_disable(struct ftrace_event_call *call)
+void perf_sysexit_disable(struct ftrace_event_call *call)
 {
 	int num;
 
 	num = ((struct syscall_metadata *)call->data)->syscall_nr;
 
 	mutex_lock(&syscall_trace_lock);
-	sys_prof_refcount_exit--;
-	clear_bit(num, enabled_prof_exit_syscalls);
-	if (!sys_prof_refcount_exit)
-		unregister_trace_sys_exit(prof_syscall_exit);
+	sys_perf_refcount_exit--;
+	clear_bit(num, enabled_perf_exit_syscalls);
+	if (!sys_perf_refcount_exit)
+		unregister_trace_sys_exit(perf_syscall_exit);
 	mutex_unlock(&syscall_trace_lock);
 }
 
diff --git a/kernel/trace/trace_workqueue.c b/kernel/trace/trace_workqueue.c
index 40cafb07dff..cc2d2faa7d9 100644
--- a/kernel/trace/trace_workqueue.c
+++ b/kernel/trace/trace_workqueue.c
@@ -9,6 +9,7 @@
 #include <trace/events/workqueue.h>
 #include <linux/list.h>
 #include <linux/percpu.h>
+#include <linux/slab.h>
 #include <linux/kref.h>
 #include "trace_stat.h"
 #include "trace.h"
diff --git a/kernel/tsacct.c b/kernel/tsacct.c
index 00d59d048ed..0a67e041edf 100644
--- a/kernel/tsacct.c
+++ b/kernel/tsacct.c
@@ -21,6 +21,7 @@
 #include <linux/tsacct_kern.h>
 #include <linux/acct.h>
 #include <linux/jiffies.h>
+#include <linux/mm.h>
 
 /*
  * fill in basic accounting fields
diff --git a/kernel/user.c b/kernel/user.c
index 46d0165ca70..766467b3bcb 100644
--- a/kernel/user.c
+++ b/kernel/user.c
@@ -56,9 +56,6 @@ struct user_struct root_user = {
 	.sigpending	= ATOMIC_INIT(0),
 	.locked_shm     = 0,
 	.user_ns	= &init_user_ns,
-#ifdef CONFIG_USER_SCHED
-	.tg		= &init_task_group,
-#endif
 };
 
 /*
@@ -75,268 +72,6 @@ static void uid_hash_remove(struct user_struct *up)
 	put_user_ns(up->user_ns);
 }
 
-#ifdef CONFIG_USER_SCHED
-
-static void sched_destroy_user(struct user_struct *up)
-{
-	sched_destroy_group(up->tg);
-}
-
-static int sched_create_user(struct user_struct *up)
-{
-	int rc = 0;
-
-	up->tg = sched_create_group(&root_task_group);
-	if (IS_ERR(up->tg))
-		rc = -ENOMEM;
-
-	set_tg_uid(up);
-
-	return rc;
-}
-
-#else	/* CONFIG_USER_SCHED */
-
-static void sched_destroy_user(struct user_struct *up) { }
-static int sched_create_user(struct user_struct *up) { return 0; }
-
-#endif	/* CONFIG_USER_SCHED */
-
-#if defined(CONFIG_USER_SCHED) && defined(CONFIG_SYSFS)
-
-static struct user_struct *uid_hash_find(uid_t uid, struct hlist_head *hashent)
-{
-	struct user_struct *user;
-	struct hlist_node *h;
-
-	hlist_for_each_entry(user, h, hashent, uidhash_node) {
-		if (user->uid == uid) {
-			/* possibly resurrect an "almost deleted" object */
-			if (atomic_inc_return(&user->__count) == 1)
-				cancel_delayed_work(&user->work);
-			return user;
-		}
-	}
-
-	return NULL;
-}
-
-static struct kset *uids_kset; /* represents the /sys/kernel/uids/ directory */
-static DEFINE_MUTEX(uids_mutex);
-
-static inline void uids_mutex_lock(void)
-{
-	mutex_lock(&uids_mutex);
-}
-
-static inline void uids_mutex_unlock(void)
-{
-	mutex_unlock(&uids_mutex);
-}
-
-/* uid directory attributes */
-#ifdef CONFIG_FAIR_GROUP_SCHED
-static ssize_t cpu_shares_show(struct kobject *kobj,
-			       struct kobj_attribute *attr,
-			       char *buf)
-{
-	struct user_struct *up = container_of(kobj, struct user_struct, kobj);
-
-	return sprintf(buf, "%lu\n", sched_group_shares(up->tg));
-}
-
-static ssize_t cpu_shares_store(struct kobject *kobj,
-				struct kobj_attribute *attr,
-				const char *buf, size_t size)
-{
-	struct user_struct *up = container_of(kobj, struct user_struct, kobj);
-	unsigned long shares;
-	int rc;
-
-	sscanf(buf, "%lu", &shares);
-
-	rc = sched_group_set_shares(up->tg, shares);
-
-	return (rc ? rc : size);
-}
-
-static struct kobj_attribute cpu_share_attr =
-	__ATTR(cpu_share, 0644, cpu_shares_show, cpu_shares_store);
-#endif
-
-#ifdef CONFIG_RT_GROUP_SCHED
-static ssize_t cpu_rt_runtime_show(struct kobject *kobj,
-				   struct kobj_attribute *attr,
-				   char *buf)
-{
-	struct user_struct *up = container_of(kobj, struct user_struct, kobj);
-
-	return sprintf(buf, "%ld\n", sched_group_rt_runtime(up->tg));
-}
-
-static ssize_t cpu_rt_runtime_store(struct kobject *kobj,
-				    struct kobj_attribute *attr,
-				    const char *buf, size_t size)
-{
-	struct user_struct *up = container_of(kobj, struct user_struct, kobj);
-	unsigned long rt_runtime;
-	int rc;
-
-	sscanf(buf, "%ld", &rt_runtime);
-
-	rc = sched_group_set_rt_runtime(up->tg, rt_runtime);
-
-	return (rc ? rc : size);
-}
-
-static struct kobj_attribute cpu_rt_runtime_attr =
-	__ATTR(cpu_rt_runtime, 0644, cpu_rt_runtime_show, cpu_rt_runtime_store);
-
-static ssize_t cpu_rt_period_show(struct kobject *kobj,
-				   struct kobj_attribute *attr,
-				   char *buf)
-{
-	struct user_struct *up = container_of(kobj, struct user_struct, kobj);
-
-	return sprintf(buf, "%lu\n", sched_group_rt_period(up->tg));
-}
-
-static ssize_t cpu_rt_period_store(struct kobject *kobj,
-				    struct kobj_attribute *attr,
-				    const char *buf, size_t size)
-{
-	struct user_struct *up = container_of(kobj, struct user_struct, kobj);
-	unsigned long rt_period;
-	int rc;
-
-	sscanf(buf, "%lu", &rt_period);
-
-	rc = sched_group_set_rt_period(up->tg, rt_period);
-
-	return (rc ? rc : size);
-}
-
-static struct kobj_attribute cpu_rt_period_attr =
-	__ATTR(cpu_rt_period, 0644, cpu_rt_period_show, cpu_rt_period_store);
-#endif
-
-/* default attributes per uid directory */
-static struct attribute *uids_attributes[] = {
-#ifdef CONFIG_FAIR_GROUP_SCHED
-	&cpu_share_attr.attr,
-#endif
-#ifdef CONFIG_RT_GROUP_SCHED
-	&cpu_rt_runtime_attr.attr,
-	&cpu_rt_period_attr.attr,
-#endif
-	NULL
-};
-
-/* the lifetime of user_struct is not managed by the core (now) */
-static void uids_release(struct kobject *kobj)
-{
-	return;
-}
-
-static struct kobj_type uids_ktype = {
-	.sysfs_ops = &kobj_sysfs_ops,
-	.default_attrs = uids_attributes,
-	.release = uids_release,
-};
-
-/*
- * Create /sys/kernel/uids/<uid>/cpu_share file for this user
- * We do not create this file for users in a user namespace (until
- * sysfs tagging is implemented).
- *
- * See Documentation/scheduler/sched-design-CFS.txt for ramifications.
- */
-static int uids_user_create(struct user_struct *up)
-{
-	struct kobject *kobj = &up->kobj;
-	int error;
-
-	memset(kobj, 0, sizeof(struct kobject));
-	if (up->user_ns != &init_user_ns)
-		return 0;
-	kobj->kset = uids_kset;
-	error = kobject_init_and_add(kobj, &uids_ktype, NULL, "%d", up->uid);
-	if (error) {
-		kobject_put(kobj);
-		goto done;
-	}
-
-	kobject_uevent(kobj, KOBJ_ADD);
-done:
-	return error;
-}
-
-/* create these entries in sysfs:
- * 	"/sys/kernel/uids" directory
- * 	"/sys/kernel/uids/0" directory (for root user)
- * 	"/sys/kernel/uids/0/cpu_share" file (for root user)
- */
-int __init uids_sysfs_init(void)
-{
-	uids_kset = kset_create_and_add("uids", NULL, kernel_kobj);
-	if (!uids_kset)
-		return -ENOMEM;
-
-	return uids_user_create(&root_user);
-}
-
-/* delayed work function to remove sysfs directory for a user and free up
- * corresponding structures.
- */
-static void cleanup_user_struct(struct work_struct *w)
-{
-	struct user_struct *up = container_of(w, struct user_struct, work.work);
-	unsigned long flags;
-	int remove_user = 0;
-
-	/* Make uid_hash_remove() + sysfs_remove_file() + kobject_del()
-	 * atomic.
-	 */
-	uids_mutex_lock();
-
-	spin_lock_irqsave(&uidhash_lock, flags);
-	if (atomic_read(&up->__count) == 0) {
-		uid_hash_remove(up);
-		remove_user = 1;
-	}
-	spin_unlock_irqrestore(&uidhash_lock, flags);
-
-	if (!remove_user)
-		goto done;
-
-	if (up->user_ns == &init_user_ns) {
-		kobject_uevent(&up->kobj, KOBJ_REMOVE);
-		kobject_del(&up->kobj);
-		kobject_put(&up->kobj);
-	}
-
-	sched_destroy_user(up);
-	key_put(up->uid_keyring);
-	key_put(up->session_keyring);
-	kmem_cache_free(uid_cachep, up);
-
-done:
-	uids_mutex_unlock();
-}
-
-/* IRQs are disabled and uidhash_lock is held upon function entry.
- * IRQ state (as stored in flags) is restored and uidhash_lock released
- * upon function exit.
- */
-static void free_user(struct user_struct *up, unsigned long flags)
-{
-	INIT_DELAYED_WORK(&up->work, cleanup_user_struct);
-	schedule_delayed_work(&up->work, msecs_to_jiffies(1000));
-	spin_unlock_irqrestore(&uidhash_lock, flags);
-}
-
-#else	/* CONFIG_USER_SCHED && CONFIG_SYSFS */
-
 static struct user_struct *uid_hash_find(uid_t uid, struct hlist_head *hashent)
 {
 	struct user_struct *user;
@@ -352,11 +87,6 @@ static struct user_struct *uid_hash_find(uid_t uid, struct hlist_head *hashent)
 	return NULL;
 }
 
-int uids_sysfs_init(void) { return 0; }
-static inline int uids_user_create(struct user_struct *up) { return 0; }
-static inline void uids_mutex_lock(void) { }
-static inline void uids_mutex_unlock(void) { }
-
 /* IRQs are disabled and uidhash_lock is held upon function entry.
  * IRQ state (as stored in flags) is restored and uidhash_lock released
  * upon function exit.
@@ -365,32 +95,11 @@ static void free_user(struct user_struct *up, unsigned long flags)
 {
 	uid_hash_remove(up);
 	spin_unlock_irqrestore(&uidhash_lock, flags);
-	sched_destroy_user(up);
 	key_put(up->uid_keyring);
 	key_put(up->session_keyring);
 	kmem_cache_free(uid_cachep, up);
 }
 
-#endif
-
-#if defined(CONFIG_RT_GROUP_SCHED) && defined(CONFIG_USER_SCHED)
-/*
- * We need to check if a setuid can take place. This function should be called
- * before successfully completing the setuid.
- */
-int task_can_switch_user(struct user_struct *up, struct task_struct *tsk)
-{
-
-	return sched_rt_can_attach(up->tg, tsk);
-
-}
-#else
-int task_can_switch_user(struct user_struct *up, struct task_struct *tsk)
-{
-	return 1;
-}
-#endif
-
 /*
  * Locate the user_struct for the passed UID.  If found, take a ref on it.  The
  * caller must undo that ref with free_uid().
@@ -431,8 +140,6 @@ struct user_struct *alloc_uid(struct user_namespace *ns, uid_t uid)
 	/* Make uid_hash_find() + uids_user_create() + uid_hash_insert()
 	 * atomic.
 	 */
-	uids_mutex_lock();
-
 	spin_lock_irq(&uidhash_lock);
 	up = uid_hash_find(uid, hashent);
 	spin_unlock_irq(&uidhash_lock);
@@ -445,14 +152,8 @@ struct user_struct *alloc_uid(struct user_namespace *ns, uid_t uid)
 		new->uid = uid;
 		atomic_set(&new->__count, 1);
 
-		if (sched_create_user(new) < 0)
-			goto out_free_user;
-
 		new->user_ns = get_user_ns(ns);
 
-		if (uids_user_create(new))
-			goto out_destoy_sched;
-
 		/*
 		 * Before adding this, check whether we raced
 		 * on adding the same user already..
@@ -475,17 +176,11 @@ struct user_struct *alloc_uid(struct user_namespace *ns, uid_t uid)
 		spin_unlock_irq(&uidhash_lock);
 	}
 
-	uids_mutex_unlock();
-
 	return up;
 
-out_destoy_sched:
-	sched_destroy_user(new);
 	put_user_ns(new->user_ns);
-out_free_user:
 	kmem_cache_free(uid_cachep, new);
 out_unlock:
-	uids_mutex_unlock();
 	return NULL;
 }
 
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index dee48658805..5bfb213984b 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -774,7 +774,7 @@ void flush_delayed_work(struct delayed_work *dwork)
 {
 	if (del_timer_sync(&dwork->timer)) {
 		struct cpu_workqueue_struct *cwq;
-		cwq = wq_per_cpu(keventd_wq, get_cpu());
+		cwq = wq_per_cpu(get_wq_data(&dwork->work)->wq, get_cpu());
 		__queue_work(cwq, &dwork->work);
 		put_cpu();
 	}