Merge commit 'v2.6.29-rc1' into perfcounters/core

Conflicts:
	include/linux/kernel_stat.h

96 files changed, 6247 insertions, 3004 deletions

diff --git a/kernel/Kconfig.preempt b/kernel/Kconfig.preempt
index 9fdba03dc1fc..bf987b95b356 100644
--- a/kernel/Kconfig.preempt
+++ b/kernel/Kconfig.preempt
@@ -52,28 +52,3 @@ 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
-	  This option provides tracing in RCU which presents stats
-	  in debugfs for debugging RCU implementation.
-
-	  Say Y here if you want to enable RCU tracing
-	  Say N if you are unsure.
diff --git a/kernel/Makefile b/kernel/Makefile
index 4476da868f86..8b2628c7914b 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -9,7 +9,8 @@ obj-y     = sched.o fork.o exec_domain.o panic.o printk.o \
 	    rcupdate.o extable.o params.o posix-timers.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
+	    notifier.o ksysfs.o pm_qos_params.o sched_clock.o cred.o \
+	    async.o
 
 ifdef CONFIG_FUNCTION_TRACER
 # Do not trace debug files and internal ftrace files
@@ -73,10 +74,10 @@ obj-$(CONFIG_GENERIC_HARDIRQS) += irq/
 obj-$(CONFIG_SECCOMP) += seccomp.o
 obj-$(CONFIG_RCU_TORTURE_TEST) += rcutorture.o
 obj-$(CONFIG_CLASSIC_RCU) += rcuclassic.o
+obj-$(CONFIG_TREE_RCU) += rcutree.o
 obj-$(CONFIG_PREEMPT_RCU) += rcupreempt.o
-ifeq ($(CONFIG_PREEMPT_RCU),y)
-obj-$(CONFIG_RCU_TRACE) += rcupreempt_trace.o
-endif
+obj-$(CONFIG_TREE_RCU_TRACE) += rcutree_trace.o
+obj-$(CONFIG_PREEMPT_RCU_TRACE) += rcupreempt_trace.o
 obj-$(CONFIG_RELAY) += relay.o
 obj-$(CONFIG_SYSCTL) += utsname_sysctl.o
 obj-$(CONFIG_TASK_DELAY_ACCT) += delayacct.o
diff --git a/kernel/async.c b/kernel/async.c
new file mode 100644
index 000000000000..f286e9f2b736
--- /dev/null
+++ b/kernel/async.c
@@ -0,0 +1,335 @@
+/*
+ * async.c: Asynchronous function calls for boot performance
+ *
+ * (C) Copyright 2009 Intel Corporation
+ * Author: Arjan van de Ven <arjan@linux.intel.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; version 2
+ * of the License.
+ */
+
+
+/*
+
+Goals and Theory of Operation
+
+The primary goal of this feature is to reduce the kernel boot time,
+by doing various independent hardware delays and discovery operations
+decoupled and not strictly serialized.
+
+More specifically, the asynchronous function call concept allows
+certain operations (primarily during system boot) to happen
+asynchronously, out of order, while these operations still
+have their externally visible parts happen sequentially and in-order.
+(not unlike how out-of-order CPUs retire their instructions in order)
+
+Key to the asynchronous function call implementation is the concept of
+a "sequence cookie" (which, although it has an abstracted type, can be
+thought of as a monotonically incrementing number).
+
+The async core will assign each scheduled event such a sequence cookie and
+pass this to the called functions.
+
+The asynchronously called function should before doing a globally visible
+operation, such as registering device numbers, call the
+async_synchronize_cookie() function and pass in its own cookie. The
+async_synchronize_cookie() function will make sure that all asynchronous
+operations that were scheduled prior to the operation corresponding with the
+cookie have completed.
+
+Subsystem/driver initialization code that scheduled asynchronous probe
+functions, but which shares global resources with other drivers/subsystems
+that do not use the asynchronous call feature, need to do a full
+synchronization with the async_synchronize_full() function, before returning
+from their init function. This is to maintain strict ordering between the
+asynchronous and synchronous parts of the kernel.
+
+*/
+
+#include <linux/async.h>
+#include <linux/module.h>
+#include <linux/wait.h>
+#include <linux/sched.h>
+#include <linux/init.h>
+#include <linux/kthread.h>
+#include <asm/atomic.h>
+
+static async_cookie_t next_cookie = 1;
+
+#define MAX_THREADS	256
+#define MAX_WORK	32768
+
+static LIST_HEAD(async_pending);
+static LIST_HEAD(async_running);
+static DEFINE_SPINLOCK(async_lock);
+
+static int async_enabled = 0;
+
+struct async_entry {
+	struct list_head list;
+	async_cookie_t   cookie;
+	async_func_ptr	 *func;
+	void             *data;
+	struct list_head *running;
+};
+
+static DECLARE_WAIT_QUEUE_HEAD(async_done);
+static DECLARE_WAIT_QUEUE_HEAD(async_new);
+
+static atomic_t entry_count;
+static atomic_t thread_count;
+
+extern int initcall_debug;
+
+
+/*
+ * MUST be called with the lock held!
+ */
+static async_cookie_t  __lowest_in_progress(struct list_head *running)
+{
+	struct async_entry *entry;
+	if (!list_empty(&async_pending)) {
+		entry = list_first_entry(&async_pending,
+			struct async_entry, list);
+		return entry->cookie;
+	} else if (!list_empty(running)) {
+		entry = list_first_entry(running,
+			struct async_entry, list);
+		return entry->cookie;
+	} else {
+		/* nothing in progress... next_cookie is "infinity" */
+		return next_cookie;
+	}
+
+}
+/*
+ * pick the first pending entry and run it
+ */
+static void run_one_entry(void)
+{
+	unsigned long flags;
+	struct async_entry *entry;
+	ktime_t calltime, delta, rettime;
+
+	/* 1) pick one task from the pending queue */
+
+	spin_lock_irqsave(&async_lock, flags);
+	if (list_empty(&async_pending))
+		goto out;
+	entry = list_first_entry(&async_pending, struct async_entry, list);
+
+	/* 2) move it to the running queue */
+	list_del(&entry->list);
+	list_add_tail(&entry->list, &async_running);
+	spin_unlock_irqrestore(&async_lock, flags);
+
+	/* 3) run it (and print duration)*/
+	if (initcall_debug && system_state == SYSTEM_BOOTING) {
+		printk("calling  %lli_%pF @ %i\n", entry->cookie, entry->func, task_pid_nr(current));
+		calltime = ktime_get();
+	}
+	entry->func(entry->data, entry->cookie);
+	if (initcall_debug && system_state == SYSTEM_BOOTING) {
+		rettime = ktime_get();
+		delta = ktime_sub(rettime, calltime);
+		printk("initcall %lli_%pF returned 0 after %lld usecs\n", entry->cookie,
+			entry->func, ktime_to_ns(delta) >> 10);
+	}
+
+	/* 4) remove it from the running queue */
+	spin_lock_irqsave(&async_lock, flags);
+	list_del(&entry->list);
+
+	/* 5) free the entry  */
+	kfree(entry);
+	atomic_dec(&entry_count);
+
+	spin_unlock_irqrestore(&async_lock, flags);
+
+	/* 6) wake up any waiters. */
+	wake_up(&async_done);
+	return;
+
+out:
+	spin_unlock_irqrestore(&async_lock, flags);
+}
+
+
+static async_cookie_t __async_schedule(async_func_ptr *ptr, void *data, struct list_head *running)
+{
+	struct async_entry *entry;
+	unsigned long flags;
+	async_cookie_t newcookie;
+	
+
+	/* allow irq-off callers */
+	entry = kzalloc(sizeof(struct async_entry), GFP_ATOMIC);
+
+	/*
+	 * If we're out of memory or if there's too much work
+	 * pending already, we execute synchronously.
+	 */
+	if (!async_enabled || !entry || atomic_read(&entry_count) > MAX_WORK) {
+		kfree(entry);
+		spin_lock_irqsave(&async_lock, flags);
+		newcookie = next_cookie++;
+		spin_unlock_irqrestore(&async_lock, flags);
+
+		/* low on memory.. run synchronously */
+		ptr(data, newcookie);
+		return newcookie;
+	}
+	entry->func = ptr;
+	entry->data = data;
+	entry->running = running;
+
+	spin_lock_irqsave(&async_lock, flags);
+	newcookie = entry->cookie = next_cookie++;
+	list_add_tail(&entry->list, &async_pending);
+	atomic_inc(&entry_count);
+	spin_unlock_irqrestore(&async_lock, flags);
+	wake_up(&async_new);
+	return newcookie;
+}
+
+async_cookie_t async_schedule(async_func_ptr *ptr, void *data)
+{
+	return __async_schedule(ptr, data, &async_pending);
+}
+EXPORT_SYMBOL_GPL(async_schedule);
+
+async_cookie_t async_schedule_special(async_func_ptr *ptr, void *data, struct list_head *running)
+{
+	return __async_schedule(ptr, data, running);
+}
+EXPORT_SYMBOL_GPL(async_schedule_special);
+
+void async_synchronize_full(void)
+{
+	do {
+		async_synchronize_cookie(next_cookie);
+	} while (!list_empty(&async_running) || !list_empty(&async_pending));
+}
+EXPORT_SYMBOL_GPL(async_synchronize_full);
+
+void async_synchronize_full_special(struct list_head *list)
+{
+	async_synchronize_cookie_special(next_cookie, list);
+}
+EXPORT_SYMBOL_GPL(async_synchronize_full_special);
+
+void async_synchronize_cookie_special(async_cookie_t cookie, struct list_head *running)
+{
+	ktime_t starttime, delta, endtime;
+
+	if (initcall_debug && system_state == SYSTEM_BOOTING) {
+		printk("async_waiting @ %i\n", task_pid_nr(current));
+		starttime = ktime_get();
+	}
+
+	wait_event(async_done, __lowest_in_progress(running) >= cookie);
+
+	if (initcall_debug && system_state == SYSTEM_BOOTING) {
+		endtime = ktime_get();
+		delta = ktime_sub(endtime, starttime);
+
+		printk("async_continuing @ %i after %lli usec\n",
+			task_pid_nr(current), ktime_to_ns(delta) >> 10);
+	}
+}
+EXPORT_SYMBOL_GPL(async_synchronize_cookie_special);
+
+void async_synchronize_cookie(async_cookie_t cookie)
+{
+	async_synchronize_cookie_special(cookie, &async_running);
+}
+EXPORT_SYMBOL_GPL(async_synchronize_cookie);
+
+
+static int async_thread(void *unused)
+{
+	DECLARE_WAITQUEUE(wq, current);
+	add_wait_queue(&async_new, &wq);
+
+	while (!kthread_should_stop()) {
+		int ret = HZ;
+		set_current_state(TASK_INTERRUPTIBLE);
+		/*
+		 * check the list head without lock.. false positives
+		 * are dealt with inside run_one_entry() while holding
+		 * the lock.
+		 */
+		rmb();
+		if (!list_empty(&async_pending))
+			run_one_entry();
+		else
+			ret = schedule_timeout(HZ);
+
+		if (ret == 0) {
+			/*
+			 * we timed out, this means we as thread are redundant.
+			 * we sign off and die, but we to avoid any races there
+			 * is a last-straw check to see if work snuck in.
+			 */
+			atomic_dec(&thread_count);
+			wmb(); /* manager must see our departure first */
+			if (list_empty(&async_pending))
+				break;
+			/*
+			 * woops work came in between us timing out and us
+			 * signing off; we need to stay alive and keep working.
+			 */
+			atomic_inc(&thread_count);
+		}
+	}
+	remove_wait_queue(&async_new, &wq);
+
+	return 0;
+}
+
+static int async_manager_thread(void *unused)
+{
+	DECLARE_WAITQUEUE(wq, current);
+	add_wait_queue(&async_new, &wq);
+
+	while (!kthread_should_stop()) {
+		int tc, ec;
+
+		set_current_state(TASK_INTERRUPTIBLE);
+
+		tc = atomic_read(&thread_count);
+		rmb();
+		ec = atomic_read(&entry_count);
+
+		while (tc < ec && tc < MAX_THREADS) {
+			kthread_run(async_thread, NULL, "async/%i", tc);
+			atomic_inc(&thread_count);
+			tc++;
+		}
+
+		schedule();
+	}
+	remove_wait_queue(&async_new, &wq);
+
+	return 0;
+}
+
+static int __init async_init(void)
+{
+	if (async_enabled)
+		kthread_run(async_manager_thread, NULL, "async/mgr");
+	return 0;
+}
+
+static int __init setup_async(char *str)
+{
+	async_enabled = 1;
+	return 1;
+}
+
+__setup("fastboot", setup_async);
+
+
+core_initcall(async_init);
diff --git a/kernel/audit.h b/kernel/audit.h
index 9d6717412fec..16f18cac661b 100644
--- a/kernel/audit.h
+++ b/kernel/audit.h
@@ -159,11 +159,8 @@ static inline int audit_signal_info(int sig, struct task_struct *t)
 		return __audit_signal_info(sig, t);
 	return 0;
 }
-extern enum audit_state audit_filter_inodes(struct task_struct *,
-					    struct audit_context *);
-extern void audit_set_auditable(struct audit_context *);
+extern void audit_filter_inodes(struct task_struct *, struct audit_context *);
 #else
 #define audit_signal_info(s,t) AUDIT_DISABLED
 #define audit_filter_inodes(t,c) AUDIT_DISABLED
-#define audit_set_auditable(c)
 #endif
diff --git a/kernel/audit_tree.c b/kernel/audit_tree.c
index 8b509441f49a..8ad9545b8db9 100644
--- a/kernel/audit_tree.c
+++ b/kernel/audit_tree.c
@@ -450,6 +450,7 @@ static void kill_rules(struct audit_tree *tree)
 			audit_log_end(ab);
 			rule->tree = NULL;
 			list_del_rcu(&entry->list);
+			list_del(&entry->rule.list);
 			call_rcu(&entry->rcu, audit_free_rule_rcu);
 		}
 	}
@@ -617,7 +618,7 @@ int audit_make_tree(struct audit_krule *rule, char *pathname, u32 op)
 
 	if (pathname[0] != '/' ||
 	    rule->listnr != AUDIT_FILTER_EXIT ||
-	    op & ~AUDIT_EQUAL ||
+	    op != Audit_equal ||
 	    rule->inode_f || rule->watch || rule->tree)
 		return -EINVAL;
 	rule->tree = alloc_tree(pathname);
diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c
index 9fd85a4640a0..fbf24d121d97 100644
--- a/kernel/auditfilter.c
+++ b/kernel/auditfilter.c
@@ -86,6 +86,14 @@ struct list_head audit_filter_list[AUDIT_NR_FILTERS] = {
 #error Fix audit_filter_list initialiser
 #endif
 };
+static struct list_head audit_rules_list[AUDIT_NR_FILTERS] = {
+	LIST_HEAD_INIT(audit_rules_list[0]),
+	LIST_HEAD_INIT(audit_rules_list[1]),
+	LIST_HEAD_INIT(audit_rules_list[2]),
+	LIST_HEAD_INIT(audit_rules_list[3]),
+	LIST_HEAD_INIT(audit_rules_list[4]),
+	LIST_HEAD_INIT(audit_rules_list[5]),
+};
 
 DEFINE_MUTEX(audit_filter_mutex);
 
@@ -244,7 +252,8 @@ static inline int audit_to_inode(struct audit_krule *krule,
 				 struct audit_field *f)
 {
 	if (krule->listnr != AUDIT_FILTER_EXIT ||
-	    krule->watch || krule->inode_f || krule->tree)
+	    krule->watch || krule->inode_f || krule->tree ||
+	    (f->op != Audit_equal && f->op != Audit_not_equal))
 		return -EINVAL;
 
 	krule->inode_f = f;
@@ -262,7 +271,7 @@ static int audit_to_watch(struct audit_krule *krule, char *path, int len,
 
 	if (path[0] != '/' || path[len-1] == '/' ||
 	    krule->listnr != AUDIT_FILTER_EXIT ||
-	    op & ~AUDIT_EQUAL ||
+	    op != Audit_equal ||
 	    krule->inode_f || krule->watch || krule->tree)
 		return -EINVAL;
 
@@ -412,12 +421,32 @@ exit_err:
 	return ERR_PTR(err);
 }
 
+static u32 audit_ops[] =
+{
+	[Audit_equal] = AUDIT_EQUAL,
+	[Audit_not_equal] = AUDIT_NOT_EQUAL,
+	[Audit_bitmask] = AUDIT_BIT_MASK,
+	[Audit_bittest] = AUDIT_BIT_TEST,
+	[Audit_lt] = AUDIT_LESS_THAN,
+	[Audit_gt] = AUDIT_GREATER_THAN,
+	[Audit_le] = AUDIT_LESS_THAN_OR_EQUAL,
+	[Audit_ge] = AUDIT_GREATER_THAN_OR_EQUAL,
+};
+
+static u32 audit_to_op(u32 op)
+{
+	u32 n;
+	for (n = Audit_equal; n < Audit_bad && audit_ops[n] != op; n++)
+		;
+	return n;
+}
+
+
 /* Translate struct audit_rule to kernel's rule respresentation.
  * Exists for backward compatibility with userspace. */
 static struct audit_entry *audit_rule_to_entry(struct audit_rule *rule)
 {
 	struct audit_entry *entry;
-	struct audit_field *ino_f;
 	int err = 0;
 	int i;
 
@@ -427,12 +456,28 @@ static struct audit_entry *audit_rule_to_entry(struct audit_rule *rule)
 
 	for (i = 0; i < rule->field_count; i++) {
 		struct audit_field *f = &entry->rule.fields[i];
+		u32 n;
+
+		n = rule->fields[i] & (AUDIT_NEGATE|AUDIT_OPERATORS);
+
+		/* Support for legacy operators where
+		 * AUDIT_NEGATE bit signifies != and otherwise assumes == */
+		if (n & AUDIT_NEGATE)
+			f->op = Audit_not_equal;
+		else if (!n)
+			f->op = Audit_equal;
+		else
+			f->op = audit_to_op(n);
+
+		entry->rule.vers_ops = (n & AUDIT_OPERATORS) ? 2 : 1;
 
-		f->op = rule->fields[i] & (AUDIT_NEGATE|AUDIT_OPERATORS);
 		f->type = rule->fields[i] & ~(AUDIT_NEGATE|AUDIT_OPERATORS);
 		f->val = rule->values[i];
 
 		err = -EINVAL;
+		if (f->op == Audit_bad)
+			goto exit_free;
+
 		switch(f->type) {
 		default:
 			goto exit_free;
@@ -454,11 +499,8 @@ static struct audit_entry *audit_rule_to_entry(struct audit_rule *rule)
 		case AUDIT_EXIT:
 		case AUDIT_SUCCESS:
 			/* bit ops are only useful on syscall args */
-			if (f->op == AUDIT_BIT_MASK ||
-						f->op == AUDIT_BIT_TEST) {
-				err = -EINVAL;
+			if (f->op == Audit_bitmask || f->op == Audit_bittest)
 				goto exit_free;
-			}
 			break;
 		case AUDIT_ARG0:
 		case AUDIT_ARG1:
@@ -467,11 +509,8 @@ static struct audit_entry *audit_rule_to_entry(struct audit_rule *rule)
 			break;
 		/* arch is only allowed to be = or != */
 		case AUDIT_ARCH:
-			if ((f->op != AUDIT_NOT_EQUAL) && (f->op != AUDIT_EQUAL)
-					&& (f->op != AUDIT_NEGATE) && (f->op)) {
-				err = -EINVAL;
+			if (f->op != Audit_not_equal && f->op != Audit_equal)
 				goto exit_free;
-			}
 			entry->rule.arch_f = f;
 			break;
 		case AUDIT_PERM:
@@ -488,33 +527,10 @@ static struct audit_entry *audit_rule_to_entry(struct audit_rule *rule)
 				goto exit_free;
 			break;
 		}
-
-		entry->rule.vers_ops = (f->op & AUDIT_OPERATORS) ? 2 : 1;
-
-		/* Support for legacy operators where
-		 * AUDIT_NEGATE bit signifies != and otherwise assumes == */
-		if (f->op & AUDIT_NEGATE)
-			f->op = AUDIT_NOT_EQUAL;
-		else if (!f->op)
-			f->op = AUDIT_EQUAL;
-		else if (f->op == AUDIT_OPERATORS) {
-			err = -EINVAL;
-			goto exit_free;
-		}
 	}
 
-	ino_f = entry->rule.inode_f;
-	if (ino_f) {
-		switch(ino_f->op) {
-		case AUDIT_NOT_EQUAL:
-			entry->rule.inode_f = NULL;
-		case AUDIT_EQUAL:
-			break;
-		default:
-			err = -EINVAL;
-			goto exit_free;
-		}
-	}
+	if (entry->rule.inode_f && entry->rule.inode_f->op == Audit_not_equal)
+		entry->rule.inode_f = NULL;
 
 exit_nofree:
 	return entry;
@@ -530,7 +546,6 @@ static struct audit_entry *audit_data_to_entry(struct audit_rule_data *data,
 {
 	int err = 0;
 	struct audit_entry *entry;
-	struct audit_field *ino_f;
 	void *bufp;
 	size_t remain = datasz - sizeof(struct audit_rule_data);
 	int i;
@@ -546,11 +561,11 @@ static struct audit_entry *audit_data_to_entry(struct audit_rule_data *data,
 		struct audit_field *f = &entry->rule.fields[i];
 
 		err = -EINVAL;
-		if (!(data->fieldflags[i] & AUDIT_OPERATORS) ||
-		    data->fieldflags[i] & ~AUDIT_OPERATORS)
+
+		f->op = audit_to_op(data->fieldflags[i]);
+		if (f->op == Audit_bad)
 			goto exit_free;
 
-		f->op = data->fieldflags[i] & AUDIT_OPERATORS;
 		f->type = data->fields[i];
 		f->val = data->values[i];
 		f->lsm_str = NULL;
@@ -662,18 +677,8 @@ static struct audit_entry *audit_data_to_entry(struct audit_rule_data *data,
 		}
 	}
 
-	ino_f = entry->rule.inode_f;
-	if (ino_f) {
-		switch(ino_f->op) {
-		case AUDIT_NOT_EQUAL:
-			entry->rule.inode_f = NULL;
-		case AUDIT_EQUAL:
-			break;
-		default:
-			err = -EINVAL;
-			goto exit_free;
-		}
-	}
+	if (entry->rule.inode_f && entry->rule.inode_f->op == Audit_not_equal)
+		entry->rule.inode_f = NULL;
 
 exit_nofree:
 	return entry;
@@ -713,10 +718,10 @@ static struct audit_rule *audit_krule_to_rule(struct audit_krule *krule)
 		rule->fields[i] = krule->fields[i].type;
 
 		if (krule->vers_ops == 1) {
-			if (krule->fields[i].op & AUDIT_NOT_EQUAL)
+			if (krule->fields[i].op == Audit_not_equal)
 				rule->fields[i] |= AUDIT_NEGATE;
 		} else {
-			rule->fields[i] |= krule->fields[i].op;
+			rule->fields[i] |= audit_ops[krule->fields[i].op];
 		}
 	}
 	for (i = 0; i < AUDIT_BITMASK_SIZE; i++) rule->mask[i] = krule->mask[i];
@@ -744,7 +749,7 @@ static struct audit_rule_data *audit_krule_to_data(struct audit_krule *krule)
 		struct audit_field *f = &krule->fields[i];
 
 		data->fields[i] = f->type;
-		data->fieldflags[i] = f->op;
+		data->fieldflags[i] = audit_ops[f->op];
 		switch(f->type) {
 		case AUDIT_SUBJ_USER:
 		case AUDIT_SUBJ_ROLE:
@@ -919,6 +924,7 @@ static struct audit_entry *audit_dupe_rule(struct audit_krule *old,
 	new->action = old->action;
 	for (i = 0; i < AUDIT_BITMASK_SIZE; i++)
 		new->mask[i] = old->mask[i];
+	new->prio = old->prio;
 	new->buflen = old->buflen;
 	new->inode_f = old->inode_f;
 	new->watch = NULL;
@@ -987,9 +993,8 @@ static void audit_update_watch(struct audit_parent *parent,
 
 		/* If the update involves invalidating rules, do the inode-based
 		 * filtering now, so we don't omit records. */
-		if (invalidating && current->audit_context &&
-		    audit_filter_inodes(current, current->audit_context) == AUDIT_RECORD_CONTEXT)
-			audit_set_auditable(current->audit_context);
+		if (invalidating && current->audit_context)
+			audit_filter_inodes(current, current->audit_context);
 
 		nwatch = audit_dupe_watch(owatch);
 		if (IS_ERR(nwatch)) {
@@ -1007,12 +1012,15 @@ static void audit_update_watch(struct audit_parent *parent,
 			list_del_rcu(&oentry->list);
 
 			nentry = audit_dupe_rule(&oentry->rule, nwatch);
-			if (IS_ERR(nentry))
+			if (IS_ERR(nentry)) {
+				list_del(&oentry->rule.list);
 				audit_panic("error updating watch, removing");
-			else {
+			} else {
 				int h = audit_hash_ino((u32)ino);
 				list_add(&nentry->rule.rlist, &nwatch->rules);
 				list_add_rcu(&nentry->list, &audit_inode_hash[h]);
+				list_replace(&oentry->rule.list,
+					     &nentry->rule.list);
 			}
 
 			call_rcu(&oentry->rcu, audit_free_rule_rcu);
@@ -1077,6 +1085,7 @@ static void audit_remove_parent_watches(struct audit_parent *parent)
 				audit_log_end(ab);
 			}
 			list_del(&r->rlist);
+			list_del(&r->list);
 			list_del_rcu(&e->list);
 			call_rcu(&e->rcu, audit_free_rule_rcu);
 		}
@@ -1102,12 +1111,16 @@ static void audit_inotify_unregister(struct list_head *in_list)
 /* Find an existing audit rule.
  * Caller must hold audit_filter_mutex to prevent stale rule data. */
 static struct audit_entry *audit_find_rule(struct audit_entry *entry,
-					   struct list_head *list)
+					   struct list_head **p)
 {
 	struct audit_entry *e, *found = NULL;
+	struct list_head *list;
 	int h;
 
-	if (entry->rule.watch) {
+	if (entry->rule.inode_f) {
+		h = audit_hash_ino(entry->rule.inode_f->val);
+		*p = list = &audit_inode_hash[h];
+	} else if (entry->rule.watch) {
 		/* we don't know the inode number, so must walk entire hash */
 		for (h = 0; h < AUDIT_INODE_BUCKETS; h++) {
 			list = &audit_inode_hash[h];
@@ -1118,6 +1131,8 @@ static struct audit_entry *audit_find_rule(struct audit_entry *entry,
 				}
 		}
 		goto out;
+	} else {
+		*p = list = &audit_filter_list[entry->rule.listnr];
 	}
 
 	list_for_each_entry(e, list, list)
@@ -1258,15 +1273,17 @@ static int audit_add_watch(struct audit_krule *krule, struct nameidata *ndp,
 	return ret;
 }
 
+static u64 prio_low = ~0ULL/2;
+static u64 prio_high = ~0ULL/2 - 1;
+
 /* Add rule to given filterlist if not a duplicate. */
-static inline int audit_add_rule(struct audit_entry *entry,
-				 struct list_head *list)
+static inline int audit_add_rule(struct audit_entry *entry)
 {
 	struct audit_entry *e;
-	struct audit_field *inode_f = entry->rule.inode_f;
 	struct audit_watch *watch = entry->rule.watch;
 	struct audit_tree *tree = entry->rule.tree;
 	struct nameidata *ndp = NULL, *ndw = NULL;
+	struct list_head *list;
 	int h, err;
 #ifdef CONFIG_AUDITSYSCALL
 	int dont_count = 0;
@@ -1277,13 +1294,8 @@ static inline int audit_add_rule(struct audit_entry *entry,
 		dont_count = 1;
 #endif
 
-	if (inode_f) {
-		h = audit_hash_ino(inode_f->val);
-		list = &audit_inode_hash[h];
-	}
-
 	mutex_lock(&audit_filter_mutex);
-	e = audit_find_rule(entry, list);
+	e = audit_find_rule(entry, &list);
 	mutex_unlock(&audit_filter_mutex);
 	if (e) {
 		err = -EEXIST;
@@ -1319,10 +1331,22 @@ static inline int audit_add_rule(struct audit_entry *entry,
 		}
 	}
 
+	entry->rule.prio = ~0ULL;
+	if (entry->rule.listnr == AUDIT_FILTER_EXIT) {
+		if (entry->rule.flags & AUDIT_FILTER_PREPEND)
+			entry->rule.prio = ++prio_high;
+		else
+			entry->rule.prio = --prio_low;
+	}
+
 	if (entry->rule.flags & AUDIT_FILTER_PREPEND) {
+		list_add(&entry->rule.list,
+			 &audit_rules_list[entry->rule.listnr]);
 		list_add_rcu(&entry->list, list);
 		entry->rule.flags &= ~AUDIT_FILTER_PREPEND;
 	} else {
+		list_add_tail(&entry->rule.list,
+			      &audit_rules_list[entry->rule.listnr]);
 		list_add_tail_rcu(&entry->list, list);
 	}
 #ifdef CONFIG_AUDITSYSCALL
@@ -1345,15 +1369,14 @@ error:
 }
 
 /* Remove an existing rule from filterlist. */
-static inline int audit_del_rule(struct audit_entry *entry,
-				 struct list_head *list)
+static inline int audit_del_rule(struct audit_entry *entry)
 {
 	struct audit_entry  *e;
-	struct audit_field *inode_f = entry->rule.inode_f;
 	struct audit_watch *watch, *tmp_watch = entry->rule.watch;
 	struct audit_tree *tree = entry->rule.tree;
+	struct list_head *list;
 	LIST_HEAD(inotify_list);
-	int h, ret = 0;
+	int ret = 0;
 #ifdef CONFIG_AUDITSYSCALL
 	int dont_count = 0;
 
@@ -1363,13 +1386,8 @@ static inline int audit_del_rule(struct audit_entry *entry,
 		dont_count = 1;
 #endif
 
-	if (inode_f) {
-		h = audit_hash_ino(inode_f->val);
-		list = &audit_inode_hash[h];
-	}
-
 	mutex_lock(&audit_filter_mutex);
-	e = audit_find_rule(entry, list);
+	e = audit_find_rule(entry, &list);
 	if (!e) {
 		mutex_unlock(&audit_filter_mutex);
 		ret = -ENOENT;
@@ -1404,6 +1422,7 @@ static inline int audit_del_rule(struct audit_entry *entry,
 		audit_remove_tree_rule(&e->rule);
 
 	list_del_rcu(&e->list);
+	list_del(&e->rule.list);
 	call_rcu(&e->rcu, audit_free_rule_rcu);
 
 #ifdef CONFIG_AUDITSYSCALL
@@ -1432,30 +1451,16 @@ out:
 static void audit_list(int pid, int seq, struct sk_buff_head *q)
 {
 	struct sk_buff *skb;
-	struct audit_entry *entry;
+	struct audit_krule *r;
 	int i;
 
 	/* This is a blocking read, so use audit_filter_mutex instead of rcu
 	 * iterator to sync with list writers. */
 	for (i=0; i<AUDIT_NR_FILTERS; i++) {
-		list_for_each_entry(entry, &audit_filter_list[i], list) {
-			struct audit_rule *rule;
-
-			rule = audit_krule_to_rule(&entry->rule);
-			if (unlikely(!rule))
-				break;
-			skb = audit_make_reply(pid, seq, AUDIT_LIST, 0, 1,
-					 rule, sizeof(*rule));
-			if (skb)
-				skb_queue_tail(q, skb);
-			kfree(rule);
-		}
-	}
-	for (i = 0; i < AUDIT_INODE_BUCKETS; i++) {
-		list_for_each_entry(entry, &audit_inode_hash[i], list) {
+		list_for_each_entry(r, &audit_rules_list[i], list) {
 			struct audit_rule *rule;
 
-			rule = audit_krule_to_rule(&entry->rule);
+			rule = audit_krule_to_rule(r);
 			if (unlikely(!rule))
 				break;
 			skb = audit_make_reply(pid, seq, AUDIT_LIST, 0, 1,
@@ -1474,30 +1479,16 @@ static void audit_list(int pid, int seq, struct sk_buff_head *q)
 static void audit_list_rules(int pid, int seq, struct sk_buff_head *q)
 {
 	struct sk_buff *skb;
-	struct audit_entry *e;
+	struct audit_krule *r;
 	int i;
 
 	/* This is a blocking read, so use audit_filter_mutex instead of rcu
 	 * iterator to sync with list writers. */
 	for (i=0; i<AUDIT_NR_FILTERS; i++) {
-		list_for_each_entry(e, &audit_filter_list[i], list) {
-			struct audit_rule_data *data;
-
-			data = audit_krule_to_data(&e->rule);
-			if (unlikely(!data))
-				break;
-			skb = audit_make_reply(pid, seq, AUDIT_LIST_RULES, 0, 1,
-					 data, sizeof(*data) + data->buflen);
-			if (skb)
-				skb_queue_tail(q, skb);
-			kfree(data);
-		}
-	}
-	for (i=0; i< AUDIT_INODE_BUCKETS; i++) {
-		list_for_each_entry(e, &audit_inode_hash[i], list) {
+		list_for_each_entry(r, &audit_rules_list[i], list) {
 			struct audit_rule_data *data;
 
-			data = audit_krule_to_data(&e->rule);
+			data = audit_krule_to_data(r);
 			if (unlikely(!data))
 				break;
 			skb = audit_make_reply(pid, seq, AUDIT_LIST_RULES, 0, 1,
@@ -1603,8 +1594,7 @@ int audit_receive_filter(int type, int pid, int uid, int seq, void *data,
 		if (IS_ERR(entry))
 			return PTR_ERR(entry);
 
-		err = audit_add_rule(entry,
-				     &audit_filter_list[entry->rule.listnr]);
+		err = audit_add_rule(entry);
 		audit_log_rule_change(loginuid, sessionid, sid, "add",
 				      &entry->rule, !err);
 
@@ -1620,8 +1610,7 @@ int audit_receive_filter(int type, int pid, int uid, int seq, void *data,
 		if (IS_ERR(entry))
 			return PTR_ERR(entry);
 
-		err = audit_del_rule(entry,
-				     &audit_filter_list[entry->rule.listnr]);
+		err = audit_del_rule(entry);
 		audit_log_rule_change(loginuid, sessionid, sid, "remove",
 				      &entry->rule, !err);
 
@@ -1634,28 +1623,29 @@ int audit_receive_filter(int type, int pid, int uid, int seq, void *data,
 	return err;
 }
 
-int audit_comparator(const u32 left, const u32 op, const u32 right)
+int audit_comparator(u32 left, u32 op, u32 right)
 {
 	switch (op) {
-	case AUDIT_EQUAL:
+	case Audit_equal:
 		return (left == right);
-	case AUDIT_NOT_EQUAL:
+	case Audit_not_equal:
 		return (left != right);
-	case AUDIT_LESS_THAN:
+	case Audit_lt:
 		return (left < right);
-	case AUDIT_LESS_THAN_OR_EQUAL:
+	case Audit_le:
 		return (left <= right);
-	case AUDIT_GREATER_THAN:
+	case Audit_gt:
 		return (left > right);
-	case AUDIT_GREATER_THAN_OR_EQUAL:
+	case Audit_ge:
 		return (left >= right);
-	case AUDIT_BIT_MASK:
+	case Audit_bitmask:
 		return (left & right);
-	case AUDIT_BIT_TEST:
+	case Audit_bittest:
 		return ((left & right) == right);
+	default:
+		BUG();
+		return 0;
 	}
-	BUG();
-	return 0;
 }
 
 /* Compare given dentry name with last component in given path,
@@ -1778,6 +1768,43 @@ unlock_and_return:
 	return result;
 }
 
+static int update_lsm_rule(struct audit_krule *r)
+{
+	struct audit_entry *entry = container_of(r, struct audit_entry, rule);
+	struct audit_entry *nentry;
+	struct audit_watch *watch;
+	struct audit_tree *tree;
+	int err = 0;
+
+	if (!security_audit_rule_known(r))
+		return 0;
+
+	watch = r->watch;
+	tree = r->tree;
+	nentry = audit_dupe_rule(r, watch);
+	if (IS_ERR(nentry)) {
+		/* save the first error encountered for the
+		 * return value */
+		err = PTR_ERR(nentry);
+		audit_panic("error updating LSM filters");
+		if (watch)
+			list_del(&r->rlist);
+		list_del_rcu(&entry->list);
+		list_del(&r->list);
+	} else {
+		if (watch) {
+			list_add(&nentry->rule.rlist, &watch->rules);
+			list_del(&r->rlist);
+		} else if (tree)
+			list_replace_init(&r->rlist, &nentry->rule.rlist);
+		list_replace_rcu(&entry->list, &nentry->list);
+		list_replace(&r->list, &nentry->rule.list);
+	}
+	call_rcu(&entry->rcu, audit_free_rule_rcu);
+
+	return err;
+}
+
 /* This function will re-initialize the lsm_rule field of all applicable rules.
  * It will traverse the filter lists serarching for rules that contain LSM
  * specific filter fields.  When such a rule is found, it is copied, the
@@ -1785,45 +1812,19 @@ unlock_and_return:
  * updated rule. */
 int audit_update_lsm_rules(void)
 {
-	struct audit_entry *entry, *n, *nentry;
-	struct audit_watch *watch;
-	struct audit_tree *tree;
+	struct audit_krule *r, *n;
 	int i, err = 0;
 
 	/* audit_filter_mutex synchronizes the writers */
 	mutex_lock(&audit_filter_mutex);
 
 	for (i = 0; i < AUDIT_NR_FILTERS; i++) {
-		list_for_each_entry_safe(entry, n, &audit_filter_list[i], list) {
-			if (!security_audit_rule_known(&entry->rule))
-				continue;
-
-			watch = entry->rule.watch;
-			tree = entry->rule.tree;
-			nentry = audit_dupe_rule(&entry->rule, watch);
-			if (IS_ERR(nentry)) {
-				/* save the first error encountered for the
-				 * return value */
-				if (!err)
-					err = PTR_ERR(nentry);
-				audit_panic("error updating LSM filters");
-				if (watch)
-					list_del(&entry->rule.rlist);
-				list_del_rcu(&entry->list);
-			} else {
-				if (watch) {
-					list_add(&nentry->rule.rlist,
-						 &watch->rules);
-					list_del(&entry->rule.rlist);
-				} else if (tree)
-					list_replace_init(&entry->rule.rlist,
-						     &nentry->rule.rlist);
-				list_replace_rcu(&entry->list, &nentry->list);
-			}
-			call_rcu(&entry->rcu, audit_free_rule_rcu);
+		list_for_each_entry_safe(r, n, &audit_rules_list[i], list) {
+			int res = update_lsm_rule(r);
+			if (!err)
+				err = res;
 		}
 	}
-
 	mutex_unlock(&audit_filter_mutex);
 
 	return err;
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index 4819f3711973..8cbddff6c283 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -124,43 +124,6 @@ struct audit_aux_data {
 /* Number of target pids per aux struct. */
 #define AUDIT_AUX_PIDS	16
 
-struct audit_aux_data_mq_open {
-	struct audit_aux_data	d;
-	int			oflag;
-	mode_t			mode;
-	struct mq_attr		attr;
-};
-
-struct audit_aux_data_mq_sendrecv {
-	struct audit_aux_data	d;
-	mqd_t			mqdes;
-	size_t			msg_len;
-	unsigned int		msg_prio;
-	struct timespec		abs_timeout;
-};
-
-struct audit_aux_data_mq_notify {
-	struct audit_aux_data	d;
-	mqd_t			mqdes;
-	struct sigevent 	notification;
-};
-
-struct audit_aux_data_mq_getsetattr {
-	struct audit_aux_data	d;
-	mqd_t			mqdes;
-	struct mq_attr 		mqstat;
-};
-
-struct audit_aux_data_ipcctl {
-	struct audit_aux_data	d;
-	struct ipc_perm		p;
-	unsigned long		qbytes;
-	uid_t			uid;
-	gid_t			gid;
-	mode_t			mode;
-	u32			osid;
-};
-
 struct audit_aux_data_execve {
 	struct audit_aux_data	d;
 	int argc;
@@ -168,23 +131,6 @@ struct audit_aux_data_execve {
 	struct mm_struct *mm;
 };
 
-struct audit_aux_data_socketcall {
-	struct audit_aux_data	d;
-	int			nargs;
-	unsigned long		args[0];
-};
-
-struct audit_aux_data_sockaddr {
-	struct audit_aux_data	d;
-	int			len;
-	char			a[0];
-};
-
-struct audit_aux_data_fd_pair {
-	struct	audit_aux_data d;
-	int	fd[2];
-};
-
 struct audit_aux_data_pids {
 	struct audit_aux_data	d;
 	pid_t			target_pid[AUDIT_AUX_PIDS];
@@ -219,14 +165,14 @@ struct audit_tree_refs {
 struct audit_context {
 	int		    dummy;	/* must be the first element */
 	int		    in_syscall;	/* 1 if task is in a syscall */
-	enum audit_state    state;
+	enum audit_state    state, current_state;
 	unsigned int	    serial;     /* serial number for record */
 	struct timespec	    ctime;      /* time of syscall entry */
 	int		    major;      /* syscall number */
 	unsigned long	    argv[4];    /* syscall arguments */
 	int		    return_valid; /* return code is valid */
 	long		    return_code;/* syscall return code */
-	int		    auditable;  /* 1 if record should be written */
+	u64		    prio;
 	int		    name_count;
 	struct audit_names  names[AUDIT_NAMES];
 	char *		    filterkey;	/* key for rule that triggered record */
@@ -234,7 +180,8 @@ struct audit_context {
 	struct audit_context *previous; /* For nested syscalls */
 	struct audit_aux_data *aux;
 	struct audit_aux_data *aux_pids;
-
+	struct sockaddr_storage *sockaddr;
+	size_t sockaddr_len;
 				/* Save things to print about task_struct */
 	pid_t		    pid, ppid;
 	uid_t		    uid, euid, suid, fsuid;
@@ -252,6 +199,49 @@ struct audit_context {
 	struct audit_tree_refs *trees, *first_trees;
 	int tree_count;
 
+	int type;
+	union {
+		struct {
+			int nargs;
+			long args[6];
+		} socketcall;
+		struct {
+			uid_t			uid;
+			gid_t			gid;
+			mode_t			mode;
+			u32			osid;
+			int			has_perm;
+			uid_t			perm_uid;
+			gid_t			perm_gid;
+			mode_t			perm_mode;
+			unsigned long		qbytes;
+		} ipc;
+		struct {
+			mqd_t			mqdes;
+			struct mq_attr 		mqstat;
+		} mq_getsetattr;
+		struct {
+			mqd_t			mqdes;
+			int			sigev_signo;
+		} mq_notify;
+		struct {
+			mqd_t			mqdes;
+			size_t			msg_len;
+			unsigned int		msg_prio;
+			struct timespec		abs_timeout;
+		} mq_sendrecv;
+		struct {
+			int			oflag;
+			mode_t			mode;
+			struct mq_attr		attr;
+		} mq_open;
+		struct {
+			pid_t			pid;
+			struct audit_cap_data	cap;
+		} capset;
+	};
+	int fds[2];
+
 #if AUDIT_DEBUG
 	int		    put_count;
 	int		    ino_count;
@@ -608,19 +598,12 @@ static int audit_filter_rules(struct task_struct *tsk,
 					}
 				}
 				/* Find ipc objects that match */
-				if (ctx) {
-					struct audit_aux_data *aux;
-					for (aux = ctx->aux; aux;
-					     aux = aux->next) {
-						if (aux->type == AUDIT_IPC) {
-							struct audit_aux_data_ipcctl *axi = (void *)aux;
-							if (security_audit_rule_match(axi->osid, f->type, f->op, f->lsm_rule, ctx)) {
-								++result;
-								break;
-							}
-						}
-					}
-				}
+				if (!ctx || ctx->type != AUDIT_IPC)
+					break;
+				if (security_audit_rule_match(ctx->ipc.osid,
+							      f->type, f->op,
+							      f->lsm_rule, ctx))
+					++result;
 			}
 			break;
 		case AUDIT_ARG0:
@@ -647,8 +630,16 @@ static int audit_filter_rules(struct task_struct *tsk,
 			return 0;
 		}
 	}
-	if (rule->filterkey && ctx)
-		ctx->filterkey = kstrdup(rule->filterkey, GFP_ATOMIC);
+
+	if (ctx) {
+		if (rule->prio <= ctx->prio)
+			return 0;
+		if (rule->filterkey) {
+			kfree(ctx->filterkey);
+			ctx->filterkey = kstrdup(rule->filterkey, GFP_ATOMIC);
+		}
+		ctx->prio = rule->prio;
+	}
 	switch (rule->action) {
 	case AUDIT_NEVER:    *state = AUDIT_DISABLED;	    break;
 	case AUDIT_ALWAYS:   *state = AUDIT_RECORD_CONTEXT; break;
@@ -661,7 +652,7 @@ static int audit_filter_rules(struct task_struct *tsk,
  * completely disabled for this task.  Since we only have the task
  * structure at this point, we can only check uid and gid.
  */
-static enum audit_state audit_filter_task(struct task_struct *tsk)
+static enum audit_state audit_filter_task(struct task_struct *tsk, char **key)
 {
 	struct audit_entry *e;
 	enum audit_state   state;
@@ -669,6 +660,8 @@ static enum audit_state audit_filter_task(struct task_struct *tsk)
 	rcu_read_lock();
 	list_for_each_entry_rcu(e, &audit_filter_list[AUDIT_FILTER_TASK], list) {
 		if (audit_filter_rules(tsk, &e->rule, NULL, NULL, &state)) {
+			if (state == AUDIT_RECORD_CONTEXT)
+				*key = kstrdup(e->rule.filterkey, GFP_ATOMIC);
 			rcu_read_unlock();
 			return state;
 		}
@@ -702,6 +695,7 @@ static enum audit_state audit_filter_syscall(struct task_struct *tsk,
 			    audit_filter_rules(tsk, &e->rule, ctx, NULL,
 					       &state)) {
 				rcu_read_unlock();
+				ctx->current_state = state;
 				return state;
 			}
 		}
@@ -715,15 +709,14 @@ static enum audit_state audit_filter_syscall(struct task_struct *tsk,
  * buckets applicable to the inode numbers in audit_names[].
  * Regarding audit_state, same rules apply as for audit_filter_syscall().
  */
-enum audit_state audit_filter_inodes(struct task_struct *tsk,
-				     struct audit_context *ctx)
+void audit_filter_inodes(struct task_struct *tsk, struct audit_context *ctx)
 {
 	int i;
 	struct audit_entry *e;
 	enum audit_state state;
 
 	if (audit_pid && tsk->tgid == audit_pid)
-		return AUDIT_DISABLED;
+		return;
 
 	rcu_read_lock();
 	for (i = 0; i < ctx->name_count; i++) {
@@ -740,17 +733,20 @@ enum audit_state audit_filter_inodes(struct task_struct *tsk,
 			if ((e->rule.mask[word] & bit) == bit &&
 			    audit_filter_rules(tsk, &e->rule, ctx, n, &state)) {
 				rcu_read_unlock();
-				return state;
+				ctx->current_state = state;
+				return;
 			}
 		}
 	}
 	rcu_read_unlock();
-	return AUDIT_BUILD_CONTEXT;
 }
 
-void audit_set_auditable(struct audit_context *ctx)
+static void audit_set_auditable(struct audit_context *ctx)
 {
-	ctx->auditable = 1;
+	if (!ctx->prio) {
+		ctx->prio = 1;
+		ctx->current_state = AUDIT_RECORD_CONTEXT;
+	}
 }
 
 static inline struct audit_context *audit_get_context(struct task_struct *tsk,
@@ -781,23 +777,11 @@ static inline struct audit_context *audit_get_context(struct task_struct *tsk,
 	else
 		context->return_code  = return_code;
 
-	if (context->in_syscall && !context->dummy && !context->auditable) {
-		enum audit_state state;
-
-		state = audit_filter_syscall(tsk, context, &audit_filter_list[AUDIT_FILTER_EXIT]);
-		if (state == AUDIT_RECORD_CONTEXT) {
-			context->auditable = 1;
-			goto get_context;
-		}
-
-		state = audit_filter_inodes(tsk, context);
-		if (state == AUDIT_RECORD_CONTEXT)
-			context->auditable = 1;
-
+	if (context->in_syscall && !context->dummy) {
+		audit_filter_syscall(tsk, context, &audit_filter_list[AUDIT_FILTER_EXIT]);
+		audit_filter_inodes(tsk, context);
 	}
 
-get_context:
-
 	tsk->audit_context = NULL;
 	return context;
 }
@@ -807,8 +791,7 @@ static inline void audit_free_names(struct audit_context *context)
 	int i;
 
 #if AUDIT_DEBUG == 2
-	if (context->auditable
-	    ||context->put_count + context->ino_count != context->name_count) {
+	if (context->put_count + context->ino_count != context->name_count) {
 		printk(KERN_ERR "%s:%d(:%d): major=%d in_syscall=%d"
 		       " name_count=%d put_count=%d"
 		       " ino_count=%d [NOT freeing]\n",
@@ -859,6 +842,7 @@ static inline void audit_zero_context(struct audit_context *context,
 {
 	memset(context, 0, sizeof(*context));
 	context->state      = state;
+	context->prio = state == AUDIT_RECORD_CONTEXT ? ~0ULL : 0;
 }
 
 static inline struct audit_context *audit_alloc_context(enum audit_state state)
@@ -884,18 +868,21 @@ int audit_alloc(struct task_struct *tsk)
 {
 	struct audit_context *context;
 	enum audit_state     state;
+	char *key = NULL;
 
 	if (likely(!audit_ever_enabled))
 		return 0; /* Return if not auditing. */
 
-	state = audit_filter_task(tsk);
+	state = audit_filter_task(tsk, &key);
 	if (likely(state == AUDIT_DISABLED))
 		return 0;
 
 	if (!(context = audit_alloc_context(state))) {
+		kfree(key);
 		audit_log_lost("out of memory in audit_alloc");
 		return -ENOMEM;
 	}
+	context->filterkey = key;
 
 	tsk->audit_context  = context;
 	set_tsk_thread_flag(tsk, TIF_SYSCALL_AUDIT);
@@ -921,6 +908,7 @@ static inline void audit_free_context(struct audit_context *context)
 		free_tree_refs(context);
 		audit_free_aux(context);
 		kfree(context->filterkey);
+		kfree(context->sockaddr);
 		kfree(context);
 		context  = previous;
 	} while (context);
@@ -1230,6 +1218,97 @@ static void audit_log_fcaps(struct audit_buffer *ab, struct audit_names *name)
 		audit_log_format(ab, " cap_fe=%d cap_fver=%x", name->fcap.fE, name->fcap_ver);
 }
 
+static void show_special(struct audit_context *context, int *call_panic)
+{
+	struct audit_buffer *ab;
+	int i;
+
+	ab = audit_log_start(context, GFP_KERNEL, context->type);
+	if (!ab)
+		return;
+
+	switch (context->type) {
+	case AUDIT_SOCKETCALL: {
+		int nargs = context->socketcall.nargs;
+		audit_log_format(ab, "nargs=%d", nargs);
+		for (i = 0; i < nargs; i++)
+			audit_log_format(ab, " a%d=%lx", i,
+				context->socketcall.args[i]);
+		break; }
+	case AUDIT_IPC: {
+		u32 osid = context->ipc.osid;
+
+		audit_log_format(ab, "ouid=%u ogid=%u mode=%#o",
+			 context->ipc.uid, context->ipc.gid, context->ipc.mode);
+		if (osid) {
+			char *ctx = NULL;
+			u32 len;
+			if (security_secid_to_secctx(osid, &ctx, &len)) {
+				audit_log_format(ab, " osid=%u", osid);
+				*call_panic = 1;
+			} else {
+				audit_log_format(ab, " obj=%s", ctx);
+				security_release_secctx(ctx, len);
+			}
+		}
+		if (context->ipc.has_perm) {
+			audit_log_end(ab);
+			ab = audit_log_start(context, GFP_KERNEL,
+					     AUDIT_IPC_SET_PERM);
+			audit_log_format(ab,
+				"qbytes=%lx ouid=%u ogid=%u mode=%#o",
+				context->ipc.qbytes,
+				context->ipc.perm_uid,
+				context->ipc.perm_gid,
+				context->ipc.perm_mode);
+			if (!ab)
+				return;
+		}
+		break; }
+	case AUDIT_MQ_OPEN: {
+		audit_log_format(ab,
+			"oflag=0x%x mode=%#o mq_flags=0x%lx mq_maxmsg=%ld "
+			"mq_msgsize=%ld mq_curmsgs=%ld",
+			context->mq_open.oflag, context->mq_open.mode,
+			context->mq_open.attr.mq_flags,
+			context->mq_open.attr.mq_maxmsg,
+			context->mq_open.attr.mq_msgsize,
+			context->mq_open.attr.mq_curmsgs);
+		break; }
+	case AUDIT_MQ_SENDRECV: {
+		audit_log_format(ab,
+			"mqdes=%d msg_len=%zd msg_prio=%u "
+			"abs_timeout_sec=%ld abs_timeout_nsec=%ld",
+			context->mq_sendrecv.mqdes,
+			context->mq_sendrecv.msg_len,
+			context->mq_sendrecv.msg_prio,
+			context->mq_sendrecv.abs_timeout.tv_sec,
+			context->mq_sendrecv.abs_timeout.tv_nsec);
+		break; }
+	case AUDIT_MQ_NOTIFY: {
+		audit_log_format(ab, "mqdes=%d sigev_signo=%d",
+				context->mq_notify.mqdes,
+				context->mq_notify.sigev_signo);
+		break; }
+	case AUDIT_MQ_GETSETATTR: {
+		struct mq_attr *attr = &context->mq_getsetattr.mqstat;
+		audit_log_format(ab,
+			"mqdes=%d mq_flags=0x%lx mq_maxmsg=%ld mq_msgsize=%ld "
+			"mq_curmsgs=%ld ",
+			context->mq_getsetattr.mqdes,
+			attr->mq_flags, attr->mq_maxmsg,
+			attr->mq_msgsize, attr->mq_curmsgs);
+		break; }
+	case AUDIT_CAPSET: {
+		audit_log_format(ab, "pid=%d", context->capset.pid);
+		audit_log_cap(ab, "cap_pi", &context->capset.cap.inheritable);
+		audit_log_cap(ab, "cap_pp", &context->capset.cap.permitted);
+		audit_log_cap(ab, "cap_pe", &context->capset.cap.effective);
+		break; }
+	}
+	audit_log_end(ab);
+}
+
 static void audit_log_exit(struct audit_context *context, struct task_struct *tsk)
 {
 	const struct cred *cred;
@@ -1307,94 +1386,12 @@ static void audit_log_exit(struct audit_context *context, struct task_struct *ts
 			continue; /* audit_panic has been called */
 
 		switch (aux->type) {
-		case AUDIT_MQ_OPEN: {
-			struct audit_aux_data_mq_open *axi = (void *)aux;
-			audit_log_format(ab,
-				"oflag=0x%x mode=%#o mq_flags=0x%lx mq_maxmsg=%ld "
-				"mq_msgsize=%ld mq_curmsgs=%ld",
-				axi->oflag, axi->mode, axi->attr.mq_flags,
-				axi->attr.mq_maxmsg, axi->attr.mq_msgsize,
-				axi->attr.mq_curmsgs);
-			break; }
-
-		case AUDIT_MQ_SENDRECV: {
-			struct audit_aux_data_mq_sendrecv *axi = (void *)aux;
-			audit_log_format(ab,
-				"mqdes=%d msg_len=%zd msg_prio=%u "
-				"abs_timeout_sec=%ld abs_timeout_nsec=%ld",
-				axi->mqdes, axi->msg_len, axi->msg_prio,
-				axi->abs_timeout.tv_sec, axi->abs_timeout.tv_nsec);
-			break; }
-
-		case AUDIT_MQ_NOTIFY: {
-			struct audit_aux_data_mq_notify *axi = (void *)aux;
-			audit_log_format(ab,
-				"mqdes=%d sigev_signo=%d",
-				axi->mqdes,
-				axi->notification.sigev_signo);
-			break; }
-
-		case AUDIT_MQ_GETSETATTR: {
-			struct audit_aux_data_mq_getsetattr *axi = (void *)aux;
-			audit_log_format(ab,
-				"mqdes=%d mq_flags=0x%lx mq_maxmsg=%ld mq_msgsize=%ld "
-				"mq_curmsgs=%ld ",
-				axi->mqdes,
-				axi->mqstat.mq_flags, axi->mqstat.mq_maxmsg,
-				axi->mqstat.mq_msgsize, axi->mqstat.mq_curmsgs);
-			break; }
-
-		case AUDIT_IPC: {
-			struct audit_aux_data_ipcctl *axi = (void *)aux;
-			audit_log_format(ab, 
-				 "ouid=%u ogid=%u mode=%#o",
-				 axi->uid, axi->gid, axi->mode);
-			if (axi->osid != 0) {
-				char *ctx = NULL;
-				u32 len;
-				if (security_secid_to_secctx(
-						axi->osid, &ctx, &len)) {
-					audit_log_format(ab, " osid=%u",
-							axi->osid);
-					call_panic = 1;
-				} else {
-					audit_log_format(ab, " obj=%s", ctx);
-					security_release_secctx(ctx, len);
-				}
-			}
-			break; }
-
-		case AUDIT_IPC_SET_PERM: {
-			struct audit_aux_data_ipcctl *axi = (void *)aux;
-			audit_log_format(ab,
-				"qbytes=%lx ouid=%u ogid=%u mode=%#o",
-				axi->qbytes, axi->uid, axi->gid, axi->mode);
-			break; }
 
 		case AUDIT_EXECVE: {
 			struct audit_aux_data_execve *axi = (void *)aux;
 			audit_log_execve_info(context, &ab, axi);
 			break; }
 
-		case AUDIT_SOCKETCALL: {
-			struct audit_aux_data_socketcall *axs = (void *)aux;
-			audit_log_format(ab, "nargs=%d", axs->nargs);
-			for (i=0; i<axs->nargs; i++)
-				audit_log_format(ab, " a%d=%lx", i, axs->args[i]);
-			break; }
-
-		case AUDIT_SOCKADDR: {
-			struct audit_aux_data_sockaddr *axs = (void *)aux;
-
-			audit_log_format(ab, "saddr=");
-			audit_log_n_hex(ab, axs->a, axs->len);
-			break; }
-
-		case AUDIT_FD_PAIR: {
-			struct audit_aux_data_fd_pair *axs = (void *)aux;
-			audit_log_format(ab, "fd0=%d fd1=%d", axs->fd[0], axs->fd[1]);
-			break; }
-
 		case AUDIT_BPRM_FCAPS: {
 			struct audit_aux_data_bprm_fcaps *axs = (void *)aux;
 			audit_log_format(ab, "fver=%x", axs->fcap_ver);
@@ -1409,18 +1406,32 @@ static void audit_log_exit(struct audit_context *context, struct task_struct *ts
 			audit_log_cap(ab, "new_pe", &axs->new_pcap.effective);
 			break; }
 
-		case AUDIT_CAPSET: {
-			struct audit_aux_data_capset *axs = (void *)aux;
-			audit_log_format(ab, "pid=%d", axs->pid);
-			audit_log_cap(ab, "cap_pi", &axs->cap.inheritable);
-			audit_log_cap(ab, "cap_pp", &axs->cap.permitted);
-			audit_log_cap(ab, "cap_pe", &axs->cap.effective);
-			break; }
-
 		}
 		audit_log_end(ab);
 	}
 
+	if (context->type)
+		show_special(context, &call_panic);
+
+	if (context->fds[0] >= 0) {
+		ab = audit_log_start(context, GFP_KERNEL, AUDIT_FD_PAIR);
+		if (ab) {
+			audit_log_format(ab, "fd0=%d fd1=%d",
+					context->fds[0], context->fds[1]);
+			audit_log_end(ab);
+		}
+	}
+
+	if (context->sockaddr_len) {
+		ab = audit_log_start(context, GFP_KERNEL, AUDIT_SOCKADDR);
+		if (ab) {
+			audit_log_format(ab, "saddr=");
+			audit_log_n_hex(ab, (void *)context->sockaddr,
+					context->sockaddr_len);
+			audit_log_end(ab);
+		}
+	}
+
 	for (aux = context->aux_pids; aux; aux = aux->next) {
 		struct audit_aux_data_pids *axs = (void *)aux;
 
@@ -1536,7 +1547,7 @@ void audit_free(struct task_struct *tsk)
 	 * We use GFP_ATOMIC here because we might be doing this
 	 * in the context of the idle thread */
 	/* that can happen only if we are called from do_exit() */
-	if (context->in_syscall && context->auditable)
+	if (context->in_syscall && context->current_state == AUDIT_RECORD_CONTEXT)
 		audit_log_exit(context, tsk);
 
 	audit_free_context(context);
@@ -1620,15 +1631,17 @@ void audit_syscall_entry(int arch, int major,
 
 	state = context->state;
 	context->dummy = !audit_n_rules;
-	if (!context->dummy && (state == AUDIT_SETUP_CONTEXT || state == AUDIT_BUILD_CONTEXT))
+	if (!context->dummy && state == AUDIT_BUILD_CONTEXT) {
+		context->prio = 0;
 		state = audit_filter_syscall(tsk, context, &audit_filter_list[AUDIT_FILTER_ENTRY]);
+	}
 	if (likely(state == AUDIT_DISABLED))
 		return;
 
 	context->serial     = 0;
 	context->ctime      = CURRENT_TIME;
 	context->in_syscall = 1;
-	context->auditable  = !!(state == AUDIT_RECORD_CONTEXT);
+	context->current_state  = state;
 	context->ppid       = 0;
 }
 
@@ -1636,17 +1649,20 @@ void audit_finish_fork(struct task_struct *child)
 {
 	struct audit_context *ctx = current->audit_context;
 	struct audit_context *p = child->audit_context;
-	if (!p || !ctx || !ctx->auditable)
+	if (!p || !ctx)
+		return;
+	if (!ctx->in_syscall || ctx->current_state != AUDIT_RECORD_CONTEXT)
 		return;
 	p->arch = ctx->arch;
 	p->major = ctx->major;
 	memcpy(p->argv, ctx->argv, sizeof(ctx->argv));
 	p->ctime = ctx->ctime;
 	p->dummy = ctx->dummy;
-	p->auditable = ctx->auditable;
 	p->in_syscall = ctx->in_syscall;
 	p->filterkey = kstrdup(ctx->filterkey, GFP_KERNEL);
 	p->ppid = current->pid;
+	p->prio = ctx->prio;
+	p->current_state = ctx->current_state;
 }
 
 /**
@@ -1670,11 +1686,11 @@ void audit_syscall_exit(int valid, long return_code)
 	if (likely(!context))
 		return;
 
-	if (context->in_syscall && context->auditable)
+	if (context->in_syscall && context->current_state == AUDIT_RECORD_CONTEXT)
 		audit_log_exit(context, tsk);
 
 	context->in_syscall = 0;
-	context->auditable  = 0;
+	context->prio = context->state == AUDIT_RECORD_CONTEXT ? ~0ULL : 0;
 
 	if (context->previous) {
 		struct audit_context *new_context = context->previous;
@@ -1689,8 +1705,13 @@ void audit_syscall_exit(int valid, long return_code)
 		context->aux_pids = NULL;
 		context->target_pid = 0;
 		context->target_sid = 0;
-		kfree(context->filterkey);
-		context->filterkey = NULL;
+		context->sockaddr_len = 0;
+		context->type = 0;
+		context->fds[0] = -1;
+		if (context->state != AUDIT_RECORD_CONTEXT) {
+			kfree(context->filterkey);
+			context->filterkey = NULL;
+		}
 		tsk->audit_context = context;
 	}
 }
@@ -2081,7 +2102,10 @@ int auditsc_get_stamp(struct audit_context *ctx,
 	t->tv_sec  = ctx->ctime.tv_sec;
 	t->tv_nsec = ctx->ctime.tv_nsec;
 	*serial    = ctx->serial;
-	ctx->auditable = 1;
+	if (!ctx->prio) {
+		ctx->prio = 1;
+		ctx->current_state = AUDIT_RECORD_CONTEXT;
+	}
 	return 1;
 }
 
@@ -2127,132 +2151,46 @@ int audit_set_loginuid(struct task_struct *task, uid_t loginuid)
  * @mode: mode bits
  * @u_attr: queue attributes
  *
- * Returns 0 for success or NULL context or < 0 on error.
  */
-int __audit_mq_open(int oflag, mode_t mode, struct mq_attr __user *u_attr)
+void __audit_mq_open(int oflag, mode_t mode, struct mq_attr *attr)
 {
-	struct audit_aux_data_mq_open *ax;
 	struct audit_context *context = current->audit_context;
 
-	if (!audit_enabled)
-		return 0;
-
-	if (likely(!context))
-		return 0;
-
-	ax = kmalloc(sizeof(*ax), GFP_ATOMIC);
-	if (!ax)
-		return -ENOMEM;
-
-	if (u_attr != NULL) {
-		if (copy_from_user(&ax->attr, u_attr, sizeof(ax->attr))) {
-			kfree(ax);
-			return -EFAULT;
-		}
-	} else
-		memset(&ax->attr, 0, sizeof(ax->attr));
+	if (attr)
+		memcpy(&context->mq_open.attr, attr, sizeof(struct mq_attr));
+	else
+		memset(&context->mq_open.attr, 0, sizeof(struct mq_attr));
 
-	ax->oflag = oflag;
-	ax->mode = mode;
+	context->mq_open.oflag = oflag;
+	context->mq_open.mode = mode;
 
-	ax->d.type = AUDIT_MQ_OPEN;
-	ax->d.next = context->aux;
-	context->aux = (void *)ax;
-	return 0;
+	context->type = AUDIT_MQ_OPEN;
 }
 
 /**
- * __audit_mq_timedsend - record audit data for a POSIX MQ timed send
+ * __audit_mq_sendrecv - record audit data for a POSIX MQ timed send/receive
  * @mqdes: MQ descriptor
  * @msg_len: Message length
  * @msg_prio: Message priority
- * @u_abs_timeout: Message timeout in absolute time
+ * @abs_timeout: Message timeout in absolute time
  *
- * Returns 0 for success or NULL context or < 0 on error.
  */
-int __audit_mq_timedsend(mqd_t mqdes, size_t msg_len, unsigned int msg_prio,
-			const struct timespec __user *u_abs_timeout)
+void __audit_mq_sendrecv(mqd_t mqdes, size_t msg_len, unsigned int msg_prio,
+			const struct timespec *abs_timeout)
 {
-	struct audit_aux_data_mq_sendrecv *ax;
 	struct audit_context *context = current->audit_context;
+	struct timespec *p = &context->mq_sendrecv.abs_timeout;
 
-	if (!audit_enabled)
-		return 0;
-
-	if (likely(!context))
-		return 0;
-
-	ax = kmalloc(sizeof(*ax), GFP_ATOMIC);
-	if (!ax)
-		return -ENOMEM;
-
-	if (u_abs_timeout != NULL) {
-		if (copy_from_user(&ax->abs_timeout, u_abs_timeout, sizeof(ax->abs_timeout))) {
-			kfree(ax);
-			return -EFAULT;
-		}
-	} else
-		memset(&ax->abs_timeout, 0, sizeof(ax->abs_timeout));
-
-	ax->mqdes = mqdes;
-	ax->msg_len = msg_len;
-	ax->msg_prio = msg_prio;
-
-	ax->d.type = AUDIT_MQ_SENDRECV;
-	ax->d.next = context->aux;
-	context->aux = (void *)ax;
-	return 0;
-}
-
-/**
- * __audit_mq_timedreceive - record audit data for a POSIX MQ timed receive
- * @mqdes: MQ descriptor
- * @msg_len: Message length
- * @u_msg_prio: Message priority
- * @u_abs_timeout: Message timeout in absolute time
- *
- * Returns 0 for success or NULL context or < 0 on error.
- */
-int __audit_mq_timedreceive(mqd_t mqdes, size_t msg_len,
-				unsigned int __user *u_msg_prio,
-				const struct timespec __user *u_abs_timeout)
-{
-	struct audit_aux_data_mq_sendrecv *ax;
-	struct audit_context *context = current->audit_context;
-
-	if (!audit_enabled)
-		return 0;
-
-	if (likely(!context))
-		return 0;
-
-	ax = kmalloc(sizeof(*ax), GFP_ATOMIC);
-	if (!ax)
-		return -ENOMEM;
-
-	if (u_msg_prio != NULL) {
-		if (get_user(ax->msg_prio, u_msg_prio)) {
-			kfree(ax);
-			return -EFAULT;
-		}
-	} else
-		ax->msg_prio = 0;
-
-	if (u_abs_timeout != NULL) {
-		if (copy_from_user(&ax->abs_timeout, u_abs_timeout, sizeof(ax->abs_timeout))) {
-			kfree(ax);
-			return -EFAULT;
-		}
-	} else
-		memset(&ax->abs_timeout, 0, sizeof(ax->abs_timeout));
+	if (abs_timeout)
+		memcpy(p, abs_timeout, sizeof(struct timespec));
+	else
+		memset(p, 0, sizeof(struct timespec));
 
-	ax->mqdes = mqdes;
-	ax->msg_len = msg_len;
+	context->mq_sendrecv.mqdes = mqdes;
+	context->mq_sendrecv.msg_len = msg_len;
+	context->mq_sendrecv.msg_prio = msg_prio;
 
-	ax->d.type = AUDIT_MQ_SENDRECV;
-	ax->d.next = context->aux;
-	context->aux = (void *)ax;
-	return 0;
+	context->type = AUDIT_MQ_SENDRECV;
 }
 
 /**
@@ -2260,38 +2198,19 @@ int __audit_mq_timedreceive(mqd_t mqdes, size_t msg_len,
  * @mqdes: MQ descriptor
  * @u_notification: Notification event
  *
- * Returns 0 for success or NULL context or < 0 on error.
  */
 
-int __audit_mq_notify(mqd_t mqdes, const struct sigevent __user *u_notification)
+void __audit_mq_notify(mqd_t mqdes, const struct sigevent *notification)
 {
-	struct audit_aux_data_mq_notify *ax;
 	struct audit_context *context = current->audit_context;
 
-	if (!audit_enabled)
-		return 0;
-
-	if (likely(!context))
-		return 0;
-
-	ax = kmalloc(sizeof(*ax), GFP_ATOMIC);
-	if (!ax)
-		return -ENOMEM;
-
-	if (u_notification != NULL) {
-		if (copy_from_user(&ax->notification, u_notification, sizeof(ax->notification))) {
-			kfree(ax);
-			return -EFAULT;
-		}
-	} else
-		memset(&ax->notification, 0, sizeof(ax->notification));
-
-	ax->mqdes = mqdes;
+	if (notification)
+		context->mq_notify.sigev_signo = notification->sigev_signo;
+	else
+		context->mq_notify.sigev_signo = 0;
 
-	ax->d.type = AUDIT_MQ_NOTIFY;
-	ax->d.next = context->aux;
-	context->aux = (void *)ax;
-	return 0;
+	context->mq_notify.mqdes = mqdes;
+	context->type = AUDIT_MQ_NOTIFY;
 }
 
 /**
@@ -2299,55 +2218,29 @@ int __audit_mq_notify(mqd_t mqdes, const struct sigevent __user *u_notification)
  * @mqdes: MQ descriptor
  * @mqstat: MQ flags
  *
- * Returns 0 for success or NULL context or < 0 on error.
  */
-int __audit_mq_getsetattr(mqd_t mqdes, struct mq_attr *mqstat)
+void __audit_mq_getsetattr(mqd_t mqdes, struct mq_attr *mqstat)
 {
-	struct audit_aux_data_mq_getsetattr *ax;
 	struct audit_context *context = current->audit_context;
-
-	if (!audit_enabled)
-		return 0;
-
-	if (likely(!context))
-		return 0;
-
-	ax = kmalloc(sizeof(*ax), GFP_ATOMIC);
-	if (!ax)
-		return -ENOMEM;
-
-	ax->mqdes = mqdes;
-	ax->mqstat = *mqstat;
-
-	ax->d.type = AUDIT_MQ_GETSETATTR;
-	ax->d.next = context->aux;
-	context->aux = (void *)ax;
-	return 0;
+	context->mq_getsetattr.mqdes = mqdes;
+	context->mq_getsetattr.mqstat = *mqstat;
+	context->type = AUDIT_MQ_GETSETATTR;
 }
 
 /**
  * audit_ipc_obj - record audit data for ipc object
  * @ipcp: ipc permissions
  *
- * Returns 0 for success or NULL context or < 0 on error.
  */
-int __audit_ipc_obj(struct kern_ipc_perm *ipcp)
+void __audit_ipc_obj(struct kern_ipc_perm *ipcp)
 {
-	struct audit_aux_data_ipcctl *ax;
 	struct audit_context *context = current->audit_context;
-
-	ax = kmalloc(sizeof(*ax), GFP_ATOMIC);
-	if (!ax)
-		return -ENOMEM;
-
-	ax->uid = ipcp->uid;
-	ax->gid = ipcp->gid;
-	ax->mode = ipcp->mode;
-	security_ipc_getsecid(ipcp, &ax->osid);
-	ax->d.type = AUDIT_IPC;
-	ax->d.next = context->aux;
-	context->aux = (void *)ax;
-	return 0;
+	context->ipc.uid = ipcp->uid;
+	context->ipc.gid = ipcp->gid;
+	context->ipc.mode = ipcp->mode;
+	context->ipc.has_perm = 0;
+	security_ipc_getsecid(ipcp, &context->ipc.osid);
+	context->type = AUDIT_IPC;
 }
 
 /**
@@ -2357,26 +2250,17 @@ int __audit_ipc_obj(struct kern_ipc_perm *ipcp)
  * @gid: msgq group id
  * @mode: msgq mode (permissions)
  *
- * Returns 0 for success or NULL context or < 0 on error.
+ * Called only after audit_ipc_obj().
  */
-int __audit_ipc_set_perm(unsigned long qbytes, uid_t uid, gid_t gid, mode_t mode)
+void __audit_ipc_set_perm(unsigned long qbytes, uid_t uid, gid_t gid, mode_t mode)
 {
-	struct audit_aux_data_ipcctl *ax;
 	struct audit_context *context = current->audit_context;
 
-	ax = kmalloc(sizeof(*ax), GFP_ATOMIC);
-	if (!ax)
-		return -ENOMEM;
-
-	ax->qbytes = qbytes;
-	ax->uid = uid;
-	ax->gid = gid;
-	ax->mode = mode;
-
-	ax->d.type = AUDIT_IPC_SET_PERM;
-	ax->d.next = context->aux;
-	context->aux = (void *)ax;
-	return 0;
+	context->ipc.qbytes = qbytes;
+	context->ipc.perm_uid = uid;
+	context->ipc.perm_gid = gid;
+	context->ipc.perm_mode = mode;
+	context->ipc.has_perm = 1;
 }
 
 int audit_bprm(struct linux_binprm *bprm)
@@ -2406,27 +2290,17 @@ int audit_bprm(struct linux_binprm *bprm)
  * @nargs: number of args
  * @args: args array
  *
- * Returns 0 for success or NULL context or < 0 on error.
  */
-int audit_socketcall(int nargs, unsigned long *args)
+void audit_socketcall(int nargs, unsigned long *args)
 {
-	struct audit_aux_data_socketcall *ax;
 	struct audit_context *context = current->audit_context;
 
 	if (likely(!context || context->dummy))
-		return 0;
-
-	ax = kmalloc(sizeof(*ax) + nargs * sizeof(unsigned long), GFP_KERNEL);
-	if (!ax)
-		return -ENOMEM;
-
-	ax->nargs = nargs;
-	memcpy(ax->args, args, nargs * sizeof(unsigned long));
+		return;
 
-	ax->d.type = AUDIT_SOCKETCALL;
-	ax->d.next = context->aux;
-	context->aux = (void *)ax;
-	return 0;
+	context->type = AUDIT_SOCKETCALL;
+	context->socketcall.nargs = nargs;
+	memcpy(context->socketcall.args, args, nargs * sizeof(unsigned long));
 }
 
 /**
@@ -2434,29 +2308,12 @@ int audit_socketcall(int nargs, unsigned long *args)
  * @fd1: the first file descriptor
  * @fd2: the second file descriptor
  *
- * Returns 0 for success or NULL context or < 0 on error.
  */
-int __audit_fd_pair(int fd1, int fd2)
+void __audit_fd_pair(int fd1, int fd2)
 {
 	struct audit_context *context = current->audit_context;
-	struct audit_aux_data_fd_pair *ax;
-
-	if (likely(!context)) {
-		return 0;
-	}
-
-	ax = kmalloc(sizeof(*ax), GFP_KERNEL);
-	if (!ax) {
-		return -ENOMEM;
-	}
-
-	ax->fd[0] = fd1;
-	ax->fd[1] = fd2;
-
-	ax->d.type = AUDIT_FD_PAIR;
-	ax->d.next = context->aux;
-	context->aux = (void *)ax;
-	return 0;
+	context->fds[0] = fd1;
+	context->fds[1] = fd2;
 }
 
 /**
@@ -2468,22 +2325,20 @@ int __audit_fd_pair(int fd1, int fd2)
  */
 int audit_sockaddr(int len, void *a)
 {
-	struct audit_aux_data_sockaddr *ax;
 	struct audit_context *context = current->audit_context;
 
 	if (likely(!context || context->dummy))
 		return 0;
 
-	ax = kmalloc(sizeof(*ax) + len, GFP_KERNEL);
-	if (!ax)
-		return -ENOMEM;
-
-	ax->len = len;
-	memcpy(ax->a, a, len);
+	if (!context->sockaddr) {
+		void *p = kmalloc(sizeof(struct sockaddr_storage), GFP_KERNEL);
+		if (!p)
+			return -ENOMEM;
+		context->sockaddr = p;
+	}
 
-	ax->d.type = AUDIT_SOCKADDR;
-	ax->d.next = context->aux;
-	context->aux = (void *)ax;
+	context->sockaddr_len = len;
+	memcpy(context->sockaddr, a, len);
 	return 0;
 }
 
@@ -2617,29 +2472,15 @@ int __audit_log_bprm_fcaps(struct linux_binprm *bprm,
  * Record the aguments userspace sent to sys_capset for later printing by the
  * audit system if applicable
  */
-int __audit_log_capset(pid_t pid,
+void __audit_log_capset(pid_t pid,
 		       const struct cred *new, const struct cred *old)
 {
-	struct audit_aux_data_capset *ax;
 	struct audit_context *context = current->audit_context;
-
-	if (likely(!audit_enabled || !context || context->dummy))
-		return 0;
-
-	ax = kmalloc(sizeof(*ax), GFP_KERNEL);
-	if (!ax)
-		return -ENOMEM;
-
-	ax->d.type = AUDIT_CAPSET;
-	ax->d.next = context->aux;
-	context->aux = (void *)ax;
-
-	ax->pid = pid;
-	ax->cap.effective   = new->cap_effective;
-	ax->cap.inheritable = new->cap_effective;
-	ax->cap.permitted   = new->cap_permitted;
-
-	return 0;
+	context->capset.pid = pid;
+	context->capset.cap.effective   = new->cap_effective;
+	context->capset.cap.inheritable = new->cap_effective;
+	context->capset.cap.permitted   = new->cap_permitted;
+	context->type = AUDIT_CAPSET;
 }
 
 /**
diff --git a/kernel/capability.c b/kernel/capability.c
index 36b4b4daebec..688926e496be 100644
--- a/kernel/capability.c
+++ b/kernel/capability.c
@@ -280,9 +280,7 @@ asmlinkage long sys_capset(cap_user_header_t header, const cap_user_data_t data)
 	if (ret < 0)
 		goto error;
 
-	ret = audit_log_capset(pid, new, current_cred());
-	if (ret < 0)
-		return ret;
+	audit_log_capset(pid, new, current_cred());
 
 	return commit_creds(new);
 
@@ -308,7 +306,7 @@ int capable(int cap)
 		BUG();
 	}
 
-	if (has_capability(current, cap)) {
+	if (security_capable(cap) == 0) {
 		current->flags |= PF_SUPERPRIV;
 		return 1;
 	}
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 48348dde6d81..c29831076e7a 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -84,7 +84,7 @@ struct cgroupfs_root {
 	/* Tracks how many cgroups are currently defined in hierarchy.*/
 	int number_of_cgroups;
 
-	/* A list running through the mounted hierarchies */
+	/* A list running through the active hierarchies */
 	struct list_head root_list;
 
 	/* Hierarchy-specific flags */
@@ -116,7 +116,6 @@ static int root_count;
  * be called.
  */
 static int need_forkexit_callback __read_mostly;
-static int need_mm_owner_callback __read_mostly;
 
 /* convenient tests for these bits */
 inline int cgroup_is_removed(const struct cgroup *cgrp)
@@ -149,8 +148,8 @@ static int notify_on_release(const struct cgroup *cgrp)
 #define for_each_subsys(_root, _ss) \
 list_for_each_entry(_ss, &_root->subsys_list, sibling)
 
-/* for_each_root() allows you to iterate across the active hierarchies */
-#define for_each_root(_root) \
+/* for_each_active_root() allows you to iterate across the active hierarchies */
+#define for_each_active_root(_root) \
 list_for_each_entry(_root, &roots, root_list)
 
 /* the list of cgroups eligible for automatic release. Protected by
@@ -272,7 +271,7 @@ static void __put_css_set(struct css_set *cg, int taskexit)
 
 	rcu_read_lock();
 	for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
-		struct cgroup *cgrp = cg->subsys[i]->cgroup;
+		struct cgroup *cgrp = rcu_dereference(cg->subsys[i]->cgroup);
 		if (atomic_dec_and_test(&cgrp->count) &&
 		    notify_on_release(cgrp)) {
 			if (taskexit)
@@ -385,6 +384,25 @@ static int allocate_cg_links(int count, struct list_head *tmp)
 	return 0;
 }
 
+/**
+ * link_css_set - a helper function to link a css_set to a cgroup
+ * @tmp_cg_links: cg_cgroup_link objects allocated by allocate_cg_links()
+ * @cg: the css_set to be linked
+ * @cgrp: the destination cgroup
+ */
+static void link_css_set(struct list_head *tmp_cg_links,
+			 struct css_set *cg, struct cgroup *cgrp)
+{
+	struct cg_cgroup_link *link;
+
+	BUG_ON(list_empty(tmp_cg_links));
+	link = list_first_entry(tmp_cg_links, struct cg_cgroup_link,
+				cgrp_link_list);
+	link->cg = cg;
+	list_move(&link->cgrp_link_list, &cgrp->css_sets);
+	list_add(&link->cg_link_list, &cg->cg_links);
+}
+
 /*
  * find_css_set() takes an existing cgroup group and a
  * cgroup object, and returns a css_set object that's
@@ -400,7 +418,6 @@ static struct css_set *find_css_set(
 	int i;
 
 	struct list_head tmp_cg_links;
-	struct cg_cgroup_link *link;
 
 	struct hlist_head *hhead;
 
@@ -445,26 +462,11 @@ static struct css_set *find_css_set(
 		 * only do it for the first subsystem in each
 		 * hierarchy
 		 */
-		if (ss->root->subsys_list.next == &ss->sibling) {
-			BUG_ON(list_empty(&tmp_cg_links));
-			link = list_entry(tmp_cg_links.next,
-					  struct cg_cgroup_link,
-					  cgrp_link_list);
-			list_del(&link->cgrp_link_list);
-			list_add(&link->cgrp_link_list, &cgrp->css_sets);
-			link->cg = res;
-			list_add(&link->cg_link_list, &res->cg_links);
-		}
-	}
-	if (list_empty(&rootnode.subsys_list)) {
-		link = list_entry(tmp_cg_links.next,
-				  struct cg_cgroup_link,
-				  cgrp_link_list);
-		list_del(&link->cgrp_link_list);
-		list_add(&link->cgrp_link_list, &dummytop->css_sets);
-		link->cg = res;
-		list_add(&link->cg_link_list, &res->cg_links);
+		if (ss->root->subsys_list.next == &ss->sibling)
+			link_css_set(&tmp_cg_links, res, cgrp);
 	}
+	if (list_empty(&rootnode.subsys_list))
+		link_css_set(&tmp_cg_links, res, dummytop);
 
 	BUG_ON(!list_empty(&tmp_cg_links));
 
@@ -573,7 +575,6 @@ static struct inode *cgroup_new_inode(mode_t mode, struct super_block *sb)
 		inode->i_mode = mode;
 		inode->i_uid = current_fsuid();
 		inode->i_gid = current_fsgid();
-		inode->i_blocks = 0;
 		inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
 		inode->i_mapping->backing_dev_info = &cgroup_backing_dev_info;
 	}
@@ -588,11 +589,18 @@ static void cgroup_call_pre_destroy(struct cgroup *cgrp)
 {
 	struct cgroup_subsys *ss;
 	for_each_subsys(cgrp->root, ss)
-		if (ss->pre_destroy && cgrp->subsys[ss->subsys_id])
+		if (ss->pre_destroy)
 			ss->pre_destroy(ss, cgrp);
 	return;
 }
 
+static void free_cgroup_rcu(struct rcu_head *obj)
+{
+	struct cgroup *cgrp = container_of(obj, struct cgroup, rcu_head);
+
+	kfree(cgrp);
+}
+
 static void cgroup_diput(struct dentry *dentry, struct inode *inode)
 {
 	/* is dentry a directory ? if so, kfree() associated cgroup */
@@ -612,19 +620,19 @@ static void cgroup_diput(struct dentry *dentry, struct inode *inode)
 		/*
 		 * Release the subsystem state objects.
 		 */
-		for_each_subsys(cgrp->root, ss) {
-			if (cgrp->subsys[ss->subsys_id])
-				ss->destroy(ss, cgrp);
-		}
+		for_each_subsys(cgrp->root, ss)
+			ss->destroy(ss, cgrp);
 
 		cgrp->root->number_of_cgroups--;
 		mutex_unlock(&cgroup_mutex);
 
-		/* Drop the active superblock reference that we took when we
-		 * created the cgroup */
+		/*
+		 * Drop the active superblock reference that we took when we
+		 * created the cgroup
+		 */
 		deactivate_super(cgrp->root->sb);
 
-		kfree(cgrp);
+		call_rcu(&cgrp->rcu_head, free_cgroup_rcu);
 	}
 	iput(inode);
 }
@@ -714,23 +722,26 @@ static int rebind_subsystems(struct cgroupfs_root *root,
 			BUG_ON(cgrp->subsys[i]);
 			BUG_ON(!dummytop->subsys[i]);
 			BUG_ON(dummytop->subsys[i]->cgroup != dummytop);
+			mutex_lock(&ss->hierarchy_mutex);
 			cgrp->subsys[i] = dummytop->subsys[i];
 			cgrp->subsys[i]->cgroup = cgrp;
-			list_add(&ss->sibling, &root->subsys_list);
-			rcu_assign_pointer(ss->root, root);
+			list_move(&ss->sibling, &root->subsys_list);
+			ss->root = root;
 			if (ss->bind)
 				ss->bind(ss, cgrp);
-
+			mutex_unlock(&ss->hierarchy_mutex);
 		} else if (bit & removed_bits) {
 			/* We're removing this subsystem */
 			BUG_ON(cgrp->subsys[i] != dummytop->subsys[i]);
 			BUG_ON(cgrp->subsys[i]->cgroup != cgrp);
+			mutex_lock(&ss->hierarchy_mutex);
 			if (ss->bind)
 				ss->bind(ss, dummytop);
 			dummytop->subsys[i]->cgroup = dummytop;
 			cgrp->subsys[i] = NULL;
-			rcu_assign_pointer(subsys[i]->root, &rootnode);
-			list_del(&ss->sibling);
+			subsys[i]->root = &rootnode;
+			list_move(&ss->sibling, &rootnode.subsys_list);
+			mutex_unlock(&ss->hierarchy_mutex);
 		} else if (bit & final_bits) {
 			/* Subsystem state should already exist */
 			BUG_ON(!cgrp->subsys[i]);
@@ -992,7 +1003,7 @@ static int cgroup_get_sb(struct file_system_type *fs_type,
 		root = NULL;
 	} else {
 		/* New superblock */
-		struct cgroup *cgrp = &root->top_cgroup;
+		struct cgroup *root_cgrp = &root->top_cgroup;
 		struct inode *inode;
 		int i;
 
@@ -1033,7 +1044,7 @@ static int cgroup_get_sb(struct file_system_type *fs_type,
 		list_add(&root->root_list, &roots);
 		root_count++;
 
-		sb->s_root->d_fsdata = &root->top_cgroup;
+		sb->s_root->d_fsdata = root_cgrp;
 		root->top_cgroup.dentry = sb->s_root;
 
 		/* Link the top cgroup in this hierarchy into all
@@ -1044,29 +1055,18 @@ static int cgroup_get_sb(struct file_system_type *fs_type,
 			struct hlist_node *node;
 			struct css_set *cg;
 
-			hlist_for_each_entry(cg, node, hhead, hlist) {
-				struct cg_cgroup_link *link;
-
-				BUG_ON(list_empty(&tmp_cg_links));
-				link = list_entry(tmp_cg_links.next,
-						  struct cg_cgroup_link,
-						  cgrp_link_list);
-				list_del(&link->cgrp_link_list);
-				link->cg = cg;
-				list_add(&link->cgrp_link_list,
-					 &root->top_cgroup.css_sets);
-				list_add(&link->cg_link_list, &cg->cg_links);
-			}
+			hlist_for_each_entry(cg, node, hhead, hlist)
+				link_css_set(&tmp_cg_links, cg, root_cgrp);
 		}
 		write_unlock(&css_set_lock);
 
 		free_cg_links(&tmp_cg_links);
 
-		BUG_ON(!list_empty(&cgrp->sibling));
-		BUG_ON(!list_empty(&cgrp->children));
+		BUG_ON(!list_empty(&root_cgrp->sibling));
+		BUG_ON(!list_empty(&root_cgrp->children));
 		BUG_ON(root->number_of_cgroups != 1);
 
-		cgroup_populate_dir(cgrp);
+		cgroup_populate_dir(root_cgrp);
 		mutex_unlock(&inode->i_mutex);
 		mutex_unlock(&cgroup_mutex);
 	}
@@ -1115,10 +1115,9 @@ static void cgroup_kill_sb(struct super_block *sb) {
 	}
 	write_unlock(&css_set_lock);
 
-	if (!list_empty(&root->root_list)) {
-		list_del(&root->root_list);
-		root_count--;
-	}
+	list_del(&root->root_list);
+	root_count--;
+
 	mutex_unlock(&cgroup_mutex);
 
 	kfree(root);
@@ -1147,14 +1146,16 @@ static inline struct cftype *__d_cft(struct dentry *dentry)
  * @buf: the buffer to write the path into
  * @buflen: the length of the buffer
  *
- * Called with cgroup_mutex held. Writes path of cgroup into buf.
- * Returns 0 on success, -errno on error.
+ * Called with cgroup_mutex held or else with an RCU-protected cgroup
+ * reference.  Writes path of cgroup into buf.  Returns 0 on success,
+ * -errno on error.
  */
 int cgroup_path(const struct cgroup *cgrp, char *buf, int buflen)
 {
 	char *start;
+	struct dentry *dentry = rcu_dereference(cgrp->dentry);
 
-	if (cgrp == dummytop) {
+	if (!dentry || cgrp == dummytop) {
 		/*
 		 * Inactive subsystems have no dentry for their root
 		 * cgroup
@@ -1167,13 +1168,14 @@ int cgroup_path(const struct cgroup *cgrp, char *buf, int buflen)
 
 	*--start = '\0';
 	for (;;) {
-		int len = cgrp->dentry->d_name.len;
+		int len = dentry->d_name.len;
 		if ((start -= len) < buf)
 			return -ENAMETOOLONG;
 		memcpy(start, cgrp->dentry->d_name.name, len);
 		cgrp = cgrp->parent;
 		if (!cgrp)
 			break;
+		dentry = rcu_dereference(cgrp->dentry);
 		if (!cgrp->parent)
 			continue;
 		if (--start < buf)
@@ -1218,7 +1220,7 @@ int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk)
 	int retval = 0;
 	struct cgroup_subsys *ss;
 	struct cgroup *oldcgrp;
-	struct css_set *cg = tsk->cgroups;
+	struct css_set *cg;
 	struct css_set *newcg;
 	struct cgroupfs_root *root = cgrp->root;
 	int subsys_id;
@@ -1238,11 +1240,16 @@ int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk)
 		}
 	}
 
+	task_lock(tsk);
+	cg = tsk->cgroups;
+	get_css_set(cg);
+	task_unlock(tsk);
 	/*
 	 * Locate or allocate a new css_set for this task,
 	 * based on its final set of cgroups
 	 */
 	newcg = find_css_set(cg, cgrp);
+	put_css_set(cg);
 	if (!newcg)
 		return -ENOMEM;
 
@@ -1447,7 +1454,7 @@ static ssize_t cgroup_file_write(struct file *file, const char __user *buf,
 	struct cftype *cft = __d_cft(file->f_dentry);
 	struct cgroup *cgrp = __d_cgrp(file->f_dentry->d_parent);
 
-	if (!cft || cgroup_is_removed(cgrp))
+	if (cgroup_is_removed(cgrp))
 		return -ENODEV;
 	if (cft->write)
 		return cft->write(cgrp, cft, file, buf, nbytes, ppos);
@@ -1492,7 +1499,7 @@ static ssize_t cgroup_file_read(struct file *file, char __user *buf,
 	struct cftype *cft = __d_cft(file->f_dentry);
 	struct cgroup *cgrp = __d_cgrp(file->f_dentry->d_parent);
 
-	if (!cft || cgroup_is_removed(cgrp))
+	if (cgroup_is_removed(cgrp))
 		return -ENODEV;
 
 	if (cft->read)
@@ -1556,10 +1563,8 @@ static int cgroup_file_open(struct inode *inode, struct file *file)
 	err = generic_file_open(inode, file);
 	if (err)
 		return err;
-
 	cft = __d_cft(file->f_dentry);
-	if (!cft)
-		return -ENODEV;
+
 	if (cft->read_map || cft->read_seq_string) {
 		struct cgroup_seqfile_state *state =
 			kzalloc(sizeof(*state), GFP_USER);
@@ -1673,7 +1678,7 @@ static int cgroup_create_dir(struct cgroup *cgrp, struct dentry *dentry,
 	if (!error) {
 		dentry->d_fsdata = cgrp;
 		inc_nlink(parent->d_inode);
-		cgrp->dentry = dentry;
+		rcu_assign_pointer(cgrp->dentry, dentry);
 		dget(dentry);
 	}
 	dput(dentry);
@@ -1814,6 +1819,7 @@ struct task_struct *cgroup_iter_next(struct cgroup *cgrp,
 {
 	struct task_struct *res;
 	struct list_head *l = it->task;
+	struct cg_cgroup_link *link;
 
 	/* If the iterator cg is NULL, we have no tasks */
 	if (!it->cg_link)
@@ -1821,7 +1827,8 @@ struct task_struct *cgroup_iter_next(struct cgroup *cgrp,
 	res = list_entry(l, struct task_struct, cg_list);
 	/* Advance iterator to find next entry */
 	l = l->next;
-	if (l == &res->cgroups->tasks) {
+	link = list_entry(it->cg_link, struct cg_cgroup_link, cgrp_link_list);
+	if (l == &link->cg->tasks) {
 		/* We reached the end of this task list - move on to
 		 * the next cg_cgroup_link */
 		cgroup_advance_iter(cgrp, it);
@@ -2015,14 +2022,16 @@ int cgroup_scan_tasks(struct cgroup_scanner *scan)
  */
 static int pid_array_load(pid_t *pidarray, int npids, struct cgroup *cgrp)
 {
-	int n = 0;
+	int n = 0, pid;
 	struct cgroup_iter it;
 	struct task_struct *tsk;
 	cgroup_iter_start(cgrp, &it);
 	while ((tsk = cgroup_iter_next(cgrp, &it))) {
 		if (unlikely(n == npids))
 			break;
-		pidarray[n++] = task_pid_vnr(tsk);
+		pid = task_pid_vnr(tsk);
+		if (pid > 0)
+			pidarray[n++] = pid;
 	}
 	cgroup_iter_end(cgrp, &it);
 	return n;
@@ -2054,7 +2063,6 @@ int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry)
 
 	ret = 0;
 	cgrp = dentry->d_fsdata;
-	rcu_read_lock();
 
 	cgroup_iter_start(cgrp, &it);
 	while ((tsk = cgroup_iter_next(cgrp, &it))) {
@@ -2079,7 +2087,6 @@ int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry)
 	}
 	cgroup_iter_end(cgrp, &it);
 
-	rcu_read_unlock();
 err:
 	return ret;
 }
@@ -2326,7 +2333,7 @@ static void init_cgroup_css(struct cgroup_subsys_state *css,
 			       struct cgroup *cgrp)
 {
 	css->cgroup = cgrp;
-	atomic_set(&css->refcnt, 0);
+	atomic_set(&css->refcnt, 1);
 	css->flags = 0;
 	if (cgrp == dummytop)
 		set_bit(CSS_ROOT, &css->flags);
@@ -2334,6 +2341,29 @@ static void init_cgroup_css(struct cgroup_subsys_state *css,
 	cgrp->subsys[ss->subsys_id] = css;
 }
 
+static void cgroup_lock_hierarchy(struct cgroupfs_root *root)
+{
+	/* We need to take each hierarchy_mutex in a consistent order */
+	int i;
+
+	for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
+		struct cgroup_subsys *ss = subsys[i];
+		if (ss->root == root)
+			mutex_lock_nested(&ss->hierarchy_mutex, i);
+	}
+}
+
+static void cgroup_unlock_hierarchy(struct cgroupfs_root *root)
+{
+	int i;
+
+	for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
+		struct cgroup_subsys *ss = subsys[i];
+		if (ss->root == root)
+			mutex_unlock(&ss->hierarchy_mutex);
+	}
+}
+
 /*
  * cgroup_create - create a cgroup
  * @parent: cgroup that will be parent of the new cgroup
@@ -2382,7 +2412,9 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
 		init_cgroup_css(css, ss, cgrp);
 	}
 
+	cgroup_lock_hierarchy(root);
 	list_add(&cgrp->sibling, &cgrp->parent->children);
+	cgroup_unlock_hierarchy(root);
 	root->number_of_cgroups++;
 
 	err = cgroup_create_dir(cgrp, dentry, mode);
@@ -2433,7 +2465,7 @@ static int cgroup_has_css_refs(struct cgroup *cgrp)
 {
 	/* Check the reference count on each subsystem. Since we
 	 * already established that there are no tasks in the
-	 * cgroup, if the css refcount is also 0, then there should
+	 * cgroup, if the css refcount is also 1, then there should
 	 * be no outstanding references, so the subsystem is safe to
 	 * destroy. We scan across all subsystems rather than using
 	 * the per-hierarchy linked list of mounted subsystems since
@@ -2454,19 +2486,67 @@ static int cgroup_has_css_refs(struct cgroup *cgrp)
 		 * matter, since it can only happen if the cgroup
 		 * has been deleted and hence no longer needs the
 		 * release agent to be called anyway. */
-		if (css && atomic_read(&css->refcnt))
+		if (css && (atomic_read(&css->refcnt) > 1))
 			return 1;
 	}
 	return 0;
 }
 
+/*
+ * Atomically mark all (or else none) of the cgroup's CSS objects as
+ * CSS_REMOVED. Return true on success, or false if the cgroup has
+ * busy subsystems. Call with cgroup_mutex held
+ */
+
+static int cgroup_clear_css_refs(struct cgroup *cgrp)
+{
+	struct cgroup_subsys *ss;
+	unsigned long flags;
+	bool failed = false;
+	local_irq_save(flags);
+	for_each_subsys(cgrp->root, ss) {
+		struct cgroup_subsys_state *css = cgrp->subsys[ss->subsys_id];
+		int refcnt;
+		do {
+			/* We can only remove a CSS with a refcnt==1 */
+			refcnt = atomic_read(&css->refcnt);
+			if (refcnt > 1) {
+				failed = true;
+				goto done;
+			}
+			BUG_ON(!refcnt);
+			/*
+			 * Drop the refcnt to 0 while we check other
+			 * subsystems. This will cause any racing
+			 * css_tryget() to spin until we set the
+			 * CSS_REMOVED bits or abort
+			 */
+		} while (atomic_cmpxchg(&css->refcnt, refcnt, 0) != refcnt);
+	}
+ done:
+	for_each_subsys(cgrp->root, ss) {
+		struct cgroup_subsys_state *css = cgrp->subsys[ss->subsys_id];
+		if (failed) {
+			/*
+			 * Restore old refcnt if we previously managed
+			 * to clear it from 1 to 0
+			 */
+			if (!atomic_read(&css->refcnt))
+				atomic_set(&css->refcnt, 1);
+		} else {
+			/* Commit the fact that the CSS is removed */
+			set_bit(CSS_REMOVED, &css->flags);
+		}
+	}
+	local_irq_restore(flags);
+	return !failed;
+}
+
 static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry)
 {
 	struct cgroup *cgrp = dentry->d_fsdata;
 	struct dentry *d;
 	struct cgroup *parent;
-	struct super_block *sb;
-	struct cgroupfs_root *root;
 
 	/* the vfs holds both inode->i_mutex already */
 
@@ -2489,12 +2569,10 @@ static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry)
 
 	mutex_lock(&cgroup_mutex);
 	parent = cgrp->parent;
-	root = cgrp->root;
-	sb = root->sb;
 
 	if (atomic_read(&cgrp->count)
 	    || !list_empty(&cgrp->children)
-	    || cgroup_has_css_refs(cgrp)) {
+	    || !cgroup_clear_css_refs(cgrp)) {
 		mutex_unlock(&cgroup_mutex);
 		return -EBUSY;
 	}
@@ -2504,8 +2582,12 @@ static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry)
 	if (!list_empty(&cgrp->release_list))
 		list_del(&cgrp->release_list);
 	spin_unlock(&release_list_lock);
-	/* delete my sibling from parent->children */
+
+	cgroup_lock_hierarchy(cgrp->root);
+	/* delete this cgroup from parent->children */
 	list_del(&cgrp->sibling);
+	cgroup_unlock_hierarchy(cgrp->root);
+
 	spin_lock(&cgrp->dentry->d_lock);
 	d = dget(cgrp->dentry);
 	spin_unlock(&d->d_lock);
@@ -2527,6 +2609,7 @@ static void __init cgroup_init_subsys(struct cgroup_subsys *ss)
 	printk(KERN_INFO "Initializing cgroup subsys %s\n", ss->name);
 
 	/* Create the top cgroup state for this subsystem */
+	list_add(&ss->sibling, &rootnode.subsys_list);
 	ss->root = &rootnode;
 	css = ss->create(ss, dummytop);
 	/* We don't handle early failures gracefully */
@@ -2540,13 +2623,13 @@ static void __init cgroup_init_subsys(struct cgroup_subsys *ss)
 	init_css_set.subsys[ss->subsys_id] = dummytop->subsys[ss->subsys_id];
 
 	need_forkexit_callback |= ss->fork || ss->exit;
-	need_mm_owner_callback |= !!ss->mm_owner_changed;
 
 	/* At system boot, before all subsystems have been
 	 * registered, no tasks have been forked, so we don't
 	 * need to invoke fork callbacks here. */
 	BUG_ON(!list_empty(&init_task.tasks));
 
+	mutex_init(&ss->hierarchy_mutex);
 	ss->active = 1;
 }
 
@@ -2565,7 +2648,6 @@ int __init cgroup_init_early(void)
 	INIT_HLIST_NODE(&init_css_set.hlist);
 	css_set_count = 1;
 	init_cgroup_root(&rootnode);
-	list_add(&rootnode.root_list, &roots);
 	root_count = 1;
 	init_task.cgroups = &init_css_set;
 
@@ -2672,15 +2754,12 @@ static int proc_cgroup_show(struct seq_file *m, void *v)
 
 	mutex_lock(&cgroup_mutex);
 
-	for_each_root(root) {
+	for_each_active_root(root) {
 		struct cgroup_subsys *ss;
 		struct cgroup *cgrp;
 		int subsys_id;
 		int count = 0;
 
-		/* Skip this hierarchy if it has no active subsystems */
-		if (!root->actual_subsys_bits)
-			continue;
 		seq_printf(m, "%lu:", root->subsys_bits);
 		for_each_subsys(root, ss)
 			seq_printf(m, "%s%s", count++ ? "," : "", ss->name);
@@ -2790,37 +2869,6 @@ void cgroup_fork_callbacks(struct task_struct *child)
 	}
 }
 
-#ifdef CONFIG_MM_OWNER
-/**
- * cgroup_mm_owner_callbacks - run callbacks when the mm->owner changes
- * @p: the new owner
- *
- * Called on every change to mm->owner. mm_init_owner() does not
- * invoke this routine, since it assigns the mm->owner the first time
- * and does not change it.
- *
- * The callbacks are invoked with mmap_sem held in read mode.
- */
-void cgroup_mm_owner_callbacks(struct task_struct *old, struct task_struct *new)
-{
-	struct cgroup *oldcgrp, *newcgrp = NULL;
-
-	if (need_mm_owner_callback) {
-		int i;
-		for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
-			struct cgroup_subsys *ss = subsys[i];
-			oldcgrp = task_cgroup(old, ss->subsys_id);
-			if (new)
-				newcgrp = task_cgroup(new, ss->subsys_id);
-			if (oldcgrp == newcgrp)
-				continue;
-			if (ss->mm_owner_changed)
-				ss->mm_owner_changed(ss, oldcgrp, newcgrp, new);
-		}
-	}
-}
-#endif /* CONFIG_MM_OWNER */
-
 /**
  * cgroup_post_fork - called on a new task after adding it to the task list
  * @child: the task in question
@@ -2834,8 +2882,10 @@ void cgroup_post_fork(struct task_struct *child)
 {
 	if (use_task_css_set_links) {
 		write_lock(&css_set_lock);
+		task_lock(child);
 		if (list_empty(&child->cg_list))
 			list_add(&child->cg_list, &child->cgroups->tasks);
+		task_unlock(child);
 		write_unlock(&css_set_lock);
 	}
 }
@@ -2941,14 +2991,20 @@ int cgroup_clone(struct task_struct *tsk, struct cgroup_subsys *subsys,
 		mutex_unlock(&cgroup_mutex);
 		return 0;
 	}
+	task_lock(tsk);
 	cg = tsk->cgroups;
 	parent = task_cgroup(tsk, subsys->subsys_id);
 
 	/* Pin the hierarchy */
-	atomic_inc(&parent->root->sb->s_active);
+	if (!atomic_inc_not_zero(&parent->root->sb->s_active)) {
+		/* We race with the final deactivate_super() */
+		mutex_unlock(&cgroup_mutex);
+		return 0;
+	}
 
 	/* Keep the cgroup alive */
 	get_css_set(cg);
+	task_unlock(tsk);
 	mutex_unlock(&cgroup_mutex);
 
 	/* Now do the VFS work to create a cgroup */
@@ -2967,7 +3023,7 @@ int cgroup_clone(struct task_struct *tsk, struct cgroup_subsys *subsys,
 	}
 
 	/* Create the cgroup directory, which also creates the cgroup */
-	ret = vfs_mkdir(inode, dentry, S_IFDIR | 0755);
+	ret = vfs_mkdir(inode, dentry, 0755);
 	child = __d_cgrp(dentry);
 	dput(dentry);
 	if (ret) {
@@ -2977,13 +3033,6 @@ int cgroup_clone(struct task_struct *tsk, struct cgroup_subsys *subsys,
 		goto out_release;
 	}
 
-	if (!child) {
-		printk(KERN_INFO
-		       "Couldn't find new cgroup %s\n", nodename);
-		ret = -ENOMEM;
-		goto out_release;
-	}
-
 	/* The cgroup now exists. Retake cgroup_mutex and check
 	 * that we're still in the same state that we thought we
 	 * were. */
@@ -3079,7 +3128,8 @@ void __css_put(struct cgroup_subsys_state *css)
 {
 	struct cgroup *cgrp = css->cgroup;
 	rcu_read_lock();
-	if (atomic_dec_and_test(&css->refcnt) && notify_on_release(cgrp)) {
+	if ((atomic_dec_return(&css->refcnt) == 1) &&
+	    notify_on_release(cgrp)) {
 		set_bit(CGRP_RELEASABLE, &cgrp->flags);
 		check_for_release(cgrp);
 	}
diff --git a/kernel/compat.c b/kernel/compat.c
index 8eafe3eb50d9..42d56544460f 100644
--- a/kernel/compat.c
+++ b/kernel/compat.c
@@ -24,6 +24,7 @@
 #include <linux/migrate.h>
 #include <linux/posix-timers.h>
 #include <linux/times.h>
+#include <linux/ptrace.h>
 
 #include <asm/uaccess.h>
 
@@ -229,6 +230,7 @@ asmlinkage long compat_sys_times(struct compat_tms __user *tbuf)
 		if (copy_to_user(tbuf, &tmp, sizeof(tmp)))
 			return -EFAULT;
 	}
+	force_successful_syscall_return();
 	return compat_jiffies_to_clock_t(jiffies);
 }
 
@@ -454,16 +456,16 @@ asmlinkage long compat_sys_waitid(int which, compat_pid_t pid,
 }
 
 static int compat_get_user_cpu_mask(compat_ulong_t __user *user_mask_ptr,
-				    unsigned len, cpumask_t *new_mask)
+				    unsigned len, struct cpumask *new_mask)
 {
 	unsigned long *k;
 
-	if (len < sizeof(cpumask_t))
-		memset(new_mask, 0, sizeof(cpumask_t));
-	else if (len > sizeof(cpumask_t))
-		len = sizeof(cpumask_t);
+	if (len < cpumask_size())
+		memset(new_mask, 0, cpumask_size());
+	else if (len > cpumask_size())
+		len = cpumask_size();
 
-	k = cpus_addr(*new_mask);
+	k = cpumask_bits(new_mask);
 	return compat_get_bitmap(k, user_mask_ptr, len * 8);
 }
 
@@ -471,40 +473,51 @@ asmlinkage long compat_sys_sched_setaffinity(compat_pid_t pid,
 					     unsigned int len,
 					     compat_ulong_t __user *user_mask_ptr)
 {
-	cpumask_t new_mask;
+	cpumask_var_t new_mask;
 	int retval;
 
-	retval = compat_get_user_cpu_mask(user_mask_ptr, len, &new_mask);
+	if (!alloc_cpumask_var(&new_mask, GFP_KERNEL))
+		return -ENOMEM;
+
+	retval = compat_get_user_cpu_mask(user_mask_ptr, len, new_mask);
 	if (retval)
-		return retval;
+		goto out;
 
-	return sched_setaffinity(pid, &new_mask);
+	retval = sched_setaffinity(pid, new_mask);
+out:
+	free_cpumask_var(new_mask);
+	return retval;
 }
 
 asmlinkage long compat_sys_sched_getaffinity(compat_pid_t pid, unsigned int len,
 					     compat_ulong_t __user *user_mask_ptr)
 {
 	int ret;
-	cpumask_t mask;
+	cpumask_var_t mask;
 	unsigned long *k;
-	unsigned int min_length = sizeof(cpumask_t);
+	unsigned int min_length = cpumask_size();
 
-	if (NR_CPUS <= BITS_PER_COMPAT_LONG)
+	if (nr_cpu_ids <= BITS_PER_COMPAT_LONG)
 		min_length = sizeof(compat_ulong_t);
 
 	if (len < min_length)
 		return -EINVAL;
 
-	ret = sched_getaffinity(pid, &mask);
+	if (!alloc_cpumask_var(&mask, GFP_KERNEL))
+		return -ENOMEM;
+
+	ret = sched_getaffinity(pid, mask);
 	if (ret < 0)
-		return ret;
+		goto out;
 
-	k = cpus_addr(mask);
+	k = cpumask_bits(mask);
 	ret = compat_put_bitmap(user_mask_ptr, k, min_length * 8);
-	if (ret)
-		return ret;
+	if (ret == 0)
+		ret = min_length;
 
-	return min_length;
+out:
+	free_cpumask_var(mask);
+	return ret;
 }
 
 int get_compat_itimerspec(struct itimerspec *dst,
@@ -883,8 +896,9 @@ asmlinkage long compat_sys_time(compat_time_t __user * tloc)
 
 	if (tloc) {
 		if (put_user(i,tloc))
-			i = -EFAULT;
+			return -EFAULT;
 	}
+	force_successful_syscall_return();
 	return i;
 }
 
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 8ea32e8d68b0..79e40f00dcb8 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -15,29 +15,8 @@
 #include <linux/stop_machine.h>
 #include <linux/mutex.h>
 
-/*
- * Represents all cpu's present in the system
- * In systems capable of hotplug, this map could dynamically grow
- * as new cpu's are detected in the system via any platform specific
- * method, such as ACPI for e.g.
- */
-cpumask_t cpu_present_map __read_mostly;
-EXPORT_SYMBOL(cpu_present_map);
-
-#ifndef CONFIG_SMP
-
-/*
- * Represents all cpu's that are currently online.
- */
-cpumask_t cpu_online_map __read_mostly = CPU_MASK_ALL;
-EXPORT_SYMBOL(cpu_online_map);
-
-cpumask_t cpu_possible_map __read_mostly = CPU_MASK_ALL;
-EXPORT_SYMBOL(cpu_possible_map);
-
-#else /* CONFIG_SMP */
-
-/* Serializes the updates to cpu_online_map, cpu_present_map */
+#ifdef CONFIG_SMP
+/* Serializes the updates to cpu_online_mask, cpu_present_mask */
 static DEFINE_MUTEX(cpu_add_remove_lock);
 
 static __cpuinitdata RAW_NOTIFIER_HEAD(cpu_chain);
@@ -64,8 +43,6 @@ void __init cpu_hotplug_init(void)
 	cpu_hotplug.refcount = 0;
 }
 
-cpumask_t cpu_active_map;
-
 #ifdef CONFIG_HOTPLUG_CPU
 
 void get_online_cpus(void)
@@ -96,7 +73,7 @@ EXPORT_SYMBOL_GPL(put_online_cpus);
 
 /*
  * The following two API's must be used when attempting
- * to serialize the updates to cpu_online_map, cpu_present_map.
+ * to serialize the updates to cpu_online_mask, cpu_present_mask.
  */
 void cpu_maps_update_begin(void)
 {
@@ -217,7 +194,7 @@ static int __ref take_cpu_down(void *_param)
 static int __ref _cpu_down(unsigned int cpu, int tasks_frozen)
 {
 	int err, nr_calls = 0;
-	cpumask_t old_allowed, tmp;
+	cpumask_var_t old_allowed;
 	void *hcpu = (void *)(long)cpu;
 	unsigned long mod = tasks_frozen ? CPU_TASKS_FROZEN : 0;
 	struct take_cpu_down_param tcd_param = {
@@ -231,6 +208,9 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen)
 	if (!cpu_online(cpu))
 		return -EINVAL;
 
+	if (!alloc_cpumask_var(&old_allowed, GFP_KERNEL))
+		return -ENOMEM;
+
 	cpu_hotplug_begin();
 	err = __raw_notifier_call_chain(&cpu_chain, CPU_DOWN_PREPARE | mod,
 					hcpu, -1, &nr_calls);
@@ -245,13 +225,11 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen)
 	}
 
 	/* Ensure that we are not runnable on dying cpu */
-	old_allowed = current->cpus_allowed;
-	cpus_setall(tmp);
-	cpu_clear(cpu, tmp);
-	set_cpus_allowed_ptr(current, &tmp);
-	tmp = cpumask_of_cpu(cpu);
+	cpumask_copy(old_allowed, &current->cpus_allowed);
+	set_cpus_allowed_ptr(current,
+			     cpumask_of(cpumask_any_but(cpu_online_mask, cpu)));
 
-	err = __stop_machine(take_cpu_down, &tcd_param, &tmp);
+	err = __stop_machine(take_cpu_down, &tcd_param, cpumask_of(cpu));
 	if (err) {
 		/* CPU didn't die: tell everyone.  Can't complain. */
 		if (raw_notifier_call_chain(&cpu_chain, CPU_DOWN_FAILED | mod,
@@ -277,7 +255,7 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen)
 	check_for_tasks(cpu);
 
 out_allowed:
-	set_cpus_allowed_ptr(current, &old_allowed);
+	set_cpus_allowed_ptr(current, old_allowed);
 out_release:
 	cpu_hotplug_done();
 	if (!err) {
@@ -285,13 +263,17 @@ out_release:
 					    hcpu) == NOTIFY_BAD)
 			BUG();
 	}
+	free_cpumask_var(old_allowed);
 	return err;
 }
 
 int __ref cpu_down(unsigned int cpu)
 {
-	int err = 0;
+	int err;
 
+	err = stop_machine_create();
+	if (err)
+		return err;
 	cpu_maps_update_begin();
 
 	if (cpu_hotplug_disabled) {
@@ -303,7 +285,7 @@ int __ref cpu_down(unsigned int cpu)
 
 	/*
 	 * Make sure the all cpus did the reschedule and are not
-	 * using stale version of the cpu_active_map.
+	 * using stale version of the cpu_active_mask.
 	 * This is not strictly necessary becuase stop_machine()
 	 * that we run down the line already provides the required
 	 * synchronization. But it's really a side effect and we do not
@@ -318,6 +300,7 @@ int __ref cpu_down(unsigned int cpu)
 
 out:
 	cpu_maps_update_done();
+	stop_machine_destroy();
 	return err;
 }
 EXPORT_SYMBOL(cpu_down);
@@ -367,7 +350,7 @@ out_notify:
 int __cpuinit cpu_up(unsigned int cpu)
 {
 	int err = 0;
-	if (!cpu_isset(cpu, cpu_possible_map)) {
+	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)
@@ -392,25 +375,28 @@ out:
 }
 
 #ifdef CONFIG_PM_SLEEP_SMP
-static cpumask_t frozen_cpus;
+static cpumask_var_t frozen_cpus;
 
 int disable_nonboot_cpus(void)
 {
-	int cpu, first_cpu, error = 0;
+	int cpu, first_cpu, error;
 
+	error = stop_machine_create();
+	if (error)
+		return error;
 	cpu_maps_update_begin();
-	first_cpu = first_cpu(cpu_online_map);
+	first_cpu = cpumask_first(cpu_online_mask);
 	/* We take down all of the non-boot CPUs in one shot to avoid races
 	 * with the userspace trying to use the CPU hotplug at the same time
 	 */
-	cpus_clear(frozen_cpus);
+	cpumask_clear(frozen_cpus);
 	printk("Disabling non-boot CPUs ...\n");
 	for_each_online_cpu(cpu) {
 		if (cpu == first_cpu)
 			continue;
 		error = _cpu_down(cpu, 1);
 		if (!error) {
-			cpu_set(cpu, frozen_cpus);
+			cpumask_set_cpu(cpu, frozen_cpus);
 			printk("CPU%d is down\n", cpu);
 		} else {
 			printk(KERN_ERR "Error taking CPU%d down: %d\n",
@@ -426,6 +412,7 @@ int disable_nonboot_cpus(void)
 		printk(KERN_ERR "Non-boot CPUs are not disabled\n");
 	}
 	cpu_maps_update_done();
+	stop_machine_destroy();
 	return error;
 }
 
@@ -436,11 +423,11 @@ void __ref enable_nonboot_cpus(void)
 	/* Allow everyone to use the CPU hotplug again */
 	cpu_maps_update_begin();
 	cpu_hotplug_disabled = 0;
-	if (cpus_empty(frozen_cpus))
+	if (cpumask_empty(frozen_cpus))
 		goto out;
 
 	printk("Enabling non-boot CPUs ...\n");
-	for_each_cpu_mask_nr(cpu, frozen_cpus) {
+	for_each_cpu(cpu, frozen_cpus) {
 		error = _cpu_up(cpu, 1);
 		if (!error) {
 			printk("CPU%d is up\n", cpu);
@@ -448,10 +435,18 @@ void __ref enable_nonboot_cpus(void)
 		}
 		printk(KERN_WARNING "Error taking CPU%d up: %d\n", cpu, error);
 	}
-	cpus_clear(frozen_cpus);
+	cpumask_clear(frozen_cpus);
 out:
 	cpu_maps_update_done();
 }
+
+static int alloc_frozen_cpus(void)
+{
+	if (!alloc_cpumask_var(&frozen_cpus, GFP_KERNEL|__GFP_ZERO))
+		return -ENOMEM;
+	return 0;
+}
+core_initcall(alloc_frozen_cpus);
 #endif /* CONFIG_PM_SLEEP_SMP */
 
 /**
@@ -467,7 +462,7 @@ void __cpuinit notify_cpu_starting(unsigned int cpu)
 	unsigned long val = CPU_STARTING;
 
 #ifdef CONFIG_PM_SLEEP_SMP
-	if (cpu_isset(cpu, frozen_cpus))
+	if (frozen_cpus != NULL && cpumask_test_cpu(cpu, frozen_cpus))
 		val = CPU_STARTING_FROZEN;
 #endif /* CONFIG_PM_SLEEP_SMP */
 	raw_notifier_call_chain(&cpu_chain, val, (void *)(long)cpu);
@@ -479,7 +474,7 @@ void __cpuinit notify_cpu_starting(unsigned int cpu)
  * cpu_bit_bitmap[] is a special, "compressed" data structure that
  * represents all NR_CPUS bits binary values of 1<<nr.
  *
- * It is used by cpumask_of_cpu() to get a constant address to a CPU
+ * It is used by cpumask_of() to get a constant address to a CPU
  * mask value that has a single bit set only.
  */
 
@@ -502,3 +497,71 @@ EXPORT_SYMBOL_GPL(cpu_bit_bitmap);
 
 const DECLARE_BITMAP(cpu_all_bits, NR_CPUS) = CPU_BITS_ALL;
 EXPORT_SYMBOL(cpu_all_bits);
+
+#ifdef CONFIG_INIT_ALL_POSSIBLE
+static DECLARE_BITMAP(cpu_possible_bits, CONFIG_NR_CPUS) __read_mostly
+	= CPU_BITS_ALL;
+#else
+static DECLARE_BITMAP(cpu_possible_bits, CONFIG_NR_CPUS) __read_mostly;
+#endif
+const struct cpumask *const cpu_possible_mask = to_cpumask(cpu_possible_bits);
+EXPORT_SYMBOL(cpu_possible_mask);
+
+static DECLARE_BITMAP(cpu_online_bits, CONFIG_NR_CPUS) __read_mostly;
+const struct cpumask *const cpu_online_mask = to_cpumask(cpu_online_bits);
+EXPORT_SYMBOL(cpu_online_mask);
+
+static DECLARE_BITMAP(cpu_present_bits, CONFIG_NR_CPUS) __read_mostly;
+const struct cpumask *const cpu_present_mask = to_cpumask(cpu_present_bits);
+EXPORT_SYMBOL(cpu_present_mask);
+
+static DECLARE_BITMAP(cpu_active_bits, CONFIG_NR_CPUS) __read_mostly;
+const struct cpumask *const cpu_active_mask = to_cpumask(cpu_active_bits);
+EXPORT_SYMBOL(cpu_active_mask);
+
+void set_cpu_possible(unsigned int cpu, bool possible)
+{
+	if (possible)
+		cpumask_set_cpu(cpu, to_cpumask(cpu_possible_bits));
+	else
+		cpumask_clear_cpu(cpu, to_cpumask(cpu_possible_bits));
+}
+
+void set_cpu_present(unsigned int cpu, bool present)
+{
+	if (present)
+		cpumask_set_cpu(cpu, to_cpumask(cpu_present_bits));
+	else
+		cpumask_clear_cpu(cpu, to_cpumask(cpu_present_bits));
+}
+
+void set_cpu_online(unsigned int cpu, bool online)
+{
+	if (online)
+		cpumask_set_cpu(cpu, to_cpumask(cpu_online_bits));
+	else
+		cpumask_clear_cpu(cpu, to_cpumask(cpu_online_bits));
+}
+
+void set_cpu_active(unsigned int cpu, bool active)
+{
+	if (active)
+		cpumask_set_cpu(cpu, to_cpumask(cpu_active_bits));
+	else
+		cpumask_clear_cpu(cpu, to_cpumask(cpu_active_bits));
+}
+
+void init_cpu_present(const struct cpumask *src)
+{
+	cpumask_copy(to_cpumask(cpu_present_bits), src);
+}
+
+void init_cpu_possible(const struct cpumask *src)
+{
+	cpumask_copy(to_cpumask(cpu_possible_bits), src);
+}
+
+void init_cpu_online(const struct cpumask *src)
+{
+	cpumask_copy(to_cpumask(cpu_online_bits), src);
+}
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 96c0ba13b8cd..647c77a88fcb 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -84,7 +84,7 @@ struct cpuset {
 	struct cgroup_subsys_state css;
 
 	unsigned long flags;		/* "unsigned long" so bitops work */
-	cpumask_t cpus_allowed;		/* CPUs allowed to tasks in cpuset */
+	cpumask_var_t cpus_allowed;	/* CPUs allowed to tasks in cpuset */
 	nodemask_t mems_allowed;	/* Memory Nodes allowed to tasks */
 
 	struct cpuset *parent;		/* my parent */
@@ -195,8 +195,6 @@ static int cpuset_mems_generation;
 
 static struct cpuset top_cpuset = {
 	.flags = ((1 << CS_CPU_EXCLUSIVE) | (1 << CS_MEM_EXCLUSIVE)),
-	.cpus_allowed = CPU_MASK_ALL,
-	.mems_allowed = NODE_MASK_ALL,
 };
 
 /*
@@ -240,6 +238,17 @@ static struct cpuset top_cpuset = {
 static DEFINE_MUTEX(callback_mutex);
 
 /*
+ * cpuset_buffer_lock protects both the cpuset_name and cpuset_nodelist
+ * buffers.  They are statically allocated to prevent using excess stack
+ * when calling cpuset_print_task_mems_allowed().
+ */
+#define CPUSET_NAME_LEN		(128)
+#define	CPUSET_NODELIST_LEN	(256)
+static char cpuset_name[CPUSET_NAME_LEN];
+static char cpuset_nodelist[CPUSET_NODELIST_LEN];
+static DEFINE_SPINLOCK(cpuset_buffer_lock);
+
+/*
  * This is ugly, but preserves the userspace API for existing cpuset
  * users. If someone tries to mount the "cpuset" filesystem, we
  * silently switch it to mount "cgroup" instead
@@ -267,7 +276,7 @@ static struct file_system_type cpuset_fs_type = {
 };
 
 /*
- * Return in *pmask the portion of a cpusets's cpus_allowed that
+ * Return in pmask the portion of a cpusets's cpus_allowed that
  * are online.  If none are online, walk up the cpuset hierarchy
  * until we find one that does have some online cpus.  If we get
  * all the way to the top and still haven't found any online cpus,
@@ -280,15 +289,16 @@ static struct file_system_type cpuset_fs_type = {
  * Call with callback_mutex held.
  */
 
-static void guarantee_online_cpus(const struct cpuset *cs, cpumask_t *pmask)
+static void guarantee_online_cpus(const struct cpuset *cs,
+				  struct cpumask *pmask)
 {
-	while (cs && !cpus_intersects(cs->cpus_allowed, cpu_online_map))
+	while (cs && !cpumask_intersects(cs->cpus_allowed, cpu_online_mask))
 		cs = cs->parent;
 	if (cs)
-		cpus_and(*pmask, cs->cpus_allowed, cpu_online_map);
+		cpumask_and(pmask, cs->cpus_allowed, cpu_online_mask);
 	else
-		*pmask = cpu_online_map;
-	BUG_ON(!cpus_intersects(*pmask, cpu_online_map));
+		cpumask_copy(pmask, cpu_online_mask);
+	BUG_ON(!cpumask_intersects(pmask, cpu_online_mask));
 }
 
 /*
@@ -364,14 +374,9 @@ void cpuset_update_task_memory_state(void)
 	struct task_struct *tsk = current;
 	struct cpuset *cs;
 
-	if (task_cs(tsk) == &top_cpuset) {
-		/* Don't need rcu for top_cpuset.  It's never freed. */
-		my_cpusets_mem_gen = top_cpuset.mems_generation;
-	} else {
-		rcu_read_lock();
-		my_cpusets_mem_gen = task_cs(tsk)->mems_generation;
-		rcu_read_unlock();
-	}
+	rcu_read_lock();
+	my_cpusets_mem_gen = task_cs(tsk)->mems_generation;
+	rcu_read_unlock();
 
 	if (my_cpusets_mem_gen != tsk->cpuset_mems_generation) {
 		mutex_lock(&callback_mutex);
@@ -403,12 +408,43 @@ void cpuset_update_task_memory_state(void)
 
 static int is_cpuset_subset(const struct cpuset *p, const struct cpuset *q)
 {
-	return	cpus_subset(p->cpus_allowed, q->cpus_allowed) &&
+	return	cpumask_subset(p->cpus_allowed, q->cpus_allowed) &&
 		nodes_subset(p->mems_allowed, q->mems_allowed) &&
 		is_cpu_exclusive(p) <= is_cpu_exclusive(q) &&
 		is_mem_exclusive(p) <= is_mem_exclusive(q);
 }
 
+/**
+ * alloc_trial_cpuset - allocate a trial cpuset
+ * @cs: the cpuset that the trial cpuset duplicates
+ */
+static struct cpuset *alloc_trial_cpuset(const struct cpuset *cs)
+{
+	struct cpuset *trial;
+
+	trial = kmemdup(cs, sizeof(*cs), GFP_KERNEL);
+	if (!trial)
+		return NULL;
+
+	if (!alloc_cpumask_var(&trial->cpus_allowed, GFP_KERNEL)) {
+		kfree(trial);
+		return NULL;
+	}
+	cpumask_copy(trial->cpus_allowed, cs->cpus_allowed);
+
+	return trial;
+}
+
+/**
+ * free_trial_cpuset - free the trial cpuset
+ * @trial: the trial cpuset to be freed
+ */
+static void free_trial_cpuset(struct cpuset *trial)
+{
+	free_cpumask_var(trial->cpus_allowed);
+	kfree(trial);
+}
+
 /*
  * validate_change() - Used to validate that any proposed cpuset change
  *		       follows the structural rules for cpusets.
@@ -458,7 +494,7 @@ static int validate_change(const struct cpuset *cur, const struct cpuset *trial)
 		c = cgroup_cs(cont);
 		if ((is_cpu_exclusive(trial) || is_cpu_exclusive(c)) &&
 		    c != cur &&
-		    cpus_intersects(trial->cpus_allowed, c->cpus_allowed))
+		    cpumask_intersects(trial->cpus_allowed, c->cpus_allowed))
 			return -EINVAL;
 		if ((is_mem_exclusive(trial) || is_mem_exclusive(c)) &&
 		    c != cur &&
@@ -468,7 +504,7 @@ static int validate_change(const struct cpuset *cur, const struct cpuset *trial)
 
 	/* Cpusets with tasks can't have empty cpus_allowed or mems_allowed */
 	if (cgroup_task_count(cur->css.cgroup)) {
-		if (cpus_empty(trial->cpus_allowed) ||
+		if (cpumask_empty(trial->cpus_allowed) ||
 		    nodes_empty(trial->mems_allowed)) {
 			return -ENOSPC;
 		}
@@ -483,7 +519,7 @@ static int validate_change(const struct cpuset *cur, const struct cpuset *trial)
  */
 static int cpusets_overlap(struct cpuset *a, struct cpuset *b)
 {
-	return cpus_intersects(a->cpus_allowed, b->cpus_allowed);
+	return cpumask_intersects(a->cpus_allowed, b->cpus_allowed);
 }
 
 static void
@@ -508,7 +544,7 @@ update_domain_attr_tree(struct sched_domain_attr *dattr, struct cpuset *c)
 		cp = list_first_entry(&q, struct cpuset, stack_list);
 		list_del(q.next);
 
-		if (cpus_empty(cp->cpus_allowed))
+		if (cpumask_empty(cp->cpus_allowed))
 			continue;
 
 		if (is_sched_load_balance(cp))
@@ -575,7 +611,8 @@ update_domain_attr_tree(struct sched_domain_attr *dattr, struct cpuset *c)
  *	element of the partition (one sched domain) to be passed to
  *	partition_sched_domains().
  */
-static int generate_sched_domains(cpumask_t **domains,
+/* FIXME: see the FIXME in partition_sched_domains() */
+static int generate_sched_domains(struct cpumask **domains,
 			struct sched_domain_attr **attributes)
 {
 	LIST_HEAD(q);		/* queue of cpusets to be scanned */
@@ -583,10 +620,10 @@ static int generate_sched_domains(cpumask_t **domains,
 	struct cpuset **csa;	/* array of all cpuset ptrs */
 	int csn;		/* how many cpuset ptrs in csa so far */
 	int i, j, k;		/* indices for partition finding loops */
-	cpumask_t *doms;	/* resulting partition; i.e. sched domains */
+	struct cpumask *doms;	/* resulting partition; i.e. sched domains */
 	struct sched_domain_attr *dattr;  /* attributes for custom domains */
 	int ndoms = 0;		/* number of sched domains in result */
-	int nslot;		/* next empty doms[] cpumask_t slot */
+	int nslot;		/* next empty doms[] struct cpumask slot */
 
 	doms = NULL;
 	dattr = NULL;
@@ -594,7 +631,7 @@ static int generate_sched_domains(cpumask_t **domains,
 
 	/* Special case for the 99% of systems with one, full, sched domain */
 	if (is_sched_load_balance(&top_cpuset)) {
-		doms = kmalloc(sizeof(cpumask_t), GFP_KERNEL);
+		doms = kmalloc(cpumask_size(), GFP_KERNEL);
 		if (!doms)
 			goto done;
 
@@ -603,7 +640,7 @@ static int generate_sched_domains(cpumask_t **domains,
 			*dattr = SD_ATTR_INIT;
 			update_domain_attr_tree(dattr, &top_cpuset);
 		}
-		*doms = top_cpuset.cpus_allowed;
+		cpumask_copy(doms, top_cpuset.cpus_allowed);
 
 		ndoms = 1;
 		goto done;
@@ -622,7 +659,7 @@ static int generate_sched_domains(cpumask_t **domains,
 		cp = list_first_entry(&q, struct cpuset, stack_list);
 		list_del(q.next);
 
-		if (cpus_empty(cp->cpus_allowed))
+		if (cpumask_empty(cp->cpus_allowed))
 			continue;
 
 		/*
@@ -673,7 +710,7 @@ restart:
 	 * Now we know how many domains to create.
 	 * Convert <csn, csa> to <ndoms, doms> and populate cpu masks.
 	 */
-	doms = kmalloc(ndoms * sizeof(cpumask_t), GFP_KERNEL);
+	doms = kmalloc(ndoms * cpumask_size(), GFP_KERNEL);
 	if (!doms)
 		goto done;
 
@@ -685,7 +722,7 @@ restart:
 
 	for (nslot = 0, i = 0; i < csn; i++) {
 		struct cpuset *a = csa[i];
-		cpumask_t *dp;
+		struct cpumask *dp;
 		int apn = a->pn;
 
 		if (apn < 0) {
@@ -708,14 +745,14 @@ restart:
 			continue;
 		}
 
-		cpus_clear(*dp);
+		cpumask_clear(dp);
 		if (dattr)
 			*(dattr + nslot) = SD_ATTR_INIT;
 		for (j = i; j < csn; j++) {
 			struct cpuset *b = csa[j];
 
 			if (apn == b->pn) {
-				cpus_or(*dp, *dp, b->cpus_allowed);
+				cpumask_or(dp, dp, b->cpus_allowed);
 				if (dattr)
 					update_domain_attr_tree(dattr + nslot, b);
 
@@ -755,7 +792,7 @@ done:
 static void do_rebuild_sched_domains(struct work_struct *unused)
 {
 	struct sched_domain_attr *attr;
-	cpumask_t *doms;
+	struct cpumask *doms;
 	int ndoms;
 
 	get_online_cpus();
@@ -824,7 +861,7 @@ void rebuild_sched_domains(void)
 static int cpuset_test_cpumask(struct task_struct *tsk,
 			       struct cgroup_scanner *scan)
 {
-	return !cpus_equal(tsk->cpus_allowed,
+	return !cpumask_equal(&tsk->cpus_allowed,
 			(cgroup_cs(scan->cg))->cpus_allowed);
 }
 
@@ -842,7 +879,7 @@ static int cpuset_test_cpumask(struct task_struct *tsk,
 static void cpuset_change_cpumask(struct task_struct *tsk,
 				  struct cgroup_scanner *scan)
 {
-	set_cpus_allowed_ptr(tsk, &((cgroup_cs(scan->cg))->cpus_allowed));
+	set_cpus_allowed_ptr(tsk, ((cgroup_cs(scan->cg))->cpus_allowed));
 }
 
 /**
@@ -874,10 +911,10 @@ static void update_tasks_cpumask(struct cpuset *cs, struct ptr_heap *heap)
  * @cs: the cpuset to consider
  * @buf: buffer of cpu numbers written to this cpuset
  */
-static int update_cpumask(struct cpuset *cs, const char *buf)
+static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs,
+			  const char *buf)
 {
 	struct ptr_heap heap;
-	struct cpuset trialcs;
 	int retval;
 	int is_load_balanced;
 
@@ -885,8 +922,6 @@ static int update_cpumask(struct cpuset *cs, const char *buf)
 	if (cs == &top_cpuset)
 		return -EACCES;
 
-	trialcs = *cs;
-
 	/*
 	 * An empty cpus_allowed is ok only if the cpuset has no tasks.
 	 * Since cpulist_parse() fails on an empty mask, we special case
@@ -894,31 +929,31 @@ static int update_cpumask(struct cpuset *cs, const char *buf)
 	 * with tasks have cpus.
 	 */
 	if (!*buf) {
-		cpus_clear(trialcs.cpus_allowed);
+		cpumask_clear(trialcs->cpus_allowed);
 	} else {
-		retval = cpulist_parse(buf, trialcs.cpus_allowed);
+		retval = cpulist_parse(buf, trialcs->cpus_allowed);
 		if (retval < 0)
 			return retval;
 
-		if (!cpus_subset(trialcs.cpus_allowed, cpu_online_map))
+		if (!cpumask_subset(trialcs->cpus_allowed, cpu_online_mask))
 			return -EINVAL;
 	}
-	retval = validate_change(cs, &trialcs);
+	retval = validate_change(cs, trialcs);
 	if (retval < 0)
 		return retval;
 
 	/* Nothing to do if the cpus didn't change */
-	if (cpus_equal(cs->cpus_allowed, trialcs.cpus_allowed))
+	if (cpumask_equal(cs->cpus_allowed, trialcs->cpus_allowed))
 		return 0;
 
 	retval = heap_init(&heap, PAGE_SIZE, GFP_KERNEL, NULL);
 	if (retval)
 		return retval;
 
-	is_load_balanced = is_sched_load_balance(&trialcs);
+	is_load_balanced = is_sched_load_balance(trialcs);
 
 	mutex_lock(&callback_mutex);
-	cs->cpus_allowed = trialcs.cpus_allowed;
+	cpumask_copy(cs->cpus_allowed, trialcs->cpus_allowed);
 	mutex_unlock(&callback_mutex);
 
 	/*
@@ -1006,7 +1041,7 @@ static int update_tasks_nodemask(struct cpuset *cs, const nodemask_t *oldmem)
 	cpuset_being_rebound = cs;		/* causes mpol_dup() rebind */
 
 	fudge = 10;				/* spare mmarray[] slots */
-	fudge += cpus_weight(cs->cpus_allowed);	/* imagine one fork-bomb/cpu */
+	fudge += cpumask_weight(cs->cpus_allowed);/* imagine 1 fork-bomb/cpu */
 	retval = -ENOMEM;
 
 	/*
@@ -1093,9 +1128,9 @@ done:
  * lock each such tasks mm->mmap_sem, scan its vma's and rebind
  * their mempolicies to the cpusets new mems_allowed.
  */
-static int update_nodemask(struct cpuset *cs, const char *buf)
+static int update_nodemask(struct cpuset *cs, struct cpuset *trialcs,
+			   const char *buf)
 {
-	struct cpuset trialcs;
 	nodemask_t oldmem;
 	int retval;
 
@@ -1106,8 +1141,6 @@ static int update_nodemask(struct cpuset *cs, const char *buf)
 	if (cs == &top_cpuset)
 		return -EACCES;
 
-	trialcs = *cs;
-
 	/*
 	 * An empty mems_allowed is ok iff there are no tasks in the cpuset.
 	 * Since nodelist_parse() fails on an empty mask, we special case
@@ -1115,27 +1148,27 @@ static int update_nodemask(struct cpuset *cs, const char *buf)
 	 * with tasks have memory.
 	 */
 	if (!*buf) {
-		nodes_clear(trialcs.mems_allowed);
+		nodes_clear(trialcs->mems_allowed);
 	} else {
-		retval = nodelist_parse(buf, trialcs.mems_allowed);
+		retval = nodelist_parse(buf, trialcs->mems_allowed);
 		if (retval < 0)
 			goto done;
 
-		if (!nodes_subset(trialcs.mems_allowed,
+		if (!nodes_subset(trialcs->mems_allowed,
 				node_states[N_HIGH_MEMORY]))
 			return -EINVAL;
 	}
 	oldmem = cs->mems_allowed;
-	if (nodes_equal(oldmem, trialcs.mems_allowed)) {
+	if (nodes_equal(oldmem, trialcs->mems_allowed)) {
 		retval = 0;		/* Too easy - nothing to do */
 		goto done;
 	}
-	retval = validate_change(cs, &trialcs);
+	retval = validate_change(cs, trialcs);
 	if (retval < 0)
 		goto done;
 
 	mutex_lock(&callback_mutex);
-	cs->mems_allowed = trialcs.mems_allowed;
+	cs->mems_allowed = trialcs->mems_allowed;
 	cs->mems_generation = cpuset_mems_generation++;
 	mutex_unlock(&callback_mutex);
 
@@ -1156,7 +1189,8 @@ static int update_relax_domain_level(struct cpuset *cs, s64 val)
 
 	if (val != cs->relax_domain_level) {
 		cs->relax_domain_level = val;
-		if (!cpus_empty(cs->cpus_allowed) && is_sched_load_balance(cs))
+		if (!cpumask_empty(cs->cpus_allowed) &&
+		    is_sched_load_balance(cs))
 			async_rebuild_sched_domains();
 	}
 
@@ -1175,31 +1209,36 @@ static int update_relax_domain_level(struct cpuset *cs, s64 val)
 static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs,
 		       int turning_on)
 {
-	struct cpuset trialcs;
+	struct cpuset *trialcs;
 	int err;
 	int balance_flag_changed;
 
-	trialcs = *cs;
+	trialcs = alloc_trial_cpuset(cs);
+	if (!trialcs)
+		return -ENOMEM;
+
 	if (turning_on)
-		set_bit(bit, &trialcs.flags);
+		set_bit(bit, &trialcs->flags);
 	else
-		clear_bit(bit, &trialcs.flags);
+		clear_bit(bit, &trialcs->flags);
 
-	err = validate_change(cs, &trialcs);
+	err = validate_change(cs, trialcs);
 	if (err < 0)
-		return err;
+		goto out;
 
 	balance_flag_changed = (is_sched_load_balance(cs) !=
-		 			is_sched_load_balance(&trialcs));
+				is_sched_load_balance(trialcs));
 
 	mutex_lock(&callback_mutex);
-	cs->flags = trialcs.flags;
+	cs->flags = trialcs->flags;
 	mutex_unlock(&callback_mutex);
 
-	if (!cpus_empty(trialcs.cpus_allowed) && balance_flag_changed)
+	if (!cpumask_empty(trialcs->cpus_allowed) && balance_flag_changed)
 		async_rebuild_sched_domains();
 
-	return 0;
+out:
+	free_trial_cpuset(trialcs);
+	return err;
 }
 
 /*
@@ -1300,42 +1339,47 @@ static int fmeter_getrate(struct fmeter *fmp)
 	return val;
 }
 
+/* Protected by cgroup_lock */
+static cpumask_var_t cpus_attach;
+
 /* Called by cgroups to determine if a cpuset is usable; cgroup_mutex held */
 static int cpuset_can_attach(struct cgroup_subsys *ss,
 			     struct cgroup *cont, struct task_struct *tsk)
 {
 	struct cpuset *cs = cgroup_cs(cont);
+	int ret = 0;
 
-	if (cpus_empty(cs->cpus_allowed) || nodes_empty(cs->mems_allowed))
+	if (cpumask_empty(cs->cpus_allowed) || nodes_empty(cs->mems_allowed))
 		return -ENOSPC;
-	if (tsk->flags & PF_THREAD_BOUND) {
-		cpumask_t mask;
 
+	if (tsk->flags & PF_THREAD_BOUND) {
 		mutex_lock(&callback_mutex);
-		mask = cs->cpus_allowed;
+		if (!cpumask_equal(&tsk->cpus_allowed, cs->cpus_allowed))
+			ret = -EINVAL;
 		mutex_unlock(&callback_mutex);
-		if (!cpus_equal(tsk->cpus_allowed, mask))
-			return -EINVAL;
 	}
 
-	return security_task_setscheduler(tsk, 0, NULL);
+	return ret < 0 ? ret : security_task_setscheduler(tsk, 0, NULL);
 }
 
 static void cpuset_attach(struct cgroup_subsys *ss,
 			  struct cgroup *cont, struct cgroup *oldcont,
 			  struct task_struct *tsk)
 {
-	cpumask_t cpus;
 	nodemask_t from, to;
 	struct mm_struct *mm;
 	struct cpuset *cs = cgroup_cs(cont);
 	struct cpuset *oldcs = cgroup_cs(oldcont);
 	int err;
 
-	mutex_lock(&callback_mutex);
-	guarantee_online_cpus(cs, &cpus);
-	err = set_cpus_allowed_ptr(tsk, &cpus);
-	mutex_unlock(&callback_mutex);
+	if (cs == &top_cpuset) {
+		cpumask_copy(cpus_attach, cpu_possible_mask);
+	} else {
+		mutex_lock(&callback_mutex);
+		guarantee_online_cpus(cs, cpus_attach);
+		mutex_unlock(&callback_mutex);
+	}
+	err = set_cpus_allowed_ptr(tsk, cpus_attach);
 	if (err)
 		return;
 
@@ -1348,7 +1392,6 @@ static void cpuset_attach(struct cgroup_subsys *ss,
 			cpuset_migrate_mm(mm, &from, &to);
 		mmput(mm);
 	}
-
 }
 
 /* The various types of files and directories in a cpuset file system */
@@ -1443,21 +1486,29 @@ static int cpuset_write_resmask(struct cgroup *cgrp, struct cftype *cft,
 				const char *buf)
 {
 	int retval = 0;
+	struct cpuset *cs = cgroup_cs(cgrp);
+	struct cpuset *trialcs;
 
 	if (!cgroup_lock_live_group(cgrp))
 		return -ENODEV;
 
+	trialcs = alloc_trial_cpuset(cs);
+	if (!trialcs)
+		return -ENOMEM;
+
 	switch (cft->private) {
 	case FILE_CPULIST:
-		retval = update_cpumask(cgroup_cs(cgrp), buf);
+		retval = update_cpumask(cs, trialcs, buf);
 		break;
 	case FILE_MEMLIST:
-		retval = update_nodemask(cgroup_cs(cgrp), buf);
+		retval = update_nodemask(cs, trialcs, buf);
 		break;
 	default:
 		retval = -EINVAL;
 		break;
 	}
+
+	free_trial_cpuset(trialcs);
 	cgroup_unlock();
 	return retval;
 }
@@ -1476,13 +1527,13 @@ static int cpuset_write_resmask(struct cgroup *cgrp, struct cftype *cft,
 
 static int cpuset_sprintf_cpulist(char *page, struct cpuset *cs)
 {
-	cpumask_t mask;
+	int ret;
 
 	mutex_lock(&callback_mutex);
-	mask = cs->cpus_allowed;
+	ret = cpulist_scnprintf(page, PAGE_SIZE, cs->cpus_allowed);
 	mutex_unlock(&callback_mutex);
 
-	return cpulist_scnprintf(page, PAGE_SIZE, mask);
+	return ret;
 }
 
 static int cpuset_sprintf_memlist(char *page, struct cpuset *cs)
@@ -1718,7 +1769,7 @@ static void cpuset_post_clone(struct cgroup_subsys *ss,
 	parent_cs = cgroup_cs(parent);
 
 	cs->mems_allowed = parent_cs->mems_allowed;
-	cs->cpus_allowed = parent_cs->cpus_allowed;
+	cpumask_copy(cs->cpus_allowed, parent_cs->cpus_allowed);
 	return;
 }
 
@@ -1744,6 +1795,10 @@ static struct cgroup_subsys_state *cpuset_create(
 	cs = kmalloc(sizeof(*cs), GFP_KERNEL);
 	if (!cs)
 		return ERR_PTR(-ENOMEM);
+	if (!alloc_cpumask_var(&cs->cpus_allowed, GFP_KERNEL)) {
+		kfree(cs);
+		return ERR_PTR(-ENOMEM);
+	}
 
 	cpuset_update_task_memory_state();
 	cs->flags = 0;
@@ -1752,7 +1807,7 @@ static struct cgroup_subsys_state *cpuset_create(
 	if (is_spread_slab(parent))
 		set_bit(CS_SPREAD_SLAB, &cs->flags);
 	set_bit(CS_SCHED_LOAD_BALANCE, &cs->flags);
-	cpus_clear(cs->cpus_allowed);
+	cpumask_clear(cs->cpus_allowed);
 	nodes_clear(cs->mems_allowed);
 	cs->mems_generation = cpuset_mems_generation++;
 	fmeter_init(&cs->fmeter);
@@ -1779,6 +1834,7 @@ static void cpuset_destroy(struct cgroup_subsys *ss, struct cgroup *cont)
 		update_flag(CS_SCHED_LOAD_BALANCE, cs, 0);
 
 	number_of_cpusets--;
+	free_cpumask_var(cs->cpus_allowed);
 	kfree(cs);
 }
 
@@ -1802,6 +1858,8 @@ struct cgroup_subsys cpuset_subsys = {
 
 int __init cpuset_init_early(void)
 {
+	alloc_bootmem_cpumask_var(&top_cpuset.cpus_allowed);
+
 	top_cpuset.mems_generation = cpuset_mems_generation++;
 	return 0;
 }
@@ -1817,7 +1875,7 @@ int __init cpuset_init(void)
 {
 	int err = 0;
 
-	cpus_setall(top_cpuset.cpus_allowed);
+	cpumask_setall(top_cpuset.cpus_allowed);
 	nodes_setall(top_cpuset.mems_allowed);
 
 	fmeter_init(&top_cpuset.fmeter);
@@ -1829,6 +1887,9 @@ int __init cpuset_init(void)
 	if (err < 0)
 		return err;
 
+	if (!alloc_cpumask_var(&cpus_attach, GFP_KERNEL))
+		BUG();
+
 	number_of_cpusets = 1;
 	return 0;
 }
@@ -1903,7 +1964,7 @@ static void remove_tasks_in_empty_cpuset(struct cpuset *cs)
 	 * has online cpus, so can't be empty).
 	 */
 	parent = cs->parent;
-	while (cpus_empty(parent->cpus_allowed) ||
+	while (cpumask_empty(parent->cpus_allowed) ||
 			nodes_empty(parent->mems_allowed))
 		parent = parent->parent;
 
@@ -1944,7 +2005,7 @@ static void scan_for_empty_cpusets(struct cpuset *root)
 		}
 
 		/* Continue past cpusets with all cpus, mems online */
-		if (cpus_subset(cp->cpus_allowed, cpu_online_map) &&
+		if (cpumask_subset(cp->cpus_allowed, cpu_online_mask) &&
 		    nodes_subset(cp->mems_allowed, node_states[N_HIGH_MEMORY]))
 			continue;
 
@@ -1952,13 +2013,14 @@ static void scan_for_empty_cpusets(struct cpuset *root)
 
 		/* Remove offline cpus and mems from this cpuset. */
 		mutex_lock(&callback_mutex);
-		cpus_and(cp->cpus_allowed, cp->cpus_allowed, cpu_online_map);
+		cpumask_and(cp->cpus_allowed, cp->cpus_allowed,
+			    cpu_online_mask);
 		nodes_and(cp->mems_allowed, cp->mems_allowed,
 						node_states[N_HIGH_MEMORY]);
 		mutex_unlock(&callback_mutex);
 
 		/* Move tasks from the empty cpuset to a parent */
-		if (cpus_empty(cp->cpus_allowed) ||
+		if (cpumask_empty(cp->cpus_allowed) ||
 		     nodes_empty(cp->mems_allowed))
 			remove_tasks_in_empty_cpuset(cp);
 		else {
@@ -1984,7 +2046,7 @@ static int cpuset_track_online_cpus(struct notifier_block *unused_nb,
 				unsigned long phase, void *unused_cpu)
 {
 	struct sched_domain_attr *attr;
-	cpumask_t *doms;
+	struct cpumask *doms;
 	int ndoms;
 
 	switch (phase) {
@@ -1999,7 +2061,7 @@ static int cpuset_track_online_cpus(struct notifier_block *unused_nb,
 	}
 
 	cgroup_lock();
-	top_cpuset.cpus_allowed = cpu_online_map;
+	cpumask_copy(top_cpuset.cpus_allowed, cpu_online_mask);
 	scan_for_empty_cpusets(&top_cpuset);
 	ndoms = generate_sched_domains(&doms, &attr);
 	cgroup_unlock();
@@ -2044,7 +2106,7 @@ static int cpuset_track_online_nodes(struct notifier_block *self,
 
 void __init cpuset_init_smp(void)
 {
-	top_cpuset.cpus_allowed = cpu_online_map;
+	cpumask_copy(top_cpuset.cpus_allowed, cpu_online_mask);
 	top_cpuset.mems_allowed = node_states[N_HIGH_MEMORY];
 
 	hotcpu_notifier(cpuset_track_online_cpus, 0);
@@ -2054,15 +2116,15 @@ void __init cpuset_init_smp(void)
 /**
  * cpuset_cpus_allowed - return cpus_allowed mask from a tasks cpuset.
  * @tsk: pointer to task_struct from which to obtain cpuset->cpus_allowed.
- * @pmask: pointer to cpumask_t variable to receive cpus_allowed set.
+ * @pmask: pointer to struct cpumask variable to receive cpus_allowed set.
  *
- * Description: Returns the cpumask_t cpus_allowed of the cpuset
+ * Description: Returns the cpumask_var_t cpus_allowed of the cpuset
  * attached to the specified @tsk.  Guaranteed to return some non-empty
  * subset of cpu_online_map, even if this means going outside the
  * tasks cpuset.
  **/
 
-void cpuset_cpus_allowed(struct task_struct *tsk, cpumask_t *pmask)
+void cpuset_cpus_allowed(struct task_struct *tsk, struct cpumask *pmask)
 {
 	mutex_lock(&callback_mutex);
 	cpuset_cpus_allowed_locked(tsk, pmask);
@@ -2073,7 +2135,7 @@ void cpuset_cpus_allowed(struct task_struct *tsk, cpumask_t *pmask)
  * cpuset_cpus_allowed_locked - return cpus_allowed mask from a tasks cpuset.
  * Must be called with callback_mutex held.
  **/
-void cpuset_cpus_allowed_locked(struct task_struct *tsk, cpumask_t *pmask)
+void cpuset_cpus_allowed_locked(struct task_struct *tsk, struct cpumask *pmask)
 {
 	task_lock(tsk);
 	guarantee_online_cpus(task_cs(tsk), pmask);
@@ -2356,6 +2418,29 @@ int cpuset_mems_allowed_intersects(const struct task_struct *tsk1,
 	return nodes_intersects(tsk1->mems_allowed, tsk2->mems_allowed);
 }
 
+/**
+ * cpuset_print_task_mems_allowed - prints task's cpuset and mems_allowed
+ * @task: pointer to task_struct of some task.
+ *
+ * Description: Prints @task's name, cpuset name, and cached copy of its
+ * mems_allowed to the kernel log.  Must hold task_lock(task) to allow
+ * dereferencing task_cs(task).
+ */
+void cpuset_print_task_mems_allowed(struct task_struct *tsk)
+{
+	struct dentry *dentry;
+
+	dentry = task_cs(tsk)->css.cgroup->dentry;
+	spin_lock(&cpuset_buffer_lock);
+	snprintf(cpuset_name, CPUSET_NAME_LEN,
+		 dentry ? (const char *)dentry->d_name.name : "/");
+	nodelist_scnprintf(cpuset_nodelist, CPUSET_NODELIST_LEN,
+			   tsk->mems_allowed);
+	printk(KERN_INFO "%s cpuset=%s mems_allowed=%s\n",
+	       tsk->comm, cpuset_name, cpuset_nodelist);
+	spin_unlock(&cpuset_buffer_lock);
+}
+
 /*
  * Collection of memory_pressure is suppressed unless
  * this flag is enabled by writing "1" to the special
diff --git a/kernel/cred.c b/kernel/cred.c
index ff7bc071991c..3a039189d707 100644
--- a/kernel/cred.c
+++ b/kernel/cred.c
@@ -372,7 +372,8 @@ int commit_creds(struct cred *new)
 	    old->fsuid != new->fsuid ||
 	    old->fsgid != new->fsgid ||
 	    !cap_issubset(new->cap_permitted, old->cap_permitted)) {
-		set_dumpable(task->mm, suid_dumpable);
+		if (task->mm)
+			set_dumpable(task->mm, suid_dumpable);
 		task->pdeath_signal = 0;
 		smp_wmb();
 	}
@@ -506,6 +507,7 @@ struct cred *prepare_kernel_cred(struct task_struct *daemon)
 	else
 		old = get_cred(&init_cred);
 
+	*new = *old;
 	get_uid(new->user);
 	get_group_info(new->group_info);
 
@@ -529,6 +531,7 @@ struct cred *prepare_kernel_cred(struct task_struct *daemon)
 
 error:
 	put_cred(new);
+	put_cred(old);
 	return NULL;
 }
 EXPORT_SYMBOL(prepare_kernel_cred);
diff --git a/kernel/dma-coherent.c b/kernel/dma-coherent.c
index f013a0c2e111..038707404b76 100644
--- a/kernel/dma-coherent.c
+++ b/kernel/dma-coherent.c
@@ -109,20 +109,40 @@ EXPORT_SYMBOL(dma_mark_declared_memory_occupied);
 int dma_alloc_from_coherent(struct device *dev, ssize_t size,
 				       dma_addr_t *dma_handle, void **ret)
 {
-	struct dma_coherent_mem *mem = dev ? dev->dma_mem : NULL;
+	struct dma_coherent_mem *mem;
 	int order = get_order(size);
+	int pageno;
 
-	if (mem) {
-		int page = bitmap_find_free_region(mem->bitmap, mem->size,
-						     order);
-		if (page >= 0) {
-			*dma_handle = mem->device_base + (page << PAGE_SHIFT);
-			*ret = mem->virt_base + (page << PAGE_SHIFT);
-			memset(*ret, 0, size);
-		} else if (mem->flags & DMA_MEMORY_EXCLUSIVE)
-			*ret = NULL;
+	if (!dev)
+		return 0;
+	mem = dev->dma_mem;
+	if (!mem)
+		return 0;
+	if (unlikely(size > mem->size))
+ 		return 0;
+
+	pageno = bitmap_find_free_region(mem->bitmap, mem->size, order);
+	if (pageno >= 0) {
+		/*
+		 * Memory was found in the per-device arena.
+		 */
+		*dma_handle = mem->device_base + (pageno << PAGE_SHIFT);
+		*ret = mem->virt_base + (pageno << PAGE_SHIFT);
+		memset(*ret, 0, size);
+	} else if (mem->flags & DMA_MEMORY_EXCLUSIVE) {
+		/*
+		 * The per-device arena is exhausted and we are not
+		 * permitted to fall back to generic memory.
+		 */
+		*ret = NULL;
+	} else {
+		/*
+		 * The per-device arena is exhausted and we are
+		 * permitted to fall back to generic memory.
+		 */
+		 return 0;
 	}
-	return (mem != NULL);
+	return 1;
 }
 EXPORT_SYMBOL(dma_alloc_from_coherent);
 
diff --git a/kernel/exit.c b/kernel/exit.c
index ad8d04d83a2e..cbdb39a498eb 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -645,35 +645,31 @@ retry:
 	/*
 	 * We found no owner yet mm_users > 1: this implies that we are
 	 * most likely racing with swapoff (try_to_unuse()) or /proc or
-	 * ptrace or page migration (get_task_mm()).  Mark owner as NULL,
-	 * so that subsystems can understand the callback and take action.
+	 * ptrace or page migration (get_task_mm()).  Mark owner as NULL.
 	 */
-	down_write(&mm->mmap_sem);
-	cgroup_mm_owner_callbacks(mm->owner, NULL);
 	mm->owner = NULL;
-	up_write(&mm->mmap_sem);
 	return;
 
 assign_new_owner:
 	BUG_ON(c == p);
 	get_task_struct(c);
-	read_unlock(&tasklist_lock);
-	down_write(&mm->mmap_sem);
 	/*
 	 * The task_lock protects c->mm from changing.
 	 * We always want mm->owner->mm == mm
 	 */
 	task_lock(c);
+	/*
+	 * Delay read_unlock() till we have the task_lock()
+	 * to ensure that c does not slip away underneath us
+	 */
+	read_unlock(&tasklist_lock);
 	if (c->mm != mm) {
 		task_unlock(c);
-		up_write(&mm->mmap_sem);
 		put_task_struct(c);
 		goto retry;
 	}
-	cgroup_mm_owner_callbacks(mm->owner, c);
 	mm->owner = c;
 	task_unlock(c);
-	up_write(&mm->mmap_sem);
 	put_task_struct(c);
 }
 #endif /* CONFIG_MM_OWNER */
@@ -1040,8 +1036,6 @@ NORET_TYPE void do_exit(long code)
 		 * task into the wait for ever nirwana as well.
 		 */
 		tsk->flags |= PF_EXITPIDONE;
-		if (tsk->io_context)
-			exit_io_context();
 		set_current_state(TASK_UNINTERRUPTIBLE);
 		schedule();
 	}
@@ -1060,10 +1054,7 @@ NORET_TYPE void do_exit(long code)
 				preempt_count());
 
 	acct_update_integrals(tsk);
-	if (tsk->mm) {
-		update_hiwater_rss(tsk->mm);
-		update_hiwater_vm(tsk->mm);
-	}
+
 	group_dead = atomic_dec_and_test(&tsk->signal->live);
 	if (group_dead) {
 		hrtimer_cancel(&tsk->signal->real_timer);
@@ -1327,10 +1318,10 @@ static int wait_task_zombie(struct task_struct *p, int options,
 		 * group, which consolidates times for all threads in the
 		 * group including the group leader.
 		 */
+		thread_group_cputime(p, &cputime);
 		spin_lock_irq(&p->parent->sighand->siglock);
 		psig = p->parent->signal;
 		sig = p->signal;
-		thread_group_cputime(p, &cputime);
 		psig->cutime =
 			cputime_add(psig->cutime,
 			cputime_add(cputime.utime,
diff --git a/kernel/extable.c b/kernel/extable.c
index feb0317cf09a..e136ed8d82ba 100644
--- a/kernel/extable.c
+++ b/kernel/extable.c
@@ -67,3 +67,19 @@ int kernel_text_address(unsigned long addr)
 		return 1;
 	return module_text_address(addr) != NULL;
 }
+
+/*
+ * On some architectures (PPC64, IA64) function pointers
+ * are actually only tokens to some data that then holds the
+ * real function address. As a result, to find if a function
+ * pointer is part of the kernel text, we need to do some
+ * special dereferencing first.
+ */
+int func_ptr_is_kernel_text(void *ptr)
+{
+	unsigned long addr;
+	addr = (unsigned long) dereference_function_descriptor(ptr);
+	if (core_kernel_text(addr))
+		return 1;
+	return module_text_address(addr) != NULL;
+}
diff --git a/kernel/fork.c b/kernel/fork.c
index cb706599057f..b1f8609287eb 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -400,6 +400,18 @@ __cacheline_aligned_in_smp DEFINE_SPINLOCK(mmlist_lock);
 #define allocate_mm()	(kmem_cache_alloc(mm_cachep, GFP_KERNEL))
 #define free_mm(mm)	(kmem_cache_free(mm_cachep, (mm)))
 
+static unsigned long default_dump_filter = MMF_DUMP_FILTER_DEFAULT;
+
+static int __init coredump_filter_setup(char *s)
+{
+	default_dump_filter =
+		(simple_strtoul(s, NULL, 0) << MMF_DUMP_FILTER_SHIFT) &
+		MMF_DUMP_FILTER_MASK;
+	return 1;
+}
+
+__setup("coredump_filter=", coredump_filter_setup);
+
 #include <linux/init_task.h>
 
 static struct mm_struct * mm_init(struct mm_struct * mm, struct task_struct *p)
@@ -408,15 +420,14 @@ static struct mm_struct * mm_init(struct mm_struct * mm, struct task_struct *p)
 	atomic_set(&mm->mm_count, 1);
 	init_rwsem(&mm->mmap_sem);
 	INIT_LIST_HEAD(&mm->mmlist);
-	mm->flags = (current->mm) ? current->mm->flags
-				  : MMF_DUMP_FILTER_DEFAULT;
+	mm->flags = (current->mm) ? current->mm->flags : 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);
 	spin_lock_init(&mm->page_table_lock);
-	rwlock_init(&mm->ioctx_list_lock);
-	mm->ioctx_list = NULL;
+	spin_lock_init(&mm->ioctx_lock);
+	INIT_HLIST_HEAD(&mm->ioctx_list);
 	mm->free_area_cache = TASK_UNMAPPED_BASE;
 	mm->cached_hole_size = ~0UL;
 	mm_init_owner(mm, p);
@@ -758,7 +769,7 @@ static int copy_sighand(unsigned long clone_flags, struct task_struct *tsk)
 {
 	struct sighand_struct *sig;
 
-	if (clone_flags & (CLONE_SIGHAND | CLONE_THREAD)) {
+	if (clone_flags & CLONE_SIGHAND) {
 		atomic_inc(&current->sighand->count);
 		return 0;
 	}
@@ -1116,12 +1127,12 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 
 	if (pid != &init_struct_pid) {
 		retval = -ENOMEM;
-		pid = alloc_pid(task_active_pid_ns(p));
+		pid = alloc_pid(p->nsproxy->pid_ns);
 		if (!pid)
 			goto bad_fork_cleanup_io;
 
 		if (clone_flags & CLONE_NEWPID) {
-			retval = pid_ns_prepare_proc(task_active_pid_ns(p));
+			retval = pid_ns_prepare_proc(p->nsproxy->pid_ns);
 			if (retval < 0)
 				goto bad_fork_free_pid;
 		}
@@ -1471,12 +1482,10 @@ void __init proc_caches_init(void)
 	fs_cachep = kmem_cache_create("fs_cache",
 			sizeof(struct fs_struct), 0,
 			SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL);
-	vm_area_cachep = kmem_cache_create("vm_area_struct",
-			sizeof(struct vm_area_struct), 0,
-			SLAB_PANIC, NULL);
 	mm_cachep = kmem_cache_create("mm_struct",
 			sizeof(struct mm_struct), ARCH_MIN_MMSTRUCT_ALIGN,
 			SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL);
+	mmap_init();
 }
 
 /*
diff --git a/kernel/futex.c b/kernel/futex.c
index 4fe790e89d0f..002aa189eb09 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -92,11 +92,12 @@ struct futex_pi_state {
  * A futex_q has a woken state, just like tasks have TASK_RUNNING.
  * It is considered woken when plist_node_empty(&q->list) || q->lock_ptr == 0.
  * The order of wakup is always to make the first condition true, then
- * wake up q->waiters, then make the second condition true.
+ * wake up q->waiter, then make the second condition true.
  */
 struct futex_q {
 	struct plist_node list;
-	wait_queue_head_t waiters;
+	/* There can only be a single waiter */
+	wait_queue_head_t waiter;
 
 	/* Which hash list lock to use: */
 	spinlock_t *lock_ptr;
@@ -123,24 +124,6 @@ struct futex_hash_bucket {
 static struct futex_hash_bucket futex_queues[1<<FUTEX_HASHBITS];
 
 /*
- * Take mm->mmap_sem, when futex is shared
- */
-static inline void futex_lock_mm(struct rw_semaphore *fshared)
-{
-	if (fshared)
-		down_read(fshared);
-}
-
-/*
- * Release mm->mmap_sem, when the futex is shared
- */
-static inline void futex_unlock_mm(struct rw_semaphore *fshared)
-{
-	if (fshared)
-		up_read(fshared);
-}
-
-/*
  * We hash on the keys returned from get_futex_key (see below).
  */
 static struct futex_hash_bucket *hash_futex(union futex_key *key)
@@ -161,6 +144,48 @@ static inline int match_futex(union futex_key *key1, union futex_key *key2)
 		&& key1->both.offset == key2->both.offset);
 }
 
+/*
+ * Take a reference to the resource addressed by a key.
+ * Can be called while holding spinlocks.
+ *
+ */
+static void get_futex_key_refs(union futex_key *key)
+{
+	if (!key->both.ptr)
+		return;
+
+	switch (key->both.offset & (FUT_OFF_INODE|FUT_OFF_MMSHARED)) {
+	case FUT_OFF_INODE:
+		atomic_inc(&key->shared.inode->i_count);
+		break;
+	case FUT_OFF_MMSHARED:
+		atomic_inc(&key->private.mm->mm_count);
+		break;
+	}
+}
+
+/*
+ * Drop a reference to the resource addressed by a key.
+ * The hash bucket spinlock must not be held.
+ */
+static void drop_futex_key_refs(union futex_key *key)
+{
+	if (!key->both.ptr) {
+		/* If we're here then we tried to put a key we failed to get */
+		WARN_ON_ONCE(1);
+		return;
+	}
+
+	switch (key->both.offset & (FUT_OFF_INODE|FUT_OFF_MMSHARED)) {
+	case FUT_OFF_INODE:
+		iput(key->shared.inode);
+		break;
+	case FUT_OFF_MMSHARED:
+		mmdrop(key->private.mm);
+		break;
+	}
+}
+
 /**
  * get_futex_key - Get parameters which are the keys for a futex.
  * @uaddr: virtual address of the futex
@@ -179,12 +204,10 @@ static inline int match_futex(union futex_key *key1, union futex_key *key2)
  * For other futexes, it points to &current->mm->mmap_sem and
  * caller must have taken the reader lock. but NOT any spinlocks.
  */
-static int get_futex_key(u32 __user *uaddr, struct rw_semaphore *fshared,
-			 union futex_key *key)
+static int get_futex_key(u32 __user *uaddr, int fshared, union futex_key *key)
 {
 	unsigned long address = (unsigned long)uaddr;
 	struct mm_struct *mm = current->mm;
-	struct vm_area_struct *vma;
 	struct page *page;
 	int err;
 
@@ -208,100 +231,50 @@ static int get_futex_key(u32 __user *uaddr, struct rw_semaphore *fshared,
 			return -EFAULT;
 		key->private.mm = mm;
 		key->private.address = address;
+		get_futex_key_refs(key);
 		return 0;
 	}
-	/*
-	 * The futex is hashed differently depending on whether
-	 * it's in a shared or private mapping.  So check vma first.
-	 */
-	vma = find_extend_vma(mm, address);
-	if (unlikely(!vma))
-		return -EFAULT;
 
-	/*
-	 * Permissions.
-	 */
-	if (unlikely((vma->vm_flags & (VM_IO|VM_READ)) != VM_READ))
-		return (vma->vm_flags & VM_IO) ? -EPERM : -EACCES;
+again:
+	err = get_user_pages_fast(address, 1, 0, &page);
+	if (err < 0)
+		return err;
+
+	lock_page(page);
+	if (!page->mapping) {
+		unlock_page(page);
+		put_page(page);
+		goto again;
+	}
 
 	/*
 	 * Private mappings are handled in a simple way.
 	 *
 	 * NOTE: When userspace waits on a MAP_SHARED mapping, even if
 	 * it's a read-only handle, it's expected that futexes attach to
-	 * the object not the particular process.  Therefore we use
-	 * VM_MAYSHARE here, not VM_SHARED which is restricted to shared
-	 * mappings of _writable_ handles.
+	 * the object not the particular process.
 	 */
-	if (likely(!(vma->vm_flags & VM_MAYSHARE))) {
-		key->both.offset |= FUT_OFF_MMSHARED; /* reference taken on mm */
+	if (PageAnon(page)) {
+		key->both.offset |= FUT_OFF_MMSHARED; /* ref taken on mm */
 		key->private.mm = mm;
 		key->private.address = address;
-		return 0;
-	}
-
-	/*
-	 * Linear file mappings are also simple.
-	 */
-	key->shared.inode = vma->vm_file->f_path.dentry->d_inode;
-	key->both.offset |= FUT_OFF_INODE; /* inode-based key. */
-	if (likely(!(vma->vm_flags & VM_NONLINEAR))) {
-		key->shared.pgoff = (((address - vma->vm_start) >> PAGE_SHIFT)
-				     + vma->vm_pgoff);
-		return 0;
+	} else {
+		key->both.offset |= FUT_OFF_INODE; /* inode-based key */
+		key->shared.inode = page->mapping->host;
+		key->shared.pgoff = page->index;
 	}
 
-	/*
-	 * We could walk the page table to read the non-linear
-	 * pte, and get the page index without fetching the page
-	 * from swap.  But that's a lot of code to duplicate here
-	 * for a rare case, so we simply fetch the page.
-	 */
-	err = get_user_pages(current, mm, address, 1, 0, 0, &page, NULL);
-	if (err >= 0) {
-		key->shared.pgoff =
-			page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT);
-		put_page(page);
-		return 0;
-	}
-	return err;
-}
+	get_futex_key_refs(key);
 
-/*
- * Take a reference to the resource addressed by a key.
- * Can be called while holding spinlocks.
- *
- */
-static void get_futex_key_refs(union futex_key *key)
-{
-	if (key->both.ptr == NULL)
-		return;
-	switch (key->both.offset & (FUT_OFF_INODE|FUT_OFF_MMSHARED)) {
-		case FUT_OFF_INODE:
-			atomic_inc(&key->shared.inode->i_count);
-			break;
-		case FUT_OFF_MMSHARED:
-			atomic_inc(&key->private.mm->mm_count);
-			break;
-	}
+	unlock_page(page);
+	put_page(page);
+	return 0;
 }
 
-/*
- * Drop a reference to the resource addressed by a key.
- * The hash bucket spinlock must not be held.
- */
-static void drop_futex_key_refs(union futex_key *key)
+static inline
+void put_futex_key(int fshared, union futex_key *key)
 {
-	if (!key->both.ptr)
-		return;
-	switch (key->both.offset & (FUT_OFF_INODE|FUT_OFF_MMSHARED)) {
-		case FUT_OFF_INODE:
-			iput(key->shared.inode);
-			break;
-		case FUT_OFF_MMSHARED:
-			mmdrop(key->private.mm);
-			break;
-	}
+	drop_futex_key_refs(key);
 }
 
 static u32 cmpxchg_futex_value_locked(u32 __user *uaddr, u32 uval, u32 newval)
@@ -328,10 +301,8 @@ static int get_futex_value_locked(u32 *dest, u32 __user *from)
 
 /*
  * Fault handling.
- * if fshared is non NULL, current->mm->mmap_sem is already held
  */
-static int futex_handle_fault(unsigned long address,
-			      struct rw_semaphore *fshared, int attempt)
+static int futex_handle_fault(unsigned long address, int attempt)
 {
 	struct vm_area_struct * vma;
 	struct mm_struct *mm = current->mm;
@@ -340,8 +311,7 @@ static int futex_handle_fault(unsigned long address,
 	if (attempt > 2)
 		return ret;
 
-	if (!fshared)
-		down_read(&mm->mmap_sem);
+	down_read(&mm->mmap_sem);
 	vma = find_vma(mm, address);
 	if (vma && address >= vma->vm_start &&
 	    (vma->vm_flags & VM_WRITE)) {
@@ -361,8 +331,7 @@ static int futex_handle_fault(unsigned long address,
 				current->min_flt++;
 		}
 	}
-	if (!fshared)
-		up_read(&mm->mmap_sem);
+	up_read(&mm->mmap_sem);
 	return ret;
 }
 
@@ -385,6 +354,7 @@ static int refill_pi_state_cache(void)
 	/* pi_mutex gets initialized later */
 	pi_state->owner = NULL;
 	atomic_set(&pi_state->refcount, 1);
+	pi_state->key = FUTEX_KEY_INIT;
 
 	current->pi_state_cache = pi_state;
 
@@ -469,7 +439,7 @@ void exit_pi_state_list(struct task_struct *curr)
 	struct list_head *next, *head = &curr->pi_state_list;
 	struct futex_pi_state *pi_state;
 	struct futex_hash_bucket *hb;
-	union futex_key key;
+	union futex_key key = FUTEX_KEY_INIT;
 
 	if (!futex_cmpxchg_enabled)
 		return;
@@ -614,7 +584,7 @@ static void wake_futex(struct futex_q *q)
 	 * The lock in wake_up_all() is a crucial memory barrier after the
 	 * plist_del() and also before assigning to q->lock_ptr.
 	 */
-	wake_up_all(&q->waiters);
+	wake_up(&q->waiter);
 	/*
 	 * The waiting task can free the futex_q as soon as this is written,
 	 * without taking any locks.  This must come last.
@@ -726,20 +696,17 @@ double_lock_hb(struct futex_hash_bucket *hb1, struct futex_hash_bucket *hb2)
  * Wake up all waiters hashed on the physical page that is mapped
  * to this virtual address:
  */
-static int futex_wake(u32 __user *uaddr, struct rw_semaphore *fshared,
-		      int nr_wake, u32 bitset)
+static int futex_wake(u32 __user *uaddr, int fshared, int nr_wake, u32 bitset)
 {
 	struct futex_hash_bucket *hb;
 	struct futex_q *this, *next;
 	struct plist_head *head;
-	union futex_key key;
+	union futex_key key = FUTEX_KEY_INIT;
 	int ret;
 
 	if (!bitset)
 		return -EINVAL;
 
-	futex_lock_mm(fshared);
-
 	ret = get_futex_key(uaddr, fshared, &key);
 	if (unlikely(ret != 0))
 		goto out;
@@ -766,8 +733,8 @@ static int futex_wake(u32 __user *uaddr, struct rw_semaphore *fshared,
 	}
 
 	spin_unlock(&hb->lock);
+	put_futex_key(fshared, &key);
 out:
-	futex_unlock_mm(fshared);
 	return ret;
 }
 
@@ -776,25 +743,22 @@ out:
  * to this virtual address:
  */
 static int
-futex_wake_op(u32 __user *uaddr1, struct rw_semaphore *fshared,
-	      u32 __user *uaddr2,
+futex_wake_op(u32 __user *uaddr1, int fshared, u32 __user *uaddr2,
 	      int nr_wake, int nr_wake2, int op)
 {
-	union futex_key key1, key2;
+	union futex_key key1 = FUTEX_KEY_INIT, key2 = FUTEX_KEY_INIT;
 	struct futex_hash_bucket *hb1, *hb2;
 	struct plist_head *head;
 	struct futex_q *this, *next;
 	int ret, op_ret, attempt = 0;
 
 retryfull:
-	futex_lock_mm(fshared);
-
 	ret = get_futex_key(uaddr1, fshared, &key1);
 	if (unlikely(ret != 0))
 		goto out;
 	ret = get_futex_key(uaddr2, fshared, &key2);
 	if (unlikely(ret != 0))
-		goto out;
+		goto out_put_key1;
 
 	hb1 = hash_futex(&key1);
 	hb2 = hash_futex(&key2);
@@ -816,12 +780,12 @@ retry:
 		 * but we might get them from range checking
 		 */
 		ret = op_ret;
-		goto out;
+		goto out_put_keys;
 #endif
 
 		if (unlikely(op_ret != -EFAULT)) {
 			ret = op_ret;
-			goto out;
+			goto out_put_keys;
 		}
 
 		/*
@@ -833,18 +797,12 @@ retry:
 		 */
 		if (attempt++) {
 			ret = futex_handle_fault((unsigned long)uaddr2,
-						 fshared, attempt);
+						 attempt);
 			if (ret)
-				goto out;
+				goto out_put_keys;
 			goto retry;
 		}
 
-		/*
-		 * If we would have faulted, release mmap_sem,
-		 * fault it in and start all over again.
-		 */
-		futex_unlock_mm(fshared);
-
 		ret = get_user(dummy, uaddr2);
 		if (ret)
 			return ret;
@@ -879,9 +837,11 @@ retry:
 	spin_unlock(&hb1->lock);
 	if (hb1 != hb2)
 		spin_unlock(&hb2->lock);
+out_put_keys:
+	put_futex_key(fshared, &key2);
+out_put_key1:
+	put_futex_key(fshared, &key1);
 out:
-	futex_unlock_mm(fshared);
-
 	return ret;
 }
 
@@ -889,25 +849,22 @@ out:
  * Requeue all waiters hashed on one physical page to another
  * physical page.
  */
-static int futex_requeue(u32 __user *uaddr1, struct rw_semaphore *fshared,
-			 u32 __user *uaddr2,
+static int futex_requeue(u32 __user *uaddr1, int fshared, u32 __user *uaddr2,
 			 int nr_wake, int nr_requeue, u32 *cmpval)
 {
-	union futex_key key1, key2;
+	union futex_key key1 = FUTEX_KEY_INIT, key2 = FUTEX_KEY_INIT;
 	struct futex_hash_bucket *hb1, *hb2;
 	struct plist_head *head1;
 	struct futex_q *this, *next;
 	int ret, drop_count = 0;
 
- retry:
-	futex_lock_mm(fshared);
-
+retry:
 	ret = get_futex_key(uaddr1, fshared, &key1);
 	if (unlikely(ret != 0))
 		goto out;
 	ret = get_futex_key(uaddr2, fshared, &key2);
 	if (unlikely(ret != 0))
-		goto out;
+		goto out_put_key1;
 
 	hb1 = hash_futex(&key1);
 	hb2 = hash_futex(&key2);
@@ -924,18 +881,12 @@ static int futex_requeue(u32 __user *uaddr1, struct rw_semaphore *fshared,
 			if (hb1 != hb2)
 				spin_unlock(&hb2->lock);
 
-			/*
-			 * If we would have faulted, release mmap_sem, fault
-			 * it in and start all over again.
-			 */
-			futex_unlock_mm(fshared);
-
 			ret = get_user(curval, uaddr1);
 
 			if (!ret)
 				goto retry;
 
-			return ret;
+			goto out_put_keys;
 		}
 		if (curval != *cmpval) {
 			ret = -EAGAIN;
@@ -980,8 +931,11 @@ out_unlock:
 	while (--drop_count >= 0)
 		drop_futex_key_refs(&key1);
 
+out_put_keys:
+	put_futex_key(fshared, &key2);
+out_put_key1:
+	put_futex_key(fshared, &key1);
 out:
-	futex_unlock_mm(fshared);
 	return ret;
 }
 
@@ -990,7 +944,7 @@ static inline struct futex_hash_bucket *queue_lock(struct futex_q *q)
 {
 	struct futex_hash_bucket *hb;
 
-	init_waitqueue_head(&q->waiters);
+	init_waitqueue_head(&q->waiter);
 
 	get_futex_key_refs(&q->key);
 	hb = hash_futex(&q->key);
@@ -1042,7 +996,7 @@ static int unqueue_me(struct futex_q *q)
 	int ret = 0;
 
 	/* In the common case we don't take the spinlock, which is nice. */
- retry:
+retry:
 	lock_ptr = q->lock_ptr;
 	barrier();
 	if (lock_ptr != NULL) {
@@ -1103,8 +1057,7 @@ static void unqueue_me_pi(struct futex_q *q)
  * private futexes.
  */
 static int fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q,
-				struct task_struct *newowner,
-				struct rw_semaphore *fshared)
+				struct task_struct *newowner, int fshared)
 {
 	u32 newtid = task_pid_vnr(newowner) | FUTEX_WAITERS;
 	struct futex_pi_state *pi_state = q->pi_state;
@@ -1183,7 +1136,7 @@ retry:
 handle_fault:
 	spin_unlock(q->lock_ptr);
 
-	ret = futex_handle_fault((unsigned long)uaddr, fshared, attempt++);
+	ret = futex_handle_fault((unsigned long)uaddr, attempt++);
 
 	spin_lock(q->lock_ptr);
 
@@ -1203,12 +1156,13 @@ handle_fault:
  * In case we must use restart_block to restart a futex_wait,
  * we encode in the 'flags' shared capability
  */
-#define FLAGS_SHARED  1
+#define FLAGS_SHARED		0x01
+#define FLAGS_CLOCKRT		0x02
 
 static long futex_wait_restart(struct restart_block *restart);
 
-static int futex_wait(u32 __user *uaddr, struct rw_semaphore *fshared,
-		      u32 val, ktime_t *abs_time, u32 bitset)
+static int futex_wait(u32 __user *uaddr, int fshared,
+		      u32 val, ktime_t *abs_time, u32 bitset, int clockrt)
 {
 	struct task_struct *curr = current;
 	DECLARE_WAITQUEUE(wait, curr);
@@ -1224,12 +1178,11 @@ static int futex_wait(u32 __user *uaddr, struct rw_semaphore *fshared,
 
 	q.pi_state = NULL;
 	q.bitset = bitset;
- retry:
-	futex_lock_mm(fshared);
-
+retry:
+	q.key = FUTEX_KEY_INIT;
 	ret = get_futex_key(uaddr, fshared, &q.key);
 	if (unlikely(ret != 0))
-		goto out_release_sem;
+		goto out;
 
 	hb = queue_lock(&q);
 
@@ -1257,12 +1210,7 @@ static int futex_wait(u32 __user *uaddr, struct rw_semaphore *fshared,
 
 	if (unlikely(ret)) {
 		queue_unlock(&q, hb);
-
-		/*
-		 * If we would have faulted, release mmap_sem, fault it in and
-		 * start all over again.
-		 */
-		futex_unlock_mm(fshared);
+		put_futex_key(fshared, &q.key);
 
 		ret = get_user(uval, uaddr);
 
@@ -1272,18 +1220,12 @@ static int futex_wait(u32 __user *uaddr, struct rw_semaphore *fshared,
 	}
 	ret = -EWOULDBLOCK;
 	if (uval != val)
-		goto out_unlock_release_sem;
+		goto out_unlock_put_key;
 
 	/* Only actually queue if *uaddr contained val.  */
 	queue_me(&q, hb);
 
 	/*
-	 * Now the futex is queued and we have checked the data, we
-	 * don't want to hold mmap_sem while we sleep.
-	 */
-	futex_unlock_mm(fshared);
-
-	/*
 	 * There might have been scheduling since the queue_me(), as we
 	 * cannot hold a spinlock across the get_user() in case it
 	 * faults, and we cannot just set TASK_INTERRUPTIBLE state when
@@ -1294,7 +1236,7 @@ static int futex_wait(u32 __user *uaddr, struct rw_semaphore *fshared,
 
 	/* add_wait_queue is the barrier after __set_current_state. */
 	__set_current_state(TASK_INTERRUPTIBLE);
-	add_wait_queue(&q.waiters, &wait);
+	add_wait_queue(&q.waiter, &wait);
 	/*
 	 * !plist_node_empty() is safe here without any lock.
 	 * q.lock_ptr != 0 is not safe, because of ordering against wakeup.
@@ -1307,8 +1249,10 @@ static int futex_wait(u32 __user *uaddr, struct rw_semaphore *fshared,
 			slack = current->timer_slack_ns;
 			if (rt_task(current))
 				slack = 0;
-			hrtimer_init_on_stack(&t.timer, CLOCK_MONOTONIC,
-						HRTIMER_MODE_ABS);
+			hrtimer_init_on_stack(&t.timer,
+					      clockrt ? CLOCK_REALTIME :
+					      CLOCK_MONOTONIC,
+					      HRTIMER_MODE_ABS);
 			hrtimer_init_sleeper(&t, current);
 			hrtimer_set_expires_range_ns(&t.timer, *abs_time, slack);
 
@@ -1363,14 +1307,16 @@ static int futex_wait(u32 __user *uaddr, struct rw_semaphore *fshared,
 
 		if (fshared)
 			restart->futex.flags |= FLAGS_SHARED;
+		if (clockrt)
+			restart->futex.flags |= FLAGS_CLOCKRT;
 		return -ERESTART_RESTARTBLOCK;
 	}
 
- out_unlock_release_sem:
+out_unlock_put_key:
 	queue_unlock(&q, hb);
+	put_futex_key(fshared, &q.key);
 
- out_release_sem:
-	futex_unlock_mm(fshared);
+out:
 	return ret;
 }
 
@@ -1378,15 +1324,16 @@ static int futex_wait(u32 __user *uaddr, struct rw_semaphore *fshared,
 static long futex_wait_restart(struct restart_block *restart)
 {
 	u32 __user *uaddr = (u32 __user *)restart->futex.uaddr;
-	struct rw_semaphore *fshared = NULL;
+	int fshared = 0;
 	ktime_t t;
 
 	t.tv64 = restart->futex.time;
 	restart->fn = do_no_restart_syscall;
 	if (restart->futex.flags & FLAGS_SHARED)
-		fshared = &current->mm->mmap_sem;
+		fshared = 1;
 	return (long)futex_wait(uaddr, fshared, restart->futex.val, &t,
-				restart->futex.bitset);
+				restart->futex.bitset,
+				restart->futex.flags & FLAGS_CLOCKRT);
 }
 
 
@@ -1396,7 +1343,7 @@ static long futex_wait_restart(struct restart_block *restart)
  * if there are waiters then it will block, it does PI, etc. (Due to
  * races the kernel might see a 0 value of the futex too.)
  */
-static int futex_lock_pi(u32 __user *uaddr, struct rw_semaphore *fshared,
+static int futex_lock_pi(u32 __user *uaddr, int fshared,
 			 int detect, ktime_t *time, int trylock)
 {
 	struct hrtimer_sleeper timeout, *to = NULL;
@@ -1418,17 +1365,16 @@ static int futex_lock_pi(u32 __user *uaddr, struct rw_semaphore *fshared,
 	}
 
 	q.pi_state = NULL;
- retry:
-	futex_lock_mm(fshared);
-
+retry:
+	q.key = FUTEX_KEY_INIT;
 	ret = get_futex_key(uaddr, fshared, &q.key);
 	if (unlikely(ret != 0))
-		goto out_release_sem;
+		goto out;
 
- retry_unlocked:
+retry_unlocked:
 	hb = queue_lock(&q);
 
- retry_locked:
+retry_locked:
 	ret = lock_taken = 0;
 
 	/*
@@ -1449,14 +1395,14 @@ static int futex_lock_pi(u32 __user *uaddr, struct rw_semaphore *fshared,
 	 */
 	if (unlikely((curval & FUTEX_TID_MASK) == task_pid_vnr(current))) {
 		ret = -EDEADLK;
-		goto out_unlock_release_sem;
+		goto out_unlock_put_key;
 	}
 
 	/*
 	 * Surprise - we got the lock. Just return to userspace:
 	 */
 	if (unlikely(!curval))
-		goto out_unlock_release_sem;
+		goto out_unlock_put_key;
 
 	uval = curval;
 
@@ -1492,7 +1438,7 @@ static int futex_lock_pi(u32 __user *uaddr, struct rw_semaphore *fshared,
 	 * We took the lock due to owner died take over.
 	 */
 	if (unlikely(lock_taken))
-		goto out_unlock_release_sem;
+		goto out_unlock_put_key;
 
 	/*
 	 * We dont have the lock. Look up the PI state (or create it if
@@ -1509,7 +1455,6 @@ static int futex_lock_pi(u32 __user *uaddr, struct rw_semaphore *fshared,
 			 * exit to complete.
 			 */
 			queue_unlock(&q, hb);
-			futex_unlock_mm(fshared);
 			cond_resched();
 			goto retry;
 
@@ -1532,7 +1477,7 @@ static int futex_lock_pi(u32 __user *uaddr, struct rw_semaphore *fshared,
 				goto retry_locked;
 			}
 		default:
-			goto out_unlock_release_sem;
+			goto out_unlock_put_key;
 		}
 	}
 
@@ -1541,12 +1486,6 @@ static int futex_lock_pi(u32 __user *uaddr, struct rw_semaphore *fshared,
 	 */
 	queue_me(&q, hb);
 
-	/*
-	 * Now the futex is queued and we have checked the data, we
-	 * don't want to hold mmap_sem while we sleep.
-	 */
-	futex_unlock_mm(fshared);
-
 	WARN_ON(!q.pi_state);
 	/*
 	 * Block on the PI mutex:
@@ -1559,7 +1498,6 @@ static int futex_lock_pi(u32 __user *uaddr, struct rw_semaphore *fshared,
 		ret = ret ? 0 : -EWOULDBLOCK;
 	}
 
-	futex_lock_mm(fshared);
 	spin_lock(q.lock_ptr);
 
 	if (!ret) {
@@ -1625,44 +1563,40 @@ static int futex_lock_pi(u32 __user *uaddr, struct rw_semaphore *fshared,
 
 	/* Unqueue and drop the lock */
 	unqueue_me_pi(&q);
-	futex_unlock_mm(fshared);
 
 	if (to)
 		destroy_hrtimer_on_stack(&to->timer);
 	return ret != -EINTR ? ret : -ERESTARTNOINTR;
 
- out_unlock_release_sem:
+out_unlock_put_key:
 	queue_unlock(&q, hb);
 
- out_release_sem:
-	futex_unlock_mm(fshared);
+out_put_key:
+	put_futex_key(fshared, &q.key);
+out:
 	if (to)
 		destroy_hrtimer_on_stack(&to->timer);
 	return ret;
 
- uaddr_faulted:
+uaddr_faulted:
 	/*
-	 * We have to r/w  *(int __user *)uaddr, but we can't modify it
-	 * non-atomically.  Therefore, if get_user below is not
-	 * enough, we need to handle the fault ourselves, while
-	 * still holding the mmap_sem.
-	 *
-	 * ... and hb->lock. :-) --ANK
+	 * We have to r/w  *(int __user *)uaddr, and we have to modify it
+	 * atomically.  Therefore, if we continue to fault after get_user()
+	 * below, we need to handle the fault ourselves, while still holding
+	 * the mmap_sem.  This can occur if the uaddr is under contention as
+	 * we have to drop the mmap_sem in order to call get_user().
 	 */
 	queue_unlock(&q, hb);
 
 	if (attempt++) {
-		ret = futex_handle_fault((unsigned long)uaddr, fshared,
-					 attempt);
+		ret = futex_handle_fault((unsigned long)uaddr, attempt);
 		if (ret)
-			goto out_release_sem;
+			goto out_put_key;
 		goto retry_unlocked;
 	}
 
-	futex_unlock_mm(fshared);
-
 	ret = get_user(uval, uaddr);
-	if (!ret && (uval != -EFAULT))
+	if (!ret)
 		goto retry;
 
 	if (to)
@@ -1675,13 +1609,13 @@ static int futex_lock_pi(u32 __user *uaddr, struct rw_semaphore *fshared,
  * This is the in-kernel slowpath: we look up the PI state (if any),
  * and do the rt-mutex unlock.
  */
-static int futex_unlock_pi(u32 __user *uaddr, struct rw_semaphore *fshared)
+static int futex_unlock_pi(u32 __user *uaddr, int fshared)
 {
 	struct futex_hash_bucket *hb;
 	struct futex_q *this, *next;
 	u32 uval;
 	struct plist_head *head;
-	union futex_key key;
+	union futex_key key = FUTEX_KEY_INIT;
 	int ret, attempt = 0;
 
 retry:
@@ -1692,10 +1626,6 @@ retry:
 	 */
 	if ((uval & FUTEX_TID_MASK) != task_pid_vnr(current))
 		return -EPERM;
-	/*
-	 * First take all the futex related locks:
-	 */
-	futex_lock_mm(fshared);
 
 	ret = get_futex_key(uaddr, fshared, &key);
 	if (unlikely(ret != 0))
@@ -1753,35 +1683,31 @@ retry_unlocked:
 
 out_unlock:
 	spin_unlock(&hb->lock);
-out:
-	futex_unlock_mm(fshared);
+	put_futex_key(fshared, &key);
 
+out:
 	return ret;
 
 pi_faulted:
 	/*
-	 * We have to r/w  *(int __user *)uaddr, but we can't modify it
-	 * non-atomically.  Therefore, if get_user below is not
-	 * enough, we need to handle the fault ourselves, while
-	 * still holding the mmap_sem.
-	 *
-	 * ... and hb->lock. --ANK
+	 * We have to r/w  *(int __user *)uaddr, and we have to modify it
+	 * atomically.  Therefore, if we continue to fault after get_user()
+	 * below, we need to handle the fault ourselves, while still holding
+	 * the mmap_sem.  This can occur if the uaddr is under contention as
+	 * we have to drop the mmap_sem in order to call get_user().
 	 */
 	spin_unlock(&hb->lock);
 
 	if (attempt++) {
-		ret = futex_handle_fault((unsigned long)uaddr, fshared,
-					 attempt);
+		ret = futex_handle_fault((unsigned long)uaddr, attempt);
 		if (ret)
 			goto out;
 		uval = 0;
 		goto retry_unlocked;
 	}
 
-	futex_unlock_mm(fshared);
-
 	ret = get_user(uval, uaddr);
-	if (!ret && (uval != -EFAULT))
+	if (!ret)
 		goto retry;
 
 	return ret;
@@ -1908,8 +1834,7 @@ retry:
 		 * PI futexes happens in exit_pi_state():
 		 */
 		if (!pi && (uval & FUTEX_WAITERS))
-			futex_wake(uaddr, &curr->mm->mmap_sem, 1,
-				   FUTEX_BITSET_MATCH_ANY);
+			futex_wake(uaddr, 1, 1, FUTEX_BITSET_MATCH_ANY);
 	}
 	return 0;
 }
@@ -2003,18 +1928,22 @@ void exit_robust_list(struct task_struct *curr)
 long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout,
 		u32 __user *uaddr2, u32 val2, u32 val3)
 {
-	int ret = -ENOSYS;
+	int clockrt, ret = -ENOSYS;
 	int cmd = op & FUTEX_CMD_MASK;
-	struct rw_semaphore *fshared = NULL;
+	int fshared = 0;
 
 	if (!(op & FUTEX_PRIVATE_FLAG))
-		fshared = &current->mm->mmap_sem;
+		fshared = 1;
+
+	clockrt = op & FUTEX_CLOCK_REALTIME;
+	if (clockrt && cmd != FUTEX_WAIT_BITSET)
+		return -ENOSYS;
 
 	switch (cmd) {
 	case FUTEX_WAIT:
 		val3 = FUTEX_BITSET_MATCH_ANY;
 	case FUTEX_WAIT_BITSET:
-		ret = futex_wait(uaddr, fshared, val, timeout, val3);
+		ret = futex_wait(uaddr, fshared, val, timeout, val3, clockrt);
 		break;
 	case FUTEX_WAKE:
 		val3 = FUTEX_BITSET_MATCH_ANY;
diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index 47e63349d1b2..1455b7651b6b 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -32,7 +32,6 @@
  */
 
 #include <linux/cpu.h>
-#include <linux/irq.h>
 #include <linux/module.h>
 #include <linux/percpu.h>
 #include <linux/hrtimer.h>
@@ -442,22 +441,6 @@ static inline void debug_hrtimer_activate(struct hrtimer *timer) { }
 static inline void debug_hrtimer_deactivate(struct hrtimer *timer) { }
 #endif
 
-/*
- * Check, whether the timer is on the callback pending list
- */
-static inline int hrtimer_cb_pending(const struct hrtimer *timer)
-{
-	return timer->state & HRTIMER_STATE_PENDING;
-}
-
-/*
- * Remove a timer from the callback pending list
- */
-static inline void hrtimer_remove_cb_pending(struct hrtimer *timer)
-{
-	list_del_init(&timer->cb_entry);
-}
-
 /* High resolution timer related functions */
 #ifdef CONFIG_HIGH_RES_TIMERS
 
@@ -651,6 +634,7 @@ static inline void hrtimer_init_timer_hres(struct hrtimer *timer)
 {
 }
 
+
 /*
  * When High resolution timers are active, try to reprogram. Note, that in case
  * the state has HRTIMER_STATE_CALLBACK set, no reprogramming and no expiry
@@ -661,31 +645,10 @@ static inline int hrtimer_enqueue_reprogram(struct hrtimer *timer,
 					    struct hrtimer_clock_base *base)
 {
 	if (base->cpu_base->hres_active && hrtimer_reprogram(timer, base)) {
-
-		/* Timer is expired, act upon the callback mode */
-		switch(timer->cb_mode) {
-		case HRTIMER_CB_IRQSAFE_PERCPU:
-		case HRTIMER_CB_IRQSAFE_UNLOCKED:
-			/*
-			 * This is solely for the sched tick emulation with
-			 * dynamic tick support to ensure that we do not
-			 * restart the tick right on the edge and end up with
-			 * the tick timer in the softirq ! The calling site
-			 * takes care of this. Also used for hrtimer sleeper !
-			 */
-			debug_hrtimer_deactivate(timer);
-			return 1;
-		case HRTIMER_CB_SOFTIRQ:
-			/*
-			 * Move everything else into the softirq pending list !
-			 */
-			list_add_tail(&timer->cb_entry,
-				      &base->cpu_base->cb_pending);
-			timer->state = HRTIMER_STATE_PENDING;
-			return 1;
-		default:
-			BUG();
-		}
+		spin_unlock(&base->cpu_base->lock);
+		raise_softirq_irqoff(HRTIMER_SOFTIRQ);
+		spin_lock(&base->cpu_base->lock);
+		return 1;
 	}
 	return 0;
 }
@@ -724,11 +687,6 @@ static int hrtimer_switch_to_hres(void)
 	return 1;
 }
 
-static inline void hrtimer_raise_softirq(void)
-{
-	raise_softirq(HRTIMER_SOFTIRQ);
-}
-
 #else
 
 static inline int hrtimer_hres_active(void) { return 0; }
@@ -742,12 +700,6 @@ static inline int hrtimer_enqueue_reprogram(struct hrtimer *timer,
 }
 static inline void hrtimer_init_hres(struct hrtimer_cpu_base *base) { }
 static inline void hrtimer_init_timer_hres(struct hrtimer *timer) { }
-static inline int hrtimer_reprogram(struct hrtimer *timer,
-				    struct hrtimer_clock_base *base)
-{
-	return 0;
-}
-static inline void hrtimer_raise_softirq(void) { }
 
 #endif /* CONFIG_HIGH_RES_TIMERS */
 
@@ -818,9 +770,11 @@ EXPORT_SYMBOL_GPL(hrtimer_forward);
  *
  * The timer is inserted in expiry order. Insertion into the
  * red black tree is O(log(n)). Must hold the base lock.
+ *
+ * Returns 1 when the new timer is the leftmost timer in the tree.
  */
-static void enqueue_hrtimer(struct hrtimer *timer,
-			    struct hrtimer_clock_base *base, int reprogram)
+static int enqueue_hrtimer(struct hrtimer *timer,
+			   struct hrtimer_clock_base *base)
 {
 	struct rb_node **link = &base->active.rb_node;
 	struct rb_node *parent = NULL;
@@ -852,20 +806,8 @@ static void enqueue_hrtimer(struct hrtimer *timer,
 	 * Insert the timer to the rbtree and check whether it
 	 * replaces the first pending timer
 	 */
-	if (leftmost) {
-		/*
-		 * Reprogram the clock event device. When the timer is already
-		 * expired hrtimer_enqueue_reprogram has either called the
-		 * callback or added it to the pending list and raised the
-		 * softirq.
-		 *
-		 * This is a NOP for !HIGHRES
-		 */
-		if (reprogram && hrtimer_enqueue_reprogram(timer, base))
-			return;
-
+	if (leftmost)
 		base->first = &timer->node;
-	}
 
 	rb_link_node(&timer->node, parent, link);
 	rb_insert_color(&timer->node, &base->active);
@@ -874,6 +816,8 @@ static void enqueue_hrtimer(struct hrtimer *timer,
 	 * state of a possibly running callback.
 	 */
 	timer->state |= HRTIMER_STATE_ENQUEUED;
+
+	return leftmost;
 }
 
 /*
@@ -890,10 +834,7 @@ static void __remove_hrtimer(struct hrtimer *timer,
 			     struct hrtimer_clock_base *base,
 			     unsigned long newstate, int reprogram)
 {
-	/* High res. callback list. NOP for !HIGHRES */
-	if (hrtimer_cb_pending(timer))
-		hrtimer_remove_cb_pending(timer);
-	else {
+	if (timer->state & HRTIMER_STATE_ENQUEUED) {
 		/*
 		 * Remove the timer from the rbtree and replace the
 		 * first entry pointer if necessary.
@@ -953,7 +894,7 @@ hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, unsigned long delta_n
 {
 	struct hrtimer_clock_base *base, *new_base;
 	unsigned long flags;
-	int ret, raise;
+	int ret, leftmost;
 
 	base = lock_hrtimer_base(timer, &flags);
 
@@ -981,33 +922,19 @@ hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, unsigned long delta_n
 
 	timer_stats_hrtimer_set_start_info(timer);
 
+	leftmost = enqueue_hrtimer(timer, new_base);
+
 	/*
 	 * Only allow reprogramming if the new base is on this CPU.
 	 * (it might still be on another CPU if the timer was pending)
+	 *
+	 * XXX send_remote_softirq() ?
 	 */
-	enqueue_hrtimer(timer, new_base,
-			new_base->cpu_base == &__get_cpu_var(hrtimer_bases));
-
-	/*
-	 * The timer may be expired and moved to the cb_pending
-	 * list. We can not raise the softirq with base lock held due
-	 * to a possible deadlock with runqueue lock.
-	 */
-	raise = timer->state == HRTIMER_STATE_PENDING;
-
-	/*
-	 * We use preempt_disable to prevent this task from migrating after
-	 * setting up the softirq and raising it. Otherwise, if me migrate
-	 * we will raise the softirq on the wrong CPU.
-	 */
-	preempt_disable();
+	if (leftmost && new_base->cpu_base == &__get_cpu_var(hrtimer_bases))
+		hrtimer_enqueue_reprogram(timer, new_base);
 
 	unlock_hrtimer_base(timer, &flags);
 
-	if (raise)
-		hrtimer_raise_softirq();
-	preempt_enable();
-
 	return ret;
 }
 EXPORT_SYMBOL_GPL(hrtimer_start_range_ns);
@@ -1192,75 +1119,6 @@ int hrtimer_get_res(const clockid_t which_clock, struct timespec *tp)
 }
 EXPORT_SYMBOL_GPL(hrtimer_get_res);
 
-static void run_hrtimer_pending(struct hrtimer_cpu_base *cpu_base)
-{
-	spin_lock_irq(&cpu_base->lock);
-
-	while (!list_empty(&cpu_base->cb_pending)) {
-		enum hrtimer_restart (*fn)(struct hrtimer *);
-		struct hrtimer *timer;
-		int restart;
-		int emulate_hardirq_ctx = 0;
-
-		timer = list_entry(cpu_base->cb_pending.next,
-				   struct hrtimer, cb_entry);
-
-		debug_hrtimer_deactivate(timer);
-		timer_stats_account_hrtimer(timer);
-
-		fn = timer->function;
-		/*
-		 * A timer might have been added to the cb_pending list
-		 * when it was migrated during a cpu-offline operation.
-		 * Emulate hardirq context for such timers.
-		 */
-		if (timer->cb_mode == HRTIMER_CB_IRQSAFE_PERCPU ||
-		    timer->cb_mode == HRTIMER_CB_IRQSAFE_UNLOCKED)
-			emulate_hardirq_ctx = 1;
-
-		__remove_hrtimer(timer, timer->base, HRTIMER_STATE_CALLBACK, 0);
-		spin_unlock_irq(&cpu_base->lock);
-
-		if (unlikely(emulate_hardirq_ctx)) {
-			local_irq_disable();
-			restart = fn(timer);
-			local_irq_enable();
-		} else
-			restart = fn(timer);
-
-		spin_lock_irq(&cpu_base->lock);
-
-		timer->state &= ~HRTIMER_STATE_CALLBACK;
-		if (restart == HRTIMER_RESTART) {
-			BUG_ON(hrtimer_active(timer));
-			/*
-			 * Enqueue the timer, allow reprogramming of the event
-			 * device
-			 */
-			enqueue_hrtimer(timer, timer->base, 1);
-		} else if (hrtimer_active(timer)) {
-			/*
-			 * If the timer was rearmed on another CPU, reprogram
-			 * the event device.
-			 */
-			struct hrtimer_clock_base *base = timer->base;
-
-			if (base->first == &timer->node &&
-			    hrtimer_reprogram(timer, base)) {
-				/*
-				 * Timer is expired. Thus move it from tree to
-				 * pending list again.
-				 */
-				__remove_hrtimer(timer, base,
-						 HRTIMER_STATE_PENDING, 0);
-				list_add_tail(&timer->cb_entry,
-					      &base->cpu_base->cb_pending);
-			}
-		}
-	}
-	spin_unlock_irq(&cpu_base->lock);
-}
-
 static void __run_hrtimer(struct hrtimer *timer)
 {
 	struct hrtimer_clock_base *base = timer->base;
@@ -1268,34 +1126,30 @@ static void __run_hrtimer(struct hrtimer *timer)
 	enum hrtimer_restart (*fn)(struct hrtimer *);
 	int restart;
 
+	WARN_ON(!irqs_disabled());
+
 	debug_hrtimer_deactivate(timer);
 	__remove_hrtimer(timer, base, HRTIMER_STATE_CALLBACK, 0);
 	timer_stats_account_hrtimer(timer);
-
 	fn = timer->function;
-	if (timer->cb_mode == HRTIMER_CB_IRQSAFE_PERCPU ||
-	    timer->cb_mode == HRTIMER_CB_IRQSAFE_UNLOCKED) {
-		/*
-		 * Used for scheduler timers, avoid lock inversion with
-		 * rq->lock and tasklist_lock.
-		 *
-		 * These timers are required to deal with enqueue expiry
-		 * themselves and are not allowed to migrate.
-		 */
-		spin_unlock(&cpu_base->lock);
-		restart = fn(timer);
-		spin_lock(&cpu_base->lock);
-	} else
-		restart = fn(timer);
 
 	/*
-	 * Note: We clear the CALLBACK bit after enqueue_hrtimer to avoid
-	 * reprogramming of the event hardware. This happens at the end of this
-	 * function anyway.
+	 * Because we run timers from hardirq context, there is no chance
+	 * they get migrated to another cpu, therefore its safe to unlock
+	 * the timer base.
+	 */
+	spin_unlock(&cpu_base->lock);
+	restart = fn(timer);
+	spin_lock(&cpu_base->lock);
+
+	/*
+	 * Note: We clear the CALLBACK bit after enqueue_hrtimer and
+	 * we do not reprogramm the event hardware. Happens either in
+	 * hrtimer_start_range_ns() or in hrtimer_interrupt()
 	 */
 	if (restart != HRTIMER_NORESTART) {
 		BUG_ON(timer->state != HRTIMER_STATE_CALLBACK);
-		enqueue_hrtimer(timer, base, 0);
+		enqueue_hrtimer(timer, base);
 	}
 	timer->state &= ~HRTIMER_STATE_CALLBACK;
 }
@@ -1311,7 +1165,7 @@ void hrtimer_interrupt(struct clock_event_device *dev)
 	struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases);
 	struct hrtimer_clock_base *base;
 	ktime_t expires_next, now;
-	int i, raise = 0;
+	int i;
 
 	BUG_ON(!cpu_base->hres_active);
 	cpu_base->nr_events++;
@@ -1360,16 +1214,6 @@ void hrtimer_interrupt(struct clock_event_device *dev)
 				break;
 			}
 
-			/* Move softirq callbacks to the pending list */
-			if (timer->cb_mode == HRTIMER_CB_SOFTIRQ) {
-				__remove_hrtimer(timer, base,
-						 HRTIMER_STATE_PENDING, 0);
-				list_add_tail(&timer->cb_entry,
-					      &base->cpu_base->cb_pending);
-				raise = 1;
-				continue;
-			}
-
 			__run_hrtimer(timer);
 		}
 		spin_unlock(&cpu_base->lock);
@@ -1383,10 +1227,22 @@ void hrtimer_interrupt(struct clock_event_device *dev)
 		if (tick_program_event(expires_next, 0))
 			goto retry;
 	}
+}
+
+/*
+ * local version of hrtimer_peek_ahead_timers() called with interrupts
+ * disabled.
+ */
+static void __hrtimer_peek_ahead_timers(void)
+{
+	struct tick_device *td;
+
+	if (!hrtimer_hres_active())
+		return;
 
-	/* Raise softirq ? */
-	if (raise)
-		raise_softirq(HRTIMER_SOFTIRQ);
+	td = &__get_cpu_var(tick_cpu_device);
+	if (td && td->evtdev)
+		hrtimer_interrupt(td->evtdev);
 }
 
 /**
@@ -1400,25 +1256,23 @@ void hrtimer_interrupt(struct clock_event_device *dev)
  */
 void hrtimer_peek_ahead_timers(void)
 {
-	struct tick_device *td;
 	unsigned long flags;
 
-	if (!hrtimer_hres_active())
-		return;
-
 	local_irq_save(flags);
-	td = &__get_cpu_var(tick_cpu_device);
-	if (td && td->evtdev)
-		hrtimer_interrupt(td->evtdev);
+	__hrtimer_peek_ahead_timers();
 	local_irq_restore(flags);
 }
 
 static void run_hrtimer_softirq(struct softirq_action *h)
 {
-	run_hrtimer_pending(&__get_cpu_var(hrtimer_bases));
+	hrtimer_peek_ahead_timers();
 }
 
-#endif	/* CONFIG_HIGH_RES_TIMERS */
+#else /* CONFIG_HIGH_RES_TIMERS */
+
+static inline void __hrtimer_peek_ahead_timers(void) { }
+
+#endif	/* !CONFIG_HIGH_RES_TIMERS */
 
 /*
  * Called from timer softirq every jiffy, expire hrtimers:
@@ -1429,8 +1283,6 @@ static void run_hrtimer_softirq(struct softirq_action *h)
  */
 void hrtimer_run_pending(void)
 {
-	struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases);
-
 	if (hrtimer_hres_active())
 		return;
 
@@ -1444,8 +1296,6 @@ void hrtimer_run_pending(void)
 	 */
 	if (tick_check_oneshot_change(!hrtimer_is_hres_enabled()))
 		hrtimer_switch_to_hres();
-
-	run_hrtimer_pending(cpu_base);
 }
 
 /*
@@ -1482,14 +1332,6 @@ void hrtimer_run_queues(void)
 					hrtimer_get_expires_tv64(timer))
 				break;
 
-			if (timer->cb_mode == HRTIMER_CB_SOFTIRQ) {
-				__remove_hrtimer(timer, base,
-					HRTIMER_STATE_PENDING, 0);
-				list_add_tail(&timer->cb_entry,
-					&base->cpu_base->cb_pending);
-				continue;
-			}
-
 			__run_hrtimer(timer);
 		}
 		spin_unlock(&cpu_base->lock);
@@ -1516,9 +1358,6 @@ void hrtimer_init_sleeper(struct hrtimer_sleeper *sl, struct task_struct *task)
 {
 	sl->timer.function = hrtimer_wakeup;
 	sl->task = task;
-#ifdef CONFIG_HIGH_RES_TIMERS
-	sl->timer.cb_mode = HRTIMER_CB_IRQSAFE_UNLOCKED;
-#endif
 }
 
 static int __sched do_nanosleep(struct hrtimer_sleeper *t, enum hrtimer_mode mode)
@@ -1655,18 +1494,16 @@ static void __cpuinit init_hrtimers_cpu(int cpu)
 	for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++)
 		cpu_base->clock_base[i].cpu_base = cpu_base;
 
-	INIT_LIST_HEAD(&cpu_base->cb_pending);
 	hrtimer_init_hres(cpu_base);
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
 
-static int migrate_hrtimer_list(struct hrtimer_clock_base *old_base,
-				struct hrtimer_clock_base *new_base, int dcpu)
+static void migrate_hrtimer_list(struct hrtimer_clock_base *old_base,
+				struct hrtimer_clock_base *new_base)
 {
 	struct hrtimer *timer;
 	struct rb_node *node;
-	int raise = 0;
 
 	while ((node = rb_first(&old_base->active))) {
 		timer = rb_entry(node, struct hrtimer, node);
@@ -1674,18 +1511,6 @@ static int migrate_hrtimer_list(struct hrtimer_clock_base *old_base,
 		debug_hrtimer_deactivate(timer);
 
 		/*
-		 * Should not happen. Per CPU timers should be
-		 * canceled _before_ the migration code is called
-		 */
-		if (timer->cb_mode == HRTIMER_CB_IRQSAFE_PERCPU) {
-			__remove_hrtimer(timer, old_base,
-					 HRTIMER_STATE_INACTIVE, 0);
-			WARN(1, "hrtimer (%p %p)active but cpu %d dead\n",
-			     timer, timer->function, dcpu);
-			continue;
-		}
-
-		/*
 		 * Mark it as STATE_MIGRATE not INACTIVE otherwise the
 		 * timer could be seen as !active and just vanish away
 		 * under us on another CPU
@@ -1693,112 +1518,73 @@ static int migrate_hrtimer_list(struct hrtimer_clock_base *old_base,
 		__remove_hrtimer(timer, old_base, HRTIMER_STATE_MIGRATE, 0);
 		timer->base = new_base;
 		/*
-		 * Enqueue the timer. Allow reprogramming of the event device
+		 * Enqueue the timers on the new cpu. This does not
+		 * reprogram the event device in case the timer
+		 * expires before the earliest on this CPU, but we run
+		 * hrtimer_interrupt after we migrated everything to
+		 * sort out already expired timers and reprogram the
+		 * event device.
 		 */
-		enqueue_hrtimer(timer, new_base, 1);
+		enqueue_hrtimer(timer, new_base);
 
-#ifdef CONFIG_HIGH_RES_TIMERS
-		/*
-		 * Happens with high res enabled when the timer was
-		 * already expired and the callback mode is
-		 * HRTIMER_CB_IRQSAFE_UNLOCKED (hrtimer_sleeper). The
-		 * enqueue code does not move them to the soft irq
-		 * pending list for performance/latency reasons, but
-		 * in the migration state, we need to do that
-		 * otherwise we end up with a stale timer.
-		 */
-		if (timer->state == HRTIMER_STATE_MIGRATE) {
-			timer->state = HRTIMER_STATE_PENDING;
-			list_add_tail(&timer->cb_entry,
-				      &new_base->cpu_base->cb_pending);
-			raise = 1;
-		}
-#endif
 		/* Clear the migration state bit */
 		timer->state &= ~HRTIMER_STATE_MIGRATE;
 	}
-	return raise;
-}
-
-#ifdef CONFIG_HIGH_RES_TIMERS
-static int migrate_hrtimer_pending(struct hrtimer_cpu_base *old_base,
-				   struct hrtimer_cpu_base *new_base)
-{
-	struct hrtimer *timer;
-	int raise = 0;
-
-	while (!list_empty(&old_base->cb_pending)) {
-		timer = list_entry(old_base->cb_pending.next,
-				   struct hrtimer, cb_entry);
-
-		__remove_hrtimer(timer, timer->base, HRTIMER_STATE_PENDING, 0);
-		timer->base = &new_base->clock_base[timer->base->index];
-		list_add_tail(&timer->cb_entry, &new_base->cb_pending);
-		raise = 1;
-	}
-	return raise;
-}
-#else
-static int migrate_hrtimer_pending(struct hrtimer_cpu_base *old_base,
-				   struct hrtimer_cpu_base *new_base)
-{
-	return 0;
 }
-#endif
 
-static void migrate_hrtimers(int cpu)
+static void migrate_hrtimers(int scpu)
 {
 	struct hrtimer_cpu_base *old_base, *new_base;
-	int i, raise = 0;
+	int i;
 
-	BUG_ON(cpu_online(cpu));
-	old_base = &per_cpu(hrtimer_bases, cpu);
-	new_base = &get_cpu_var(hrtimer_bases);
+	BUG_ON(cpu_online(scpu));
+	tick_cancel_sched_timer(scpu);
 
-	tick_cancel_sched_timer(cpu);
+	local_irq_disable();
+	old_base = &per_cpu(hrtimer_bases, scpu);
+	new_base = &__get_cpu_var(hrtimer_bases);
 	/*
 	 * The caller is globally serialized and nobody else
 	 * takes two locks at once, deadlock is not possible.
 	 */
-	spin_lock_irq(&new_base->lock);
+	spin_lock(&new_base->lock);
 	spin_lock_nested(&old_base->lock, SINGLE_DEPTH_NESTING);
 
 	for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) {
-		if (migrate_hrtimer_list(&old_base->clock_base[i],
-					 &new_base->clock_base[i], cpu))
-			raise = 1;
+		migrate_hrtimer_list(&old_base->clock_base[i],
+				     &new_base->clock_base[i]);
 	}
 
-	if (migrate_hrtimer_pending(old_base, new_base))
-		raise = 1;
-
 	spin_unlock(&old_base->lock);
-	spin_unlock_irq(&new_base->lock);
-	put_cpu_var(hrtimer_bases);
+	spin_unlock(&new_base->lock);
 
-	if (raise)
-		hrtimer_raise_softirq();
+	/* Check, if we got expired work to do */
+	__hrtimer_peek_ahead_timers();
+	local_irq_enable();
 }
+
 #endif /* CONFIG_HOTPLUG_CPU */
 
 static int __cpuinit hrtimer_cpu_notify(struct notifier_block *self,
 					unsigned long action, void *hcpu)
 {
-	unsigned int cpu = (long)hcpu;
+	int scpu = (long)hcpu;
 
 	switch (action) {
 
 	case CPU_UP_PREPARE:
 	case CPU_UP_PREPARE_FROZEN:
-		init_hrtimers_cpu(cpu);
+		init_hrtimers_cpu(scpu);
 		break;
 
 #ifdef CONFIG_HOTPLUG_CPU
 	case CPU_DEAD:
 	case CPU_DEAD_FROZEN:
-		clockevents_notify(CLOCK_EVT_NOTIFY_CPU_DEAD, &cpu);
-		migrate_hrtimers(cpu);
+	{
+		clockevents_notify(CLOCK_EVT_NOTIFY_CPU_DEAD, &scpu);
+		migrate_hrtimers(scpu);
 		break;
+	}
 #endif
 
 	default:
diff --git a/kernel/irq/Makefile b/kernel/irq/Makefile
index 681c52dbfe22..4dd5b1edac98 100644
--- a/kernel/irq/Makefile
+++ b/kernel/irq/Makefile
@@ -3,3 +3,4 @@ obj-y := handle.o manage.o spurious.o resend.o chip.o devres.o
 obj-$(CONFIG_GENERIC_IRQ_PROBE) += autoprobe.o
 obj-$(CONFIG_PROC_FS) += proc.o
 obj-$(CONFIG_GENERIC_PENDING_IRQ) += migration.o
+obj-$(CONFIG_NUMA_MIGRATE_IRQ_DESC) += numa_migrate.o
diff --git a/kernel/irq/autoprobe.c b/kernel/irq/autoprobe.c
index cc0f7321b8ce..1de9700f416e 100644
--- a/kernel/irq/autoprobe.c
+++ b/kernel/irq/autoprobe.c
@@ -10,6 +10,7 @@
 #include <linux/module.h>
 #include <linux/interrupt.h>
 #include <linux/delay.h>
+#include <linux/async.h>
 
 #include "internals.h"
 
@@ -34,6 +35,10 @@ unsigned long probe_irq_on(void)
 	unsigned int status;
 	int i;
 
+	/*
+	 * quiesce the kernel, or at least the asynchronous portion
+	 */
+	async_synchronize_full();
 	mutex_lock(&probing_active);
 	/*
 	 * something may have generated an irq long ago and we want to
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index 10b5092e9bfe..f63c706d25e1 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -24,9 +24,10 @@
  */
 void dynamic_irq_init(unsigned int irq)
 {
-	struct irq_desc *desc = irq_to_desc(irq);
+	struct irq_desc *desc;
 	unsigned long flags;
 
+	desc = irq_to_desc(irq);
 	if (!desc) {
 		WARN(1, KERN_ERR "Trying to initialize invalid IRQ%d\n", irq);
 		return;
@@ -45,7 +46,7 @@ void dynamic_irq_init(unsigned int irq)
 	desc->irq_count = 0;
 	desc->irqs_unhandled = 0;
 #ifdef CONFIG_SMP
-	cpus_setall(desc->affinity);
+	cpumask_setall(&desc->affinity);
 #endif
 	spin_unlock_irqrestore(&desc->lock, flags);
 }
@@ -124,6 +125,7 @@ int set_irq_type(unsigned int irq, unsigned int type)
 		return -ENODEV;
 	}
 
+	type &= IRQ_TYPE_SENSE_MASK;
 	if (type == IRQ_TYPE_NONE)
 		return 0;
 
@@ -352,6 +354,7 @@ handle_level_irq(unsigned int irq, struct irq_desc *desc)
 
 	spin_lock(&desc->lock);
 	mask_ack_irq(desc, irq);
+	desc = irq_remap_to_desc(irq, desc);
 
 	if (unlikely(desc->status & IRQ_INPROGRESS))
 		goto out_unlock;
@@ -429,6 +432,7 @@ handle_fasteoi_irq(unsigned int irq, struct irq_desc *desc)
 	desc->status &= ~IRQ_INPROGRESS;
 out:
 	desc->chip->eoi(irq);
+	desc = irq_remap_to_desc(irq, desc);
 
 	spin_unlock(&desc->lock);
 }
@@ -465,12 +469,14 @@ handle_edge_irq(unsigned int irq, struct irq_desc *desc)
 		    !desc->action)) {
 		desc->status |= (IRQ_PENDING | IRQ_MASKED);
 		mask_ack_irq(desc, irq);
+		desc = irq_remap_to_desc(irq, desc);
 		goto out_unlock;
 	}
 	kstat_incr_irqs_this_cpu(irq, desc);
 
 	/* Start handling the irq */
 	desc->chip->ack(irq);
+	desc = irq_remap_to_desc(irq, desc);
 
 	/* Mark the IRQ currently in progress.*/
 	desc->status |= IRQ_INPROGRESS;
@@ -531,8 +537,10 @@ handle_percpu_irq(unsigned int irq, struct irq_desc *desc)
 	if (!noirqdebug)
 		note_interrupt(irq, desc, action_ret);
 
-	if (desc->chip->eoi)
+	if (desc->chip->eoi) {
 		desc->chip->eoi(irq);
+		desc = irq_remap_to_desc(irq, desc);
+	}
 }
 
 void
@@ -567,8 +575,10 @@ __set_irq_handler(unsigned int irq, irq_flow_handler_t handle, int is_chained,
 
 	/* Uninstall? */
 	if (handle == handle_bad_irq) {
-		if (desc->chip != &no_irq_chip)
+		if (desc->chip != &no_irq_chip) {
 			mask_ack_irq(desc, irq);
+			desc = irq_remap_to_desc(irq, desc);
+		}
 		desc->status |= IRQ_DISABLED;
 		desc->depth = 1;
 	}
diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c
index c815b42d0f5b..c20db0be9173 100644
--- a/kernel/irq/handle.c
+++ b/kernel/irq/handle.c
@@ -15,9 +15,16 @@
 #include <linux/random.h>
 #include <linux/interrupt.h>
 #include <linux/kernel_stat.h>
+#include <linux/rculist.h>
+#include <linux/hash.h>
 
 #include "internals.h"
 
+/*
+ * lockdep: we want to handle all irq_desc locks as a single lock-class:
+ */
+struct lock_class_key irq_desc_lock_class;
+
 /**
  * handle_bad_irq - handle spurious and unhandled irqs
  * @irq:       the interrupt number
@@ -49,6 +56,150 @@ void handle_bad_irq(unsigned int irq, struct irq_desc *desc)
 int nr_irqs = NR_IRQS;
 EXPORT_SYMBOL_GPL(nr_irqs);
 
+#ifdef CONFIG_SPARSE_IRQ
+static struct irq_desc irq_desc_init = {
+	.irq	    = -1,
+	.status	    = IRQ_DISABLED,
+	.chip	    = &no_irq_chip,
+	.handle_irq = handle_bad_irq,
+	.depth      = 1,
+	.lock       = __SPIN_LOCK_UNLOCKED(irq_desc_init.lock),
+#ifdef CONFIG_SMP
+	.affinity   = CPU_MASK_ALL
+#endif
+};
+
+void init_kstat_irqs(struct irq_desc *desc, int cpu, int nr)
+{
+	unsigned long bytes;
+	char *ptr;
+	int node;
+
+	/* Compute how many bytes we need per irq and allocate them */
+	bytes = nr * sizeof(unsigned int);
+
+	node = cpu_to_node(cpu);
+	ptr = kzalloc_node(bytes, GFP_ATOMIC, node);
+	printk(KERN_DEBUG "  alloc kstat_irqs on cpu %d node %d\n", cpu, node);
+
+	if (ptr)
+		desc->kstat_irqs = (unsigned int *)ptr;
+}
+
+static void init_one_irq_desc(int irq, struct irq_desc *desc, int cpu)
+{
+	memcpy(desc, &irq_desc_init, sizeof(struct irq_desc));
+
+	spin_lock_init(&desc->lock);
+	desc->irq = irq;
+#ifdef CONFIG_SMP
+	desc->cpu = cpu;
+#endif
+	lockdep_set_class(&desc->lock, &irq_desc_lock_class);
+	init_kstat_irqs(desc, cpu, nr_cpu_ids);
+	if (!desc->kstat_irqs) {
+		printk(KERN_ERR "can not alloc kstat_irqs\n");
+		BUG_ON(1);
+	}
+	arch_init_chip_data(desc, cpu);
+}
+
+/*
+ * Protect the sparse_irqs:
+ */
+DEFINE_SPINLOCK(sparse_irq_lock);
+
+struct irq_desc *irq_desc_ptrs[NR_IRQS] __read_mostly;
+
+static struct irq_desc irq_desc_legacy[NR_IRQS_LEGACY] __cacheline_aligned_in_smp = {
+	[0 ... NR_IRQS_LEGACY-1] = {
+		.irq	    = -1,
+		.status	    = IRQ_DISABLED,
+		.chip	    = &no_irq_chip,
+		.handle_irq = handle_bad_irq,
+		.depth	    = 1,
+		.lock	    = __SPIN_LOCK_UNLOCKED(irq_desc_init.lock),
+#ifdef CONFIG_SMP
+		.affinity   = CPU_MASK_ALL
+#endif
+	}
+};
+
+/* FIXME: use bootmem alloc ...*/
+static unsigned int kstat_irqs_legacy[NR_IRQS_LEGACY][NR_CPUS];
+
+int __init early_irq_init(void)
+{
+	struct irq_desc *desc;
+	int legacy_count;
+	int i;
+
+	desc = irq_desc_legacy;
+	legacy_count = ARRAY_SIZE(irq_desc_legacy);
+
+	for (i = 0; i < legacy_count; i++) {
+		desc[i].irq = i;
+		desc[i].kstat_irqs = kstat_irqs_legacy[i];
+		lockdep_set_class(&desc[i].lock, &irq_desc_lock_class);
+
+		irq_desc_ptrs[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)
+{
+	return (irq < NR_IRQS) ? irq_desc_ptrs[irq] : NULL;
+}
+
+struct irq_desc *irq_to_desc_alloc_cpu(unsigned int irq, int cpu)
+{
+	struct irq_desc *desc;
+	unsigned long flags;
+	int node;
+
+	if (irq >= NR_IRQS) {
+		printk(KERN_WARNING "irq >= NR_IRQS in irq_to_desc_alloc: %d %d\n",
+				irq, NR_IRQS);
+		WARN_ON(1);
+		return NULL;
+	}
+
+	desc = irq_desc_ptrs[irq];
+	if (desc)
+		return desc;
+
+	spin_lock_irqsave(&sparse_irq_lock, flags);
+
+	/* We have to check it to avoid races with another CPU */
+	desc = irq_desc_ptrs[irq];
+	if (desc)
+		goto out_unlock;
+
+	node = cpu_to_node(cpu);
+	desc = kzalloc_node(sizeof(*desc), GFP_ATOMIC, node);
+	printk(KERN_DEBUG "  alloc irq_desc for %d on cpu %d node %d\n",
+		 irq, cpu, node);
+	if (!desc) {
+		printk(KERN_ERR "can not alloc irq_desc\n");
+		BUG_ON(1);
+	}
+	init_one_irq_desc(irq, desc, cpu);
+
+	irq_desc_ptrs[irq] = desc;
+
+out_unlock:
+	spin_unlock_irqrestore(&sparse_irq_lock, flags);
+
+	return desc;
+}
+
+#else /* !CONFIG_SPARSE_IRQ */
+
 struct irq_desc irq_desc[NR_IRQS] __cacheline_aligned_in_smp = {
 	[0 ... NR_IRQS-1] = {
 		.status = IRQ_DISABLED,
@@ -62,6 +213,32 @@ struct irq_desc irq_desc[NR_IRQS] __cacheline_aligned_in_smp = {
 	}
 };
 
+int __init early_irq_init(void)
+{
+	struct irq_desc *desc;
+	int count;
+	int i;
+
+	desc = irq_desc;
+	count = ARRAY_SIZE(irq_desc);
+
+	for (i = 0; i < count; i++)
+		desc[i].irq = i;
+
+	return arch_early_irq_init();
+}
+
+struct irq_desc *irq_to_desc(unsigned int irq)
+{
+	return (irq < NR_IRQS) ? irq_desc + irq : NULL;
+}
+
+struct irq_desc *irq_to_desc_alloc_cpu(unsigned int irq, int cpu)
+{
+	return irq_to_desc(irq);
+}
+#endif /* !CONFIG_SPARSE_IRQ */
+
 /*
  * What should we do if we get a hw irq event on an illegal vector?
  * Each architecture has to answer this themself.
@@ -179,8 +356,11 @@ unsigned int __do_IRQ(unsigned int irq)
 		/*
 		 * No locking required for CPU-local interrupts:
 		 */
-		if (desc->chip->ack)
+		if (desc->chip->ack) {
 			desc->chip->ack(irq);
+			/* get new one */
+			desc = irq_remap_to_desc(irq, desc);
+		}
 		if (likely(!(desc->status & IRQ_DISABLED))) {
 			action_ret = handle_IRQ_event(irq, desc->action);
 			if (!noirqdebug)
@@ -191,8 +371,10 @@ unsigned int __do_IRQ(unsigned int irq)
 	}
 
 	spin_lock(&desc->lock);
-	if (desc->chip->ack)
+	if (desc->chip->ack) {
 		desc->chip->ack(irq);
+		desc = irq_remap_to_desc(irq, desc);
+	}
 	/*
 	 * REPLAY is when Linux resends an IRQ that was dropped earlier
 	 * WAITING is used by probe to mark irqs that are being tested
@@ -259,19 +441,22 @@ out:
 }
 #endif
 
-
-#ifdef CONFIG_TRACE_IRQFLAGS
-/*
- * lockdep: we want to handle all irq_desc locks as a single lock-class:
- */
-static struct lock_class_key irq_desc_lock_class;
-
 void early_init_irq_lock_class(void)
 {
 	struct irq_desc *desc;
 	int i;
 
-	for_each_irq_desc(i, desc)
+	for_each_irq_desc(i, desc) {
 		lockdep_set_class(&desc->lock, &irq_desc_lock_class);
+	}
+}
+
+#ifdef CONFIG_SPARSE_IRQ
+unsigned int kstat_irqs_cpu(unsigned int irq, int cpu)
+{
+	struct irq_desc *desc = irq_to_desc(irq);
+	return desc ? desc->kstat_irqs[cpu] : 0;
 }
 #endif
+EXPORT_SYMBOL(kstat_irqs_cpu);
+
diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h
index 64c1c7253dae..e6d0a43cc125 100644
--- a/kernel/irq/internals.h
+++ b/kernel/irq/internals.h
@@ -13,6 +13,11 @@ extern void compat_irq_chip_set_default_handler(struct irq_desc *desc);
 extern int __irq_set_trigger(struct irq_desc *desc, unsigned int irq,
 		unsigned long flags);
 
+extern struct lock_class_key irq_desc_lock_class;
+extern void init_kstat_irqs(struct irq_desc *desc, int cpu, int nr);
+extern spinlock_t sparse_irq_lock;
+extern struct irq_desc *irq_desc_ptrs[NR_IRQS];
+
 #ifdef CONFIG_PROC_FS
 extern void register_irq_proc(unsigned int irq, struct irq_desc *desc);
 extern void register_handler_proc(unsigned int irq, struct irqaction *action);
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 801addda3c43..cd0cd8dcb345 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -16,8 +16,15 @@
 #include "internals.h"
 
 #ifdef CONFIG_SMP
+cpumask_var_t irq_default_affinity;
 
-cpumask_t irq_default_affinity = CPU_MASK_ALL;
+static int init_irq_default_affinity(void)
+{
+	alloc_cpumask_var(&irq_default_affinity, GFP_KERNEL);
+	cpumask_setall(irq_default_affinity);
+	return 0;
+}
+core_initcall(init_irq_default_affinity);
 
 /**
  *	synchronize_irq - wait for pending IRQ handlers (on other CPUs)
@@ -79,7 +86,7 @@ int irq_can_set_affinity(unsigned int irq)
  *	@cpumask:	cpumask
  *
  */
-int irq_set_affinity(unsigned int irq, cpumask_t cpumask)
+int irq_set_affinity(unsigned int irq, const struct cpumask *cpumask)
 {
 	struct irq_desc *desc = irq_to_desc(irq);
 	unsigned long flags;
@@ -91,14 +98,14 @@ int irq_set_affinity(unsigned int irq, cpumask_t cpumask)
 
 #ifdef CONFIG_GENERIC_PENDING_IRQ
 	if (desc->status & IRQ_MOVE_PCNTXT || desc->status & IRQ_DISABLED) {
-		desc->affinity = cpumask;
+		cpumask_copy(&desc->affinity, cpumask);
 		desc->chip->set_affinity(irq, cpumask);
 	} else {
 		desc->status |= IRQ_MOVE_PENDING;
-		desc->pending_mask = cpumask;
+		cpumask_copy(&desc->pending_mask, cpumask);
 	}
 #else
-	desc->affinity = cpumask;
+	cpumask_copy(&desc->affinity, cpumask);
 	desc->chip->set_affinity(irq, cpumask);
 #endif
 	desc->status |= IRQ_AFFINITY_SET;
@@ -112,26 +119,24 @@ int irq_set_affinity(unsigned int irq, cpumask_t cpumask)
  */
 int do_irq_select_affinity(unsigned int irq, struct irq_desc *desc)
 {
-	cpumask_t mask;
-
 	if (!irq_can_set_affinity(irq))
 		return 0;
 
-	cpus_and(mask, cpu_online_map, irq_default_affinity);
-
 	/*
 	 * Preserve an userspace affinity setup, but make sure that
 	 * one of the targets is online.
 	 */
 	if (desc->status & (IRQ_AFFINITY_SET | IRQ_NO_BALANCING)) {
-		if (cpus_intersects(desc->affinity, cpu_online_map))
-			mask = desc->affinity;
+		if (cpumask_any_and(&desc->affinity, cpu_online_mask)
+		    < nr_cpu_ids)
+			goto set_affinity;
 		else
 			desc->status &= ~IRQ_AFFINITY_SET;
 	}
 
-	desc->affinity = mask;
-	desc->chip->set_affinity(irq, mask);
+	cpumask_and(&desc->affinity, cpu_online_mask, irq_default_affinity);
+set_affinity:
+	desc->chip->set_affinity(irq, &desc->affinity);
 
 	return 0;
 }
@@ -370,16 +375,18 @@ int __irq_set_trigger(struct irq_desc *desc, unsigned int irq,
 		return 0;
 	}
 
-	ret = chip->set_type(irq, flags & IRQF_TRIGGER_MASK);
+	/* caller masked out all except trigger mode flags */
+	ret = chip->set_type(irq, flags);
 
 	if (ret)
 		pr_err("setting trigger mode %d for irq %u failed (%pF)\n",
-				(int)(flags & IRQF_TRIGGER_MASK),
-				irq, chip->set_type);
+				(int)flags, irq, chip->set_type);
 	else {
+		if (flags & (IRQ_TYPE_LEVEL_LOW | IRQ_TYPE_LEVEL_HIGH))
+			flags |= IRQ_LEVEL;
 		/* note that IRQF_TRIGGER_MASK == IRQ_TYPE_SENSE_MASK */
-		desc->status &= ~IRQ_TYPE_SENSE_MASK;
-		desc->status |= flags & IRQ_TYPE_SENSE_MASK;
+		desc->status &= ~(IRQ_LEVEL | IRQ_TYPE_SENSE_MASK);
+		desc->status |= flags;
 	}
 
 	return ret;
@@ -459,7 +466,8 @@ __setup_irq(unsigned int irq, struct irq_desc * desc, struct irqaction *new)
 
 		/* Setup the type (level, edge polarity) if configured: */
 		if (new->flags & IRQF_TRIGGER_MASK) {
-			ret = __irq_set_trigger(desc, irq, new->flags);
+			ret = __irq_set_trigger(desc, irq,
+					new->flags & IRQF_TRIGGER_MASK);
 
 			if (ret) {
 				spin_unlock_irqrestore(&desc->lock, flags);
@@ -673,6 +681,18 @@ int request_irq(unsigned int irq, irq_handler_t handler,
 	struct irq_desc *desc;
 	int retval;
 
+	/*
+	 * handle_IRQ_event() always ignores IRQF_DISABLED except for
+	 * the _first_ irqaction (sigh).  That can cause oopsing, but
+	 * the behavior is classified as "will not fix" so we need to
+	 * start nudging drivers away from using that idiom.
+	 */
+	if ((irqflags & (IRQF_SHARED|IRQF_DISABLED))
+			== (IRQF_SHARED|IRQF_DISABLED))
+		pr_warning("IRQ %d/%s: IRQF_DISABLED is not "
+				"guaranteed on shared IRQs\n",
+				irq, devname);
+
 #ifdef CONFIG_LOCKDEP
 	/*
 	 * Lockdep wants atomic interrupt handlers:
diff --git a/kernel/irq/migration.c b/kernel/irq/migration.c
index 9db681d95814..bd72329e630c 100644
--- a/kernel/irq/migration.c
+++ b/kernel/irq/migration.c
@@ -4,7 +4,6 @@
 void move_masked_irq(int irq)
 {
 	struct irq_desc *desc = irq_to_desc(irq);
-	cpumask_t tmp;
 
 	if (likely(!(desc->status & IRQ_MOVE_PENDING)))
 		return;
@@ -19,7 +18,7 @@ void move_masked_irq(int irq)
 
 	desc->status &= ~IRQ_MOVE_PENDING;
 
-	if (unlikely(cpus_empty(desc->pending_mask)))
+	if (unlikely(cpumask_empty(&desc->pending_mask)))
 		return;
 
 	if (!desc->chip->set_affinity)
@@ -27,8 +26,6 @@ void move_masked_irq(int irq)
 
 	assert_spin_locked(&desc->lock);
 
-	cpus_and(tmp, desc->pending_mask, cpu_online_map);
-
 	/*
 	 * If there was a valid mask to work with, please
 	 * do the disable, re-program, enable sequence.
@@ -41,10 +38,13 @@ void move_masked_irq(int irq)
 	 * For correct operation this depends on the caller
 	 * masking the irqs.
 	 */
-	if (likely(!cpus_empty(tmp))) {
-		desc->chip->set_affinity(irq,tmp);
+	if (likely(cpumask_any_and(&desc->pending_mask, cpu_online_mask)
+		   < nr_cpu_ids)) {
+		cpumask_and(&desc->affinity,
+			    &desc->pending_mask, cpu_online_mask);
+		desc->chip->set_affinity(irq, &desc->affinity);
 	}
-	cpus_clear(desc->pending_mask);
+	cpumask_clear(&desc->pending_mask);
 }
 
 void move_native_irq(int irq)
diff --git a/kernel/irq/numa_migrate.c b/kernel/irq/numa_migrate.c
new file mode 100644
index 000000000000..ecf765c6a77a
--- /dev/null
+++ b/kernel/irq/numa_migrate.c
@@ -0,0 +1,119 @@
+/*
+ * NUMA irq-desc migration code
+ *
+ * Migrate IRQ data structures (irq_desc, chip_data, etc.) over to
+ * the new "home node" of the IRQ.
+ */
+
+#include <linux/irq.h>
+#include <linux/module.h>
+#include <linux/random.h>
+#include <linux/interrupt.h>
+#include <linux/kernel_stat.h>
+
+#include "internals.h"
+
+static void init_copy_kstat_irqs(struct irq_desc *old_desc,
+				 struct irq_desc *desc,
+				 int cpu, int nr)
+{
+	unsigned long bytes;
+
+	init_kstat_irqs(desc, cpu, nr);
+
+	if (desc->kstat_irqs != old_desc->kstat_irqs) {
+		/* Compute how many bytes we need per irq and allocate them */
+		bytes = nr * sizeof(unsigned int);
+
+		memcpy(desc->kstat_irqs, old_desc->kstat_irqs, bytes);
+	}
+}
+
+static void free_kstat_irqs(struct irq_desc *old_desc, struct irq_desc *desc)
+{
+	if (old_desc->kstat_irqs == desc->kstat_irqs)
+		return;
+
+	kfree(old_desc->kstat_irqs);
+	old_desc->kstat_irqs = NULL;
+}
+
+static void init_copy_one_irq_desc(int irq, struct irq_desc *old_desc,
+		 struct irq_desc *desc, int cpu)
+{
+	memcpy(desc, old_desc, sizeof(struct irq_desc));
+	spin_lock_init(&desc->lock);
+	desc->cpu = cpu;
+	lockdep_set_class(&desc->lock, &irq_desc_lock_class);
+	init_copy_kstat_irqs(old_desc, desc, cpu, nr_cpu_ids);
+	arch_init_copy_chip_data(old_desc, desc, cpu);
+}
+
+static void free_one_irq_desc(struct irq_desc *old_desc, struct irq_desc *desc)
+{
+	free_kstat_irqs(old_desc, desc);
+	arch_free_chip_data(old_desc, desc);
+}
+
+static struct irq_desc *__real_move_irq_desc(struct irq_desc *old_desc,
+						int cpu)
+{
+	struct irq_desc *desc;
+	unsigned int irq;
+	unsigned long flags;
+	int node;
+
+	irq = old_desc->irq;
+
+	spin_lock_irqsave(&sparse_irq_lock, flags);
+
+	/* We have to check it to avoid races with another CPU */
+	desc = irq_desc_ptrs[irq];
+
+	if (desc && old_desc != desc)
+			goto out_unlock;
+
+	node = cpu_to_node(cpu);
+	desc = kzalloc_node(sizeof(*desc), GFP_ATOMIC, node);
+	if (!desc) {
+		printk(KERN_ERR "irq %d: can not get new irq_desc for migration.\n", irq);
+		/* still use old one */
+		desc = old_desc;
+		goto out_unlock;
+	}
+	init_copy_one_irq_desc(irq, old_desc, desc, cpu);
+
+	irq_desc_ptrs[irq] = desc;
+
+	/* free the old one */
+	free_one_irq_desc(old_desc, desc);
+	kfree(old_desc);
+
+out_unlock:
+	spin_unlock_irqrestore(&sparse_irq_lock, flags);
+
+	return desc;
+}
+
+struct irq_desc *move_irq_desc(struct irq_desc *desc, int cpu)
+{
+	int old_cpu;
+	int node, old_node;
+
+	/* those all static, do move them */
+	if (desc->irq < NR_IRQS_LEGACY)
+		return desc;
+
+	old_cpu = desc->cpu;
+	if (old_cpu != cpu) {
+		node = cpu_to_node(cpu);
+		old_node = cpu_to_node(old_cpu);
+		if (old_node != node)
+			desc = __real_move_irq_desc(desc, cpu);
+		else
+			desc->cpu = cpu;
+	}
+
+	return desc;
+}
+
diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c
index d257e7d6a8a4..aae3f742bcec 100644
--- a/kernel/irq/proc.c
+++ b/kernel/irq/proc.c
@@ -20,7 +20,7 @@ static struct proc_dir_entry *root_irq_dir;
 static int irq_affinity_proc_show(struct seq_file *m, void *v)
 {
 	struct irq_desc *desc = irq_to_desc((long)m->private);
-	cpumask_t *mask = &desc->affinity;
+	const struct cpumask *mask = &desc->affinity;
 
 #ifdef CONFIG_GENERIC_PENDING_IRQ
 	if (desc->status & IRQ_MOVE_PENDING)
@@ -40,33 +40,42 @@ static ssize_t irq_affinity_proc_write(struct file *file,
 		const char __user *buffer, size_t count, loff_t *pos)
 {
 	unsigned int irq = (int)(long)PDE(file->f_path.dentry->d_inode)->data;
-	cpumask_t new_value;
+	cpumask_var_t new_value;
 	int err;
 
 	if (!irq_to_desc(irq)->chip->set_affinity || no_irq_affinity ||
 	    irq_balancing_disabled(irq))
 		return -EIO;
 
+	if (!alloc_cpumask_var(&new_value, GFP_KERNEL))
+		return -ENOMEM;
+
 	err = cpumask_parse_user(buffer, count, new_value);
 	if (err)
-		return err;
+		goto free_cpumask;
 
-	if (!is_affinity_mask_valid(new_value))
-		return -EINVAL;
+	if (!is_affinity_mask_valid(new_value)) {
+		err = -EINVAL;
+		goto free_cpumask;
+	}
 
 	/*
 	 * Do not allow disabling IRQs completely - it's a too easy
 	 * way to make the system unusable accidentally :-) At least
 	 * one online CPU still has to be targeted.
 	 */
-	if (!cpus_intersects(new_value, cpu_online_map))
+	if (!cpumask_intersects(new_value, cpu_online_mask)) {
 		/* Special case for empty set - allow the architecture
 		   code to set default SMP affinity. */
-		return irq_select_affinity_usr(irq) ? -EINVAL : count;
-
-	irq_set_affinity(irq, new_value);
+		err = irq_select_affinity_usr(irq) ? -EINVAL : count;
+	} else {
+		irq_set_affinity(irq, new_value);
+		err = count;
+	}
 
-	return count;
+free_cpumask:
+	free_cpumask_var(new_value);
+	return err;
 }
 
 static int irq_affinity_proc_open(struct inode *inode, struct file *file)
@@ -84,7 +93,7 @@ static const struct file_operations irq_affinity_proc_fops = {
 
 static int default_affinity_show(struct seq_file *m, void *v)
 {
-	seq_cpumask(m, &irq_default_affinity);
+	seq_cpumask(m, irq_default_affinity);
 	seq_putc(m, '\n');
 	return 0;
 }
@@ -92,27 +101,37 @@ static int default_affinity_show(struct seq_file *m, void *v)
 static ssize_t default_affinity_write(struct file *file,
 		const char __user *buffer, size_t count, loff_t *ppos)
 {
-	cpumask_t new_value;
+	cpumask_var_t new_value;
 	int err;
 
+	if (!alloc_cpumask_var(&new_value, GFP_KERNEL))
+		return -ENOMEM;
+
 	err = cpumask_parse_user(buffer, count, new_value);
 	if (err)
-		return err;
+		goto out;
 
-	if (!is_affinity_mask_valid(new_value))
-		return -EINVAL;
+	if (!is_affinity_mask_valid(new_value)) {
+		err = -EINVAL;
+		goto out;
+	}
 
 	/*
 	 * Do not allow disabling IRQs completely - it's a too easy
 	 * way to make the system unusable accidentally :-) At least
 	 * one online CPU still has to be targeted.
 	 */
-	if (!cpus_intersects(new_value, cpu_online_map))
-		return -EINVAL;
+	if (!cpumask_intersects(new_value, cpu_online_mask)) {
+		err = -EINVAL;
+		goto out;
+	}
 
-	irq_default_affinity = new_value;
+	cpumask_copy(irq_default_affinity, new_value);
+	err = count;
 
-	return count;
+out:
+	free_cpumask_var(new_value);
+	return err;
 }
 
 static int default_affinity_open(struct inode *inode, struct file *file)
@@ -243,7 +262,11 @@ void init_irq_proc(void)
 	/*
 	 * Create entries for all existing IRQs.
 	 */
-	for_each_irq_desc(irq, desc)
+	for_each_irq_desc(irq, desc) {
+		if (!desc)
+			continue;
+
 		register_irq_proc(irq, desc);
+	}
 }
 
diff --git a/kernel/kexec.c b/kernel/kexec.c
index ac0fde7b54d0..3fb855ad6aa0 100644
--- a/kernel/kexec.c
+++ b/kernel/kexec.c
@@ -1116,7 +1116,7 @@ void crash_save_cpu(struct pt_regs *regs, int cpu)
 	struct elf_prstatus prstatus;
 	u32 *buf;
 
-	if ((cpu < 0) || (cpu >= NR_CPUS))
+	if ((cpu < 0) || (cpu >= nr_cpu_ids))
 		return;
 
 	/* Using ELF notes here is opportunistic.
diff --git a/kernel/kmod.c b/kernel/kmod.c
index b46dbb908669..a27a5f64443d 100644
--- a/kernel/kmod.c
+++ b/kernel/kmod.c
@@ -51,8 +51,8 @@ char modprobe_path[KMOD_PATH_LEN] = "/sbin/modprobe";
 
 /**
  * request_module - try to load a kernel module
- * @fmt:     printf style format string for the name of the module
- * @varargs: arguements as specified in the format string
+ * @fmt: printf style format string for the name of the module
+ * @...: arguments as specified in the format string
  *
  * Load a module using the user mode module loader. The function returns
  * zero on success or a negative errno code on failure. Note that a
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 9f8a3f25259a..1b9cbdc0127a 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -69,7 +69,7 @@ static struct hlist_head kretprobe_inst_table[KPROBE_TABLE_SIZE];
 /* NOTE: change this value only with kprobe_mutex held */
 static bool kprobe_enabled;
 
-DEFINE_MUTEX(kprobe_mutex);		/* Protects kprobe_table */
+static DEFINE_MUTEX(kprobe_mutex);	/* Protects kprobe_table */
 static DEFINE_PER_CPU(struct kprobe *, kprobe_instance) = NULL;
 static struct {
 	spinlock_t lock ____cacheline_aligned_in_smp;
@@ -115,6 +115,7 @@ enum kprobe_slot_state {
 	SLOT_USED = 2,
 };
 
+static DEFINE_MUTEX(kprobe_insn_mutex);	/* Protects kprobe_insn_pages */
 static struct hlist_head kprobe_insn_pages;
 static int kprobe_garbage_slots;
 static int collect_garbage_slots(void);
@@ -144,10 +145,10 @@ loop_end:
 }
 
 /**
- * get_insn_slot() - Find a slot on an executable page for an instruction.
+ * __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.
  */
-kprobe_opcode_t __kprobes *get_insn_slot(void)
+static kprobe_opcode_t __kprobes *__get_insn_slot(void)
 {
 	struct kprobe_insn_page *kip;
 	struct hlist_node *pos;
@@ -196,6 +197,15 @@ kprobe_opcode_t __kprobes *get_insn_slot(void)
 	return kip->insns;
 }
 
+kprobe_opcode_t __kprobes *get_insn_slot(void)
+{
+	kprobe_opcode_t *ret;
+	mutex_lock(&kprobe_insn_mutex);
+	ret = __get_insn_slot();
+	mutex_unlock(&kprobe_insn_mutex);
+	return ret;
+}
+
 /* Return 1 if all garbages are collected, otherwise 0. */
 static int __kprobes collect_one_slot(struct kprobe_insn_page *kip, int idx)
 {
@@ -226,9 +236,13 @@ static int __kprobes collect_garbage_slots(void)
 {
 	struct kprobe_insn_page *kip;
 	struct hlist_node *pos, *next;
+	int safety;
 
 	/* Ensure no-one is preepmted on the garbages */
-	if (check_safety() != 0)
+	mutex_unlock(&kprobe_insn_mutex);
+	safety = check_safety();
+	mutex_lock(&kprobe_insn_mutex);
+	if (safety != 0)
 		return -EAGAIN;
 
 	hlist_for_each_entry_safe(kip, pos, next, &kprobe_insn_pages, hlist) {
@@ -251,6 +265,7 @@ void __kprobes free_insn_slot(kprobe_opcode_t * slot, int dirty)
 	struct kprobe_insn_page *kip;
 	struct hlist_node *pos;
 
+	mutex_lock(&kprobe_insn_mutex);
 	hlist_for_each_entry(kip, pos, &kprobe_insn_pages, hlist) {
 		if (kip->insns <= slot &&
 		    slot < kip->insns + (INSNS_PER_PAGE * MAX_INSN_SIZE)) {
@@ -267,6 +282,8 @@ void __kprobes free_insn_slot(kprobe_opcode_t * slot, int dirty)
 
 	if (dirty && ++kprobe_garbage_slots > INSNS_PER_PAGE)
 		collect_garbage_slots();
+
+	mutex_unlock(&kprobe_insn_mutex);
 }
 #endif
 
@@ -310,7 +327,7 @@ static int __kprobes aggr_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) {
+		if (kp->pre_handler && !kprobe_gone(kp)) {
 			set_kprobe_instance(kp);
 			if (kp->pre_handler(kp, regs))
 				return 1;
@@ -326,7 +343,7 @@ static void __kprobes aggr_post_handler(struct kprobe *p, struct pt_regs *regs,
 	struct kprobe *kp;
 
 	list_for_each_entry_rcu(kp, &p->list, list) {
-		if (kp->post_handler) {
+		if (kp->post_handler && !kprobe_gone(kp)) {
 			set_kprobe_instance(kp);
 			kp->post_handler(kp, regs, flags);
 			reset_kprobe_instance();
@@ -393,7 +410,7 @@ void __kprobes recycle_rp_inst(struct kretprobe_instance *ri,
 		hlist_add_head(&ri->hlist, head);
 }
 
-void kretprobe_hash_lock(struct task_struct *tsk,
+void __kprobes kretprobe_hash_lock(struct task_struct *tsk,
 			 struct hlist_head **head, unsigned long *flags)
 {
 	unsigned long hash = hash_ptr(tsk, KPROBE_HASH_BITS);
@@ -404,13 +421,15 @@ void kretprobe_hash_lock(struct task_struct *tsk,
 	spin_lock_irqsave(hlist_lock, *flags);
 }
 
-static void kretprobe_table_lock(unsigned long hash, unsigned long *flags)
+static void __kprobes kretprobe_table_lock(unsigned long hash,
+	unsigned long *flags)
 {
 	spinlock_t *hlist_lock = kretprobe_table_lock_ptr(hash);
 	spin_lock_irqsave(hlist_lock, *flags);
 }
 
-void kretprobe_hash_unlock(struct task_struct *tsk, unsigned long *flags)
+void __kprobes kretprobe_hash_unlock(struct task_struct *tsk,
+	unsigned long *flags)
 {
 	unsigned long hash = hash_ptr(tsk, KPROBE_HASH_BITS);
 	spinlock_t *hlist_lock;
@@ -419,7 +438,7 @@ void kretprobe_hash_unlock(struct task_struct *tsk, unsigned long *flags)
 	spin_unlock_irqrestore(hlist_lock, *flags);
 }
 
-void kretprobe_table_unlock(unsigned long hash, unsigned long *flags)
+void __kprobes kretprobe_table_unlock(unsigned long hash, unsigned long *flags)
 {
 	spinlock_t *hlist_lock = kretprobe_table_lock_ptr(hash);
 	spin_unlock_irqrestore(hlist_lock, *flags);
@@ -526,9 +545,10 @@ static inline void add_aggr_kprobe(struct kprobe *ap, struct kprobe *p)
 	ap->addr = p->addr;
 	ap->pre_handler = aggr_pre_handler;
 	ap->fault_handler = aggr_fault_handler;
-	if (p->post_handler)
+	/* We don't care the kprobe which has gone. */
+	if (p->post_handler && !kprobe_gone(p))
 		ap->post_handler = aggr_post_handler;
-	if (p->break_handler)
+	if (p->break_handler && !kprobe_gone(p))
 		ap->break_handler = aggr_break_handler;
 
 	INIT_LIST_HEAD(&ap->list);
@@ -547,17 +567,41 @@ static int __kprobes register_aggr_kprobe(struct kprobe *old_p,
 	int ret = 0;
 	struct kprobe *ap;
 
+	if (kprobe_gone(old_p)) {
+		/*
+		 * Attempting to insert new probe at the same location that
+		 * had a probe in the module vaddr area which already
+		 * freed. So, the instruction slot has already been
+		 * released. We need a new slot for the new probe.
+		 */
+		ret = arch_prepare_kprobe(old_p);
+		if (ret)
+			return ret;
+	}
 	if (old_p->pre_handler == aggr_pre_handler) {
 		copy_kprobe(old_p, p);
 		ret = add_new_kprobe(old_p, p);
+		ap = old_p;
 	} else {
 		ap = kzalloc(sizeof(struct kprobe), GFP_KERNEL);
-		if (!ap)
+		if (!ap) {
+			if (kprobe_gone(old_p))
+				arch_remove_kprobe(old_p);
 			return -ENOMEM;
+		}
 		add_aggr_kprobe(ap, old_p);
 		copy_kprobe(ap, p);
 		ret = add_new_kprobe(ap, p);
 	}
+	if (kprobe_gone(old_p)) {
+		/*
+		 * If the old_p has gone, its breakpoint has been disarmed.
+		 * We have to arm it again after preparing real kprobes.
+		 */
+		ap->flags &= ~KPROBE_FLAG_GONE;
+		if (kprobe_enabled)
+			arch_arm_kprobe(ap);
+	}
 	return ret;
 }
 
@@ -600,8 +644,7 @@ static kprobe_opcode_t __kprobes *kprobe_addr(struct kprobe *p)
 	return (kprobe_opcode_t *)(((char *)addr) + p->offset);
 }
 
-static int __kprobes __register_kprobe(struct kprobe *p,
-	unsigned long called_from)
+int __kprobes register_kprobe(struct kprobe *p)
 {
 	int ret = 0;
 	struct kprobe *old_p;
@@ -620,28 +663,30 @@ static int __kprobes __register_kprobe(struct kprobe *p,
 		return -EINVAL;
 	}
 
-	p->mod_refcounted = 0;
-
+	p->flags = 0;
 	/*
 	 * Check if are we probing a module.
 	 */
 	probed_mod = __module_text_address((unsigned long) p->addr);
 	if (probed_mod) {
-		struct module *calling_mod;
-		calling_mod = __module_text_address(called_from);
 		/*
-		 * We must allow modules to probe themself and in this case
-		 * avoid incrementing the module refcount, so as to allow
-		 * unloading of self probing modules.
+		 * We must hold a refcount of the probed module while updating
+		 * its code to prohibit unexpected unloading.
 		 */
-		if (calling_mod && calling_mod != probed_mod) {
-			if (unlikely(!try_module_get(probed_mod))) {
-				preempt_enable();
-				return -EINVAL;
-			}
-			p->mod_refcounted = 1;
-		} else
-			probed_mod = NULL;
+		if (unlikely(!try_module_get(probed_mod))) {
+			preempt_enable();
+			return -EINVAL;
+		}
+		/*
+		 * If the module freed .init.text, we couldn't insert
+		 * kprobes in there.
+		 */
+		if (within_module_init((unsigned long)p->addr, probed_mod) &&
+		    probed_mod->state != MODULE_STATE_COMING) {
+			module_put(probed_mod);
+			preempt_enable();
+			return -EINVAL;
+		}
 	}
 	preempt_enable();
 
@@ -668,8 +713,9 @@ static int __kprobes __register_kprobe(struct kprobe *p,
 out:
 	mutex_unlock(&kprobe_mutex);
 
-	if (ret && probed_mod)
+	if (probed_mod)
 		module_put(probed_mod);
+
 	return ret;
 }
 
@@ -697,16 +743,16 @@ valid_p:
 	     list_is_singular(&old_p->list))) {
 		/*
 		 * Only probe on the hash list. Disarm only if kprobes are
-		 * enabled - otherwise, the breakpoint would already have
-		 * been removed. We save on flushing icache.
+		 * enabled and not gone - otherwise, the breakpoint would
+		 * already have been removed. We save on flushing icache.
 		 */
-		if (kprobe_enabled)
+		if (kprobe_enabled && !kprobe_gone(old_p))
 			arch_disarm_kprobe(p);
 		hlist_del_rcu(&old_p->hlist);
 	} else {
-		if (p->break_handler)
+		if (p->break_handler && !kprobe_gone(p))
 			old_p->break_handler = NULL;
-		if (p->post_handler) {
+		if (p->post_handler && !kprobe_gone(p)) {
 			list_for_each_entry_rcu(list_p, &old_p->list, list) {
 				if ((list_p != p) && (list_p->post_handler))
 					goto noclean;
@@ -721,39 +767,27 @@ noclean:
 
 static void __kprobes __unregister_kprobe_bottom(struct kprobe *p)
 {
-	struct module *mod;
 	struct kprobe *old_p;
 
-	if (p->mod_refcounted) {
-		/*
-		 * Since we've already incremented refcount,
-		 * we don't need to disable preemption.
-		 */
-		mod = module_text_address((unsigned long)p->addr);
-		if (mod)
-			module_put(mod);
-	}
-
-	if (list_empty(&p->list) || list_is_singular(&p->list)) {
-		if (!list_empty(&p->list)) {
-			/* "p" is the last child of an aggr_kprobe */
-			old_p = list_entry(p->list.next, struct kprobe, list);
-			list_del(&p->list);
-			kfree(old_p);
-		}
+	if (list_empty(&p->list))
 		arch_remove_kprobe(p);
+	else if (list_is_singular(&p->list)) {
+		/* "p" is the last child of an aggr_kprobe */
+		old_p = list_entry(p->list.next, struct kprobe, list);
+		list_del(&p->list);
+		arch_remove_kprobe(old_p);
+		kfree(old_p);
 	}
 }
 
-static int __register_kprobes(struct kprobe **kps, int num,
-	unsigned long called_from)
+int __kprobes register_kprobes(struct kprobe **kps, int num)
 {
 	int i, ret = 0;
 
 	if (num <= 0)
 		return -EINVAL;
 	for (i = 0; i < num; i++) {
-		ret = __register_kprobe(kps[i], called_from);
+		ret = register_kprobe(kps[i]);
 		if (ret < 0) {
 			if (i > 0)
 				unregister_kprobes(kps, i);
@@ -763,26 +797,11 @@ static int __register_kprobes(struct kprobe **kps, int num,
 	return ret;
 }
 
-/*
- * Registration and unregistration functions for kprobe.
- */
-int __kprobes register_kprobe(struct kprobe *p)
-{
-	return __register_kprobes(&p, 1,
-				  (unsigned long)__builtin_return_address(0));
-}
-
 void __kprobes unregister_kprobe(struct kprobe *p)
 {
 	unregister_kprobes(&p, 1);
 }
 
-int __kprobes register_kprobes(struct kprobe **kps, int num)
-{
-	return __register_kprobes(kps, num,
-				  (unsigned long)__builtin_return_address(0));
-}
-
 void __kprobes unregister_kprobes(struct kprobe **kps, int num)
 {
 	int i;
@@ -811,8 +830,7 @@ unsigned long __weak arch_deref_entry_point(void *entry)
 	return (unsigned long)entry;
 }
 
-static int __register_jprobes(struct jprobe **jps, int num,
-	unsigned long called_from)
+int __kprobes register_jprobes(struct jprobe **jps, int num)
 {
 	struct jprobe *jp;
 	int ret = 0, i;
@@ -830,7 +848,7 @@ static int __register_jprobes(struct jprobe **jps, int num,
 			/* Todo: Verify probepoint is a function entry point */
 			jp->kp.pre_handler = setjmp_pre_handler;
 			jp->kp.break_handler = longjmp_break_handler;
-			ret = __register_kprobe(&jp->kp, called_from);
+			ret = register_kprobe(&jp->kp);
 		}
 		if (ret < 0) {
 			if (i > 0)
@@ -843,8 +861,7 @@ static int __register_jprobes(struct jprobe **jps, int num,
 
 int __kprobes register_jprobe(struct jprobe *jp)
 {
-	return __register_jprobes(&jp, 1,
-		(unsigned long)__builtin_return_address(0));
+	return register_jprobes(&jp, 1);
 }
 
 void __kprobes unregister_jprobe(struct jprobe *jp)
@@ -852,12 +869,6 @@ void __kprobes unregister_jprobe(struct jprobe *jp)
 	unregister_jprobes(&jp, 1);
 }
 
-int __kprobes register_jprobes(struct jprobe **jps, int num)
-{
-	return __register_jprobes(jps, num,
-		(unsigned long)__builtin_return_address(0));
-}
-
 void __kprobes unregister_jprobes(struct jprobe **jps, int num)
 {
 	int i;
@@ -920,8 +931,7 @@ static int __kprobes pre_handler_kretprobe(struct kprobe *p,
 	return 0;
 }
 
-static int __kprobes __register_kretprobe(struct kretprobe *rp,
-					  unsigned long called_from)
+int __kprobes register_kretprobe(struct kretprobe *rp)
 {
 	int ret = 0;
 	struct kretprobe_instance *inst;
@@ -967,21 +977,20 @@ static int __kprobes __register_kretprobe(struct kretprobe *rp,
 
 	rp->nmissed = 0;
 	/* Establish function entry probe point */
-	ret = __register_kprobe(&rp->kp, called_from);
+	ret = register_kprobe(&rp->kp);
 	if (ret != 0)
 		free_rp_inst(rp);
 	return ret;
 }
 
-static int __register_kretprobes(struct kretprobe **rps, int num,
-	unsigned long called_from)
+int __kprobes register_kretprobes(struct kretprobe **rps, int num)
 {
 	int ret = 0, i;
 
 	if (num <= 0)
 		return -EINVAL;
 	for (i = 0; i < num; i++) {
-		ret = __register_kretprobe(rps[i], called_from);
+		ret = register_kretprobe(rps[i]);
 		if (ret < 0) {
 			if (i > 0)
 				unregister_kretprobes(rps, i);
@@ -991,23 +1000,11 @@ static int __register_kretprobes(struct kretprobe **rps, int num,
 	return ret;
 }
 
-int __kprobes register_kretprobe(struct kretprobe *rp)
-{
-	return __register_kretprobes(&rp, 1,
-			(unsigned long)__builtin_return_address(0));
-}
-
 void __kprobes unregister_kretprobe(struct kretprobe *rp)
 {
 	unregister_kretprobes(&rp, 1);
 }
 
-int __kprobes register_kretprobes(struct kretprobe **rps, int num)
-{
-	return __register_kretprobes(rps, num,
-			(unsigned long)__builtin_return_address(0));
-}
-
 void __kprobes unregister_kretprobes(struct kretprobe **rps, int num)
 {
 	int i;
@@ -1055,6 +1052,72 @@ static int __kprobes pre_handler_kretprobe(struct kprobe *p,
 
 #endif /* CONFIG_KRETPROBES */
 
+/* Set the kprobe gone and remove its instruction buffer. */
+static void __kprobes kill_kprobe(struct kprobe *p)
+{
+	struct kprobe *kp;
+	p->flags |= KPROBE_FLAG_GONE;
+	if (p->pre_handler == aggr_pre_handler) {
+		/*
+		 * If this is an aggr_kprobe, we have to list all the
+		 * chained probes and mark them GONE.
+		 */
+		list_for_each_entry_rcu(kp, &p->list, list)
+			kp->flags |= KPROBE_FLAG_GONE;
+		p->post_handler = NULL;
+		p->break_handler = NULL;
+	}
+	/*
+	 * Here, we can remove insn_slot safely, because no thread calls
+	 * the original probed function (which will be freed soon) any more.
+	 */
+	arch_remove_kprobe(p);
+}
+
+/* Module notifier call back, checking kprobes on the module */
+static int __kprobes kprobes_module_callback(struct notifier_block *nb,
+					     unsigned long val, void *data)
+{
+	struct module *mod = data;
+	struct hlist_head *head;
+	struct hlist_node *node;
+	struct kprobe *p;
+	unsigned int i;
+	int checkcore = (val == MODULE_STATE_GOING);
+
+	if (val != MODULE_STATE_GOING && val != MODULE_STATE_LIVE)
+		return NOTIFY_DONE;
+
+	/*
+	 * When MODULE_STATE_GOING was notified, both of module .text and
+	 * .init.text sections would be freed. When MODULE_STATE_LIVE was
+	 * notified, only .init.text section would be freed. We need to
+	 * disable kprobes which have been inserted in the sections.
+	 */
+	mutex_lock(&kprobe_mutex);
+	for (i = 0; i < KPROBE_TABLE_SIZE; i++) {
+		head = &kprobe_table[i];
+		hlist_for_each_entry_rcu(p, node, head, hlist)
+			if (within_module_init((unsigned long)p->addr, mod) ||
+			    (checkcore &&
+			     within_module_core((unsigned long)p->addr, mod))) {
+				/*
+				 * The vaddr this probe is installed will soon
+				 * be vfreed buy not synced to disk. Hence,
+				 * disarming the breakpoint isn't needed.
+				 */
+				kill_kprobe(p);
+			}
+	}
+	mutex_unlock(&kprobe_mutex);
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block kprobe_module_nb = {
+	.notifier_call = kprobes_module_callback,
+	.priority = 0
+};
+
 static int __init init_kprobes(void)
 {
 	int i, err = 0;
@@ -1111,6 +1174,9 @@ static int __init init_kprobes(void)
 	err = arch_init_kprobes();
 	if (!err)
 		err = register_die_notifier(&kprobe_exceptions_nb);
+	if (!err)
+		err = register_module_notifier(&kprobe_module_nb);
+
 	kprobes_initialized = (err == 0);
 
 	if (!err)
@@ -1131,10 +1197,12 @@ static void __kprobes report_probe(struct seq_file *pi, struct kprobe *p,
 	else
 		kprobe_type = "k";
 	if (sym)
-		seq_printf(pi, "%p  %s  %s+0x%x  %s\n", p->addr, kprobe_type,
-			sym, offset, (modname ? modname : " "));
+		seq_printf(pi, "%p  %s  %s+0x%x  %s %s\n", p->addr, kprobe_type,
+			sym, offset, (modname ? modname : " "),
+			(kprobe_gone(p) ? "[GONE]" : ""));
 	else
-		seq_printf(pi, "%p  %s  %p\n", p->addr, kprobe_type, p->addr);
+		seq_printf(pi, "%p  %s  %p %s\n", p->addr, kprobe_type, p->addr,
+			(kprobe_gone(p) ? "[GONE]" : ""));
 }
 
 static void __kprobes *kprobe_seq_start(struct seq_file *f, loff_t *pos)
@@ -1215,7 +1283,8 @@ static void __kprobes enable_all_kprobes(void)
 	for (i = 0; i < KPROBE_TABLE_SIZE; i++) {
 		head = &kprobe_table[i];
 		hlist_for_each_entry_rcu(p, node, head, hlist)
-			arch_arm_kprobe(p);
+			if (!kprobe_gone(p))
+				arch_arm_kprobe(p);
 	}
 
 	kprobe_enabled = true;
@@ -1244,7 +1313,7 @@ static void __kprobes disable_all_kprobes(void)
 	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))
+			if (!arch_trampoline_kprobe(p) && !kprobe_gone(p))
 				arch_disarm_kprobe(p);
 		}
 	}
diff --git a/kernel/ksysfs.c b/kernel/ksysfs.c
index 08dd8ed86c77..528dd78e7e7e 100644
--- a/kernel/ksysfs.c
+++ b/kernel/ksysfs.c
@@ -24,7 +24,7 @@ static struct kobj_attribute _name##_attr = __ATTR_RO(_name)
 static struct kobj_attribute _name##_attr = \
 	__ATTR(_name, 0644, _name##_show, _name##_store)
 
-#if defined(CONFIG_HOTPLUG) && defined(CONFIG_NET)
+#if defined(CONFIG_HOTPLUG)
 /* current uevent sequence number */
 static ssize_t uevent_seqnum_show(struct kobject *kobj,
 				  struct kobj_attribute *attr, char *buf)
@@ -137,7 +137,7 @@ struct kobject *kernel_kobj;
 EXPORT_SYMBOL_GPL(kernel_kobj);
 
 static struct attribute * kernel_attrs[] = {
-#if defined(CONFIG_HOTPLUG) && defined(CONFIG_NET)
+#if defined(CONFIG_HOTPLUG)
 	&uevent_seqnum_attr.attr,
 	&uevent_helper_attr.attr,
 #endif
diff --git a/kernel/lockdep.c b/kernel/lockdep.c
index 74b1878b8bb8..06b0c3568f0b 100644
--- a/kernel/lockdep.c
+++ b/kernel/lockdep.c
@@ -137,16 +137,16 @@ static inline struct lock_class *hlock_class(struct held_lock *hlock)
 #ifdef CONFIG_LOCK_STAT
 static DEFINE_PER_CPU(struct lock_class_stats[MAX_LOCKDEP_KEYS], lock_stats);
 
-static int lock_contention_point(struct lock_class *class, unsigned long ip)
+static int lock_point(unsigned long points[], unsigned long ip)
 {
 	int i;
 
-	for (i = 0; i < ARRAY_SIZE(class->contention_point); i++) {
-		if (class->contention_point[i] == 0) {
-			class->contention_point[i] = ip;
+	for (i = 0; i < LOCKSTAT_POINTS; i++) {
+		if (points[i] == 0) {
+			points[i] = ip;
 			break;
 		}
-		if (class->contention_point[i] == ip)
+		if (points[i] == ip)
 			break;
 	}
 
@@ -186,6 +186,9 @@ struct lock_class_stats lock_stats(struct lock_class *class)
 		for (i = 0; i < ARRAY_SIZE(stats.contention_point); i++)
 			stats.contention_point[i] += pcs->contention_point[i];
 
+		for (i = 0; i < ARRAY_SIZE(stats.contending_point); i++)
+			stats.contending_point[i] += pcs->contending_point[i];
+
 		lock_time_add(&pcs->read_waittime, &stats.read_waittime);
 		lock_time_add(&pcs->write_waittime, &stats.write_waittime);
 
@@ -210,6 +213,7 @@ void clear_lock_stats(struct lock_class *class)
 		memset(cpu_stats, 0, sizeof(struct lock_class_stats));
 	}
 	memset(class->contention_point, 0, sizeof(class->contention_point));
+	memset(class->contending_point, 0, sizeof(class->contending_point));
 }
 
 static struct lock_class_stats *get_lock_stats(struct lock_class *class)
@@ -288,14 +292,12 @@ void lockdep_off(void)
 {
 	current->lockdep_recursion++;
 }
-
 EXPORT_SYMBOL(lockdep_off);
 
 void lockdep_on(void)
 {
 	current->lockdep_recursion--;
 }
-
 EXPORT_SYMBOL(lockdep_on);
 
 /*
@@ -577,7 +579,8 @@ static void print_lock_class_header(struct lock_class *class, int depth)
 /*
  * printk all lock dependencies starting at <entry>:
  */
-static void print_lock_dependencies(struct lock_class *class, int depth)
+static void __used
+print_lock_dependencies(struct lock_class *class, int depth)
 {
 	struct lock_list *entry;
 
@@ -2509,7 +2512,6 @@ void lockdep_init_map(struct lockdep_map *lock, const char *name,
 	if (subclass)
 		register_lock_class(lock, subclass, 1);
 }
-
 EXPORT_SYMBOL_GPL(lockdep_init_map);
 
 /*
@@ -2690,8 +2692,9 @@ static int check_unlock(struct task_struct *curr, struct lockdep_map *lock,
 }
 
 static int
-__lock_set_subclass(struct lockdep_map *lock,
-		    unsigned int subclass, unsigned long ip)
+__lock_set_class(struct lockdep_map *lock, const char *name,
+		 struct lock_class_key *key, unsigned int subclass,
+		 unsigned long ip)
 {
 	struct task_struct *curr = current;
 	struct held_lock *hlock, *prev_hlock;
@@ -2718,6 +2721,7 @@ __lock_set_subclass(struct lockdep_map *lock,
 	return print_unlock_inbalance_bug(curr, lock, ip);
 
 found_it:
+	lockdep_init_map(lock, name, key, 0);
 	class = register_lock_class(lock, subclass, 0);
 	hlock->class_idx = class - lock_classes + 1;
 
@@ -2902,9 +2906,9 @@ static void check_flags(unsigned long flags)
 #endif
 }
 
-void
-lock_set_subclass(struct lockdep_map *lock,
-		  unsigned int subclass, unsigned long ip)
+void lock_set_class(struct lockdep_map *lock, const char *name,
+		    struct lock_class_key *key, unsigned int subclass,
+		    unsigned long ip)
 {
 	unsigned long flags;
 
@@ -2914,13 +2918,12 @@ lock_set_subclass(struct lockdep_map *lock,
 	raw_local_irq_save(flags);
 	current->lockdep_recursion = 1;
 	check_flags(flags);
-	if (__lock_set_subclass(lock, subclass, ip))
+	if (__lock_set_class(lock, name, key, subclass, ip))
 		check_chain_key(current);
 	current->lockdep_recursion = 0;
 	raw_local_irq_restore(flags);
 }
-
-EXPORT_SYMBOL_GPL(lock_set_subclass);
+EXPORT_SYMBOL_GPL(lock_set_class);
 
 /*
  * We are not always called with irqs disabled - do that here,
@@ -2944,7 +2947,6 @@ void lock_acquire(struct lockdep_map *lock, unsigned int subclass,
 	current->lockdep_recursion = 0;
 	raw_local_irq_restore(flags);
 }
-
 EXPORT_SYMBOL_GPL(lock_acquire);
 
 void lock_release(struct lockdep_map *lock, int nested,
@@ -2962,7 +2964,6 @@ void lock_release(struct lockdep_map *lock, int nested,
 	current->lockdep_recursion = 0;
 	raw_local_irq_restore(flags);
 }
-
 EXPORT_SYMBOL_GPL(lock_release);
 
 #ifdef CONFIG_LOCK_STAT
@@ -3000,7 +3001,7 @@ __lock_contended(struct lockdep_map *lock, unsigned long ip)
 	struct held_lock *hlock, *prev_hlock;
 	struct lock_class_stats *stats;
 	unsigned int depth;
-	int i, point;
+	int i, contention_point, contending_point;
 
 	depth = curr->lockdep_depth;
 	if (DEBUG_LOCKS_WARN_ON(!depth))
@@ -3024,18 +3025,22 @@ __lock_contended(struct lockdep_map *lock, unsigned long ip)
 found_it:
 	hlock->waittime_stamp = sched_clock();
 
-	point = lock_contention_point(hlock_class(hlock), ip);
+	contention_point = lock_point(hlock_class(hlock)->contention_point, ip);
+	contending_point = lock_point(hlock_class(hlock)->contending_point,
+				      lock->ip);
 
 	stats = get_lock_stats(hlock_class(hlock));
-	if (point < ARRAY_SIZE(stats->contention_point))
-		stats->contention_point[point]++;
+	if (contention_point < LOCKSTAT_POINTS)
+		stats->contention_point[contention_point]++;
+	if (contending_point < LOCKSTAT_POINTS)
+		stats->contending_point[contending_point]++;
 	if (lock->cpu != smp_processor_id())
 		stats->bounces[bounce_contended + !!hlock->read]++;
 	put_lock_stats(stats);
 }
 
 static void
-__lock_acquired(struct lockdep_map *lock)
+__lock_acquired(struct lockdep_map *lock, unsigned long ip)
 {
 	struct task_struct *curr = current;
 	struct held_lock *hlock, *prev_hlock;
@@ -3084,6 +3089,7 @@ found_it:
 	put_lock_stats(stats);
 
 	lock->cpu = cpu;
+	lock->ip = ip;
 }
 
 void lock_contended(struct lockdep_map *lock, unsigned long ip)
@@ -3105,7 +3111,7 @@ void lock_contended(struct lockdep_map *lock, unsigned long ip)
 }
 EXPORT_SYMBOL_GPL(lock_contended);
 
-void lock_acquired(struct lockdep_map *lock)
+void lock_acquired(struct lockdep_map *lock, unsigned long ip)
 {
 	unsigned long flags;
 
@@ -3118,7 +3124,7 @@ void lock_acquired(struct lockdep_map *lock)
 	raw_local_irq_save(flags);
 	check_flags(flags);
 	current->lockdep_recursion = 1;
-	__lock_acquired(lock);
+	__lock_acquired(lock, ip);
 	current->lockdep_recursion = 0;
 	raw_local_irq_restore(flags);
 }
@@ -3442,7 +3448,6 @@ retry:
 	if (unlock)
 		read_unlock(&tasklist_lock);
 }
-
 EXPORT_SYMBOL_GPL(debug_show_all_locks);
 
 /*
@@ -3463,7 +3468,6 @@ void debug_show_held_locks(struct task_struct *task)
 {
 		__debug_show_held_locks(task);
 }
-
 EXPORT_SYMBOL_GPL(debug_show_held_locks);
 
 void lockdep_sys_exit(void)
diff --git a/kernel/lockdep_proc.c b/kernel/lockdep_proc.c
index 20dbcbf9c7dd..13716b813896 100644
--- a/kernel/lockdep_proc.c
+++ b/kernel/lockdep_proc.c
@@ -470,11 +470,12 @@ static void seq_line(struct seq_file *m, char c, int offset, int length)
 
 static void snprint_time(char *buf, size_t bufsiz, s64 nr)
 {
-	unsigned long rem;
+	s64 div;
+	s32 rem;
 
 	nr += 5; /* for display rounding */
-	rem = do_div(nr, 1000); /* XXX: do_div_signed */
-	snprintf(buf, bufsiz, "%lld.%02d", (long long)nr, (int)rem/10);
+	div = div_s64_rem(nr, 1000, &rem);
+	snprintf(buf, bufsiz, "%lld.%02d", (long long)div, (int)rem/10);
 }
 
 static void seq_time(struct seq_file *m, s64 time)
@@ -556,7 +557,7 @@ static void seq_stats(struct seq_file *m, struct lock_stat_data *data)
 	if (stats->read_holdtime.nr)
 		namelen += 2;
 
-	for (i = 0; i < ARRAY_SIZE(class->contention_point); i++) {
+	for (i = 0; i < LOCKSTAT_POINTS; i++) {
 		char sym[KSYM_SYMBOL_LEN];
 		char ip[32];
 
@@ -573,6 +574,23 @@ static void seq_stats(struct seq_file *m, struct lock_stat_data *data)
 				stats->contention_point[i],
 				ip, sym);
 	}
+	for (i = 0; i < LOCKSTAT_POINTS; i++) {
+		char sym[KSYM_SYMBOL_LEN];
+		char ip[32];
+
+		if (class->contending_point[i] == 0)
+			break;
+
+		if (!i)
+			seq_line(m, '-', 40-namelen, namelen);
+
+		sprint_symbol(sym, class->contending_point[i]);
+		snprintf(ip, sizeof(ip), "[<%p>]",
+				(void *)class->contending_point[i]);
+		seq_printf(m, "%40s %14lu %29s %s\n", name,
+				stats->contending_point[i],
+				ip, sym);
+	}
 	if (i) {
 		seq_puts(m, "\n");
 		seq_line(m, '.', 0, 40 + 1 + 10 * (14 + 1));
@@ -582,7 +600,7 @@ static void seq_stats(struct seq_file *m, struct lock_stat_data *data)
 
 static void seq_header(struct seq_file *m)
 {
-	seq_printf(m, "lock_stat version 0.2\n");
+	seq_printf(m, "lock_stat version 0.3\n");
 	seq_line(m, '-', 0, 40 + 1 + 10 * (14 + 1));
 	seq_printf(m, "%40s %14s %14s %14s %14s %14s %14s %14s %14s "
 			"%14s %14s\n",
diff --git a/kernel/module.c b/kernel/module.c
index dd2a54155b54..c9332c90d5a0 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -43,7 +43,6 @@
 #include <linux/device.h>
 #include <linux/string.h>
 #include <linux/mutex.h>
-#include <linux/unwind.h>
 #include <linux/rculist.h>
 #include <asm/uaccess.h>
 #include <asm/cacheflush.h>
@@ -51,6 +50,7 @@
 #include <asm/sections.h>
 #include <linux/tracepoint.h>
 #include <linux/ftrace.h>
+#include <linux/async.h>
 
 #if 0
 #define DEBUGP printk
@@ -757,8 +757,16 @@ sys_delete_module(const char __user *name_user, unsigned int flags)
 		return -EFAULT;
 	name[MODULE_NAME_LEN-1] = '\0';
 
-	if (mutex_lock_interruptible(&module_mutex) != 0)
-		return -EINTR;
+	/* Create stop_machine threads since free_module relies on
+	 * a non-failing stop_machine call. */
+	ret = stop_machine_create();
+	if (ret)
+		return ret;
+
+	if (mutex_lock_interruptible(&module_mutex) != 0) {
+		ret = -EINTR;
+		goto out_stop;
+	}
 
 	mod = find_module(name);
 	if (!mod) {
@@ -809,6 +817,7 @@ sys_delete_module(const char __user *name_user, unsigned int flags)
 		mod->exit();
 	blocking_notifier_call_chain(&module_notify_list,
 				     MODULE_STATE_GOING, mod);
+	async_synchronize_full();
 	mutex_lock(&module_mutex);
 	/* Store the name of the last unloaded module for diagnostic purposes */
 	strlcpy(last_unloaded_module, mod->name, sizeof(last_unloaded_module));
@@ -817,10 +826,12 @@ sys_delete_module(const char __user *name_user, unsigned int flags)
 
  out:
 	mutex_unlock(&module_mutex);
+out_stop:
+	stop_machine_destroy();
 	return ret;
 }
 
-static void print_unload_info(struct seq_file *m, struct module *mod)
+static inline void print_unload_info(struct seq_file *m, struct module *mod)
 {
 	struct module_use *use;
 	int printed_something = 0;
@@ -893,7 +904,7 @@ void module_put(struct module *module)
 EXPORT_SYMBOL(module_put);
 
 #else /* !CONFIG_MODULE_UNLOAD */
-static void print_unload_info(struct seq_file *m, struct module *mod)
+static inline void print_unload_info(struct seq_file *m, struct module *mod)
 {
 	/* We don't know the usage count, or what modules are using. */
 	seq_printf(m, " - -");
@@ -1439,8 +1450,6 @@ static void free_module(struct module *mod)
 	remove_sect_attrs(mod);
 	mod_kobject_remove(mod);
 
-	unwind_remove_table(mod->unwind_info, 0);
-
 	/* Arch-specific cleanup. */
 	module_arch_cleanup(mod);
 
@@ -1578,11 +1587,21 @@ static int simplify_symbols(Elf_Shdr *sechdrs,
 	return ret;
 }
 
+/* Additional bytes needed by arch in front of individual sections */
+unsigned int __weak arch_mod_section_prepend(struct module *mod,
+					     unsigned int section)
+{
+	/* default implementation just returns zero */
+	return 0;
+}
+
 /* Update size with this section: return offset. */
-static long get_offset(unsigned int *size, Elf_Shdr *sechdr)
+static long get_offset(struct module *mod, unsigned int *size,
+		       Elf_Shdr *sechdr, unsigned int section)
 {
 	long ret;
 
+	*size += arch_mod_section_prepend(mod, section);
 	ret = ALIGN(*size, sechdr->sh_addralign ?: 1);
 	*size = ret + sechdr->sh_size;
 	return ret;
@@ -1622,7 +1641,7 @@ static void layout_sections(struct module *mod,
 			    || strncmp(secstrings + s->sh_name,
 				       ".init", 5) == 0)
 				continue;
-			s->sh_entsize = get_offset(&mod->core_size, s);
+			s->sh_entsize = get_offset(mod, &mod->core_size, s, i);
 			DEBUGP("\t%s\n", secstrings + s->sh_name);
 		}
 		if (m == 0)
@@ -1640,7 +1659,7 @@ static void layout_sections(struct module *mod,
 			    || strncmp(secstrings + s->sh_name,
 				       ".init", 5) != 0)
 				continue;
-			s->sh_entsize = (get_offset(&mod->init_size, s)
+			s->sh_entsize = (get_offset(mod, &mod->init_size, s, i)
 					 | INIT_OFFSET_MASK);
 			DEBUGP("\t%s\n", secstrings + s->sh_name);
 		}
@@ -1725,15 +1744,15 @@ static const struct kernel_symbol *lookup_symbol(const char *name,
 	return NULL;
 }
 
-static int is_exported(const char *name, const struct module *mod)
+static int is_exported(const char *name, unsigned long value,
+		       const struct module *mod)
 {
-	if (!mod && lookup_symbol(name, __start___ksymtab, __stop___ksymtab))
-		return 1;
+	const struct kernel_symbol *ks;
+	if (!mod)
+		ks = lookup_symbol(name, __start___ksymtab, __stop___ksymtab);
 	else
-		if (mod && lookup_symbol(name, mod->syms, mod->syms + mod->num_syms))
-			return 1;
-		else
-			return 0;
+		ks = lookup_symbol(name, mod->syms, mod->syms + mod->num_syms);
+	return ks != NULL && ks->value == value;
 }
 
 /* As per nm */
@@ -1847,7 +1866,6 @@ static noinline struct module *load_module(void __user *umod,
 	unsigned int symindex = 0;
 	unsigned int strindex = 0;
 	unsigned int modindex, versindex, infoindex, pcpuindex;
-	unsigned int unwindex = 0;
 	unsigned int num_kp, num_mcount;
 	struct kernel_param *kp;
 	struct module *mod;
@@ -1865,6 +1883,13 @@ static noinline struct module *load_module(void __user *umod,
 	/* vmalloc barfs on "unusual" numbers.  Check here */
 	if (len > 64 * 1024 * 1024 || (hdr = vmalloc(len)) == NULL)
 		return ERR_PTR(-ENOMEM);
+
+	/* Create stop_machine threads since the error path relies on
+	 * a non-failing stop_machine call. */
+	err = stop_machine_create();
+	if (err)
+		goto free_hdr;
+
 	if (copy_from_user(hdr, umod, len) != 0) {
 		err = -EFAULT;
 		goto free_hdr;
@@ -1930,9 +1955,6 @@ static noinline struct module *load_module(void __user *umod,
 	versindex = find_sec(hdr, sechdrs, secstrings, "__versions");
 	infoindex = find_sec(hdr, sechdrs, secstrings, ".modinfo");
 	pcpuindex = find_pcpusec(hdr, sechdrs, secstrings);
-#ifdef ARCH_UNWIND_SECTION_NAME
-	unwindex = find_sec(hdr, sechdrs, secstrings, ARCH_UNWIND_SECTION_NAME);
-#endif
 
 	/* Don't keep modinfo and version sections. */
 	sechdrs[infoindex].sh_flags &= ~(unsigned long)SHF_ALLOC;
@@ -1942,8 +1964,6 @@ static noinline struct module *load_module(void __user *umod,
 	sechdrs[symindex].sh_flags |= SHF_ALLOC;
 	sechdrs[strindex].sh_flags |= SHF_ALLOC;
 #endif
-	if (unwindex)
-		sechdrs[unwindex].sh_flags |= SHF_ALLOC;
 
 	/* Check module struct version now, before we try to use module. */
 	if (!check_modstruct_version(sechdrs, versindex, mod)) {
@@ -2240,14 +2260,10 @@ static noinline struct module *load_module(void __user *umod,
 	add_sect_attrs(mod, hdr->e_shnum, secstrings, sechdrs);
 	add_notes_attrs(mod, hdr->e_shnum, secstrings, sechdrs);
 
-	/* Size of section 0 is 0, so this works well if no unwind info. */
-	mod->unwind_info = unwind_add_table(mod,
-					    (void *)sechdrs[unwindex].sh_addr,
-					    sechdrs[unwindex].sh_size);
-
 	/* Get rid of temporary copy */
 	vfree(hdr);
 
+	stop_machine_destroy();
 	/* Done! */
 	return mod;
 
@@ -2270,6 +2286,7 @@ static noinline struct module *load_module(void __user *umod,
 	kfree(args);
  free_hdr:
 	vfree(hdr);
+	stop_machine_destroy();
 	return ERR_PTR(err);
 
  truncated:
@@ -2337,11 +2354,12 @@ sys_init_module(void __user *umod,
 	/* Now it's a first class citizen!  Wake up anyone waiting for it. */
 	mod->state = MODULE_STATE_LIVE;
 	wake_up(&module_wq);
+	blocking_notifier_call_chain(&module_notify_list,
+				     MODULE_STATE_LIVE, mod);
 
 	mutex_lock(&module_mutex);
 	/* Drop initial reference. */
 	module_put(mod);
-	unwind_remove_table(mod->unwind_info, 1);
 	module_free(mod, mod->module_init);
 	mod->module_init = NULL;
 	mod->init_size = 0;
@@ -2376,7 +2394,7 @@ static const char *get_ksymbol(struct module *mod,
 	unsigned long nextval;
 
 	/* At worse, next value is at end of module */
-	if (within(addr, mod->module_init, mod->init_size))
+	if (within_module_init(addr, mod))
 		nextval = (unsigned long)mod->module_init+mod->init_text_size;
 	else
 		nextval = (unsigned long)mod->module_core+mod->core_text_size;
@@ -2424,8 +2442,8 @@ const char *module_address_lookup(unsigned long addr,
 
 	preempt_disable();
 	list_for_each_entry_rcu(mod, &modules, list) {
-		if (within(addr, mod->module_init, mod->init_size)
-		    || within(addr, mod->module_core, mod->core_size)) {
+		if (within_module_init(addr, mod) ||
+		    within_module_core(addr, mod)) {
 			if (modname)
 				*modname = mod->name;
 			ret = get_ksymbol(mod, addr, size, offset);
@@ -2447,8 +2465,8 @@ int lookup_module_symbol_name(unsigned long addr, char *symname)
 
 	preempt_disable();
 	list_for_each_entry_rcu(mod, &modules, list) {
-		if (within(addr, mod->module_init, mod->init_size) ||
-		    within(addr, mod->module_core, mod->core_size)) {
+		if (within_module_init(addr, mod) ||
+		    within_module_core(addr, mod)) {
 			const char *sym;
 
 			sym = get_ksymbol(mod, addr, NULL, NULL);
@@ -2471,8 +2489,8 @@ int lookup_module_symbol_attrs(unsigned long addr, unsigned long *size,
 
 	preempt_disable();
 	list_for_each_entry_rcu(mod, &modules, list) {
-		if (within(addr, mod->module_init, mod->init_size) ||
-		    within(addr, mod->module_core, mod->core_size)) {
+		if (within_module_init(addr, mod) ||
+		    within_module_core(addr, mod)) {
 			const char *sym;
 
 			sym = get_ksymbol(mod, addr, size, offset);
@@ -2504,7 +2522,7 @@ int module_get_kallsym(unsigned int symnum, unsigned long *value, char *type,
 			strlcpy(name, mod->strtab + mod->symtab[symnum].st_name,
 				KSYM_NAME_LEN);
 			strlcpy(module_name, mod->name, MODULE_NAME_LEN);
-			*exported = is_exported(name, mod);
+			*exported = is_exported(name, *value, mod);
 			preempt_enable();
 			return 0;
 		}
@@ -2691,7 +2709,7 @@ int is_module_address(unsigned long addr)
 	preempt_disable();
 
 	list_for_each_entry_rcu(mod, &modules, list) {
-		if (within(addr, mod->module_core, mod->core_size)) {
+		if (within_module_core(addr, mod)) {
 			preempt_enable();
 			return 1;
 		}
diff --git a/kernel/mutex.c b/kernel/mutex.c
index 12c779dc65d4..4f45d4b658ef 100644
--- a/kernel/mutex.c
+++ b/kernel/mutex.c
@@ -59,7 +59,7 @@ EXPORT_SYMBOL(__mutex_init);
  * We also put the fastpath first in the kernel image, to make sure the
  * branch is predicted by the CPU as default-untaken.
  */
-static void noinline __sched
+static __used noinline void __sched
 __mutex_lock_slowpath(atomic_t *lock_count);
 
 /***
@@ -96,7 +96,7 @@ void inline __sched mutex_lock(struct mutex *lock)
 EXPORT_SYMBOL(mutex_lock);
 #endif
 
-static noinline void __sched __mutex_unlock_slowpath(atomic_t *lock_count);
+static __used noinline void __sched __mutex_unlock_slowpath(atomic_t *lock_count);
 
 /***
  * mutex_unlock - release the mutex
@@ -184,7 +184,7 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
 	}
 
 done:
-	lock_acquired(&lock->dep_map);
+	lock_acquired(&lock->dep_map, ip);
 	/* got the lock - rejoice! */
 	mutex_remove_waiter(lock, &waiter, task_thread_info(task));
 	debug_mutex_set_owner(lock, task_thread_info(task));
@@ -268,7 +268,7 @@ __mutex_unlock_common_slowpath(atomic_t *lock_count, int nested)
 /*
  * Release the lock, slowpath:
  */
-static noinline void
+static __used noinline void
 __mutex_unlock_slowpath(atomic_t *lock_count)
 {
 	__mutex_unlock_common_slowpath(lock_count, 1);
@@ -313,7 +313,7 @@ int __sched mutex_lock_killable(struct mutex *lock)
 }
 EXPORT_SYMBOL(mutex_lock_killable);
 
-static noinline void __sched
+static __used noinline void __sched
 __mutex_lock_slowpath(atomic_t *lock_count)
 {
 	struct mutex *lock = container_of(lock_count, struct mutex, count);
diff --git a/kernel/notifier.c b/kernel/notifier.c
index 4282c0a40a57..61d5aa5eced3 100644
--- a/kernel/notifier.c
+++ b/kernel/notifier.c
@@ -82,6 +82,14 @@ static int __kprobes notifier_call_chain(struct notifier_block **nl,
 
 	while (nb && nr_to_call) {
 		next_nb = rcu_dereference(nb->next);
+
+#ifdef CONFIG_DEBUG_NOTIFIERS
+		if (unlikely(!func_ptr_is_kernel_text(nb->notifier_call))) {
+			WARN(1, "Invalid notifier called!");
+			nb = next_nb;
+			continue;
+		}
+#endif
 		ret = nb->notifier_call(nb, val, v);
 
 		if (nr_calls)
diff --git a/kernel/ns_cgroup.c b/kernel/ns_cgroup.c
index 43c2111cd54d..78bc3fdac0d2 100644
--- a/kernel/ns_cgroup.c
+++ b/kernel/ns_cgroup.c
@@ -13,7 +13,6 @@
 
 struct ns_cgroup {
 	struct cgroup_subsys_state css;
-	spinlock_t lock;
 };
 
 struct cgroup_subsys ns_subsys;
@@ -84,7 +83,6 @@ static struct cgroup_subsys_state *ns_create(struct cgroup_subsys *ss,
 	ns_cgroup = kzalloc(sizeof(*ns_cgroup), GFP_KERNEL);
 	if (!ns_cgroup)
 		return ERR_PTR(-ENOMEM);
-	spin_lock_init(&ns_cgroup->lock);
 	return &ns_cgroup->css;
 }
 
diff --git a/kernel/panic.c b/kernel/panic.c
index 4d5088355bfe..2a2ff36ff44d 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -21,6 +21,7 @@
 #include <linux/debug_locks.h>
 #include <linux/random.h>
 #include <linux/kallsyms.h>
+#include <linux/dmi.h>
 
 int panic_on_oops;
 static unsigned long tainted_mask;
@@ -298,6 +299,8 @@ static int init_oops_id(void)
 {
 	if (!oops_id)
 		get_random_bytes(&oops_id, sizeof(oops_id));
+	else
+		oops_id++;
 
 	return 0;
 }
@@ -321,36 +324,27 @@ void oops_exit(void)
 }
 
 #ifdef WANT_WARN_ON_SLOWPATH
-void warn_on_slowpath(const char *file, int line)
-{
-	char function[KSYM_SYMBOL_LEN];
-	unsigned long caller = (unsigned long) __builtin_return_address(0);
-	sprint_symbol(function, caller);
-
-	printk(KERN_WARNING "------------[ cut here ]------------\n");
-	printk(KERN_WARNING "WARNING: at %s:%d %s()\n", file,
-		line, function);
-	print_modules();
-	dump_stack();
-	print_oops_end_marker();
-	add_taint(TAINT_WARN);
-}
-EXPORT_SYMBOL(warn_on_slowpath);
-
-
 void warn_slowpath(const char *file, int line, const char *fmt, ...)
 {
 	va_list args;
 	char function[KSYM_SYMBOL_LEN];
 	unsigned long caller = (unsigned long)__builtin_return_address(0);
+	const char *board;
+
 	sprint_symbol(function, caller);
 
 	printk(KERN_WARNING "------------[ cut here ]------------\n");
 	printk(KERN_WARNING "WARNING: at %s:%d %s()\n", file,
 		line, function);
-	va_start(args, fmt);
-	vprintk(fmt, args);
-	va_end(args);
+	board = dmi_get_system_info(DMI_PRODUCT_NAME);
+	if (board)
+		printk(KERN_WARNING "Hardware name: %s\n", board);
+
+	if (fmt) {
+		va_start(args, fmt);
+		vprintk(fmt, args);
+		va_end(args);
+	}
 
 	print_modules();
 	dump_stack();
diff --git a/kernel/pid.c b/kernel/pid.c
index 064e76afa507..1b3586fe753a 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -474,8 +474,14 @@ pid_t task_session_nr_ns(struct task_struct *tsk, struct pid_namespace *ns)
 }
 EXPORT_SYMBOL(task_session_nr_ns);
 
+struct pid_namespace *task_active_pid_ns(struct task_struct *tsk)
+{
+	return ns_of_pid(task_pid(tsk));
+}
+EXPORT_SYMBOL_GPL(task_active_pid_ns);
+
 /*
- * Used by proc to find the first pid that is greater then or equal to nr.
+ * Used by proc to find the first pid that is greater than or equal to nr.
  *
  * If there is a pid at nr this function is exactly the same as find_pid_ns.
  */
diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c
index 4e5288a831de..157de3a47832 100644
--- a/kernel/posix-cpu-timers.c
+++ b/kernel/posix-cpu-timers.c
@@ -58,21 +58,21 @@ void thread_group_cputime(
 	struct task_struct *tsk,
 	struct task_cputime *times)
 {
-	struct signal_struct *sig;
+	struct task_cputime *totals, *tot;
 	int i;
-	struct task_cputime *tot;
 
-	sig = tsk->signal;
-	if (unlikely(!sig) || !sig->cputime.totals) {
+	totals = tsk->signal->cputime.totals;
+	if (!totals) {
 		times->utime = tsk->utime;
 		times->stime = tsk->stime;
 		times->sum_exec_runtime = tsk->se.sum_exec_runtime;
 		return;
 	}
+
 	times->stime = times->utime = cputime_zero;
 	times->sum_exec_runtime = 0;
 	for_each_possible_cpu(i) {
-		tot = per_cpu_ptr(tsk->signal->cputime.totals, i);
+		tot = per_cpu_ptr(totals, i);
 		times->utime = cputime_add(times->utime, tot->utime);
 		times->stime = cputime_add(times->stime, tot->stime);
 		times->sum_exec_runtime += tot->sum_exec_runtime;
diff --git a/kernel/posix-timers.c b/kernel/posix-timers.c
index a140e44eebba..887c63787de6 100644
--- a/kernel/posix-timers.c
+++ b/kernel/posix-timers.c
@@ -116,7 +116,7 @@ static DEFINE_SPINLOCK(idr_lock);
  *	    must supply functions here, even if the function just returns
  *	    ENOSYS.  The standard POSIX timer management code assumes the
  *	    following: 1.) The k_itimer struct (sched.h) is used for the
- *	    timer.  2.) The list, it_lock, it_clock, it_id and it_process
+ *	    timer.  2.) The list, it_lock, it_clock, it_id and it_pid
  *	    fields are not modified by timer code.
  *
  *          At this time all functions EXCEPT clock_nanosleep can be
@@ -319,7 +319,8 @@ void do_schedule_next_timer(struct siginfo *info)
 
 int posix_timer_event(struct k_itimer *timr, int si_private)
 {
-	int shared, ret;
+	struct task_struct *task;
+	int shared, ret = -1;
 	/*
 	 * FIXME: if ->sigq is queued we can race with
 	 * dequeue_signal()->do_schedule_next_timer().
@@ -333,8 +334,13 @@ int posix_timer_event(struct k_itimer *timr, int si_private)
 	 */
 	timr->sigq->info.si_sys_private = si_private;
 
-	shared = !(timr->it_sigev_notify & SIGEV_THREAD_ID);
-	ret = send_sigqueue(timr->sigq, timr->it_process, shared);
+	rcu_read_lock();
+	task = pid_task(timr->it_pid, PIDTYPE_PID);
+	if (task) {
+		shared = !(timr->it_sigev_notify & SIGEV_THREAD_ID);
+		ret = send_sigqueue(timr->sigq, task, shared);
+	}
+	rcu_read_unlock();
 	/* If we failed to send the signal the timer stops. */
 	return ret > 0;
 }
@@ -411,7 +417,7 @@ static enum hrtimer_restart posix_timer_fn(struct hrtimer *timer)
 	return ret;
 }
 
-static struct task_struct * good_sigevent(sigevent_t * event)
+static struct pid *good_sigevent(sigevent_t * event)
 {
 	struct task_struct *rtn = current->group_leader;
 
@@ -425,7 +431,7 @@ static struct task_struct * good_sigevent(sigevent_t * event)
 	    ((event->sigev_signo <= 0) || (event->sigev_signo > SIGRTMAX)))
 		return NULL;
 
-	return rtn;
+	return task_pid(rtn);
 }
 
 void register_posix_clock(const clockid_t clock_id, struct k_clock *new_clock)
@@ -464,6 +470,7 @@ static void release_posix_timer(struct k_itimer *tmr, int it_id_set)
 		idr_remove(&posix_timers_id, tmr->it_id);
 		spin_unlock_irqrestore(&idr_lock, flags);
 	}
+	put_pid(tmr->it_pid);
 	sigqueue_free(tmr->sigq);
 	kmem_cache_free(posix_timers_cache, tmr);
 }
@@ -477,7 +484,6 @@ sys_timer_create(const clockid_t which_clock,
 {
 	struct k_itimer *new_timer;
 	int error, new_timer_id;
-	struct task_struct *process;
 	sigevent_t event;
 	int it_id_set = IT_ID_NOT_SET;
 
@@ -531,11 +537,9 @@ sys_timer_create(const clockid_t which_clock,
 			goto out;
 		}
 		rcu_read_lock();
-		process = good_sigevent(&event);
-		if (process)
-			get_task_struct(process);
+		new_timer->it_pid = get_pid(good_sigevent(&event));
 		rcu_read_unlock();
-		if (!process) {
+		if (!new_timer->it_pid) {
 			error = -EINVAL;
 			goto out;
 		}
@@ -543,8 +547,7 @@ sys_timer_create(const clockid_t which_clock,
 		event.sigev_notify = SIGEV_SIGNAL;
 		event.sigev_signo = SIGALRM;
 		event.sigev_value.sival_int = new_timer->it_id;
-		process = current->group_leader;
-		get_task_struct(process);
+		new_timer->it_pid = get_pid(task_tgid(current));
 	}
 
 	new_timer->it_sigev_notify     = event.sigev_notify;
@@ -554,7 +557,7 @@ sys_timer_create(const clockid_t which_clock,
 	new_timer->sigq->info.si_code  = SI_TIMER;
 
 	spin_lock_irq(&current->sighand->siglock);
-	new_timer->it_process = process;
+	new_timer->it_signal = current->signal;
 	list_add(&new_timer->list, &current->signal->posix_timers);
 	spin_unlock_irq(&current->sighand->siglock);
 
@@ -589,8 +592,7 @@ static struct k_itimer *lock_timer(timer_t timer_id, unsigned long *flags)
 	timr = idr_find(&posix_timers_id, (int)timer_id);
 	if (timr) {
 		spin_lock(&timr->it_lock);
-		if (timr->it_process &&
-		    same_thread_group(timr->it_process, current)) {
+		if (timr->it_signal == current->signal) {
 			spin_unlock(&idr_lock);
 			return timr;
 		}
@@ -837,8 +839,7 @@ retry_delete:
 	 * This keeps any tasks waiting on the spin lock from thinking
 	 * they got something (see the lock code above).
 	 */
-	put_task_struct(timer->it_process);
-	timer->it_process = NULL;
+	timer->it_signal = NULL;
 
 	unlock_timer(timer, flags);
 	release_posix_timer(timer, IT_ID_SET);
@@ -864,8 +865,7 @@ retry_delete:
 	 * This keeps any tasks waiting on the spin lock from thinking
 	 * they got something (see the lock code above).
 	 */
-	put_task_struct(timer->it_process);
-	timer->it_process = NULL;
+	timer->it_signal = NULL;
 
 	unlock_timer(timer, flags);
 	release_posix_timer(timer, IT_ID_SET);
diff --git a/kernel/power/disk.c b/kernel/power/disk.c
index f77d3819ef57..45e8541ab7e3 100644
--- a/kernel/power/disk.c
+++ b/kernel/power/disk.c
@@ -258,12 +258,12 @@ int hibernation_snapshot(int platform_mode)
 {
 	int error;
 
-	/* Free memory before shutting down devices. */
-	error = swsusp_shrink_memory();
+	error = platform_begin(platform_mode);
 	if (error)
 		return error;
 
-	error = platform_begin(platform_mode);
+	/* Free memory before shutting down devices. */
+	error = swsusp_shrink_memory();
 	if (error)
 		goto Close;
 
diff --git a/kernel/power/main.c b/kernel/power/main.c
index 613f16941b85..239988873971 100644
--- a/kernel/power/main.c
+++ b/kernel/power/main.c
@@ -615,7 +615,7 @@ static void __init test_wakealarm(struct rtc_device *rtc, suspend_state_t state)
 	/* this may fail if the RTC hasn't been initialized */
 	status = rtc_read_time(rtc, &alm.time);
 	if (status < 0) {
-		printk(err_readtime, rtc->dev.bus_id, status);
+		printk(err_readtime, dev_name(&rtc->dev), status);
 		return;
 	}
 	rtc_tm_to_time(&alm.time, &now);
@@ -626,7 +626,7 @@ static void __init test_wakealarm(struct rtc_device *rtc, suspend_state_t state)
 
 	status = rtc_set_alarm(rtc, &alm);
 	if (status < 0) {
-		printk(err_wakealarm, rtc->dev.bus_id, status);
+		printk(err_wakealarm, dev_name(&rtc->dev), status);
 		return;
 	}
 
@@ -660,7 +660,7 @@ static int __init has_wakealarm(struct device *dev, void *name_ptr)
 	if (!device_may_wakeup(candidate->dev.parent))
 		return 0;
 
-	*(char **)name_ptr = dev->bus_id;
+	*(const char **)name_ptr = dev_name(dev);
 	return 1;
 }
 
diff --git a/kernel/power/poweroff.c b/kernel/power/poweroff.c
index 72016f051477..97890831e1b5 100644
--- a/kernel/power/poweroff.c
+++ b/kernel/power/poweroff.c
@@ -27,7 +27,7 @@ static DECLARE_WORK(poweroff_work, do_poweroff);
 static void handle_poweroff(int key, struct tty_struct *tty)
 {
 	/* run sysrq poweroff on boot cpu */
-	schedule_work_on(first_cpu(cpu_online_map), &poweroff_work);
+	schedule_work_on(cpumask_first(cpu_online_mask), &poweroff_work);
 }
 
 static struct sysrq_key_op	sysrq_poweroff_op = {
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index 5d2ab836e998..f5fc2d7680f2 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -25,6 +25,7 @@
 #include <linux/syscalls.h>
 #include <linux/console.h>
 #include <linux/highmem.h>
+#include <linux/list.h>
 
 #include <asm/uaccess.h>
 #include <asm/mmu_context.h>
@@ -192,12 +193,6 @@ static void *chain_alloc(struct chain_allocator *ca, unsigned int size)
 	return ret;
 }
 
-static void chain_free(struct chain_allocator *ca, int clear_page_nosave)
-{
-	free_list_of_pages(ca->chain, clear_page_nosave);
-	memset(ca, 0, sizeof(struct chain_allocator));
-}
-
 /**
  *	Data types related to memory bitmaps.
  *
@@ -233,7 +228,7 @@ static void chain_free(struct chain_allocator *ca, int clear_page_nosave)
 #define BM_BITS_PER_BLOCK	(PAGE_SIZE << 3)
 
 struct bm_block {
-	struct bm_block *next;		/* next element of the list */
+	struct list_head hook;	/* hook into a list of bitmap blocks */
 	unsigned long start_pfn;	/* pfn represented by the first bit */
 	unsigned long end_pfn;	/* pfn represented by the last bit plus 1 */
 	unsigned long *data;	/* bitmap representing pages */
@@ -244,24 +239,15 @@ static inline unsigned long bm_block_bits(struct bm_block *bb)
 	return bb->end_pfn - bb->start_pfn;
 }
 
-struct zone_bitmap {
-	struct zone_bitmap *next;	/* next element of the list */
-	unsigned long start_pfn;	/* minimal pfn in this zone */
-	unsigned long end_pfn;		/* maximal pfn in this zone plus 1 */
-	struct bm_block *bm_blocks;	/* list of bitmap blocks */
-	struct bm_block *cur_block;	/* recently used bitmap block */
-};
-
 /* strcut bm_position is used for browsing memory bitmaps */
 
 struct bm_position {
-	struct zone_bitmap *zone_bm;
 	struct bm_block *block;
 	int bit;
 };
 
 struct memory_bitmap {
-	struct zone_bitmap *zone_bm_list;	/* list of zone bitmaps */
+	struct list_head blocks;	/* list of bitmap blocks */
 	struct linked_page *p_list;	/* list of pages used to store zone
 					 * bitmap objects and bitmap block
 					 * objects
@@ -273,11 +259,7 @@ struct memory_bitmap {
 
 static void memory_bm_position_reset(struct memory_bitmap *bm)
 {
-	struct zone_bitmap *zone_bm;
-
-	zone_bm = bm->zone_bm_list;
-	bm->cur.zone_bm = zone_bm;
-	bm->cur.block = zone_bm->bm_blocks;
+	bm->cur.block = list_entry(bm->blocks.next, struct bm_block, hook);
 	bm->cur.bit = 0;
 }
 
@@ -285,151 +267,184 @@ static void memory_bm_free(struct memory_bitmap *bm, int clear_nosave_free);
 
 /**
  *	create_bm_block_list - create a list of block bitmap objects
+ *	@nr_blocks - number of blocks to allocate
+ *	@list - list to put the allocated blocks into
+ *	@ca - chain allocator to be used for allocating memory
  */
-
-static inline struct bm_block *
-create_bm_block_list(unsigned int nr_blocks, struct chain_allocator *ca)
+static int create_bm_block_list(unsigned long pages,
+				struct list_head *list,
+				struct chain_allocator *ca)
 {
-	struct bm_block *bblist = NULL;
+	unsigned int nr_blocks = DIV_ROUND_UP(pages, BM_BITS_PER_BLOCK);
 
 	while (nr_blocks-- > 0) {
 		struct bm_block *bb;
 
 		bb = chain_alloc(ca, sizeof(struct bm_block));
 		if (!bb)
-			return NULL;
-
-		bb->next = bblist;
-		bblist = bb;
+			return -ENOMEM;
+		list_add(&bb->hook, list);
 	}
-	return bblist;
+
+	return 0;
 }
 
+struct mem_extent {
+	struct list_head hook;
+	unsigned long start;
+	unsigned long end;
+};
+
 /**
- *	create_zone_bm_list - create a list of zone bitmap objects
+ *	free_mem_extents - free a list of memory extents
+ *	@list - list of extents to empty
  */
+static void free_mem_extents(struct list_head *list)
+{
+	struct mem_extent *ext, *aux;
 
-static inline struct zone_bitmap *
-create_zone_bm_list(unsigned int nr_zones, struct chain_allocator *ca)
+	list_for_each_entry_safe(ext, aux, list, hook) {
+		list_del(&ext->hook);
+		kfree(ext);
+	}
+}
+
+/**
+ *	create_mem_extents - create a list of memory extents representing
+ *	                     contiguous ranges of PFNs
+ *	@list - list to put the extents into
+ *	@gfp_mask - mask to use for memory allocations
+ */
+static int create_mem_extents(struct list_head *list, gfp_t gfp_mask)
 {
-	struct zone_bitmap *zbmlist = NULL;
+	struct zone *zone;
 
-	while (nr_zones-- > 0) {
-		struct zone_bitmap *zbm;
+	INIT_LIST_HEAD(list);
 
-		zbm = chain_alloc(ca, sizeof(struct zone_bitmap));
-		if (!zbm)
-			return NULL;
+	for_each_zone(zone) {
+		unsigned long zone_start, zone_end;
+		struct mem_extent *ext, *cur, *aux;
+
+		if (!populated_zone(zone))
+			continue;
 
-		zbm->next = zbmlist;
-		zbmlist = zbm;
+		zone_start = zone->zone_start_pfn;
+		zone_end = zone->zone_start_pfn + zone->spanned_pages;
+
+		list_for_each_entry(ext, list, hook)
+			if (zone_start <= ext->end)
+				break;
+
+		if (&ext->hook == list || zone_end < ext->start) {
+			/* New extent is necessary */
+			struct mem_extent *new_ext;
+
+			new_ext = kzalloc(sizeof(struct mem_extent), gfp_mask);
+			if (!new_ext) {
+				free_mem_extents(list);
+				return -ENOMEM;
+			}
+			new_ext->start = zone_start;
+			new_ext->end = zone_end;
+			list_add_tail(&new_ext->hook, &ext->hook);
+			continue;
+		}
+
+		/* Merge this zone's range of PFNs with the existing one */
+		if (zone_start < ext->start)
+			ext->start = zone_start;
+		if (zone_end > ext->end)
+			ext->end = zone_end;
+
+		/* More merging may be possible */
+		cur = ext;
+		list_for_each_entry_safe_continue(cur, aux, list, hook) {
+			if (zone_end < cur->start)
+				break;
+			if (zone_end < cur->end)
+				ext->end = cur->end;
+			list_del(&cur->hook);
+			kfree(cur);
+		}
 	}
-	return zbmlist;
+
+	return 0;
 }
 
 /**
   *	memory_bm_create - allocate memory for a memory bitmap
   */
-
 static int
 memory_bm_create(struct memory_bitmap *bm, gfp_t gfp_mask, int safe_needed)
 {
 	struct chain_allocator ca;
-	struct zone *zone;
-	struct zone_bitmap *zone_bm;
-	struct bm_block *bb;
-	unsigned int nr;
+	struct list_head mem_extents;
+	struct mem_extent *ext;
+	int error;
 
 	chain_init(&ca, gfp_mask, safe_needed);
+	INIT_LIST_HEAD(&bm->blocks);
 
-	/* Compute the number of zones */
-	nr = 0;
-	for_each_zone(zone)
-		if (populated_zone(zone))
-			nr++;
-
-	/* Allocate the list of zones bitmap objects */
-	zone_bm = create_zone_bm_list(nr, &ca);
-	bm->zone_bm_list = zone_bm;
-	if (!zone_bm) {
-		chain_free(&ca, PG_UNSAFE_CLEAR);
-		return -ENOMEM;
-	}
-
-	/* Initialize the zone bitmap objects */
-	for_each_zone(zone) {
-		unsigned long pfn;
+	error = create_mem_extents(&mem_extents, gfp_mask);
+	if (error)
+		return error;
 
-		if (!populated_zone(zone))
-			continue;
+	list_for_each_entry(ext, &mem_extents, hook) {
+		struct bm_block *bb;
+		unsigned long pfn = ext->start;
+		unsigned long pages = ext->end - ext->start;
 
-		zone_bm->start_pfn = zone->zone_start_pfn;
-		zone_bm->end_pfn = zone->zone_start_pfn + zone->spanned_pages;
-		/* Allocate the list of bitmap block objects */
-		nr = DIV_ROUND_UP(zone->spanned_pages, BM_BITS_PER_BLOCK);
-		bb = create_bm_block_list(nr, &ca);
-		zone_bm->bm_blocks = bb;
-		zone_bm->cur_block = bb;
-		if (!bb)
-			goto Free;
+		bb = list_entry(bm->blocks.prev, struct bm_block, hook);
 
-		nr = zone->spanned_pages;
-		pfn = zone->zone_start_pfn;
-		/* Initialize the bitmap block objects */
-		while (bb) {
-			unsigned long *ptr;
+		error = create_bm_block_list(pages, bm->blocks.prev, &ca);
+		if (error)
+			goto Error;
 
-			ptr = get_image_page(gfp_mask, safe_needed);
-			bb->data = ptr;
-			if (!ptr)
-				goto Free;
+		list_for_each_entry_continue(bb, &bm->blocks, hook) {
+			bb->data = get_image_page(gfp_mask, safe_needed);
+			if (!bb->data) {
+				error = -ENOMEM;
+				goto Error;
+			}
 
 			bb->start_pfn = pfn;
-			if (nr >= BM_BITS_PER_BLOCK) {
+			if (pages >= BM_BITS_PER_BLOCK) {
 				pfn += BM_BITS_PER_BLOCK;
-				nr -= BM_BITS_PER_BLOCK;
+				pages -= BM_BITS_PER_BLOCK;
 			} else {
 				/* This is executed only once in the loop */
-				pfn += nr;
+				pfn += pages;
 			}
 			bb->end_pfn = pfn;
-			bb = bb->next;
 		}
-		zone_bm = zone_bm->next;
 	}
+
 	bm->p_list = ca.chain;
 	memory_bm_position_reset(bm);
-	return 0;
+ Exit:
+	free_mem_extents(&mem_extents);
+	return error;
 
- Free:
+ Error:
 	bm->p_list = ca.chain;
 	memory_bm_free(bm, PG_UNSAFE_CLEAR);
-	return -ENOMEM;
+	goto Exit;
 }
 
 /**
   *	memory_bm_free - free memory occupied by the memory bitmap @bm
   */
-
 static void memory_bm_free(struct memory_bitmap *bm, int clear_nosave_free)
 {
-	struct zone_bitmap *zone_bm;
+	struct bm_block *bb;
 
-	/* Free the list of bit blocks for each zone_bitmap object */
-	zone_bm = bm->zone_bm_list;
-	while (zone_bm) {
-		struct bm_block *bb;
+	list_for_each_entry(bb, &bm->blocks, hook)
+		if (bb->data)
+			free_image_page(bb->data, clear_nosave_free);
 
-		bb = zone_bm->bm_blocks;
-		while (bb) {
-			if (bb->data)
-				free_image_page(bb->data, clear_nosave_free);
-			bb = bb->next;
-		}
-		zone_bm = zone_bm->next;
-	}
 	free_list_of_pages(bm->p_list, clear_nosave_free);
-	bm->zone_bm_list = NULL;
+
+	INIT_LIST_HEAD(&bm->blocks);
 }
 
 /**
@@ -437,38 +452,33 @@ static void memory_bm_free(struct memory_bitmap *bm, int clear_nosave_free)
  *	to given pfn.  The cur_zone_bm member of @bm and the cur_block member
  *	of @bm->cur_zone_bm are updated.
  */
-
 static int memory_bm_find_bit(struct memory_bitmap *bm, unsigned long pfn,
 				void **addr, unsigned int *bit_nr)
 {
-	struct zone_bitmap *zone_bm;
 	struct bm_block *bb;
 
-	/* Check if the pfn is from the current zone */
-	zone_bm = bm->cur.zone_bm;
-	if (pfn < zone_bm->start_pfn || pfn >= zone_bm->end_pfn) {
-		zone_bm = bm->zone_bm_list;
-		/* We don't assume that the zones are sorted by pfns */
-		while (pfn < zone_bm->start_pfn || pfn >= zone_bm->end_pfn) {
-			zone_bm = zone_bm->next;
-
-			if (!zone_bm)
-				return -EFAULT;
-		}
-		bm->cur.zone_bm = zone_bm;
-	}
-	/* Check if the pfn corresponds to the current bitmap block */
-	bb = zone_bm->cur_block;
+	/*
+	 * Check if the pfn corresponds to the current bitmap block and find
+	 * the block where it fits if this is not the case.
+	 */
+	bb = bm->cur.block;
 	if (pfn < bb->start_pfn)
-		bb = zone_bm->bm_blocks;
+		list_for_each_entry_continue_reverse(bb, &bm->blocks, hook)
+			if (pfn >= bb->start_pfn)
+				break;
 
-	while (pfn >= bb->end_pfn) {
-		bb = bb->next;
+	if (pfn >= bb->end_pfn)
+		list_for_each_entry_continue(bb, &bm->blocks, hook)
+			if (pfn >= bb->start_pfn && pfn < bb->end_pfn)
+				break;
 
-		BUG_ON(!bb);
-	}
-	zone_bm->cur_block = bb;
+	if (&bb->hook == &bm->blocks)
+		return -EFAULT;
+
+	/* The block has been found */
+	bm->cur.block = bb;
 	pfn -= bb->start_pfn;
+	bm->cur.bit = pfn + 1;
 	*bit_nr = pfn;
 	*addr = bb->data;
 	return 0;
@@ -519,6 +529,14 @@ static int memory_bm_test_bit(struct memory_bitmap *bm, unsigned long pfn)
 	return test_bit(bit, addr);
 }
 
+static bool memory_bm_pfn_present(struct memory_bitmap *bm, unsigned long pfn)
+{
+	void *addr;
+	unsigned int bit;
+
+	return !memory_bm_find_bit(bm, pfn, &addr, &bit);
+}
+
 /**
  *	memory_bm_next_pfn - find the pfn that corresponds to the next set bit
  *	in the bitmap @bm.  If the pfn cannot be found, BM_END_OF_MAP is
@@ -530,29 +548,21 @@ static int memory_bm_test_bit(struct memory_bitmap *bm, unsigned long pfn)
 
 static unsigned long memory_bm_next_pfn(struct memory_bitmap *bm)
 {
-	struct zone_bitmap *zone_bm;
 	struct bm_block *bb;
 	int bit;
 
+	bb = bm->cur.block;
 	do {
-		bb = bm->cur.block;
-		do {
-			bit = bm->cur.bit;
-			bit = find_next_bit(bb->data, bm_block_bits(bb), bit);
-			if (bit < bm_block_bits(bb))
-				goto Return_pfn;
-
-			bb = bb->next;
-			bm->cur.block = bb;
-			bm->cur.bit = 0;
-		} while (bb);
-		zone_bm = bm->cur.zone_bm->next;
-		if (zone_bm) {
-			bm->cur.zone_bm = zone_bm;
-			bm->cur.block = zone_bm->bm_blocks;
-			bm->cur.bit = 0;
-		}
-	} while (zone_bm);
+		bit = bm->cur.bit;
+		bit = find_next_bit(bb->data, bm_block_bits(bb), bit);
+		if (bit < bm_block_bits(bb))
+			goto Return_pfn;
+
+		bb = list_entry(bb->hook.next, struct bm_block, hook);
+		bm->cur.block = bb;
+		bm->cur.bit = 0;
+	} while (&bb->hook != &bm->blocks);
+
 	memory_bm_position_reset(bm);
 	return BM_END_OF_MAP;
 
@@ -808,8 +818,7 @@ static unsigned int count_free_highmem_pages(void)
  *	We should save the page if it isn't Nosave or NosaveFree, or Reserved,
  *	and it isn't a part of a free chunk of pages.
  */
-
-static struct page *saveable_highmem_page(unsigned long pfn)
+static struct page *saveable_highmem_page(struct zone *zone, unsigned long pfn)
 {
 	struct page *page;
 
@@ -817,6 +826,8 @@ static struct page *saveable_highmem_page(unsigned long pfn)
 		return NULL;
 
 	page = pfn_to_page(pfn);
+	if (page_zone(page) != zone)
+		return NULL;
 
 	BUG_ON(!PageHighMem(page));
 
@@ -846,13 +857,16 @@ unsigned int count_highmem_pages(void)
 		mark_free_pages(zone);
 		max_zone_pfn = zone->zone_start_pfn + zone->spanned_pages;
 		for (pfn = zone->zone_start_pfn; pfn < max_zone_pfn; pfn++)
-			if (saveable_highmem_page(pfn))
+			if (saveable_highmem_page(zone, pfn))
 				n++;
 	}
 	return n;
 }
 #else
-static inline void *saveable_highmem_page(unsigned long pfn) { return NULL; }
+static inline void *saveable_highmem_page(struct zone *z, unsigned long p)
+{
+	return NULL;
+}
 #endif /* CONFIG_HIGHMEM */
 
 /**
@@ -863,8 +877,7 @@ static inline void *saveable_highmem_page(unsigned long pfn) { return NULL; }
  *	of pages statically defined as 'unsaveable', and it isn't a part of
  *	a free chunk of pages.
  */
-
-static struct page *saveable_page(unsigned long pfn)
+static struct page *saveable_page(struct zone *zone, unsigned long pfn)
 {
 	struct page *page;
 
@@ -872,6 +885,8 @@ static struct page *saveable_page(unsigned long pfn)
 		return NULL;
 
 	page = pfn_to_page(pfn);
+	if (page_zone(page) != zone)
+		return NULL;
 
 	BUG_ON(PageHighMem(page));
 
@@ -903,7 +918,7 @@ unsigned int count_data_pages(void)
 		mark_free_pages(zone);
 		max_zone_pfn = zone->zone_start_pfn + zone->spanned_pages;
 		for (pfn = zone->zone_start_pfn; pfn < max_zone_pfn; pfn++)
-			if(saveable_page(pfn))
+			if (saveable_page(zone, pfn))
 				n++;
 	}
 	return n;
@@ -944,7 +959,7 @@ static inline struct page *
 page_is_saveable(struct zone *zone, unsigned long pfn)
 {
 	return is_highmem(zone) ?
-			saveable_highmem_page(pfn) : saveable_page(pfn);
+		saveable_highmem_page(zone, pfn) : saveable_page(zone, pfn);
 }
 
 static void copy_data_page(unsigned long dst_pfn, unsigned long src_pfn)
@@ -966,7 +981,7 @@ static void copy_data_page(unsigned long dst_pfn, unsigned long src_pfn)
 			 * data modified by kmap_atomic()
 			 */
 			safe_copy_page(buffer, s_page);
-			dst = kmap_atomic(pfn_to_page(dst_pfn), KM_USER0);
+			dst = kmap_atomic(d_page, KM_USER0);
 			memcpy(dst, buffer, PAGE_SIZE);
 			kunmap_atomic(dst, KM_USER0);
 		} else {
@@ -975,7 +990,7 @@ static void copy_data_page(unsigned long dst_pfn, unsigned long src_pfn)
 	}
 }
 #else
-#define page_is_saveable(zone, pfn)	saveable_page(pfn)
+#define page_is_saveable(zone, pfn)	saveable_page(zone, pfn)
 
 static inline void copy_data_page(unsigned long dst_pfn, unsigned long src_pfn)
 {
@@ -1459,9 +1474,7 @@ load_header(struct swsusp_info *info)
  *	unpack_orig_pfns - for each element of @buf[] (1 page at a time) set
  *	the corresponding bit in the memory bitmap @bm
  */
-
-static inline void
-unpack_orig_pfns(unsigned long *buf, struct memory_bitmap *bm)
+static int unpack_orig_pfns(unsigned long *buf, struct memory_bitmap *bm)
 {
 	int j;
 
@@ -1469,8 +1482,13 @@ unpack_orig_pfns(unsigned long *buf, struct memory_bitmap *bm)
 		if (unlikely(buf[j] == BM_END_OF_MAP))
 			break;
 
-		memory_bm_set_bit(bm, buf[j]);
+		if (memory_bm_pfn_present(bm, buf[j]))
+			memory_bm_set_bit(bm, buf[j]);
+		else
+			return -EFAULT;
 	}
+
+	return 0;
 }
 
 /* List of "safe" pages that may be used to store data loaded from the suspend
@@ -1608,7 +1626,7 @@ get_highmem_page_buffer(struct page *page, struct chain_allocator *ca)
 	pbe = chain_alloc(ca, sizeof(struct highmem_pbe));
 	if (!pbe) {
 		swsusp_free();
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 	}
 	pbe->orig_page = page;
 	if (safe_highmem_pages > 0) {
@@ -1677,7 +1695,7 @@ prepare_highmem_image(struct memory_bitmap *bm, unsigned int *nr_highmem_p)
 static inline void *
 get_highmem_page_buffer(struct page *page, struct chain_allocator *ca)
 {
-	return NULL;
+	return ERR_PTR(-EINVAL);
 }
 
 static inline void copy_last_highmem_page(void) {}
@@ -1788,8 +1806,13 @@ prepare_image(struct memory_bitmap *new_bm, struct memory_bitmap *bm)
 static void *get_buffer(struct memory_bitmap *bm, struct chain_allocator *ca)
 {
 	struct pbe *pbe;
-	struct page *page = pfn_to_page(memory_bm_next_pfn(bm));
+	struct page *page;
+	unsigned long pfn = memory_bm_next_pfn(bm);
 
+	if (pfn == BM_END_OF_MAP)
+		return ERR_PTR(-EFAULT);
+
+	page = pfn_to_page(pfn);
 	if (PageHighMem(page))
 		return get_highmem_page_buffer(page, ca);
 
@@ -1805,7 +1828,7 @@ static void *get_buffer(struct memory_bitmap *bm, struct chain_allocator *ca)
 	pbe = chain_alloc(ca, sizeof(struct pbe));
 	if (!pbe) {
 		swsusp_free();
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 	}
 	pbe->orig_address = page_address(page);
 	pbe->address = safe_pages_list;
@@ -1868,7 +1891,10 @@ int snapshot_write_next(struct snapshot_handle *handle, size_t count)
 				return error;
 
 		} else if (handle->prev <= nr_meta_pages) {
-			unpack_orig_pfns(buffer, &copy_bm);
+			error = unpack_orig_pfns(buffer, &copy_bm);
+			if (error)
+				return error;
+
 			if (handle->prev == nr_meta_pages) {
 				error = prepare_image(&orig_bm, &copy_bm);
 				if (error)
@@ -1879,12 +1905,14 @@ int snapshot_write_next(struct snapshot_handle *handle, size_t count)
 				restore_pblist = NULL;
 				handle->buffer = get_buffer(&orig_bm, &ca);
 				handle->sync_read = 0;
-				if (!handle->buffer)
-					return -ENOMEM;
+				if (IS_ERR(handle->buffer))
+					return PTR_ERR(handle->buffer);
 			}
 		} else {
 			copy_last_highmem_page();
 			handle->buffer = get_buffer(&orig_bm, &ca);
+			if (IS_ERR(handle->buffer))
+				return PTR_ERR(handle->buffer);
 			if (handle->buffer != buffer)
 				handle->sync_read = 0;
 		}
diff --git a/kernel/power/swsusp.c b/kernel/power/swsusp.c
index 023ff2a31d89..a92c91451559 100644
--- a/kernel/power/swsusp.c
+++ b/kernel/power/swsusp.c
@@ -262,3 +262,125 @@ int swsusp_shrink_memory(void)
 
 	return 0;
 }
+
+/*
+ * Platforms, like ACPI, may want us to save some memory used by them during
+ * hibernation and to restore the contents of this memory during the subsequent
+ * resume.  The code below implements a mechanism allowing us to do that.
+ */
+
+struct nvs_page {
+	unsigned long phys_start;
+	unsigned int size;
+	void *kaddr;
+	void *data;
+	struct list_head node;
+};
+
+static LIST_HEAD(nvs_list);
+
+/**
+ *	hibernate_nvs_register - register platform NVS memory region to save
+ *	@start - physical address of the region
+ *	@size - size of the region
+ *
+ *	The NVS region need not be page-aligned (both ends) and we arrange
+ *	things so that the data from page-aligned addresses in this region will
+ *	be copied into separate RAM pages.
+ */
+int hibernate_nvs_register(unsigned long start, unsigned long size)
+{
+	struct nvs_page *entry, *next;
+
+	while (size > 0) {
+		unsigned int nr_bytes;
+
+		entry = kzalloc(sizeof(struct nvs_page), GFP_KERNEL);
+		if (!entry)
+			goto Error;
+
+		list_add_tail(&entry->node, &nvs_list);
+		entry->phys_start = start;
+		nr_bytes = PAGE_SIZE - (start & ~PAGE_MASK);
+		entry->size = (size < nr_bytes) ? size : nr_bytes;
+
+		start += entry->size;
+		size -= entry->size;
+	}
+	return 0;
+
+ Error:
+	list_for_each_entry_safe(entry, next, &nvs_list, node) {
+		list_del(&entry->node);
+		kfree(entry);
+	}
+	return -ENOMEM;
+}
+
+/**
+ *	hibernate_nvs_free - free data pages allocated for saving NVS regions
+ */
+void hibernate_nvs_free(void)
+{
+	struct nvs_page *entry;
+
+	list_for_each_entry(entry, &nvs_list, node)
+		if (entry->data) {
+			free_page((unsigned long)entry->data);
+			entry->data = NULL;
+			if (entry->kaddr) {
+				iounmap(entry->kaddr);
+				entry->kaddr = NULL;
+			}
+		}
+}
+
+/**
+ *	hibernate_nvs_alloc - allocate memory necessary for saving NVS regions
+ */
+int hibernate_nvs_alloc(void)
+{
+	struct nvs_page *entry;
+
+	list_for_each_entry(entry, &nvs_list, node) {
+		entry->data = (void *)__get_free_page(GFP_KERNEL);
+		if (!entry->data) {
+			hibernate_nvs_free();
+			return -ENOMEM;
+		}
+	}
+	return 0;
+}
+
+/**
+ *	hibernate_nvs_save - save NVS memory regions
+ */
+void hibernate_nvs_save(void)
+{
+	struct nvs_page *entry;
+
+	printk(KERN_INFO "PM: Saving platform NVS memory\n");
+
+	list_for_each_entry(entry, &nvs_list, node)
+		if (entry->data) {
+			entry->kaddr = ioremap(entry->phys_start, entry->size);
+			memcpy(entry->data, entry->kaddr, entry->size);
+		}
+}
+
+/**
+ *	hibernate_nvs_restore - restore NVS memory regions
+ *
+ *	This function is going to be called with interrupts disabled, so it
+ *	cannot iounmap the virtual addresses used to access the NVS region.
+ */
+void hibernate_nvs_restore(void)
+{
+	struct nvs_page *entry;
+
+	printk(KERN_INFO "PM: Restoring platform NVS memory\n");
+
+	list_for_each_entry(entry, &nvs_list, node)
+		if (entry->data)
+			memcpy(entry->kaddr, entry->data, entry->size);
+}
diff --git a/kernel/printk.c b/kernel/printk.c
index f492f1583d77..7015733793e8 100644
--- a/kernel/printk.c
+++ b/kernel/printk.c
@@ -619,7 +619,7 @@ static int acquire_console_semaphore_for_printk(unsigned int cpu)
 static const char recursion_bug_msg [] =
 		KERN_CRIT "BUG: recent printk recursion!\n";
 static int recursion_bug;
-	static int new_text_line = 1;
+static int new_text_line = 1;
 static char printk_buf[1024];
 
 asmlinkage int vprintk(const char *fmt, va_list args)
@@ -662,7 +662,7 @@ asmlinkage int vprintk(const char *fmt, va_list args)
 	if (recursion_bug) {
 		recursion_bug = 0;
 		strcpy(printk_buf, recursion_bug_msg);
-		printed_len = sizeof(recursion_bug_msg);
+		printed_len = strlen(recursion_bug_msg);
 	}
 	/* Emit the output into the temporary buffer */
 	printed_len += vscnprintf(printk_buf + printed_len,
diff --git a/kernel/profile.c b/kernel/profile.c
index 60adefb59b5e..784933acf5b8 100644
--- a/kernel/profile.c
+++ b/kernel/profile.c
@@ -45,7 +45,7 @@ static unsigned long prof_len, prof_shift;
 int prof_on __read_mostly;
 EXPORT_SYMBOL_GPL(prof_on);
 
-static cpumask_t prof_cpu_mask = CPU_MASK_ALL;
+static cpumask_var_t prof_cpu_mask;
 #ifdef CONFIG_SMP
 static DEFINE_PER_CPU(struct profile_hit *[2], cpu_profile_hits);
 static DEFINE_PER_CPU(int, cpu_profile_flip);
@@ -113,9 +113,13 @@ int __ref profile_init(void)
 	buffer_bytes = prof_len*sizeof(atomic_t);
 	if (!slab_is_available()) {
 		prof_buffer = alloc_bootmem(buffer_bytes);
+		alloc_bootmem_cpumask_var(&prof_cpu_mask);
 		return 0;
 	}
 
+	if (!alloc_cpumask_var(&prof_cpu_mask, GFP_KERNEL))
+		return -ENOMEM;
+
 	prof_buffer = kzalloc(buffer_bytes, GFP_KERNEL);
 	if (prof_buffer)
 		return 0;
@@ -128,6 +132,7 @@ int __ref profile_init(void)
 	if (prof_buffer)
 		return 0;
 
+	free_cpumask_var(prof_cpu_mask);
 	return -ENOMEM;
 }
 
@@ -386,13 +391,15 @@ out_free:
 		return NOTIFY_BAD;
 	case CPU_ONLINE:
 	case CPU_ONLINE_FROZEN:
-		cpu_set(cpu, prof_cpu_mask);
+		if (prof_cpu_mask != NULL)
+			cpumask_set_cpu(cpu, prof_cpu_mask);
 		break;
 	case CPU_UP_CANCELED:
 	case CPU_UP_CANCELED_FROZEN:
 	case CPU_DEAD:
 	case CPU_DEAD_FROZEN:
-		cpu_clear(cpu, prof_cpu_mask);
+		if (prof_cpu_mask != NULL)
+			cpumask_clear_cpu(cpu, prof_cpu_mask);
 		if (per_cpu(cpu_profile_hits, cpu)[0]) {
 			page = virt_to_page(per_cpu(cpu_profile_hits, cpu)[0]);
 			per_cpu(cpu_profile_hits, cpu)[0] = NULL;
@@ -430,19 +437,19 @@ void profile_tick(int type)
 
 	if (type == CPU_PROFILING && timer_hook)
 		timer_hook(regs);
-	if (!user_mode(regs) && cpu_isset(smp_processor_id(), prof_cpu_mask))
+	if (!user_mode(regs) && prof_cpu_mask != NULL &&
+	    cpumask_test_cpu(smp_processor_id(), prof_cpu_mask))
 		profile_hit(type, (void *)profile_pc(regs));
 }
 
 #ifdef CONFIG_PROC_FS
 #include <linux/proc_fs.h>
 #include <asm/uaccess.h>
-#include <asm/ptrace.h>
 
 static int prof_cpu_mask_read_proc(char *page, char **start, off_t off,
 			int count, int *eof, void *data)
 {
-	int len = cpumask_scnprintf(page, count, *(cpumask_t *)data);
+	int len = cpumask_scnprintf(page, count, data);
 	if (count - len < 2)
 		return -EINVAL;
 	len += sprintf(page + len, "\n");
@@ -452,16 +459,20 @@ static int prof_cpu_mask_read_proc(char *page, char **start, off_t off,
 static int prof_cpu_mask_write_proc(struct file *file,
 	const char __user *buffer,  unsigned long count, void *data)
 {
-	cpumask_t *mask = (cpumask_t *)data;
+	struct cpumask *mask = data;
 	unsigned long full_count = count, err;
-	cpumask_t new_value;
+	cpumask_var_t new_value;
 
-	err = cpumask_parse_user(buffer, count, new_value);
-	if (err)
-		return err;
+	if (!alloc_cpumask_var(&new_value, GFP_KERNEL))
+		return -ENOMEM;
 
-	*mask = new_value;
-	return full_count;
+	err = cpumask_parse_user(buffer, count, new_value);
+	if (!err) {
+		cpumask_copy(mask, new_value);
+		err = full_count;
+	}
+	free_cpumask_var(new_value);
+	return err;
 }
 
 void create_prof_cpu_mask(struct proc_dir_entry *root_irq_dir)
@@ -472,7 +483,7 @@ void create_prof_cpu_mask(struct proc_dir_entry *root_irq_dir)
 	entry = create_proc_entry("prof_cpu_mask", 0600, root_irq_dir);
 	if (!entry)
 		return;
-	entry->data = (void *)&prof_cpu_mask;
+	entry->data = prof_cpu_mask;
 	entry->read_proc = prof_cpu_mask_read_proc;
 	entry->write_proc = prof_cpu_mask_write_proc;
 }
diff --git a/kernel/rcuclassic.c b/kernel/rcuclassic.c
index 37f72e551542..490934fc7ac3 100644
--- a/kernel/rcuclassic.c
+++ b/kernel/rcuclassic.c
@@ -63,14 +63,14 @@ static struct rcu_ctrlblk rcu_ctrlblk = {
 	.completed = -300,
 	.pending = -300,
 	.lock = __SPIN_LOCK_UNLOCKED(&rcu_ctrlblk.lock),
-	.cpumask = CPU_MASK_NONE,
+	.cpumask = CPU_BITS_NONE,
 };
 static struct rcu_ctrlblk rcu_bh_ctrlblk = {
 	.cur = -300,
 	.completed = -300,
 	.pending = -300,
 	.lock = __SPIN_LOCK_UNLOCKED(&rcu_bh_ctrlblk.lock),
-	.cpumask = CPU_MASK_NONE,
+	.cpumask = CPU_BITS_NONE,
 };
 
 DEFINE_PER_CPU(struct rcu_data, rcu_data) = { 0L };
@@ -85,7 +85,6 @@ static void force_quiescent_state(struct rcu_data *rdp,
 			struct rcu_ctrlblk *rcp)
 {
 	int cpu;
-	cpumask_t cpumask;
 	unsigned long flags;
 
 	set_need_resched();
@@ -96,10 +95,10 @@ static void force_quiescent_state(struct rcu_data *rdp,
 		 * Don't send IPI to itself. With irqs disabled,
 		 * rdp->cpu is the current cpu.
 		 *
-		 * cpu_online_map is updated by the _cpu_down()
+		 * cpu_online_mask is updated by the _cpu_down()
 		 * using __stop_machine(). Since we're in irqs disabled
 		 * section, __stop_machine() is not exectuting, hence
-		 * the cpu_online_map is stable.
+		 * the cpu_online_mask is stable.
 		 *
 		 * However,  a cpu might have been offlined _just_ before
 		 * we disabled irqs while entering here.
@@ -107,13 +106,14 @@ static void force_quiescent_state(struct rcu_data *rdp,
 		 * notification, leading to the offlined cpu's bit
 		 * being set in the rcp->cpumask.
 		 *
-		 * Hence cpumask = (rcp->cpumask & cpu_online_map) to prevent
+		 * Hence cpumask = (rcp->cpumask & cpu_online_mask) to prevent
 		 * sending smp_reschedule() to an offlined CPU.
 		 */
-		cpus_and(cpumask, rcp->cpumask, cpu_online_map);
-		cpu_clear(rdp->cpu, cpumask);
-		for_each_cpu_mask_nr(cpu, cpumask)
-			smp_send_reschedule(cpu);
+		for_each_cpu_and(cpu,
+				  to_cpumask(rcp->cpumask), cpu_online_mask) {
+			if (cpu != rdp->cpu)
+				smp_send_reschedule(cpu);
+		}
 	}
 	spin_unlock_irqrestore(&rcp->lock, flags);
 }
@@ -191,9 +191,9 @@ static void print_other_cpu_stall(struct rcu_ctrlblk *rcp)
 
 	/* OK, time to rat on our buddy... */
 
-	printk(KERN_ERR "RCU detected CPU stalls:");
+	printk(KERN_ERR "INFO: RCU detected CPU stalls:");
 	for_each_possible_cpu(cpu) {
-		if (cpu_isset(cpu, rcp->cpumask))
+		if (cpumask_test_cpu(cpu, to_cpumask(rcp->cpumask)))
 			printk(" %d", cpu);
 	}
 	printk(" (detected by %d, t=%ld jiffies)\n",
@@ -204,7 +204,7 @@ static void print_cpu_stall(struct rcu_ctrlblk *rcp)
 {
 	unsigned long flags;
 
-	printk(KERN_ERR "RCU detected CPU %d stall (t=%lu/%lu jiffies)\n",
+	printk(KERN_ERR "INFO: RCU detected CPU %d stall (t=%lu/%lu jiffies)\n",
 			smp_processor_id(), jiffies,
 			jiffies - rcp->gp_start);
 	dump_stack();
@@ -221,7 +221,8 @@ static void check_cpu_stall(struct rcu_ctrlblk *rcp)
 	long delta;
 
 	delta = jiffies - rcp->jiffies_stall;
-	if (cpu_isset(smp_processor_id(), rcp->cpumask) && delta >= 0) {
+	if (cpumask_test_cpu(smp_processor_id(), to_cpumask(rcp->cpumask)) &&
+		delta >= 0) {
 
 		/* We haven't checked in, so go dump stack. */
 		print_cpu_stall(rcp);
@@ -393,7 +394,8 @@ static void rcu_start_batch(struct rcu_ctrlblk *rcp)
 		 * unnecessarily.
 		 */
 		smp_mb();
-		cpus_andnot(rcp->cpumask, cpu_online_map, nohz_cpu_mask);
+		cpumask_andnot(to_cpumask(rcp->cpumask),
+			       cpu_online_mask, nohz_cpu_mask);
 
 		rcp->signaled = 0;
 	}
@@ -406,8 +408,8 @@ static void rcu_start_batch(struct rcu_ctrlblk *rcp)
  */
 static void cpu_quiet(int cpu, struct rcu_ctrlblk *rcp)
 {
-	cpu_clear(cpu, rcp->cpumask);
-	if (cpus_empty(rcp->cpumask)) {
+	cpumask_clear_cpu(cpu, to_cpumask(rcp->cpumask));
+	if (cpumask_empty(to_cpumask(rcp->cpumask))) {
 		/* batch completed ! */
 		rcp->completed = rcp->cur;
 		rcu_start_batch(rcp);
diff --git a/kernel/rcupdate.c b/kernel/rcupdate.c
index ad63af8b2521..d92a76a881aa 100644
--- a/kernel/rcupdate.c
+++ b/kernel/rcupdate.c
@@ -77,8 +77,15 @@ void wakeme_after_rcu(struct rcu_head  *head)
  * sections are delimited by rcu_read_lock() and rcu_read_unlock(),
  * and may be nested.
  */
-void synchronize_rcu(void);	/* Makes kernel-doc tools happy */
-synchronize_rcu_xxx(synchronize_rcu, call_rcu)
+void synchronize_rcu(void)
+{
+	struct rcu_synchronize rcu;
+	init_completion(&rcu.completion);
+	/* Will wake me after RCU finished. */
+	call_rcu(&rcu.head, wakeme_after_rcu);
+	/* Wait for it. */
+	wait_for_completion(&rcu.completion);
+}
 EXPORT_SYMBOL_GPL(synchronize_rcu);
 
 static void rcu_barrier_callback(struct rcu_head *notused)
diff --git a/kernel/rcupreempt.c b/kernel/rcupreempt.c
index 59236e8b9daa..33cfc50781f9 100644
--- a/kernel/rcupreempt.c
+++ b/kernel/rcupreempt.c
@@ -164,7 +164,8 @@ static char *rcu_try_flip_state_names[] =
 	{ "idle", "waitack", "waitzero", "waitmb" };
 #endif /* #ifdef CONFIG_RCU_TRACE */
 
-static cpumask_t rcu_cpu_online_map __read_mostly = CPU_MASK_NONE;
+static DECLARE_BITMAP(rcu_cpu_online_map, NR_CPUS) __read_mostly
+	= CPU_BITS_NONE;
 
 /*
  * Enum and per-CPU flag to determine when each CPU has seen
@@ -551,6 +552,16 @@ void rcu_irq_exit(void)
 	}
 }
 
+void rcu_nmi_enter(void)
+{
+	rcu_irq_enter();
+}
+
+void rcu_nmi_exit(void)
+{
+	rcu_irq_exit();
+}
+
 static void dyntick_save_progress_counter(int cpu)
 {
 	struct rcu_dyntick_sched *rdssp = &per_cpu(rcu_dyntick_sched, cpu);
@@ -748,7 +759,7 @@ rcu_try_flip_idle(void)
 
 	/* Now ask each CPU for acknowledgement of the flip. */
 
-	for_each_cpu_mask_nr(cpu, rcu_cpu_online_map) {
+	for_each_cpu(cpu, to_cpumask(rcu_cpu_online_map)) {
 		per_cpu(rcu_flip_flag, cpu) = rcu_flipped;
 		dyntick_save_progress_counter(cpu);
 	}
@@ -766,7 +777,7 @@ rcu_try_flip_waitack(void)
 	int cpu;
 
 	RCU_TRACE_ME(rcupreempt_trace_try_flip_a1);
-	for_each_cpu_mask_nr(cpu, rcu_cpu_online_map)
+	for_each_cpu(cpu, to_cpumask(rcu_cpu_online_map))
 		if (rcu_try_flip_waitack_needed(cpu) &&
 		    per_cpu(rcu_flip_flag, cpu) != rcu_flip_seen) {
 			RCU_TRACE_ME(rcupreempt_trace_try_flip_ae1);
@@ -798,7 +809,7 @@ rcu_try_flip_waitzero(void)
 	/* Check to see if the sum of the "last" counters is zero. */
 
 	RCU_TRACE_ME(rcupreempt_trace_try_flip_z1);
-	for_each_cpu_mask_nr(cpu, rcu_cpu_online_map)
+	for_each_cpu(cpu, to_cpumask(rcu_cpu_online_map))
 		sum += RCU_DATA_CPU(cpu)->rcu_flipctr[lastidx];
 	if (sum != 0) {
 		RCU_TRACE_ME(rcupreempt_trace_try_flip_ze1);
@@ -813,7 +824,7 @@ rcu_try_flip_waitzero(void)
 	smp_mb();  /*  ^^^^^^^^^^^^ */
 
 	/* Call for a memory barrier from each CPU. */
-	for_each_cpu_mask_nr(cpu, rcu_cpu_online_map) {
+	for_each_cpu(cpu, to_cpumask(rcu_cpu_online_map)) {
 		per_cpu(rcu_mb_flag, cpu) = rcu_mb_needed;
 		dyntick_save_progress_counter(cpu);
 	}
@@ -833,7 +844,7 @@ rcu_try_flip_waitmb(void)
 	int cpu;
 
 	RCU_TRACE_ME(rcupreempt_trace_try_flip_m1);
-	for_each_cpu_mask_nr(cpu, rcu_cpu_online_map)
+	for_each_cpu(cpu, to_cpumask(rcu_cpu_online_map))
 		if (rcu_try_flip_waitmb_needed(cpu) &&
 		    per_cpu(rcu_mb_flag, cpu) != rcu_mb_done) {
 			RCU_TRACE_ME(rcupreempt_trace_try_flip_me1);
@@ -1022,7 +1033,7 @@ void rcu_offline_cpu(int cpu)
 	RCU_DATA_CPU(cpu)->rcu_flipctr[0] = 0;
 	RCU_DATA_CPU(cpu)->rcu_flipctr[1] = 0;
 
-	cpu_clear(cpu, rcu_cpu_online_map);
+	cpumask_clear_cpu(cpu, to_cpumask(rcu_cpu_online_map));
 
 	spin_unlock_irqrestore(&rcu_ctrlblk.fliplock, flags);
 
@@ -1062,7 +1073,7 @@ void __cpuinit rcu_online_cpu(int cpu)
 	struct rcu_data *rdp;
 
 	spin_lock_irqsave(&rcu_ctrlblk.fliplock, flags);
-	cpu_set(cpu, rcu_cpu_online_map);
+	cpumask_set_cpu(cpu, to_cpumask(rcu_cpu_online_map));
 	spin_unlock_irqrestore(&rcu_ctrlblk.fliplock, flags);
 
 	/*
@@ -1166,7 +1177,16 @@ EXPORT_SYMBOL_GPL(call_rcu_sched);
  * in -rt this does -not- necessarily result in all currently executing
  * interrupt -handlers- having completed.
  */
-synchronize_rcu_xxx(__synchronize_sched, call_rcu_sched)
+void __synchronize_sched(void)
+{
+	struct rcu_synchronize rcu;
+
+	init_completion(&rcu.completion);
+	/* Will wake me after RCU finished. */
+	call_rcu_sched(&rcu.head, wakeme_after_rcu);
+	/* Wait for it. */
+	wait_for_completion(&rcu.completion);
+}
 EXPORT_SYMBOL_GPL(__synchronize_sched);
 
 /*
@@ -1420,7 +1440,7 @@ void __init __rcu_init(void)
 	 * We don't need protection against CPU-Hotplug here
 	 * since
 	 * a) If a CPU comes online while we are iterating over the
-	 *    cpu_online_map below, we would only end up making a
+	 *    cpu_online_mask below, we would only end up making a
 	 *    duplicate call to rcu_online_cpu() which sets the corresponding
 	 *    CPU's mask in the rcu_cpu_online_map.
 	 *
diff --git a/kernel/rcupreempt_trace.c b/kernel/rcupreempt_trace.c
index 35c2d3360ecf..7c2665cac172 100644
--- a/kernel/rcupreempt_trace.c
+++ b/kernel/rcupreempt_trace.c
@@ -149,12 +149,12 @@ static void rcupreempt_trace_sum(struct rcupreempt_trace *sp)
 		sp->done_length += cp->done_length;
 		sp->done_add += cp->done_add;
 		sp->done_remove += cp->done_remove;
-		atomic_set(&sp->done_invoked, atomic_read(&cp->done_invoked));
+		atomic_add(atomic_read(&cp->done_invoked), &sp->done_invoked);
 		sp->rcu_check_callbacks += cp->rcu_check_callbacks;
-		atomic_set(&sp->rcu_try_flip_1,
-			   atomic_read(&cp->rcu_try_flip_1));
-		atomic_set(&sp->rcu_try_flip_e1,
-			   atomic_read(&cp->rcu_try_flip_e1));
+		atomic_add(atomic_read(&cp->rcu_try_flip_1),
+			   &sp->rcu_try_flip_1);
+		atomic_add(atomic_read(&cp->rcu_try_flip_e1),
+			   &sp->rcu_try_flip_e1);
 		sp->rcu_try_flip_i1 += cp->rcu_try_flip_i1;
 		sp->rcu_try_flip_ie1 += cp->rcu_try_flip_ie1;
 		sp->rcu_try_flip_g1 += cp->rcu_try_flip_g1;
diff --git a/kernel/rcutorture.c b/kernel/rcutorture.c
index 85cb90588a55..1cff28db56b6 100644
--- a/kernel/rcutorture.c
+++ b/kernel/rcutorture.c
@@ -39,6 +39,7 @@
 #include <linux/moduleparam.h>
 #include <linux/percpu.h>
 #include <linux/notifier.h>
+#include <linux/reboot.h>
 #include <linux/freezer.h>
 #include <linux/cpu.h>
 #include <linux/delay.h>
@@ -108,7 +109,6 @@ struct rcu_torture {
 	int rtort_mbtest;
 };
 
-static int fullstop = 0;	/* stop generating callbacks at test end. */
 static LIST_HEAD(rcu_torture_freelist);
 static struct rcu_torture *rcu_torture_current = NULL;
 static long rcu_torture_current_version = 0;
@@ -136,6 +136,28 @@ static int stutter_pause_test = 0;
 #endif
 int rcutorture_runnable = RCUTORTURE_RUNNABLE_INIT;
 
+#define FULLSTOP_SHUTDOWN 1	/* Bail due to system shutdown/panic. */
+#define FULLSTOP_CLEANUP  2	/* Orderly shutdown. */
+static int fullstop;		/* stop generating callbacks at test end. */
+DEFINE_MUTEX(fullstop_mutex);	/* protect fullstop transitions and */
+				/*  spawning of kthreads. */
+
+/*
+ * Detect and respond to a signal-based shutdown.
+ */
+static int
+rcutorture_shutdown_notify(struct notifier_block *unused1,
+			   unsigned long unused2, void *unused3)
+{
+	if (fullstop)
+		return NOTIFY_DONE;
+	mutex_lock(&fullstop_mutex);
+	if (!fullstop)
+		fullstop = FULLSTOP_SHUTDOWN;
+	mutex_unlock(&fullstop_mutex);
+	return NOTIFY_DONE;
+}
+
 /*
  * Allocate an element from the rcu_tortures pool.
  */
@@ -199,11 +221,12 @@ rcu_random(struct rcu_random_state *rrsp)
 static void
 rcu_stutter_wait(void)
 {
-	while (stutter_pause_test || !rcutorture_runnable)
+	while ((stutter_pause_test || !rcutorture_runnable) && !fullstop) {
 		if (rcutorture_runnable)
 			schedule_timeout_interruptible(1);
 		else
 			schedule_timeout_interruptible(round_jiffies_relative(HZ));
+	}
 }
 
 /*
@@ -599,7 +622,7 @@ rcu_torture_writer(void *arg)
 		rcu_stutter_wait();
 	} while (!kthread_should_stop() && !fullstop);
 	VERBOSE_PRINTK_STRING("rcu_torture_writer task stopping");
-	while (!kthread_should_stop())
+	while (!kthread_should_stop() && fullstop != FULLSTOP_SHUTDOWN)
 		schedule_timeout_uninterruptible(1);
 	return 0;
 }
@@ -624,7 +647,7 @@ rcu_torture_fakewriter(void *arg)
 	} while (!kthread_should_stop() && !fullstop);
 
 	VERBOSE_PRINTK_STRING("rcu_torture_fakewriter task stopping");
-	while (!kthread_should_stop())
+	while (!kthread_should_stop() && fullstop != FULLSTOP_SHUTDOWN)
 		schedule_timeout_uninterruptible(1);
 	return 0;
 }
@@ -734,7 +757,7 @@ rcu_torture_reader(void *arg)
 	VERBOSE_PRINTK_STRING("rcu_torture_reader task stopping");
 	if (irqreader && cur_ops->irqcapable)
 		del_timer_sync(&t);
-	while (!kthread_should_stop())
+	while (!kthread_should_stop() && fullstop != FULLSTOP_SHUTDOWN)
 		schedule_timeout_uninterruptible(1);
 	return 0;
 }
@@ -831,7 +854,7 @@ rcu_torture_stats(void *arg)
 	do {
 		schedule_timeout_interruptible(stat_interval * HZ);
 		rcu_torture_stats_print();
-	} while (!kthread_should_stop());
+	} while (!kthread_should_stop() && !fullstop);
 	VERBOSE_PRINTK_STRING("rcu_torture_stats task stopping");
 	return 0;
 }
@@ -843,49 +866,52 @@ static int rcu_idle_cpu;	/* Force all torture tasks off this CPU */
  */
 static void rcu_torture_shuffle_tasks(void)
 {
-	cpumask_t tmp_mask;
+	cpumask_var_t tmp_mask;
 	int i;
 
-	cpus_setall(tmp_mask);
+	if (!alloc_cpumask_var(&tmp_mask, GFP_KERNEL))
+		BUG();
+
+	cpumask_setall(tmp_mask);
 	get_online_cpus();
 
 	/* No point in shuffling if there is only one online CPU (ex: UP) */
-	if (num_online_cpus() == 1) {
-		put_online_cpus();
-		return;
-	}
+	if (num_online_cpus() == 1)
+		goto out;
 
 	if (rcu_idle_cpu != -1)
-		cpu_clear(rcu_idle_cpu, tmp_mask);
+		cpumask_clear_cpu(rcu_idle_cpu, tmp_mask);
 
-	set_cpus_allowed_ptr(current, &tmp_mask);
+	set_cpus_allowed_ptr(current, tmp_mask);
 
 	if (reader_tasks) {
 		for (i = 0; i < nrealreaders; i++)
 			if (reader_tasks[i])
 				set_cpus_allowed_ptr(reader_tasks[i],
-						     &tmp_mask);
+						     tmp_mask);
 	}
 
 	if (fakewriter_tasks) {
 		for (i = 0; i < nfakewriters; i++)
 			if (fakewriter_tasks[i])
 				set_cpus_allowed_ptr(fakewriter_tasks[i],
-						     &tmp_mask);
+						     tmp_mask);
 	}
 
 	if (writer_task)
-		set_cpus_allowed_ptr(writer_task, &tmp_mask);
+		set_cpus_allowed_ptr(writer_task, tmp_mask);
 
 	if (stats_task)
-		set_cpus_allowed_ptr(stats_task, &tmp_mask);
+		set_cpus_allowed_ptr(stats_task, tmp_mask);
 
 	if (rcu_idle_cpu == -1)
 		rcu_idle_cpu = num_online_cpus() - 1;
 	else
 		rcu_idle_cpu--;
 
+out:
 	put_online_cpus();
+	free_cpumask_var(tmp_mask);
 }
 
 /* Shuffle tasks across CPUs, with the intent of allowing each CPU in the
@@ -899,7 +925,7 @@ rcu_torture_shuffle(void *arg)
 	do {
 		schedule_timeout_interruptible(shuffle_interval * HZ);
 		rcu_torture_shuffle_tasks();
-	} while (!kthread_should_stop());
+	} while (!kthread_should_stop() && !fullstop);
 	VERBOSE_PRINTK_STRING("rcu_torture_shuffle task stopping");
 	return 0;
 }
@@ -914,10 +940,10 @@ rcu_torture_stutter(void *arg)
 	do {
 		schedule_timeout_interruptible(stutter * HZ);
 		stutter_pause_test = 1;
-		if (!kthread_should_stop())
+		if (!kthread_should_stop() && !fullstop)
 			schedule_timeout_interruptible(stutter * HZ);
 		stutter_pause_test = 0;
-	} while (!kthread_should_stop());
+	} while (!kthread_should_stop() && !fullstop);
 	VERBOSE_PRINTK_STRING("rcu_torture_stutter task stopping");
 	return 0;
 }
@@ -934,12 +960,27 @@ rcu_torture_print_module_parms(char *tag)
 		stutter, irqreader);
 }
 
+static struct notifier_block rcutorture_nb = {
+	.notifier_call = rcutorture_shutdown_notify,
+};
+
 static void
 rcu_torture_cleanup(void)
 {
 	int i;
 
-	fullstop = 1;
+	mutex_lock(&fullstop_mutex);
+	if (!fullstop) {
+		/* If being signaled, let it happen, then exit. */
+		mutex_unlock(&fullstop_mutex);
+		schedule_timeout_interruptible(10 * HZ);
+		if (cur_ops->cb_barrier != NULL)
+			cur_ops->cb_barrier();
+		return;
+	}
+	fullstop = FULLSTOP_CLEANUP;
+	mutex_unlock(&fullstop_mutex);
+	unregister_reboot_notifier(&rcutorture_nb);
 	if (stutter_task) {
 		VERBOSE_PRINTK_STRING("Stopping rcu_torture_stutter task");
 		kthread_stop(stutter_task);
@@ -1015,6 +1056,8 @@ rcu_torture_init(void)
 		{ &rcu_ops, &rcu_sync_ops, &rcu_bh_ops, &rcu_bh_sync_ops,
 		  &srcu_ops, &sched_ops, &sched_ops_sync, };
 
+	mutex_lock(&fullstop_mutex);
+
 	/* Process args and tell the world that the torturer is on the job. */
 	for (i = 0; i < ARRAY_SIZE(torture_ops); i++) {
 		cur_ops = torture_ops[i];
@@ -1024,6 +1067,7 @@ rcu_torture_init(void)
 	if (i == ARRAY_SIZE(torture_ops)) {
 		printk(KERN_ALERT "rcutorture: invalid torture type: \"%s\"\n",
 		       torture_type);
+		mutex_unlock(&fullstop_mutex);
 		return (-EINVAL);
 	}
 	if (cur_ops->init)
@@ -1146,9 +1190,12 @@ rcu_torture_init(void)
 			goto unwind;
 		}
 	}
+	register_reboot_notifier(&rcutorture_nb);
+	mutex_unlock(&fullstop_mutex);
 	return 0;
 
 unwind:
+	mutex_unlock(&fullstop_mutex);
 	rcu_torture_cleanup();
 	return firsterr;
 }
diff --git a/kernel/rcutree.c b/kernel/rcutree.c
new file mode 100644
index 000000000000..f2d8638e6c60
--- /dev/null
+++ b/kernel/rcutree.c
@@ -0,0 +1,1532 @@
+/*
+ * Read-Copy Update mechanism for mutual exclusion
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that 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., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ *
+ * Copyright IBM Corporation, 2008
+ *
+ * Authors: Dipankar Sarma <dipankar@in.ibm.com>
+ *	    Manfred Spraul <manfred@colorfullife.com>
+ *	    Paul E. McKenney <paulmck@linux.vnet.ibm.com> Hierarchical version
+ *
+ * Based on the original work by Paul McKenney <paulmck@us.ibm.com>
+ * and inputs from Rusty Russell, Andrea Arcangeli and Andi Kleen.
+ *
+ * For detailed explanation of Read-Copy Update mechanism see -
+ * 	Documentation/RCU
+ */
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/spinlock.h>
+#include <linux/smp.h>
+#include <linux/rcupdate.h>
+#include <linux/interrupt.h>
+#include <linux/sched.h>
+#include <asm/atomic.h>
+#include <linux/bitops.h>
+#include <linux/module.h>
+#include <linux/completion.h>
+#include <linux/moduleparam.h>
+#include <linux/percpu.h>
+#include <linux/notifier.h>
+#include <linux/cpu.h>
+#include <linux/mutex.h>
+#include <linux/time.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);
+#endif
+
+/* Data structures. */
+
+#define RCU_STATE_INITIALIZER(name) { \
+	.level = { &name.node[0] }, \
+	.levelcnt = { \
+		NUM_RCU_LVL_0,  /* root of hierarchy. */ \
+		NUM_RCU_LVL_1, \
+		NUM_RCU_LVL_2, \
+		NUM_RCU_LVL_3, /* == MAX_RCU_LVLS */ \
+	}, \
+	.signaled = RCU_SIGNAL_INIT, \
+	.gpnum = -300, \
+	.completed = -300, \
+	.onofflock = __SPIN_LOCK_UNLOCKED(&name.onofflock), \
+	.fqslock = __SPIN_LOCK_UNLOCKED(&name.fqslock), \
+	.n_force_qs = 0, \
+	.n_force_qs_ngp = 0, \
+}
+
+struct rcu_state rcu_state = RCU_STATE_INITIALIZER(rcu_state);
+DEFINE_PER_CPU(struct rcu_data, rcu_data);
+
+struct rcu_state rcu_bh_state = RCU_STATE_INITIALIZER(rcu_bh_state);
+DEFINE_PER_CPU(struct rcu_data, rcu_bh_data);
+
+#ifdef CONFIG_NO_HZ
+DEFINE_PER_CPU(struct rcu_dynticks, rcu_dynticks) = {
+	.dynticks_nesting = 1,
+	.dynticks = 1,
+};
+#endif /* #ifdef CONFIG_NO_HZ */
+
+static int blimit = 10;		/* Maximum callbacks per softirq. */
+static int qhimark = 10000;	/* If this many pending, ignore blimit. */
+static int qlowmark = 100;	/* Once only this many pending, use blimit. */
+
+static void force_quiescent_state(struct rcu_state *rsp, int relaxed);
+
+/*
+ * Return the number of RCU batches processed thus far for debug & stats.
+ */
+long rcu_batches_completed(void)
+{
+	return rcu_state.completed;
+}
+EXPORT_SYMBOL_GPL(rcu_batches_completed);
+
+/*
+ * Return the number of RCU BH batches processed thus far for debug & stats.
+ */
+long rcu_batches_completed_bh(void)
+{
+	return rcu_bh_state.completed;
+}
+EXPORT_SYMBOL_GPL(rcu_batches_completed_bh);
+
+/*
+ * Does the CPU have callbacks ready to be invoked?
+ */
+static int
+cpu_has_callbacks_ready_to_invoke(struct rcu_data *rdp)
+{
+	return &rdp->nxtlist != rdp->nxttail[RCU_DONE_TAIL];
+}
+
+/*
+ * Does the current CPU require a yet-as-unscheduled grace period?
+ */
+static int
+cpu_needs_another_gp(struct rcu_state *rsp, struct rcu_data *rdp)
+{
+	/* ACCESS_ONCE() because we are accessing outside of lock. */
+	return *rdp->nxttail[RCU_DONE_TAIL] &&
+	       ACCESS_ONCE(rsp->completed) == ACCESS_ONCE(rsp->gpnum);
+}
+
+/*
+ * Return the root node of the specified rcu_state structure.
+ */
+static struct rcu_node *rcu_get_root(struct rcu_state *rsp)
+{
+	return &rsp->node[0];
+}
+
+#ifdef CONFIG_SMP
+
+/*
+ * If the specified CPU is offline, tell the caller that it is in
+ * a quiescent state.  Otherwise, whack it with a reschedule IPI.
+ * Grace periods can end up waiting on an offline CPU when that
+ * CPU is in the process of coming online -- it will be added to the
+ * rcu_node bitmasks before it actually makes it online.  The same thing
+ * can happen while a CPU is in the process of coming online.  Because this
+ * race is quite rare, we check for it after detecting that the grace
+ * period has been delayed rather than checking each and every CPU
+ * each and every time we start a new grace period.
+ */
+static int rcu_implicit_offline_qs(struct rcu_data *rdp)
+{
+	/*
+	 * If the CPU is offline, it is in a quiescent state.  We can
+	 * trust its state not to change because interrupts are disabled.
+	 */
+	if (cpu_is_offline(rdp->cpu)) {
+		rdp->offline_fqs++;
+		return 1;
+	}
+
+	/* The CPU is online, so send it a reschedule IPI. */
+	if (rdp->cpu != smp_processor_id())
+		smp_send_reschedule(rdp->cpu);
+	else
+		set_need_resched();
+	rdp->resched_ipi++;
+	return 0;
+}
+
+#endif /* #ifdef CONFIG_SMP */
+
+#ifdef CONFIG_NO_HZ
+static DEFINE_RATELIMIT_STATE(rcu_rs, 10 * HZ, 5);
+
+/**
+ * rcu_enter_nohz - inform RCU that current CPU is entering nohz
+ *
+ * Enter nohz mode, in other words, -leave- the mode in which RCU
+ * read-side critical sections can occur.  (Though RCU read-side
+ * critical sections can occur in irq handlers in nohz mode, a possibility
+ * handled by rcu_irq_enter() and rcu_irq_exit()).
+ */
+void rcu_enter_nohz(void)
+{
+	unsigned long flags;
+	struct rcu_dynticks *rdtp;
+
+	smp_mb(); /* CPUs seeing ++ must see prior RCU read-side crit sects */
+	local_irq_save(flags);
+	rdtp = &__get_cpu_var(rcu_dynticks);
+	rdtp->dynticks++;
+	rdtp->dynticks_nesting--;
+	WARN_ON_RATELIMIT(rdtp->dynticks & 0x1, &rcu_rs);
+	local_irq_restore(flags);
+}
+
+/*
+ * rcu_exit_nohz - inform RCU that current CPU is leaving nohz
+ *
+ * Exit nohz mode, in other words, -enter- the mode in which RCU
+ * read-side critical sections normally occur.
+ */
+void rcu_exit_nohz(void)
+{
+	unsigned long flags;
+	struct rcu_dynticks *rdtp;
+
+	local_irq_save(flags);
+	rdtp = &__get_cpu_var(rcu_dynticks);
+	rdtp->dynticks++;
+	rdtp->dynticks_nesting++;
+	WARN_ON_RATELIMIT(!(rdtp->dynticks & 0x1), &rcu_rs);
+	local_irq_restore(flags);
+	smp_mb(); /* CPUs seeing ++ must see later RCU read-side crit sects */
+}
+
+/**
+ * rcu_nmi_enter - inform RCU of entry to NMI context
+ *
+ * If the CPU was idle with dynamic ticks active, and there is no
+ * irq handler running, this updates rdtp->dynticks_nmi to let the
+ * RCU grace-period handling know that the CPU is active.
+ */
+void rcu_nmi_enter(void)
+{
+	struct rcu_dynticks *rdtp = &__get_cpu_var(rcu_dynticks);
+
+	if (rdtp->dynticks & 0x1)
+		return;
+	rdtp->dynticks_nmi++;
+	WARN_ON_RATELIMIT(!(rdtp->dynticks_nmi & 0x1), &rcu_rs);
+	smp_mb(); /* CPUs seeing ++ must see later RCU read-side crit sects */
+}
+
+/**
+ * rcu_nmi_exit - inform RCU of exit from NMI context
+ *
+ * If the CPU was idle with dynamic ticks active, and there is no
+ * irq handler running, this updates rdtp->dynticks_nmi to let the
+ * RCU grace-period handling know that the CPU is no longer active.
+ */
+void rcu_nmi_exit(void)
+{
+	struct rcu_dynticks *rdtp = &__get_cpu_var(rcu_dynticks);
+
+	if (rdtp->dynticks & 0x1)
+		return;
+	smp_mb(); /* CPUs seeing ++ must see prior RCU read-side crit sects */
+	rdtp->dynticks_nmi++;
+	WARN_ON_RATELIMIT(rdtp->dynticks_nmi & 0x1, &rcu_rs);
+}
+
+/**
+ * rcu_irq_enter - inform RCU of entry to hard irq context
+ *
+ * If the CPU was idle with dynamic ticks active, this updates the
+ * rdtp->dynticks to let the RCU handling know that the CPU is active.
+ */
+void rcu_irq_enter(void)
+{
+	struct rcu_dynticks *rdtp = &__get_cpu_var(rcu_dynticks);
+
+	if (rdtp->dynticks_nesting++)
+		return;
+	rdtp->dynticks++;
+	WARN_ON_RATELIMIT(!(rdtp->dynticks & 0x1), &rcu_rs);
+	smp_mb(); /* CPUs seeing ++ must see later RCU read-side crit sects */
+}
+
+/**
+ * rcu_irq_exit - inform RCU of exit from hard irq context
+ *
+ * If the CPU was idle with dynamic ticks active, update the rdp->dynticks
+ * to put let the RCU handling be aware that the CPU is going back to idle
+ * with no ticks.
+ */
+void rcu_irq_exit(void)
+{
+	struct rcu_dynticks *rdtp = &__get_cpu_var(rcu_dynticks);
+
+	if (--rdtp->dynticks_nesting)
+		return;
+	smp_mb(); /* CPUs seeing ++ must see prior RCU read-side crit sects */
+	rdtp->dynticks++;
+	WARN_ON_RATELIMIT(rdtp->dynticks & 0x1, &rcu_rs);
+
+	/* If the interrupt queued a callback, get out of dyntick mode. */
+	if (__get_cpu_var(rcu_data).nxtlist ||
+	    __get_cpu_var(rcu_bh_data).nxtlist)
+		set_need_resched();
+}
+
+/*
+ * Record the specified "completed" value, which is later used to validate
+ * dynticks counter manipulations.  Specify "rsp->completed - 1" to
+ * unconditionally invalidate any future dynticks manipulations (which is
+ * useful at the beginning of a grace period).
+ */
+static void dyntick_record_completed(struct rcu_state *rsp, long comp)
+{
+	rsp->dynticks_completed = comp;
+}
+
+#ifdef CONFIG_SMP
+
+/*
+ * Recall the previously recorded value of the completion for dynticks.
+ */
+static long dyntick_recall_completed(struct rcu_state *rsp)
+{
+	return rsp->dynticks_completed;
+}
+
+/*
+ * Snapshot the specified CPU's dynticks counter so that we can later
+ * credit them with an implicit quiescent state.  Return 1 if this CPU
+ * is already in a quiescent state courtesy of dynticks idle mode.
+ */
+static int dyntick_save_progress_counter(struct rcu_data *rdp)
+{
+	int ret;
+	int snap;
+	int snap_nmi;
+
+	snap = rdp->dynticks->dynticks;
+	snap_nmi = rdp->dynticks->dynticks_nmi;
+	smp_mb();	/* Order sampling of snap with end of grace period. */
+	rdp->dynticks_snap = snap;
+	rdp->dynticks_nmi_snap = snap_nmi;
+	ret = ((snap & 0x1) == 0) && ((snap_nmi & 0x1) == 0);
+	if (ret)
+		rdp->dynticks_fqs++;
+	return ret;
+}
+
+/*
+ * Return true if the specified CPU has passed through a quiescent
+ * state by virtue of being in or having passed through an dynticks
+ * idle state since the last call to dyntick_save_progress_counter()
+ * for this same CPU.
+ */
+static int rcu_implicit_dynticks_qs(struct rcu_data *rdp)
+{
+	long curr;
+	long curr_nmi;
+	long snap;
+	long snap_nmi;
+
+	curr = rdp->dynticks->dynticks;
+	snap = rdp->dynticks_snap;
+	curr_nmi = rdp->dynticks->dynticks_nmi;
+	snap_nmi = rdp->dynticks_nmi_snap;
+	smp_mb(); /* force ordering with cpu entering/leaving dynticks. */
+
+	/*
+	 * If the CPU passed through or entered a dynticks idle phase with
+	 * no active irq/NMI handlers, then we can safely pretend that the CPU
+	 * already acknowledged the request to pass through a quiescent
+	 * state.  Either way, that CPU cannot possibly be in an RCU
+	 * read-side critical section that started before the beginning
+	 * of the current RCU grace period.
+	 */
+	if ((curr != snap || (curr & 0x1) == 0) &&
+	    (curr_nmi != snap_nmi || (curr_nmi & 0x1) == 0)) {
+		rdp->dynticks_fqs++;
+		return 1;
+	}
+
+	/* Go check for the CPU being offline. */
+	return rcu_implicit_offline_qs(rdp);
+}
+
+#endif /* #ifdef CONFIG_SMP */
+
+#else /* #ifdef CONFIG_NO_HZ */
+
+static void dyntick_record_completed(struct rcu_state *rsp, long comp)
+{
+}
+
+#ifdef CONFIG_SMP
+
+/*
+ * If there are no dynticks, then the only way that a CPU can passively
+ * be in a quiescent state is to be offline.  Unlike dynticks idle, which
+ * is a point in time during the prior (already finished) grace period,
+ * an offline CPU is always in a quiescent state, and thus can be
+ * unconditionally applied.  So just return the current value of completed.
+ */
+static long dyntick_recall_completed(struct rcu_state *rsp)
+{
+	return rsp->completed;
+}
+
+static int dyntick_save_progress_counter(struct rcu_data *rdp)
+{
+	return 0;
+}
+
+static int rcu_implicit_dynticks_qs(struct rcu_data *rdp)
+{
+	return rcu_implicit_offline_qs(rdp);
+}
+
+#endif /* #ifdef CONFIG_SMP */
+
+#endif /* #else #ifdef CONFIG_NO_HZ */
+
+#ifdef CONFIG_RCU_CPU_STALL_DETECTOR
+
+static void record_gp_stall_check_time(struct rcu_state *rsp)
+{
+	rsp->gp_start = jiffies;
+	rsp->jiffies_stall = jiffies + RCU_SECONDS_TILL_STALL_CHECK;
+}
+
+static void print_other_cpu_stall(struct rcu_state *rsp)
+{
+	int cpu;
+	long delta;
+	unsigned long flags;
+	struct rcu_node *rnp = rcu_get_root(rsp);
+	struct rcu_node *rnp_cur = rsp->level[NUM_RCU_LVLS - 1];
+	struct rcu_node *rnp_end = &rsp->node[NUM_RCU_NODES];
+
+	/* Only let one CPU complain about others per time interval. */
+
+	spin_lock_irqsave(&rnp->lock, flags);
+	delta = jiffies - rsp->jiffies_stall;
+	if (delta < RCU_STALL_RAT_DELAY || rsp->gpnum == rsp->completed) {
+		spin_unlock_irqrestore(&rnp->lock, flags);
+		return;
+	}
+	rsp->jiffies_stall = jiffies + RCU_SECONDS_TILL_STALL_RECHECK;
+	spin_unlock_irqrestore(&rnp->lock, flags);
+
+	/* OK, time to rat on our buddy... */
+
+	printk(KERN_ERR "INFO: RCU detected CPU stalls:");
+	for (; rnp_cur < rnp_end; rnp_cur++) {
+		if (rnp_cur->qsmask == 0)
+			continue;
+		for (cpu = 0; cpu <= rnp_cur->grphi - rnp_cur->grplo; cpu++)
+			if (rnp_cur->qsmask & (1UL << cpu))
+				printk(" %d", rnp_cur->grplo + cpu);
+	}
+	printk(" (detected by %d, t=%ld jiffies)\n",
+	       smp_processor_id(), (long)(jiffies - rsp->gp_start));
+	force_quiescent_state(rsp, 0);  /* Kick them all. */
+}
+
+static void print_cpu_stall(struct rcu_state *rsp)
+{
+	unsigned long flags;
+	struct rcu_node *rnp = rcu_get_root(rsp);
+
+	printk(KERN_ERR "INFO: RCU detected CPU %d stall (t=%lu jiffies)\n",
+			smp_processor_id(), jiffies - rsp->gp_start);
+	dump_stack();
+	spin_lock_irqsave(&rnp->lock, flags);
+	if ((long)(jiffies - rsp->jiffies_stall) >= 0)
+		rsp->jiffies_stall =
+			jiffies + RCU_SECONDS_TILL_STALL_RECHECK;
+	spin_unlock_irqrestore(&rnp->lock, flags);
+	set_need_resched();  /* kick ourselves to get things going. */
+}
+
+static void check_cpu_stall(struct rcu_state *rsp, struct rcu_data *rdp)
+{
+	long delta;
+	struct rcu_node *rnp;
+
+	delta = jiffies - rsp->jiffies_stall;
+	rnp = rdp->mynode;
+	if ((rnp->qsmask & rdp->grpmask) && delta >= 0) {
+
+		/* We haven't checked in, so go dump stack. */
+		print_cpu_stall(rsp);
+
+	} else if (rsp->gpnum != rsp->completed &&
+		   delta >= RCU_STALL_RAT_DELAY) {
+
+		/* They had two time units to dump stack, so complain. */
+		print_other_cpu_stall(rsp);
+	}
+}
+
+#else /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
+
+static void record_gp_stall_check_time(struct rcu_state *rsp)
+{
+}
+
+static void check_cpu_stall(struct rcu_state *rsp, struct rcu_data *rdp)
+{
+}
+
+#endif /* #else #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
+
+/*
+ * Update CPU-local rcu_data state to record the newly noticed grace period.
+ * This is used both when we started the grace period and when we notice
+ * that someone else started the grace period.
+ */
+static void note_new_gpnum(struct rcu_state *rsp, struct rcu_data *rdp)
+{
+	rdp->qs_pending = 1;
+	rdp->passed_quiesc = 0;
+	rdp->gpnum = rsp->gpnum;
+	rdp->n_rcu_pending_force_qs = rdp->n_rcu_pending +
+				      RCU_JIFFIES_TILL_FORCE_QS;
+}
+
+/*
+ * Did someone else start a new RCU grace period start since we last
+ * checked?  Update local state appropriately if so.  Must be called
+ * on the CPU corresponding to rdp.
+ */
+static int
+check_for_new_grace_period(struct rcu_state *rsp, struct rcu_data *rdp)
+{
+	unsigned long flags;
+	int ret = 0;
+
+	local_irq_save(flags);
+	if (rdp->gpnum != rsp->gpnum) {
+		note_new_gpnum(rsp, rdp);
+		ret = 1;
+	}
+	local_irq_restore(flags);
+	return ret;
+}
+
+/*
+ * Start a new RCU grace period if warranted, re-initializing the hierarchy
+ * in preparation for detecting the next grace period.  The caller must hold
+ * the root node's ->lock, which is released before return.  Hard irqs must
+ * be disabled.
+ */
+static void
+rcu_start_gp(struct rcu_state *rsp, unsigned long flags)
+	__releases(rcu_get_root(rsp)->lock)
+{
+	struct rcu_data *rdp = rsp->rda[smp_processor_id()];
+	struct rcu_node *rnp = rcu_get_root(rsp);
+	struct rcu_node *rnp_cur;
+	struct rcu_node *rnp_end;
+
+	if (!cpu_needs_another_gp(rsp, rdp)) {
+		spin_unlock_irqrestore(&rnp->lock, flags);
+		return;
+	}
+
+	/* Advance to a new grace period and initialize state. */
+	rsp->gpnum++;
+	rsp->signaled = RCU_GP_INIT; /* Hold off force_quiescent_state. */
+	rsp->jiffies_force_qs = jiffies + RCU_JIFFIES_TILL_FORCE_QS;
+	rdp->n_rcu_pending_force_qs = rdp->n_rcu_pending +
+				      RCU_JIFFIES_TILL_FORCE_QS;
+	record_gp_stall_check_time(rsp);
+	dyntick_record_completed(rsp, rsp->completed - 1);
+	note_new_gpnum(rsp, rdp);
+
+	/*
+	 * Because we are first, we know that all our callbacks will
+	 * be covered by this upcoming grace period, even the ones
+	 * that were registered arbitrarily recently.
+	 */
+	rdp->nxttail[RCU_NEXT_READY_TAIL] = rdp->nxttail[RCU_NEXT_TAIL];
+	rdp->nxttail[RCU_WAIT_TAIL] = rdp->nxttail[RCU_NEXT_TAIL];
+
+	/* Special-case the common single-level case. */
+	if (NUM_RCU_NODES == 1) {
+		rnp->qsmask = rnp->qsmaskinit;
+		rsp->signaled = RCU_SIGNAL_INIT; /* force_quiescent_state OK. */
+		spin_unlock_irqrestore(&rnp->lock, flags);
+		return;
+	}
+
+	spin_unlock(&rnp->lock);  /* leave irqs disabled. */
+
+
+	/* Exclude any concurrent CPU-hotplug operations. */
+	spin_lock(&rsp->onofflock);  /* irqs already disabled. */
+
+	/*
+	 * Set the quiescent-state-needed bits in all the non-leaf RCU
+	 * nodes for all currently online CPUs.  This operation relies
+	 * on the layout of the hierarchy within the rsp->node[] array.
+	 * Note that other CPUs will access only the leaves of the
+	 * hierarchy, which still indicate that no grace period is in
+	 * progress.  In addition, we have excluded CPU-hotplug operations.
+	 *
+	 * We therefore do not need to hold any locks.  Any required
+	 * memory barriers will be supplied by the locks guarding the
+	 * leaf rcu_nodes in the hierarchy.
+	 */
+
+	rnp_end = rsp->level[NUM_RCU_LVLS - 1];
+	for (rnp_cur = &rsp->node[0]; rnp_cur < rnp_end; rnp_cur++)
+		rnp_cur->qsmask = rnp_cur->qsmaskinit;
+
+	/*
+	 * Now set up the leaf nodes.  Here we must be careful.  First,
+	 * we need to hold the lock in order to exclude other CPUs, which
+	 * might be contending for the leaf nodes' locks.  Second, as
+	 * soon as we initialize a given leaf node, its CPUs might run
+	 * up the rest of the hierarchy.  We must therefore acquire locks
+	 * for each node that we touch during this stage.  (But we still
+	 * are excluding CPU-hotplug operations.)
+	 *
+	 * Note that the grace period cannot complete until we finish
+	 * the initialization process, as there will be at least one
+	 * qsmask bit set in the root node until that time, namely the
+	 * one corresponding to this CPU.
+	 */
+	rnp_end = &rsp->node[NUM_RCU_NODES];
+	rnp_cur = rsp->level[NUM_RCU_LVLS - 1];
+	for (; rnp_cur < rnp_end; rnp_cur++) {
+		spin_lock(&rnp_cur->lock);	/* irqs already disabled. */
+		rnp_cur->qsmask = rnp_cur->qsmaskinit;
+		spin_unlock(&rnp_cur->lock);	/* irqs already disabled. */
+	}
+
+	rsp->signaled = RCU_SIGNAL_INIT; /* force_quiescent_state now OK. */
+	spin_unlock_irqrestore(&rsp->onofflock, flags);
+}
+
+/*
+ * Advance this CPU's callbacks, but only if the current grace period
+ * has ended.  This may be called only from the CPU to whom the rdp
+ * belongs.
+ */
+static void
+rcu_process_gp_end(struct rcu_state *rsp, struct rcu_data *rdp)
+{
+	long completed_snap;
+	unsigned long flags;
+
+	local_irq_save(flags);
+	completed_snap = ACCESS_ONCE(rsp->completed);  /* outside of lock. */
+
+	/* Did another grace period end? */
+	if (rdp->completed != completed_snap) {
+
+		/* Advance callbacks.  No harm if list empty. */
+		rdp->nxttail[RCU_DONE_TAIL] = rdp->nxttail[RCU_WAIT_TAIL];
+		rdp->nxttail[RCU_WAIT_TAIL] = rdp->nxttail[RCU_NEXT_READY_TAIL];
+		rdp->nxttail[RCU_NEXT_READY_TAIL] = rdp->nxttail[RCU_NEXT_TAIL];
+
+		/* Remember that we saw this grace-period completion. */
+		rdp->completed = completed_snap;
+	}
+	local_irq_restore(flags);
+}
+
+/*
+ * Similar to cpu_quiet(), for which it is a helper function.  Allows
+ * a group of CPUs to be quieted at one go, though all the CPUs in the
+ * group must be represented by the same leaf rcu_node structure.
+ * That structure's lock must be held upon entry, and it is released
+ * before return.
+ */
+static void
+cpu_quiet_msk(unsigned long mask, struct rcu_state *rsp, struct rcu_node *rnp,
+	      unsigned long flags)
+	__releases(rnp->lock)
+{
+	/* Walk up the rcu_node hierarchy. */
+	for (;;) {
+		if (!(rnp->qsmask & mask)) {
+
+			/* Our bit has already been cleared, so done. */
+			spin_unlock_irqrestore(&rnp->lock, flags);
+			return;
+		}
+		rnp->qsmask &= ~mask;
+		if (rnp->qsmask != 0) {
+
+			/* Other bits still set at this level, so done. */
+			spin_unlock_irqrestore(&rnp->lock, flags);
+			return;
+		}
+		mask = rnp->grpmask;
+		if (rnp->parent == NULL) {
+
+			/* No more levels.  Exit loop holding root lock. */
+
+			break;
+		}
+		spin_unlock_irqrestore(&rnp->lock, flags);
+		rnp = rnp->parent;
+		spin_lock_irqsave(&rnp->lock, flags);
+	}
+
+	/*
+	 * Get here if we are the last CPU to pass through a quiescent
+	 * state for this grace period.  Clean up and let rcu_start_gp()
+	 * start up the next grace period if one is needed.  Note that
+	 * we still hold rnp->lock, as required by rcu_start_gp(), which
+	 * will release it.
+	 */
+	rsp->completed = rsp->gpnum;
+	rcu_process_gp_end(rsp, rsp->rda[smp_processor_id()]);
+	rcu_start_gp(rsp, flags);  /* releases rnp->lock. */
+}
+
+/*
+ * Record a quiescent state for the specified CPU, which must either be
+ * the current CPU or an offline CPU.  The lastcomp argument is used to
+ * make sure we are still in the grace period of interest.  We don't want
+ * to end the current grace period based on quiescent states detected in
+ * an earlier grace period!
+ */
+static void
+cpu_quiet(int cpu, struct rcu_state *rsp, struct rcu_data *rdp, long lastcomp)
+{
+	unsigned long flags;
+	unsigned long mask;
+	struct rcu_node *rnp;
+
+	rnp = rdp->mynode;
+	spin_lock_irqsave(&rnp->lock, flags);
+	if (lastcomp != ACCESS_ONCE(rsp->completed)) {
+
+		/*
+		 * Someone beat us to it for this grace period, so leave.
+		 * The race with GP start is resolved by the fact that we
+		 * hold the leaf rcu_node lock, so that the per-CPU bits
+		 * cannot yet be initialized -- so we would simply find our
+		 * CPU's bit already cleared in cpu_quiet_msk() if this race
+		 * occurred.
+		 */
+		rdp->passed_quiesc = 0;	/* try again later! */
+		spin_unlock_irqrestore(&rnp->lock, flags);
+		return;
+	}
+	mask = rdp->grpmask;
+	if ((rnp->qsmask & mask) == 0) {
+		spin_unlock_irqrestore(&rnp->lock, flags);
+	} else {
+		rdp->qs_pending = 0;
+
+		/*
+		 * This GP can't end until cpu checks in, so all of our
+		 * callbacks can be processed during the next GP.
+		 */
+		rdp = rsp->rda[smp_processor_id()];
+		rdp->nxttail[RCU_NEXT_READY_TAIL] = rdp->nxttail[RCU_NEXT_TAIL];
+
+		cpu_quiet_msk(mask, rsp, rnp, flags); /* releases rnp->lock */
+	}
+}
+
+/*
+ * Check to see if there is a new grace period of which this CPU
+ * is not yet aware, and if so, set up local rcu_data state for it.
+ * Otherwise, see if this CPU has just passed through its first
+ * quiescent state for this grace period, and record that fact if so.
+ */
+static void
+rcu_check_quiescent_state(struct rcu_state *rsp, struct rcu_data *rdp)
+{
+	/* If there is now a new grace period, record and return. */
+	if (check_for_new_grace_period(rsp, rdp))
+		return;
+
+	/*
+	 * Does this CPU still need to do its part for current grace period?
+	 * If no, return and let the other CPUs do their part as well.
+	 */
+	if (!rdp->qs_pending)
+		return;
+
+	/*
+	 * Was there a quiescent state since the beginning of the grace
+	 * period? If no, then exit and wait for the next call.
+	 */
+	if (!rdp->passed_quiesc)
+		return;
+
+	/* Tell RCU we are done (but cpu_quiet() will be the judge of that). */
+	cpu_quiet(rdp->cpu, rsp, rdp, rdp->passed_quiesc_completed);
+}
+
+#ifdef CONFIG_HOTPLUG_CPU
+
+/*
+ * Remove the outgoing CPU from the bitmasks in the rcu_node hierarchy
+ * and move all callbacks from the outgoing CPU to the current one.
+ */
+static void __rcu_offline_cpu(int cpu, struct rcu_state *rsp)
+{
+	int i;
+	unsigned long flags;
+	long lastcomp;
+	unsigned long mask;
+	struct rcu_data *rdp = rsp->rda[cpu];
+	struct rcu_data *rdp_me;
+	struct rcu_node *rnp;
+
+	/* Exclude any attempts to start a new grace period. */
+	spin_lock_irqsave(&rsp->onofflock, flags);
+
+	/* Remove the outgoing CPU from the masks in the rcu_node hierarchy. */
+	rnp = rdp->mynode;
+	mask = rdp->grpmask;	/* rnp->grplo is constant. */
+	do {
+		spin_lock(&rnp->lock);		/* irqs already disabled. */
+		rnp->qsmaskinit &= ~mask;
+		if (rnp->qsmaskinit != 0) {
+			spin_unlock(&rnp->lock); /* irqs already disabled. */
+			break;
+		}
+		mask = rnp->grpmask;
+		spin_unlock(&rnp->lock);	/* irqs already disabled. */
+		rnp = rnp->parent;
+	} while (rnp != NULL);
+	lastcomp = rsp->completed;
+
+	spin_unlock(&rsp->onofflock);		/* irqs remain disabled. */
+
+	/* Being offline is a quiescent state, so go record it. */
+	cpu_quiet(cpu, rsp, rdp, lastcomp);
+
+	/*
+	 * Move callbacks from the outgoing CPU to the running CPU.
+	 * Note that the outgoing CPU is now quiscent, so it is now
+	 * (uncharacteristically) safe to access it rcu_data structure.
+	 * Note also that we must carefully retain the order of the
+	 * outgoing CPU's callbacks in order for rcu_barrier() to work
+	 * correctly.  Finally, note that we start all the callbacks
+	 * afresh, even those that have passed through a grace period
+	 * and are therefore ready to invoke.  The theory is that hotplug
+	 * events are rare, and that if they are frequent enough to
+	 * indefinitely delay callbacks, you have far worse things to
+	 * be worrying about.
+	 */
+	rdp_me = rsp->rda[smp_processor_id()];
+	if (rdp->nxtlist != NULL) {
+		*rdp_me->nxttail[RCU_NEXT_TAIL] = rdp->nxtlist;
+		rdp_me->nxttail[RCU_NEXT_TAIL] = rdp->nxttail[RCU_NEXT_TAIL];
+		rdp->nxtlist = NULL;
+		for (i = 0; i < RCU_NEXT_SIZE; i++)
+			rdp->nxttail[i] = &rdp->nxtlist;
+		rdp_me->qlen += rdp->qlen;
+		rdp->qlen = 0;
+	}
+	local_irq_restore(flags);
+}
+
+/*
+ * Remove the specified CPU from the RCU hierarchy and move any pending
+ * callbacks that it might have to the current CPU.  This code assumes
+ * that at least one CPU in the system will remain running at all times.
+ * Any attempt to offline -all- CPUs is likely to strand RCU callbacks.
+ */
+static void rcu_offline_cpu(int cpu)
+{
+	__rcu_offline_cpu(cpu, &rcu_state);
+	__rcu_offline_cpu(cpu, &rcu_bh_state);
+}
+
+#else /* #ifdef CONFIG_HOTPLUG_CPU */
+
+static void rcu_offline_cpu(int cpu)
+{
+}
+
+#endif /* #else #ifdef CONFIG_HOTPLUG_CPU */
+
+/*
+ * Invoke any RCU callbacks that have made it to the end of their grace
+ * period.  Thottle as specified by rdp->blimit.
+ */
+static void rcu_do_batch(struct rcu_data *rdp)
+{
+	unsigned long flags;
+	struct rcu_head *next, *list, **tail;
+	int count;
+
+	/* If no callbacks are ready, just return.*/
+	if (!cpu_has_callbacks_ready_to_invoke(rdp))
+		return;
+
+	/*
+	 * Extract the list of ready callbacks, disabling to prevent
+	 * races with call_rcu() from interrupt handlers.
+	 */
+	local_irq_save(flags);
+	list = rdp->nxtlist;
+	rdp->nxtlist = *rdp->nxttail[RCU_DONE_TAIL];
+	*rdp->nxttail[RCU_DONE_TAIL] = NULL;
+	tail = rdp->nxttail[RCU_DONE_TAIL];
+	for (count = RCU_NEXT_SIZE - 1; count >= 0; count--)
+		if (rdp->nxttail[count] == rdp->nxttail[RCU_DONE_TAIL])
+			rdp->nxttail[count] = &rdp->nxtlist;
+	local_irq_restore(flags);
+
+	/* Invoke callbacks. */
+	count = 0;
+	while (list) {
+		next = list->next;
+		prefetch(next);
+		list->func(list);
+		list = next;
+		if (++count >= rdp->blimit)
+			break;
+	}
+
+	local_irq_save(flags);
+
+	/* Update count, and requeue any remaining callbacks. */
+	rdp->qlen -= count;
+	if (list != NULL) {
+		*tail = rdp->nxtlist;
+		rdp->nxtlist = list;
+		for (count = 0; count < RCU_NEXT_SIZE; count++)
+			if (&rdp->nxtlist == rdp->nxttail[count])
+				rdp->nxttail[count] = tail;
+			else
+				break;
+	}
+
+	/* Reinstate batch limit if we have worked down the excess. */
+	if (rdp->blimit == LONG_MAX && rdp->qlen <= qlowmark)
+		rdp->blimit = blimit;
+
+	local_irq_restore(flags);
+
+	/* Re-raise the RCU softirq if there are callbacks remaining. */
+	if (cpu_has_callbacks_ready_to_invoke(rdp))
+		raise_softirq(RCU_SOFTIRQ);
+}
+
+/*
+ * Check to see if this CPU is in a non-context-switch quiescent state
+ * (user mode or idle loop for rcu, non-softirq execution for rcu_bh).
+ * Also schedule the RCU softirq handler.
+ *
+ * This function must be called with hardirqs disabled.  It is normally
+ * invoked from the scheduling-clock interrupt.  If rcu_pending returns
+ * false, there is no point in invoking rcu_check_callbacks().
+ */
+void rcu_check_callbacks(int cpu, int user)
+{
+	if (user ||
+	    (idle_cpu(cpu) && !in_softirq() &&
+				hardirq_count() <= (1 << HARDIRQ_SHIFT))) {
+
+		/*
+		 * Get here if this CPU took its interrupt from user
+		 * mode or from the idle loop, and if this is not a
+		 * nested interrupt.  In this case, the CPU is in
+		 * a quiescent state, so count it.
+		 *
+		 * No memory barrier is required here because both
+		 * rcu_qsctr_inc() and rcu_bh_qsctr_inc() reference
+		 * only CPU-local variables that other CPUs neither
+		 * access nor modify, at least not while the corresponding
+		 * CPU is online.
+		 */
+
+		rcu_qsctr_inc(cpu);
+		rcu_bh_qsctr_inc(cpu);
+
+	} else if (!in_softirq()) {
+
+		/*
+		 * Get here if this CPU did not take its interrupt from
+		 * softirq, in other words, if it is not interrupting
+		 * a rcu_bh read-side critical section.  This is an _bh
+		 * critical section, so count it.
+		 */
+
+		rcu_bh_qsctr_inc(cpu);
+	}
+	raise_softirq(RCU_SOFTIRQ);
+}
+
+#ifdef CONFIG_SMP
+
+/*
+ * 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).
+ */
+static int rcu_process_dyntick(struct rcu_state *rsp, long lastcomp,
+			       int (*f)(struct rcu_data *))
+{
+	unsigned long bit;
+	int cpu;
+	unsigned long flags;
+	unsigned long mask;
+	struct rcu_node *rnp_cur = rsp->level[NUM_RCU_LVLS - 1];
+	struct rcu_node *rnp_end = &rsp->node[NUM_RCU_NODES];
+
+	for (; rnp_cur < rnp_end; rnp_cur++) {
+		mask = 0;
+		spin_lock_irqsave(&rnp_cur->lock, flags);
+		if (rsp->completed != lastcomp) {
+			spin_unlock_irqrestore(&rnp_cur->lock, flags);
+			return 1;
+		}
+		if (rnp_cur->qsmask == 0) {
+			spin_unlock_irqrestore(&rnp_cur->lock, flags);
+			continue;
+		}
+		cpu = rnp_cur->grplo;
+		bit = 1;
+		for (; cpu <= rnp_cur->grphi; cpu++, bit <<= 1) {
+			if ((rnp_cur->qsmask & bit) != 0 && f(rsp->rda[cpu]))
+				mask |= bit;
+		}
+		if (mask != 0 && rsp->completed == lastcomp) {
+
+			/* cpu_quiet_msk() releases rnp_cur->lock. */
+			cpu_quiet_msk(mask, rsp, rnp_cur, flags);
+			continue;
+		}
+		spin_unlock_irqrestore(&rnp_cur->lock, flags);
+	}
+	return 0;
+}
+
+/*
+ * Force quiescent states on reluctant CPUs, and also detect which
+ * CPUs are in dyntick-idle mode.
+ */
+static void force_quiescent_state(struct rcu_state *rsp, int relaxed)
+{
+	unsigned long flags;
+	long lastcomp;
+	struct rcu_data *rdp = rsp->rda[smp_processor_id()];
+	struct rcu_node *rnp = rcu_get_root(rsp);
+	u8 signaled;
+
+	if (ACCESS_ONCE(rsp->completed) == ACCESS_ONCE(rsp->gpnum))
+		return;  /* No grace period in progress, nothing to force. */
+	if (!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 &&
+	    (rdp->n_rcu_pending_force_qs - rdp->n_rcu_pending) >= 0)
+		goto unlock_ret; /* no emergency and done recently. */
+	rsp->n_force_qs++;
+	spin_lock(&rnp->lock);
+	lastcomp = rsp->completed;
+	signaled = rsp->signaled;
+	rsp->jiffies_force_qs = jiffies + RCU_JIFFIES_TILL_FORCE_QS;
+	rdp->n_rcu_pending_force_qs = rdp->n_rcu_pending +
+				      RCU_JIFFIES_TILL_FORCE_QS;
+	if (lastcomp == rsp->gpnum) {
+		rsp->n_force_qs_ngp++;
+		spin_unlock(&rnp->lock);
+		goto unlock_ret;  /* no GP in progress, time updated. */
+	}
+	spin_unlock(&rnp->lock);
+	switch (signaled) {
+	case RCU_GP_INIT:
+
+		break; /* grace period still initializing, ignore. */
+
+	case RCU_SAVE_DYNTICK:
+
+		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;
+
+		/* Update state, record completion counter. */
+		spin_lock(&rnp->lock);
+		if (lastcomp == rsp->completed) {
+			rsp->signaled = RCU_FORCE_QS;
+			dyntick_record_completed(rsp, lastcomp);
+		}
+		spin_unlock(&rnp->lock);
+		break;
+
+	case RCU_FORCE_QS:
+
+		/* Check dyntick-idle state, send IPI to laggarts. */
+		if (rcu_process_dyntick(rsp, dyntick_recall_completed(rsp),
+					rcu_implicit_dynticks_qs))
+			goto unlock_ret;
+
+		/* Leave state in case more forcing is required. */
+
+		break;
+	}
+unlock_ret:
+	spin_unlock_irqrestore(&rsp->fqslock, flags);
+}
+
+#else /* #ifdef CONFIG_SMP */
+
+static void force_quiescent_state(struct rcu_state *rsp, int relaxed)
+{
+	set_need_resched();
+}
+
+#endif /* #else #ifdef CONFIG_SMP */
+
+/*
+ * This does the RCU processing work from softirq context for the
+ * specified rcu_state and rcu_data structures.  This may be called
+ * only from the CPU to whom the rdp belongs.
+ */
+static void
+__rcu_process_callbacks(struct rcu_state *rsp, struct rcu_data *rdp)
+{
+	unsigned long flags;
+
+	/*
+	 * 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 ||
+	    (rdp->n_rcu_pending_force_qs - rdp->n_rcu_pending) < 0)
+		force_quiescent_state(rsp, 1);
+
+	/*
+	 * Advance callbacks in response to end of earlier grace
+	 * period that some other CPU ended.
+	 */
+	rcu_process_gp_end(rsp, rdp);
+
+	/* Update RCU state based on any recent quiescent states. */
+	rcu_check_quiescent_state(rsp, 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);
+		rcu_start_gp(rsp, flags);  /* releases above lock */
+	}
+
+	/* If there are callbacks ready, invoke them. */
+	rcu_do_batch(rdp);
+}
+
+/*
+ * Do softirq processing for the current CPU.
+ */
+static void rcu_process_callbacks(struct softirq_action *unused)
+{
+	/*
+	 * Memory references from any prior RCU read-side critical sections
+	 * executed by the interrupted code must be seen before any RCU
+	 * grace-period manipulations below.
+	 */
+	smp_mb(); /* See above block comment. */
+
+	__rcu_process_callbacks(&rcu_state, &__get_cpu_var(rcu_data));
+	__rcu_process_callbacks(&rcu_bh_state, &__get_cpu_var(rcu_bh_data));
+
+	/*
+	 * Memory references from any later RCU read-side critical sections
+	 * executed by the interrupted code must be seen after any RCU
+	 * grace-period manipulations above.
+	 */
+	smp_mb(); /* See above block comment. */
+}
+
+static void
+__call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu),
+	   struct rcu_state *rsp)
+{
+	unsigned long flags;
+	struct rcu_data *rdp;
+
+	head->func = func;
+	head->next = NULL;
+
+	smp_mb(); /* Ensure RCU update seen before callback registry. */
+
+	/*
+	 * Opportunistically note grace-period endings and beginnings.
+	 * Note that we might see a beginning right after we see an
+	 * end, but never vice versa, since this CPU has to pass through
+	 * a quiescent state betweentimes.
+	 */
+	local_irq_save(flags);
+	rdp = rsp->rda[smp_processor_id()];
+	rcu_process_gp_end(rsp, rdp);
+	check_for_new_grace_period(rsp, rdp);
+
+	/* Add the callback to our list. */
+	*rdp->nxttail[RCU_NEXT_TAIL] = head;
+	rdp->nxttail[RCU_NEXT_TAIL] = &head->next;
+
+	/* Start a new grace period if one not already started. */
+	if (ACCESS_ONCE(rsp->completed) == ACCESS_ONCE(rsp->gpnum)) {
+		unsigned long nestflag;
+		struct rcu_node *rnp_root = rcu_get_root(rsp);
+
+		spin_lock_irqsave(&rnp_root->lock, nestflag);
+		rcu_start_gp(rsp, nestflag);  /* releases rnp_root->lock. */
+	}
+
+	/* Force the grace period if too many callbacks or too long waiting. */
+	if (unlikely(++rdp->qlen > qhimark)) {
+		rdp->blimit = LONG_MAX;
+		force_quiescent_state(rsp, 0);
+	} else if ((long)(ACCESS_ONCE(rsp->jiffies_force_qs) - jiffies) < 0 ||
+		   (rdp->n_rcu_pending_force_qs - rdp->n_rcu_pending) < 0)
+		force_quiescent_state(rsp, 1);
+	local_irq_restore(flags);
+}
+
+/*
+ * Queue an RCU callback for invocation after a grace period.
+ */
+void call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu))
+{
+	__call_rcu(head, func, &rcu_state);
+}
+EXPORT_SYMBOL_GPL(call_rcu);
+
+/*
+ * Queue an RCU for invocation after a quicker grace period.
+ */
+void call_rcu_bh(struct rcu_head *head, void (*func)(struct rcu_head *rcu))
+{
+	__call_rcu(head, func, &rcu_bh_state);
+}
+EXPORT_SYMBOL_GPL(call_rcu_bh);
+
+/*
+ * Check to see if there is any immediate RCU-related work to be done
+ * by the current CPU, for the specified type of RCU, returning 1 if so.
+ * The checks are in order of increasing expense: checks that can be
+ * carried out against CPU-local state are performed first.  However,
+ * we must check for CPU stalls first, else we might not get a chance.
+ */
+static int __rcu_pending(struct rcu_state *rsp, struct rcu_data *rdp)
+{
+	rdp->n_rcu_pending++;
+
+	/* Check for CPU stalls, if enabled. */
+	check_cpu_stall(rsp, rdp);
+
+	/* Is the RCU core waiting for a quiescent state from this CPU? */
+	if (rdp->qs_pending)
+		return 1;
+
+	/* Does this CPU have callbacks ready to invoke? */
+	if (cpu_has_callbacks_ready_to_invoke(rdp))
+		return 1;
+
+	/* Has RCU gone idle with this CPU needing another grace period? */
+	if (cpu_needs_another_gp(rsp, rdp))
+		return 1;
+
+	/* Has another RCU grace period completed?  */
+	if (ACCESS_ONCE(rsp->completed) != rdp->completed) /* outside of lock */
+		return 1;
+
+	/* Has a new RCU grace period started? */
+	if (ACCESS_ONCE(rsp->gpnum) != rdp->gpnum) /* outside of lock */
+		return 1;
+
+	/* Has an RCU GP gone long enough to send resched IPIs &c? */
+	if (ACCESS_ONCE(rsp->completed) != ACCESS_ONCE(rsp->gpnum) &&
+	    ((long)(ACCESS_ONCE(rsp->jiffies_force_qs) - jiffies) < 0 ||
+	     (rdp->n_rcu_pending_force_qs - rdp->n_rcu_pending) < 0))
+		return 1;
+
+	/* nothing to do */
+	return 0;
+}
+
+/*
+ * Check to see if there is any immediate RCU-related work to be done
+ * by the current CPU, returning 1 if so.  This function is part of the
+ * RCU implementation; it is -not- an exported member of the RCU API.
+ */
+int rcu_pending(int cpu)
+{
+	return __rcu_pending(&rcu_state, &per_cpu(rcu_data, cpu)) ||
+	       __rcu_pending(&rcu_bh_state, &per_cpu(rcu_bh_data, 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.
+ */
+int rcu_needs_cpu(int cpu)
+{
+	/* RCU callbacks either ready or pending? */
+	return per_cpu(rcu_data, cpu).nxtlist ||
+	       per_cpu(rcu_bh_data, cpu).nxtlist;
+}
+
+/*
+ * Initialize a CPU's per-CPU RCU data.  We take this "scorched earth"
+ * approach so that we don't have to worry about how long the CPU has
+ * been gone, or whether it ever was online previously.  We do trust the
+ * ->mynode field, as it is constant for a given struct rcu_data and
+ * initialized during early boot.
+ *
+ * Note that only one online or offline event can be happening at a given
+ * time.  Note also that we can accept some slop in the rsp->completed
+ * access due to the fact that this CPU cannot possibly have any RCU
+ * callbacks in flight yet.
+ */
+static void
+rcu_init_percpu_data(int cpu, struct rcu_state *rsp)
+{
+	unsigned long flags;
+	int i;
+	long lastcomp;
+	unsigned long mask;
+	struct rcu_data *rdp = rsp->rda[cpu];
+	struct rcu_node *rnp = rcu_get_root(rsp);
+
+	/* Set up local state, ensuring consistent view of global state. */
+	spin_lock_irqsave(&rnp->lock, flags);
+	lastcomp = rsp->completed;
+	rdp->completed = lastcomp;
+	rdp->gpnum = lastcomp;
+	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. */
+	rdp->passed_quiesc_completed = lastcomp - 1;
+	rdp->grpmask = 1UL << (cpu - rdp->mynode->grplo);
+	rdp->nxtlist = NULL;
+	for (i = 0; i < RCU_NEXT_SIZE; i++)
+		rdp->nxttail[i] = &rdp->nxtlist;
+	rdp->qlen = 0;
+	rdp->blimit = blimit;
+#ifdef CONFIG_NO_HZ
+	rdp->dynticks = &per_cpu(rcu_dynticks, cpu);
+#endif /* #ifdef CONFIG_NO_HZ */
+	rdp->cpu = cpu;
+	spin_unlock(&rnp->lock);		/* irqs remain disabled. */
+
+	/*
+	 * A new grace period might start here.  If so, we won't be part
+	 * of it, but that is OK, as we are currently in a quiescent state.
+	 */
+
+	/* Exclude any attempts to start a new GP on large systems. */
+	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. */
+		rnp->qsmaskinit |= mask;
+		mask = rnp->grpmask;
+		spin_unlock(&rnp->lock); /* irqs already disabled. */
+		rnp = rnp->parent;
+	} while (rnp != NULL && !(rnp->qsmaskinit & mask));
+
+	spin_unlock(&rsp->onofflock);		/* irqs remain disabled. */
+
+	/*
+	 * A new grace period might start here.  If so, we will be part of
+	 * it, and its gpnum will be greater than ours, so we will
+	 * participate.  It is also possible for the gpnum to have been
+	 * incremented before this function was called, and the bitmasks
+	 * to not be filled out until now, in which case we will also
+	 * participate due to our gpnum being behind.
+	 */
+
+	/* Since it is coming online, the CPU is in a quiescent state. */
+	cpu_quiet(cpu, rsp, rdp, lastcomp);
+	local_irq_restore(flags);
+}
+
+static void __cpuinit rcu_online_cpu(int cpu)
+{
+	rcu_init_percpu_data(cpu, &rcu_state);
+	rcu_init_percpu_data(cpu, &rcu_bh_state);
+	open_softirq(RCU_SOFTIRQ, rcu_process_callbacks);
+}
+
+/*
+ * Handle CPU online/offline notifcation events.
+ */
+static int __cpuinit rcu_cpu_notify(struct notifier_block *self,
+				unsigned long action, void *hcpu)
+{
+	long cpu = (long)hcpu;
+
+	switch (action) {
+	case CPU_UP_PREPARE:
+	case CPU_UP_PREPARE_FROZEN:
+		rcu_online_cpu(cpu);
+		break;
+	case CPU_DEAD:
+	case CPU_DEAD_FROZEN:
+	case CPU_UP_CANCELED:
+	case CPU_UP_CANCELED_FROZEN:
+		rcu_offline_cpu(cpu);
+		break;
+	default:
+		break;
+	}
+	return NOTIFY_OK;
+}
+
+/*
+ * Compute the per-level fanout, either using the exact fanout specified
+ * or balancing the tree, depending on CONFIG_RCU_FANOUT_EXACT.
+ */
+#ifdef CONFIG_RCU_FANOUT_EXACT
+static void __init rcu_init_levelspread(struct rcu_state *rsp)
+{
+	int i;
+
+	for (i = NUM_RCU_LVLS - 1; i >= 0; i--)
+		rsp->levelspread[i] = CONFIG_RCU_FANOUT;
+}
+#else /* #ifdef CONFIG_RCU_FANOUT_EXACT */
+static void __init rcu_init_levelspread(struct rcu_state *rsp)
+{
+	int ccur;
+	int cprv;
+	int i;
+
+	cprv = NR_CPUS;
+	for (i = NUM_RCU_LVLS - 1; i >= 0; i--) {
+		ccur = rsp->levelcnt[i];
+		rsp->levelspread[i] = (cprv + ccur - 1) / ccur;
+		cprv = ccur;
+	}
+}
+#endif /* #else #ifdef CONFIG_RCU_FANOUT_EXACT */
+
+/*
+ * Helper function for rcu_init() that initializes one rcu_state structure.
+ */
+static void __init rcu_init_one(struct rcu_state *rsp)
+{
+	int cpustride = 1;
+	int i;
+	int j;
+	struct rcu_node *rnp;
+
+	/* Initialize the level-tracking arrays. */
+
+	for (i = 1; i < NUM_RCU_LVLS; i++)
+		rsp->level[i] = rsp->level[i - 1] + rsp->levelcnt[i - 1];
+	rcu_init_levelspread(rsp);
+
+	/* Initialize the elements themselves, starting from the leaves. */
+
+	for (i = NUM_RCU_LVLS - 1; i >= 0; i--) {
+		cpustride *= rsp->levelspread[i];
+		rnp = rsp->level[i];
+		for (j = 0; j < rsp->levelcnt[i]; j++, rnp++) {
+			spin_lock_init(&rnp->lock);
+			rnp->qsmask = 0;
+			rnp->qsmaskinit = 0;
+			rnp->grplo = j * cpustride;
+			rnp->grphi = (j + 1) * cpustride - 1;
+			if (rnp->grphi >= NR_CPUS)
+				rnp->grphi = NR_CPUS - 1;
+			if (i == 0) {
+				rnp->grpnum = 0;
+				rnp->grpmask = 0;
+				rnp->parent = NULL;
+			} else {
+				rnp->grpnum = j % rsp->levelspread[i - 1];
+				rnp->grpmask = 1UL << rnp->grpnum;
+				rnp->parent = rsp->level[i - 1] +
+					      j / rsp->levelspread[i - 1];
+			}
+			rnp->level = i;
+		}
+	}
+}
+
+/*
+ * Helper macro for __rcu_init().  To be used nowhere else!
+ * Assigns leaf node pointers into each CPU's rcu_data structure.
+ */
+#define RCU_DATA_PTR_INIT(rsp, rcu_data) \
+do { \
+	rnp = (rsp)->level[NUM_RCU_LVLS - 1]; \
+	j = 0; \
+	for_each_possible_cpu(i) { \
+		if (i > rnp[j].grphi) \
+			j++; \
+		per_cpu(rcu_data, i).mynode = &rnp[j]; \
+		(rsp)->rda[i] = &per_cpu(rcu_data, i); \
+	} \
+} while (0)
+
+static struct notifier_block __cpuinitdata rcu_nb = {
+	.notifier_call	= rcu_cpu_notify,
+};
+
+void __init __rcu_init(void)
+{
+	int i;			/* All used by RCU_DATA_PTR_INIT(). */
+	int j;
+	struct rcu_node *rnp;
+
+	printk(KERN_WARNING "Experimental hierarchical RCU implementation.\n");
+#ifdef CONFIG_RCU_CPU_STALL_DETECTOR
+	printk(KERN_INFO "RCU-based detection of stalled CPUs is enabled.\n");
+#endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
+	rcu_init_one(&rcu_state);
+	RCU_DATA_PTR_INIT(&rcu_state, rcu_data);
+	rcu_init_one(&rcu_bh_state);
+	RCU_DATA_PTR_INIT(&rcu_bh_state, rcu_bh_data);
+
+	for_each_online_cpu(i)
+		rcu_cpu_notify(&rcu_nb, CPU_UP_PREPARE, (void *)(long)i);
+	/* Register notifier for non-boot CPUs */
+	register_cpu_notifier(&rcu_nb);
+	printk(KERN_WARNING "Experimental hierarchical RCU init done.\n");
+}
+
+module_param(blimit, int, 0);
+module_param(qhimark, int, 0);
+module_param(qlowmark, int, 0);
diff --git a/kernel/rcutree_trace.c b/kernel/rcutree_trace.c
new file mode 100644
index 000000000000..d6db3e837826
--- /dev/null
+++ b/kernel/rcutree_trace.c
@@ -0,0 +1,271 @@
+/*
+ * Read-Copy Update tracing for classic implementation
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that 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., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ *
+ * Copyright IBM Corporation, 2008
+ *
+ * Papers:  http://www.rdrop.com/users/paulmck/RCU
+ *
+ * For detailed explanation of Read-Copy Update mechanism see -
+ * 		Documentation/RCU
+ *
+ */
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/spinlock.h>
+#include <linux/smp.h>
+#include <linux/rcupdate.h>
+#include <linux/interrupt.h>
+#include <linux/sched.h>
+#include <asm/atomic.h>
+#include <linux/bitops.h>
+#include <linux/module.h>
+#include <linux/completion.h>
+#include <linux/moduleparam.h>
+#include <linux/percpu.h>
+#include <linux/notifier.h>
+#include <linux/cpu.h>
+#include <linux/mutex.h>
+#include <linux/debugfs.h>
+#include <linux/seq_file.h>
+
+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 rpfq=%ld rp=%x",
+		   rdp->cpu,
+		   cpu_is_offline(rdp->cpu) ? '!' : ' ',
+		   rdp->completed, rdp->gpnum,
+		   rdp->passed_quiesc, rdp->passed_quiesc_completed,
+		   rdp->qs_pending,
+		   rdp->n_rcu_pending_force_qs - rdp->n_rcu_pending,
+		   (int)(rdp->n_rcu_pending & 0xffff));
+#ifdef CONFIG_NO_HZ
+	seq_printf(m, " dt=%d/%d dn=%d df=%lu",
+		   rdp->dynticks->dynticks,
+		   rdp->dynticks->dynticks_nesting,
+		   rdp->dynticks->dynticks_nmi,
+		   rdp->dynticks_fqs);
+#endif /* #ifdef CONFIG_NO_HZ */
+	seq_printf(m, " of=%lu ri=%lu", rdp->offline_fqs, rdp->resched_ipi);
+	seq_printf(m, " ql=%ld b=%ld\n", rdp->qlen, rdp->blimit);
+}
+
+#define PRINT_RCU_DATA(name, func, m) \
+	do { \
+		int _p_r_d_i; \
+		\
+		for_each_possible_cpu(_p_r_d_i) \
+			func(m, &per_cpu(name, _p_r_d_i)); \
+	} while (0)
+
+static int show_rcudata(struct seq_file *m, void *unused)
+{
+	seq_puts(m, "rcu:\n");
+	PRINT_RCU_DATA(rcu_data, print_one_rcu_data, m);
+	seq_puts(m, "rcu_bh:\n");
+	PRINT_RCU_DATA(rcu_bh_data, print_one_rcu_data, m);
+	return 0;
+}
+
+static int rcudata_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, show_rcudata, NULL);
+}
+
+static struct file_operations rcudata_fops = {
+	.owner = THIS_MODULE,
+	.open = rcudata_open,
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.release = single_release,
+};
+
+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,%ld,%ld",
+		   rdp->cpu,
+		   cpu_is_offline(rdp->cpu) ? "\"Y\"" : "\"N\"",
+		   rdp->completed, rdp->gpnum,
+		   rdp->passed_quiesc, rdp->passed_quiesc_completed,
+		   rdp->qs_pending,
+		   rdp->n_rcu_pending_force_qs - rdp->n_rcu_pending,
+		   rdp->n_rcu_pending);
+#ifdef CONFIG_NO_HZ
+	seq_printf(m, ",%d,%d,%d,%lu",
+		   rdp->dynticks->dynticks,
+		   rdp->dynticks->dynticks_nesting,
+		   rdp->dynticks->dynticks_nmi,
+		   rdp->dynticks_fqs);
+#endif /* #ifdef CONFIG_NO_HZ */
+	seq_printf(m, ",%lu,%lu", rdp->offline_fqs, rdp->resched_ipi);
+	seq_printf(m, ",%ld,%ld\n", rdp->qlen, rdp->blimit);
+}
+
+static int show_rcudata_csv(struct seq_file *m, void *unused)
+{
+	seq_puts(m, "\"CPU\",\"Online?\",\"c\",\"g\",\"pq\",\"pqc\",\"pq\",\"rpfq\",\"rp\",");
+#ifdef CONFIG_NO_HZ
+	seq_puts(m, "\"dt\",\"dt nesting\",\"dn\",\"df\",");
+#endif /* #ifdef CONFIG_NO_HZ */
+	seq_puts(m, "\"of\",\"ri\",\"ql\",\"b\"\n");
+	seq_puts(m, "\"rcu:\"\n");
+	PRINT_RCU_DATA(rcu_data, print_one_rcu_data_csv, m);
+	seq_puts(m, "\"rcu_bh:\"\n");
+	PRINT_RCU_DATA(rcu_bh_data, print_one_rcu_data_csv, m);
+	return 0;
+}
+
+static int rcudata_csv_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, show_rcudata_csv, NULL);
+}
+
+static struct file_operations rcudata_csv_fops = {
+	.owner = THIS_MODULE,
+	.open = rcudata_csv_open,
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.release = single_release,
+};
+
+static void print_one_rcu_state(struct seq_file *m, struct rcu_state *rsp)
+{
+	int level = 0;
+	struct rcu_node *rnp;
+
+	seq_printf(m, "c=%ld g=%ld s=%d jfq=%ld j=%x "
+	              "nfqs=%lu/nfqsng=%lu(%lu) fqlh=%lu\n",
+		   rsp->completed, rsp->gpnum, rsp->signaled,
+		   (long)(rsp->jiffies_force_qs - jiffies),
+		   (int)(jiffies & 0xffff),
+		   rsp->n_force_qs, rsp->n_force_qs_ngp,
+		   rsp->n_force_qs - rsp->n_force_qs_ngp,
+		   rsp->n_force_qs_lh);
+	for (rnp = &rsp->node[0]; rnp - &rsp->node[0] < NUM_RCU_NODES; rnp++) {
+		if (rnp->level != level) {
+			seq_puts(m, "\n");
+			level = rnp->level;
+		}
+		seq_printf(m, "%lx/%lx %d:%d ^%d    ",
+			   rnp->qsmask, rnp->qsmaskinit,
+			   rnp->grplo, rnp->grphi, rnp->grpnum);
+	}
+	seq_puts(m, "\n");
+}
+
+static int show_rcuhier(struct seq_file *m, void *unused)
+{
+	seq_puts(m, "rcu:\n");
+	print_one_rcu_state(m, &rcu_state);
+	seq_puts(m, "rcu_bh:\n");
+	print_one_rcu_state(m, &rcu_bh_state);
+	return 0;
+}
+
+static int rcuhier_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, show_rcuhier, NULL);
+}
+
+static struct file_operations rcuhier_fops = {
+	.owner = THIS_MODULE,
+	.open = rcuhier_open,
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.release = single_release,
+};
+
+static int show_rcugp(struct seq_file *m, void *unused)
+{
+	seq_printf(m, "rcu: completed=%ld  gpnum=%ld\n",
+		   rcu_state.completed, rcu_state.gpnum);
+	seq_printf(m, "rcu_bh: completed=%ld  gpnum=%ld\n",
+		   rcu_bh_state.completed, rcu_bh_state.gpnum);
+	return 0;
+}
+
+static int rcugp_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, show_rcugp, NULL);
+}
+
+static struct file_operations rcugp_fops = {
+	.owner = THIS_MODULE,
+	.open = rcugp_open,
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.release = single_release,
+};
+
+static struct dentry *rcudir, *datadir, *datadir_csv, *hierdir, *gpdir;
+static int __init rcuclassic_trace_init(void)
+{
+	rcudir = debugfs_create_dir("rcu", NULL);
+	if (!rcudir)
+		goto out;
+
+	datadir = debugfs_create_file("rcudata", 0444, rcudir,
+						NULL, &rcudata_fops);
+	if (!datadir)
+		goto free_out;
+
+	datadir_csv = debugfs_create_file("rcudata.csv", 0444, rcudir,
+						NULL, &rcudata_csv_fops);
+	if (!datadir_csv)
+		goto free_out;
+
+	gpdir = debugfs_create_file("rcugp", 0444, rcudir, NULL, &rcugp_fops);
+	if (!gpdir)
+		goto free_out;
+
+	hierdir = debugfs_create_file("rcuhier", 0444, rcudir,
+						NULL, &rcuhier_fops);
+	if (!hierdir)
+		goto free_out;
+	return 0;
+free_out:
+	if (datadir)
+		debugfs_remove(datadir);
+	if (datadir_csv)
+		debugfs_remove(datadir_csv);
+	if (gpdir)
+		debugfs_remove(gpdir);
+	debugfs_remove(rcudir);
+out:
+	return 1;
+}
+
+static void __exit rcuclassic_trace_cleanup(void)
+{
+	debugfs_remove(datadir);
+	debugfs_remove(datadir_csv);
+	debugfs_remove(gpdir);
+	debugfs_remove(hierdir);
+	debugfs_remove(rcudir);
+}
+
+
+module_init(rcuclassic_trace_init);
+module_exit(rcuclassic_trace_cleanup);
+
+MODULE_AUTHOR("Paul E. McKenney");
+MODULE_DESCRIPTION("Read-Copy Update tracing for hierarchical implementation");
+MODULE_LICENSE("GPL");
diff --git a/kernel/res_counter.c b/kernel/res_counter.c
index f275c8eca772..bf8e7534c803 100644
--- a/kernel/res_counter.c
+++ b/kernel/res_counter.c
@@ -15,10 +15,11 @@
 #include <linux/uaccess.h>
 #include <linux/mm.h>
 
-void res_counter_init(struct res_counter *counter)
+void res_counter_init(struct res_counter *counter, struct res_counter *parent)
 {
 	spin_lock_init(&counter->lock);
 	counter->limit = (unsigned long long)LLONG_MAX;
+	counter->parent = parent;
 }
 
 int res_counter_charge_locked(struct res_counter *counter, unsigned long val)
@@ -34,14 +35,34 @@ int res_counter_charge_locked(struct res_counter *counter, unsigned long val)
 	return 0;
 }
 
-int res_counter_charge(struct res_counter *counter, unsigned long val)
+int res_counter_charge(struct res_counter *counter, unsigned long val,
+			struct res_counter **limit_fail_at)
 {
 	int ret;
 	unsigned long flags;
-
-	spin_lock_irqsave(&counter->lock, flags);
-	ret = res_counter_charge_locked(counter, val);
-	spin_unlock_irqrestore(&counter->lock, flags);
+	struct res_counter *c, *u;
+
+	*limit_fail_at = NULL;
+	local_irq_save(flags);
+	for (c = counter; c != NULL; c = c->parent) {
+		spin_lock(&c->lock);
+		ret = res_counter_charge_locked(c, val);
+		spin_unlock(&c->lock);
+		if (ret < 0) {
+			*limit_fail_at = c;
+			goto undo;
+		}
+	}
+	ret = 0;
+	goto done;
+undo:
+	for (u = counter; u != c; u = u->parent) {
+		spin_lock(&u->lock);
+		res_counter_uncharge_locked(u, val);
+		spin_unlock(&u->lock);
+	}
+done:
+	local_irq_restore(flags);
 	return ret;
 }
 
@@ -56,10 +77,15 @@ void res_counter_uncharge_locked(struct res_counter *counter, unsigned long val)
 void res_counter_uncharge(struct res_counter *counter, unsigned long val)
 {
 	unsigned long flags;
+	struct res_counter *c;
 
-	spin_lock_irqsave(&counter->lock, flags);
-	res_counter_uncharge_locked(counter, val);
-	spin_unlock_irqrestore(&counter->lock, flags);
+	local_irq_save(flags);
+	for (c = counter; c != NULL; c = c->parent) {
+		spin_lock(&c->lock);
+		res_counter_uncharge_locked(c, val);
+		spin_unlock(&c->lock);
+	}
+	local_irq_restore(flags);
 }
 
 
diff --git a/kernel/resource.c b/kernel/resource.c
index 4337063663ef..ca6a1536b205 100644
--- a/kernel/resource.c
+++ b/kernel/resource.c
@@ -623,7 +623,7 @@ resource_size_t resource_alignment(struct resource *res)
  */
 struct resource * __request_region(struct resource *parent,
 				   resource_size_t start, resource_size_t n,
-				   const char *name)
+				   const char *name, int flags)
 {
 	struct resource *res = kzalloc(sizeof(*res), GFP_KERNEL);
 
@@ -634,6 +634,7 @@ struct resource * __request_region(struct resource *parent,
 	res->start = start;
 	res->end = start + n - 1;
 	res->flags = IORESOURCE_BUSY;
+	res->flags |= flags;
 
 	write_lock(&resource_lock);
 
@@ -679,7 +680,7 @@ int __check_region(struct resource *parent, resource_size_t start,
 {
 	struct resource * res;
 
-	res = __request_region(parent, start, n, "check-region");
+	res = __request_region(parent, start, n, "check-region", 0);
 	if (!res)
 		return -EBUSY;
 
@@ -776,7 +777,7 @@ struct resource * __devm_request_region(struct device *dev,
 	dr->start = start;
 	dr->n = n;
 
-	res = __request_region(parent, start, n, name);
+	res = __request_region(parent, start, n, name, 0);
 	if (res)
 		devres_add(dev, dr);
 	else
@@ -853,6 +854,15 @@ int iomem_map_sanity_check(resource_size_t addr, unsigned long size)
 		if (PFN_DOWN(p->start) <= PFN_DOWN(addr) &&
 		    PFN_DOWN(p->end) >= PFN_DOWN(addr + size - 1))
 			continue;
+		/*
+		 * if a resource is "BUSY", it's not a hardware resource
+		 * but a driver mapping of such a resource; we don't want
+		 * to warn for those; some drivers legitimately map only
+		 * partial hardware resources. (example: vesafb)
+		 */
+		if (p->flags & IORESOURCE_BUSY)
+			continue;
+
 		printk(KERN_WARNING "resource map sanity check conflict: "
 		       "0x%llx 0x%llx 0x%llx 0x%llx %s\n",
 		       (unsigned long long)addr,
@@ -867,3 +877,57 @@ int iomem_map_sanity_check(resource_size_t addr, unsigned long size)
 
 	return err;
 }
+
+#ifdef CONFIG_STRICT_DEVMEM
+static int strict_iomem_checks = 1;
+#else
+static int strict_iomem_checks;
+#endif
+
+/*
+ * check if an address is reserved in the iomem resource tree
+ * returns 1 if reserved, 0 if not reserved.
+ */
+int iomem_is_exclusive(u64 addr)
+{
+	struct resource *p = &iomem_resource;
+	int err = 0;
+	loff_t l;
+	int size = PAGE_SIZE;
+
+	if (!strict_iomem_checks)
+		return 0;
+
+	addr = addr & PAGE_MASK;
+
+	read_lock(&resource_lock);
+	for (p = p->child; p ; p = r_next(NULL, p, &l)) {
+		/*
+		 * We can probably skip the resources without
+		 * IORESOURCE_IO attribute?
+		 */
+		if (p->start >= addr + size)
+			break;
+		if (p->end < addr)
+			continue;
+		if (p->flags & IORESOURCE_BUSY &&
+		     p->flags & IORESOURCE_EXCLUSIVE) {
+			err = 1;
+			break;
+		}
+	}
+	read_unlock(&resource_lock);
+
+	return err;
+}
+
+static int __init strict_iomem(char *str)
+{
+	if (strstr(str, "relaxed"))
+		strict_iomem_checks = 0;
+	if (strstr(str, "strict"))
+		strict_iomem_checks = 1;
+	return 1;
+}
+
+__setup("iomem=", strict_iomem);
diff --git a/kernel/sched.c b/kernel/sched.c
index 3dfbff5fb1ac..43fd21233b93 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -209,7 +209,6 @@ void init_rt_bandwidth(struct rt_bandwidth *rt_b, u64 period, u64 runtime)
 	hrtimer_init(&rt_b->rt_period_timer,
 			CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	rt_b->rt_period_timer.function = sched_rt_period_timer;
-	rt_b->rt_period_timer.cb_mode = HRTIMER_CB_IRQSAFE_UNLOCKED;
 }
 
 static inline int rt_bandwidth_enabled(void)
@@ -499,18 +498,26 @@ struct rt_rq {
  */
 struct root_domain {
 	atomic_t refcount;
-	cpumask_t span;
-	cpumask_t online;
+	cpumask_var_t span;
+	cpumask_var_t online;
 
 	/*
 	 * The "RT overload" flag: it gets set if a CPU has more than
 	 * one runnable RT task.
 	 */
-	cpumask_t rto_mask;
+	cpumask_var_t rto_mask;
 	atomic_t rto_count;
 #ifdef CONFIG_SMP
 	struct cpupri cpupri;
 #endif
+#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT)
+	/*
+	 * Preferred wake up cpu nominated by sched_mc balance that will be
+	 * used when most cpus are idle in the system indicating overall very
+	 * low system utilisation. Triggered at POWERSAVINGS_BALANCE_WAKEUP(2)
+	 */
+	unsigned int sched_mc_preferred_wakeup_cpu;
+#endif
 };
 
 /*
@@ -1159,7 +1166,6 @@ static void init_rq_hrtick(struct rq *rq)
 
 	hrtimer_init(&rq->hrtick_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	rq->hrtick_timer.function = hrtick;
-	rq->hrtick_timer.cb_mode = HRTIMER_CB_IRQSAFE_PERCPU;
 }
 #else	/* CONFIG_SCHED_HRTICK */
 static inline void hrtick_clear(struct rq *rq)
@@ -1536,7 +1542,7 @@ static int tg_shares_up(struct task_group *tg, void *data)
 	struct sched_domain *sd = data;
 	int i;
 
-	for_each_cpu_mask(i, sd->span) {
+	for_each_cpu(i, sched_domain_span(sd)) {
 		/*
 		 * If there are currently no tasks on the cpu pretend there
 		 * is one of average load so that when a new task gets to
@@ -1557,7 +1563,7 @@ static int tg_shares_up(struct task_group *tg, void *data)
 	if (!sd->parent || !(sd->parent->flags & SD_LOAD_BALANCE))
 		shares = tg->shares;
 
-	for_each_cpu_mask(i, sd->span)
+	for_each_cpu(i, sched_domain_span(sd))
 		update_group_shares_cpu(tg, i, shares, rq_weight);
 
 	return 0;
@@ -2125,15 +2131,17 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p, int this_cpu)
 		int i;
 
 		/* Skip over this group if it has no CPUs allowed */
-		if (!cpus_intersects(group->cpumask, p->cpus_allowed))
+		if (!cpumask_intersects(sched_group_cpus(group),
+					&p->cpus_allowed))
 			continue;
 
-		local_group = cpu_isset(this_cpu, group->cpumask);
+		local_group = cpumask_test_cpu(this_cpu,
+					       sched_group_cpus(group));
 
 		/* Tally up the load of all CPUs in the group */
 		avg_load = 0;
 
-		for_each_cpu_mask_nr(i, group->cpumask) {
+		for_each_cpu(i, sched_group_cpus(group)) {
 			/* Bias balancing toward cpus of our domain */
 			if (local_group)
 				load = source_load(i, load_idx);
@@ -2165,17 +2173,14 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p, int this_cpu)
  * find_idlest_cpu - find the idlest cpu among the cpus in group.
  */
 static int
-find_idlest_cpu(struct sched_group *group, struct task_struct *p, int this_cpu,
-		cpumask_t *tmp)
+find_idlest_cpu(struct sched_group *group, struct task_struct *p, int this_cpu)
 {
 	unsigned long load, min_load = ULONG_MAX;
 	int idlest = -1;
 	int i;
 
 	/* Traverse only the allowed CPUs */
-	cpus_and(*tmp, group->cpumask, p->cpus_allowed);
-
-	for_each_cpu_mask_nr(i, *tmp) {
+	for_each_cpu_and(i, sched_group_cpus(group), &p->cpus_allowed) {
 		load = weighted_cpuload(i);
 
 		if (load < min_load || (load == min_load && i == this_cpu)) {
@@ -2217,7 +2222,6 @@ static int sched_balance_self(int cpu, int flag)
 		update_shares(sd);
 
 	while (sd) {
-		cpumask_t span, tmpmask;
 		struct sched_group *group;
 		int new_cpu, weight;
 
@@ -2226,14 +2230,13 @@ static int sched_balance_self(int cpu, int flag)
 			continue;
 		}
 
-		span = sd->span;
 		group = find_idlest_group(sd, t, cpu);
 		if (!group) {
 			sd = sd->child;
 			continue;
 		}
 
-		new_cpu = find_idlest_cpu(group, t, cpu, &tmpmask);
+		new_cpu = find_idlest_cpu(group, t, cpu);
 		if (new_cpu == -1 || new_cpu == cpu) {
 			/* Now try balancing at a lower domain level of cpu */
 			sd = sd->child;
@@ -2242,10 +2245,10 @@ static int sched_balance_self(int cpu, int flag)
 
 		/* Now try balancing at a lower domain level of new_cpu */
 		cpu = new_cpu;
+		weight = cpumask_weight(sched_domain_span(sd));
 		sd = NULL;
-		weight = cpus_weight(span);
 		for_each_domain(cpu, tmp) {
-			if (weight <= cpus_weight(tmp->span))
+			if (weight <= cpumask_weight(sched_domain_span(tmp)))
 				break;
 			if (tmp->flags & flag)
 				sd = tmp;
@@ -2311,7 +2314,7 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state, int sync)
 		cpu = task_cpu(p);
 
 		for_each_domain(this_cpu, sd) {
-			if (cpu_isset(cpu, sd->span)) {
+			if (cpumask_test_cpu(cpu, sched_domain_span(sd))) {
 				update_shares(sd);
 				break;
 			}
@@ -2360,7 +2363,7 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state, int sync)
 	else {
 		struct sched_domain *sd;
 		for_each_domain(this_cpu, sd) {
-			if (cpu_isset(cpu, sd->span)) {
+			if (cpumask_test_cpu(cpu, sched_domain_span(sd))) {
 				schedstat_inc(sd, ttwu_wake_remote);
 				break;
 			}
@@ -2893,7 +2896,7 @@ static void sched_migrate_task(struct task_struct *p, int dest_cpu)
 	struct rq *rq;
 
 	rq = task_rq_lock(p, &flags);
-	if (!cpu_isset(dest_cpu, p->cpus_allowed)
+	if (!cpumask_test_cpu(dest_cpu, &p->cpus_allowed)
 	    || unlikely(!cpu_active(dest_cpu)))
 		goto out;
 
@@ -2958,7 +2961,7 @@ int can_migrate_task(struct task_struct *p, struct rq *rq, int this_cpu,
 	 * 2) cannot be migrated to this CPU due to cpus_allowed, or
 	 * 3) are cache-hot on their current CPU.
 	 */
-	if (!cpu_isset(this_cpu, p->cpus_allowed)) {
+	if (!cpumask_test_cpu(this_cpu, &p->cpus_allowed)) {
 		schedstat_inc(p, se.nr_failed_migrations_affine);
 		return 0;
 	}
@@ -3133,7 +3136,7 @@ static int move_one_task(struct rq *this_rq, int this_cpu, struct rq *busiest,
 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 cpumask_t *cpus, int *balance)
+		   int *sd_idle, const struct cpumask *cpus, int *balance)
 {
 	struct sched_group *busiest = NULL, *this = NULL, *group = sd->groups;
 	unsigned long max_load, avg_load, total_load, this_load, total_pwr;
@@ -3169,10 +3172,11 @@ find_busiest_group(struct sched_domain *sd, int this_cpu,
 		unsigned long sum_avg_load_per_task;
 		unsigned long avg_load_per_task;
 
-		local_group = cpu_isset(this_cpu, group->cpumask);
+		local_group = cpumask_test_cpu(this_cpu,
+					       sched_group_cpus(group));
 
 		if (local_group)
-			balance_cpu = first_cpu(group->cpumask);
+			balance_cpu = cpumask_first(sched_group_cpus(group));
 
 		/* Tally up the load of all CPUs in the group */
 		sum_weighted_load = sum_nr_running = avg_load = 0;
@@ -3181,13 +3185,8 @@ find_busiest_group(struct sched_domain *sd, int this_cpu,
 		max_cpu_load = 0;
 		min_cpu_load = ~0UL;
 
-		for_each_cpu_mask_nr(i, group->cpumask) {
-			struct rq *rq;
-
-			if (!cpu_isset(i, *cpus))
-				continue;
-
-			rq = cpu_rq(i);
+		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;
@@ -3298,8 +3297,8 @@ find_busiest_group(struct sched_domain *sd, int this_cpu,
 		 */
 		if ((sum_nr_running < min_nr_running) ||
 		    (sum_nr_running == min_nr_running &&
-		     first_cpu(group->cpumask) <
-		     first_cpu(group_min->cpumask))) {
+		     cpumask_first(sched_group_cpus(group)) >
+		     cpumask_first(sched_group_cpus(group_min)))) {
 			group_min = group;
 			min_nr_running = sum_nr_running;
 			min_load_per_task = sum_weighted_load /
@@ -3314,8 +3313,8 @@ find_busiest_group(struct sched_domain *sd, int this_cpu,
 		if (sum_nr_running <= group_capacity - 1) {
 			if (sum_nr_running > leader_nr_running ||
 			    (sum_nr_running == leader_nr_running &&
-			     first_cpu(group->cpumask) >
-			      first_cpu(group_leader->cpumask))) {
+			     cpumask_first(sched_group_cpus(group)) <
+			     cpumask_first(sched_group_cpus(group_leader)))) {
 				group_leader = group;
 				leader_nr_running = sum_nr_running;
 			}
@@ -3441,6 +3440,10 @@ out_balanced:
 
 	if (this == group_leader && group_leader != group_min) {
 		*imbalance = min_load_per_task;
+		if (sched_mc_power_savings >= POWERSAVINGS_BALANCE_WAKEUP) {
+			cpu_rq(this_cpu)->rd->sched_mc_preferred_wakeup_cpu =
+				cpumask_first(sched_group_cpus(group_leader));
+		}
 		return group_min;
 	}
 #endif
@@ -3454,16 +3457,16 @@ ret:
  */
 static struct rq *
 find_busiest_queue(struct sched_group *group, enum cpu_idle_type idle,
-		   unsigned long imbalance, const cpumask_t *cpus)
+		   unsigned long imbalance, const struct cpumask *cpus)
 {
 	struct rq *busiest = NULL, *rq;
 	unsigned long max_load = 0;
 	int i;
 
-	for_each_cpu_mask_nr(i, group->cpumask) {
+	for_each_cpu(i, sched_group_cpus(group)) {
 		unsigned long wl;
 
-		if (!cpu_isset(i, *cpus))
+		if (!cpumask_test_cpu(i, cpus))
 			continue;
 
 		rq = cpu_rq(i);
@@ -3493,7 +3496,7 @@ find_busiest_queue(struct sched_group *group, enum cpu_idle_type idle,
  */
 static int load_balance(int this_cpu, struct rq *this_rq,
 			struct sched_domain *sd, enum cpu_idle_type idle,
-			int *balance, cpumask_t *cpus)
+			int *balance, struct cpumask *cpus)
 {
 	int ld_moved, all_pinned = 0, active_balance = 0, sd_idle = 0;
 	struct sched_group *group;
@@ -3501,7 +3504,7 @@ static int load_balance(int this_cpu, struct rq *this_rq,
 	struct rq *busiest;
 	unsigned long flags;
 
-	cpus_setall(*cpus);
+	cpumask_setall(cpus);
 
 	/*
 	 * When power savings policy is enabled for the parent domain, idle
@@ -3561,8 +3564,8 @@ redo:
 
 		/* All tasks on this runqueue were pinned by CPU affinity */
 		if (unlikely(all_pinned)) {
-			cpu_clear(cpu_of(busiest), *cpus);
-			if (!cpus_empty(*cpus))
+			cpumask_clear_cpu(cpu_of(busiest), cpus);
+			if (!cpumask_empty(cpus))
 				goto redo;
 			goto out_balanced;
 		}
@@ -3579,7 +3582,8 @@ redo:
 			/* don't kick the migration_thread, if the curr
 			 * task on busiest cpu can't be moved to this_cpu
 			 */
-			if (!cpu_isset(this_cpu, busiest->curr->cpus_allowed)) {
+			if (!cpumask_test_cpu(this_cpu,
+					      &busiest->curr->cpus_allowed)) {
 				spin_unlock_irqrestore(&busiest->lock, flags);
 				all_pinned = 1;
 				goto out_one_pinned;
@@ -3654,7 +3658,7 @@ out:
  */
 static int
 load_balance_newidle(int this_cpu, struct rq *this_rq, struct sched_domain *sd,
-			cpumask_t *cpus)
+			struct cpumask *cpus)
 {
 	struct sched_group *group;
 	struct rq *busiest = NULL;
@@ -3663,7 +3667,7 @@ load_balance_newidle(int this_cpu, struct rq *this_rq, struct sched_domain *sd,
 	int sd_idle = 0;
 	int all_pinned = 0;
 
-	cpus_setall(*cpus);
+	cpumask_setall(cpus);
 
 	/*
 	 * When power savings policy is enabled for the parent domain, idle
@@ -3707,17 +3711,76 @@ redo:
 		double_unlock_balance(this_rq, busiest);
 
 		if (unlikely(all_pinned)) {
-			cpu_clear(cpu_of(busiest), *cpus);
-			if (!cpus_empty(*cpus))
+			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
+		 */
+		spin_unlock(&this_rq->lock);
+		if (active_balance)
+			wake_up_process(busiest->migration_thread);
+		spin_lock(&this_rq->lock);
+
 	} else
 		sd->nr_balance_failed = 0;
 
@@ -3743,7 +3806,10 @@ 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;
-	cpumask_t tmpmask;
+	cpumask_var_t tmpmask;
+
+	if (!alloc_cpumask_var(&tmpmask, GFP_ATOMIC))
+		return;
 
 	for_each_domain(this_cpu, sd) {
 		unsigned long interval;
@@ -3754,7 +3820,7 @@ static void idle_balance(int this_cpu, struct rq *this_rq)
 		if (sd->flags & SD_BALANCE_NEWIDLE)
 			/* If we've pulled tasks over stop searching: */
 			pulled_task = load_balance_newidle(this_cpu, this_rq,
-							   sd, &tmpmask);
+							   sd, tmpmask);
 
 		interval = msecs_to_jiffies(sd->balance_interval);
 		if (time_after(next_balance, sd->last_balance + interval))
@@ -3769,6 +3835,7 @@ static void idle_balance(int this_cpu, struct rq *this_rq)
 		 */
 		this_rq->next_balance = next_balance;
 	}
+	free_cpumask_var(tmpmask);
 }
 
 /*
@@ -3806,7 +3873,7 @@ static void active_load_balance(struct rq *busiest_rq, int busiest_cpu)
 	/* Search for an sd spanning us and the target CPU. */
 	for_each_domain(target_cpu, sd) {
 		if ((sd->flags & SD_LOAD_BALANCE) &&
-		    cpu_isset(busiest_cpu, sd->span))
+		    cpumask_test_cpu(busiest_cpu, sched_domain_span(sd)))
 				break;
 	}
 
@@ -3825,10 +3892,9 @@ static void active_load_balance(struct rq *busiest_rq, int busiest_cpu)
 #ifdef CONFIG_NO_HZ
 static struct {
 	atomic_t load_balancer;
-	cpumask_t cpu_mask;
+	cpumask_var_t cpu_mask;
 } nohz ____cacheline_aligned = {
 	.load_balancer = ATOMIC_INIT(-1),
-	.cpu_mask = CPU_MASK_NONE,
 };
 
 /*
@@ -3856,7 +3922,7 @@ int select_nohz_load_balancer(int stop_tick)
 	int cpu = smp_processor_id();
 
 	if (stop_tick) {
-		cpu_set(cpu, nohz.cpu_mask);
+		cpumask_set_cpu(cpu, nohz.cpu_mask);
 		cpu_rq(cpu)->in_nohz_recently = 1;
 
 		/*
@@ -3870,7 +3936,7 @@ int select_nohz_load_balancer(int stop_tick)
 		}
 
 		/* time for ilb owner also to sleep */
-		if (cpus_weight(nohz.cpu_mask) == num_online_cpus()) {
+		if (cpumask_weight(nohz.cpu_mask) == num_online_cpus()) {
 			if (atomic_read(&nohz.load_balancer) == cpu)
 				atomic_set(&nohz.load_balancer, -1);
 			return 0;
@@ -3883,10 +3949,10 @@ int select_nohz_load_balancer(int stop_tick)
 		} else if (atomic_read(&nohz.load_balancer) == cpu)
 			return 1;
 	} else {
-		if (!cpu_isset(cpu, nohz.cpu_mask))
+		if (!cpumask_test_cpu(cpu, nohz.cpu_mask))
 			return 0;
 
-		cpu_clear(cpu, nohz.cpu_mask);
+		cpumask_clear_cpu(cpu, nohz.cpu_mask);
 
 		if (atomic_read(&nohz.load_balancer) == cpu)
 			if (atomic_cmpxchg(&nohz.load_balancer, cpu, -1) != cpu)
@@ -3914,7 +3980,11 @@ static void rebalance_domains(int cpu, enum cpu_idle_type idle)
 	unsigned long next_balance = jiffies + 60*HZ;
 	int update_next_balance = 0;
 	int need_serialize;
-	cpumask_t tmp;
+	cpumask_var_t tmp;
+
+	/* Fails alloc?  Rebalancing probably not a priority right now. */
+	if (!alloc_cpumask_var(&tmp, GFP_ATOMIC))
+		return;
 
 	for_each_domain(cpu, sd) {
 		if (!(sd->flags & SD_LOAD_BALANCE))
@@ -3939,7 +4009,7 @@ static void rebalance_domains(int cpu, enum cpu_idle_type idle)
 		}
 
 		if (time_after_eq(jiffies, sd->last_balance + interval)) {
-			if (load_balance(cpu, rq, sd, idle, &balance, &tmp)) {
+			if (load_balance(cpu, rq, sd, idle, &balance, tmp)) {
 				/*
 				 * We've pulled tasks over so either we're no
 				 * longer idle, or one of our SMT siblings is
@@ -3973,6 +4043,8 @@ out:
 	 */
 	if (likely(update_next_balance))
 		rq->next_balance = next_balance;
+
+	free_cpumask_var(tmp);
 }
 
 /*
@@ -3997,12 +4069,13 @@ static void run_rebalance_domains(struct softirq_action *h)
 	 */
 	if (this_rq->idle_at_tick &&
 	    atomic_read(&nohz.load_balancer) == this_cpu) {
-		cpumask_t cpus = nohz.cpu_mask;
 		struct rq *rq;
 		int balance_cpu;
 
-		cpu_clear(this_cpu, cpus);
-		for_each_cpu_mask_nr(balance_cpu, cpus) {
+		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
@@ -4040,7 +4113,7 @@ static inline void trigger_load_balance(struct rq *rq, int cpu)
 		rq->in_nohz_recently = 0;
 
 		if (atomic_read(&nohz.load_balancer) == cpu) {
-			cpu_clear(cpu, nohz.cpu_mask);
+			cpumask_clear_cpu(cpu, nohz.cpu_mask);
 			atomic_set(&nohz.load_balancer, -1);
 		}
 
@@ -4053,7 +4126,7 @@ static inline void trigger_load_balance(struct rq *rq, int cpu)
 			 * TBD: Traverse the sched domains and nominate
 			 * the nearest cpu in the nohz.cpu_mask.
 			 */
-			int ilb = first_cpu(nohz.cpu_mask);
+			int ilb = cpumask_first(nohz.cpu_mask);
 
 			if (ilb < nr_cpu_ids)
 				resched_cpu(ilb);
@@ -4065,7 +4138,7 @@ static inline void trigger_load_balance(struct rq *rq, int cpu)
 	 * cpus with ticks stopped, is it time for that to stop?
 	 */
 	if (rq->idle_at_tick && atomic_read(&nohz.load_balancer) == cpu &&
-	    cpus_weight(nohz.cpu_mask) == num_online_cpus()) {
+	    cpumask_weight(nohz.cpu_mask) == num_online_cpus()) {
 		resched_cpu(cpu);
 		return;
 	}
@@ -4075,7 +4148,7 @@ static inline void trigger_load_balance(struct rq *rq, int cpu)
 	 * someone else, then no need raise the SCHED_SOFTIRQ
 	 */
 	if (rq->idle_at_tick && atomic_read(&nohz.load_balancer) != cpu &&
-	    cpu_isset(cpu, nohz.cpu_mask))
+	    cpumask_test_cpu(cpu, nohz.cpu_mask))
 		return;
 #endif
 	if (time_after_eq(jiffies, rq->next_balance))
@@ -4150,13 +4223,17 @@ unsigned long long task_delta_exec(struct task_struct *p)
  * Account user cpu time to a process.
  * @p: the process that the cpu time gets accounted to
  * @cputime: the cpu time spent in user space since the last update
+ * @cputime_scaled: cputime scaled by cpu frequency
  */
-void account_user_time(struct task_struct *p, cputime_t cputime)
+void account_user_time(struct task_struct *p, cputime_t cputime,
+		       cputime_t cputime_scaled)
 {
 	struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
 	cputime64_t tmp;
 
+	/* Add user time to process. */
 	p->utime = cputime_add(p->utime, cputime);
+	p->utimescaled = cputime_add(p->utimescaled, cputime_scaled);
 	account_group_user_time(p, cputime);
 
 	/* Add user time to cpustat. */
@@ -4173,51 +4250,48 @@ void account_user_time(struct task_struct *p, cputime_t cputime)
  * Account guest cpu time to a process.
  * @p: the process that the cpu time gets accounted to
  * @cputime: the cpu time spent in virtual machine since the last update
+ * @cputime_scaled: cputime scaled by cpu frequency
  */
-static void account_guest_time(struct task_struct *p, cputime_t cputime)
+static void account_guest_time(struct task_struct *p, cputime_t cputime,
+			       cputime_t cputime_scaled)
 {
 	cputime64_t tmp;
 	struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
 
 	tmp = cputime_to_cputime64(cputime);
 
+	/* Add guest time to process. */
 	p->utime = cputime_add(p->utime, cputime);
+	p->utimescaled = cputime_add(p->utimescaled, cputime_scaled);
 	account_group_user_time(p, cputime);
 	p->gtime = cputime_add(p->gtime, cputime);
 
+	/* Add guest time to cpustat. */
 	cpustat->user = cputime64_add(cpustat->user, tmp);
 	cpustat->guest = cputime64_add(cpustat->guest, tmp);
 }
 
 /*
- * Account scaled user cpu time to a process.
- * @p: the process that the cpu time gets accounted to
- * @cputime: the cpu time spent in user space since the last update
- */
-void account_user_time_scaled(struct task_struct *p, cputime_t cputime)
-{
-	p->utimescaled = cputime_add(p->utimescaled, cputime);
-}
-
-/*
  * Account system cpu time to a process.
  * @p: the process that the cpu time gets accounted to
  * @hardirq_offset: the offset to subtract from hardirq_count()
  * @cputime: the cpu time spent in kernel space since the last update
+ * @cputime_scaled: cputime scaled by cpu frequency
  */
 void account_system_time(struct task_struct *p, int hardirq_offset,
-			 cputime_t cputime)
+			 cputime_t cputime, cputime_t cputime_scaled)
 {
 	struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
-	struct rq *rq = this_rq();
 	cputime64_t tmp;
 
 	if ((p->flags & PF_VCPU) && (irq_count() - hardirq_offset == 0)) {
-		account_guest_time(p, cputime);
+		account_guest_time(p, cputime, cputime_scaled);
 		return;
 	}
 
+	/* Add system time to process. */
 	p->stime = cputime_add(p->stime, cputime);
+	p->stimescaled = cputime_add(p->stimescaled, cputime_scaled);
 	account_group_system_time(p, cputime);
 
 	/* Add system time to cpustat. */
@@ -4226,49 +4300,84 @@ void account_system_time(struct task_struct *p, int hardirq_offset,
 		cpustat->irq = cputime64_add(cpustat->irq, tmp);
 	else if (softirq_count())
 		cpustat->softirq = cputime64_add(cpustat->softirq, tmp);
-	else if (p != rq->idle)
-		cpustat->system = cputime64_add(cpustat->system, tmp);
-	else if (atomic_read(&rq->nr_iowait) > 0)
-		cpustat->iowait = cputime64_add(cpustat->iowait, tmp);
 	else
-		cpustat->idle = cputime64_add(cpustat->idle, tmp);
+		cpustat->system = cputime64_add(cpustat->system, tmp);
+
 	/* Account for system time used */
 	acct_update_integrals(p);
 }
 
 /*
- * Account scaled system cpu time to a process.
- * @p: the process that the cpu time gets accounted to
- * @hardirq_offset: the offset to subtract from hardirq_count()
- * @cputime: the cpu time spent in kernel space since the last update
+ * Account for involuntary wait time.
+ * @steal: the cpu time spent in involuntary wait
  */
-void account_system_time_scaled(struct task_struct *p, cputime_t cputime)
+void account_steal_time(cputime_t cputime)
 {
-	p->stimescaled = cputime_add(p->stimescaled, cputime);
+	struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
+	cputime64_t cputime64 = cputime_to_cputime64(cputime);
+
+	cpustat->steal = cputime64_add(cpustat->steal, cputime64);
 }
 
 /*
- * Account for involuntary wait time.
- * @p: the process from which the cpu time has been stolen
- * @steal: the cpu time spent in involuntary wait
+ * Account for idle time.
+ * @cputime: the cpu time spent in idle wait
  */
-void account_steal_time(struct task_struct *p, cputime_t steal)
+void account_idle_time(cputime_t cputime)
 {
 	struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
-	cputime64_t tmp = cputime_to_cputime64(steal);
+	cputime64_t cputime64 = cputime_to_cputime64(cputime);
 	struct rq *rq = this_rq();
 
-	if (p == rq->idle) {
-		p->stime = cputime_add(p->stime, steal);
-		account_group_system_time(p, steal);
-		if (atomic_read(&rq->nr_iowait) > 0)
-			cpustat->iowait = cputime64_add(cpustat->iowait, tmp);
-		else
-			cpustat->idle = cputime64_add(cpustat->idle, tmp);
-	} else
-		cpustat->steal = cputime64_add(cpustat->steal, tmp);
+	if (atomic_read(&rq->nr_iowait) > 0)
+		cpustat->iowait = cputime64_add(cpustat->iowait, cputime64);
+	else
+		cpustat->idle = cputime64_add(cpustat->idle, cputime64);
 }
 
+#ifndef CONFIG_VIRT_CPU_ACCOUNTING
+
+/*
+ * Account a single tick of cpu time.
+ * @p: the process that the cpu time gets accounted to
+ * @user_tick: indicates if the tick is a user or a system tick
+ */
+void account_process_tick(struct task_struct *p, int user_tick)
+{
+	cputime_t one_jiffy = jiffies_to_cputime(1);
+	cputime_t one_jiffy_scaled = cputime_to_scaled(one_jiffy);
+	struct rq *rq = this_rq();
+
+	if (user_tick)
+		account_user_time(p, one_jiffy, one_jiffy_scaled);
+	else if (p != rq->idle)
+		account_system_time(p, HARDIRQ_OFFSET, one_jiffy,
+				    one_jiffy_scaled);
+	else
+		account_idle_time(one_jiffy);
+}
+
+/*
+ * Account multiple ticks of steal time.
+ * @p: the process from which the cpu time has been stolen
+ * @ticks: number of stolen ticks
+ */
+void account_steal_ticks(unsigned long ticks)
+{
+	account_steal_time(jiffies_to_cputime(ticks));
+}
+
+/*
+ * Account multiple ticks of idle time.
+ * @ticks: number of stolen ticks
+ */
+void account_idle_ticks(unsigned long ticks)
+{
+	account_idle_time(jiffies_to_cputime(ticks));
+}
+
+#endif
+
 /*
  * Use precise platform statistics if available:
  */
@@ -4397,7 +4506,7 @@ void __kprobes sub_preempt_count(int val)
 	/*
 	 * Underflow?
 	 */
-	if (DEBUG_LOCKS_WARN_ON(val > preempt_count()))
+       if (DEBUG_LOCKS_WARN_ON(val > preempt_count() - (!!kernel_locked())))
 		return;
 	/*
 	 * Is the spinlock portion underflowing?
@@ -5474,10 +5583,9 @@ out_unlock:
 	return retval;
 }
 
-long sched_setaffinity(pid_t pid, const cpumask_t *in_mask)
+long sched_setaffinity(pid_t pid, const struct cpumask *in_mask)
 {
-	cpumask_t cpus_allowed;
-	cpumask_t new_mask = *in_mask;
+	cpumask_var_t cpus_allowed, new_mask;
 	struct task_struct *p;
 	int retval;
 
@@ -5499,6 +5607,14 @@ long sched_setaffinity(pid_t pid, const cpumask_t *in_mask)
 	get_task_struct(p);
 	read_unlock(&tasklist_lock);
 
+	if (!alloc_cpumask_var(&cpus_allowed, GFP_KERNEL)) {
+		retval = -ENOMEM;
+		goto out_put_task;
+	}
+	if (!alloc_cpumask_var(&new_mask, GFP_KERNEL)) {
+		retval = -ENOMEM;
+		goto out_free_cpus_allowed;
+	}
 	retval = -EPERM;
 	if (!check_same_owner(p) && !capable(CAP_SYS_NICE))
 		goto out_unlock;
@@ -5507,37 +5623,41 @@ long sched_setaffinity(pid_t pid, const cpumask_t *in_mask)
 	if (retval)
 		goto out_unlock;
 
-	cpuset_cpus_allowed(p, &cpus_allowed);
-	cpus_and(new_mask, new_mask, cpus_allowed);
+	cpuset_cpus_allowed(p, cpus_allowed);
+	cpumask_and(new_mask, in_mask, cpus_allowed);
  again:
-	retval = set_cpus_allowed_ptr(p, &new_mask);
+	retval = set_cpus_allowed_ptr(p, new_mask);
 
 	if (!retval) {
-		cpuset_cpus_allowed(p, &cpus_allowed);
-		if (!cpus_subset(new_mask, cpus_allowed)) {
+		cpuset_cpus_allowed(p, cpus_allowed);
+		if (!cpumask_subset(new_mask, cpus_allowed)) {
 			/*
 			 * We must have raced with a concurrent cpuset
 			 * update. Just reset the cpus_allowed to the
 			 * cpuset's cpus_allowed
 			 */
-			new_mask = cpus_allowed;
+			cpumask_copy(new_mask, cpus_allowed);
 			goto again;
 		}
 	}
 out_unlock:
+	free_cpumask_var(new_mask);
+out_free_cpus_allowed:
+	free_cpumask_var(cpus_allowed);
+out_put_task:
 	put_task_struct(p);
 	put_online_cpus();
 	return retval;
 }
 
 static int get_user_cpu_mask(unsigned long __user *user_mask_ptr, unsigned len,
-			     cpumask_t *new_mask)
+			     struct cpumask *new_mask)
 {
-	if (len < sizeof(cpumask_t)) {
-		memset(new_mask, 0, sizeof(cpumask_t));
-	} else if (len > sizeof(cpumask_t)) {
-		len = sizeof(cpumask_t);
-	}
+	if (len < cpumask_size())
+		cpumask_clear(new_mask);
+	else if (len > cpumask_size())
+		len = cpumask_size();
+
 	return copy_from_user(new_mask, user_mask_ptr, len) ? -EFAULT : 0;
 }
 
@@ -5550,17 +5670,20 @@ static int get_user_cpu_mask(unsigned long __user *user_mask_ptr, unsigned len,
 asmlinkage long sys_sched_setaffinity(pid_t pid, unsigned int len,
 				      unsigned long __user *user_mask_ptr)
 {
-	cpumask_t new_mask;
+	cpumask_var_t new_mask;
 	int retval;
 
-	retval = get_user_cpu_mask(user_mask_ptr, len, &new_mask);
-	if (retval)
-		return retval;
+	if (!alloc_cpumask_var(&new_mask, GFP_KERNEL))
+		return -ENOMEM;
 
-	return sched_setaffinity(pid, &new_mask);
+	retval = get_user_cpu_mask(user_mask_ptr, len, new_mask);
+	if (retval == 0)
+		retval = sched_setaffinity(pid, new_mask);
+	free_cpumask_var(new_mask);
+	return retval;
 }
 
-long sched_getaffinity(pid_t pid, cpumask_t *mask)
+long sched_getaffinity(pid_t pid, struct cpumask *mask)
 {
 	struct task_struct *p;
 	int retval;
@@ -5577,7 +5700,7 @@ long sched_getaffinity(pid_t pid, cpumask_t *mask)
 	if (retval)
 		goto out_unlock;
 
-	cpus_and(*mask, p->cpus_allowed, cpu_online_map);
+	cpumask_and(mask, &p->cpus_allowed, cpu_online_mask);
 
 out_unlock:
 	read_unlock(&tasklist_lock);
@@ -5596,19 +5719,24 @@ asmlinkage long sys_sched_getaffinity(pid_t pid, unsigned int len,
 				      unsigned long __user *user_mask_ptr)
 {
 	int ret;
-	cpumask_t mask;
+	cpumask_var_t mask;
 
-	if (len < sizeof(cpumask_t))
+	if (len < cpumask_size())
 		return -EINVAL;
 
-	ret = sched_getaffinity(pid, &mask);
-	if (ret < 0)
-		return ret;
+	if (!alloc_cpumask_var(&mask, GFP_KERNEL))
+		return -ENOMEM;
 
-	if (copy_to_user(user_mask_ptr, &mask, sizeof(cpumask_t)))
-		return -EFAULT;
+	ret = sched_getaffinity(pid, mask);
+	if (ret == 0) {
+		if (copy_to_user(user_mask_ptr, mask, cpumask_size()))
+			ret = -EFAULT;
+		else
+			ret = cpumask_size();
+	}
+	free_cpumask_var(mask);
 
-	return sizeof(cpumask_t);
+	return ret;
 }
 
 /**
@@ -5950,7 +6078,7 @@ void __cpuinit init_idle(struct task_struct *idle, int cpu)
 	idle->se.exec_start = sched_clock();
 
 	idle->prio = idle->normal_prio = MAX_PRIO;
-	idle->cpus_allowed = cpumask_of_cpu(cpu);
+	cpumask_copy(&idle->cpus_allowed, cpumask_of(cpu));
 	__set_task_cpu(idle, cpu);
 
 	rq->curr = rq->idle = idle;
@@ -5977,9 +6105,9 @@ void __cpuinit init_idle(struct task_struct *idle, int cpu)
  * indicates which cpus entered this state. This is used
  * in the rcu update to wait only for active cpus. For system
  * which do not switch off the HZ timer nohz_cpu_mask should
- * always be CPU_MASK_NONE.
+ * always be CPU_BITS_NONE.
  */
-cpumask_t nohz_cpu_mask = CPU_MASK_NONE;
+cpumask_var_t nohz_cpu_mask;
 
 /*
  * Increase the granularity value when there are more CPUs,
@@ -6034,7 +6162,7 @@ static inline void sched_init_granularity(void)
  * task must not exit() & deallocate itself prematurely. The
  * call is not atomic; no spinlocks may be held.
  */
-int set_cpus_allowed_ptr(struct task_struct *p, const cpumask_t *new_mask)
+int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask)
 {
 	struct migration_req req;
 	unsigned long flags;
@@ -6042,13 +6170,13 @@ int set_cpus_allowed_ptr(struct task_struct *p, const cpumask_t *new_mask)
 	int ret = 0;
 
 	rq = task_rq_lock(p, &flags);
-	if (!cpus_intersects(*new_mask, cpu_online_map)) {
+	if (!cpumask_intersects(new_mask, cpu_online_mask)) {
 		ret = -EINVAL;
 		goto out;
 	}
 
 	if (unlikely((p->flags & PF_THREAD_BOUND) && p != current &&
-		     !cpus_equal(p->cpus_allowed, *new_mask))) {
+		     !cpumask_equal(&p->cpus_allowed, new_mask))) {
 		ret = -EINVAL;
 		goto out;
 	}
@@ -6056,15 +6184,15 @@ int set_cpus_allowed_ptr(struct task_struct *p, const cpumask_t *new_mask)
 	if (p->sched_class->set_cpus_allowed)
 		p->sched_class->set_cpus_allowed(p, new_mask);
 	else {
-		p->cpus_allowed = *new_mask;
-		p->rt.nr_cpus_allowed = cpus_weight(*new_mask);
+		cpumask_copy(&p->cpus_allowed, new_mask);
+		p->rt.nr_cpus_allowed = cpumask_weight(new_mask);
 	}
 
 	/* Can the task run on the task's current CPU? If so, we're done */
-	if (cpu_isset(task_cpu(p), *new_mask))
+	if (cpumask_test_cpu(task_cpu(p), new_mask))
 		goto out;
 
-	if (migrate_task(p, any_online_cpu(*new_mask), &req)) {
+	if (migrate_task(p, cpumask_any_and(cpu_online_mask, new_mask), &req)) {
 		/* Need help from migration thread: drop lock and wait. */
 		task_rq_unlock(rq, &flags);
 		wake_up_process(rq->migration_thread);
@@ -6106,7 +6234,7 @@ static int __migrate_task(struct task_struct *p, int src_cpu, int dest_cpu)
 	if (task_cpu(p) != src_cpu)
 		goto done;
 	/* Affinity changed (again). */
-	if (!cpu_isset(dest_cpu, p->cpus_allowed))
+	if (!cpumask_test_cpu(dest_cpu, &p->cpus_allowed))
 		goto fail;
 
 	on_rq = p->se.on_rq;
@@ -6203,50 +6331,41 @@ static int __migrate_task_irq(struct task_struct *p, int src_cpu, int dest_cpu)
  */
 static void move_task_off_dead_cpu(int dead_cpu, struct task_struct *p)
 {
-	unsigned long flags;
-	cpumask_t mask;
-	struct rq *rq;
 	int dest_cpu;
+	const struct cpumask *nodemask = cpumask_of_node(cpu_to_node(dead_cpu));
 
-	do {
-		/* On same node? */
-		mask = node_to_cpumask(cpu_to_node(dead_cpu));
-		cpus_and(mask, mask, p->cpus_allowed);
-		dest_cpu = any_online_cpu(mask);
+again:
+	/* Look for allowed, online CPU in same node. */
+	for_each_cpu_and(dest_cpu, nodemask, cpu_online_mask)
+		if (cpumask_test_cpu(dest_cpu, &p->cpus_allowed))
+			goto move;
 
-		/* On any allowed CPU? */
-		if (dest_cpu >= nr_cpu_ids)
-			dest_cpu = any_online_cpu(p->cpus_allowed);
+	/* Any allowed, online CPU? */
+	dest_cpu = cpumask_any_and(&p->cpus_allowed, cpu_online_mask);
+	if (dest_cpu < nr_cpu_ids)
+		goto move;
 
-		/* No more Mr. Nice Guy. */
-		if (dest_cpu >= nr_cpu_ids) {
-			cpumask_t cpus_allowed;
+	/* No more Mr. Nice Guy. */
+	if (dest_cpu >= nr_cpu_ids) {
+		cpuset_cpus_allowed_locked(p, &p->cpus_allowed);
+		dest_cpu = cpumask_any_and(cpu_online_mask, &p->cpus_allowed);
 
-			cpuset_cpus_allowed_locked(p, &cpus_allowed);
-			/*
-			 * Try to stay on the same cpuset, where the
-			 * current cpuset may be a subset of all cpus.
-			 * The cpuset_cpus_allowed_locked() variant of
-			 * cpuset_cpus_allowed() will not block. It must be
-			 * called within calls to cpuset_lock/cpuset_unlock.
-			 */
-			rq = task_rq_lock(p, &flags);
-			p->cpus_allowed = cpus_allowed;
-			dest_cpu = any_online_cpu(p->cpus_allowed);
-			task_rq_unlock(rq, &flags);
-
-			/*
-			 * Don't tell them about moving exiting tasks or
-			 * kernel threads (both mm NULL), since they never
-			 * leave kernel.
-			 */
-			if (p->mm && printk_ratelimit()) {
-				printk(KERN_INFO "process %d (%s) no "
-				       "longer affine to cpu%d\n",
-					task_pid_nr(p), p->comm, dead_cpu);
-			}
+		/*
+		 * Don't tell them about moving exiting tasks or
+		 * kernel threads (both mm NULL), since they never
+		 * leave kernel.
+		 */
+		if (p->mm && printk_ratelimit()) {
+			printk(KERN_INFO "process %d (%s) no "
+			       "longer affine to cpu%d\n",
+			       task_pid_nr(p), p->comm, dead_cpu);
 		}
-	} while (!__migrate_task_irq(p, dead_cpu, dest_cpu));
+	}
+
+move:
+	/* It can have affinity changed while we were choosing. */
+	if (unlikely(!__migrate_task_irq(p, dead_cpu, dest_cpu)))
+		goto again;
 }
 
 /*
@@ -6258,7 +6377,7 @@ static void move_task_off_dead_cpu(int dead_cpu, struct task_struct *p)
  */
 static void migrate_nr_uninterruptible(struct rq *rq_src)
 {
-	struct rq *rq_dest = cpu_rq(any_online_cpu(*CPU_MASK_ALL_PTR));
+	struct rq *rq_dest = cpu_rq(cpumask_any(cpu_online_mask));
 	unsigned long flags;
 
 	local_irq_save(flags);
@@ -6548,7 +6667,7 @@ static void set_rq_online(struct rq *rq)
 	if (!rq->online) {
 		const struct sched_class *class;
 
-		cpu_set(rq->cpu, rq->rd->online);
+		cpumask_set_cpu(rq->cpu, rq->rd->online);
 		rq->online = 1;
 
 		for_each_class(class) {
@@ -6568,7 +6687,7 @@ static void set_rq_offline(struct rq *rq)
 				class->rq_offline(rq);
 		}
 
-		cpu_clear(rq->cpu, rq->rd->online);
+		cpumask_clear_cpu(rq->cpu, rq->rd->online);
 		rq->online = 0;
 	}
 }
@@ -6609,7 +6728,7 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu)
 		rq = cpu_rq(cpu);
 		spin_lock_irqsave(&rq->lock, flags);
 		if (rq->rd) {
-			BUG_ON(!cpu_isset(cpu, rq->rd->span));
+			BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span));
 
 			set_rq_online(rq);
 		}
@@ -6623,7 +6742,7 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu)
 			break;
 		/* Unbind it from offline cpu so it can run. Fall thru. */
 		kthread_bind(cpu_rq(cpu)->migration_thread,
-			     any_online_cpu(cpu_online_map));
+			     cpumask_any(cpu_online_mask));
 		kthread_stop(cpu_rq(cpu)->migration_thread);
 		cpu_rq(cpu)->migration_thread = NULL;
 		break;
@@ -6673,7 +6792,7 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu)
 		rq = cpu_rq(cpu);
 		spin_lock_irqsave(&rq->lock, flags);
 		if (rq->rd) {
-			BUG_ON(!cpu_isset(cpu, rq->rd->span));
+			BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span));
 			set_rq_offline(rq);
 		}
 		spin_unlock_irqrestore(&rq->lock, flags);
@@ -6712,13 +6831,13 @@ early_initcall(migration_init);
 #ifdef CONFIG_SCHED_DEBUG
 
 static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level,
-				  cpumask_t *groupmask)
+				  struct cpumask *groupmask)
 {
 	struct sched_group *group = sd->groups;
 	char str[256];
 
-	cpulist_scnprintf(str, sizeof(str), sd->span);
-	cpus_clear(*groupmask);
+	cpulist_scnprintf(str, sizeof(str), sched_domain_span(sd));
+	cpumask_clear(groupmask);
 
 	printk(KERN_DEBUG "%*s domain %d: ", level, "", level);
 
@@ -6732,11 +6851,11 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level,
 
 	printk(KERN_CONT "span %s level %s\n", str, sd->name);
 
-	if (!cpu_isset(cpu, sd->span)) {
+	if (!cpumask_test_cpu(cpu, sched_domain_span(sd))) {
 		printk(KERN_ERR "ERROR: domain->span does not contain "
 				"CPU%d\n", cpu);
 	}
-	if (!cpu_isset(cpu, group->cpumask)) {
+	if (!cpumask_test_cpu(cpu, sched_group_cpus(group))) {
 		printk(KERN_ERR "ERROR: domain->groups does not contain"
 				" CPU%d\n", cpu);
 	}
@@ -6756,31 +6875,32 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level,
 			break;
 		}
 
-		if (!cpus_weight(group->cpumask)) {
+		if (!cpumask_weight(sched_group_cpus(group))) {
 			printk(KERN_CONT "\n");
 			printk(KERN_ERR "ERROR: empty group\n");
 			break;
 		}
 
-		if (cpus_intersects(*groupmask, group->cpumask)) {
+		if (cpumask_intersects(groupmask, sched_group_cpus(group))) {
 			printk(KERN_CONT "\n");
 			printk(KERN_ERR "ERROR: repeated CPUs\n");
 			break;
 		}
 
-		cpus_or(*groupmask, *groupmask, group->cpumask);
+		cpumask_or(groupmask, groupmask, sched_group_cpus(group));
 
-		cpulist_scnprintf(str, sizeof(str), group->cpumask);
+		cpulist_scnprintf(str, sizeof(str), sched_group_cpus(group));
 		printk(KERN_CONT " %s", str);
 
 		group = group->next;
 	} while (group != sd->groups);
 	printk(KERN_CONT "\n");
 
-	if (!cpus_equal(sd->span, *groupmask))
+	if (!cpumask_equal(sched_domain_span(sd), groupmask))
 		printk(KERN_ERR "ERROR: groups don't span domain->span\n");
 
-	if (sd->parent && !cpus_subset(*groupmask, sd->parent->span))
+	if (sd->parent &&
+	    !cpumask_subset(groupmask, sched_domain_span(sd->parent)))
 		printk(KERN_ERR "ERROR: parent span is not a superset "
 			"of domain->span\n");
 	return 0;
@@ -6788,7 +6908,7 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level,
 
 static void sched_domain_debug(struct sched_domain *sd, int cpu)
 {
-	cpumask_t *groupmask;
+	cpumask_var_t groupmask;
 	int level = 0;
 
 	if (!sd) {
@@ -6798,8 +6918,7 @@ static void sched_domain_debug(struct sched_domain *sd, int cpu)
 
 	printk(KERN_DEBUG "CPU%d attaching sched-domain:\n", cpu);
 
-	groupmask = kmalloc(sizeof(cpumask_t), GFP_KERNEL);
-	if (!groupmask) {
+	if (!alloc_cpumask_var(&groupmask, GFP_KERNEL)) {
 		printk(KERN_DEBUG "Cannot load-balance (out of memory)\n");
 		return;
 	}
@@ -6812,7 +6931,7 @@ static void sched_domain_debug(struct sched_domain *sd, int cpu)
 		if (!sd)
 			break;
 	}
-	kfree(groupmask);
+	free_cpumask_var(groupmask);
 }
 #else /* !CONFIG_SCHED_DEBUG */
 # define sched_domain_debug(sd, cpu) do { } while (0)
@@ -6820,7 +6939,7 @@ static void sched_domain_debug(struct sched_domain *sd, int cpu)
 
 static int sd_degenerate(struct sched_domain *sd)
 {
-	if (cpus_weight(sd->span) == 1)
+	if (cpumask_weight(sched_domain_span(sd)) == 1)
 		return 1;
 
 	/* Following flags need at least 2 groups */
@@ -6851,7 +6970,7 @@ sd_parent_degenerate(struct sched_domain *sd, struct sched_domain *parent)
 	if (sd_degenerate(parent))
 		return 1;
 
-	if (!cpus_equal(sd->span, parent->span))
+	if (!cpumask_equal(sched_domain_span(sd), sched_domain_span(parent)))
 		return 0;
 
 	/* Does parent contain flags not in child? */
@@ -6875,6 +6994,16 @@ sd_parent_degenerate(struct sched_domain *sd, struct sched_domain *parent)
 	return 1;
 }
 
+static void free_rootdomain(struct root_domain *rd)
+{
+	cpupri_cleanup(&rd->cpupri);
+
+	free_cpumask_var(rd->rto_mask);
+	free_cpumask_var(rd->online);
+	free_cpumask_var(rd->span);
+	kfree(rd);
+}
+
 static void rq_attach_root(struct rq *rq, struct root_domain *rd)
 {
 	unsigned long flags;
@@ -6884,38 +7013,62 @@ static void rq_attach_root(struct rq *rq, struct root_domain *rd)
 	if (rq->rd) {
 		struct root_domain *old_rd = rq->rd;
 
-		if (cpu_isset(rq->cpu, old_rd->online))
+		if (cpumask_test_cpu(rq->cpu, old_rd->online))
 			set_rq_offline(rq);
 
-		cpu_clear(rq->cpu, old_rd->span);
+		cpumask_clear_cpu(rq->cpu, old_rd->span);
 
 		if (atomic_dec_and_test(&old_rd->refcount))
-			kfree(old_rd);
+			free_rootdomain(old_rd);
 	}
 
 	atomic_inc(&rd->refcount);
 	rq->rd = rd;
 
-	cpu_set(rq->cpu, rd->span);
-	if (cpu_isset(rq->cpu, cpu_online_map))
+	cpumask_set_cpu(rq->cpu, rd->span);
+	if (cpumask_test_cpu(rq->cpu, cpu_online_mask))
 		set_rq_online(rq);
 
 	spin_unlock_irqrestore(&rq->lock, flags);
 }
 
-static void init_rootdomain(struct root_domain *rd)
+static int __init_refok init_rootdomain(struct root_domain *rd, bool bootmem)
 {
 	memset(rd, 0, sizeof(*rd));
 
-	cpus_clear(rd->span);
-	cpus_clear(rd->online);
+	if (bootmem) {
+		alloc_bootmem_cpumask_var(&def_root_domain.span);
+		alloc_bootmem_cpumask_var(&def_root_domain.online);
+		alloc_bootmem_cpumask_var(&def_root_domain.rto_mask);
+		cpupri_init(&rd->cpupri, true);
+		return 0;
+	}
 
-	cpupri_init(&rd->cpupri);
+	if (!alloc_cpumask_var(&rd->span, GFP_KERNEL))
+		goto out;
+	if (!alloc_cpumask_var(&rd->online, GFP_KERNEL))
+		goto free_span;
+	if (!alloc_cpumask_var(&rd->rto_mask, GFP_KERNEL))
+		goto free_online;
+
+	if (cpupri_init(&rd->cpupri, false) != 0)
+		goto free_rto_mask;
+	return 0;
+
+free_rto_mask:
+	free_cpumask_var(rd->rto_mask);
+free_online:
+	free_cpumask_var(rd->online);
+free_span:
+	free_cpumask_var(rd->span);
+out:
+	return -ENOMEM;
 }
 
 static void init_defrootdomain(void)
 {
-	init_rootdomain(&def_root_domain);
+	init_rootdomain(&def_root_domain, true);
+
 	atomic_set(&def_root_domain.refcount, 1);
 }
 
@@ -6927,7 +7080,10 @@ static struct root_domain *alloc_rootdomain(void)
 	if (!rd)
 		return NULL;
 
-	init_rootdomain(rd);
+	if (init_rootdomain(rd, false) != 0) {
+		kfree(rd);
+		return NULL;
+	}
 
 	return rd;
 }
@@ -6969,19 +7125,12 @@ cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu)
 }
 
 /* cpus with isolated domains */
-static cpumask_t cpu_isolated_map = CPU_MASK_NONE;
+static cpumask_var_t cpu_isolated_map;
 
 /* Setup the mask of cpus configured for isolated domains */
 static int __init isolated_cpu_setup(char *str)
 {
-	static int __initdata ints[NR_CPUS];
-	int i;
-
-	str = get_options(str, ARRAY_SIZE(ints), ints);
-	cpus_clear(cpu_isolated_map);
-	for (i = 1; i <= ints[0]; i++)
-		if (ints[i] < NR_CPUS)
-			cpu_set(ints[i], cpu_isolated_map);
+	cpulist_parse(str, cpu_isolated_map);
 	return 1;
 }
 
@@ -6990,42 +7139,43 @@ __setup("isolcpus=", isolated_cpu_setup);
 /*
  * init_sched_build_groups takes the cpumask we wish to span, and a pointer
  * to a function which identifies what group(along with sched group) a CPU
- * belongs to. The return value of group_fn must be a >= 0 and < NR_CPUS
- * (due to the fact that we keep track of groups covered with a cpumask_t).
+ * belongs to. The return value of group_fn must be a >= 0 and < nr_cpu_ids
+ * (due to the fact that we keep track of groups covered with a struct cpumask).
  *
  * init_sched_build_groups will build a circular linked list of the groups
  * covered by the given span, and will set each group's ->cpumask correctly,
  * and ->cpu_power to 0.
  */
 static void
-init_sched_build_groups(const cpumask_t *span, const cpumask_t *cpu_map,
-			int (*group_fn)(int cpu, const cpumask_t *cpu_map,
+init_sched_build_groups(const struct cpumask *span,
+			const struct cpumask *cpu_map,
+			int (*group_fn)(int cpu, const struct cpumask *cpu_map,
 					struct sched_group **sg,
-					cpumask_t *tmpmask),
-			cpumask_t *covered, cpumask_t *tmpmask)
+					struct cpumask *tmpmask),
+			struct cpumask *covered, struct cpumask *tmpmask)
 {
 	struct sched_group *first = NULL, *last = NULL;
 	int i;
 
-	cpus_clear(*covered);
+	cpumask_clear(covered);
 
-	for_each_cpu_mask_nr(i, *span) {
+	for_each_cpu(i, span) {
 		struct sched_group *sg;
 		int group = group_fn(i, cpu_map, &sg, tmpmask);
 		int j;
 
-		if (cpu_isset(i, *covered))
+		if (cpumask_test_cpu(i, covered))
 			continue;
 
-		cpus_clear(sg->cpumask);
+		cpumask_clear(sched_group_cpus(sg));
 		sg->__cpu_power = 0;
 
-		for_each_cpu_mask_nr(j, *span) {
+		for_each_cpu(j, span) {
 			if (group_fn(j, cpu_map, NULL, tmpmask) != group)
 				continue;
 
-			cpu_set(j, *covered);
-			cpu_set(j, sg->cpumask);
+			cpumask_set_cpu(j, covered);
+			cpumask_set_cpu(j, sched_group_cpus(sg));
 		}
 		if (!first)
 			first = sg;
@@ -7089,23 +7239,21 @@ static int find_next_best_node(int node, nodemask_t *used_nodes)
  * should be one that prevents unnecessary balancing, but also spreads tasks
  * out optimally.
  */
-static void sched_domain_node_span(int node, cpumask_t *span)
+static void sched_domain_node_span(int node, struct cpumask *span)
 {
 	nodemask_t used_nodes;
-	node_to_cpumask_ptr(nodemask, node);
 	int i;
 
-	cpus_clear(*span);
+	cpumask_clear(span);
 	nodes_clear(used_nodes);
 
-	cpus_or(*span, *span, *nodemask);
+	cpumask_or(span, span, cpumask_of_node(node));
 	node_set(node, used_nodes);
 
 	for (i = 1; i < SD_NODES_PER_DOMAIN; i++) {
 		int next_node = find_next_best_node(node, &used_nodes);
 
-		node_to_cpumask_ptr_next(nodemask, next_node);
-		cpus_or(*span, *span, *nodemask);
+		cpumask_or(span, span, cpumask_of_node(next_node));
 	}
 }
 #endif /* CONFIG_NUMA */
@@ -7113,18 +7261,33 @@ static void sched_domain_node_span(int node, cpumask_t *span)
 int sched_smt_power_savings = 0, sched_mc_power_savings = 0;
 
 /*
+ * The cpus mask in sched_group and sched_domain hangs off the end.
+ * FIXME: use cpumask_var_t or dynamic percpu alloc to avoid wasting space
+ * for nr_cpu_ids < CONFIG_NR_CPUS.
+ */
+struct static_sched_group {
+	struct sched_group sg;
+	DECLARE_BITMAP(cpus, CONFIG_NR_CPUS);
+};
+
+struct static_sched_domain {
+	struct sched_domain sd;
+	DECLARE_BITMAP(span, CONFIG_NR_CPUS);
+};
+
+/*
  * SMT sched-domains:
  */
 #ifdef CONFIG_SCHED_SMT
-static DEFINE_PER_CPU(struct sched_domain, cpu_domains);
-static DEFINE_PER_CPU(struct sched_group, sched_group_cpus);
+static DEFINE_PER_CPU(struct static_sched_domain, cpu_domains);
+static DEFINE_PER_CPU(struct static_sched_group, sched_group_cpus);
 
 static int
-cpu_to_cpu_group(int cpu, const cpumask_t *cpu_map, struct sched_group **sg,
-		 cpumask_t *unused)
+cpu_to_cpu_group(int cpu, const struct cpumask *cpu_map,
+		 struct sched_group **sg, struct cpumask *unused)
 {
 	if (sg)
-		*sg = &per_cpu(sched_group_cpus, cpu);
+		*sg = &per_cpu(sched_group_cpus, cpu).sg;
 	return cpu;
 }
 #endif /* CONFIG_SCHED_SMT */
@@ -7133,56 +7296,53 @@ cpu_to_cpu_group(int cpu, const cpumask_t *cpu_map, struct sched_group **sg,
  * multi-core sched-domains:
  */
 #ifdef CONFIG_SCHED_MC
-static DEFINE_PER_CPU(struct sched_domain, core_domains);
-static DEFINE_PER_CPU(struct sched_group, sched_group_core);
+static DEFINE_PER_CPU(struct static_sched_domain, core_domains);
+static DEFINE_PER_CPU(struct static_sched_group, sched_group_core);
 #endif /* CONFIG_SCHED_MC */
 
 #if defined(CONFIG_SCHED_MC) && defined(CONFIG_SCHED_SMT)
 static int
-cpu_to_core_group(int cpu, const cpumask_t *cpu_map, struct sched_group **sg,
-		  cpumask_t *mask)
+cpu_to_core_group(int cpu, const struct cpumask *cpu_map,
+		  struct sched_group **sg, struct cpumask *mask)
 {
 	int group;
 
-	*mask = per_cpu(cpu_sibling_map, cpu);
-	cpus_and(*mask, *mask, *cpu_map);
-	group = first_cpu(*mask);
+	cpumask_and(mask, &per_cpu(cpu_sibling_map, cpu), cpu_map);
+	group = cpumask_first(mask);
 	if (sg)
-		*sg = &per_cpu(sched_group_core, group);
+		*sg = &per_cpu(sched_group_core, group).sg;
 	return group;
 }
 #elif defined(CONFIG_SCHED_MC)
 static int
-cpu_to_core_group(int cpu, const cpumask_t *cpu_map, struct sched_group **sg,
-		  cpumask_t *unused)
+cpu_to_core_group(int cpu, const struct cpumask *cpu_map,
+		  struct sched_group **sg, struct cpumask *unused)
 {
 	if (sg)
-		*sg = &per_cpu(sched_group_core, cpu);
+		*sg = &per_cpu(sched_group_core, cpu).sg;
 	return cpu;
 }
 #endif
 
-static DEFINE_PER_CPU(struct sched_domain, phys_domains);
-static DEFINE_PER_CPU(struct sched_group, sched_group_phys);
+static DEFINE_PER_CPU(struct static_sched_domain, phys_domains);
+static DEFINE_PER_CPU(struct static_sched_group, sched_group_phys);
 
 static int
-cpu_to_phys_group(int cpu, const cpumask_t *cpu_map, struct sched_group **sg,
-		  cpumask_t *mask)
+cpu_to_phys_group(int cpu, const struct cpumask *cpu_map,
+		  struct sched_group **sg, struct cpumask *mask)
 {
 	int group;
 #ifdef CONFIG_SCHED_MC
-	*mask = cpu_coregroup_map(cpu);
-	cpus_and(*mask, *mask, *cpu_map);
-	group = first_cpu(*mask);
+	cpumask_and(mask, cpu_coregroup_mask(cpu), cpu_map);
+	group = cpumask_first(mask);
 #elif defined(CONFIG_SCHED_SMT)
-	*mask = per_cpu(cpu_sibling_map, cpu);
-	cpus_and(*mask, *mask, *cpu_map);
-	group = first_cpu(*mask);
+	cpumask_and(mask, &per_cpu(cpu_sibling_map, cpu), cpu_map);
+	group = cpumask_first(mask);
 #else
 	group = cpu;
 #endif
 	if (sg)
-		*sg = &per_cpu(sched_group_phys, group);
+		*sg = &per_cpu(sched_group_phys, group).sg;
 	return group;
 }
 
@@ -7196,19 +7356,19 @@ static DEFINE_PER_CPU(struct sched_domain, node_domains);
 static struct sched_group ***sched_group_nodes_bycpu;
 
 static DEFINE_PER_CPU(struct sched_domain, allnodes_domains);
-static DEFINE_PER_CPU(struct sched_group, sched_group_allnodes);
+static DEFINE_PER_CPU(struct static_sched_group, sched_group_allnodes);
 
-static int cpu_to_allnodes_group(int cpu, const cpumask_t *cpu_map,
-				 struct sched_group **sg, cpumask_t *nodemask)
+static int cpu_to_allnodes_group(int cpu, const struct cpumask *cpu_map,
+				 struct sched_group **sg,
+				 struct cpumask *nodemask)
 {
 	int group;
 
-	*nodemask = node_to_cpumask(cpu_to_node(cpu));
-	cpus_and(*nodemask, *nodemask, *cpu_map);
-	group = first_cpu(*nodemask);
+	cpumask_and(nodemask, cpumask_of_node(cpu_to_node(cpu)), cpu_map);
+	group = cpumask_first(nodemask);
 
 	if (sg)
-		*sg = &per_cpu(sched_group_allnodes, group);
+		*sg = &per_cpu(sched_group_allnodes, group).sg;
 	return group;
 }
 
@@ -7220,11 +7380,11 @@ static void init_numa_sched_groups_power(struct sched_group *group_head)
 	if (!sg)
 		return;
 	do {
-		for_each_cpu_mask_nr(j, sg->cpumask) {
+		for_each_cpu(j, sched_group_cpus(sg)) {
 			struct sched_domain *sd;
 
-			sd = &per_cpu(phys_domains, j);
-			if (j != first_cpu(sd->groups->cpumask)) {
+			sd = &per_cpu(phys_domains, j).sd;
+			if (j != cpumask_first(sched_group_cpus(sd->groups))) {
 				/*
 				 * Only add "power" once for each
 				 * physical package.
@@ -7241,11 +7401,12 @@ static void init_numa_sched_groups_power(struct sched_group *group_head)
 
 #ifdef CONFIG_NUMA
 /* Free memory allocated for various sched_group structures */
-static void free_sched_groups(const cpumask_t *cpu_map, cpumask_t *nodemask)
+static void free_sched_groups(const struct cpumask *cpu_map,
+			      struct cpumask *nodemask)
 {
 	int cpu, i;
 
-	for_each_cpu_mask_nr(cpu, *cpu_map) {
+	for_each_cpu(cpu, cpu_map) {
 		struct sched_group **sched_group_nodes
 			= sched_group_nodes_bycpu[cpu];
 
@@ -7255,9 +7416,8 @@ static void free_sched_groups(const cpumask_t *cpu_map, cpumask_t *nodemask)
 		for (i = 0; i < nr_node_ids; i++) {
 			struct sched_group *oldsg, *sg = sched_group_nodes[i];
 
-			*nodemask = node_to_cpumask(i);
-			cpus_and(*nodemask, *nodemask, *cpu_map);
-			if (cpus_empty(*nodemask))
+			cpumask_and(nodemask, cpumask_of_node(i), cpu_map);
+			if (cpumask_empty(nodemask))
 				continue;
 
 			if (sg == NULL)
@@ -7275,7 +7435,8 @@ next_sg:
 	}
 }
 #else /* !CONFIG_NUMA */
-static void free_sched_groups(const cpumask_t *cpu_map, cpumask_t *nodemask)
+static void free_sched_groups(const struct cpumask *cpu_map,
+			      struct cpumask *nodemask)
 {
 }
 #endif /* CONFIG_NUMA */
@@ -7301,7 +7462,7 @@ static void init_sched_groups_power(int cpu, struct sched_domain *sd)
 
 	WARN_ON(!sd || !sd->groups);
 
-	if (cpu != first_cpu(sd->groups->cpumask))
+	if (cpu != cpumask_first(sched_group_cpus(sd->groups)))
 		return;
 
 	child = sd->child;
@@ -7366,48 +7527,6 @@ SD_INIT_FUNC(CPU)
  SD_INIT_FUNC(MC)
 #endif
 
-/*
- * To minimize stack usage kmalloc room for cpumasks and share the
- * space as the usage in build_sched_domains() dictates.  Used only
- * if the amount of space is significant.
- */
-struct allmasks {
-	cpumask_t tmpmask;			/* make this one first */
-	union {
-		cpumask_t nodemask;
-		cpumask_t this_sibling_map;
-		cpumask_t this_core_map;
-	};
-	cpumask_t send_covered;
-
-#ifdef CONFIG_NUMA
-	cpumask_t domainspan;
-	cpumask_t covered;
-	cpumask_t notcovered;
-#endif
-};
-
-#if	NR_CPUS > 128
-#define SCHED_CPUMASK_DECLARE(v)	struct allmasks *v
-static inline void sched_cpumask_alloc(struct allmasks **masks)
-{
-	*masks = kmalloc(sizeof(**masks), GFP_KERNEL);
-}
-static inline void sched_cpumask_free(struct allmasks *masks)
-{
-	kfree(masks);
-}
-#else
-#define SCHED_CPUMASK_DECLARE(v)	struct allmasks _v, *v = &_v
-static inline void sched_cpumask_alloc(struct allmasks **masks)
-{ }
-static inline void sched_cpumask_free(struct allmasks *masks)
-{ }
-#endif
-
-#define	SCHED_CPUMASK_VAR(v, a) 	cpumask_t *v = (cpumask_t *) \
-			((unsigned long)(a) + offsetof(struct allmasks, v))
-
 static int default_relax_domain_level = -1;
 
 static int __init setup_relax_domain_level(char *str)
@@ -7447,17 +7566,38 @@ static void set_domain_attribute(struct sched_domain *sd,
  * Build sched domains for a given set of cpus and attach the sched domains
  * to the individual cpus
  */
-static int __build_sched_domains(const cpumask_t *cpu_map,
+static int __build_sched_domains(const struct cpumask *cpu_map,
 				 struct sched_domain_attr *attr)
 {
-	int i;
+	int i, err = -ENOMEM;
 	struct root_domain *rd;
-	SCHED_CPUMASK_DECLARE(allmasks);
-	cpumask_t *tmpmask;
+	cpumask_var_t nodemask, this_sibling_map, this_core_map, send_covered,
+		tmpmask;
 #ifdef CONFIG_NUMA
+	cpumask_var_t domainspan, covered, notcovered;
 	struct sched_group **sched_group_nodes = NULL;
 	int sd_allnodes = 0;
 
+	if (!alloc_cpumask_var(&domainspan, GFP_KERNEL))
+		goto out;
+	if (!alloc_cpumask_var(&covered, GFP_KERNEL))
+		goto free_domainspan;
+	if (!alloc_cpumask_var(&notcovered, GFP_KERNEL))
+		goto free_covered;
+#endif
+
+	if (!alloc_cpumask_var(&nodemask, GFP_KERNEL))
+		goto free_notcovered;
+	if (!alloc_cpumask_var(&this_sibling_map, GFP_KERNEL))
+		goto free_nodemask;
+	if (!alloc_cpumask_var(&this_core_map, GFP_KERNEL))
+		goto free_this_sibling_map;
+	if (!alloc_cpumask_var(&send_covered, GFP_KERNEL))
+		goto free_this_core_map;
+	if (!alloc_cpumask_var(&tmpmask, GFP_KERNEL))
+		goto free_send_covered;
+
+#ifdef CONFIG_NUMA
 	/*
 	 * Allocate the per-node list of sched groups
 	 */
@@ -7465,54 +7605,35 @@ static int __build_sched_domains(const cpumask_t *cpu_map,
 				    GFP_KERNEL);
 	if (!sched_group_nodes) {
 		printk(KERN_WARNING "Can not alloc sched group node list\n");
-		return -ENOMEM;
+		goto free_tmpmask;
 	}
 #endif
 
 	rd = alloc_rootdomain();
 	if (!rd) {
 		printk(KERN_WARNING "Cannot alloc root domain\n");
-#ifdef CONFIG_NUMA
-		kfree(sched_group_nodes);
-#endif
-		return -ENOMEM;
-	}
-
-	/* get space for all scratch cpumask variables */
-	sched_cpumask_alloc(&allmasks);
-	if (!allmasks) {
-		printk(KERN_WARNING "Cannot alloc cpumask array\n");
-		kfree(rd);
-#ifdef CONFIG_NUMA
-		kfree(sched_group_nodes);
-#endif
-		return -ENOMEM;
+		goto free_sched_groups;
 	}
 
-	tmpmask = (cpumask_t *)allmasks;
-
-
 #ifdef CONFIG_NUMA
-	sched_group_nodes_bycpu[first_cpu(*cpu_map)] = sched_group_nodes;
+	sched_group_nodes_bycpu[cpumask_first(cpu_map)] = sched_group_nodes;
 #endif
 
 	/*
 	 * Set up domains for cpus specified by the cpu_map.
 	 */
-	for_each_cpu_mask_nr(i, *cpu_map) {
+	for_each_cpu(i, cpu_map) {
 		struct sched_domain *sd = NULL, *p;
-		SCHED_CPUMASK_VAR(nodemask, allmasks);
 
-		*nodemask = node_to_cpumask(cpu_to_node(i));
-		cpus_and(*nodemask, *nodemask, *cpu_map);
+		cpumask_and(nodemask, cpumask_of_node(cpu_to_node(i)), cpu_map);
 
 #ifdef CONFIG_NUMA
-		if (cpus_weight(*cpu_map) >
-				SD_NODES_PER_DOMAIN*cpus_weight(*nodemask)) {
+		if (cpumask_weight(cpu_map) >
+				SD_NODES_PER_DOMAIN*cpumask_weight(nodemask)) {
 			sd = &per_cpu(allnodes_domains, i);
 			SD_INIT(sd, ALLNODES);
 			set_domain_attribute(sd, attr);
-			sd->span = *cpu_map;
+			cpumask_copy(sched_domain_span(sd), cpu_map);
 			cpu_to_allnodes_group(i, cpu_map, &sd->groups, tmpmask);
 			p = sd;
 			sd_allnodes = 1;
@@ -7522,18 +7643,19 @@ static int __build_sched_domains(const cpumask_t *cpu_map,
 		sd = &per_cpu(node_domains, i);
 		SD_INIT(sd, NODE);
 		set_domain_attribute(sd, attr);
-		sched_domain_node_span(cpu_to_node(i), &sd->span);
+		sched_domain_node_span(cpu_to_node(i), sched_domain_span(sd));
 		sd->parent = p;
 		if (p)
 			p->child = sd;
-		cpus_and(sd->span, sd->span, *cpu_map);
+		cpumask_and(sched_domain_span(sd),
+			    sched_domain_span(sd), cpu_map);
 #endif
 
 		p = sd;
-		sd = &per_cpu(phys_domains, i);
+		sd = &per_cpu(phys_domains, i).sd;
 		SD_INIT(sd, CPU);
 		set_domain_attribute(sd, attr);
-		sd->span = *nodemask;
+		cpumask_copy(sched_domain_span(sd), nodemask);
 		sd->parent = p;
 		if (p)
 			p->child = sd;
@@ -7541,11 +7663,11 @@ static int __build_sched_domains(const cpumask_t *cpu_map,
 
 #ifdef CONFIG_SCHED_MC
 		p = sd;
-		sd = &per_cpu(core_domains, i);
+		sd = &per_cpu(core_domains, i).sd;
 		SD_INIT(sd, MC);
 		set_domain_attribute(sd, attr);
-		sd->span = cpu_coregroup_map(i);
-		cpus_and(sd->span, sd->span, *cpu_map);
+		cpumask_and(sched_domain_span(sd), cpu_map,
+						   cpu_coregroup_mask(i));
 		sd->parent = p;
 		p->child = sd;
 		cpu_to_core_group(i, cpu_map, &sd->groups, tmpmask);
@@ -7553,11 +7675,11 @@ static int __build_sched_domains(const cpumask_t *cpu_map,
 
 #ifdef CONFIG_SCHED_SMT
 		p = sd;
-		sd = &per_cpu(cpu_domains, i);
+		sd = &per_cpu(cpu_domains, i).sd;
 		SD_INIT(sd, SIBLING);
 		set_domain_attribute(sd, attr);
-		sd->span = per_cpu(cpu_sibling_map, i);
-		cpus_and(sd->span, sd->span, *cpu_map);
+		cpumask_and(sched_domain_span(sd),
+			    &per_cpu(cpu_sibling_map, i), cpu_map);
 		sd->parent = p;
 		p->child = sd;
 		cpu_to_cpu_group(i, cpu_map, &sd->groups, tmpmask);
@@ -7566,13 +7688,10 @@ static int __build_sched_domains(const cpumask_t *cpu_map,
 
 #ifdef CONFIG_SCHED_SMT
 	/* Set up CPU (sibling) groups */
-	for_each_cpu_mask_nr(i, *cpu_map) {
-		SCHED_CPUMASK_VAR(this_sibling_map, allmasks);
-		SCHED_CPUMASK_VAR(send_covered, allmasks);
-
-		*this_sibling_map = per_cpu(cpu_sibling_map, i);
-		cpus_and(*this_sibling_map, *this_sibling_map, *cpu_map);
-		if (i != first_cpu(*this_sibling_map))
+	for_each_cpu(i, cpu_map) {
+		cpumask_and(this_sibling_map,
+			    &per_cpu(cpu_sibling_map, i), cpu_map);
+		if (i != cpumask_first(this_sibling_map))
 			continue;
 
 		init_sched_build_groups(this_sibling_map, cpu_map,
@@ -7583,13 +7702,9 @@ static int __build_sched_domains(const cpumask_t *cpu_map,
 
 #ifdef CONFIG_SCHED_MC
 	/* Set up multi-core groups */
-	for_each_cpu_mask_nr(i, *cpu_map) {
-		SCHED_CPUMASK_VAR(this_core_map, allmasks);
-		SCHED_CPUMASK_VAR(send_covered, allmasks);
-
-		*this_core_map = cpu_coregroup_map(i);
-		cpus_and(*this_core_map, *this_core_map, *cpu_map);
-		if (i != first_cpu(*this_core_map))
+	for_each_cpu(i, cpu_map) {
+		cpumask_and(this_core_map, cpu_coregroup_mask(i), cpu_map);
+		if (i != cpumask_first(this_core_map))
 			continue;
 
 		init_sched_build_groups(this_core_map, cpu_map,
@@ -7600,12 +7715,8 @@ static int __build_sched_domains(const cpumask_t *cpu_map,
 
 	/* Set up physical groups */
 	for (i = 0; i < nr_node_ids; i++) {
-		SCHED_CPUMASK_VAR(nodemask, allmasks);
-		SCHED_CPUMASK_VAR(send_covered, allmasks);
-
-		*nodemask = node_to_cpumask(i);
-		cpus_and(*nodemask, *nodemask, *cpu_map);
-		if (cpus_empty(*nodemask))
+		cpumask_and(nodemask, cpumask_of_node(i), cpu_map);
+		if (cpumask_empty(nodemask))
 			continue;
 
 		init_sched_build_groups(nodemask, cpu_map,
@@ -7616,8 +7727,6 @@ static int __build_sched_domains(const cpumask_t *cpu_map,
 #ifdef CONFIG_NUMA
 	/* Set up node groups */
 	if (sd_allnodes) {
-		SCHED_CPUMASK_VAR(send_covered, allmasks);
-
 		init_sched_build_groups(cpu_map, cpu_map,
 					&cpu_to_allnodes_group,
 					send_covered, tmpmask);
@@ -7626,58 +7735,53 @@ static int __build_sched_domains(const cpumask_t *cpu_map,
 	for (i = 0; i < nr_node_ids; i++) {
 		/* Set up node groups */
 		struct sched_group *sg, *prev;
-		SCHED_CPUMASK_VAR(nodemask, allmasks);
-		SCHED_CPUMASK_VAR(domainspan, allmasks);
-		SCHED_CPUMASK_VAR(covered, allmasks);
 		int j;
 
-		*nodemask = node_to_cpumask(i);
-		cpus_clear(*covered);
-
-		cpus_and(*nodemask, *nodemask, *cpu_map);
-		if (cpus_empty(*nodemask)) {
+		cpumask_clear(covered);
+		cpumask_and(nodemask, cpumask_of_node(i), cpu_map);
+		if (cpumask_empty(nodemask)) {
 			sched_group_nodes[i] = NULL;
 			continue;
 		}
 
 		sched_domain_node_span(i, domainspan);
-		cpus_and(*domainspan, *domainspan, *cpu_map);
+		cpumask_and(domainspan, domainspan, cpu_map);
 
-		sg = kmalloc_node(sizeof(struct sched_group), GFP_KERNEL, i);
+		sg = kmalloc_node(sizeof(struct sched_group) + cpumask_size(),
+				  GFP_KERNEL, i);
 		if (!sg) {
 			printk(KERN_WARNING "Can not alloc domain group for "
 				"node %d\n", i);
 			goto error;
 		}
 		sched_group_nodes[i] = sg;
-		for_each_cpu_mask_nr(j, *nodemask) {
+		for_each_cpu(j, nodemask) {
 			struct sched_domain *sd;
 
 			sd = &per_cpu(node_domains, j);
 			sd->groups = sg;
 		}
 		sg->__cpu_power = 0;
-		sg->cpumask = *nodemask;
+		cpumask_copy(sched_group_cpus(sg), nodemask);
 		sg->next = sg;
-		cpus_or(*covered, *covered, *nodemask);
+		cpumask_or(covered, covered, nodemask);
 		prev = sg;
 
 		for (j = 0; j < nr_node_ids; j++) {
-			SCHED_CPUMASK_VAR(notcovered, allmasks);
 			int n = (i + j) % nr_node_ids;
-			node_to_cpumask_ptr(pnodemask, n);
 
-			cpus_complement(*notcovered, *covered);
-			cpus_and(*tmpmask, *notcovered, *cpu_map);
-			cpus_and(*tmpmask, *tmpmask, *domainspan);
-			if (cpus_empty(*tmpmask))
+			cpumask_complement(notcovered, covered);
+			cpumask_and(tmpmask, notcovered, cpu_map);
+			cpumask_and(tmpmask, tmpmask, domainspan);
+			if (cpumask_empty(tmpmask))
 				break;
 
-			cpus_and(*tmpmask, *tmpmask, *pnodemask);
-			if (cpus_empty(*tmpmask))
+			cpumask_and(tmpmask, tmpmask, cpumask_of_node(n));
+			if (cpumask_empty(tmpmask))
 				continue;
 
-			sg = kmalloc_node(sizeof(struct sched_group),
+			sg = kmalloc_node(sizeof(struct sched_group) +
+					  cpumask_size(),
 					  GFP_KERNEL, i);
 			if (!sg) {
 				printk(KERN_WARNING
@@ -7685,9 +7789,9 @@ static int __build_sched_domains(const cpumask_t *cpu_map,
 				goto error;
 			}
 			sg->__cpu_power = 0;
-			sg->cpumask = *tmpmask;
+			cpumask_copy(sched_group_cpus(sg), tmpmask);
 			sg->next = prev->next;
-			cpus_or(*covered, *covered, *tmpmask);
+			cpumask_or(covered, covered, tmpmask);
 			prev->next = sg;
 			prev = sg;
 		}
@@ -7696,22 +7800,22 @@ static int __build_sched_domains(const cpumask_t *cpu_map,
 
 	/* Calculate CPU power for physical packages and nodes */
 #ifdef CONFIG_SCHED_SMT
-	for_each_cpu_mask_nr(i, *cpu_map) {
-		struct sched_domain *sd = &per_cpu(cpu_domains, i);
+	for_each_cpu(i, cpu_map) {
+		struct sched_domain *sd = &per_cpu(cpu_domains, i).sd;
 
 		init_sched_groups_power(i, sd);
 	}
 #endif
 #ifdef CONFIG_SCHED_MC
-	for_each_cpu_mask_nr(i, *cpu_map) {
-		struct sched_domain *sd = &per_cpu(core_domains, i);
+	for_each_cpu(i, cpu_map) {
+		struct sched_domain *sd = &per_cpu(core_domains, i).sd;
 
 		init_sched_groups_power(i, sd);
 	}
 #endif
 
-	for_each_cpu_mask_nr(i, *cpu_map) {
-		struct sched_domain *sd = &per_cpu(phys_domains, i);
+	for_each_cpu(i, cpu_map) {
+		struct sched_domain *sd = &per_cpu(phys_domains, i).sd;
 
 		init_sched_groups_power(i, sd);
 	}
@@ -7723,53 +7827,78 @@ static int __build_sched_domains(const cpumask_t *cpu_map,
 	if (sd_allnodes) {
 		struct sched_group *sg;
 
-		cpu_to_allnodes_group(first_cpu(*cpu_map), cpu_map, &sg,
+		cpu_to_allnodes_group(cpumask_first(cpu_map), cpu_map, &sg,
 								tmpmask);
 		init_numa_sched_groups_power(sg);
 	}
 #endif
 
 	/* Attach the domains */
-	for_each_cpu_mask_nr(i, *cpu_map) {
+	for_each_cpu(i, cpu_map) {
 		struct sched_domain *sd;
 #ifdef CONFIG_SCHED_SMT
-		sd = &per_cpu(cpu_domains, i);
+		sd = &per_cpu(cpu_domains, i).sd;
 #elif defined(CONFIG_SCHED_MC)
-		sd = &per_cpu(core_domains, i);
+		sd = &per_cpu(core_domains, i).sd;
 #else
-		sd = &per_cpu(phys_domains, i);
+		sd = &per_cpu(phys_domains, i).sd;
 #endif
 		cpu_attach_domain(sd, rd, i);
 	}
 
-	sched_cpumask_free(allmasks);
-	return 0;
+	err = 0;
+
+free_tmpmask:
+	free_cpumask_var(tmpmask);
+free_send_covered:
+	free_cpumask_var(send_covered);
+free_this_core_map:
+	free_cpumask_var(this_core_map);
+free_this_sibling_map:
+	free_cpumask_var(this_sibling_map);
+free_nodemask:
+	free_cpumask_var(nodemask);
+free_notcovered:
+#ifdef CONFIG_NUMA
+	free_cpumask_var(notcovered);
+free_covered:
+	free_cpumask_var(covered);
+free_domainspan:
+	free_cpumask_var(domainspan);
+out:
+#endif
+	return err;
+
+free_sched_groups:
+#ifdef CONFIG_NUMA
+	kfree(sched_group_nodes);
+#endif
+	goto free_tmpmask;
 
 #ifdef CONFIG_NUMA
 error:
 	free_sched_groups(cpu_map, tmpmask);
-	sched_cpumask_free(allmasks);
-	kfree(rd);
-	return -ENOMEM;
+	free_rootdomain(rd);
+	goto free_tmpmask;
 #endif
 }
 
-static int build_sched_domains(const cpumask_t *cpu_map)
+static int build_sched_domains(const struct cpumask *cpu_map)
 {
 	return __build_sched_domains(cpu_map, NULL);
 }
 
-static cpumask_t *doms_cur;	/* current sched domains */
+static struct cpumask *doms_cur;	/* current sched domains */
 static int ndoms_cur;		/* number of sched domains in 'doms_cur' */
 static struct sched_domain_attr *dattr_cur;
 				/* attribues of custom domains in 'doms_cur' */
 
 /*
  * Special case: If a kmalloc of a doms_cur partition (array of
- * cpumask_t) fails, then fallback to a single sched domain,
- * as determined by the single cpumask_t fallback_doms.
+ * cpumask) fails, then fallback to a single sched domain,
+ * as determined by the single cpumask fallback_doms.
  */
-static cpumask_t fallback_doms;
+static cpumask_var_t fallback_doms;
 
 /*
  * arch_update_cpu_topology lets virtualized architectures update the
@@ -7786,16 +7915,16 @@ int __attribute__((weak)) arch_update_cpu_topology(void)
  * For now this just excludes isolated cpus, but could be used to
  * exclude other special cases in the future.
  */
-static int arch_init_sched_domains(const cpumask_t *cpu_map)
+static int arch_init_sched_domains(const struct cpumask *cpu_map)
 {
 	int err;
 
 	arch_update_cpu_topology();
 	ndoms_cur = 1;
-	doms_cur = kmalloc(sizeof(cpumask_t), GFP_KERNEL);
+	doms_cur = kmalloc(cpumask_size(), GFP_KERNEL);
 	if (!doms_cur)
-		doms_cur = &fallback_doms;
-	cpus_andnot(*doms_cur, *cpu_map, cpu_isolated_map);
+		doms_cur = fallback_doms;
+	cpumask_andnot(doms_cur, cpu_map, cpu_isolated_map);
 	dattr_cur = NULL;
 	err = build_sched_domains(doms_cur);
 	register_sched_domain_sysctl();
@@ -7803,8 +7932,8 @@ static int arch_init_sched_domains(const cpumask_t *cpu_map)
 	return err;
 }
 
-static void arch_destroy_sched_domains(const cpumask_t *cpu_map,
-				       cpumask_t *tmpmask)
+static void arch_destroy_sched_domains(const struct cpumask *cpu_map,
+				       struct cpumask *tmpmask)
 {
 	free_sched_groups(cpu_map, tmpmask);
 }
@@ -7813,15 +7942,16 @@ static void arch_destroy_sched_domains(const cpumask_t *cpu_map,
  * Detach sched domains from a group of cpus specified in cpu_map
  * These cpus will now be attached to the NULL domain
  */
-static void detach_destroy_domains(const cpumask_t *cpu_map)
+static void detach_destroy_domains(const struct cpumask *cpu_map)
 {
-	cpumask_t tmpmask;
+	/* Save because hotplug lock held. */
+	static DECLARE_BITMAP(tmpmask, CONFIG_NR_CPUS);
 	int i;
 
-	for_each_cpu_mask_nr(i, *cpu_map)
+	for_each_cpu(i, cpu_map)
 		cpu_attach_domain(NULL, &def_root_domain, i);
 	synchronize_sched();
-	arch_destroy_sched_domains(cpu_map, &tmpmask);
+	arch_destroy_sched_domains(cpu_map, to_cpumask(tmpmask));
 }
 
 /* handle null as "default" */
@@ -7846,7 +7976,7 @@ static int dattrs_equal(struct sched_domain_attr *cur, int idx_cur,
  * doms_new[] to the current sched domain partitioning, doms_cur[].
  * It destroys each deleted domain and builds each new domain.
  *
- * 'doms_new' is an array of cpumask_t's of length 'ndoms_new'.
+ * 'doms_new' is an array of cpumask's of length 'ndoms_new'.
  * The masks don't intersect (don't overlap.) We should setup one
  * sched domain for each mask. CPUs not in any of the cpumasks will
  * not be load balanced. If the same cpumask appears both in the
@@ -7860,13 +7990,14 @@ static int dattrs_equal(struct sched_domain_attr *cur, int idx_cur,
  * the single partition 'fallback_doms', it also forces the domains
  * to be rebuilt.
  *
- * If doms_new == NULL it will be replaced with cpu_online_map.
+ * If doms_new == NULL it will be replaced with cpu_online_mask.
  * ndoms_new == 0 is a special case for destroying existing domains,
  * and it will not create the default domain.
  *
  * Call with hotplug lock held
  */
-void partition_sched_domains(int ndoms_new, cpumask_t *doms_new,
+/* FIXME: Change to struct cpumask *doms_new[] */
+void partition_sched_domains(int ndoms_new, struct cpumask *doms_new,
 			     struct sched_domain_attr *dattr_new)
 {
 	int i, j, n;
@@ -7885,7 +8016,7 @@ void partition_sched_domains(int ndoms_new, cpumask_t *doms_new,
 	/* Destroy deleted domains */
 	for (i = 0; i < ndoms_cur; i++) {
 		for (j = 0; j < n && !new_topology; j++) {
-			if (cpus_equal(doms_cur[i], doms_new[j])
+			if (cpumask_equal(&doms_cur[i], &doms_new[j])
 			    && dattrs_equal(dattr_cur, i, dattr_new, j))
 				goto match1;
 		}
@@ -7897,15 +8028,15 @@ match1:
 
 	if (doms_new == NULL) {
 		ndoms_cur = 0;
-		doms_new = &fallback_doms;
-		cpus_andnot(doms_new[0], cpu_online_map, cpu_isolated_map);
+		doms_new = fallback_doms;
+		cpumask_andnot(&doms_new[0], cpu_online_mask, cpu_isolated_map);
 		WARN_ON_ONCE(dattr_new);
 	}
 
 	/* Build new domains */
 	for (i = 0; i < ndoms_new; i++) {
 		for (j = 0; j < ndoms_cur && !new_topology; j++) {
-			if (cpus_equal(doms_new[i], doms_cur[j])
+			if (cpumask_equal(&doms_new[i], &doms_cur[j])
 			    && dattrs_equal(dattr_new, i, dattr_cur, j))
 				goto match2;
 		}
@@ -7917,7 +8048,7 @@ match2:
 	}
 
 	/* Remember the new sched domains */
-	if (doms_cur != &fallback_doms)
+	if (doms_cur != fallback_doms)
 		kfree(doms_cur);
 	kfree(dattr_cur);	/* kfree(NULL) is safe */
 	doms_cur = doms_new;
@@ -7930,7 +8061,7 @@ match2:
 }
 
 #if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT)
-int arch_reinit_sched_domains(void)
+static void arch_reinit_sched_domains(void)
 {
 	get_online_cpus();
 
@@ -7939,25 +8070,33 @@ int arch_reinit_sched_domains(void)
 
 	rebuild_sched_domains();
 	put_online_cpus();
-
-	return 0;
 }
 
 static ssize_t sched_power_savings_store(const char *buf, size_t count, int smt)
 {
-	int ret;
+	unsigned int level = 0;
+
+	if (sscanf(buf, "%u", &level) != 1)
+		return -EINVAL;
+
+	/*
+	 * level is always be positive so don't check for
+	 * level < POWERSAVINGS_BALANCE_NONE which is 0
+	 * What happens on 0 or 1 byte write,
+	 * need to check for count as well?
+	 */
 
-	if (buf[0] != '0' && buf[0] != '1')
+	if (level >= MAX_POWERSAVINGS_BALANCE_LEVELS)
 		return -EINVAL;
 
 	if (smt)
-		sched_smt_power_savings = (buf[0] == '1');
+		sched_smt_power_savings = level;
 	else
-		sched_mc_power_savings = (buf[0] == '1');
+		sched_mc_power_savings = level;
 
-	ret = arch_reinit_sched_domains();
+	arch_reinit_sched_domains();
 
-	return ret ? ret : count;
+	return count;
 }
 
 #ifdef CONFIG_SCHED_MC
@@ -7992,7 +8131,7 @@ static SYSDEV_CLASS_ATTR(sched_smt_power_savings, 0644,
 		   sched_smt_power_savings_store);
 #endif
 
-int sched_create_sysfs_power_savings_entries(struct sysdev_class *cls)
+int __init sched_create_sysfs_power_savings_entries(struct sysdev_class *cls)
 {
 	int err = 0;
 
@@ -8057,7 +8196,9 @@ static int update_runtime(struct notifier_block *nfb,
 
 void __init sched_init_smp(void)
 {
-	cpumask_t non_isolated_cpus;
+	cpumask_var_t non_isolated_cpus;
+
+	alloc_cpumask_var(&non_isolated_cpus, GFP_KERNEL);
 
 #if defined(CONFIG_NUMA)
 	sched_group_nodes_bycpu = kzalloc(nr_cpu_ids * sizeof(void **),
@@ -8066,10 +8207,10 @@ void __init sched_init_smp(void)
 #endif
 	get_online_cpus();
 	mutex_lock(&sched_domains_mutex);
-	arch_init_sched_domains(&cpu_online_map);
-	cpus_andnot(non_isolated_cpus, cpu_possible_map, cpu_isolated_map);
-	if (cpus_empty(non_isolated_cpus))
-		cpu_set(smp_processor_id(), non_isolated_cpus);
+	arch_init_sched_domains(cpu_online_mask);
+	cpumask_andnot(non_isolated_cpus, cpu_possible_mask, cpu_isolated_map);
+	if (cpumask_empty(non_isolated_cpus))
+		cpumask_set_cpu(smp_processor_id(), non_isolated_cpus);
 	mutex_unlock(&sched_domains_mutex);
 	put_online_cpus();
 
@@ -8084,9 +8225,13 @@ void __init sched_init_smp(void)
 	init_hrtick();
 
 	/* Move init over to a non-isolated CPU */
-	if (set_cpus_allowed_ptr(current, &non_isolated_cpus) < 0)
+	if (set_cpus_allowed_ptr(current, non_isolated_cpus) < 0)
 		BUG();
 	sched_init_granularity();
+	free_cpumask_var(non_isolated_cpus);
+
+	alloc_cpumask_var(&fallback_doms, GFP_KERNEL);
+	init_sched_rt_class();
 }
 #else
 void __init sched_init_smp(void)
@@ -8401,6 +8546,15 @@ void __init sched_init(void)
 	 */
 	current->sched_class = &fair_sched_class;
 
+	/* Allocate the nohz_cpu_mask if CONFIG_CPUMASK_OFFSTACK */
+	alloc_bootmem_cpumask_var(&nohz_cpu_mask);
+#ifdef CONFIG_SMP
+#ifdef CONFIG_NO_HZ
+	alloc_bootmem_cpumask_var(&nohz.cpu_mask);
+#endif
+	alloc_bootmem_cpumask_var(&cpu_isolated_map);
+#endif /* SMP */
+
 	scheduler_running = 1;
 }
 
diff --git a/kernel/sched_clock.c b/kernel/sched_clock.c
index e8ab096ddfe3..a0b0852414cc 100644
--- a/kernel/sched_clock.c
+++ b/kernel/sched_clock.c
@@ -124,7 +124,7 @@ static u64 __update_sched_clock(struct sched_clock_data *scd, u64 now)
 
 	clock = scd->tick_gtod + delta;
 	min_clock = wrap_max(scd->tick_gtod, scd->clock);
-	max_clock = scd->tick_gtod + TICK_NSEC;
+	max_clock = wrap_max(scd->clock, scd->tick_gtod + TICK_NSEC);
 
 	clock = wrap_max(clock, min_clock);
 	clock = wrap_min(clock, max_clock);
@@ -227,6 +227,9 @@ EXPORT_SYMBOL_GPL(sched_clock_idle_sleep_event);
  */
 void sched_clock_idle_wakeup_event(u64 delta_ns)
 {
+	if (timekeeping_suspended)
+		return;
+
 	sched_clock_tick();
 	touch_softlockup_watchdog();
 }
diff --git a/kernel/sched_cpupri.c b/kernel/sched_cpupri.c
index 52154fefab7e..1e00bfacf9b8 100644
--- a/kernel/sched_cpupri.c
+++ b/kernel/sched_cpupri.c
@@ -67,24 +67,21 @@ static int convert_prio(int prio)
  * Returns: (int)bool - CPUs were found
  */
 int cpupri_find(struct cpupri *cp, struct task_struct *p,
-		cpumask_t *lowest_mask)
+		struct cpumask *lowest_mask)
 {
 	int                  idx      = 0;
 	int                  task_pri = convert_prio(p->prio);
 
 	for_each_cpupri_active(cp->pri_active, idx) {
 		struct cpupri_vec *vec  = &cp->pri_to_cpu[idx];
-		cpumask_t mask;
 
 		if (idx >= task_pri)
 			break;
 
-		cpus_and(mask, p->cpus_allowed, vec->mask);
-
-		if (cpus_empty(mask))
+		if (cpumask_any_and(&p->cpus_allowed, vec->mask) >= nr_cpu_ids)
 			continue;
 
-		*lowest_mask = mask;
+		cpumask_and(lowest_mask, &p->cpus_allowed, vec->mask);
 		return 1;
 	}
 
@@ -126,7 +123,7 @@ void cpupri_set(struct cpupri *cp, int cpu, int newpri)
 		vec->count--;
 		if (!vec->count)
 			clear_bit(oldpri, cp->pri_active);
-		cpu_clear(cpu, vec->mask);
+		cpumask_clear_cpu(cpu, vec->mask);
 
 		spin_unlock_irqrestore(&vec->lock, flags);
 	}
@@ -136,7 +133,7 @@ void cpupri_set(struct cpupri *cp, int cpu, int newpri)
 
 		spin_lock_irqsave(&vec->lock, flags);
 
-		cpu_set(cpu, vec->mask);
+		cpumask_set_cpu(cpu, vec->mask);
 		vec->count++;
 		if (vec->count == 1)
 			set_bit(newpri, cp->pri_active);
@@ -150,10 +147,11 @@ void cpupri_set(struct cpupri *cp, int cpu, int newpri)
 /**
  * cpupri_init - initialize the cpupri structure
  * @cp: The cpupri context
+ * @bootmem: true if allocations need to use bootmem
  *
- * Returns: (void)
+ * Returns: -ENOMEM if memory fails.
  */
-void cpupri_init(struct cpupri *cp)
+int __init_refok cpupri_init(struct cpupri *cp, bool bootmem)
 {
 	int i;
 
@@ -164,11 +162,30 @@ void cpupri_init(struct cpupri *cp)
 
 		spin_lock_init(&vec->lock);
 		vec->count = 0;
-		cpus_clear(vec->mask);
+		if (bootmem)
+			alloc_bootmem_cpumask_var(&vec->mask);
+		else if (!alloc_cpumask_var(&vec->mask, GFP_KERNEL))
+			goto cleanup;
 	}
 
 	for_each_possible_cpu(i)
 		cp->cpu_to_pri[i] = CPUPRI_INVALID;
+	return 0;
+
+cleanup:
+	for (i--; i >= 0; i--)
+		free_cpumask_var(cp->pri_to_cpu[i].mask);
+	return -ENOMEM;
 }
 
+/**
+ * cpupri_cleanup - clean up the cpupri structure
+ * @cp: The cpupri context
+ */
+void cpupri_cleanup(struct cpupri *cp)
+{
+	int i;
 
+	for (i = 0; i < CPUPRI_NR_PRIORITIES; i++)
+		free_cpumask_var(cp->pri_to_cpu[i].mask);
+}
diff --git a/kernel/sched_cpupri.h b/kernel/sched_cpupri.h
index f25811b0f931..642a94ef8a0a 100644
--- a/kernel/sched_cpupri.h
+++ b/kernel/sched_cpupri.h
@@ -14,7 +14,7 @@
 struct cpupri_vec {
 	spinlock_t lock;
 	int        count;
-	cpumask_t  mask;
+	cpumask_var_t mask;
 };
 
 struct cpupri {
@@ -27,7 +27,8 @@ struct cpupri {
 int  cpupri_find(struct cpupri *cp,
 		 struct task_struct *p, cpumask_t *lowest_mask);
 void cpupri_set(struct cpupri *cp, int cpu, int pri);
-void cpupri_init(struct cpupri *cp);
+int cpupri_init(struct cpupri *cp, bool bootmem);
+void cpupri_cleanup(struct cpupri *cp);
 #else
 #define cpupri_set(cp, cpu, pri) do { } while (0)
 #define cpupri_init() do { } while (0)
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 5ad4440f0fc4..8e1352c75557 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -386,20 +386,6 @@ int sched_nr_latency_handler(struct ctl_table *table, int write,
 #endif
 
 /*
- * delta *= P[w / rw]
- */
-static inline unsigned long
-calc_delta_weight(unsigned long delta, struct sched_entity *se)
-{
-	for_each_sched_entity(se) {
-		delta = calc_delta_mine(delta,
-				se->load.weight, &cfs_rq_of(se)->load);
-	}
-
-	return delta;
-}
-
-/*
  * delta /= w
  */
 static inline unsigned long
@@ -440,12 +426,20 @@ static u64 __sched_period(unsigned long nr_running)
  */
 static u64 sched_slice(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
-	unsigned long nr_running = cfs_rq->nr_running;
+	u64 slice = __sched_period(cfs_rq->nr_running + !se->on_rq);
 
-	if (unlikely(!se->on_rq))
-		nr_running++;
+	for_each_sched_entity(se) {
+		struct load_weight *load = &cfs_rq->load;
+
+		if (unlikely(!se->on_rq)) {
+			struct load_weight lw = cfs_rq->load;
 
-	return calc_delta_weight(__sched_period(nr_running), se);
+			update_load_add(&lw, se->load.weight);
+			load = &lw;
+		}
+		slice = calc_delta_mine(slice, se->load.weight, load);
+	}
+	return slice;
 }
 
 /*
@@ -1019,16 +1013,33 @@ static void yield_task_fair(struct rq *rq)
  * search starts with cpus closest then further out as needed,
  * so we always favor a closer, idle cpu.
  * Domains may include CPUs that are not usable for migration,
- * hence we need to mask them out (cpu_active_map)
+ * hence we need to mask them out (cpu_active_mask)
  *
  * Returns the CPU we should wake onto.
  */
 #if defined(ARCH_HAS_SCHED_WAKE_IDLE)
 static int wake_idle(int cpu, struct task_struct *p)
 {
-	cpumask_t tmp;
 	struct sched_domain *sd;
 	int i;
+	unsigned int chosen_wakeup_cpu;
+	int this_cpu;
+
+	/*
+	 * At POWERSAVINGS_BALANCE_WAKEUP level, if both this_cpu and prev_cpu
+	 * are idle and this is not a kernel thread and this task's affinity
+	 * allows it to be moved to preferred cpu, then just move!
+	 */
+
+	this_cpu = smp_processor_id();
+	chosen_wakeup_cpu =
+		cpu_rq(this_cpu)->rd->sched_mc_preferred_wakeup_cpu;
+
+	if (sched_mc_power_savings >= POWERSAVINGS_BALANCE_WAKEUP &&
+		idle_cpu(cpu) && idle_cpu(this_cpu) &&
+		p->mm && !(p->flags & PF_KTHREAD) &&
+		cpu_isset(chosen_wakeup_cpu, p->cpus_allowed))
+		return chosen_wakeup_cpu;
 
 	/*
 	 * If it is idle, then it is the best cpu to run this task.
@@ -1046,10 +1057,9 @@ static int wake_idle(int cpu, struct task_struct *p)
 		if ((sd->flags & SD_WAKE_IDLE)
 		    || ((sd->flags & SD_WAKE_IDLE_FAR)
 			&& !task_hot(p, task_rq(p)->clock, sd))) {
-			cpus_and(tmp, sd->span, p->cpus_allowed);
-			cpus_and(tmp, tmp, cpu_active_map);
-			for_each_cpu_mask_nr(i, tmp) {
-				if (idle_cpu(i)) {
+			for_each_cpu_and(i, sched_domain_span(sd),
+					 &p->cpus_allowed) {
+				if (cpu_active(i) && idle_cpu(i)) {
 					if (i != task_cpu(p)) {
 						schedstat_inc(p,
 						       se.nr_wakeups_idle);
@@ -1242,13 +1252,13 @@ static int select_task_rq_fair(struct task_struct *p, int sync)
 	 * this_cpu and prev_cpu are present in:
 	 */
 	for_each_domain(this_cpu, sd) {
-		if (cpu_isset(prev_cpu, sd->span)) {
+		if (cpumask_test_cpu(prev_cpu, sched_domain_span(sd))) {
 			this_sd = sd;
 			break;
 		}
 	}
 
-	if (unlikely(!cpu_isset(this_cpu, p->cpus_allowed)))
+	if (unlikely(!cpumask_test_cpu(this_cpu, &p->cpus_allowed)))
 		goto out;
 
 	/*
@@ -1607,8 +1617,6 @@ static void task_tick_fair(struct rq *rq, struct task_struct *curr, int queued)
 	}
 }
 
-#define swap(a, b) do { typeof(a) tmp = (a); (a) = (b); (b) = tmp; } while (0)
-
 /*
  * Share the fairness runtime between parent and child, thus the
  * total amount of pressure for CPU stays equal - new tasks
diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c
index 51d2af3e6191..954e1a81b796 100644
--- a/kernel/sched_rt.c
+++ b/kernel/sched_rt.c
@@ -15,7 +15,7 @@ static inline void rt_set_overload(struct rq *rq)
 	if (!rq->online)
 		return;
 
-	cpu_set(rq->cpu, rq->rd->rto_mask);
+	cpumask_set_cpu(rq->cpu, rq->rd->rto_mask);
 	/*
 	 * Make sure the mask is visible before we set
 	 * the overload count. That is checked to determine
@@ -34,7 +34,7 @@ static inline void rt_clear_overload(struct rq *rq)
 
 	/* the order here really doesn't matter */
 	atomic_dec(&rq->rd->rto_count);
-	cpu_clear(rq->cpu, rq->rd->rto_mask);
+	cpumask_clear_cpu(rq->cpu, rq->rd->rto_mask);
 }
 
 static void update_rt_migration(struct rq *rq)
@@ -139,14 +139,14 @@ static int rt_se_boosted(struct sched_rt_entity *rt_se)
 }
 
 #ifdef CONFIG_SMP
-static inline cpumask_t sched_rt_period_mask(void)
+static inline const struct cpumask *sched_rt_period_mask(void)
 {
 	return cpu_rq(smp_processor_id())->rd->span;
 }
 #else
-static inline cpumask_t sched_rt_period_mask(void)
+static inline const struct cpumask *sched_rt_period_mask(void)
 {
-	return cpu_online_map;
+	return cpu_online_mask;
 }
 #endif
 
@@ -212,9 +212,9 @@ static inline int rt_rq_throttled(struct rt_rq *rt_rq)
 	return rt_rq->rt_throttled;
 }
 
-static inline cpumask_t sched_rt_period_mask(void)
+static inline const struct cpumask *sched_rt_period_mask(void)
 {
-	return cpu_online_map;
+	return cpu_online_mask;
 }
 
 static inline
@@ -241,11 +241,11 @@ static int do_balance_runtime(struct rt_rq *rt_rq)
 	int i, weight, more = 0;
 	u64 rt_period;
 
-	weight = cpus_weight(rd->span);
+	weight = cpumask_weight(rd->span);
 
 	spin_lock(&rt_b->rt_runtime_lock);
 	rt_period = ktime_to_ns(rt_b->rt_period);
-	for_each_cpu_mask_nr(i, rd->span) {
+	for_each_cpu(i, rd->span) {
 		struct rt_rq *iter = sched_rt_period_rt_rq(rt_b, i);
 		s64 diff;
 
@@ -324,7 +324,7 @@ static void __disable_runtime(struct rq *rq)
 		/*
 		 * Greedy reclaim, take back as much as we can.
 		 */
-		for_each_cpu_mask(i, rd->span) {
+		for_each_cpu(i, rd->span) {
 			struct rt_rq *iter = sched_rt_period_rt_rq(rt_b, i);
 			s64 diff;
 
@@ -429,13 +429,13 @@ static inline int balance_runtime(struct rt_rq *rt_rq)
 static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun)
 {
 	int i, idle = 1;
-	cpumask_t span;
+	const struct cpumask *span;
 
 	if (!rt_bandwidth_enabled() || rt_b->rt_runtime == RUNTIME_INF)
 		return 1;
 
 	span = sched_rt_period_mask();
-	for_each_cpu_mask(i, span) {
+	for_each_cpu(i, span) {
 		int enqueue = 0;
 		struct rt_rq *rt_rq = sched_rt_period_rt_rq(rt_b, i);
 		struct rq *rq = rq_of_rt_rq(rt_rq);
@@ -805,17 +805,20 @@ static int select_task_rq_rt(struct task_struct *p, int sync)
 
 static void check_preempt_equal_prio(struct rq *rq, struct task_struct *p)
 {
-	cpumask_t mask;
+	cpumask_var_t mask;
 
 	if (rq->curr->rt.nr_cpus_allowed == 1)
 		return;
 
-	if (p->rt.nr_cpus_allowed != 1
-	    && cpupri_find(&rq->rd->cpupri, p, &mask))
+	if (!alloc_cpumask_var(&mask, GFP_ATOMIC))
 		return;
 
-	if (!cpupri_find(&rq->rd->cpupri, rq->curr, &mask))
-		return;
+	if (p->rt.nr_cpus_allowed != 1
+	    && cpupri_find(&rq->rd->cpupri, p, mask))
+		goto free;
+
+	if (!cpupri_find(&rq->rd->cpupri, rq->curr, mask))
+		goto free;
 
 	/*
 	 * There appears to be other cpus that can accept
@@ -824,6 +827,8 @@ static void check_preempt_equal_prio(struct rq *rq, struct task_struct *p)
 	 */
 	requeue_task_rt(rq, p, 1);
 	resched_task(rq->curr);
+free:
+	free_cpumask_var(mask);
 }
 
 #endif /* CONFIG_SMP */
@@ -914,7 +919,7 @@ static void deactivate_task(struct rq *rq, struct task_struct *p, int sleep);
 static int pick_rt_task(struct rq *rq, struct task_struct *p, int cpu)
 {
 	if (!task_running(rq, p) &&
-	    (cpu < 0 || cpu_isset(cpu, p->cpus_allowed)) &&
+	    (cpu < 0 || cpumask_test_cpu(cpu, &p->cpus_allowed)) &&
 	    (p->rt.nr_cpus_allowed > 1))
 		return 1;
 	return 0;
@@ -953,7 +958,7 @@ static struct task_struct *pick_next_highest_task_rt(struct rq *rq, int cpu)
 	return next;
 }
 
-static DEFINE_PER_CPU(cpumask_t, local_cpu_mask);
+static DEFINE_PER_CPU(cpumask_var_t, local_cpu_mask);
 
 static inline int pick_optimal_cpu(int this_cpu, cpumask_t *mask)
 {
@@ -973,7 +978,7 @@ static inline int pick_optimal_cpu(int this_cpu, cpumask_t *mask)
 static int find_lowest_rq(struct task_struct *task)
 {
 	struct sched_domain *sd;
-	cpumask_t *lowest_mask = &__get_cpu_var(local_cpu_mask);
+	struct cpumask *lowest_mask = __get_cpu_var(local_cpu_mask);
 	int this_cpu = smp_processor_id();
 	int cpu      = task_cpu(task);
 
@@ -988,7 +993,7 @@ static int find_lowest_rq(struct task_struct *task)
 	 * I guess we might want to change cpupri_find() to ignore those
 	 * in the first place.
 	 */
-	cpus_and(*lowest_mask, *lowest_mask, cpu_active_map);
+	cpumask_and(lowest_mask, lowest_mask, cpu_active_mask);
 
 	/*
 	 * At this point we have built a mask of cpus representing the
@@ -998,7 +1003,7 @@ static int find_lowest_rq(struct task_struct *task)
 	 * We prioritize the last cpu that the task executed on since
 	 * it is most likely cache-hot in that location.
 	 */
-	if (cpu_isset(cpu, *lowest_mask))
+	if (cpumask_test_cpu(cpu, lowest_mask))
 		return cpu;
 
 	/*
@@ -1013,7 +1018,8 @@ static int find_lowest_rq(struct task_struct *task)
 			cpumask_t domain_mask;
 			int       best_cpu;
 
-			cpus_and(domain_mask, sd->span, *lowest_mask);
+			cpumask_and(&domain_mask, sched_domain_span(sd),
+				    lowest_mask);
 
 			best_cpu = pick_optimal_cpu(this_cpu,
 						    &domain_mask);
@@ -1054,8 +1060,8 @@ static struct rq *find_lock_lowest_rq(struct task_struct *task, struct rq *rq)
 			 * Also make sure that it wasn't scheduled on its rq.
 			 */
 			if (unlikely(task_rq(task) != rq ||
-				     !cpu_isset(lowest_rq->cpu,
-						task->cpus_allowed) ||
+				     !cpumask_test_cpu(lowest_rq->cpu,
+						       &task->cpus_allowed) ||
 				     task_running(rq, task) ||
 				     !task->se.on_rq)) {
 
@@ -1176,7 +1182,7 @@ static int pull_rt_task(struct rq *this_rq)
 
 	next = pick_next_task_rt(this_rq);
 
-	for_each_cpu_mask_nr(cpu, this_rq->rd->rto_mask) {
+	for_each_cpu(cpu, this_rq->rd->rto_mask) {
 		if (this_cpu == cpu)
 			continue;
 
@@ -1305,9 +1311,9 @@ move_one_task_rt(struct rq *this_rq, int this_cpu, struct rq *busiest,
 }
 
 static void set_cpus_allowed_rt(struct task_struct *p,
-				const cpumask_t *new_mask)
+				const struct cpumask *new_mask)
 {
-	int weight = cpus_weight(*new_mask);
+	int weight = cpumask_weight(new_mask);
 
 	BUG_ON(!rt_task(p));
 
@@ -1328,7 +1334,7 @@ static void set_cpus_allowed_rt(struct task_struct *p,
 		update_rt_migration(rq);
 	}
 
-	p->cpus_allowed    = *new_mask;
+	cpumask_copy(&p->cpus_allowed, new_mask);
 	p->rt.nr_cpus_allowed = weight;
 }
 
@@ -1371,6 +1377,15 @@ static void switched_from_rt(struct rq *rq, struct task_struct *p,
 	if (!rq->rt.rt_nr_running)
 		pull_rt_task(rq);
 }
+
+static inline void init_sched_rt_class(void)
+{
+	unsigned int i;
+
+	for_each_possible_cpu(i)
+		alloc_cpumask_var_node(&per_cpu(local_cpu_mask, i),
+					GFP_KERNEL, cpu_to_node(i));
+}
 #endif /* CONFIG_SMP */
 
 /*
@@ -1541,3 +1556,4 @@ static void print_rt_stats(struct seq_file *m, int cpu)
 	rcu_read_unlock();
 }
 #endif /* CONFIG_SCHED_DEBUG */
+
diff --git a/kernel/sched_stats.h b/kernel/sched_stats.h
index 3b01098164c8..f2773b5d1226 100644
--- a/kernel/sched_stats.h
+++ b/kernel/sched_stats.h
@@ -42,7 +42,8 @@ static int show_schedstat(struct seq_file *seq, void *v)
 		for_each_domain(cpu, sd) {
 			enum cpu_idle_type itype;
 
-			cpumask_scnprintf(mask_str, mask_len, sd->span);
+			cpumask_scnprintf(mask_str, mask_len,
+					  sched_domain_span(sd));
 			seq_printf(seq, "domain%d %s", dcount++, mask_str);
 			for (itype = CPU_IDLE; itype < CPU_MAX_IDLE_TYPES;
 					itype++) {
diff --git a/kernel/signal.c b/kernel/signal.c
index 8e95855ff3cf..3152ac3b62e2 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -858,7 +858,8 @@ static int send_signal(int sig, struct siginfo *info, struct task_struct *t,
 			q->info.si_signo = sig;
 			q->info.si_errno = 0;
 			q->info.si_code = SI_USER;
-			q->info.si_pid = task_pid_vnr(current);
+			q->info.si_pid = task_tgid_nr_ns(current,
+							task_active_pid_ns(t));
 			q->info.si_uid = current_uid();
 			break;
 		case (unsigned long) SEND_SIG_PRIV:
diff --git a/kernel/smp.c b/kernel/smp.c
index 75c8dde58c55..5cfa0e5e3e88 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -24,8 +24,8 @@ struct call_function_data {
 	struct call_single_data csd;
 	spinlock_t lock;
 	unsigned int refs;
-	cpumask_t cpumask;
 	struct rcu_head rcu_head;
+	unsigned long cpumask_bits[];
 };
 
 struct call_single_queue {
@@ -110,13 +110,13 @@ void generic_smp_call_function_interrupt(void)
 	list_for_each_entry_rcu(data, &call_function_queue, csd.list) {
 		int refs;
 
-		if (!cpu_isset(cpu, data->cpumask))
+		if (!cpumask_test_cpu(cpu, to_cpumask(data->cpumask_bits)))
 			continue;
 
 		data->csd.func(data->csd.info);
 
 		spin_lock(&data->lock);
-		cpu_clear(cpu, data->cpumask);
+		cpumask_clear_cpu(cpu, to_cpumask(data->cpumask_bits));
 		WARN_ON(data->refs == 0);
 		data->refs--;
 		refs = data->refs;
@@ -223,7 +223,7 @@ int smp_call_function_single(int cpu, void (*func) (void *info), void *info,
 		local_irq_save(flags);
 		func(info);
 		local_irq_restore(flags);
-	} else if ((unsigned)cpu < NR_CPUS && cpu_online(cpu)) {
+	} else if ((unsigned)cpu < nr_cpu_ids && cpu_online(cpu)) {
 		struct call_single_data *data = NULL;
 
 		if (!wait) {
@@ -266,51 +266,19 @@ void __smp_call_function_single(int cpu, struct call_single_data *data)
 	generic_exec_single(cpu, data);
 }
 
-/* Dummy function */
-static void quiesce_dummy(void *unused)
-{
-}
-
-/*
- * Ensure stack based data used in call function mask is safe to free.
- *
- * This is needed by smp_call_function_mask when using on-stack data, because
- * a single call function queue is shared by all CPUs, and any CPU may pick up
- * the data item on the queue at any time before it is deleted. So we need to
- * ensure that all CPUs have transitioned through a quiescent state after
- * this call.
- *
- * This is a very slow function, implemented by sending synchronous IPIs to
- * all possible CPUs. For this reason, we have to alloc data rather than use
- * stack based data even in the case of synchronous calls. The stack based
- * data is then just used for deadlock/oom fallback which will be very rare.
- *
- * If a faster scheme can be made, we could go back to preferring stack based
- * data -- the data allocation/free is non-zero cost.
- */
-static void smp_call_function_mask_quiesce_stack(cpumask_t mask)
-{
-	struct call_single_data data;
-	int cpu;
-
-	data.func = quiesce_dummy;
-	data.info = NULL;
-
-	for_each_cpu_mask(cpu, mask) {
-		data.flags = CSD_FLAG_WAIT;
-		generic_exec_single(cpu, &data);
-	}
-}
+/* FIXME: Shim for archs using old arch_send_call_function_ipi API. */
+#ifndef arch_send_call_function_ipi_mask
+#define arch_send_call_function_ipi_mask(maskp) \
+	arch_send_call_function_ipi(*(maskp))
+#endif
 
 /**
- * smp_call_function_mask(): Run a function on a set of other CPUs.
- * @mask: The set of cpus to run on.
+ * smp_call_function_many(): Run a function on a set of other CPUs.
+ * @mask: The set of cpus to run on (only runs on online subset).
  * @func: The function to run. This must be fast and non-blocking.
  * @info: An arbitrary pointer to pass to the function.
  * @wait: If true, wait (atomically) until function has completed on other CPUs.
  *
- * Returns 0 on success, else a negative status code.
- *
  * If @wait is true, then returns once @func has returned. Note that @wait
  * will be implicitly turned on in case of allocation failures, since
  * we fall back to on-stack allocation.
@@ -319,53 +287,57 @@ static void smp_call_function_mask_quiesce_stack(cpumask_t mask)
  * hardware interrupt handler or from a bottom half handler. Preemption
  * must be disabled when calling this function.
  */
-int smp_call_function_mask(cpumask_t mask, void (*func)(void *), void *info,
-			   int wait)
+void smp_call_function_many(const struct cpumask *mask,
+			    void (*func)(void *), void *info,
+			    bool wait)
 {
-	struct call_function_data d;
-	struct call_function_data *data = NULL;
-	cpumask_t allbutself;
+	struct call_function_data *data;
 	unsigned long flags;
-	int cpu, num_cpus;
-	int slowpath = 0;
+	int cpu, next_cpu;
 
 	/* Can deadlock when called with interrupts disabled */
 	WARN_ON(irqs_disabled());
 
-	cpu = smp_processor_id();
-	allbutself = cpu_online_map;
-	cpu_clear(cpu, allbutself);
-	cpus_and(mask, mask, allbutself);
-	num_cpus = cpus_weight(mask);
-
-	/*
-	 * If zero CPUs, return. If just a single CPU, turn this request
-	 * into a targetted single call instead since it's faster.
-	 */
-	if (!num_cpus)
-		return 0;
-	else if (num_cpus == 1) {
-		cpu = first_cpu(mask);
-		return smp_call_function_single(cpu, func, info, wait);
+	/* So, what's a CPU they want?  Ignoring this one. */
+	cpu = cpumask_first_and(mask, cpu_online_mask);
+	if (cpu == smp_processor_id())
+		cpu = cpumask_next_and(cpu, mask, cpu_online_mask);
+	/* No online cpus?  We're done. */
+	if (cpu >= nr_cpu_ids)
+		return;
+
+	/* Do we have another CPU which isn't us? */
+	next_cpu = cpumask_next_and(cpu, mask, cpu_online_mask);
+	if (next_cpu == smp_processor_id())
+		next_cpu = cpumask_next_and(next_cpu, mask, cpu_online_mask);
+
+	/* Fastpath: do that cpu by itself. */
+	if (next_cpu >= nr_cpu_ids) {
+		smp_call_function_single(cpu, func, info, wait);
+		return;
 	}
 
-	data = kmalloc(sizeof(*data), GFP_ATOMIC);
-	if (data) {
-		data->csd.flags = CSD_FLAG_ALLOC;
-		if (wait)
-			data->csd.flags |= CSD_FLAG_WAIT;
-	} else {
-		data = &d;
-		data->csd.flags = CSD_FLAG_WAIT;
-		wait = 1;
-		slowpath = 1;
+	data = kmalloc(sizeof(*data) + cpumask_size(), GFP_ATOMIC);
+	if (unlikely(!data)) {
+		/* Slow path. */
+		for_each_online_cpu(cpu) {
+			if (cpu == smp_processor_id())
+				continue;
+			if (cpumask_test_cpu(cpu, mask))
+				smp_call_function_single(cpu, func, info, wait);
+		}
+		return;
 	}
 
 	spin_lock_init(&data->lock);
+	data->csd.flags = CSD_FLAG_ALLOC;
+	if (wait)
+		data->csd.flags |= CSD_FLAG_WAIT;
 	data->csd.func = func;
 	data->csd.info = info;
-	data->refs = num_cpus;
-	data->cpumask = mask;
+	cpumask_and(to_cpumask(data->cpumask_bits), mask, cpu_online_mask);
+	cpumask_clear_cpu(smp_processor_id(), to_cpumask(data->cpumask_bits));
+	data->refs = cpumask_weight(to_cpumask(data->cpumask_bits));
 
 	spin_lock_irqsave(&call_function_lock, flags);
 	list_add_tail_rcu(&data->csd.list, &call_function_queue);
@@ -377,18 +349,13 @@ int smp_call_function_mask(cpumask_t mask, void (*func)(void *), void *info,
 	smp_mb();
 
 	/* Send a message to all CPUs in the map */
-	arch_send_call_function_ipi(mask);
+	arch_send_call_function_ipi_mask(to_cpumask(data->cpumask_bits));
 
 	/* optionally wait for the CPUs to complete */
-	if (wait) {
+	if (wait)
 		csd_flag_wait(&data->csd);
-		if (unlikely(slowpath))
-			smp_call_function_mask_quiesce_stack(mask);
-	}
-
-	return 0;
 }
-EXPORT_SYMBOL(smp_call_function_mask);
+EXPORT_SYMBOL(smp_call_function_many);
 
 /**
  * smp_call_function(): Run a function on all other CPUs.
@@ -396,7 +363,7 @@ EXPORT_SYMBOL(smp_call_function_mask);
  * @info: An arbitrary pointer to pass to the function.
  * @wait: If true, wait (atomically) until function has completed on other CPUs.
  *
- * Returns 0 on success, else a negative status code.
+ * Returns 0.
  *
  * If @wait is true, then returns once @func has returned; otherwise
  * it returns just before the target cpu calls @func. In case of allocation
@@ -407,12 +374,10 @@ EXPORT_SYMBOL(smp_call_function_mask);
  */
 int smp_call_function(void (*func)(void *), void *info, int wait)
 {
-	int ret;
-
 	preempt_disable();
-	ret = smp_call_function_mask(cpu_online_map, func, info, wait);
+	smp_call_function_many(cpu_online_mask, func, info, wait);
 	preempt_enable();
-	return ret;
+	return 0;
 }
 EXPORT_SYMBOL(smp_call_function);
 
diff --git a/kernel/softirq.c b/kernel/softirq.c
index e7c69a720d69..bdbe9de9cd8d 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -102,20 +102,6 @@ void local_bh_disable(void)
 
 EXPORT_SYMBOL(local_bh_disable);
 
-void __local_bh_enable(void)
-{
-	WARN_ON_ONCE(in_irq());
-
-	/*
-	 * softirqs should never be enabled by __local_bh_enable(),
-	 * it always nests inside local_bh_enable() sections:
-	 */
-	WARN_ON_ONCE(softirq_count() == SOFTIRQ_OFFSET);
-
-	sub_preempt_count(SOFTIRQ_OFFSET);
-}
-EXPORT_SYMBOL_GPL(__local_bh_enable);
-
 /*
  * Special-case - softirqs can safely be enabled in
  * cond_resched_softirq(), or by __do_softirq(),
@@ -269,6 +255,7 @@ void irq_enter(void)
 {
 	int cpu = smp_processor_id();
 
+	rcu_irq_enter();
 	if (idle_cpu(cpu) && !in_interrupt()) {
 		__irq_enter();
 		tick_check_idle(cpu);
@@ -295,9 +282,9 @@ void irq_exit(void)
 
 #ifdef CONFIG_NO_HZ
 	/* Make sure that timer wheel updates are propagated */
-	if (!in_interrupt() && idle_cpu(smp_processor_id()) && !need_resched())
-		tick_nohz_stop_sched_tick(0);
 	rcu_irq_exit();
+	if (idle_cpu(smp_processor_id()) && !in_interrupt() && !need_resched())
+		tick_nohz_stop_sched_tick(0);
 #endif
 	preempt_enable_no_resched();
 }
@@ -746,7 +733,7 @@ static int __cpuinit cpu_callback(struct notifier_block *nfb,
 			break;
 		/* Unbind so it can run.  Fall thru. */
 		kthread_bind(per_cpu(ksoftirqd, hotcpu),
-			     any_online_cpu(cpu_online_map));
+			     cpumask_any(cpu_online_mask));
 	case CPU_DEAD:
 	case CPU_DEAD_FROZEN: {
 		struct sched_param param = { .sched_priority = MAX_RT_PRIO-1 };
@@ -797,3 +784,23 @@ int on_each_cpu(void (*func) (void *info), void *info, int wait)
 }
 EXPORT_SYMBOL(on_each_cpu);
 #endif
+
+/*
+ * [ These __weak aliases are kept in a separate compilation unit, so that
+ *   GCC does not inline them incorrectly. ]
+ */
+
+int __init __weak early_irq_init(void)
+{
+	return 0;
+}
+
+int __init __weak arch_early_irq_init(void)
+{
+	return 0;
+}
+
+int __weak arch_init_chip_data(struct irq_desc *desc, int cpu)
+{
+	return 0;
+}
diff --git a/kernel/softlockup.c b/kernel/softlockup.c
index dc0b3be6b7d5..d9188c66278a 100644
--- a/kernel/softlockup.c
+++ b/kernel/softlockup.c
@@ -164,7 +164,7 @@ unsigned long __read_mostly sysctl_hung_task_check_count = 1024;
 /*
  * Zero means infinite timeout - no checking done:
  */
-unsigned long __read_mostly sysctl_hung_task_timeout_secs = 120;
+unsigned long __read_mostly sysctl_hung_task_timeout_secs = 480;
 
 unsigned long __read_mostly sysctl_hung_task_warnings = 10;
 
@@ -303,17 +303,15 @@ cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu)
 		break;
 	case CPU_ONLINE:
 	case CPU_ONLINE_FROZEN:
-		check_cpu = any_online_cpu(cpu_online_map);
+		check_cpu = cpumask_any(cpu_online_mask);
 		wake_up_process(per_cpu(watchdog_task, hotcpu));
 		break;
 #ifdef CONFIG_HOTPLUG_CPU
 	case CPU_DOWN_PREPARE:
 	case CPU_DOWN_PREPARE_FROZEN:
 		if (hotcpu == check_cpu) {
-			cpumask_t temp_cpu_online_map = cpu_online_map;
-
-			cpu_clear(hotcpu, temp_cpu_online_map);
-			check_cpu = any_online_cpu(temp_cpu_online_map);
+			/* Pick any other online cpu. */
+			check_cpu = cpumask_any_but(cpu_online_mask, hotcpu);
 		}
 		break;
 
@@ -323,7 +321,7 @@ cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu)
 			break;
 		/* Unbind so it can run.  Fall thru. */
 		kthread_bind(per_cpu(watchdog_task, hotcpu),
-			     any_online_cpu(cpu_online_map));
+			     cpumask_any(cpu_online_mask));
 	case CPU_DEAD:
 	case CPU_DEAD_FROZEN:
 		p = per_cpu(watchdog_task, hotcpu);
diff --git a/kernel/stacktrace.c b/kernel/stacktrace.c
index 94b527ef1d1e..eb212f8f8bc8 100644
--- a/kernel/stacktrace.c
+++ b/kernel/stacktrace.c
@@ -6,6 +6,7 @@
  *  Copyright (C) 2006 Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
  */
 #include <linux/sched.h>
+#include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/kallsyms.h>
 #include <linux/stacktrace.h>
@@ -24,3 +25,13 @@ void print_stack_trace(struct stack_trace *trace, int spaces)
 }
 EXPORT_SYMBOL_GPL(print_stack_trace);
 
+/*
+ * Architectures that do not implement save_stack_trace_tsk get this
+ * weak alias and a once-per-bootup warning (whenever this facility
+ * is utilized - for example by procfs):
+ */
+__weak void
+save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
+{
+	WARN_ONCE(1, KERN_INFO "save_stack_trace_tsk() not implemented yet.\n");
+}
diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c
index 24e8ceacc388..0cd415ee62a2 100644
--- a/kernel/stop_machine.c
+++ b/kernel/stop_machine.c
@@ -38,7 +38,10 @@ struct stop_machine_data {
 static unsigned int num_threads;
 static atomic_t thread_ack;
 static DEFINE_MUTEX(lock);
-
+/* setup_lock protects refcount, stop_machine_wq and stop_machine_work. */
+static DEFINE_MUTEX(setup_lock);
+/* Users of stop_machine. */
+static int refcount;
 static struct workqueue_struct *stop_machine_wq;
 static struct stop_machine_data active, idle;
 static const cpumask_t *active_cpus;
@@ -69,10 +72,10 @@ static void stop_cpu(struct work_struct *unused)
 	int err;
 
 	if (!active_cpus) {
-		if (cpu == first_cpu(cpu_online_map))
+		if (cpu == cpumask_first(cpu_online_mask))
 			smdata = &active;
 	} else {
-		if (cpu_isset(cpu, *active_cpus))
+		if (cpumask_test_cpu(cpu, active_cpus))
 			smdata = &active;
 	}
 	/* Simple state machine */
@@ -109,7 +112,44 @@ static int chill(void *unused)
 	return 0;
 }
 
-int __stop_machine(int (*fn)(void *), void *data, const cpumask_t *cpus)
+int stop_machine_create(void)
+{
+	mutex_lock(&setup_lock);
+	if (refcount)
+		goto done;
+	stop_machine_wq = create_rt_workqueue("kstop");
+	if (!stop_machine_wq)
+		goto err_out;
+	stop_machine_work = alloc_percpu(struct work_struct);
+	if (!stop_machine_work)
+		goto err_out;
+done:
+	refcount++;
+	mutex_unlock(&setup_lock);
+	return 0;
+
+err_out:
+	if (stop_machine_wq)
+		destroy_workqueue(stop_machine_wq);
+	mutex_unlock(&setup_lock);
+	return -ENOMEM;
+}
+EXPORT_SYMBOL_GPL(stop_machine_create);
+
+void stop_machine_destroy(void)
+{
+	mutex_lock(&setup_lock);
+	refcount--;
+	if (refcount)
+		goto done;
+	destroy_workqueue(stop_machine_wq);
+	free_percpu(stop_machine_work);
+done:
+	mutex_unlock(&setup_lock);
+}
+EXPORT_SYMBOL_GPL(stop_machine_destroy);
+
+int __stop_machine(int (*fn)(void *), void *data, const struct cpumask *cpus)
 {
 	struct work_struct *sm_work;
 	int i, ret;
@@ -142,23 +182,18 @@ int __stop_machine(int (*fn)(void *), void *data, const cpumask_t *cpus)
 	return ret;
 }
 
-int stop_machine(int (*fn)(void *), void *data, const cpumask_t *cpus)
+int stop_machine(int (*fn)(void *), void *data, const struct cpumask *cpus)
 {
 	int ret;
 
+	ret = stop_machine_create();
+	if (ret)
+		return ret;
 	/* No CPUs can come up or down during this. */
 	get_online_cpus();
 	ret = __stop_machine(fn, data, cpus);
 	put_online_cpus();
-
+	stop_machine_destroy();
 	return ret;
 }
 EXPORT_SYMBOL_GPL(stop_machine);
-
-static int __init stop_machine_init(void)
-{
-	stop_machine_wq = create_rt_workqueue("kstop");
-	stop_machine_work = alloc_percpu(struct work_struct);
-	return 0;
-}
-core_initcall(stop_machine_init);
diff --git a/kernel/sys.c b/kernel/sys.c
index 1544c305751e..c2a951ae4223 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -34,6 +34,7 @@
 #include <linux/task_io_accounting_ops.h>
 #include <linux/seccomp.h>
 #include <linux/cpu.h>
+#include <linux/ptrace.h>
 
 #include <linux/compat.h>
 #include <linux/syscalls.h>
@@ -908,8 +909,8 @@ void do_sys_times(struct tms *tms)
 	struct task_cputime cputime;
 	cputime_t cutime, cstime;
 
-	spin_lock_irq(&current->sighand->siglock);
 	thread_group_cputime(current, &cputime);
+	spin_lock_irq(&current->sighand->siglock);
 	cutime = current->signal->cutime;
 	cstime = current->signal->cstime;
 	spin_unlock_irq(&current->sighand->siglock);
@@ -928,6 +929,7 @@ asmlinkage long sys_times(struct tms __user * tbuf)
 		if (copy_to_user(tbuf, &tmp, sizeof(struct tms)))
 			return -EFAULT;
 	}
+	force_successful_syscall_return();
 	return (long) jiffies_64_to_clock_t(get_jiffies_64());
 }
 
@@ -1628,6 +1630,8 @@ static void k_getrusage(struct task_struct *p, int who, struct rusage *r)
 	utime = stime = cputime_zero;
 
 	if (who == RUSAGE_THREAD) {
+		utime = task_utime(current);
+		stime = task_stime(current);
 		accumulate_thread_rusage(p, r);
 		goto out;
 	}
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 0b627d9c93d8..89d74436318c 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -82,15 +82,14 @@ extern int percpu_pagelist_fraction;
 extern int compat_log;
 extern int latencytop_enabled;
 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 */
 
 /* Constants used for minimum and  maximum */
-#if defined(CONFIG_HIGHMEM) || defined(CONFIG_DETECT_SOFTLOCKUP)
-static int one = 1;
-#endif
-
 #ifdef CONFIG_DETECT_SOFTLOCKUP
 static int sixty = 60;
 static int neg_one = -1;
@@ -101,6 +100,7 @@ static int two = 2;
 #endif
 
 static int zero;
+static int one = 1;
 static int one_hundred = 100;
 
 /* this is needed for the proc_dointvec_minmax for [fs_]overflow UID and GID */
@@ -121,6 +121,10 @@ extern int sg_big_buff;
 #include <asm/system.h>
 #endif
 
+#ifdef CONFIG_SPARC64
+extern int sysctl_tsb_ratio;
+#endif
+
 #ifdef __hppa__
 extern int pwrsw_enabled;
 extern int unaligned_enabled;
@@ -451,6 +455,16 @@ static struct ctl_table kern_table[] = {
 		.proc_handler	= &proc_dointvec,
 	},
 #endif
+#ifdef CONFIG_SPARC64
+	{
+		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "tsb-ratio",
+		.data		= &sysctl_tsb_ratio,
+		.maxlen		= sizeof (int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec,
+	},
+#endif
 #ifdef __hppa__
 	{
 		.ctl_name	= KERN_HPPA_PWRSW,
@@ -938,12 +952,22 @@ static struct ctl_table vm_table[] = {
 		.data		= &dirty_background_ratio,
 		.maxlen		= sizeof(dirty_background_ratio),
 		.mode		= 0644,
-		.proc_handler	= &proc_dointvec_minmax,
+		.proc_handler	= &dirty_background_ratio_handler,
 		.strategy	= &sysctl_intvec,
 		.extra1		= &zero,
 		.extra2		= &one_hundred,
 	},
 	{
+		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "dirty_background_bytes",
+		.data		= &dirty_background_bytes,
+		.maxlen		= sizeof(dirty_background_bytes),
+		.mode		= 0644,
+		.proc_handler	= &dirty_background_bytes_handler,
+		.strategy	= &sysctl_intvec,
+		.extra1		= &one,
+	},
+	{
 		.ctl_name	= VM_DIRTY_RATIO,
 		.procname	= "dirty_ratio",
 		.data		= &vm_dirty_ratio,
@@ -955,6 +979,16 @@ static struct ctl_table vm_table[] = {
 		.extra2		= &one_hundred,
 	},
 	{
+		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "dirty_bytes",
+		.data		= &vm_dirty_bytes,
+		.maxlen		= sizeof(vm_dirty_bytes),
+		.mode		= 0644,
+		.proc_handler	= &dirty_bytes_handler,
+		.strategy	= &sysctl_intvec,
+		.extra1		= &one,
+	},
+	{
 		.procname	= "dirty_writeback_centisecs",
 		.data		= &dirty_writeback_interval,
 		.maxlen		= sizeof(dirty_writeback_interval),
@@ -1071,6 +1105,17 @@ static struct ctl_table vm_table[] = {
 		.mode		= 0644,
 		.proc_handler	= &proc_dointvec
 	},
+#else
+	{
+		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "nr_trim_pages",
+		.data		= &sysctl_nr_trim_pages,
+		.maxlen		= sizeof(sysctl_nr_trim_pages),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec_minmax,
+		.strategy	= &sysctl_intvec,
+		.extra1		= &zero,
+	},
 #endif
 	{
 		.ctl_name	= VM_LAPTOP_MODE,
diff --git a/kernel/sysctl_check.c b/kernel/sysctl_check.c
index c35da23ab8fb..fafeb48f27c0 100644
--- a/kernel/sysctl_check.c
+++ b/kernel/sysctl_check.c
@@ -730,7 +730,6 @@ static const struct trans_ctl_table trans_fs_quota_table[] = {
 };
 
 static const struct trans_ctl_table trans_fs_xfs_table[] = {
-	{ XFS_RESTRICT_CHOWN,	"restrict_chown" },
 	{ XFS_SGID_INHERIT,	"irix_sgid_inherit" },
 	{ XFS_SYMLINK_MODE,	"irix_symlink_mode" },
 	{ XFS_PANIC_MASK,	"panic_mask" },
diff --git a/kernel/taskstats.c b/kernel/taskstats.c
index bd6be76303cf..888adbcca30c 100644
--- a/kernel/taskstats.c
+++ b/kernel/taskstats.c
@@ -290,18 +290,17 @@ ret:
 	return;
 }
 
-static int add_del_listener(pid_t pid, cpumask_t *maskp, int isadd)
+static int add_del_listener(pid_t pid, const struct cpumask *mask, int isadd)
 {
 	struct listener_list *listeners;
 	struct listener *s, *tmp;
 	unsigned int cpu;
-	cpumask_t mask = *maskp;
 
-	if (!cpus_subset(mask, cpu_possible_map))
+	if (!cpumask_subset(mask, cpu_possible_mask))
 		return -EINVAL;
 
 	if (isadd == REGISTER) {
-		for_each_cpu_mask_nr(cpu, mask) {
+		for_each_cpu(cpu, mask) {
 			s = kmalloc_node(sizeof(struct listener), GFP_KERNEL,
 					 cpu_to_node(cpu));
 			if (!s)
@@ -320,7 +319,7 @@ static int add_del_listener(pid_t pid, cpumask_t *maskp, int isadd)
 
 	/* Deregister or cleanup */
 cleanup:
-	for_each_cpu_mask_nr(cpu, mask) {
+	for_each_cpu(cpu, mask) {
 		listeners = &per_cpu(listener_array, cpu);
 		down_write(&listeners->sem);
 		list_for_each_entry_safe(s, tmp, &listeners->list, list) {
@@ -335,7 +334,7 @@ cleanup:
 	return 0;
 }
 
-static int parse(struct nlattr *na, cpumask_t *mask)
+static int parse(struct nlattr *na, struct cpumask *mask)
 {
 	char *data;
 	int len;
@@ -352,7 +351,7 @@ static int parse(struct nlattr *na, cpumask_t *mask)
 	if (!data)
 		return -ENOMEM;
 	nla_strlcpy(data, na, len);
-	ret = cpulist_parse(data, *mask);
+	ret = cpulist_parse(data, mask);
 	kfree(data);
 	return ret;
 }
@@ -428,23 +427,33 @@ err:
 
 static int taskstats_user_cmd(struct sk_buff *skb, struct genl_info *info)
 {
-	int rc = 0;
+	int rc;
 	struct sk_buff *rep_skb;
 	struct taskstats *stats;
 	size_t size;
-	cpumask_t mask;
+	cpumask_var_t mask;
+
+	if (!alloc_cpumask_var(&mask, GFP_KERNEL))
+		return -ENOMEM;
 
-	rc = parse(info->attrs[TASKSTATS_CMD_ATTR_REGISTER_CPUMASK], &mask);
+	rc = parse(info->attrs[TASKSTATS_CMD_ATTR_REGISTER_CPUMASK], mask);
 	if (rc < 0)
-		return rc;
-	if (rc == 0)
-		return add_del_listener(info->snd_pid, &mask, REGISTER);
+		goto free_return_rc;
+	if (rc == 0) {
+		rc = add_del_listener(info->snd_pid, mask, REGISTER);
+		goto free_return_rc;
+	}
 
-	rc = parse(info->attrs[TASKSTATS_CMD_ATTR_DEREGISTER_CPUMASK], &mask);
+	rc = parse(info->attrs[TASKSTATS_CMD_ATTR_DEREGISTER_CPUMASK], mask);
 	if (rc < 0)
+		goto free_return_rc;
+	if (rc == 0) {
+		rc = add_del_listener(info->snd_pid, mask, DEREGISTER);
+free_return_rc:
+		free_cpumask_var(mask);
 		return rc;
-	if (rc == 0)
-		return add_del_listener(info->snd_pid, &mask, DEREGISTER);
+	}
+	free_cpumask_var(mask);
 
 	/*
 	 * Size includes space for nested attributes
diff --git a/kernel/test_kprobes.c b/kernel/test_kprobes.c
index 06b6395b45b2..4f104515a19b 100644
--- a/kernel/test_kprobes.c
+++ b/kernel/test_kprobes.c
@@ -22,21 +22,11 @@
 
 static u32 rand1, preh_val, posth_val, jph_val;
 static int errors, handler_errors, num_tests;
+static u32 (*target)(u32 value);
+static u32 (*target2)(u32 value);
 
 static noinline u32 kprobe_target(u32 value)
 {
-	/*
-	 * gcc ignores noinline on some architectures unless we stuff
-	 * sufficient lard into the function. The get_kprobe() here is
-	 * just for that.
-	 *
-	 * NOTE: We aren't concerned about the correctness of get_kprobe()
-	 * here; hence, this call is neither under !preempt nor with the
-	 * kprobe_mutex held. This is fine(tm)
-	 */
-	if (get_kprobe((void *)0xdeadbeef))
-		printk(KERN_INFO "Kprobe smoke test: probe on 0xdeadbeef!\n");
-
 	return (value / div_factor);
 }
 
@@ -74,7 +64,7 @@ static int test_kprobe(void)
 		return ret;
 	}
 
-	ret = kprobe_target(rand1);
+	ret = target(rand1);
 	unregister_kprobe(&kp);
 
 	if (preh_val == 0) {
@@ -92,6 +82,84 @@ static int test_kprobe(void)
 	return 0;
 }
 
+static noinline u32 kprobe_target2(u32 value)
+{
+	return (value / div_factor) + 1;
+}
+
+static int kp_pre_handler2(struct kprobe *p, struct pt_regs *regs)
+{
+	preh_val = (rand1 / div_factor) + 1;
+	return 0;
+}
+
+static void kp_post_handler2(struct kprobe *p, struct pt_regs *regs,
+		unsigned long flags)
+{
+	if (preh_val != (rand1 / div_factor) + 1) {
+		handler_errors++;
+		printk(KERN_ERR "Kprobe smoke test failed: "
+				"incorrect value in post_handler2\n");
+	}
+	posth_val = preh_val + div_factor;
+}
+
+static struct kprobe kp2 = {
+	.symbol_name = "kprobe_target2",
+	.pre_handler = kp_pre_handler2,
+	.post_handler = kp_post_handler2
+};
+
+static int test_kprobes(void)
+{
+	int ret;
+	struct kprobe *kps[2] = {&kp, &kp2};
+
+	kp.addr = 0; /* addr should be cleard for reusing kprobe. */
+	ret = register_kprobes(kps, 2);
+	if (ret < 0) {
+		printk(KERN_ERR "Kprobe smoke test failed: "
+				"register_kprobes returned %d\n", ret);
+		return ret;
+	}
+
+	preh_val = 0;
+	posth_val = 0;
+	ret = target(rand1);
+
+	if (preh_val == 0) {
+		printk(KERN_ERR "Kprobe smoke test failed: "
+				"kprobe pre_handler not called\n");
+		handler_errors++;
+	}
+
+	if (posth_val == 0) {
+		printk(KERN_ERR "Kprobe smoke test failed: "
+				"kprobe post_handler not called\n");
+		handler_errors++;
+	}
+
+	preh_val = 0;
+	posth_val = 0;
+	ret = target2(rand1);
+
+	if (preh_val == 0) {
+		printk(KERN_ERR "Kprobe smoke test failed: "
+				"kprobe pre_handler2 not called\n");
+		handler_errors++;
+	}
+
+	if (posth_val == 0) {
+		printk(KERN_ERR "Kprobe smoke test failed: "
+				"kprobe post_handler2 not called\n");
+		handler_errors++;
+	}
+
+	unregister_kprobes(kps, 2);
+	return 0;
+
+}
+
 static u32 j_kprobe_target(u32 value)
 {
 	if (value != rand1) {
@@ -121,7 +189,7 @@ static int test_jprobe(void)
 		return ret;
 	}
 
-	ret = kprobe_target(rand1);
+	ret = target(rand1);
 	unregister_jprobe(&jp);
 	if (jph_val == 0) {
 		printk(KERN_ERR "Kprobe smoke test failed: "
@@ -132,6 +200,43 @@ static int test_jprobe(void)
 	return 0;
 }
 
+static struct jprobe jp2 = {
+	.entry          = j_kprobe_target,
+	.kp.symbol_name = "kprobe_target2"
+};
+
+static int test_jprobes(void)
+{
+	int ret;
+	struct jprobe *jps[2] = {&jp, &jp2};
+
+	jp.kp.addr = 0; /* addr should be cleard for reusing kprobe. */
+	ret = register_jprobes(jps, 2);
+	if (ret < 0) {
+		printk(KERN_ERR "Kprobe smoke test failed: "
+				"register_jprobes returned %d\n", ret);
+		return ret;
+	}
+
+	jph_val = 0;
+	ret = target(rand1);
+	if (jph_val == 0) {
+		printk(KERN_ERR "Kprobe smoke test failed: "
+				"jprobe handler not called\n");
+		handler_errors++;
+	}
+
+	jph_val = 0;
+	ret = target2(rand1);
+	if (jph_val == 0) {
+		printk(KERN_ERR "Kprobe smoke test failed: "
+				"jprobe handler2 not called\n");
+		handler_errors++;
+	}
+	unregister_jprobes(jps, 2);
+
+	return 0;
+}
 #ifdef CONFIG_KRETPROBES
 static u32 krph_val;
 
@@ -177,7 +282,7 @@ static int test_kretprobe(void)
 		return ret;
 	}
 
-	ret = kprobe_target(rand1);
+	ret = target(rand1);
 	unregister_kretprobe(&rp);
 	if (krph_val != rand1) {
 		printk(KERN_ERR "Kprobe smoke test failed: "
@@ -187,12 +292,72 @@ static int test_kretprobe(void)
 
 	return 0;
 }
+
+static int return_handler2(struct kretprobe_instance *ri, struct pt_regs *regs)
+{
+	unsigned long ret = regs_return_value(regs);
+
+	if (ret != (rand1 / div_factor) + 1) {
+		handler_errors++;
+		printk(KERN_ERR "Kprobe smoke test failed: "
+				"incorrect value in kretprobe handler2\n");
+	}
+	if (krph_val == 0) {
+		handler_errors++;
+		printk(KERN_ERR "Kprobe smoke test failed: "
+				"call to kretprobe entry handler failed\n");
+	}
+
+	krph_val = rand1;
+	return 0;
+}
+
+static struct kretprobe rp2 = {
+	.handler	= return_handler2,
+	.entry_handler  = entry_handler,
+	.kp.symbol_name = "kprobe_target2"
+};
+
+static int test_kretprobes(void)
+{
+	int ret;
+	struct kretprobe *rps[2] = {&rp, &rp2};
+
+	rp.kp.addr = 0; /* addr should be cleard for reusing kprobe. */
+	ret = register_kretprobes(rps, 2);
+	if (ret < 0) {
+		printk(KERN_ERR "Kprobe smoke test failed: "
+				"register_kretprobe returned %d\n", ret);
+		return ret;
+	}
+
+	krph_val = 0;
+	ret = target(rand1);
+	if (krph_val != rand1) {
+		printk(KERN_ERR "Kprobe smoke test failed: "
+				"kretprobe handler not called\n");
+		handler_errors++;
+	}
+
+	krph_val = 0;
+	ret = target2(rand1);
+	if (krph_val != rand1) {
+		printk(KERN_ERR "Kprobe smoke test failed: "
+				"kretprobe handler2 not called\n");
+		handler_errors++;
+	}
+	unregister_kretprobes(rps, 2);
+	return 0;
+}
 #endif /* CONFIG_KRETPROBES */
 
 int init_test_probes(void)
 {
 	int ret;
 
+	target = kprobe_target;
+	target2 = kprobe_target2;
+
 	do {
 		rand1 = random32();
 	} while (rand1 <= div_factor);
@@ -204,15 +369,30 @@ int init_test_probes(void)
 		errors++;
 
 	num_tests++;
+	ret = test_kprobes();
+	if (ret < 0)
+		errors++;
+
+	num_tests++;
 	ret = test_jprobe();
 	if (ret < 0)
 		errors++;
 
+	num_tests++;
+	ret = test_jprobes();
+	if (ret < 0)
+		errors++;
+
 #ifdef CONFIG_KRETPROBES
 	num_tests++;
 	ret = test_kretprobe();
 	if (ret < 0)
 		errors++;
+
+	num_tests++;
+	ret = test_kretprobes();
+	if (ret < 0)
+		errors++;
 #endif /* CONFIG_KRETPROBES */
 
 	if (errors)
diff --git a/kernel/time.c b/kernel/time.c
index d63a4336fad6..4886e3ce83a4 100644
--- a/kernel/time.c
+++ b/kernel/time.c
@@ -37,6 +37,7 @@
 #include <linux/fs.h>
 #include <linux/slab.h>
 #include <linux/math64.h>
+#include <linux/ptrace.h>
 
 #include <asm/uaccess.h>
 #include <asm/unistd.h>
@@ -65,8 +66,9 @@ asmlinkage long sys_time(time_t __user * tloc)
 
 	if (tloc) {
 		if (put_user(i,tloc))
-			i = -EFAULT;
+			return -EFAULT;
 	}
+	force_successful_syscall_return();
 	return i;
 }
 
diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c
index f8d968063cea..ea2f48af83cf 100644
--- a/kernel/time/clockevents.c
+++ b/kernel/time/clockevents.c
@@ -166,6 +166,8 @@ static void clockevents_notify_released(void)
 void clockevents_register_device(struct clock_event_device *dev)
 {
 	BUG_ON(dev->mode != CLOCK_EVT_MODE_UNUSED);
+	BUG_ON(!dev->cpumask);
+
 	/*
 	 * A nsec2cyc multiplicator of 0 is invalid and we'd crash
 	 * on it, so fix it up and emit a warning:
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index 9ed2eec97526..ca89e1593f08 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -145,10 +145,11 @@ static void clocksource_watchdog(unsigned long data)
 		 * Cycle through CPUs to check if the CPUs stay
 		 * synchronized to each other.
 		 */
-		int next_cpu = next_cpu_nr(raw_smp_processor_id(), cpu_online_map);
+		int next_cpu = cpumask_next(raw_smp_processor_id(),
+					    cpu_online_mask);
 
 		if (next_cpu >= nr_cpu_ids)
-			next_cpu = first_cpu(cpu_online_map);
+			next_cpu = cpumask_first(cpu_online_mask);
 		watchdog_timer.expires += WATCHDOG_INTERVAL;
 		add_timer_on(&watchdog_timer, next_cpu);
 	}
@@ -173,7 +174,7 @@ static void clocksource_check_watchdog(struct clocksource *cs)
 			watchdog_last = watchdog->read();
 			watchdog_timer.expires = jiffies + WATCHDOG_INTERVAL;
 			add_timer_on(&watchdog_timer,
-				     first_cpu(cpu_online_map));
+				     cpumask_first(cpu_online_mask));
 		}
 	} else {
 		if (cs->flags & CLOCK_SOURCE_IS_CONTINUOUS)
@@ -195,7 +196,7 @@ static void clocksource_check_watchdog(struct clocksource *cs)
 				watchdog_timer.expires =
 					jiffies + WATCHDOG_INTERVAL;
 				add_timer_on(&watchdog_timer,
-					     first_cpu(cpu_online_map));
+					     cpumask_first(cpu_online_mask));
 			}
 		}
 	}
diff --git a/kernel/time/jiffies.c b/kernel/time/jiffies.c
index 1ca99557e929..06f197560f3b 100644
--- a/kernel/time/jiffies.c
+++ b/kernel/time/jiffies.c
@@ -45,7 +45,7 @@
  *
  * The value 8 is somewhat carefully chosen, as anything
  * larger can result in overflows. NSEC_PER_JIFFY grows as
- * HZ shrinks, so values greater then 8 overflow 32bits when
+ * HZ shrinks, so values greater than 8 overflow 32bits when
  * HZ=100.
  */
 #define JIFFIES_SHIFT	8
diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c
index 8ff15e5d486b..f5f793d92415 100644
--- a/kernel/time/ntp.c
+++ b/kernel/time/ntp.c
@@ -131,7 +131,7 @@ static enum hrtimer_restart ntp_leap_second(struct hrtimer *timer)
 {
 	enum hrtimer_restart res = HRTIMER_NORESTART;
 
-	write_seqlock_irq(&xtime_lock);
+	write_seqlock(&xtime_lock);
 
 	switch (time_state) {
 	case TIME_OK:
@@ -164,7 +164,7 @@ static enum hrtimer_restart ntp_leap_second(struct hrtimer *timer)
 	}
 	update_vsyscall(&xtime, clock);
 
-	write_sequnlock_irq(&xtime_lock);
+	write_sequnlock(&xtime_lock);
 
 	return res;
 }
diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
index f98a1b7b16e9..118a3b3b3f9a 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -28,7 +28,9 @@
  */
 
 struct tick_device tick_broadcast_device;
-static cpumask_t tick_broadcast_mask;
+/* FIXME: Use cpumask_var_t. */
+static DECLARE_BITMAP(tick_broadcast_mask, NR_CPUS);
+static DECLARE_BITMAP(tmpmask, NR_CPUS);
 static DEFINE_SPINLOCK(tick_broadcast_lock);
 static int tick_broadcast_force;
 
@@ -46,9 +48,9 @@ struct tick_device *tick_get_broadcast_device(void)
 	return &tick_broadcast_device;
 }
 
-cpumask_t *tick_get_broadcast_mask(void)
+struct cpumask *tick_get_broadcast_mask(void)
 {
-	return &tick_broadcast_mask;
+	return to_cpumask(tick_broadcast_mask);
 }
 
 /*
@@ -72,7 +74,7 @@ int tick_check_broadcast_device(struct clock_event_device *dev)
 
 	clockevents_exchange_device(NULL, dev);
 	tick_broadcast_device.evtdev = dev;
-	if (!cpus_empty(tick_broadcast_mask))
+	if (!cpumask_empty(tick_get_broadcast_mask()))
 		tick_broadcast_start_periodic(dev);
 	return 1;
 }
@@ -104,7 +106,7 @@ int tick_device_uses_broadcast(struct clock_event_device *dev, int cpu)
 	 */
 	if (!tick_device_is_functional(dev)) {
 		dev->event_handler = tick_handle_periodic;
-		cpu_set(cpu, tick_broadcast_mask);
+		cpumask_set_cpu(cpu, tick_get_broadcast_mask());
 		tick_broadcast_start_periodic(tick_broadcast_device.evtdev);
 		ret = 1;
 	} else {
@@ -116,7 +118,7 @@ int tick_device_uses_broadcast(struct clock_event_device *dev, int cpu)
 		if (!(dev->features & CLOCK_EVT_FEAT_C3STOP)) {
 			int cpu = smp_processor_id();
 
-			cpu_clear(cpu, tick_broadcast_mask);
+			cpumask_clear_cpu(cpu, tick_get_broadcast_mask());
 			tick_broadcast_clear_oneshot(cpu);
 		}
 	}
@@ -125,9 +127,9 @@ int tick_device_uses_broadcast(struct clock_event_device *dev, int cpu)
 }
 
 /*
- * Broadcast the event to the cpus, which are set in the mask
+ * Broadcast the event to the cpus, which are set in the mask (mangled).
  */
-static void tick_do_broadcast(cpumask_t mask)
+static void tick_do_broadcast(struct cpumask *mask)
 {
 	int cpu = smp_processor_id();
 	struct tick_device *td;
@@ -135,21 +137,20 @@ static void tick_do_broadcast(cpumask_t mask)
 	/*
 	 * Check, if the current cpu is in the mask
 	 */
-	if (cpu_isset(cpu, mask)) {
-		cpu_clear(cpu, mask);
+	if (cpumask_test_cpu(cpu, mask)) {
+		cpumask_clear_cpu(cpu, mask);
 		td = &per_cpu(tick_cpu_device, cpu);
 		td->evtdev->event_handler(td->evtdev);
 	}
 
-	if (!cpus_empty(mask)) {
+	if (!cpumask_empty(mask)) {
 		/*
 		 * It might be necessary to actually check whether the devices
 		 * have different broadcast functions. For now, just use the
 		 * one of the first device. This works as long as we have this
 		 * misfeature only on x86 (lapic)
 		 */
-		cpu = first_cpu(mask);
-		td = &per_cpu(tick_cpu_device, cpu);
+		td = &per_cpu(tick_cpu_device, cpumask_first(mask));
 		td->evtdev->broadcast(mask);
 	}
 }
@@ -160,12 +161,11 @@ static void tick_do_broadcast(cpumask_t mask)
  */
 static void tick_do_periodic_broadcast(void)
 {
-	cpumask_t mask;
-
 	spin_lock(&tick_broadcast_lock);
 
-	cpus_and(mask, cpu_online_map, tick_broadcast_mask);
-	tick_do_broadcast(mask);
+	cpumask_and(to_cpumask(tmpmask),
+		    cpu_online_mask, tick_get_broadcast_mask());
+	tick_do_broadcast(to_cpumask(tmpmask));
 
 	spin_unlock(&tick_broadcast_lock);
 }
@@ -228,13 +228,13 @@ static void tick_do_broadcast_on_off(void *why)
 	if (!tick_device_is_functional(dev))
 		goto out;
 
-	bc_stopped = cpus_empty(tick_broadcast_mask);
+	bc_stopped = cpumask_empty(tick_get_broadcast_mask());
 
 	switch (*reason) {
 	case CLOCK_EVT_NOTIFY_BROADCAST_ON:
 	case CLOCK_EVT_NOTIFY_BROADCAST_FORCE:
-		if (!cpu_isset(cpu, tick_broadcast_mask)) {
-			cpu_set(cpu, tick_broadcast_mask);
+		if (!cpumask_test_cpu(cpu, tick_get_broadcast_mask())) {
+			cpumask_set_cpu(cpu, tick_get_broadcast_mask());
 			if (tick_broadcast_device.mode ==
 			    TICKDEV_MODE_PERIODIC)
 				clockevents_shutdown(dev);
@@ -244,8 +244,8 @@ static void tick_do_broadcast_on_off(void *why)
 		break;
 	case CLOCK_EVT_NOTIFY_BROADCAST_OFF:
 		if (!tick_broadcast_force &&
-		    cpu_isset(cpu, tick_broadcast_mask)) {
-			cpu_clear(cpu, tick_broadcast_mask);
+		    cpumask_test_cpu(cpu, tick_get_broadcast_mask())) {
+			cpumask_clear_cpu(cpu, tick_get_broadcast_mask());
 			if (tick_broadcast_device.mode ==
 			    TICKDEV_MODE_PERIODIC)
 				tick_setup_periodic(dev, 0);
@@ -253,7 +253,7 @@ static void tick_do_broadcast_on_off(void *why)
 		break;
 	}
 
-	if (cpus_empty(tick_broadcast_mask)) {
+	if (cpumask_empty(tick_get_broadcast_mask())) {
 		if (!bc_stopped)
 			clockevents_shutdown(bc);
 	} else if (bc_stopped) {
@@ -272,7 +272,7 @@ out:
  */
 void tick_broadcast_on_off(unsigned long reason, int *oncpu)
 {
-	if (!cpu_isset(*oncpu, cpu_online_map))
+	if (!cpumask_test_cpu(*oncpu, cpu_online_mask))
 		printk(KERN_ERR "tick-broadcast: ignoring broadcast for "
 		       "offline CPU #%d\n", *oncpu);
 	else
@@ -303,10 +303,10 @@ void tick_shutdown_broadcast(unsigned int *cpup)
 	spin_lock_irqsave(&tick_broadcast_lock, flags);
 
 	bc = tick_broadcast_device.evtdev;
-	cpu_clear(cpu, tick_broadcast_mask);
+	cpumask_clear_cpu(cpu, tick_get_broadcast_mask());
 
 	if (tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC) {
-		if (bc && cpus_empty(tick_broadcast_mask))
+		if (bc && cpumask_empty(tick_get_broadcast_mask()))
 			clockevents_shutdown(bc);
 	}
 
@@ -342,10 +342,10 @@ int tick_resume_broadcast(void)
 
 		switch (tick_broadcast_device.mode) {
 		case TICKDEV_MODE_PERIODIC:
-			if(!cpus_empty(tick_broadcast_mask))
+			if (!cpumask_empty(tick_get_broadcast_mask()))
 				tick_broadcast_start_periodic(bc);
-			broadcast = cpu_isset(smp_processor_id(),
-					      tick_broadcast_mask);
+			broadcast = cpumask_test_cpu(smp_processor_id(),
+						     tick_get_broadcast_mask());
 			break;
 		case TICKDEV_MODE_ONESHOT:
 			broadcast = tick_resume_broadcast_oneshot(bc);
@@ -360,14 +360,15 @@ int tick_resume_broadcast(void)
 
 #ifdef CONFIG_TICK_ONESHOT
 
-static cpumask_t tick_broadcast_oneshot_mask;
+/* FIXME: use cpumask_var_t. */
+static DECLARE_BITMAP(tick_broadcast_oneshot_mask, NR_CPUS);
 
 /*
- * Debugging: see timer_list.c
+ * Exposed for debugging: see timer_list.c
  */
-cpumask_t *tick_get_broadcast_oneshot_mask(void)
+struct cpumask *tick_get_broadcast_oneshot_mask(void)
 {
-	return &tick_broadcast_oneshot_mask;
+	return to_cpumask(tick_broadcast_oneshot_mask);
 }
 
 static int tick_broadcast_set_event(ktime_t expires, int force)
@@ -389,7 +390,7 @@ int tick_resume_broadcast_oneshot(struct clock_event_device *bc)
  */
 void tick_check_oneshot_broadcast(int cpu)
 {
-	if (cpu_isset(cpu, tick_broadcast_oneshot_mask)) {
+	if (cpumask_test_cpu(cpu, to_cpumask(tick_broadcast_oneshot_mask))) {
 		struct tick_device *td = &per_cpu(tick_cpu_device, cpu);
 
 		clockevents_set_mode(td->evtdev, CLOCK_EVT_MODE_ONESHOT);
@@ -402,7 +403,6 @@ void tick_check_oneshot_broadcast(int cpu)
 static void tick_handle_oneshot_broadcast(struct clock_event_device *dev)
 {
 	struct tick_device *td;
-	cpumask_t mask;
 	ktime_t now, next_event;
 	int cpu;
 
@@ -410,13 +410,13 @@ static void tick_handle_oneshot_broadcast(struct clock_event_device *dev)
 again:
 	dev->next_event.tv64 = KTIME_MAX;
 	next_event.tv64 = KTIME_MAX;
-	mask = CPU_MASK_NONE;
+	cpumask_clear(to_cpumask(tmpmask));
 	now = ktime_get();
 	/* Find all expired events */
-	for_each_cpu_mask_nr(cpu, tick_broadcast_oneshot_mask) {
+	for_each_cpu(cpu, tick_get_broadcast_oneshot_mask()) {
 		td = &per_cpu(tick_cpu_device, cpu);
 		if (td->evtdev->next_event.tv64 <= now.tv64)
-			cpu_set(cpu, mask);
+			cpumask_set_cpu(cpu, to_cpumask(tmpmask));
 		else if (td->evtdev->next_event.tv64 < next_event.tv64)
 			next_event.tv64 = td->evtdev->next_event.tv64;
 	}
@@ -424,7 +424,7 @@ again:
 	/*
 	 * Wakeup the cpus which have an expired event.
 	 */
-	tick_do_broadcast(mask);
+	tick_do_broadcast(to_cpumask(tmpmask));
 
 	/*
 	 * Two reasons for reprogram:
@@ -476,15 +476,16 @@ void tick_broadcast_oneshot_control(unsigned long reason)
 		goto out;
 
 	if (reason == CLOCK_EVT_NOTIFY_BROADCAST_ENTER) {
-		if (!cpu_isset(cpu, tick_broadcast_oneshot_mask)) {
-			cpu_set(cpu, tick_broadcast_oneshot_mask);
+		if (!cpumask_test_cpu(cpu, tick_get_broadcast_oneshot_mask())) {
+			cpumask_set_cpu(cpu, tick_get_broadcast_oneshot_mask());
 			clockevents_set_mode(dev, CLOCK_EVT_MODE_SHUTDOWN);
 			if (dev->next_event.tv64 < bc->next_event.tv64)
 				tick_broadcast_set_event(dev->next_event, 1);
 		}
 	} else {
-		if (cpu_isset(cpu, tick_broadcast_oneshot_mask)) {
-			cpu_clear(cpu, tick_broadcast_oneshot_mask);
+		if (cpumask_test_cpu(cpu, tick_get_broadcast_oneshot_mask())) {
+			cpumask_clear_cpu(cpu,
+					  tick_get_broadcast_oneshot_mask());
 			clockevents_set_mode(dev, CLOCK_EVT_MODE_ONESHOT);
 			if (dev->next_event.tv64 != KTIME_MAX)
 				tick_program_event(dev->next_event, 1);
@@ -502,15 +503,16 @@ out:
  */
 static void tick_broadcast_clear_oneshot(int cpu)
 {
-	cpu_clear(cpu, tick_broadcast_oneshot_mask);
+	cpumask_clear_cpu(cpu, tick_get_broadcast_oneshot_mask());
 }
 
-static void tick_broadcast_init_next_event(cpumask_t *mask, ktime_t expires)
+static void tick_broadcast_init_next_event(struct cpumask *mask,
+					   ktime_t expires)
 {
 	struct tick_device *td;
 	int cpu;
 
-	for_each_cpu_mask_nr(cpu, *mask) {
+	for_each_cpu(cpu, mask) {
 		td = &per_cpu(tick_cpu_device, cpu);
 		if (td->evtdev)
 			td->evtdev->next_event = expires;
@@ -526,7 +528,6 @@ void tick_broadcast_setup_oneshot(struct clock_event_device *bc)
 	if (bc->event_handler != tick_handle_oneshot_broadcast) {
 		int was_periodic = bc->mode == CLOCK_EVT_MODE_PERIODIC;
 		int cpu = smp_processor_id();
-		cpumask_t mask;
 
 		bc->event_handler = tick_handle_oneshot_broadcast;
 		clockevents_set_mode(bc, CLOCK_EVT_MODE_ONESHOT);
@@ -540,13 +541,15 @@ void tick_broadcast_setup_oneshot(struct clock_event_device *bc)
 		 * oneshot_mask bits for those and program the
 		 * broadcast device to fire.
 		 */
-		mask = tick_broadcast_mask;
-		cpu_clear(cpu, mask);
-		cpus_or(tick_broadcast_oneshot_mask,
-			tick_broadcast_oneshot_mask, mask);
-
-		if (was_periodic && !cpus_empty(mask)) {
-			tick_broadcast_init_next_event(&mask, tick_next_period);
+		cpumask_copy(to_cpumask(tmpmask), tick_get_broadcast_mask());
+		cpumask_clear_cpu(cpu, to_cpumask(tmpmask));
+		cpumask_or(tick_get_broadcast_oneshot_mask(),
+			   tick_get_broadcast_oneshot_mask(),
+			   to_cpumask(tmpmask));
+
+		if (was_periodic && !cpumask_empty(to_cpumask(tmpmask))) {
+			tick_broadcast_init_next_event(to_cpumask(tmpmask),
+						       tick_next_period);
 			tick_broadcast_set_event(tick_next_period, 1);
 		} else
 			bc->next_event.tv64 = KTIME_MAX;
@@ -585,7 +588,7 @@ void tick_shutdown_broadcast_oneshot(unsigned int *cpup)
 	 * Clear the broadcast mask flag for the dead cpu, but do not
 	 * stop the broadcast device!
 	 */
-	cpu_clear(cpu, tick_broadcast_oneshot_mask);
+	cpumask_clear_cpu(cpu, tick_get_broadcast_oneshot_mask());
 
 	spin_unlock_irqrestore(&tick_broadcast_lock, flags);
 }
diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c
index df12434b43ca..63e05d423a09 100644
--- a/kernel/time/tick-common.c
+++ b/kernel/time/tick-common.c
@@ -136,7 +136,7 @@ void tick_setup_periodic(struct clock_event_device *dev, int broadcast)
  */
 static void tick_setup_device(struct tick_device *td,
 			      struct clock_event_device *newdev, int cpu,
-			      const cpumask_t *cpumask)
+			      const struct cpumask *cpumask)
 {
 	ktime_t next_event;
 	void (*handler)(struct clock_event_device *) = NULL;
@@ -171,8 +171,8 @@ static void tick_setup_device(struct tick_device *td,
 	 * When the device is not per cpu, pin the interrupt to the
 	 * current cpu:
 	 */
-	if (!cpus_equal(newdev->cpumask, *cpumask))
-		irq_set_affinity(newdev->irq, *cpumask);
+	if (!cpumask_equal(newdev->cpumask, cpumask))
+		irq_set_affinity(newdev->irq, cpumask);
 
 	/*
 	 * When global broadcasting is active, check if the current
@@ -202,14 +202,14 @@ static int tick_check_new_device(struct clock_event_device *newdev)
 	spin_lock_irqsave(&tick_device_lock, flags);
 
 	cpu = smp_processor_id();
-	if (!cpu_isset(cpu, newdev->cpumask))
+	if (!cpumask_test_cpu(cpu, newdev->cpumask))
 		goto out_bc;
 
 	td = &per_cpu(tick_cpu_device, cpu);
 	curdev = td->evtdev;
 
 	/* cpu local device ? */
-	if (!cpus_equal(newdev->cpumask, cpumask_of_cpu(cpu))) {
+	if (!cpumask_equal(newdev->cpumask, cpumask_of(cpu))) {
 
 		/*
 		 * If the cpu affinity of the device interrupt can not
@@ -222,7 +222,7 @@ static int tick_check_new_device(struct clock_event_device *newdev)
 		 * If we have a cpu local device already, do not replace it
 		 * by a non cpu local device
 		 */
-		if (curdev && cpus_equal(curdev->cpumask, cpumask_of_cpu(cpu)))
+		if (curdev && cpumask_equal(curdev->cpumask, cpumask_of(cpu)))
 			goto out_bc;
 	}
 
@@ -254,7 +254,7 @@ static int tick_check_new_device(struct clock_event_device *newdev)
 		curdev = NULL;
 	}
 	clockevents_exchange_device(curdev, newdev);
-	tick_setup_device(td, newdev, cpu, &cpumask_of_cpu(cpu));
+	tick_setup_device(td, newdev, cpu, cpumask_of(cpu));
 	if (newdev->features & CLOCK_EVT_FEAT_ONESHOT)
 		tick_oneshot_notify();
 
@@ -299,9 +299,9 @@ static void tick_shutdown(unsigned int *cpup)
 	}
 	/* Transfer the do_timer job away from this cpu */
 	if (*cpup == tick_do_timer_cpu) {
-		int cpu = first_cpu(cpu_online_map);
+		int cpu = cpumask_first(cpu_online_mask);
 
-		tick_do_timer_cpu = (cpu != NR_CPUS) ? cpu :
+		tick_do_timer_cpu = (cpu < nr_cpu_ids) ? cpu :
 			TICK_DO_TIMER_NONE;
 	}
 	spin_unlock_irqrestore(&tick_device_lock, flags);
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 342fc9ccab46..1b6c05bd0d0a 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -144,7 +144,7 @@ void tick_nohz_update_jiffies(void)
 	if (!ts->tick_stopped)
 		return;
 
-	cpu_clear(cpu, nohz_cpu_mask);
+	cpumask_clear_cpu(cpu, nohz_cpu_mask);
 	now = ktime_get();
 	ts->idle_waketime = now;
 
@@ -247,7 +247,7 @@ void tick_nohz_stop_sched_tick(int inidle)
 	if (need_resched())
 		goto end;
 
-	if (unlikely(local_softirq_pending())) {
+	if (unlikely(local_softirq_pending() && cpu_online(cpu))) {
 		static int ratelimit;
 
 		if (ratelimit < 10) {
@@ -282,8 +282,31 @@ void tick_nohz_stop_sched_tick(int inidle)
 	/* Schedule the tick, if we are at least one jiffie off */
 	if ((long)delta_jiffies >= 1) {
 
+		/*
+		* calculate the expiry time for the next timer wheel
+		* timer
+		*/
+		expires = ktime_add_ns(last_update, tick_period.tv64 *
+				   delta_jiffies);
+
+		/*
+		 * If this cpu is the one which updates jiffies, then
+		 * give up the assignment and let it be taken by the
+		 * cpu which runs the tick timer next, which might be
+		 * this cpu as well. If we don't drop this here the
+		 * jiffies might be stale and do_timer() never
+		 * invoked.
+		 */
+		if (cpu == tick_do_timer_cpu)
+			tick_do_timer_cpu = TICK_DO_TIMER_NONE;
+
 		if (delta_jiffies > 1)
-			cpu_set(cpu, nohz_cpu_mask);
+			cpumask_set_cpu(cpu, nohz_cpu_mask);
+
+		/* Skip reprogram of event if its not changed */
+		if (ts->tick_stopped && ktime_equal(expires, dev->next_event))
+			goto out;
+
 		/*
 		 * nohz_stop_sched_tick can be called several times before
 		 * the nohz_restart_sched_tick is called. This happens when
@@ -296,7 +319,7 @@ void tick_nohz_stop_sched_tick(int inidle)
 				/*
 				 * sched tick not stopped!
 				 */
-				cpu_clear(cpu, nohz_cpu_mask);
+				cpumask_clear_cpu(cpu, nohz_cpu_mask);
 				goto out;
 			}
 
@@ -306,17 +329,6 @@ void tick_nohz_stop_sched_tick(int inidle)
 			rcu_enter_nohz();
 		}
 
-		/*
-		 * If this cpu is the one which updates jiffies, then
-		 * give up the assignment and let it be taken by the
-		 * cpu which runs the tick timer next, which might be
-		 * this cpu as well. If we don't drop this here the
-		 * jiffies might be stale and do_timer() never
-		 * invoked.
-		 */
-		if (cpu == tick_do_timer_cpu)
-			tick_do_timer_cpu = TICK_DO_TIMER_NONE;
-
 		ts->idle_sleeps++;
 
 		/*
@@ -332,12 +344,7 @@ void tick_nohz_stop_sched_tick(int inidle)
 			goto out;
 		}
 
-		/*
-		 * calculate the expiry time for the next timer wheel
-		 * timer
-		 */
-		expires = ktime_add_ns(last_update, tick_period.tv64 *
-				       delta_jiffies);
+		/* Mark expiries */
 		ts->idle_expires = expires;
 
 		if (ts->nohz_mode == NOHZ_MODE_HIGHRES) {
@@ -354,7 +361,7 @@ void tick_nohz_stop_sched_tick(int inidle)
 		 * softirq.
 		 */
 		tick_do_update_jiffies64(ktime_get());
-		cpu_clear(cpu, nohz_cpu_mask);
+		cpumask_clear_cpu(cpu, nohz_cpu_mask);
 	}
 	raise_softirq_irqoff(TIMER_SOFTIRQ);
 out:
@@ -412,7 +419,9 @@ void tick_nohz_restart_sched_tick(void)
 {
 	int cpu = smp_processor_id();
 	struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
+#ifndef CONFIG_VIRT_CPU_ACCOUNTING
 	unsigned long ticks;
+#endif
 	ktime_t now;
 
 	local_irq_disable();
@@ -432,8 +441,9 @@ void tick_nohz_restart_sched_tick(void)
 	select_nohz_load_balancer(0);
 	now = ktime_get();
 	tick_do_update_jiffies64(now);
-	cpu_clear(cpu, nohz_cpu_mask);
+	cpumask_clear_cpu(cpu, nohz_cpu_mask);
 
+#ifndef CONFIG_VIRT_CPU_ACCOUNTING
 	/*
 	 * We stopped the tick in idle. Update process times would miss the
 	 * time we slept as update_process_times does only a 1 tick
@@ -443,12 +453,9 @@ void tick_nohz_restart_sched_tick(void)
 	/*
 	 * We might be one off. Do not randomly account a huge number of ticks!
 	 */
-	if (ticks && ticks < LONG_MAX) {
-		add_preempt_count(HARDIRQ_OFFSET);
-		account_system_time(current, HARDIRQ_OFFSET,
-				    jiffies_to_cputime(ticks));
-		sub_preempt_count(HARDIRQ_OFFSET);
-	}
+	if (ticks && ticks < LONG_MAX)
+		account_idle_ticks(ticks);
+#endif
 
 	touch_softlockup_watchdog();
 	/*
@@ -681,7 +688,6 @@ void tick_setup_sched_timer(void)
 	 */
 	hrtimer_init(&ts->sched_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
 	ts->sched_timer.function = tick_sched_timer;
-	ts->sched_timer.cb_mode = HRTIMER_CB_IRQSAFE_PERCPU;
 
 	/* Get the next period (per cpu) */
 	hrtimer_set_expires(&ts->sched_timer, tick_init_jiffy_update());
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index fa05e88aa76f..900f1b6598d1 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -46,6 +46,9 @@ struct timespec xtime __attribute__ ((aligned (16)));
 struct timespec wall_to_monotonic __attribute__ ((aligned (16)));
 static unsigned long total_sleep_time;		/* seconds */
 
+/* flag for if timekeeping is suspended */
+int __read_mostly timekeeping_suspended;
+
 static struct timespec xtime_cache __attribute__ ((aligned (16)));
 void update_xtime_cache(u64 nsec)
 {
@@ -92,6 +95,8 @@ void getnstimeofday(struct timespec *ts)
 	unsigned long seq;
 	s64 nsecs;
 
+	WARN_ON(timekeeping_suspended);
+
 	do {
 		seq = read_seqbegin(&xtime_lock);
 
@@ -299,8 +304,6 @@ void __init timekeeping_init(void)
 	write_sequnlock_irqrestore(&xtime_lock, flags);
 }
 
-/* flag for if timekeeping is suspended */
-static int timekeeping_suspended;
 /* time in seconds when suspend began */
 static unsigned long timekeeping_suspend_time;
 
diff --git a/kernel/timer.c b/kernel/timer.c
index 566257d1dc10..dee3f641a7a7 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -1018,21 +1018,6 @@ unsigned long get_next_timer_interrupt(unsigned long now)
 }
 #endif
 
-#ifndef CONFIG_VIRT_CPU_ACCOUNTING
-void account_process_tick(struct task_struct *p, int user_tick)
-{
-	cputime_t one_jiffy = jiffies_to_cputime(1);
-
-	if (user_tick) {
-		account_user_time(p, one_jiffy);
-		account_user_time_scaled(p, cputime_to_scaled(one_jiffy));
-	} else {
-		account_system_time(p, HARDIRQ_OFFSET, one_jiffy);
-		account_system_time_scaled(p, cputime_to_scaled(one_jiffy));
-	}
-}
-#endif
-
 /*
  * Called from the timer interrupt handler to charge one tick to the current
  * process.  user_tick is 1 if the tick is user time, 0 for system.
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 76f34c0ef29c..8b0daf0662ef 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -69,6 +69,7 @@ void tracing_on(void)
 {
 	set_bit(RB_BUFFERS_ON_BIT, &ring_buffer_flags);
 }
+EXPORT_SYMBOL_GPL(tracing_on);
 
 /**
  * tracing_off - turn off all tracing buffers
@@ -82,6 +83,7 @@ void tracing_off(void)
 {
 	clear_bit(RB_BUFFERS_ON_BIT, &ring_buffer_flags);
 }
+EXPORT_SYMBOL_GPL(tracing_off);
 
 /**
  * tracing_off_permanent - permanently disable ring buffers
@@ -111,12 +113,14 @@ u64 ring_buffer_time_stamp(int cpu)
 
 	return time;
 }
+EXPORT_SYMBOL_GPL(ring_buffer_time_stamp);
 
 void ring_buffer_normalize_time_stamp(int cpu, u64 *ts)
 {
 	/* Just stupid testing the normalize function and deltas */
 	*ts >>= DEBUG_SHIFT;
 }
+EXPORT_SYMBOL_GPL(ring_buffer_normalize_time_stamp);
 
 #define RB_EVNT_HDR_SIZE (sizeof(struct ring_buffer_event))
 #define RB_ALIGNMENT_SHIFT	2
@@ -164,8 +168,15 @@ rb_event_length(struct ring_buffer_event *event)
  */
 unsigned ring_buffer_event_length(struct ring_buffer_event *event)
 {
-	return rb_event_length(event);
+	unsigned length = rb_event_length(event);
+	if (event->type != RINGBUF_TYPE_DATA)
+		return length;
+	length -= RB_EVNT_HDR_SIZE;
+	if (length > RB_MAX_SMALL_DATA + sizeof(event->array[0]))
+                length -= sizeof(event->array[0]);
+	return length;
 }
+EXPORT_SYMBOL_GPL(ring_buffer_event_length);
 
 /* inline for ring buffer fast paths */
 static inline void *
@@ -187,9 +198,10 @@ void *ring_buffer_event_data(struct ring_buffer_event *event)
 {
 	return rb_event_data(event);
 }
+EXPORT_SYMBOL_GPL(ring_buffer_event_data);
 
 #define for_each_buffer_cpu(buffer, cpu)		\
-	for_each_cpu_mask(cpu, buffer->cpumask)
+	for_each_cpu(cpu, buffer->cpumask)
 
 #define TS_SHIFT	27
 #define TS_MASK		((1ULL << TS_SHIFT) - 1)
@@ -261,7 +273,7 @@ struct ring_buffer {
 	unsigned			pages;
 	unsigned			flags;
 	int				cpus;
-	cpumask_t			cpumask;
+	cpumask_var_t			cpumask;
 	atomic_t			record_disabled;
 
 	struct mutex			mutex;
@@ -427,7 +439,7 @@ extern int ring_buffer_page_too_big(void);
 
 /**
  * ring_buffer_alloc - allocate a new ring_buffer
- * @size: the size in bytes that is needed.
+ * @size: the size in bytes per cpu that is needed.
  * @flags: attributes to set for the ring buffer.
  *
  * Currently the only flag that is available is the RB_FL_OVERWRITE
@@ -452,6 +464,9 @@ struct ring_buffer *ring_buffer_alloc(unsigned long size, unsigned flags)
 	if (!buffer)
 		return NULL;
 
+	if (!alloc_cpumask_var(&buffer->cpumask, GFP_KERNEL))
+		goto fail_free_buffer;
+
 	buffer->pages = DIV_ROUND_UP(size, BUF_PAGE_SIZE);
 	buffer->flags = flags;
 
@@ -459,14 +474,14 @@ struct ring_buffer *ring_buffer_alloc(unsigned long size, unsigned flags)
 	if (buffer->pages == 1)
 		buffer->pages++;
 
-	buffer->cpumask = cpu_possible_map;
+	cpumask_copy(buffer->cpumask, cpu_possible_mask);
 	buffer->cpus = nr_cpu_ids;
 
 	bsize = sizeof(void *) * nr_cpu_ids;
 	buffer->buffers = kzalloc(ALIGN(bsize, cache_line_size()),
 				  GFP_KERNEL);
 	if (!buffer->buffers)
-		goto fail_free_buffer;
+		goto fail_free_cpumask;
 
 	for_each_buffer_cpu(buffer, cpu) {
 		buffer->buffers[cpu] =
@@ -486,10 +501,14 @@ struct ring_buffer *ring_buffer_alloc(unsigned long size, unsigned flags)
 	}
 	kfree(buffer->buffers);
 
+ fail_free_cpumask:
+	free_cpumask_var(buffer->cpumask);
+
  fail_free_buffer:
 	kfree(buffer);
 	return NULL;
 }
+EXPORT_SYMBOL_GPL(ring_buffer_alloc);
 
 /**
  * ring_buffer_free - free a ring buffer.
@@ -503,8 +522,11 @@ ring_buffer_free(struct ring_buffer *buffer)
 	for_each_buffer_cpu(buffer, cpu)
 		rb_free_cpu_buffer(buffer->buffers[cpu]);
 
+	free_cpumask_var(buffer->cpumask);
+
 	kfree(buffer);
 }
+EXPORT_SYMBOL_GPL(ring_buffer_free);
 
 static void rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer);
 
@@ -680,6 +702,7 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size)
 	mutex_unlock(&buffer->mutex);
 	return -ENOMEM;
 }
+EXPORT_SYMBOL_GPL(ring_buffer_resize);
 
 static inline int rb_null_event(struct ring_buffer_event *event)
 {
@@ -1274,7 +1297,7 @@ ring_buffer_lock_reserve(struct ring_buffer *buffer,
 
 	cpu = raw_smp_processor_id();
 
-	if (!cpu_isset(cpu, buffer->cpumask))
+	if (!cpumask_test_cpu(cpu, buffer->cpumask))
 		goto out;
 
 	cpu_buffer = buffer->buffers[cpu];
@@ -1304,6 +1327,7 @@ ring_buffer_lock_reserve(struct ring_buffer *buffer,
 	ftrace_preempt_enable(resched);
 	return NULL;
 }
+EXPORT_SYMBOL_GPL(ring_buffer_lock_reserve);
 
 static void rb_commit(struct ring_buffer_per_cpu *cpu_buffer,
 		      struct ring_buffer_event *event)
@@ -1350,6 +1374,7 @@ int ring_buffer_unlock_commit(struct ring_buffer *buffer,
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(ring_buffer_unlock_commit);
 
 /**
  * ring_buffer_write - write data to the buffer without reserving
@@ -1385,7 +1410,7 @@ int ring_buffer_write(struct ring_buffer *buffer,
 
 	cpu = raw_smp_processor_id();
 
-	if (!cpu_isset(cpu, buffer->cpumask))
+	if (!cpumask_test_cpu(cpu, buffer->cpumask))
 		goto out;
 
 	cpu_buffer = buffer->buffers[cpu];
@@ -1411,6 +1436,7 @@ int ring_buffer_write(struct ring_buffer *buffer,
 
 	return ret;
 }
+EXPORT_SYMBOL_GPL(ring_buffer_write);
 
 static inline int rb_per_cpu_empty(struct ring_buffer_per_cpu *cpu_buffer)
 {
@@ -1437,6 +1463,7 @@ void ring_buffer_record_disable(struct ring_buffer *buffer)
 {
 	atomic_inc(&buffer->record_disabled);
 }
+EXPORT_SYMBOL_GPL(ring_buffer_record_disable);
 
 /**
  * ring_buffer_record_enable - enable writes to the buffer
@@ -1449,6 +1476,7 @@ void ring_buffer_record_enable(struct ring_buffer *buffer)
 {
 	atomic_dec(&buffer->record_disabled);
 }
+EXPORT_SYMBOL_GPL(ring_buffer_record_enable);
 
 /**
  * ring_buffer_record_disable_cpu - stop all writes into the cpu_buffer
@@ -1464,12 +1492,13 @@ void ring_buffer_record_disable_cpu(struct ring_buffer *buffer, int cpu)
 {
 	struct ring_buffer_per_cpu *cpu_buffer;
 
-	if (!cpu_isset(cpu, buffer->cpumask))
+	if (!cpumask_test_cpu(cpu, buffer->cpumask))
 		return;
 
 	cpu_buffer = buffer->buffers[cpu];
 	atomic_inc(&cpu_buffer->record_disabled);
 }
+EXPORT_SYMBOL_GPL(ring_buffer_record_disable_cpu);
 
 /**
  * ring_buffer_record_enable_cpu - enable writes to the buffer
@@ -1483,12 +1512,13 @@ void ring_buffer_record_enable_cpu(struct ring_buffer *buffer, int cpu)
 {
 	struct ring_buffer_per_cpu *cpu_buffer;
 
-	if (!cpu_isset(cpu, buffer->cpumask))
+	if (!cpumask_test_cpu(cpu, buffer->cpumask))
 		return;
 
 	cpu_buffer = buffer->buffers[cpu];
 	atomic_dec(&cpu_buffer->record_disabled);
 }
+EXPORT_SYMBOL_GPL(ring_buffer_record_enable_cpu);
 
 /**
  * ring_buffer_entries_cpu - get the number of entries in a cpu buffer
@@ -1499,12 +1529,13 @@ unsigned long ring_buffer_entries_cpu(struct ring_buffer *buffer, int cpu)
 {
 	struct ring_buffer_per_cpu *cpu_buffer;
 
-	if (!cpu_isset(cpu, buffer->cpumask))
+	if (!cpumask_test_cpu(cpu, buffer->cpumask))
 		return 0;
 
 	cpu_buffer = buffer->buffers[cpu];
 	return cpu_buffer->entries;
 }
+EXPORT_SYMBOL_GPL(ring_buffer_entries_cpu);
 
 /**
  * ring_buffer_overrun_cpu - get the number of overruns in a cpu_buffer
@@ -1515,12 +1546,13 @@ unsigned long ring_buffer_overrun_cpu(struct ring_buffer *buffer, int cpu)
 {
 	struct ring_buffer_per_cpu *cpu_buffer;
 
-	if (!cpu_isset(cpu, buffer->cpumask))
+	if (!cpumask_test_cpu(cpu, buffer->cpumask))
 		return 0;
 
 	cpu_buffer = buffer->buffers[cpu];
 	return cpu_buffer->overrun;
 }
+EXPORT_SYMBOL_GPL(ring_buffer_overrun_cpu);
 
 /**
  * ring_buffer_entries - get the number of entries in a buffer
@@ -1543,6 +1575,7 @@ unsigned long ring_buffer_entries(struct ring_buffer *buffer)
 
 	return entries;
 }
+EXPORT_SYMBOL_GPL(ring_buffer_entries);
 
 /**
  * ring_buffer_overrun_cpu - get the number of overruns in buffer
@@ -1565,6 +1598,7 @@ unsigned long ring_buffer_overruns(struct ring_buffer *buffer)
 
 	return overruns;
 }
+EXPORT_SYMBOL_GPL(ring_buffer_overruns);
 
 static void rb_iter_reset(struct ring_buffer_iter *iter)
 {
@@ -1600,6 +1634,7 @@ void ring_buffer_iter_reset(struct ring_buffer_iter *iter)
 	rb_iter_reset(iter);
 	spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
 }
+EXPORT_SYMBOL_GPL(ring_buffer_iter_reset);
 
 /**
  * ring_buffer_iter_empty - check if an iterator has no more to read
@@ -1614,6 +1649,7 @@ int ring_buffer_iter_empty(struct ring_buffer_iter *iter)
 	return iter->head_page == cpu_buffer->commit_page &&
 		iter->head == rb_commit_index(cpu_buffer);
 }
+EXPORT_SYMBOL_GPL(ring_buffer_iter_empty);
 
 static void
 rb_update_read_stamp(struct ring_buffer_per_cpu *cpu_buffer,
@@ -1828,7 +1864,7 @@ rb_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts)
 	struct buffer_page *reader;
 	int nr_loops = 0;
 
-	if (!cpu_isset(cpu, buffer->cpumask))
+	if (!cpumask_test_cpu(cpu, buffer->cpumask))
 		return NULL;
 
 	cpu_buffer = buffer->buffers[cpu];
@@ -1880,6 +1916,7 @@ rb_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts)
 
 	return NULL;
 }
+EXPORT_SYMBOL_GPL(ring_buffer_peek);
 
 static struct ring_buffer_event *
 rb_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
@@ -1940,6 +1977,7 @@ rb_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
 
 	return NULL;
 }
+EXPORT_SYMBOL_GPL(ring_buffer_iter_peek);
 
 /**
  * ring_buffer_peek - peek at the next event to be read
@@ -2001,7 +2039,7 @@ ring_buffer_consume(struct ring_buffer *buffer, int cpu, u64 *ts)
 	struct ring_buffer_event *event;
 	unsigned long flags;
 
-	if (!cpu_isset(cpu, buffer->cpumask))
+	if (!cpumask_test_cpu(cpu, buffer->cpumask))
 		return NULL;
 
 	spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
@@ -2017,6 +2055,7 @@ ring_buffer_consume(struct ring_buffer *buffer, int cpu, u64 *ts)
 
 	return event;
 }
+EXPORT_SYMBOL_GPL(ring_buffer_consume);
 
 /**
  * ring_buffer_read_start - start a non consuming read of the buffer
@@ -2037,7 +2076,7 @@ ring_buffer_read_start(struct ring_buffer *buffer, int cpu)
 	struct ring_buffer_iter *iter;
 	unsigned long flags;
 
-	if (!cpu_isset(cpu, buffer->cpumask))
+	if (!cpumask_test_cpu(cpu, buffer->cpumask))
 		return NULL;
 
 	iter = kmalloc(sizeof(*iter), GFP_KERNEL);
@@ -2059,6 +2098,7 @@ ring_buffer_read_start(struct ring_buffer *buffer, int cpu)
 
 	return iter;
 }
+EXPORT_SYMBOL_GPL(ring_buffer_read_start);
 
 /**
  * ring_buffer_finish - finish reading the iterator of the buffer
@@ -2075,6 +2115,7 @@ ring_buffer_read_finish(struct ring_buffer_iter *iter)
 	atomic_dec(&cpu_buffer->record_disabled);
 	kfree(iter);
 }
+EXPORT_SYMBOL_GPL(ring_buffer_read_finish);
 
 /**
  * ring_buffer_read - read the next item in the ring buffer by the iterator
@@ -2101,6 +2142,7 @@ ring_buffer_read(struct ring_buffer_iter *iter, u64 *ts)
 
 	return event;
 }
+EXPORT_SYMBOL_GPL(ring_buffer_read);
 
 /**
  * ring_buffer_size - return the size of the ring buffer (in bytes)
@@ -2110,6 +2152,7 @@ unsigned long ring_buffer_size(struct ring_buffer *buffer)
 {
 	return BUF_PAGE_SIZE * buffer->pages;
 }
+EXPORT_SYMBOL_GPL(ring_buffer_size);
 
 static void
 rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer)
@@ -2143,7 +2186,7 @@ void ring_buffer_reset_cpu(struct ring_buffer *buffer, int cpu)
 	struct ring_buffer_per_cpu *cpu_buffer = buffer->buffers[cpu];
 	unsigned long flags;
 
-	if (!cpu_isset(cpu, buffer->cpumask))
+	if (!cpumask_test_cpu(cpu, buffer->cpumask))
 		return;
 
 	spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
@@ -2156,6 +2199,7 @@ void ring_buffer_reset_cpu(struct ring_buffer *buffer, int cpu)
 
 	spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
 }
+EXPORT_SYMBOL_GPL(ring_buffer_reset_cpu);
 
 /**
  * ring_buffer_reset - reset a ring buffer
@@ -2168,6 +2212,7 @@ void ring_buffer_reset(struct ring_buffer *buffer)
 	for_each_buffer_cpu(buffer, cpu)
 		ring_buffer_reset_cpu(buffer, cpu);
 }
+EXPORT_SYMBOL_GPL(ring_buffer_reset);
 
 /**
  * rind_buffer_empty - is the ring buffer empty?
@@ -2186,6 +2231,7 @@ int ring_buffer_empty(struct ring_buffer *buffer)
 	}
 	return 1;
 }
+EXPORT_SYMBOL_GPL(ring_buffer_empty);
 
 /**
  * ring_buffer_empty_cpu - is a cpu buffer of a ring buffer empty?
@@ -2196,12 +2242,13 @@ int ring_buffer_empty_cpu(struct ring_buffer *buffer, int cpu)
 {
 	struct ring_buffer_per_cpu *cpu_buffer;
 
-	if (!cpu_isset(cpu, buffer->cpumask))
+	if (!cpumask_test_cpu(cpu, buffer->cpumask))
 		return 1;
 
 	cpu_buffer = buffer->buffers[cpu];
 	return rb_per_cpu_empty(cpu_buffer);
 }
+EXPORT_SYMBOL_GPL(ring_buffer_empty_cpu);
 
 /**
  * ring_buffer_swap_cpu - swap a CPU buffer between two ring buffers
@@ -2219,8 +2266,8 @@ int ring_buffer_swap_cpu(struct ring_buffer *buffer_a,
 	struct ring_buffer_per_cpu *cpu_buffer_a;
 	struct ring_buffer_per_cpu *cpu_buffer_b;
 
-	if (!cpu_isset(cpu, buffer_a->cpumask) ||
-	    !cpu_isset(cpu, buffer_b->cpumask))
+	if (!cpumask_test_cpu(cpu, buffer_a->cpumask) ||
+	    !cpumask_test_cpu(cpu, buffer_b->cpumask))
 		return -EINVAL;
 
 	/* At least make sure the two buffers are somewhat the same */
@@ -2250,6 +2297,7 @@ int ring_buffer_swap_cpu(struct ring_buffer *buffer_a,
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(ring_buffer_swap_cpu);
 
 static void rb_remove_entries(struct ring_buffer_per_cpu *cpu_buffer,
 			      struct buffer_data_page *bpage)
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index f4bb3800318b..c580233add95 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -30,7 +30,6 @@
 #include <linux/gfp.h>
 #include <linux/fs.h>
 #include <linux/kprobes.h>
-#include <linux/seq_file.h>
 #include <linux/writeback.h>
 
 #include <linux/stacktrace.h>
@@ -90,10 +89,10 @@ static inline void ftrace_enable_cpu(void)
 	preempt_enable();
 }
 
-static cpumask_t __read_mostly		tracing_buffer_mask;
+static cpumask_var_t __read_mostly	tracing_buffer_mask;
 
 #define for_each_tracing_cpu(cpu)	\
-	for_each_cpu_mask(cpu, tracing_buffer_mask)
+	for_each_cpu(cpu, tracing_buffer_mask)
 
 /*
  * ftrace_dump_on_oops - variable to dump ftrace buffer on oops
@@ -1310,7 +1309,7 @@ enum trace_file_type {
 	TRACE_FILE_ANNOTATE	= 2,
 };
 
-static void trace_iterator_increment(struct trace_iterator *iter, int cpu)
+static void trace_iterator_increment(struct trace_iterator *iter)
 {
 	/* Don't allow ftrace to trace into the ring buffers */
 	ftrace_disable_cpu();
@@ -1389,7 +1388,7 @@ static void *find_next_entry_inc(struct trace_iterator *iter)
 	iter->ent = __find_next_entry(iter, &iter->cpu, &iter->ts);
 
 	if (iter->ent)
-		trace_iterator_increment(iter, iter->cpu);
+		trace_iterator_increment(iter);
 
 	return iter->ent ? iter : NULL;
 }
@@ -1812,10 +1811,10 @@ static void test_cpu_buff_start(struct trace_iterator *iter)
 	if (!(iter->iter_flags & TRACE_FILE_ANNOTATE))
 		return;
 
-	if (cpu_isset(iter->cpu, iter->started))
+	if (cpumask_test_cpu(iter->cpu, iter->started))
 		return;
 
-	cpu_set(iter->cpu, iter->started);
+	cpumask_set_cpu(iter->cpu, iter->started);
 	trace_seq_printf(s, "##### CPU %u buffer started ####\n", iter->cpu);
 }
 
@@ -2647,13 +2646,7 @@ static struct file_operations show_traces_fops = {
 /*
  * Only trace on a CPU if the bitmask is set:
  */
-static cpumask_t tracing_cpumask = CPU_MASK_ALL;
-
-/*
- * When tracing/tracing_cpu_mask is modified then this holds
- * the new bitmask we are about to install:
- */
-static cpumask_t tracing_cpumask_new;
+static cpumask_var_t tracing_cpumask;
 
 /*
  * The tracer itself will not take this lock, but still we want
@@ -2694,6 +2687,10 @@ tracing_cpumask_write(struct file *filp, const char __user *ubuf,
 		      size_t count, loff_t *ppos)
 {
 	int err, cpu;
+	cpumask_var_t tracing_cpumask_new;
+
+	if (!alloc_cpumask_var(&tracing_cpumask_new, GFP_KERNEL))
+		return -ENOMEM;
 
 	mutex_lock(&tracing_cpumask_update_lock);
 	err = cpumask_parse_user(ubuf, count, tracing_cpumask_new);
@@ -2707,26 +2704,28 @@ tracing_cpumask_write(struct file *filp, const char __user *ubuf,
 		 * Increase/decrease the disabled counter if we are
 		 * about to flip a bit in the cpumask:
 		 */
-		if (cpu_isset(cpu, tracing_cpumask) &&
-				!cpu_isset(cpu, tracing_cpumask_new)) {
+		if (cpumask_test_cpu(cpu, tracing_cpumask) &&
+				!cpumask_test_cpu(cpu, tracing_cpumask_new)) {
 			atomic_inc(&global_trace.data[cpu]->disabled);
 		}
-		if (!cpu_isset(cpu, tracing_cpumask) &&
-				cpu_isset(cpu, tracing_cpumask_new)) {
+		if (!cpumask_test_cpu(cpu, tracing_cpumask) &&
+				cpumask_test_cpu(cpu, tracing_cpumask_new)) {
 			atomic_dec(&global_trace.data[cpu]->disabled);
 		}
 	}
 	__raw_spin_unlock(&ftrace_max_lock);
 	local_irq_enable();
 
-	tracing_cpumask = tracing_cpumask_new;
+	cpumask_copy(tracing_cpumask, tracing_cpumask_new);
 
 	mutex_unlock(&tracing_cpumask_update_lock);
+	free_cpumask_var(tracing_cpumask_new);
 
 	return count;
 
 err_unlock:
 	mutex_unlock(&tracing_cpumask_update_lock);
+	free_cpumask_var(tracing_cpumask);
 
 	return err;
 }
@@ -3115,10 +3114,15 @@ static int tracing_open_pipe(struct inode *inode, struct file *filp)
 	if (!iter)
 		return -ENOMEM;
 
+	if (!alloc_cpumask_var(&iter->started, GFP_KERNEL)) {
+		kfree(iter);
+		return -ENOMEM;
+	}
+
 	mutex_lock(&trace_types_lock);
 
 	/* trace pipe does not show start of buffer */
-	cpus_setall(iter->started);
+	cpumask_setall(iter->started);
 
 	iter->tr = &global_trace;
 	iter->trace = current_trace;
@@ -3135,6 +3139,7 @@ static int tracing_release_pipe(struct inode *inode, struct file *file)
 {
 	struct trace_iterator *iter = file->private_data;
 
+	free_cpumask_var(iter->started);
 	kfree(iter);
 	atomic_dec(&tracing_reader);
 
@@ -3753,7 +3758,6 @@ void ftrace_dump(void)
 	static DEFINE_SPINLOCK(ftrace_dump_lock);
 	/* use static because iter can be a bit big for the stack */
 	static struct trace_iterator iter;
-	static cpumask_t mask;
 	static int dump_ran;
 	unsigned long flags;
 	int cnt = 0, cpu;
@@ -3787,8 +3791,6 @@ void ftrace_dump(void)
 	 * and then release the locks again.
 	 */
 
-	cpus_clear(mask);
-
 	while (!trace_empty(&iter)) {
 
 		if (!cnt)
@@ -3824,19 +3826,28 @@ __init static int tracer_alloc_buffers(void)
 {
 	struct trace_array_cpu *data;
 	int i;
+	int ret = -ENOMEM;
 
-	/* TODO: make the number of buffers hot pluggable with CPUS */
-	tracing_buffer_mask = cpu_possible_map;
+	if (!alloc_cpumask_var(&tracing_buffer_mask, GFP_KERNEL))
+		goto out;
+
+	if (!alloc_cpumask_var(&tracing_cpumask, GFP_KERNEL))
+		goto out_free_buffer_mask;
+
+	cpumask_copy(tracing_buffer_mask, cpu_possible_mask);
+	cpumask_copy(tracing_cpumask, cpu_all_mask);
 
+	/* TODO: make the number of buffers hot pluggable with CPUS */
 	global_trace.buffer = ring_buffer_alloc(trace_buf_size,
 						   TRACE_BUFFER_FLAGS);
 	if (!global_trace.buffer) {
 		printk(KERN_ERR "tracer: failed to allocate ring buffer!\n");
 		WARN_ON(1);
-		return 0;
+		goto out_free_cpumask;
 	}
 	global_trace.entries = ring_buffer_size(global_trace.buffer);
 
+
 #ifdef CONFIG_TRACER_MAX_TRACE
 	max_tr.buffer = ring_buffer_alloc(trace_buf_size,
 					     TRACE_BUFFER_FLAGS);
@@ -3844,7 +3855,7 @@ __init static int tracer_alloc_buffers(void)
 		printk(KERN_ERR "tracer: failed to allocate max ring buffer!\n");
 		WARN_ON(1);
 		ring_buffer_free(global_trace.buffer);
-		return 0;
+		goto out_free_cpumask;
 	}
 	max_tr.entries = ring_buffer_size(max_tr.buffer);
 	WARN_ON(max_tr.entries != global_trace.entries);
@@ -3874,8 +3885,14 @@ __init static int tracer_alloc_buffers(void)
 				       &trace_panic_notifier);
 
 	register_die_notifier(&trace_die_notifier);
+	ret = 0;
 
-	return 0;
+out_free_cpumask:
+	free_cpumask_var(tracing_cpumask);
+out_free_buffer_mask:
+	free_cpumask_var(tracing_buffer_mask);
+out:
+	return ret;
 }
 early_initcall(tracer_alloc_buffers);
 fs_initcall(tracer_init_debugfs);
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index cc7a4f864036..4d3d381bfd95 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -368,7 +368,7 @@ struct trace_iterator {
 	loff_t			pos;
 	long			idx;
 
-	cpumask_t		started;
+	cpumask_var_t		started;
 };
 
 int tracing_is_enabled(void);
diff --git a/kernel/trace/trace_boot.c b/kernel/trace/trace_boot.c
index 3ccebde28482..366c8c333e13 100644
--- a/kernel/trace/trace_boot.c
+++ b/kernel/trace/trace_boot.c
@@ -42,7 +42,7 @@ static int boot_trace_init(struct trace_array *tr)
 	int cpu;
 	boot_trace = tr;
 
-	for_each_cpu_mask(cpu, cpu_possible_map)
+	for_each_cpu(cpu, cpu_possible_mask)
 		tracing_reset(tr, cpu);
 
 	tracing_sched_switch_assign_trace(tr);
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index 4bf39fcae97a..930c08e5b38e 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -79,7 +79,7 @@ print_graph_cpu(struct trace_seq *s, int cpu)
 	int i;
 	int ret;
 	int log10_this = log10_cpu(cpu);
-	int log10_all = log10_cpu(cpus_weight_nr(cpu_online_map));
+	int log10_all = log10_cpu(cpumask_weight(cpu_online_mask));
 
 
 	/*
diff --git a/kernel/trace/trace_hw_branches.c b/kernel/trace/trace_hw_branches.c
index b6a3e20a49a9..649df22d435f 100644
--- a/kernel/trace/trace_hw_branches.c
+++ b/kernel/trace/trace_hw_branches.c
@@ -46,7 +46,7 @@ static void bts_trace_start(struct trace_array *tr)
 
 	tracing_reset_online_cpus(tr);
 
-	for_each_cpu_mask(cpu, cpu_possible_map)
+	for_each_cpu(cpu, cpu_possible_mask)
 		smp_call_function_single(cpu, bts_trace_start_cpu, NULL, 1);
 }
 
@@ -62,7 +62,7 @@ static void bts_trace_stop(struct trace_array *tr)
 {
 	int cpu;
 
-	for_each_cpu_mask(cpu, cpu_possible_map)
+	for_each_cpu(cpu, cpu_possible_mask)
 		smp_call_function_single(cpu, bts_trace_stop_cpu, NULL, 1);
 }
 
@@ -172,7 +172,7 @@ static void trace_bts_prepare(struct trace_iterator *iter)
 {
 	int cpu;
 
-	for_each_cpu_mask(cpu, cpu_possible_map)
+	for_each_cpu(cpu, cpu_possible_mask)
 		smp_call_function_single(cpu, trace_bts_cpu, iter->tr, 1);
 }
 
diff --git a/kernel/trace/trace_power.c b/kernel/trace/trace_power.c
index a7172a352f62..7bda248daf55 100644
--- a/kernel/trace/trace_power.c
+++ b/kernel/trace/trace_power.c
@@ -39,7 +39,7 @@ static int power_trace_init(struct trace_array *tr)
 
 	trace_power_enabled = 1;
 
-	for_each_cpu_mask(cpu, cpu_possible_map)
+	for_each_cpu(cpu, cpu_possible_mask)
 		tracing_reset(tr, cpu);
 	return 0;
 }
diff --git a/kernel/trace/trace_sysprof.c b/kernel/trace/trace_sysprof.c
index 01becf1f19ff..eaca5ad803ff 100644
--- a/kernel/trace/trace_sysprof.c
+++ b/kernel/trace/trace_sysprof.c
@@ -196,27 +196,19 @@ static enum hrtimer_restart stack_trace_timer_fn(struct hrtimer *hrtimer)
 	return HRTIMER_RESTART;
 }
 
-static void start_stack_timer(int cpu)
+static void start_stack_timer(void *unused)
 {
-	struct hrtimer *hrtimer = &per_cpu(stack_trace_hrtimer, cpu);
+	struct hrtimer *hrtimer = &__get_cpu_var(stack_trace_hrtimer);
 
 	hrtimer_init(hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	hrtimer->function = stack_trace_timer_fn;
-	hrtimer->cb_mode = HRTIMER_CB_IRQSAFE_PERCPU;
 
 	hrtimer_start(hrtimer, ns_to_ktime(sample_period), HRTIMER_MODE_REL);
 }
 
 static void start_stack_timers(void)
 {
-	cpumask_t saved_mask = current->cpus_allowed;
-	int cpu;
-
-	for_each_online_cpu(cpu) {
-		set_cpus_allowed_ptr(current, &cpumask_of_cpu(cpu));
-		start_stack_timer(cpu);
-	}
-	set_cpus_allowed_ptr(current, &saved_mask);
+	on_each_cpu(start_stack_timer, NULL, 1);
 }
 
 static void stop_stack_timer(int cpu)
diff --git a/kernel/tsacct.c b/kernel/tsacct.c
index 2dc06ab35716..43f891b05a4b 100644
--- a/kernel/tsacct.c
+++ b/kernel/tsacct.c
@@ -92,8 +92,8 @@ void xacct_add_tsk(struct taskstats *stats, struct task_struct *p)
 	mm = get_task_mm(p);
 	if (mm) {
 		/* adjust to KB unit */
-		stats->hiwater_rss   = mm->hiwater_rss * PAGE_SIZE / KB;
-		stats->hiwater_vm    = mm->hiwater_vm * PAGE_SIZE / KB;
+		stats->hiwater_rss   = get_mm_hiwater_rss(mm) * PAGE_SIZE / KB;
+		stats->hiwater_vm    = get_mm_hiwater_vm(mm)  * PAGE_SIZE / KB;
 		mmput(mm);
 	}
 	stats->read_char	= p->ioac.rchar;
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 4952322cba45..2f445833ae37 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -73,7 +73,7 @@ static DEFINE_SPINLOCK(workqueue_lock);
 static LIST_HEAD(workqueues);
 
 static int singlethread_cpu __read_mostly;
-static cpumask_t cpu_singlethread_map __read_mostly;
+static const struct cpumask *cpu_singlethread_map __read_mostly;
 /*
  * _cpu_down() first removes CPU from cpu_online_map, then CPU_DEAD
  * flushes cwq->worklist. This means that flush_workqueue/wait_on_work
@@ -81,7 +81,7 @@ static cpumask_t cpu_singlethread_map __read_mostly;
  * use cpu_possible_map, the cpumask below is more a documentation
  * than optimization.
  */
-static cpumask_t cpu_populated_map __read_mostly;
+static cpumask_var_t cpu_populated_map __read_mostly;
 
 /* If it's single threaded, it isn't in the list of workqueues. */
 static inline int is_wq_single_threaded(struct workqueue_struct *wq)
@@ -89,10 +89,10 @@ static inline int is_wq_single_threaded(struct workqueue_struct *wq)
 	return wq->singlethread;
 }
 
-static const cpumask_t *wq_cpu_map(struct workqueue_struct *wq)
+static const struct cpumask *wq_cpu_map(struct workqueue_struct *wq)
 {
 	return is_wq_single_threaded(wq)
-		? &cpu_singlethread_map : &cpu_populated_map;
+		? cpu_singlethread_map : cpu_populated_map;
 }
 
 static
@@ -410,7 +410,7 @@ static int flush_cpu_workqueue(struct cpu_workqueue_struct *cwq)
  */
 void flush_workqueue(struct workqueue_struct *wq)
 {
-	const cpumask_t *cpu_map = wq_cpu_map(wq);
+	const struct cpumask *cpu_map = wq_cpu_map(wq);
 	int cpu;
 
 	might_sleep();
@@ -532,7 +532,7 @@ static void wait_on_work(struct work_struct *work)
 {
 	struct cpu_workqueue_struct *cwq;
 	struct workqueue_struct *wq;
-	const cpumask_t *cpu_map;
+	const struct cpumask *cpu_map;
 	int cpu;
 
 	might_sleep();
@@ -903,7 +903,7 @@ static void cleanup_workqueue_thread(struct cpu_workqueue_struct *cwq)
  */
 void destroy_workqueue(struct workqueue_struct *wq)
 {
-	const cpumask_t *cpu_map = wq_cpu_map(wq);
+	const struct cpumask *cpu_map = wq_cpu_map(wq);
 	int cpu;
 
 	cpu_maps_update_begin();
@@ -933,7 +933,7 @@ static int __devinit workqueue_cpu_callback(struct notifier_block *nfb,
 
 	switch (action) {
 	case CPU_UP_PREPARE:
-		cpu_set(cpu, cpu_populated_map);
+		cpumask_set_cpu(cpu, cpu_populated_map);
 	}
 undo:
 	list_for_each_entry(wq, &workqueues, list) {
@@ -964,7 +964,7 @@ undo:
 	switch (action) {
 	case CPU_UP_CANCELED:
 	case CPU_POST_DEAD:
-		cpu_clear(cpu, cpu_populated_map);
+		cpumask_clear_cpu(cpu, cpu_populated_map);
 	}
 
 	return ret;
@@ -1017,9 +1017,11 @@ EXPORT_SYMBOL_GPL(work_on_cpu);
 
 void __init init_workqueues(void)
 {
-	cpu_populated_map = cpu_online_map;
-	singlethread_cpu = first_cpu(cpu_possible_map);
-	cpu_singlethread_map = cpumask_of_cpu(singlethread_cpu);
+	alloc_cpumask_var(&cpu_populated_map, GFP_KERNEL);
+
+	cpumask_copy(cpu_populated_map, cpu_online_mask);
+	singlethread_cpu = cpumask_first(cpu_possible_mask);
+	cpu_singlethread_map = cpumask_of(singlethread_cpu);
 	hotcpu_notifier(workqueue_cpu_callback, 0);
 	keventd_wq = create_workqueue("events");
 	BUG_ON(!keventd_wq);