Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-2.6

Conflicts:

	drivers/net/wireless/rt2x00/rt2x00dev.c
	net/8021q/vlan_dev.c

26 files changed, 670 insertions, 575 deletions

diff --git a/kernel/Kconfig.preempt b/kernel/Kconfig.preempt
index 0669b70fa6a3..9fdba03dc1fc 100644
--- a/kernel/Kconfig.preempt
+++ b/kernel/Kconfig.preempt
@@ -52,8 +52,23 @@ config PREEMPT
 
 endchoice
 
+config PREEMPT_RCU
+	bool "Preemptible RCU"
+	depends on PREEMPT
+	default n
+	help
+	  This option reduces the latency of the kernel by making certain
+	  RCU sections preemptible. Normally RCU code is non-preemptible, if
+	  this option is selected then read-only RCU sections become
+	  preemptible. This helps latency, but may expose bugs due to
+	  now-naive assumptions about each RCU read-side critical section
+	  remaining on a given CPU through its execution.
+
+	  Say N if you are unsure.
+
 config RCU_TRACE
 	bool "Enable tracing for RCU - currently stats in debugfs"
+	depends on PREEMPT_RCU
 	select DEBUG_FS
 	default y
 	help
diff --git a/kernel/audit.c b/kernel/audit.c
index 2eeea9a14240..10c4930c2bbf 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -170,7 +170,9 @@ void audit_panic(const char *message)
 			printk(KERN_ERR "audit: %s\n", message);
 		break;
 	case AUDIT_FAIL_PANIC:
-		panic("audit: %s\n", message);
+		/* test audit_pid since printk is always losey, why bother? */
+		if (audit_pid)
+			panic("audit: %s\n", message);
 		break;
 	}
 }
@@ -352,6 +354,7 @@ static int kauditd_thread(void *dummy)
 				if (err < 0) {
 					BUG_ON(err != -ECONNREFUSED); /* Shoudn't happen */
 					printk(KERN_ERR "audit: *NO* daemon at audit_pid=%d\n", audit_pid);
+					audit_log_lost("auditd dissapeared\n");
 					audit_pid = 0;
 				}
 			} else {
@@ -1350,17 +1353,19 @@ void audit_log_end(struct audit_buffer *ab)
 	if (!audit_rate_check()) {
 		audit_log_lost("rate limit exceeded");
 	} else {
+		struct nlmsghdr *nlh = nlmsg_hdr(ab->skb);
 		if (audit_pid) {
-			struct nlmsghdr *nlh = nlmsg_hdr(ab->skb);
 			nlh->nlmsg_len = ab->skb->len - NLMSG_SPACE(0);
 			skb_queue_tail(&audit_skb_queue, ab->skb);
 			ab->skb = NULL;
 			wake_up_interruptible(&kauditd_wait);
-		} else if (printk_ratelimit()) {
-			struct nlmsghdr *nlh = nlmsg_hdr(ab->skb);
-			printk(KERN_NOTICE "type=%d %s\n", nlh->nlmsg_type, ab->skb->data + NLMSG_SPACE(0));
-		} else {
-			audit_log_lost("printk limit exceeded\n");
+		} else if (nlh->nlmsg_type != AUDIT_EOE) {
+			if (printk_ratelimit()) {
+				printk(KERN_NOTICE "type=%d %s\n",
+					nlh->nlmsg_type,
+					ab->skb->data + NLMSG_SPACE(0));
+			} else
+				audit_log_lost("printk limit exceeded\n");
 		}
 	}
 	audit_buffer_free(ab);
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index 2087d6de67ea..782262e4107d 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -1070,7 +1070,7 @@ static int audit_log_single_execve_arg(struct audit_context *context,
 		 * so we can be sure nothing was lost.
 		 */
 		if ((i == 0) && (too_long))
-			audit_log_format(*ab, "a%d_len=%ld ", arg_num,
+			audit_log_format(*ab, "a%d_len=%zu ", arg_num,
 					 has_cntl ? 2*len : len);
 
 		/*
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index d8abe996e009..e9c2fb01e89b 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -2232,7 +2232,6 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
 
 	mutex_lock(&cgroup_mutex);
 
-	cgrp->flags = 0;
 	INIT_LIST_HEAD(&cgrp->sibling);
 	INIT_LIST_HEAD(&cgrp->children);
 	INIT_LIST_HEAD(&cgrp->css_sets);
@@ -2242,6 +2241,9 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
 	cgrp->root = parent->root;
 	cgrp->top_cgroup = parent->top_cgroup;
 
+	if (notify_on_release(parent))
+		set_bit(CGRP_NOTIFY_ON_RELEASE, &cgrp->flags);
+
 	for_each_subsys(root, ss) {
 		struct cgroup_subsys_state *css = ss->create(ss, cgrp);
 		if (IS_ERR(css)) {
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 3e296ed81d4d..a1b61f414228 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -322,8 +322,8 @@ static void guarantee_online_mems(const struct cpuset *cs, nodemask_t *pmask)
  * Call without callback_mutex or task_lock() held.  May be
  * called with or without cgroup_mutex held.  Thanks in part to
  * 'the_top_cpuset_hack', the task's cpuset pointer will never
- * be NULL.  This routine also might acquire callback_mutex and
- * current->mm->mmap_sem during call.
+ * be NULL.  This routine also might acquire callback_mutex during
+ * call.
  *
  * Reading current->cpuset->mems_generation doesn't need task_lock
  * to guard the current->cpuset derefence, because it is guarded
diff --git a/kernel/exit.c b/kernel/exit.c
index 506a957b665a..53872bf993fa 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -214,20 +214,19 @@ struct pid *session_of_pgrp(struct pid *pgrp)
 static int will_become_orphaned_pgrp(struct pid *pgrp, struct task_struct *ignored_task)
 {
 	struct task_struct *p;
-	int ret = 1;
 
 	do_each_pid_task(pgrp, PIDTYPE_PGID, p) {
-		if (p == ignored_task
-				|| p->exit_state
-				|| is_global_init(p->real_parent))
+		if ((p == ignored_task) ||
+		    (p->exit_state && thread_group_empty(p)) ||
+		    is_global_init(p->real_parent))
 			continue;
+
 		if (task_pgrp(p->real_parent) != pgrp &&
-		    task_session(p->real_parent) == task_session(p)) {
-			ret = 0;
-			break;
-		}
+		    task_session(p->real_parent) == task_session(p))
+			return 0;
 	} while_each_pid_task(pgrp, PIDTYPE_PGID, p);
-	return ret;	/* (sighing) "Often!" */
+
+	return 1;
 }
 
 int is_current_pgrp_orphaned(void)
@@ -255,6 +254,37 @@ static int has_stopped_jobs(struct pid *pgrp)
 	return retval;
 }
 
+/*
+ * Check to see if any process groups have become orphaned as
+ * a result of our exiting, and if they have any stopped jobs,
+ * send them a SIGHUP and then a SIGCONT. (POSIX 3.2.2.2)
+ */
+static void
+kill_orphaned_pgrp(struct task_struct *tsk, struct task_struct *parent)
+{
+	struct pid *pgrp = task_pgrp(tsk);
+	struct task_struct *ignored_task = tsk;
+
+	if (!parent)
+		 /* exit: our father is in a different pgrp than
+		  * we are and we were the only connection outside.
+		  */
+		parent = tsk->real_parent;
+	else
+		/* reparent: our child is in a different pgrp than
+		 * we are, and it was the only connection outside.
+		 */
+		ignored_task = NULL;
+
+	if (task_pgrp(parent) != pgrp &&
+	    task_session(parent) == task_session(tsk) &&
+	    will_become_orphaned_pgrp(pgrp, ignored_task) &&
+	    has_stopped_jobs(pgrp)) {
+		__kill_pgrp_info(SIGHUP, SEND_SIG_PRIV, pgrp);
+		__kill_pgrp_info(SIGCONT, SEND_SIG_PRIV, pgrp);
+	}
+}
+
 /**
  * reparent_to_kthreadd - Reparent the calling kernel thread to kthreadd
  *
@@ -635,22 +665,7 @@ reparent_thread(struct task_struct *p, struct task_struct *father, int traced)
 	    p->exit_signal != -1 && thread_group_empty(p))
 		do_notify_parent(p, p->exit_signal);
 
-	/*
-	 * process group orphan check
-	 * Case ii: Our child is in a different pgrp
-	 * than we are, and it was the only connection
-	 * outside, so the child pgrp is now orphaned.
-	 */
-	if ((task_pgrp(p) != task_pgrp(father)) &&
-	    (task_session(p) == task_session(father))) {
-		struct pid *pgrp = task_pgrp(p);
-
-		if (will_become_orphaned_pgrp(pgrp, NULL) &&
-		    has_stopped_jobs(pgrp)) {
-			__kill_pgrp_info(SIGHUP, SEND_SIG_PRIV, pgrp);
-			__kill_pgrp_info(SIGCONT, SEND_SIG_PRIV, pgrp);
-		}
-	}
+	kill_orphaned_pgrp(p, father);
 }
 
 /*
@@ -735,11 +750,9 @@ static void forget_original_parent(struct task_struct *father)
  * Send signals to all our closest relatives so that they know
  * to properly mourn us..
  */
-static void exit_notify(struct task_struct *tsk)
+static void exit_notify(struct task_struct *tsk, int group_dead)
 {
 	int state;
-	struct task_struct *t;
-	struct pid *pgrp;
 
 	/*
 	 * This does two things:
@@ -753,25 +766,8 @@ static void exit_notify(struct task_struct *tsk)
 	exit_task_namespaces(tsk);
 
 	write_lock_irq(&tasklist_lock);
-	/*
-	 * Check to see if any process groups have become orphaned
-	 * as a result of our exiting, and if they have any stopped
-	 * jobs, send them a SIGHUP and then a SIGCONT.  (POSIX 3.2.2.2)
-	 *
-	 * Case i: Our father is in a different pgrp than we are
-	 * and we were the only connection outside, so our pgrp
-	 * is about to become orphaned.
-	 */
-	t = tsk->real_parent;
-
-	pgrp = task_pgrp(tsk);
-	if ((task_pgrp(t) != pgrp) &&
-	    (task_session(t) == task_session(tsk)) &&
-	    will_become_orphaned_pgrp(pgrp, tsk) &&
-	    has_stopped_jobs(pgrp)) {
-		__kill_pgrp_info(SIGHUP, SEND_SIG_PRIV, pgrp);
-		__kill_pgrp_info(SIGCONT, SEND_SIG_PRIV, pgrp);
-	}
+	if (group_dead)
+		kill_orphaned_pgrp(tsk->group_leader, NULL);
 
 	/* Let father know we died
 	 *
@@ -788,8 +784,8 @@ static void exit_notify(struct task_struct *tsk)
 	 * the same after a fork.
 	 */
 	if (tsk->exit_signal != SIGCHLD && tsk->exit_signal != -1 &&
-	    ( tsk->parent_exec_id != t->self_exec_id  ||
-	      tsk->self_exec_id != tsk->parent_exec_id)
+	    (tsk->parent_exec_id != tsk->real_parent->self_exec_id ||
+	     tsk->self_exec_id != tsk->parent_exec_id)
 	    && !capable(CAP_KILL))
 		tsk->exit_signal = SIGCHLD;
 
@@ -986,7 +982,7 @@ NORET_TYPE void do_exit(long code)
 		module_put(tsk->binfmt->module);
 
 	proc_exit_connector(tsk);
-	exit_notify(tsk);
+	exit_notify(tsk, group_dead);
 #ifdef CONFIG_NUMA
 	mpol_free(tsk->mempolicy);
 	tsk->mempolicy = NULL;
@@ -1382,7 +1378,7 @@ unlock_sig:
 	if (!retval && infop)
 		retval = put_user(0, &infop->si_errno);
 	if (!retval && infop)
-		retval = put_user(why, &infop->si_code);
+		retval = put_user((short)why, &infop->si_code);
 	if (!retval && infop)
 		retval = put_user(exit_code, &infop->si_status);
 	if (!retval && infop)
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 7a86e6432338..fcfb580c3afc 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -498,27 +498,36 @@ static int __kprobes in_kprobes_functions(unsigned long addr)
 	return 0;
 }
 
+/*
+ * If we have a symbol_name argument, look it up and add the offset field
+ * to it. This way, we can specify a relative address to a symbol.
+ */
+static kprobe_opcode_t __kprobes *kprobe_addr(struct kprobe *p)
+{
+	kprobe_opcode_t *addr = p->addr;
+	if (p->symbol_name) {
+		if (addr)
+			return NULL;
+		kprobe_lookup_name(p->symbol_name, addr);
+	}
+
+	if (!addr)
+		return NULL;
+	return (kprobe_opcode_t *)(((char *)addr) + p->offset);
+}
+
 static int __kprobes __register_kprobe(struct kprobe *p,
 	unsigned long called_from)
 {
 	int ret = 0;
 	struct kprobe *old_p;
 	struct module *probed_mod;
+	kprobe_opcode_t *addr;
 
-	/*
-	 * If we have a symbol_name argument look it up,
-	 * and add it to the address.  That way the addr
-	 * field can either be global or relative to a symbol.
-	 */
-	if (p->symbol_name) {
-		if (p->addr)
-			return -EINVAL;
-		kprobe_lookup_name(p->symbol_name, p->addr);
-	}
-
-	if (!p->addr)
+	addr = kprobe_addr(p);
+	if (!addr)
 		return -EINVAL;
-	p->addr = (kprobe_opcode_t *)(((char *)p->addr)+ p->offset);
+	p->addr = addr;
 
 	if (!kernel_text_address((unsigned long) p->addr) ||
 	    in_kprobes_functions((unsigned long) p->addr))
@@ -678,8 +687,7 @@ void __kprobes unregister_jprobe(struct jprobe *jp)
 	unregister_kprobe(&jp->kp);
 }
 
-#ifdef ARCH_SUPPORTS_KRETPROBES
-
+#ifdef CONFIG_KRETPROBES
 /*
  * This kprobe pre_handler is registered with every kretprobe. When probe
  * hits it will set up the return probe.
@@ -722,12 +730,12 @@ int __kprobes register_kretprobe(struct kretprobe *rp)
 	int ret = 0;
 	struct kretprobe_instance *inst;
 	int i;
-	void *addr = rp->kp.addr;
+	void *addr;
 
 	if (kretprobe_blacklist_size) {
-		if (addr == NULL)
-			kprobe_lookup_name(rp->kp.symbol_name, addr);
-		addr += rp->kp.offset;
+		addr = kprobe_addr(&rp->kp);
+		if (!addr)
+			return -EINVAL;
 
 		for (i = 0; kretprobe_blacklist[i].name != NULL; i++) {
 			if (kretprobe_blacklist[i].addr == addr)
@@ -769,8 +777,7 @@ int __kprobes register_kretprobe(struct kretprobe *rp)
 	return ret;
 }
 
-#else /* ARCH_SUPPORTS_KRETPROBES */
-
+#else /* CONFIG_KRETPROBES */
 int __kprobes register_kretprobe(struct kretprobe *rp)
 {
 	return -ENOSYS;
@@ -781,8 +788,7 @@ static int __kprobes pre_handler_kretprobe(struct kprobe *p,
 {
 	return 0;
 }
-
-#endif /* ARCH_SUPPORTS_KRETPROBES */
+#endif /* CONFIG_KRETPROBES */
 
 void __kprobes unregister_kretprobe(struct kretprobe *rp)
 {
diff --git a/kernel/lockdep.c b/kernel/lockdep.c
index 3574379f4d62..81a4e4a3f087 100644
--- a/kernel/lockdep.c
+++ b/kernel/lockdep.c
@@ -779,6 +779,10 @@ register_lock_class(struct lockdep_map *lock, unsigned int subclass, int force)
 	 * parallel walking of the hash-list safe:
 	 */
 	list_add_tail_rcu(&class->hash_entry, hash_head);
+	/*
+	 * Add it to the global list of classes:
+	 */
+	list_add_tail_rcu(&class->lock_entry, &all_lock_classes);
 
 	if (verbose(class)) {
 		graph_unlock();
@@ -2282,10 +2286,6 @@ static int mark_lock(struct task_struct *curr, struct held_lock *this,
 			return 0;
 		break;
 	case LOCK_USED:
-		/*
-		 * Add it to the global list of classes:
-		 */
-		list_add_tail_rcu(&this->class->lock_entry, &all_lock_classes);
 		debug_atomic_dec(&nr_unused_locks);
 		break;
 	default:
diff --git a/kernel/marker.c b/kernel/marker.c
index 50effc01d9a2..48a4ea5afffd 100644
--- a/kernel/marker.c
+++ b/kernel/marker.c
@@ -698,14 +698,12 @@ int marker_probe_unregister(const char *name,
 {
 	struct marker_entry *entry;
 	struct marker_probe_closure *old;
-	int ret = 0;
+	int ret = -ENOENT;
 
 	mutex_lock(&markers_mutex);
 	entry = get_marker(name);
-	if (!entry) {
-		ret = -ENOENT;
+	if (!entry)
 		goto end;
-	}
 	if (entry->rcu_pending)
 		rcu_barrier();
 	old = marker_entry_remove_probe(entry, probe, probe_private);
@@ -713,12 +711,15 @@ int marker_probe_unregister(const char *name,
 	marker_update_probes();		/* may update entry */
 	mutex_lock(&markers_mutex);
 	entry = get_marker(name);
+	if (!entry)
+		goto end;
 	entry->oldptr = old;
 	entry->rcu_pending = 1;
 	/* write rcu_pending before calling the RCU callback */
 	smp_wmb();
 	call_rcu(&entry->rcu, free_old_closure);
 	remove_marker(name);	/* Ignore busy error message */
+	ret = 0;
 end:
 	mutex_unlock(&markers_mutex);
 	return ret;
diff --git a/kernel/module.c b/kernel/module.c
index 901cd6ac2f11..5d437bffd8dc 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -1933,8 +1933,15 @@ static struct module *load_module(void __user *umod,
 	/* Set up license info based on the info section */
 	set_license(mod, get_modinfo(sechdrs, infoindex, "license"));
 
+	/*
+	 * ndiswrapper is under GPL by itself, but loads proprietary modules.
+	 * Don't use add_taint_module(), as it would prevent ndiswrapper from
+	 * using GPL-only symbols it needs.
+	 */
 	if (strcmp(mod->name, "ndiswrapper") == 0)
-		add_taint_module(mod, TAINT_PROPRIETARY_MODULE);
+		add_taint(TAINT_PROPRIETARY_MODULE);
+
+	/* driverloader was caught wrongly pretending to be under GPL */
 	if (strcmp(mod->name, "driverloader") == 0)
 		add_taint_module(mod, TAINT_PROPRIETARY_MODULE);
 
@@ -2171,10 +2178,20 @@ sys_init_module(void __user *umod,
 		wake_up(&module_wq);
 		return ret;
 	}
+	if (ret > 0) {
+		printk(KERN_WARNING "%s: '%s'->init suspiciously returned %d, "
+				    "it should follow 0/-E convention\n"
+		       KERN_WARNING "%s: loading module anyway...\n",
+		       __func__, mod->name, ret,
+		       __func__);
+		dump_stack();
+	}
 
-	/* Now it's a first class citizen! */
-	mutex_lock(&module_mutex);
+	/* Now it's a first class citizen!  Wake up anyone waiting for it. */
 	mod->state = MODULE_STATE_LIVE;
+	wake_up(&module_wq);
+
+	mutex_lock(&module_mutex);
 	/* Drop initial reference. */
 	module_put(mod);
 	unwind_remove_table(mod->unwind_info, 1);
@@ -2183,7 +2200,6 @@ sys_init_module(void __user *umod,
 	mod->init_size = 0;
 	mod->init_text_size = 0;
 	mutex_unlock(&module_mutex);
-	wake_up(&module_wq);
 
 	return 0;
 }
diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig
index 79833170bb9c..6233f3b4ae66 100644
--- a/kernel/power/Kconfig
+++ b/kernel/power/Kconfig
@@ -190,7 +190,7 @@ config APM_EMULATION
 	  notification of APM "events" (e.g. battery status change).
 
 	  In order to use APM, you will need supporting software. For location
-	  and more information, read <file:Documentation/pm.txt> and the
+	  and more information, read <file:Documentation/power/pm.txt> and the
 	  Battery Powered Linux mini-HOWTO, available from
 	  <http://www.tldp.org/docs.html#howto>.
 
diff --git a/kernel/power/process.c b/kernel/power/process.c
index 7c2118f9597f..f1d0b345c9ba 100644
--- a/kernel/power/process.c
+++ b/kernel/power/process.c
@@ -75,22 +75,15 @@ void refrigerator(void)
 	__set_current_state(save);
 }
 
-static void fake_signal_wake_up(struct task_struct *p, int resume)
+static void fake_signal_wake_up(struct task_struct *p)
 {
 	unsigned long flags;
 
 	spin_lock_irqsave(&p->sighand->siglock, flags);
-	signal_wake_up(p, resume);
+	signal_wake_up(p, 0);
 	spin_unlock_irqrestore(&p->sighand->siglock, flags);
 }
 
-static void send_fake_signal(struct task_struct *p)
-{
-	if (task_is_stopped(p))
-		force_sig_specific(SIGSTOP, p);
-	fake_signal_wake_up(p, task_is_stopped(p));
-}
-
 static int has_mm(struct task_struct *p)
 {
 	return (p->mm && !(p->flags & PF_BORROWED_MM));
@@ -121,7 +114,7 @@ static int freeze_task(struct task_struct *p, int with_mm_only)
 	if (freezing(p)) {
 		if (has_mm(p)) {
 			if (!signal_pending(p))
-				fake_signal_wake_up(p, 0);
+				fake_signal_wake_up(p);
 		} else {
 			if (with_mm_only)
 				ret = 0;
@@ -135,7 +128,7 @@ static int freeze_task(struct task_struct *p, int with_mm_only)
 		} else {
 			if (has_mm(p)) {
 				set_freeze_flag(p);
-				send_fake_signal(p);
+				fake_signal_wake_up(p);
 			} else {
 				if (with_mm_only) {
 					ret = 0;
@@ -182,15 +175,17 @@ static int try_to_freeze_tasks(int freeze_user_space)
 			if (frozen(p) || !freezeable(p))
 				continue;
 
-			if (task_is_traced(p) && frozen(p->parent)) {
-				cancel_freezing(p);
-				continue;
-			}
-
 			if (!freeze_task(p, freeze_user_space))
 				continue;
 
-			if (!freezer_should_skip(p))
+			/*
+			 * Now that we've done set_freeze_flag, don't
+			 * perturb a task in TASK_STOPPED or TASK_TRACED.
+			 * It is "frozen enough".  If the task does wake
+			 * up, it will immediately call try_to_freeze.
+			 */
+			if (!task_is_stopped_or_traced(p) &&
+			    !freezer_should_skip(p))
 				todo++;
 		} while_each_thread(g, p);
 		read_unlock(&tasklist_lock);
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index 72a020cabb4c..5f91a07c4eac 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -447,7 +447,7 @@ static void memory_bm_free(struct memory_bitmap *bm, int clear_nosave_free)
  *	of @bm->cur_zone_bm are updated.
  */
 
-static void memory_bm_find_bit(struct memory_bitmap *bm, unsigned long pfn,
+static int memory_bm_find_bit(struct memory_bitmap *bm, unsigned long pfn,
 				void **addr, unsigned int *bit_nr)
 {
 	struct zone_bitmap *zone_bm;
@@ -461,7 +461,8 @@ static void memory_bm_find_bit(struct memory_bitmap *bm, unsigned long pfn,
 		while (pfn < zone_bm->start_pfn || pfn >= zone_bm->end_pfn) {
 			zone_bm = zone_bm->next;
 
-			BUG_ON(!zone_bm);
+			if (!zone_bm)
+				return -EFAULT;
 		}
 		bm->cur.zone_bm = zone_bm;
 	}
@@ -479,23 +480,40 @@ static void memory_bm_find_bit(struct memory_bitmap *bm, unsigned long pfn,
 	pfn -= bb->start_pfn;
 	*bit_nr = pfn % BM_BITS_PER_CHUNK;
 	*addr = bb->data + pfn / BM_BITS_PER_CHUNK;
+	return 0;
 }
 
 static void memory_bm_set_bit(struct memory_bitmap *bm, unsigned long pfn)
 {
 	void *addr;
 	unsigned int bit;
+	int error;
 
-	memory_bm_find_bit(bm, pfn, &addr, &bit);
+	error = memory_bm_find_bit(bm, pfn, &addr, &bit);
+	BUG_ON(error);
 	set_bit(bit, addr);
 }
 
+static int mem_bm_set_bit_check(struct memory_bitmap *bm, unsigned long pfn)
+{
+	void *addr;
+	unsigned int bit;
+	int error;
+
+	error = memory_bm_find_bit(bm, pfn, &addr, &bit);
+	if (!error)
+		set_bit(bit, addr);
+	return error;
+}
+
 static void memory_bm_clear_bit(struct memory_bitmap *bm, unsigned long pfn)
 {
 	void *addr;
 	unsigned int bit;
+	int error;
 
-	memory_bm_find_bit(bm, pfn, &addr, &bit);
+	error = memory_bm_find_bit(bm, pfn, &addr, &bit);
+	BUG_ON(error);
 	clear_bit(bit, addr);
 }
 
@@ -503,8 +521,10 @@ static int memory_bm_test_bit(struct memory_bitmap *bm, unsigned long pfn)
 {
 	void *addr;
 	unsigned int bit;
+	int error;
 
-	memory_bm_find_bit(bm, pfn, &addr, &bit);
+	error = memory_bm_find_bit(bm, pfn, &addr, &bit);
+	BUG_ON(error);
 	return test_bit(bit, addr);
 }
 
@@ -709,8 +729,15 @@ static void mark_nosave_pages(struct memory_bitmap *bm)
 				region->end_pfn << PAGE_SHIFT);
 
 		for (pfn = region->start_pfn; pfn < region->end_pfn; pfn++)
-			if (pfn_valid(pfn))
-				memory_bm_set_bit(bm, pfn);
+			if (pfn_valid(pfn)) {
+				/*
+				 * It is safe to ignore the result of
+				 * mem_bm_set_bit_check() here, since we won't
+				 * touch the PFNs for which the error is
+				 * returned anyway.
+				 */
+				mem_bm_set_bit_check(bm, pfn);
+			}
 	}
 }
 
diff --git a/kernel/printk.c b/kernel/printk.c
index bee36100f110..9adc2a473e6e 100644
--- a/kernel/printk.c
+++ b/kernel/printk.c
@@ -666,7 +666,7 @@ asmlinkage int vprintk(const char *fmt, va_list args)
 	}
 	/* Emit the output into the temporary buffer */
 	printed_len += vscnprintf(printk_buf + printed_len,
-				  sizeof(printk_buf), fmt, args);
+				  sizeof(printk_buf) - printed_len, fmt, args);
 
 	/*
 	 * Copy the output into log_buf.  If the caller didn't provide
diff --git a/kernel/rcupreempt.c b/kernel/rcupreempt.c
index 987cfb7ade89..e9517014b57c 100644
--- a/kernel/rcupreempt.c
+++ b/kernel/rcupreempt.c
@@ -23,6 +23,10 @@
  *		to Suparna Bhattacharya for pushing me completely away
  *		from atomic instructions on the read side.
  *
+ *  - Added handling of Dynamic Ticks
+ *      Copyright 2007 - Paul E. Mckenney <paulmck@us.ibm.com>
+ *                     - Steven Rostedt <srostedt@redhat.com>
+ *
  * Papers:  http://www.rdrop.com/users/paulmck/RCU
  *
  * Design Document: http://lwn.net/Articles/253651/
@@ -409,6 +413,212 @@ static void __rcu_advance_callbacks(struct rcu_data *rdp)
 	}
 }
 
+#ifdef CONFIG_NO_HZ
+
+DEFINE_PER_CPU(long, dynticks_progress_counter) = 1;
+static DEFINE_PER_CPU(long, rcu_dyntick_snapshot);
+static DEFINE_PER_CPU(int, rcu_update_flag);
+
+/**
+ * rcu_irq_enter - Called from Hard irq handlers and NMI/SMI.
+ *
+ * If the CPU was idle with dynamic ticks active, this updates the
+ * dynticks_progress_counter to let the RCU handling know that the
+ * CPU is active.
+ */
+void rcu_irq_enter(void)
+{
+	int cpu = smp_processor_id();
+
+	if (per_cpu(rcu_update_flag, cpu))
+		per_cpu(rcu_update_flag, cpu)++;
+
+	/*
+	 * Only update if we are coming from a stopped ticks mode
+	 * (dynticks_progress_counter is even).
+	 */
+	if (!in_interrupt() &&
+	    (per_cpu(dynticks_progress_counter, cpu) & 0x1) == 0) {
+		/*
+		 * The following might seem like we could have a race
+		 * with NMI/SMIs. But this really isn't a problem.
+		 * Here we do a read/modify/write, and the race happens
+		 * when an NMI/SMI comes in after the read and before
+		 * the write. But NMI/SMIs will increment this counter
+		 * twice before returning, so the zero bit will not
+		 * be corrupted by the NMI/SMI which is the most important
+		 * part.
+		 *
+		 * The only thing is that we would bring back the counter
+		 * to a postion that it was in during the NMI/SMI.
+		 * But the zero bit would be set, so the rest of the
+		 * counter would again be ignored.
+		 *
+		 * On return from the IRQ, the counter may have the zero
+		 * bit be 0 and the counter the same as the return from
+		 * the NMI/SMI. If the state machine was so unlucky to
+		 * see that, it still doesn't matter, since all
+		 * RCU read-side critical sections on this CPU would
+		 * have already completed.
+		 */
+		per_cpu(dynticks_progress_counter, cpu)++;
+		/*
+		 * The following memory barrier ensures that any
+		 * rcu_read_lock() primitives in the irq handler
+		 * are seen by other CPUs to follow the above
+		 * increment to dynticks_progress_counter. This is
+		 * required in order for other CPUs to correctly
+		 * determine when it is safe to advance the RCU
+		 * grace-period state machine.
+		 */
+		smp_mb(); /* see above block comment. */
+		/*
+		 * Since we can't determine the dynamic tick mode from
+		 * the dynticks_progress_counter after this routine,
+		 * we use a second flag to acknowledge that we came
+		 * from an idle state with ticks stopped.
+		 */
+		per_cpu(rcu_update_flag, cpu)++;
+		/*
+		 * If we take an NMI/SMI now, they will also increment
+		 * the rcu_update_flag, and will not update the
+		 * dynticks_progress_counter on exit. That is for
+		 * this IRQ to do.
+		 */
+	}
+}
+
+/**
+ * rcu_irq_exit - Called from exiting Hard irq context.
+ *
+ * If the CPU was idle with dynamic ticks active, update the
+ * dynticks_progress_counter to put let the RCU handling be
+ * aware that the CPU is going back to idle with no ticks.
+ */
+void rcu_irq_exit(void)
+{
+	int cpu = smp_processor_id();
+
+	/*
+	 * rcu_update_flag is set if we interrupted the CPU
+	 * when it was idle with ticks stopped.
+	 * Once this occurs, we keep track of interrupt nesting
+	 * because a NMI/SMI could also come in, and we still
+	 * only want the IRQ that started the increment of the
+	 * dynticks_progress_counter to be the one that modifies
+	 * it on exit.
+	 */
+	if (per_cpu(rcu_update_flag, cpu)) {
+		if (--per_cpu(rcu_update_flag, cpu))
+			return;
+
+		/* This must match the interrupt nesting */
+		WARN_ON(in_interrupt());
+
+		/*
+		 * If an NMI/SMI happens now we are still
+		 * protected by the dynticks_progress_counter being odd.
+		 */
+
+		/*
+		 * The following memory barrier ensures that any
+		 * rcu_read_unlock() primitives in the irq handler
+		 * are seen by other CPUs to preceed the following
+		 * increment to dynticks_progress_counter. This
+		 * is required in order for other CPUs to determine
+		 * when it is safe to advance the RCU grace-period
+		 * state machine.
+		 */
+		smp_mb(); /* see above block comment. */
+		per_cpu(dynticks_progress_counter, cpu)++;
+		WARN_ON(per_cpu(dynticks_progress_counter, cpu) & 0x1);
+	}
+}
+
+static void dyntick_save_progress_counter(int cpu)
+{
+	per_cpu(rcu_dyntick_snapshot, cpu) =
+		per_cpu(dynticks_progress_counter, cpu);
+}
+
+static inline int
+rcu_try_flip_waitack_needed(int cpu)
+{
+	long curr;
+	long snap;
+
+	curr = per_cpu(dynticks_progress_counter, cpu);
+	snap = per_cpu(rcu_dyntick_snapshot, cpu);
+	smp_mb(); /* force ordering with cpu entering/leaving dynticks. */
+
+	/*
+	 * If the CPU remained in dynticks mode for the entire time
+	 * and didn't take any interrupts, NMIs, SMIs, or whatever,
+	 * then it cannot be in the middle of an rcu_read_lock(), so
+	 * the next rcu_read_lock() it executes must use the new value
+	 * of the counter.  So we can safely pretend that this CPU
+	 * already acknowledged the counter.
+	 */
+
+	if ((curr == snap) && ((curr & 0x1) == 0))
+		return 0;
+
+	/*
+	 * If the CPU passed through or entered a dynticks idle phase with
+	 * no active irq handlers, then, as above, we can safely pretend
+	 * that this CPU already acknowledged the counter.
+	 */
+
+	if ((curr - snap) > 2 || (snap & 0x1) == 0)
+		return 0;
+
+	/* We need this CPU to explicitly acknowledge the counter flip. */
+
+	return 1;
+}
+
+static inline int
+rcu_try_flip_waitmb_needed(int cpu)
+{
+	long curr;
+	long snap;
+
+	curr = per_cpu(dynticks_progress_counter, cpu);
+	snap = per_cpu(rcu_dyntick_snapshot, cpu);
+	smp_mb(); /* force ordering with cpu entering/leaving dynticks. */
+
+	/*
+	 * If the CPU remained in dynticks mode for the entire time
+	 * and didn't take any interrupts, NMIs, SMIs, or whatever,
+	 * then it cannot have executed an RCU read-side critical section
+	 * during that time, so there is no need for it to execute a
+	 * memory barrier.
+	 */
+
+	if ((curr == snap) && ((curr & 0x1) == 0))
+		return 0;
+
+	/*
+	 * If the CPU either entered or exited an outermost interrupt,
+	 * SMI, NMI, or whatever handler, then we know that it executed
+	 * a memory barrier when doing so.  So we don't need another one.
+	 */
+	if (curr != snap)
+		return 0;
+
+	/* We need the CPU to execute a memory barrier. */
+
+	return 1;
+}
+
+#else /* !CONFIG_NO_HZ */
+
+# define dyntick_save_progress_counter(cpu)	do { } while (0)
+# define rcu_try_flip_waitack_needed(cpu)	(1)
+# define rcu_try_flip_waitmb_needed(cpu)	(1)
+
+#endif /* CONFIG_NO_HZ */
+
 /*
  * Get here when RCU is idle.  Decide whether we need to
  * move out of idle state, and return non-zero if so.
@@ -447,8 +657,10 @@ rcu_try_flip_idle(void)
 
 	/* Now ask each CPU for acknowledgement of the flip. */
 
-	for_each_cpu_mask(cpu, rcu_cpu_online_map)
+	for_each_cpu_mask(cpu, rcu_cpu_online_map) {
 		per_cpu(rcu_flip_flag, cpu) = rcu_flipped;
+		dyntick_save_progress_counter(cpu);
+	}
 
 	return 1;
 }
@@ -464,7 +676,8 @@ rcu_try_flip_waitack(void)
 
 	RCU_TRACE_ME(rcupreempt_trace_try_flip_a1);
 	for_each_cpu_mask(cpu, rcu_cpu_online_map)
-		if (per_cpu(rcu_flip_flag, cpu) != rcu_flip_seen) {
+		if (rcu_try_flip_waitack_needed(cpu) &&
+		    per_cpu(rcu_flip_flag, cpu) != rcu_flip_seen) {
 			RCU_TRACE_ME(rcupreempt_trace_try_flip_ae1);
 			return 0;
 		}
@@ -509,8 +722,10 @@ rcu_try_flip_waitzero(void)
 	smp_mb();  /*  ^^^^^^^^^^^^ */
 
 	/* Call for a memory barrier from each CPU. */
-	for_each_cpu_mask(cpu, rcu_cpu_online_map)
+	for_each_cpu_mask(cpu, rcu_cpu_online_map) {
 		per_cpu(rcu_mb_flag, cpu) = rcu_mb_needed;
+		dyntick_save_progress_counter(cpu);
+	}
 
 	RCU_TRACE_ME(rcupreempt_trace_try_flip_z2);
 	return 1;
@@ -528,7 +743,8 @@ rcu_try_flip_waitmb(void)
 
 	RCU_TRACE_ME(rcupreempt_trace_try_flip_m1);
 	for_each_cpu_mask(cpu, rcu_cpu_online_map)
-		if (per_cpu(rcu_mb_flag, cpu) != rcu_mb_done) {
+		if (rcu_try_flip_waitmb_needed(cpu) &&
+		    per_cpu(rcu_mb_flag, cpu) != rcu_mb_done) {
 			RCU_TRACE_ME(rcupreempt_trace_try_flip_me1);
 			return 0;
 		}
@@ -702,8 +918,9 @@ void rcu_offline_cpu(int cpu)
 	 * fix.
 	 */
 
+	local_irq_save(flags);
 	rdp = RCU_DATA_ME();
-	spin_lock_irqsave(&rdp->lock, flags);
+	spin_lock(&rdp->lock);
 	*rdp->nexttail = list;
 	if (list)
 		rdp->nexttail = tail;
@@ -735,9 +952,11 @@ static void rcu_process_callbacks(struct softirq_action *unused)
 {
 	unsigned long flags;
 	struct rcu_head *next, *list;
-	struct rcu_data *rdp = RCU_DATA_ME();
+	struct rcu_data *rdp;
 
-	spin_lock_irqsave(&rdp->lock, flags);
+	local_irq_save(flags);
+	rdp = RCU_DATA_ME();
+	spin_lock(&rdp->lock);
 	list = rdp->donelist;
 	if (list == NULL) {
 		spin_unlock_irqrestore(&rdp->lock, flags);
diff --git a/kernel/res_counter.c b/kernel/res_counter.c
index 16cbec2d5d60..efbfc0fc232f 100644
--- a/kernel/res_counter.c
+++ b/kernel/res_counter.c
@@ -113,6 +113,7 @@ ssize_t res_counter_write(struct res_counter *counter, int member,
 
 	ret = -EINVAL;
 
+	strstrip(buf);
 	if (write_strategy) {
 		if (write_strategy(buf, &tmp)) {
 			goto out_free;
diff --git a/kernel/sched.c b/kernel/sched.c
index b387a8de26a5..d1ad69b270ca 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -174,41 +174,6 @@ struct task_group {
 	struct sched_entity **se;
 	/* runqueue "owned" by this group on each cpu */
 	struct cfs_rq **cfs_rq;
-
-	/*
-	 * shares assigned to a task group governs how much of cpu bandwidth
-	 * is allocated to the group. The more shares a group has, the more is
-	 * the cpu bandwidth allocated to it.
-	 *
-	 * For ex, lets say that there are three task groups, A, B and C which
-	 * have been assigned shares 1000, 2000 and 3000 respectively. Then,
-	 * cpu bandwidth allocated by the scheduler to task groups A, B and C
-	 * should be:
-	 *
-	 *	Bw(A) = 1000/(1000+2000+3000) * 100 = 16.66%
-	 *	Bw(B) = 2000/(1000+2000+3000) * 100 = 33.33%
-	 *	Bw(C) = 3000/(1000+2000+3000) * 100 = 50%
-	 *
-	 * The weight assigned to a task group's schedulable entities on every
-	 * cpu (task_group.se[a_cpu]->load.weight) is derived from the task
-	 * group's shares. For ex: lets say that task group A has been
-	 * assigned shares of 1000 and there are two CPUs in a system. Then,
-	 *
-	 *  tg_A->se[0]->load.weight = tg_A->se[1]->load.weight = 1000;
-	 *
-	 * Note: It's not necessary that each of a task's group schedulable
-	 *	 entity have the same weight on all CPUs. If the group
-	 *	 has 2 of its tasks on CPU0 and 1 task on CPU1, then a
-	 *	 better distribution of weight could be:
-	 *
-	 *	tg_A->se[0]->load.weight = 2/3 * 2000 = 1333
-	 *	tg_A->se[1]->load.weight = 1/2 * 2000 =  667
-	 *
-	 * rebalance_shares() is responsible for distributing the shares of a
-	 * task groups like this among the group's schedulable entities across
-	 * cpus.
-	 *
-	 */
 	unsigned long shares;
 #endif
 
@@ -250,22 +215,12 @@ static DEFINE_SPINLOCK(task_group_lock);
 static DEFINE_MUTEX(doms_cur_mutex);
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
-#ifdef CONFIG_SMP
-/* kernel thread that runs rebalance_shares() periodically */
-static struct task_struct *lb_monitor_task;
-static int load_balance_monitor(void *unused);
-#endif
-
-static void set_se_shares(struct sched_entity *se, unsigned long shares);
-
 #ifdef CONFIG_USER_SCHED
 # define INIT_TASK_GROUP_LOAD	(2*NICE_0_LOAD)
 #else
 # define INIT_TASK_GROUP_LOAD	NICE_0_LOAD
 #endif
 
-#define MIN_GROUP_SHARES	2
-
 static int init_task_group_load = INIT_TASK_GROUP_LOAD;
 #endif
 
@@ -346,7 +301,7 @@ struct cfs_rq {
 	/* 'curr' points to currently running entity on this cfs_rq.
 	 * It is set to NULL otherwise (i.e when none are currently running).
 	 */
-	struct sched_entity *curr;
+	struct sched_entity *curr, *next;
 
 	unsigned long nr_spread_over;
 
@@ -668,6 +623,8 @@ const_debug unsigned int sysctl_sched_nr_migrate = 32;
  */
 unsigned int sysctl_sched_rt_period = 1000000;
 
+static __read_mostly int scheduler_running;
+
 /*
  * part of the period that we allow rt tasks to run in us.
  * default: 0.95s
@@ -689,14 +646,16 @@ unsigned long long cpu_clock(int cpu)
 	unsigned long flags;
 	struct rq *rq;
 
-	local_irq_save(flags);
-	rq = cpu_rq(cpu);
 	/*
 	 * Only call sched_clock() if the scheduler has already been
 	 * initialized (some code might call cpu_clock() very early):
 	 */
-	if (rq->idle)
-		update_rq_clock(rq);
+	if (unlikely(!scheduler_running))
+		return 0;
+
+	local_irq_save(flags);
+	rq = cpu_rq(cpu);
+	update_rq_clock(rq);
 	now = rq->clock;
 	local_irq_restore(flags);
 
@@ -1125,7 +1084,7 @@ calc_delta_mine(unsigned long delta_exec, unsigned long weight,
 	u64 tmp;
 
 	if (unlikely(!lw->inv_weight))
-		lw->inv_weight = (WMULT_CONST - lw->weight/2) / lw->weight + 1;
+		lw->inv_weight = (WMULT_CONST-lw->weight/2) / (lw->weight+1);
 
 	tmp = (u64)delta_exec * weight;
 	/*
@@ -1149,11 +1108,13 @@ calc_delta_fair(unsigned long delta_exec, struct load_weight *lw)
 static inline void update_load_add(struct load_weight *lw, unsigned long inc)
 {
 	lw->weight += inc;
+	lw->inv_weight = 0;
 }
 
 static inline void update_load_sub(struct load_weight *lw, unsigned long dec)
 {
 	lw->weight -= dec;
+	lw->inv_weight = 0;
 }
 
 /*
@@ -1241,16 +1202,6 @@ static void cpuacct_charge(struct task_struct *tsk, u64 cputime);
 static inline void cpuacct_charge(struct task_struct *tsk, u64 cputime) {}
 #endif
 
-static inline void inc_cpu_load(struct rq *rq, unsigned long load)
-{
-	update_load_add(&rq->load, load);
-}
-
-static inline void dec_cpu_load(struct rq *rq, unsigned long load)
-{
-	update_load_sub(&rq->load, load);
-}
-
 #ifdef CONFIG_SMP
 static unsigned long source_load(int cpu, int type);
 static unsigned long target_load(int cpu, int type);
@@ -1268,14 +1219,26 @@ static int task_hot(struct task_struct *p, u64 now, struct sched_domain *sd);
 
 #define sched_class_highest (&rt_sched_class)
 
-static void inc_nr_running(struct rq *rq)
+static inline void inc_load(struct rq *rq, const struct task_struct *p)
+{
+	update_load_add(&rq->load, p->se.load.weight);
+}
+
+static inline void dec_load(struct rq *rq, const struct task_struct *p)
+{
+	update_load_sub(&rq->load, p->se.load.weight);
+}
+
+static void inc_nr_running(struct task_struct *p, struct rq *rq)
 {
 	rq->nr_running++;
+	inc_load(rq, p);
 }
 
-static void dec_nr_running(struct rq *rq)
+static void dec_nr_running(struct task_struct *p, struct rq *rq)
 {
 	rq->nr_running--;
+	dec_load(rq, p);
 }
 
 static void set_load_weight(struct task_struct *p)
@@ -1367,7 +1330,7 @@ static void activate_task(struct rq *rq, struct task_struct *p, int wakeup)
 		rq->nr_uninterruptible--;
 
 	enqueue_task(rq, p, wakeup);
-	inc_nr_running(rq);
+	inc_nr_running(p, rq);
 }
 
 /*
@@ -1379,7 +1342,7 @@ static void deactivate_task(struct rq *rq, struct task_struct *p, int sleep)
 		rq->nr_uninterruptible++;
 
 	dequeue_task(rq, p, sleep);
-	dec_nr_running(rq);
+	dec_nr_running(p, rq);
 }
 
 /**
@@ -2019,7 +1982,7 @@ void wake_up_new_task(struct task_struct *p, unsigned long clone_flags)
 		 * management (if any):
 		 */
 		p->sched_class->task_new(rq, p);
-		inc_nr_running(rq);
+		inc_nr_running(p, rq);
 	}
 	check_preempt_curr(rq, p);
 #ifdef CONFIG_SMP
@@ -3885,7 +3848,7 @@ pick_next_task(struct rq *rq, struct task_struct *prev)
 asmlinkage void __sched schedule(void)
 {
 	struct task_struct *prev, *next;
-	long *switch_count;
+	unsigned long *switch_count;
 	struct rq *rq;
 	int cpu;
 
@@ -4307,11 +4270,10 @@ void rt_mutex_setprio(struct task_struct *p, int prio)
 	oldprio = p->prio;
 	on_rq = p->se.on_rq;
 	running = task_current(rq, p);
-	if (on_rq) {
+	if (on_rq)
 		dequeue_task(rq, p, 0);
-		if (running)
-			p->sched_class->put_prev_task(rq, p);
-	}
+	if (running)
+		p->sched_class->put_prev_task(rq, p);
 
 	if (rt_prio(prio))
 		p->sched_class = &rt_sched_class;
@@ -4320,10 +4282,9 @@ void rt_mutex_setprio(struct task_struct *p, int prio)
 
 	p->prio = prio;
 
+	if (running)
+		p->sched_class->set_curr_task(rq);
 	if (on_rq) {
-		if (running)
-			p->sched_class->set_curr_task(rq);
-
 		enqueue_task(rq, p, 0);
 
 		check_class_changed(rq, p, prev_class, oldprio, running);
@@ -4358,8 +4319,10 @@ void set_user_nice(struct task_struct *p, long nice)
 		goto out_unlock;
 	}
 	on_rq = p->se.on_rq;
-	if (on_rq)
+	if (on_rq) {
 		dequeue_task(rq, p, 0);
+		dec_load(rq, p);
+	}
 
 	p->static_prio = NICE_TO_PRIO(nice);
 	set_load_weight(p);
@@ -4369,6 +4332,7 @@ void set_user_nice(struct task_struct *p, long nice)
 
 	if (on_rq) {
 		enqueue_task(rq, p, 0);
+		inc_load(rq, p);
 		/*
 		 * If the task increased its priority or is running and
 		 * lowered its priority, then reschedule its CPU:
@@ -4458,7 +4422,7 @@ int task_nice(const struct task_struct *p)
 {
 	return TASK_NICE(p);
 }
-EXPORT_SYMBOL_GPL(task_nice);
+EXPORT_SYMBOL(task_nice);
 
 /**
  * idle_cpu - is a given cpu idle currently?
@@ -4617,19 +4581,17 @@ recheck:
 	update_rq_clock(rq);
 	on_rq = p->se.on_rq;
 	running = task_current(rq, p);
-	if (on_rq) {
+	if (on_rq)
 		deactivate_task(rq, p, 0);
-		if (running)
-			p->sched_class->put_prev_task(rq, p);
-	}
+	if (running)
+		p->sched_class->put_prev_task(rq, p);
 
 	oldprio = p->prio;
 	__setscheduler(rq, p, policy, param->sched_priority);
 
+	if (running)
+		p->sched_class->set_curr_task(rq);
 	if (on_rq) {
-		if (running)
-			p->sched_class->set_curr_task(rq);
-
 		activate_task(rq, p, 0);
 
 		check_class_changed(rq, p, prev_class, oldprio, running);
@@ -5136,7 +5098,7 @@ long sys_sched_rr_get_interval(pid_t pid, struct timespec __user *interval)
 	time_slice = 0;
 	if (p->policy == SCHED_RR) {
 		time_slice = DEF_TIMESLICE;
-	} else {
+	} else if (p->policy != SCHED_FIFO) {
 		struct sched_entity *se = &p->se;
 		unsigned long flags;
 		struct rq *rq;
@@ -5917,7 +5879,8 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu)
 		spin_unlock_irq(&rq->lock);
 		break;
 
-	case CPU_DOWN_PREPARE:
+	case CPU_DYING:
+	case CPU_DYING_FROZEN:
 		/* Update our root-domain */
 		rq = cpu_rq(cpu);
 		spin_lock_irqsave(&rq->lock, flags);
@@ -7083,21 +7046,6 @@ void __init sched_init_smp(void)
 	if (set_cpus_allowed(current, non_isolated_cpus) < 0)
 		BUG();
 	sched_init_granularity();
-
-#ifdef CONFIG_FAIR_GROUP_SCHED
-	if (nr_cpu_ids == 1)
-		return;
-
-	lb_monitor_task = kthread_create(load_balance_monitor, NULL,
-					 "group_balance");
-	if (!IS_ERR(lb_monitor_task)) {
-		lb_monitor_task->flags |= PF_NOFREEZE;
-		wake_up_process(lb_monitor_task);
-	} else {
-		printk(KERN_ERR "Could not create load balance monitor thread"
-			"(error = %ld) \n", PTR_ERR(lb_monitor_task));
-	}
-#endif
 }
 #else
 void __init sched_init_smp(void)
@@ -7284,6 +7232,8 @@ void __init sched_init(void)
 	 * During early bootup we pretend to be a normal task:
 	 */
 	current->sched_class = &fair_sched_class;
+
+	scheduler_running = 1;
 }
 
 #ifdef CONFIG_DEBUG_SPINLOCK_SLEEP
@@ -7418,157 +7368,6 @@ void set_curr_task(int cpu, struct task_struct *p)
 
 #ifdef CONFIG_GROUP_SCHED
 
-#if defined CONFIG_FAIR_GROUP_SCHED && defined CONFIG_SMP
-/*
- * distribute shares of all task groups among their schedulable entities,
- * to reflect load distribution across cpus.
- */
-static int rebalance_shares(struct sched_domain *sd, int this_cpu)
-{
-	struct cfs_rq *cfs_rq;
-	struct rq *rq = cpu_rq(this_cpu);
-	cpumask_t sdspan = sd->span;
-	int balanced = 1;
-
-	/* Walk thr' all the task groups that we have */
-	for_each_leaf_cfs_rq(rq, cfs_rq) {
-		int i;
-		unsigned long total_load = 0, total_shares;
-		struct task_group *tg = cfs_rq->tg;
-
-		/* Gather total task load of this group across cpus */
-		for_each_cpu_mask(i, sdspan)
-			total_load += tg->cfs_rq[i]->load.weight;
-
-		/* Nothing to do if this group has no load */
-		if (!total_load)
-			continue;
-
-		/*
-		 * tg->shares represents the number of cpu shares the task group
-		 * is eligible to hold on a single cpu. On N cpus, it is
-		 * eligible to hold (N * tg->shares) number of cpu shares.
-		 */
-		total_shares = tg->shares * cpus_weight(sdspan);
-
-		/*
-		 * redistribute total_shares across cpus as per the task load
-		 * distribution.
-		 */
-		for_each_cpu_mask(i, sdspan) {
-			unsigned long local_load, local_shares;
-
-			local_load = tg->cfs_rq[i]->load.weight;
-			local_shares = (local_load * total_shares) / total_load;
-			if (!local_shares)
-				local_shares = MIN_GROUP_SHARES;
-			if (local_shares == tg->se[i]->load.weight)
-				continue;
-
-			spin_lock_irq(&cpu_rq(i)->lock);
-			set_se_shares(tg->se[i], local_shares);
-			spin_unlock_irq(&cpu_rq(i)->lock);
-			balanced = 0;
-		}
-	}
-
-	return balanced;
-}
-
-/*
- * How frequently should we rebalance_shares() across cpus?
- *
- * The more frequently we rebalance shares, the more accurate is the fairness
- * of cpu bandwidth distribution between task groups. However higher frequency
- * also implies increased scheduling overhead.
- *
- * sysctl_sched_min_bal_int_shares represents the minimum interval between
- * consecutive calls to rebalance_shares() in the same sched domain.
- *
- * sysctl_sched_max_bal_int_shares represents the maximum interval between
- * consecutive calls to rebalance_shares() in the same sched domain.
- *
- * These settings allows for the appropriate trade-off between accuracy of
- * fairness and the associated overhead.
- *
- */
-
-/* default: 8ms, units: milliseconds */
-const_debug unsigned int sysctl_sched_min_bal_int_shares = 8;
-
-/* default: 128ms, units: milliseconds */
-const_debug unsigned int sysctl_sched_max_bal_int_shares = 128;
-
-/* kernel thread that runs rebalance_shares() periodically */
-static int load_balance_monitor(void *unused)
-{
-	unsigned int timeout = sysctl_sched_min_bal_int_shares;
-	struct sched_param schedparm;
-	int ret;
-
-	/*
-	 * We don't want this thread's execution to be limited by the shares
-	 * assigned to default group (init_task_group). Hence make it run
-	 * as a SCHED_RR RT task at the lowest priority.
-	 */
-	schedparm.sched_priority = 1;
-	ret = sched_setscheduler(current, SCHED_RR, &schedparm);
-	if (ret)
-		printk(KERN_ERR "Couldn't set SCHED_RR policy for load balance"
-				" monitor thread (error = %d) \n", ret);
-
-	while (!kthread_should_stop()) {
-		int i, cpu, balanced = 1;
-
-		/* Prevent cpus going down or coming up */
-		get_online_cpus();
-		/* lockout changes to doms_cur[] array */
-		lock_doms_cur();
-		/*
-		 * Enter a rcu read-side critical section to safely walk rq->sd
-		 * chain on various cpus and to walk task group list
-		 * (rq->leaf_cfs_rq_list) in rebalance_shares().
-		 */
-		rcu_read_lock();
-
-		for (i = 0; i < ndoms_cur; i++) {
-			cpumask_t cpumap = doms_cur[i];
-			struct sched_domain *sd = NULL, *sd_prev = NULL;
-
-			cpu = first_cpu(cpumap);
-
-			/* Find the highest domain at which to balance shares */
-			for_each_domain(cpu, sd) {
-				if (!(sd->flags & SD_LOAD_BALANCE))
-					continue;
-				sd_prev = sd;
-			}
-
-			sd = sd_prev;
-			/* sd == NULL? No load balance reqd in this domain */
-			if (!sd)
-				continue;
-
-			balanced &= rebalance_shares(sd, cpu);
-		}
-
-		rcu_read_unlock();
-
-		unlock_doms_cur();
-		put_online_cpus();
-
-		if (!balanced)
-			timeout = sysctl_sched_min_bal_int_shares;
-		else if (timeout < sysctl_sched_max_bal_int_shares)
-			timeout *= 2;
-
-		msleep_interruptible(timeout);
-	}
-
-	return 0;
-}
-#endif	/* CONFIG_SMP */
-
 #ifdef CONFIG_FAIR_GROUP_SCHED
 static void free_fair_sched_group(struct task_group *tg)
 {
@@ -7817,47 +7616,46 @@ void sched_move_task(struct task_struct *tsk)
 	running = task_current(rq, tsk);
 	on_rq = tsk->se.on_rq;
 
-	if (on_rq) {
+	if (on_rq)
 		dequeue_task(rq, tsk, 0);
-		if (unlikely(running))
-			tsk->sched_class->put_prev_task(rq, tsk);
-	}
+	if (unlikely(running))
+		tsk->sched_class->put_prev_task(rq, tsk);
 
 	set_task_rq(tsk, task_cpu(tsk));
 
-	if (on_rq) {
-		if (unlikely(running))
-			tsk->sched_class->set_curr_task(rq);
+#ifdef CONFIG_FAIR_GROUP_SCHED
+	if (tsk->sched_class->moved_group)
+		tsk->sched_class->moved_group(tsk);
+#endif
+
+	if (unlikely(running))
+		tsk->sched_class->set_curr_task(rq);
+	if (on_rq)
 		enqueue_task(rq, tsk, 0);
-	}
 
 	task_rq_unlock(rq, &flags);
 }
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
-/* rq->lock to be locked by caller */
 static void set_se_shares(struct sched_entity *se, unsigned long shares)
 {
 	struct cfs_rq *cfs_rq = se->cfs_rq;
 	struct rq *rq = cfs_rq->rq;
 	int on_rq;
 
-	if (!shares)
-		shares = MIN_GROUP_SHARES;
+	spin_lock_irq(&rq->lock);
 
 	on_rq = se->on_rq;
-	if (on_rq) {
+	if (on_rq)
 		dequeue_entity(cfs_rq, se, 0);
-		dec_cpu_load(rq, se->load.weight);
-	}
 
 	se->load.weight = shares;
 	se->load.inv_weight = div64_64((1ULL<<32), shares);
 
-	if (on_rq) {
+	if (on_rq)
 		enqueue_entity(cfs_rq, se, 0);
-		inc_cpu_load(rq, se->load.weight);
-	}
+
+	spin_unlock_irq(&rq->lock);
 }
 
 static DEFINE_MUTEX(shares_mutex);
@@ -7867,18 +7665,18 @@ int sched_group_set_shares(struct task_group *tg, unsigned long shares)
 	int i;
 	unsigned long flags;
 
+	/*
+	 * A weight of 0 or 1 can cause arithmetics problems.
+	 * (The default weight is 1024 - so there's no practical
+	 *  limitation from this.)
+	 */
+	if (shares < 2)
+		shares = 2;
+
 	mutex_lock(&shares_mutex);
 	if (tg->shares == shares)
 		goto done;
 
-	if (shares < MIN_GROUP_SHARES)
-		shares = MIN_GROUP_SHARES;
-
-	/*
-	 * Prevent any load balance activity (rebalance_shares,
-	 * load_balance_fair) from referring to this group first,
-	 * by taking it off the rq->leaf_cfs_rq_list on each cpu.
-	 */
 	spin_lock_irqsave(&task_group_lock, flags);
 	for_each_possible_cpu(i)
 		unregister_fair_sched_group(tg, i);
@@ -7892,11 +7690,8 @@ int sched_group_set_shares(struct task_group *tg, unsigned long shares)
 	 * w/o tripping rebalance_share or load_balance_fair.
 	 */
 	tg->shares = shares;
-	for_each_possible_cpu(i) {
-		spin_lock_irq(&cpu_rq(i)->lock);
+	for_each_possible_cpu(i)
 		set_se_shares(tg->se[i], shares);
-		spin_unlock_irq(&cpu_rq(i)->lock);
-	}
 
 	/*
 	 * Enable load balance activity on this group, by inserting it back on
@@ -7928,9 +7723,7 @@ static unsigned long to_ratio(u64 period, u64 runtime)
 	if (runtime == RUNTIME_INF)
 		return 1ULL << 16;
 
-	runtime *= (1ULL << 16);
-	div64_64(runtime, period);
-	return runtime;
+	return div64_64(runtime << 16, period);
 }
 
 static int __rt_schedulable(struct task_group *tg, u64 period, u64 runtime)
@@ -7954,25 +7747,40 @@ static int __rt_schedulable(struct task_group *tg, u64 period, u64 runtime)
 	return total + to_ratio(period, runtime) < global_ratio;
 }
 
+/* Must be called with tasklist_lock held */
+static inline int tg_has_rt_tasks(struct task_group *tg)
+{
+	struct task_struct *g, *p;
+	do_each_thread(g, p) {
+		if (rt_task(p) && rt_rq_of_se(&p->rt)->tg == tg)
+			return 1;
+	} while_each_thread(g, p);
+	return 0;
+}
+
 int sched_group_set_rt_runtime(struct task_group *tg, long rt_runtime_us)
 {
 	u64 rt_runtime, rt_period;
 	int err = 0;
 
-	rt_period = sysctl_sched_rt_period * NSEC_PER_USEC;
+	rt_period = (u64)sysctl_sched_rt_period * NSEC_PER_USEC;
 	rt_runtime = (u64)rt_runtime_us * NSEC_PER_USEC;
 	if (rt_runtime_us == -1)
-		rt_runtime = rt_period;
+		rt_runtime = RUNTIME_INF;
 
 	mutex_lock(&rt_constraints_mutex);
+	read_lock(&tasklist_lock);
+	if (rt_runtime_us == 0 && tg_has_rt_tasks(tg)) {
+		err = -EBUSY;
+		goto unlock;
+	}
 	if (!__rt_schedulable(tg, rt_period, rt_runtime)) {
 		err = -EINVAL;
 		goto unlock;
 	}
-	if (rt_runtime_us == -1)
-		rt_runtime = RUNTIME_INF;
 	tg->rt_runtime = rt_runtime;
  unlock:
+	read_unlock(&tasklist_lock);
 	mutex_unlock(&rt_constraints_mutex);
 
 	return err;
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 6c091d6e159d..f2cc59080efa 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -175,8 +175,15 @@ static void __enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
 	 * Maintain a cache of leftmost tree entries (it is frequently
 	 * used):
 	 */
-	if (leftmost)
+	if (leftmost) {
 		cfs_rq->rb_leftmost = &se->run_node;
+		/*
+		 * maintain cfs_rq->min_vruntime to be a monotonic increasing
+		 * value tracking the leftmost vruntime in the tree.
+		 */
+		cfs_rq->min_vruntime =
+			max_vruntime(cfs_rq->min_vruntime, se->vruntime);
+	}
 
 	rb_link_node(&se->run_node, parent, link);
 	rb_insert_color(&se->run_node, &cfs_rq->tasks_timeline);
@@ -184,8 +191,24 @@ static void __enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
 
 static void __dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
-	if (cfs_rq->rb_leftmost == &se->run_node)
-		cfs_rq->rb_leftmost = rb_next(&se->run_node);
+	if (cfs_rq->rb_leftmost == &se->run_node) {
+		struct rb_node *next_node;
+		struct sched_entity *next;
+
+		next_node = rb_next(&se->run_node);
+		cfs_rq->rb_leftmost = next_node;
+
+		if (next_node) {
+			next = rb_entry(next_node,
+					struct sched_entity, run_node);
+			cfs_rq->min_vruntime =
+				max_vruntime(cfs_rq->min_vruntime,
+					     next->vruntime);
+		}
+	}
+
+	if (cfs_rq->next == se)
+		cfs_rq->next = NULL;
 
 	rb_erase(&se->run_node, &cfs_rq->tasks_timeline);
 }
@@ -202,17 +225,12 @@ static struct sched_entity *__pick_next_entity(struct cfs_rq *cfs_rq)
 
 static inline struct sched_entity *__pick_last_entity(struct cfs_rq *cfs_rq)
 {
-	struct rb_node **link = &cfs_rq->tasks_timeline.rb_node;
-	struct sched_entity *se = NULL;
-	struct rb_node *parent;
+	struct rb_node *last = rb_last(&cfs_rq->tasks_timeline);
 
-	while (*link) {
-		parent = *link;
-		se = rb_entry(parent, struct sched_entity, run_node);
-		link = &parent->rb_right;
-	}
+	if (!last)
+		return NULL;
 
-	return se;
+	return rb_entry(last, struct sched_entity, run_node);
 }
 
 /**************************************************************
@@ -265,12 +283,8 @@ static u64 __sched_period(unsigned long nr_running)
  */
 static u64 sched_slice(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
-	u64 slice = __sched_period(cfs_rq->nr_running);
-
-	slice *= se->load.weight;
-	do_div(slice, cfs_rq->load.weight);
-
-	return slice;
+	return calc_delta_mine(__sched_period(cfs_rq->nr_running),
+			       se->load.weight, &cfs_rq->load);
 }
 
 /*
@@ -308,7 +322,6 @@ __update_curr(struct cfs_rq *cfs_rq, struct sched_entity *curr,
 	      unsigned long delta_exec)
 {
 	unsigned long delta_exec_weighted;
-	u64 vruntime;
 
 	schedstat_set(curr->exec_max, max((u64)delta_exec, curr->exec_max));
 
@@ -320,19 +333,6 @@ __update_curr(struct cfs_rq *cfs_rq, struct sched_entity *curr,
 							&curr->load);
 	}
 	curr->vruntime += delta_exec_weighted;
-
-	/*
-	 * maintain cfs_rq->min_vruntime to be a monotonic increasing
-	 * value tracking the leftmost vruntime in the tree.
-	 */
-	if (first_fair(cfs_rq)) {
-		vruntime = min_vruntime(curr->vruntime,
-				__pick_next_entity(cfs_rq)->vruntime);
-	} else
-		vruntime = curr->vruntime;
-
-	cfs_rq->min_vruntime =
-		max_vruntime(cfs_rq->min_vruntime, vruntime);
 }
 
 static void update_curr(struct cfs_rq *cfs_rq)
@@ -498,7 +498,11 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial)
 {
 	u64 vruntime;
 
-	vruntime = cfs_rq->min_vruntime;
+	if (first_fair(cfs_rq)) {
+		vruntime = min_vruntime(cfs_rq->min_vruntime,
+				__pick_next_entity(cfs_rq)->vruntime);
+	} else
+		vruntime = cfs_rq->min_vruntime;
 
 	if (sched_feat(TREE_AVG)) {
 		struct sched_entity *last = __pick_last_entity(cfs_rq);
@@ -520,8 +524,10 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial)
 
 	if (!initial) {
 		/* sleeps upto a single latency don't count. */
-		if (sched_feat(NEW_FAIR_SLEEPERS))
-			vruntime -= sysctl_sched_latency;
+		if (sched_feat(NEW_FAIR_SLEEPERS)) {
+			vruntime -= calc_delta_fair(sysctl_sched_latency,
+						    &cfs_rq->load);
+		}
 
 		/* ensure we never gain time by being placed backwards. */
 		vruntime = max_vruntime(se->vruntime, vruntime);
@@ -621,12 +627,32 @@ set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
 	se->prev_sum_exec_runtime = se->sum_exec_runtime;
 }
 
+static struct sched_entity *
+pick_next(struct cfs_rq *cfs_rq, struct sched_entity *se)
+{
+	s64 diff, gran;
+
+	if (!cfs_rq->next)
+		return se;
+
+	diff = cfs_rq->next->vruntime - se->vruntime;
+	if (diff < 0)
+		return se;
+
+	gran = calc_delta_fair(sysctl_sched_wakeup_granularity, &cfs_rq->load);
+	if (diff > gran)
+		return se;
+
+	return cfs_rq->next;
+}
+
 static struct sched_entity *pick_next_entity(struct cfs_rq *cfs_rq)
 {
 	struct sched_entity *se = NULL;
 
 	if (first_fair(cfs_rq)) {
 		se = __pick_next_entity(cfs_rq);
+		se = pick_next(cfs_rq, se);
 		set_next_entity(cfs_rq, se);
 	}
 
@@ -732,8 +758,6 @@ static inline struct sched_entity *parent_entity(struct sched_entity *se)
 	return se->parent;
 }
 
-#define GROUP_IMBALANCE_PCT	20
-
 #else	/* CONFIG_FAIR_GROUP_SCHED */
 
 #define for_each_sched_entity(se) \
@@ -824,26 +848,15 @@ hrtick_start_fair(struct rq *rq, struct task_struct *p)
 static void enqueue_task_fair(struct rq *rq, struct task_struct *p, int wakeup)
 {
 	struct cfs_rq *cfs_rq;
-	struct sched_entity *se = &p->se,
-			    *topse = NULL;	/* Highest schedulable entity */
-	int incload = 1;
+	struct sched_entity *se = &p->se;
 
 	for_each_sched_entity(se) {
-		topse = se;
-		if (se->on_rq) {
-			incload = 0;
+		if (se->on_rq)
 			break;
-		}
 		cfs_rq = cfs_rq_of(se);
 		enqueue_entity(cfs_rq, se, wakeup);
 		wakeup = 1;
 	}
-	/* Increment cpu load if we just enqueued the first task of a group on
-	 * 'rq->cpu'. 'topse' represents the group to which task 'p' belongs
-	 * at the highest grouping level.
-	 */
-	if (incload)
-		inc_cpu_load(rq, topse->load.weight);
 
 	hrtick_start_fair(rq, rq->curr);
 }
@@ -856,28 +869,16 @@ static void enqueue_task_fair(struct rq *rq, struct task_struct *p, int wakeup)
 static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int sleep)
 {
 	struct cfs_rq *cfs_rq;
-	struct sched_entity *se = &p->se,
-			    *topse = NULL; 	/* Highest schedulable entity */
-	int decload = 1;
+	struct sched_entity *se = &p->se;
 
 	for_each_sched_entity(se) {
-		topse = se;
 		cfs_rq = cfs_rq_of(se);
 		dequeue_entity(cfs_rq, se, sleep);
 		/* Don't dequeue parent if it has other entities besides us */
-		if (cfs_rq->load.weight) {
-			if (parent_entity(se))
-				decload = 0;
+		if (cfs_rq->load.weight)
 			break;
-		}
 		sleep = 1;
 	}
-	/* Decrement cpu load if we just dequeued the last task of a group on
-	 * 'rq->cpu'. 'topse' represents the group to which task 'p' belongs
-	 * at the highest grouping level.
-	 */
-	if (decload)
-		dec_cpu_load(rq, topse->load.weight);
 
 	hrtick_start_fair(rq, rq->curr);
 }
@@ -1090,6 +1091,9 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p)
 		resched_task(curr);
 		return;
 	}
+
+	cfs_rq_of(pse)->next = pse;
+
 	/*
 	 * Batch tasks do not preempt (their preemption is driven by
 	 * the tick):
@@ -1191,6 +1195,25 @@ static struct task_struct *load_balance_next_fair(void *arg)
 	return __load_balance_iterator(cfs_rq, cfs_rq->rb_load_balance_curr);
 }
 
+#ifdef CONFIG_FAIR_GROUP_SCHED
+static int cfs_rq_best_prio(struct cfs_rq *cfs_rq)
+{
+	struct sched_entity *curr;
+	struct task_struct *p;
+
+	if (!cfs_rq->nr_running || !first_fair(cfs_rq))
+		return MAX_PRIO;
+
+	curr = cfs_rq->curr;
+	if (!curr)
+		curr = __pick_next_entity(cfs_rq);
+
+	p = task_of(curr);
+
+	return p->prio;
+}
+#endif
+
 static unsigned long
 load_balance_fair(struct rq *this_rq, int this_cpu, struct rq *busiest,
 		  unsigned long max_load_move,
@@ -1200,45 +1223,28 @@ load_balance_fair(struct rq *this_rq, int this_cpu, struct rq *busiest,
 	struct cfs_rq *busy_cfs_rq;
 	long rem_load_move = max_load_move;
 	struct rq_iterator cfs_rq_iterator;
-	unsigned long load_moved;
 
 	cfs_rq_iterator.start = load_balance_start_fair;
 	cfs_rq_iterator.next = load_balance_next_fair;
 
 	for_each_leaf_cfs_rq(busiest, busy_cfs_rq) {
 #ifdef CONFIG_FAIR_GROUP_SCHED
-		struct cfs_rq *this_cfs_rq = busy_cfs_rq->tg->cfs_rq[this_cpu];
-		unsigned long maxload, task_load, group_weight;
-		unsigned long thisload, per_task_load;
-		struct sched_entity *se = busy_cfs_rq->tg->se[busiest->cpu];
+		struct cfs_rq *this_cfs_rq;
+		long imbalance;
+		unsigned long maxload;
 
-		task_load = busy_cfs_rq->load.weight;
-		group_weight = se->load.weight;
+		this_cfs_rq = cpu_cfs_rq(busy_cfs_rq, this_cpu);
 
-		/*
-		 * 'group_weight' is contributed by tasks of total weight
-		 * 'task_load'. To move 'rem_load_move' worth of weight only,
-		 * we need to move a maximum task load of:
-		 *
-		 * 	maxload = (remload / group_weight) * task_load;
-		 */
-		maxload = (rem_load_move * task_load) / group_weight;
-
-		if (!maxload || !task_load)
+		imbalance = busy_cfs_rq->load.weight - this_cfs_rq->load.weight;
+		/* Don't pull if this_cfs_rq has more load than busy_cfs_rq */
+		if (imbalance <= 0)
 			continue;
 
-		per_task_load = task_load / busy_cfs_rq->nr_running;
-		/*
-		 * balance_tasks will try to forcibly move atleast one task if
-		 * possible (because of SCHED_LOAD_SCALE_FUZZ). Avoid that if
-		 * maxload is less than GROUP_IMBALANCE_FUZZ% the per_task_load.
-		 */
-		 if (100 * maxload < GROUP_IMBALANCE_PCT * per_task_load)
-			continue;
+		/* Don't pull more than imbalance/2 */
+		imbalance /= 2;
+		maxload = min(rem_load_move, imbalance);
 
-		/* Disable priority-based load balance */
-		*this_best_prio = 0;
-		thisload = this_cfs_rq->load.weight;
+		*this_best_prio = cfs_rq_best_prio(this_cfs_rq);
 #else
 # define maxload rem_load_move
 #endif
@@ -1247,33 +1253,11 @@ load_balance_fair(struct rq *this_rq, int this_cpu, struct rq *busiest,
 		 * load_balance_[start|next]_fair iterators
 		 */
 		cfs_rq_iterator.arg = busy_cfs_rq;
-		load_moved = balance_tasks(this_rq, this_cpu, busiest,
+		rem_load_move -= balance_tasks(this_rq, this_cpu, busiest,
 					       maxload, sd, idle, all_pinned,
 					       this_best_prio,
 					       &cfs_rq_iterator);
 
-#ifdef CONFIG_FAIR_GROUP_SCHED
-		/*
-		 * load_moved holds the task load that was moved. The
-		 * effective (group) weight moved would be:
-		 * 	load_moved_eff = load_moved/task_load * group_weight;
-		 */
-		load_moved = (group_weight * load_moved) / task_load;
-
-		/* Adjust shares on both cpus to reflect load_moved */
-		group_weight -= load_moved;
-		set_se_shares(se, group_weight);
-
-		se = busy_cfs_rq->tg->se[this_cpu];
-		if (!thisload)
-			group_weight = load_moved;
-		else
-			group_weight = se->load.weight + load_moved;
-		set_se_shares(se, group_weight);
-#endif
-
-		rem_load_move -= load_moved;
-
 		if (rem_load_move <= 0)
 			break;
 	}
@@ -1403,6 +1387,16 @@ static void set_curr_task_fair(struct rq *rq)
 		set_next_entity(cfs_rq_of(se), se);
 }
 
+#ifdef CONFIG_FAIR_GROUP_SCHED
+static void moved_group_fair(struct task_struct *p)
+{
+	struct cfs_rq *cfs_rq = task_cfs_rq(p);
+
+	update_curr(cfs_rq);
+	place_entity(cfs_rq, &p->se, 1);
+}
+#endif
+
 /*
  * All the scheduling class methods:
  */
@@ -1431,6 +1425,10 @@ static const struct sched_class fair_sched_class = {
 
 	.prio_changed		= prio_changed_fair,
 	.switched_to		= switched_to_fair,
+
+#ifdef CONFIG_FAIR_GROUP_SCHED
+	.moved_group		= moved_group_fair,
+#endif
 };
 
 #ifdef CONFIG_SCHED_DEBUG
diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c
index f54792b175b2..0a6d2e516420 100644
--- a/kernel/sched_rt.c
+++ b/kernel/sched_rt.c
@@ -393,8 +393,6 @@ static void enqueue_task_rt(struct rq *rq, struct task_struct *p, int wakeup)
 	 */
 	for_each_sched_rt_entity(rt_se)
 		enqueue_rt_entity(rt_se);
-
-	inc_cpu_load(rq, p->se.load.weight);
 }
 
 static void dequeue_task_rt(struct rq *rq, struct task_struct *p, int sleep)
@@ -414,8 +412,6 @@ static void dequeue_task_rt(struct rq *rq, struct task_struct *p, int sleep)
 		if (rt_rq && rt_rq->rt_nr_running)
 			enqueue_rt_entity(rt_se);
 	}
-
-	dec_cpu_load(rq, p->se.load.weight);
 }
 
 /*
@@ -1111,9 +1107,11 @@ static void prio_changed_rt(struct rq *rq, struct task_struct *p,
 			pull_rt_task(rq);
 		/*
 		 * If there's a higher priority task waiting to run
-		 * then reschedule.
+		 * then reschedule. Note, the above pull_rt_task
+		 * can release the rq lock and p could migrate.
+		 * Only reschedule if p is still on the same runqueue.
 		 */
-		if (p->prio > rq->rt.highest_prio)
+		if (p->prio > rq->rt.highest_prio && rq->curr == p)
 			resched_task(p);
 #else
 		/* For UP simply resched on drop of prio */
diff --git a/kernel/signal.c b/kernel/signal.c
index 84917fe507f7..6af1210092c3 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -1623,7 +1623,6 @@ static void ptrace_stop(int exit_code, int clear_code, siginfo_t *info)
 	/* Let the debugger run.  */
 	__set_current_state(TASK_TRACED);
 	spin_unlock_irq(&current->sighand->siglock);
-	try_to_freeze();
 	read_lock(&tasklist_lock);
 	if (!unlikely(killed) && may_ptrace_stop()) {
 		do_notify_parent_cldstop(current, CLD_TRAPPED);
@@ -1641,6 +1640,13 @@ static void ptrace_stop(int exit_code, int clear_code, siginfo_t *info)
 	}
 
 	/*
+	 * While in TASK_TRACED, we were considered "frozen enough".
+	 * Now that we woke up, it's crucial if we're supposed to be
+	 * frozen that we freeze now before running anything substantial.
+	 */
+	try_to_freeze();
+
+	/*
 	 * We are back.  Now reacquire the siglock before touching
 	 * last_siginfo, so that we are sure to have synchronized with
 	 * any signal-sending on another CPU that wants to examine it.
@@ -1757,9 +1763,15 @@ int get_signal_to_deliver(siginfo_t *info, struct k_sigaction *return_ka,
 	sigset_t *mask = &current->blocked;
 	int signr = 0;
 
+relock:
+	/*
+	 * We'll jump back here after any time we were stopped in TASK_STOPPED.
+	 * While in TASK_STOPPED, we were considered "frozen enough".
+	 * Now that we woke up, it's crucial if we're supposed to be
+	 * frozen that we freeze now before running anything substantial.
+	 */
 	try_to_freeze();
 
-relock:
 	spin_lock_irq(&current->sighand->siglock);
 	for (;;) {
 		struct k_sigaction *ka;
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 5b3aea5f471e..31e9f2a47928 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -313,6 +313,7 @@ void irq_exit(void)
 	/* Make sure that timer wheel updates are propagated */
 	if (!in_interrupt() && idle_cpu(smp_processor_id()) && !need_resched())
 		tick_nohz_stop_sched_tick();
+	rcu_irq_exit();
 #endif
 	preempt_enable_no_resched();
 }
diff --git a/kernel/softlockup.c b/kernel/softlockup.c
index 7c2da88db4ed..01b6522fd92b 100644
--- a/kernel/softlockup.c
+++ b/kernel/softlockup.c
@@ -216,26 +216,27 @@ static int watchdog(void *__bind_cpu)
 	/* initialize timestamp */
 	touch_softlockup_watchdog();
 
+	set_current_state(TASK_INTERRUPTIBLE);
 	/*
 	 * Run briefly once per second to reset the softlockup timestamp.
 	 * If this gets delayed for more than 60 seconds then the
 	 * debug-printout triggers in softlockup_tick().
 	 */
 	while (!kthread_should_stop()) {
-		set_current_state(TASK_INTERRUPTIBLE);
 		touch_softlockup_watchdog();
 		schedule();
 
 		if (kthread_should_stop())
 			break;
 
-		if (this_cpu != check_cpu)
-			continue;
-
-		if (sysctl_hung_task_timeout_secs)
-			check_hung_uninterruptible_tasks(this_cpu);
+		if (this_cpu == check_cpu) {
+			if (sysctl_hung_task_timeout_secs)
+				check_hung_uninterruptible_tasks(this_cpu);
+		}
 
+		set_current_state(TASK_INTERRUPTIBLE);
 	}
+	__set_current_state(TASK_RUNNING);
 
 	return 0;
 }
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 8b7e95411795..b2a2d6889bab 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -311,24 +311,6 @@ static struct ctl_table kern_table[] = {
 		.mode		= 0644,
 		.proc_handler	= &proc_dointvec,
 	},
-#if defined(CONFIG_FAIR_GROUP_SCHED) && defined(CONFIG_SMP)
-	{
-		.ctl_name       = CTL_UNNUMBERED,
-		.procname       = "sched_min_bal_int_shares",
-		.data           = &sysctl_sched_min_bal_int_shares,
-		.maxlen         = sizeof(unsigned int),
-		.mode           = 0644,
-		.proc_handler   = &proc_dointvec,
-	},
-	{
-		.ctl_name       = CTL_UNNUMBERED,
-		.procname       = "sched_max_bal_int_shares",
-		.data           = &sysctl_sched_max_bal_int_shares,
-		.maxlen         = sizeof(unsigned int),
-		.mode           = 0644,
-		.proc_handler   = &proc_dointvec,
-	},
-#endif
 #endif
 	{
 		.ctl_name	= CTL_UNNUMBERED,
diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c
index c88b5910e7ab..5fd9b9469770 100644
--- a/kernel/time/ntp.c
+++ b/kernel/time/ntp.c
@@ -42,12 +42,13 @@ long time_esterror = NTP_PHASE_LIMIT;	/* estimated error (us)		*/
 long time_freq;				/* frequency offset (scaled ppm)*/
 static long time_reftime;		/* time at last adjustment (s)	*/
 long time_adjust;
+static long ntp_tick_adj;
 
 static void ntp_update_frequency(void)
 {
 	u64 second_length = (u64)(tick_usec * NSEC_PER_USEC * USER_HZ)
 				<< TICK_LENGTH_SHIFT;
-	second_length += (s64)CLOCK_TICK_ADJUST << TICK_LENGTH_SHIFT;
+	second_length += (s64)ntp_tick_adj << TICK_LENGTH_SHIFT;
 	second_length += (s64)time_freq << (TICK_LENGTH_SHIFT - SHIFT_NSEC);
 
 	tick_length_base = second_length;
@@ -342,14 +343,16 @@ int do_adjtimex(struct timex *txc)
 		    freq_adj = shift_right(freq_adj, time_constant * 2 +
 					   (SHIFT_PLL + 2) * 2 - SHIFT_NSEC);
 		    if (mtemp >= MINSEC && (time_status & STA_FLL || mtemp > MAXSEC)) {
+			u64 utemp64;
 			temp64 = time_offset << (SHIFT_NSEC - SHIFT_FLL);
 			if (time_offset < 0) {
-			    temp64 = -temp64;
-			    do_div(temp64, mtemp);
-			    freq_adj -= temp64;
+			    utemp64 = -temp64;
+			    do_div(utemp64, mtemp);
+			    freq_adj -= utemp64;
 			} else {
-			    do_div(temp64, mtemp);
-			    freq_adj += temp64;
+			    utemp64 = temp64;
+			    do_div(utemp64, mtemp);
+			    freq_adj += utemp64;
 			}
 		    }
 		    freq_adj += time_freq;
@@ -400,3 +403,11 @@ leave:	if ((time_status & (STA_UNSYNC|STA_CLOCKERR)) != 0)
 	notify_cmos_timer();
 	return(result);
 }
+
+static int __init ntp_tick_adj_setup(char *str)
+{
+	ntp_tick_adj = simple_strtol(str, NULL, 0);
+	return 1;
+}
+
+__setup("ntp_tick_adj=", ntp_tick_adj_setup);
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index fa9bb73dbdb4..686da821d376 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -282,6 +282,7 @@ void tick_nohz_stop_sched_tick(void)
 			ts->idle_tick = ts->sched_timer.expires;
 			ts->tick_stopped = 1;
 			ts->idle_jiffies = last_jiffies;
+			rcu_enter_nohz();
 		}
 
 		/*
@@ -375,6 +376,8 @@ void tick_nohz_restart_sched_tick(void)
 		return;
 	}
 
+	rcu_exit_nohz();
+
 	/* Update jiffies first */
 	select_nohz_load_balancer(0);
 	now = ktime_get();
@@ -637,7 +640,7 @@ void tick_cancel_sched_timer(int cpu)
 
 	if (ts->sched_timer.base)
 		hrtimer_cancel(&ts->sched_timer);
-	ts->tick_stopped = 0;
+
 	ts->nohz_mode = NOHZ_MODE_INACTIVE;
 }
 #endif /* HIGH_RES_TIMERS */
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 1af9fb050fe2..671af612b768 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -187,8 +187,7 @@ static void change_clocksource(void)
 
 	clock->error = 0;
 	clock->xtime_nsec = 0;
-	clocksource_calculate_interval(clock,
-		(unsigned long)(current_tick_length()>>TICK_LENGTH_SHIFT));
+	clocksource_calculate_interval(clock, NTP_INTERVAL_LENGTH);
 
 	tick_clock_notify();
 
@@ -245,8 +244,7 @@ void __init timekeeping_init(void)
 	ntp_clear();
 
 	clock = clocksource_get_next();
-	clocksource_calculate_interval(clock,
-		(unsigned long)(current_tick_length()>>TICK_LENGTH_SHIFT));
+	clocksource_calculate_interval(clock, NTP_INTERVAL_LENGTH);
 	clock->cycle_last = clocksource_read(clock);
 
 	xtime.tv_sec = sec;