Merge remote-tracking branch 'eas-next/eas-next' into sched/cpuidle/eas-nexteas-next-20141120sched/cpuidle/eas-next

Conflicts:
	include/linux/sched.h
	kernel/sched/Makefile

35 files changed, 1705 insertions, 522 deletions

diff --git a/arch/x86/include/asm/preempt.h b/arch/x86/include/asm/preempt.h
index 7024c12f7bfe..8f3271842533 100644
--- a/arch/x86/include/asm/preempt.h
+++ b/arch/x86/include/asm/preempt.h
@@ -30,9 +30,6 @@ static __always_inline void preempt_count_set(int pc)
 /*
  * must be macros to avoid header recursion hell
  */
-#define task_preempt_count(p) \
-	(task_thread_info(p)->saved_preempt_count & ~PREEMPT_NEED_RESCHED)
-
 #define init_task_preempt_count(p) do { \
 	task_thread_info(p)->saved_preempt_count = PREEMPT_DISABLED; \
 } while (0)
@@ -105,6 +102,7 @@ static __always_inline bool should_resched(void)
 # ifdef CONFIG_CONTEXT_TRACKING
     extern asmlinkage void ___preempt_schedule_context(void);
 #   define __preempt_schedule_context() asm ("call ___preempt_schedule_context")
+    extern asmlinkage void preempt_schedule_context(void);
 # endif
 #endif
 
diff --git a/drivers/cpufreq/Kconfig b/drivers/cpufreq/Kconfig
index 3489f8f5fada..6520ff6461e1 100644
--- a/drivers/cpufreq/Kconfig
+++ b/drivers/cpufreq/Kconfig
@@ -102,6 +102,15 @@ config CPU_FREQ_DEFAULT_GOV_CONSERVATIVE
 	  Be aware that not all cpufreq drivers support the conservative
 	  governor. If unsure have a look at the help section of the
 	  driver. Fallback governor will be the performance governor.
+
+config CPU_FREQ_DEFAULT_GOV_ENERGY_MODEL
+	bool "energy_model"
+	select CPU_FREQ_GOV_ENERGY_MODEL
+	select CPU_FREQ_GOV_PERFORMANCE
+	help
+	  Use the CPUfreq governor 'energy_model' as default. This
+	  scales cpu frequency from the scheduler as per-task statistics
+	  are updated.
 endchoice
 
 config CPU_FREQ_GOV_PERFORMANCE
@@ -183,6 +192,18 @@ config CPU_FREQ_GOV_CONSERVATIVE
 
 	  If in doubt, say N.
 
+config CPU_FREQ_GOV_ENERGY_MODEL
+	tristate "'energy model' cpufreq governor"
+	depends on CPU_FREQ
+	select CPU_FREQ_GOV_COMMON
+	help
+	  'energy_model' - this governor scales cpu frequency from the
+	  scheduler as a function of cpu utilization. It does not
+	  evaluate utilization on a periodic basis (unlike ondemand) but
+	  instead is invoked from CFS when updating per-task statistics.
+
+	  If in doubt, say N.
+
 config CPUFREQ_DT
 	tristate "Generic DT based cpufreq driver"
 	depends on HAVE_CLK && OF
diff --git a/drivers/tty/n_tty.c b/drivers/tty/n_tty.c
index 89c4cee253e3..fb3f519b803f 100644
--- a/drivers/tty/n_tty.c
+++ b/drivers/tty/n_tty.c
@@ -2123,7 +2123,7 @@ static ssize_t n_tty_read(struct tty_struct *tty, struct file *file,
 {
 	struct n_tty_data *ldata = tty->disc_data;
 	unsigned char __user *b = buf;
-	DECLARE_WAITQUEUE(wait, current);
+	DEFINE_WAIT_FUNC(wait, woken_wake_function);
 	int c;
 	int minimum, time;
 	ssize_t retval = 0;
@@ -2186,10 +2186,6 @@ static ssize_t n_tty_read(struct tty_struct *tty, struct file *file,
 			nr--;
 			break;
 		}
-		/* This statement must be first before checking for input
-		   so that any interrupt will set the state back to
-		   TASK_RUNNING. */
-		set_current_state(TASK_INTERRUPTIBLE);
 
 		if (((minimum - (b - buf)) < ldata->minimum_to_wake) &&
 		    ((minimum - (b - buf)) >= 1))
@@ -2220,13 +2216,13 @@ static ssize_t n_tty_read(struct tty_struct *tty, struct file *file,
 				n_tty_set_room(tty);
 				up_read(&tty->termios_rwsem);
 
-				timeout = schedule_timeout(timeout);
+				timeout = wait_woken(&wait, TASK_INTERRUPTIBLE,
+						     timeout);
 
 				down_read(&tty->termios_rwsem);
 				continue;
 			}
 		}
-		__set_current_state(TASK_RUNNING);
 
 		/* Deal with packet mode. */
 		if (packet && b == buf) {
@@ -2273,7 +2269,6 @@ static ssize_t n_tty_read(struct tty_struct *tty, struct file *file,
 
 	mutex_unlock(&ldata->atomic_read_lock);
 
-	__set_current_state(TASK_RUNNING);
 	if (b - buf)
 		retval = b - buf;
 
@@ -2306,7 +2301,7 @@ static ssize_t n_tty_write(struct tty_struct *tty, struct file *file,
 			   const unsigned char *buf, size_t nr)
 {
 	const unsigned char *b = buf;
-	DECLARE_WAITQUEUE(wait, current);
+	DEFINE_WAIT_FUNC(wait, woken_wake_function);
 	int c;
 	ssize_t retval = 0;
 
@@ -2324,7 +2319,6 @@ static ssize_t n_tty_write(struct tty_struct *tty, struct file *file,
 
 	add_wait_queue(&tty->write_wait, &wait);
 	while (1) {
-		set_current_state(TASK_INTERRUPTIBLE);
 		if (signal_pending(current)) {
 			retval = -ERESTARTSYS;
 			break;
@@ -2378,12 +2372,11 @@ static ssize_t n_tty_write(struct tty_struct *tty, struct file *file,
 		}
 		up_read(&tty->termios_rwsem);
 
-		schedule();
+		wait_woken(&wait, TASK_INTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT);
 
 		down_read(&tty->termios_rwsem);
 	}
 break_out:
-	__set_current_state(TASK_RUNNING);
 	remove_wait_queue(&tty->write_wait, &wait);
 	if (b - buf != nr && tty->fasync)
 		set_bit(TTY_DO_WRITE_WAKEUP, &tty->flags);
diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c
index daf76652fe58..283aa312d745 100644
--- a/fs/notify/inotify/inotify_user.c
+++ b/fs/notify/inotify/inotify_user.c
@@ -227,14 +227,13 @@ static ssize_t inotify_read(struct file *file, char __user *buf,
 	struct fsnotify_event *kevent;
 	char __user *start;
 	int ret;
-	DEFINE_WAIT(wait);
+	DEFINE_WAIT_FUNC(wait, woken_wake_function);
 
 	start = buf;
 	group = file->private_data;
 
+	add_wait_queue(&group->notification_waitq, &wait);
 	while (1) {
-		prepare_to_wait(&group->notification_waitq, &wait, TASK_INTERRUPTIBLE);
-
 		mutex_lock(&group->notification_mutex);
 		kevent = get_one_event(group, count);
 		mutex_unlock(&group->notification_mutex);
@@ -264,10 +263,10 @@ static ssize_t inotify_read(struct file *file, char __user *buf,
 		if (start != buf)
 			break;
 
-		schedule();
+		wait_woken(&wait, TASK_INTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT);
 	}
+	remove_wait_queue(&group->notification_waitq, &wait);
 
-	finish_wait(&group->notification_waitq, &wait);
 	if (start != buf && ret != -EFAULT)
 		ret = buf - start;
 	return ret;
diff --git a/include/asm-generic/preempt.h b/include/asm-generic/preempt.h
index 1cd3f5d767a8..eb6f9e6c3075 100644
--- a/include/asm-generic/preempt.h
+++ b/include/asm-generic/preempt.h
@@ -23,9 +23,6 @@ static __always_inline void preempt_count_set(int pc)
 /*
  * must be macros to avoid header recursion hell
  */
-#define task_preempt_count(p) \
-	(task_thread_info(p)->preempt_count & ~PREEMPT_NEED_RESCHED)
-
 #define init_task_preempt_count(p) do { \
 	task_thread_info(p)->preempt_count = PREEMPT_DISABLED; \
 } while (0)
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index 503b085b7832..9ae4b27c2b4b 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -115,6 +115,9 @@ struct cpufreq_policy {
 
 	/* For cpufreq driver's internal use */
 	void			*driver_data;
+
+	/* For cpufreq governor's internal use */
+	void			*gov_data;
 };
 
 /* Only for ACPI */
@@ -481,6 +484,9 @@ extern struct cpufreq_governor cpufreq_gov_ondemand;
 #elif defined(CONFIG_CPU_FREQ_DEFAULT_GOV_CONSERVATIVE)
 extern struct cpufreq_governor cpufreq_gov_conservative;
 #define CPUFREQ_DEFAULT_GOVERNOR	(&cpufreq_gov_conservative)
+#elif defined(CONFIG_CPU_FREQ_DEFAULT_GOV_ENERGY_MODEL)
+extern struct cpufreq_governor cpufreq_gov_energy_model;
+#define CPUFREQ_DEFAULT_GOVERNOR	(&cpufreq_gov_energy_model)
 #endif
 
 /*********************************************************************
diff --git a/include/linux/freezer.h b/include/linux/freezer.h
index 7fd81b8c4897..6b7fd9cf5ea2 100644
--- a/include/linux/freezer.h
+++ b/include/linux/freezer.h
@@ -246,15 +246,6 @@ static inline int freezable_schedule_hrtimeout_range(ktime_t *expires,
  * defined in <linux/wait.h>
  */
 
-#define wait_event_freezekillable(wq, condition)			\
-({									\
-	int __retval;							\
-	freezer_do_not_count();						\
-	__retval = wait_event_killable(wq, (condition));		\
-	freezer_count();						\
-	__retval;							\
-})
-
 /* DO NOT ADD ANY NEW CALLERS OF THIS FUNCTION */
 #define wait_event_freezekillable_unsafe(wq, condition)			\
 ({									\
@@ -265,35 +256,6 @@ static inline int freezable_schedule_hrtimeout_range(ktime_t *expires,
 	__retval;							\
 })
 
-#define wait_event_freezable(wq, condition)				\
-({									\
-	int __retval;							\
-	freezer_do_not_count();						\
-	__retval = wait_event_interruptible(wq, (condition));		\
-	freezer_count();						\
-	__retval;							\
-})
-
-#define wait_event_freezable_timeout(wq, condition, timeout)		\
-({									\
-	long __retval = timeout;					\
-	freezer_do_not_count();						\
-	__retval = wait_event_interruptible_timeout(wq,	(condition),	\
-				__retval);				\
-	freezer_count();						\
-	__retval;							\
-})
-
-#define wait_event_freezable_exclusive(wq, condition)			\
-({									\
-	int __retval;							\
-	freezer_do_not_count();						\
-	__retval = wait_event_interruptible_exclusive(wq, condition);	\
-	freezer_count();						\
-	__retval;							\
-})
-
-
 #else /* !CONFIG_FREEZER */
 static inline bool frozen(struct task_struct *p) { return false; }
 static inline bool freezing(struct task_struct *p) { return false; }
@@ -331,18 +293,6 @@ static inline void set_freezable(void) {}
 #define freezable_schedule_hrtimeout_range(expires, delta, mode)	\
 	schedule_hrtimeout_range(expires, delta, mode)
 
-#define wait_event_freezable(wq, condition)				\
-		wait_event_interruptible(wq, condition)
-
-#define wait_event_freezable_timeout(wq, condition, timeout)		\
-		wait_event_interruptible_timeout(wq, condition, timeout)
-
-#define wait_event_freezable_exclusive(wq, condition)			\
-		wait_event_interruptible_exclusive(wq, condition)
-
-#define wait_event_freezekillable(wq, condition)		\
-		wait_event_killable(wq, condition)
-
 #define wait_event_freezekillable_unsafe(wq, condition)			\
 		wait_event_killable(wq, condition)
 
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 3d770f5564b8..446d76a87ba1 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -162,6 +162,7 @@ extern int _cond_resched(void);
 #endif
 
 #ifdef CONFIG_DEBUG_ATOMIC_SLEEP
+  void ___might_sleep(const char *file, int line, int preempt_offset);
   void __might_sleep(const char *file, int line, int preempt_offset);
 /**
  * might_sleep - annotation for functions that can sleep
@@ -175,10 +176,14 @@ extern int _cond_resched(void);
  */
 # define might_sleep() \
 	do { __might_sleep(__FILE__, __LINE__, 0); might_resched(); } while (0)
+# define sched_annotate_sleep()	__set_current_state(TASK_RUNNING)
 #else
+  static inline void ___might_sleep(const char *file, int line,
+				   int preempt_offset) { }
   static inline void __might_sleep(const char *file, int line,
 				   int preempt_offset) { }
 # define might_sleep() do { might_resched(); } while (0)
+# define sched_annotate_sleep() do { } while (0)
 #endif
 
 #define might_sleep_if(cond) do { if (cond) might_sleep(); } while (0)
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 50f8c6343f17..fc3a7cf107ec 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -243,6 +243,43 @@ extern char ___assert_task_state[1 - 2*!!(
 				((task->state & TASK_UNINTERRUPTIBLE) != 0 && \
 				 (task->flags & PF_FROZEN) == 0)
 
+#ifdef CONFIG_DEBUG_ATOMIC_SLEEP
+
+#define __set_task_state(tsk, state_value)			\
+	do {							\
+		(tsk)->task_state_change = _THIS_IP_;		\
+		(tsk)->state = (state_value);			\
+	} while (0)
+#define set_task_state(tsk, state_value)			\
+	do {							\
+		(tsk)->task_state_change = _THIS_IP_;		\
+		set_mb((tsk)->state, (state_value));		\
+	} while (0)
+
+/*
+ * set_current_state() includes a barrier so that the write of current->state
+ * is correctly serialised wrt the caller's subsequent test of whether to
+ * actually sleep:
+ *
+ *	set_current_state(TASK_UNINTERRUPTIBLE);
+ *	if (do_i_need_to_sleep())
+ *		schedule();
+ *
+ * If the caller does not need such serialisation then use __set_current_state()
+ */
+#define __set_current_state(state_value)			\
+	do {							\
+		current->task_state_change = _THIS_IP_;		\
+		current->state = (state_value);			\
+	} while (0)
+#define set_current_state(state_value)				\
+	do {							\
+		current->task_state_change = _THIS_IP_;		\
+		set_mb(current->state, (state_value));		\
+	} while (0)
+
+#else
+
 #define __set_task_state(tsk, state_value)		\
 	do { (tsk)->state = (state_value); } while (0)
 #define set_task_state(tsk, state_value)		\
@@ -259,11 +296,13 @@ extern char ___assert_task_state[1 - 2*!!(
  *
  * If the caller does not need such serialisation then use __set_current_state()
  */
-#define __set_current_state(state_value)			\
+#define __set_current_state(state_value)		\
 	do { current->state = (state_value); } while (0)
-#define set_current_state(state_value)		\
+#define set_current_state(state_value)			\
 	set_mb(current->state, (state_value))
 
+#endif
+
 /* Task command name length */
 #define TASK_COMM_LEN 16
 
@@ -1072,15 +1111,28 @@ struct load_weight {
 };
 
 struct sched_avg {
+	u64 last_runnable_update;
+	s64 decay_count;
+	/*
+	 * utilization_avg_contrib describes the amount of time that a
+	 * sched_entity is running on a CPU. It is based on running_avg_sum
+	 * and is scaled in the range [0..SCHED_LOAD_SCALE].
+	 * load_avg_contrib described the amount of time that a sched_entity
+	 * is runnable on a rq. It is based on both runnable_avg_sum and the
+	 * weight of the task.
+	 */
+	unsigned long load_avg_contrib, utilization_avg_contrib;
 	/*
 	 * These sums represent an infinite geometric series and so are bound
 	 * above by 1024/(1-y).  Thus we only need a u32 to store them for all
 	 * choices of y < 1-2^(-32)*1024.
+	 * running_avg_sum reflects the time that the sched_entity is
+	 * effectively running on the CPU.
+	 * runnable_avg_sum represents the amount of time a sched_entity is on
+	 * a runqueue which includes the running time that is monitored by
+	 * running_avg_sum.
 	 */
-	u32 runnable_avg_sum, runnable_avg_period;
-	u64 last_runnable_update;
-	s64 decay_count;
-	unsigned long load_avg_contrib;
+	u32 runnable_avg_sum, avg_period, running_avg_sum;
 };
 
 #ifdef CONFIG_SCHEDSTATS
@@ -1576,28 +1628,23 @@ struct task_struct {
 	struct numa_group *numa_group;
 
 	/*
-	 * Exponential decaying average of faults on a per-node basis.
-	 * Scheduling placement decisions are made based on the these counts.
-	 * The values remain static for the duration of a PTE scan
+	 * numa_faults is an array split into four regions:
+	 * faults_memory, faults_cpu, faults_memory_buffer, faults_cpu_buffer
+	 * in this precise order.
+	 *
+	 * faults_memory: Exponential decaying average of faults on a per-node
+	 * basis. Scheduling placement decisions are made based on these
+	 * counts. The values remain static for the duration of a PTE scan.
+	 * faults_cpu: Track the nodes the process was running on when a NUMA
+	 * hinting fault was incurred.
+	 * faults_memory_buffer and faults_cpu_buffer: Record faults per node
+	 * during the current scan window. When the scan completes, the counts
+	 * in faults_memory and faults_cpu decay and these values are copied.
 	 */
-	unsigned long *numa_faults_memory;
+	unsigned long *numa_faults;
 	unsigned long total_numa_faults;
 
 	/*
-	 * numa_faults_buffer records faults per node during the current
-	 * scan window. When the scan completes, the counts in
-	 * numa_faults_memory decay and these values are copied.
-	 */
-	unsigned long *numa_faults_buffer_memory;
-
-	/*
-	 * Track the nodes the process was running on when a NUMA hinting
-	 * fault was incurred.
-	 */
-	unsigned long *numa_faults_cpu;
-	unsigned long *numa_faults_buffer_cpu;
-
-	/*
 	 * numa_faults_locality tracks if faults recorded during the last
 	 * scan window were remote/local. The task scan period is adapted
 	 * based on the locality of the faults with different weights
@@ -1682,6 +1729,9 @@ struct task_struct {
 #ifdef CONFIG_SCHED_IO_LATENCY
 	struct io_latency_node io_latency;
 #endif
+#ifdef CONFIG_DEBUG_ATOMIC_SLEEP
+	unsigned long	task_state_change;
+#endif
 };
 
 /* Future-safe accessor for struct task_struct's cpus_allowed. */
@@ -2073,6 +2123,10 @@ static inline void tsk_restore_flags(struct task_struct *task,
 	task->flags |= orig_flags & flags;
 }
 
+extern int cpuset_cpumask_can_shrink(const struct cpumask *cur,
+				     const struct cpumask *trial);
+extern int task_can_attach(struct task_struct *p,
+			   const struct cpumask *cs_cpus_allowed);
 #ifdef CONFIG_SMP
 extern void do_set_cpus_allowed(struct task_struct *p,
 			       const struct cpumask *new_mask);
@@ -2781,7 +2835,7 @@ static inline int signal_pending_state(long state, struct task_struct *p)
 extern int _cond_resched(void);
 
 #define cond_resched() ({			\
-	__might_sleep(__FILE__, __LINE__, 0);	\
+	___might_sleep(__FILE__, __LINE__, 0);	\
 	_cond_resched();			\
 })
 
@@ -2794,14 +2848,14 @@ extern int __cond_resched_lock(spinlock_t *lock);
 #endif
 
 #define cond_resched_lock(lock) ({				\
-	__might_sleep(__FILE__, __LINE__, PREEMPT_LOCK_OFFSET);	\
+	___might_sleep(__FILE__, __LINE__, PREEMPT_LOCK_OFFSET);\
 	__cond_resched_lock(lock);				\
 })
 
 extern int __cond_resched_softirq(void);
 
 #define cond_resched_softirq() ({					\
-	__might_sleep(__FILE__, __LINE__, SOFTIRQ_DISABLE_OFFSET);	\
+	___might_sleep(__FILE__, __LINE__, SOFTIRQ_DISABLE_OFFSET);	\
 	__cond_resched_softirq();					\
 })
 
diff --git a/include/linux/wait.h b/include/linux/wait.h
index e4a8eb9312ea..2232ed16635a 100644
--- a/include/linux/wait.h
+++ b/include/linux/wait.h
@@ -13,9 +13,12 @@ typedef struct __wait_queue wait_queue_t;
 typedef int (*wait_queue_func_t)(wait_queue_t *wait, unsigned mode, int flags, void *key);
 int default_wake_function(wait_queue_t *wait, unsigned mode, int flags, void *key);
 
+/* __wait_queue::flags */
+#define WQ_FLAG_EXCLUSIVE	0x01
+#define WQ_FLAG_WOKEN		0x02
+
 struct __wait_queue {
 	unsigned int		flags;
-#define WQ_FLAG_EXCLUSIVE	0x01
 	void			*private;
 	wait_queue_func_t	func;
 	struct list_head	task_list;
@@ -258,11 +261,37 @@ __out:	__ret;								\
  */
 #define wait_event(wq, condition)					\
 do {									\
+	might_sleep();							\
 	if (condition)							\
 		break;							\
 	__wait_event(wq, condition);					\
 } while (0)
 
+#define __wait_event_freezable(wq, condition)				\
+	___wait_event(wq, condition, TASK_INTERRUPTIBLE, 0, 0,		\
+			    schedule(); try_to_freeze())
+
+/**
+ * wait_event - sleep (or freeze) until a condition gets true
+ * @wq: the waitqueue to wait on
+ * @condition: a C expression for the event to wait for
+ *
+ * The process is put to sleep (TASK_INTERRUPTIBLE -- so as not to contribute
+ * to system load) until the @condition evaluates to true. The
+ * @condition is checked each time the waitqueue @wq is woken up.
+ *
+ * wake_up() has to be called after changing any variable that could
+ * change the result of the wait condition.
+ */
+#define wait_event_freezable(wq, condition)				\
+({									\
+	int __ret = 0;							\
+	might_sleep();							\
+	if (!(condition))						\
+		__ret = __wait_event_freezable(wq, condition);		\
+	__ret;								\
+})
+
 #define __wait_event_timeout(wq, condition, timeout)			\
 	___wait_event(wq, ___wait_cond_timeout(condition),		\
 		      TASK_UNINTERRUPTIBLE, 0, timeout,			\
@@ -290,11 +319,30 @@ do {									\
 #define wait_event_timeout(wq, condition, timeout)			\
 ({									\
 	long __ret = timeout;						\
+	might_sleep();							\
 	if (!___wait_cond_timeout(condition))				\
 		__ret = __wait_event_timeout(wq, condition, timeout);	\
 	__ret;								\
 })
 
+#define __wait_event_freezable_timeout(wq, condition, timeout)		\
+	___wait_event(wq, ___wait_cond_timeout(condition),		\
+		      TASK_INTERRUPTIBLE, 0, timeout,			\
+		      __ret = schedule_timeout(__ret); try_to_freeze())
+
+/*
+ * like wait_event_timeout() -- except it uses TASK_INTERRUPTIBLE to avoid
+ * increasing load and is freezable.
+ */
+#define wait_event_freezable_timeout(wq, condition, timeout)		\
+({									\
+	long __ret = timeout;						\
+	might_sleep();							\
+	if (!___wait_cond_timeout(condition))				\
+		__ret = __wait_event_freezable_timeout(wq, condition, timeout);	\
+	__ret;								\
+})
+
 #define __wait_event_cmd(wq, condition, cmd1, cmd2)			\
 	(void)___wait_event(wq, condition, TASK_UNINTERRUPTIBLE, 0, 0,	\
 			    cmd1; schedule(); cmd2)
@@ -315,6 +363,7 @@ do {									\
  */
 #define wait_event_cmd(wq, condition, cmd1, cmd2)			\
 do {									\
+	might_sleep();							\
 	if (condition)							\
 		break;							\
 	__wait_event_cmd(wq, condition, cmd1, cmd2);			\
@@ -342,6 +391,7 @@ do {									\
 #define wait_event_interruptible(wq, condition)				\
 ({									\
 	int __ret = 0;							\
+	might_sleep();							\
 	if (!(condition))						\
 		__ret = __wait_event_interruptible(wq, condition);	\
 	__ret;								\
@@ -375,6 +425,7 @@ do {									\
 #define wait_event_interruptible_timeout(wq, condition, timeout)	\
 ({									\
 	long __ret = timeout;						\
+	might_sleep();							\
 	if (!___wait_cond_timeout(condition))				\
 		__ret = __wait_event_interruptible_timeout(wq,		\
 						condition, timeout);	\
@@ -425,6 +476,7 @@ do {									\
 #define wait_event_hrtimeout(wq, condition, timeout)			\
 ({									\
 	int __ret = 0;							\
+	might_sleep();							\
 	if (!(condition))						\
 		__ret = __wait_event_hrtimeout(wq, condition, timeout,	\
 					       TASK_UNINTERRUPTIBLE);	\
@@ -450,6 +502,7 @@ do {									\
 #define wait_event_interruptible_hrtimeout(wq, condition, timeout)	\
 ({									\
 	long __ret = 0;							\
+	might_sleep();							\
 	if (!(condition))						\
 		__ret = __wait_event_hrtimeout(wq, condition, timeout,	\
 					       TASK_INTERRUPTIBLE);	\
@@ -463,12 +516,27 @@ do {									\
 #define wait_event_interruptible_exclusive(wq, condition)		\
 ({									\
 	int __ret = 0;							\
+	might_sleep();							\
 	if (!(condition))						\
 		__ret = __wait_event_interruptible_exclusive(wq, condition);\
 	__ret;								\
 })
 
 
+#define __wait_event_freezable_exclusive(wq, condition)			\
+	___wait_event(wq, condition, TASK_INTERRUPTIBLE, 1, 0,		\
+			schedule(); try_to_freeze())
+
+#define wait_event_freezable_exclusive(wq, condition)			\
+({									\
+	int __ret = 0;							\
+	might_sleep();							\
+	if (!(condition))						\
+		__ret = __wait_event_freezable_exclusive(wq, condition);\
+	__ret;								\
+})
+
+
 #define __wait_event_interruptible_locked(wq, condition, exclusive, irq) \
 ({									\
 	int __ret = 0;							\
@@ -637,6 +705,7 @@ do {									\
 #define wait_event_killable(wq, condition)				\
 ({									\
 	int __ret = 0;							\
+	might_sleep();							\
 	if (!(condition))						\
 		__ret = __wait_event_killable(wq, condition);		\
 	__ret;								\
@@ -830,6 +899,8 @@ void prepare_to_wait_exclusive(wait_queue_head_t *q, wait_queue_t *wait, int sta
 long prepare_to_wait_event(wait_queue_head_t *q, wait_queue_t *wait, int state);
 void finish_wait(wait_queue_head_t *q, wait_queue_t *wait);
 void abort_exclusive_wait(wait_queue_head_t *q, wait_queue_t *wait, unsigned int mode, void *key);
+long wait_woken(wait_queue_t *wait, unsigned mode, long timeout);
+int woken_wake_function(wait_queue_t *wait, unsigned mode, int sync, void *key);
 int autoremove_wake_function(wait_queue_t *wait, unsigned mode, int sync, void *key);
 int wake_bit_function(wait_queue_t *wait, unsigned mode, int sync, void *key);
 
@@ -886,6 +957,7 @@ extern int bit_wait_io_timeout(struct wait_bit_key *);
 static inline int
 wait_on_bit(void *word, int bit, unsigned mode)
 {
+	might_sleep();
 	if (!test_bit(bit, word))
 		return 0;
 	return out_of_line_wait_on_bit(word, bit,
@@ -910,6 +982,7 @@ wait_on_bit(void *word, int bit, unsigned mode)
 static inline int
 wait_on_bit_io(void *word, int bit, unsigned mode)
 {
+	might_sleep();
 	if (!test_bit(bit, word))
 		return 0;
 	return out_of_line_wait_on_bit(word, bit,
@@ -936,6 +1009,7 @@ wait_on_bit_io(void *word, int bit, unsigned mode)
 static inline int
 wait_on_bit_action(void *word, int bit, wait_bit_action_f *action, unsigned mode)
 {
+	might_sleep();
 	if (!test_bit(bit, word))
 		return 0;
 	return out_of_line_wait_on_bit(word, bit, action, mode);
@@ -963,6 +1037,7 @@ wait_on_bit_action(void *word, int bit, wait_bit_action_f *action, unsigned mode
 static inline int
 wait_on_bit_lock(void *word, int bit, unsigned mode)
 {
+	might_sleep();
 	if (!test_and_set_bit(bit, word))
 		return 0;
 	return out_of_line_wait_on_bit_lock(word, bit, bit_wait, mode);
@@ -986,6 +1061,7 @@ wait_on_bit_lock(void *word, int bit, unsigned mode)
 static inline int
 wait_on_bit_lock_io(void *word, int bit, unsigned mode)
 {
+	might_sleep();
 	if (!test_and_set_bit(bit, word))
 		return 0;
 	return out_of_line_wait_on_bit_lock(word, bit, bit_wait_io, mode);
@@ -1011,6 +1087,7 @@ wait_on_bit_lock_io(void *word, int bit, unsigned mode)
 static inline int
 wait_on_bit_lock_action(void *word, int bit, wait_bit_action_f *action, unsigned mode)
 {
+	might_sleep();
 	if (!test_and_set_bit(bit, word))
 		return 0;
 	return out_of_line_wait_on_bit_lock(word, bit, action, mode);
@@ -1029,6 +1106,7 @@ wait_on_bit_lock_action(void *word, int bit, wait_bit_action_f *action, unsigned
 static inline
 int wait_on_atomic_t(atomic_t *val, int (*action)(atomic_t *), unsigned mode)
 {
+	might_sleep();
 	if (atomic_read(val) == 0)
 		return 0;
 	return out_of_line_wait_on_atomic_t(val, action, mode);
diff --git a/include/net/sock.h b/include/net/sock.h
index 7db3db112baa..e6f235ebf6c9 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -897,6 +897,7 @@ static inline void sock_rps_reset_rxhash(struct sock *sk)
 		if (!__rc) {						\
 			*(__timeo) = schedule_timeout(*(__timeo));	\
 		}							\
+		sched_annotate_sleep();						\
 		lock_sock(__sk);					\
 		__rc = __condition;					\
 		__rc;							\
diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
index 0a68d5ae584e..30fedaf3e56a 100644
--- a/include/trace/events/sched.h
+++ b/include/trace/events/sched.h
@@ -97,16 +97,19 @@ static inline long __trace_sched_switch_state(struct task_struct *p)
 	long state = p->state;
 
 #ifdef CONFIG_PREEMPT
+#ifdef CONFIG_SCHED_DEBUG
+	BUG_ON(p != current);
+#endif /* CONFIG_SCHED_DEBUG */
 	/*
 	 * For all intents and purposes a preempted task is a running task.
 	 */
-	if (task_preempt_count(p) & PREEMPT_ACTIVE)
+	if (preempt_count() & PREEMPT_ACTIVE)
 		state = TASK_RUNNING | TASK_STATE_MAX;
-#endif
+#endif /* CONFIG_PREEMPT */
 
 	return state;
 }
-#endif
+#endif /* CREATE_TRACE_POINTS */
 
 /*
  * Tracepoint for task switches, performed by the scheduler:
diff --git a/include/uapi/linux/sched.h b/include/uapi/linux/sched.h
index 34f9d7387d13..cc89ddefa926 100644
--- a/include/uapi/linux/sched.h
+++ b/include/uapi/linux/sched.h
@@ -13,7 +13,7 @@
 #define CLONE_VFORK	0x00004000	/* set if the parent wants the child to wake it up on mm_release */
 #define CLONE_PARENT	0x00008000	/* set if we want to have the same parent as the cloner */
 #define CLONE_THREAD	0x00010000	/* Same thread group? */
-#define CLONE_NEWNS	0x00020000	/* New namespace group? */
+#define CLONE_NEWNS	0x00020000	/* New mount namespace group */
 #define CLONE_SYSVSEM	0x00040000	/* share system V SEM_UNDO semantics */
 #define CLONE_SETTLS	0x00080000	/* create a new TLS for the child */
 #define CLONE_PARENT_SETTID	0x00100000	/* set the TID in the parent */
@@ -23,8 +23,8 @@
 #define CLONE_CHILD_SETTID	0x01000000	/* set the TID in the child */
 /* 0x02000000 was previously the unused CLONE_STOPPED (Start in stopped state)
    and is now available for re-use. */
-#define CLONE_NEWUTS		0x04000000	/* New utsname group? */
-#define CLONE_NEWIPC		0x08000000	/* New ipcs */
+#define CLONE_NEWUTS		0x04000000	/* New utsname namespace */
+#define CLONE_NEWIPC		0x08000000	/* New ipc namespace */
 #define CLONE_NEWUSER		0x10000000	/* New user namespace */
 #define CLONE_NEWPID		0x20000000	/* New pid namespace */
 #define CLONE_NEWNET		0x40000000	/* New network namespace */
diff --git a/kernel/audit.c b/kernel/audit.c
index 80983df92cd4..32bfc43ffb9a 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -499,7 +499,6 @@ static int kauditd_thread(void *dummy)
 	set_freezable();
 	while (!kthread_should_stop()) {
 		struct sk_buff *skb;
-		DECLARE_WAITQUEUE(wait, current);
 
 		flush_hold_queue();
 
@@ -514,16 +513,8 @@ static int kauditd_thread(void *dummy)
 				audit_printk_skb(skb);
 			continue;
 		}
-		set_current_state(TASK_INTERRUPTIBLE);
-		add_wait_queue(&kauditd_wait, &wait);
 
-		if (!skb_queue_len(&audit_skb_queue)) {
-			try_to_freeze();
-			schedule();
-		}
-
-		__set_current_state(TASK_RUNNING);
-		remove_wait_queue(&kauditd_wait, &wait);
+		wait_event_freezable(kauditd_wait, skb_queue_len(&audit_skb_queue));
 	}
 	return 0;
 }
diff --git a/kernel/context_tracking.c b/kernel/context_tracking.c
index 5664985c46a0..937ecdfdf258 100644
--- a/kernel/context_tracking.c
+++ b/kernel/context_tracking.c
@@ -107,46 +107,6 @@ void context_tracking_user_enter(void)
 }
 NOKPROBE_SYMBOL(context_tracking_user_enter);
 
-#ifdef CONFIG_PREEMPT
-/**
- * preempt_schedule_context - preempt_schedule called by tracing
- *
- * The tracing infrastructure uses preempt_enable_notrace to prevent
- * recursion and tracing preempt enabling caused by the tracing
- * infrastructure itself. But as tracing can happen in areas coming
- * from userspace or just about to enter userspace, a preempt enable
- * can occur before user_exit() is called. This will cause the scheduler
- * to be called when the system is still in usermode.
- *
- * To prevent this, the preempt_enable_notrace will use this function
- * instead of preempt_schedule() to exit user context if needed before
- * calling the scheduler.
- */
-asmlinkage __visible void __sched notrace preempt_schedule_context(void)
-{
-	enum ctx_state prev_ctx;
-
-	if (likely(!preemptible()))
-		return;
-
-	/*
-	 * Need to disable preemption in case user_exit() is traced
-	 * and the tracer calls preempt_enable_notrace() causing
-	 * an infinite recursion.
-	 */
-	preempt_disable_notrace();
-	prev_ctx = exception_enter();
-	preempt_enable_no_resched_notrace();
-
-	preempt_schedule();
-
-	preempt_disable_notrace();
-	exception_exit(prev_ctx);
-	preempt_enable_notrace();
-}
-EXPORT_SYMBOL_GPL(preempt_schedule_context);
-#endif /* CONFIG_PREEMPT */
-
 /**
  * context_tracking_user_exit - Inform the context tracking that the CPU is
  *                              exiting userspace mode and entering the kernel.
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 1f107c74087b..723cfc9d0ad7 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -506,6 +506,16 @@ static int validate_change(struct cpuset *cur, struct cpuset *trial)
 			goto out;
 	}
 
+	/*
+	 * We can't shrink if we won't have enough room for SCHED_DEADLINE
+	 * tasks.
+	 */
+	ret = -EBUSY;
+	if (is_cpu_exclusive(cur) &&
+	    !cpuset_cpumask_can_shrink(cur->cpus_allowed,
+				       trial->cpus_allowed))
+		goto out;
+
 	ret = 0;
 out:
 	rcu_read_unlock();
@@ -1429,17 +1439,8 @@ static int cpuset_can_attach(struct cgroup_subsys_state *css,
 		goto out_unlock;
 
 	cgroup_taskset_for_each(task, tset) {
-		/*
-		 * Kthreads which disallow setaffinity shouldn't be moved
-		 * to a new cpuset; we don't want to change their cpu
-		 * affinity and isolating such threads by their set of
-		 * allowed nodes is unnecessary.  Thus, cpusets are not
-		 * applicable for such threads.  This prevents checking for
-		 * success of set_cpus_allowed_ptr() on all attached tasks
-		 * before cpus_allowed may be changed.
-		 */
-		ret = -EINVAL;
-		if (task->flags & PF_NO_SETAFFINITY)
+		ret = task_can_attach(task, cs->cpus_allowed);
+		if (ret)
 			goto out_unlock;
 		ret = security_task_setscheduler(task);
 		if (ret)
diff --git a/kernel/exit.c b/kernel/exit.c
index 123419be6f84..8e4e75d5efaa 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -998,6 +998,8 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p)
 
 		get_task_struct(p);
 		read_unlock(&tasklist_lock);
+		sched_annotate_sleep();
+
 		if ((exit_code & 0x7f) == 0) {
 			why = CLD_EXITED;
 			status = exit_code >> 8;
@@ -1080,6 +1082,7 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p)
 	 * thread can reap it because we its state == DEAD/TRACE.
 	 */
 	read_unlock(&tasklist_lock);
+	sched_annotate_sleep();
 
 	retval = wo->wo_rusage
 		? getrusage(p, RUSAGE_BOTH, wo->wo_rusage) : 0;
@@ -1211,6 +1214,7 @@ unlock_sig:
 	pid = task_pid_vnr(p);
 	why = ptrace ? CLD_TRAPPED : CLD_STOPPED;
 	read_unlock(&tasklist_lock);
+	sched_annotate_sleep();
 
 	if (unlikely(wo->wo_flags & WNOWAIT))
 		return wait_noreap_copyout(wo, p, pid, uid, why, exit_code);
@@ -1273,6 +1277,7 @@ static int wait_task_continued(struct wait_opts *wo, struct task_struct *p)
 	pid = task_pid_vnr(p);
 	get_task_struct(p);
 	read_unlock(&tasklist_lock);
+	sched_annotate_sleep();
 
 	if (!wo->wo_info) {
 		retval = wo->wo_rusage
diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c
index dadbf88c22c4..454195194d4a 100644
--- a/kernel/locking/mutex.c
+++ b/kernel/locking/mutex.c
@@ -378,8 +378,14 @@ done:
 	 * reschedule now, before we try-lock the mutex. This avoids getting
 	 * scheduled out right after we obtained the mutex.
 	 */
-	if (need_resched())
+	if (need_resched()) {
+		/*
+		 * We _should_ have TASK_RUNNING here, but just in case
+		 * we do not, make it so, otherwise we might get stuck.
+		 */
+		__set_current_state(TASK_RUNNING);
 		schedule_preempt_disabled();
+	}
 
 	return false;
 }
diff --git a/kernel/module.c b/kernel/module.c
index 88cec1ddb1e3..e52a8739361a 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -3097,6 +3097,32 @@ static int may_init_module(void)
 }
 
 /*
+ * Can't use wait_event_interruptible() because our condition
+ * 'finished_loading()' contains a blocking primitive itself (mutex_lock).
+ */
+static int wait_finished_loading(struct module *mod)
+{
+	DEFINE_WAIT_FUNC(wait, woken_wake_function);
+	int ret = 0;
+
+	add_wait_queue(&module_wq, &wait);
+	for (;;) {
+		if (finished_loading(mod->name))
+			break;
+
+		if (signal_pending(current)) {
+			ret = -ERESTARTSYS;
+			break;
+		}
+
+		wait_woken(&wait, TASK_INTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT);
+	}
+	remove_wait_queue(&module_wq, &wait);
+
+	return ret;
+}
+
+/*
  * We try to place it in the list now to make sure it's unique before
  * we dedicate too many resources.  In particular, temporary percpu
  * memory exhaustion.
@@ -3116,8 +3142,8 @@ again:
 		    || old->state == MODULE_STATE_UNFORMED) {
 			/* Wait in case it fails to load. */
 			mutex_unlock(&module_mutex);
-			err = wait_event_interruptible(module_wq,
-					       finished_loading(mod->name));
+
+			err = wait_finished_loading(mod);
 			if (err)
 				goto out_unlocked;
 			goto again;
diff --git a/kernel/sched/Makefile b/kernel/sched/Makefile
index 622511a4e49e..5d5380090741 100644
--- a/kernel/sched/Makefile
+++ b/kernel/sched/Makefile
@@ -20,4 +20,5 @@ obj-$(CONFIG_SCHEDSTATS) += stats.o
 obj-$(CONFIG_SCHED_DEBUG) += debug.o
 obj-$(CONFIG_CGROUP_CPUACCT) += cpuacct.o
 obj-$(CONFIG_SCHED_IO_LATENCY) += io_latency.o
-obj-$(CONFIG_SCHED_IDLE_DEBUG) += idle_debug.o
\ No newline at end of file
+obj-$(CONFIG_SCHED_IDLE_DEBUG) += idle_debug.o
+obj-$(CONFIG_CPU_FREQ_GOV_ENERGY_MODEL) += energy_model.o
diff --git a/kernel/sched/completion.c b/kernel/sched/completion.c
index a63f4dc27909..607f852b4d04 100644
--- a/kernel/sched/completion.c
+++ b/kernel/sched/completion.c
@@ -148,7 +148,7 @@ EXPORT_SYMBOL(wait_for_completion_timeout);
  *
  * This waits to be signaled for completion of a specific task. It is NOT
  * interruptible and there is no timeout. The caller is accounted as waiting
- * for IO.
+ * for IO (which traditionally means blkio only).
  */
 void __sched wait_for_completion_io(struct completion *x)
 {
@@ -163,7 +163,8 @@ EXPORT_SYMBOL(wait_for_completion_io);
  *
  * This waits for either a completion of a specific task to be signaled or for a
  * specified timeout to expire. The timeout is in jiffies. It is not
- * interruptible. The caller is accounted as waiting for IO.
+ * interruptible. The caller is accounted as waiting for IO (which traditionally
+ * means blkio only).
  *
  * Return: 0 if timed out, and positive (at least 1, or number of jiffies left
  * till timeout) if completed.
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 827ddf978f38..4db493445cd6 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1009,6 +1009,9 @@ inline int task_curr(const struct task_struct *p)
 	return cpu_curr(task_cpu(p)) == p;
 }
 
+/*
+ * Can drop rq->lock because from sched_class::switched_from() methods drop it.
+ */
 static inline void check_class_changed(struct rq *rq, struct task_struct *p,
 				       const struct sched_class *prev_class,
 				       int oldprio)
@@ -1016,6 +1019,7 @@ static inline void check_class_changed(struct rq *rq, struct task_struct *p,
 	if (prev_class != p->sched_class) {
 		if (prev_class->switched_from)
 			prev_class->switched_from(rq, p);
+		/* Possble rq->lock 'hole'.  */
 		p->sched_class->switched_to(rq, p);
 	} else if (oldprio != p->prio || dl_task(p))
 		p->sched_class->prio_changed(rq, p, oldprio);
@@ -1055,7 +1059,7 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
 	 * ttwu() will sort out the placement.
 	 */
 	WARN_ON_ONCE(p->state != TASK_RUNNING && p->state != TASK_WAKING &&
-			!(task_preempt_count(p) & PREEMPT_ACTIVE));
+			!p->on_rq);
 
 #ifdef CONFIG_LOCKDEP
 	/*
@@ -1854,8 +1858,7 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p)
 	p->numa_scan_seq = p->mm ? p->mm->numa_scan_seq : 0;
 	p->numa_scan_period = sysctl_numa_balancing_scan_delay;
 	p->numa_work.next = &p->numa_work;
-	p->numa_faults_memory = NULL;
-	p->numa_faults_buffer_memory = NULL;
+	p->numa_faults = NULL;
 	p->last_task_numa_placement = 0;
 	p->last_sum_exec_runtime = 0;
 
@@ -2035,25 +2038,6 @@ static inline int dl_bw_cpus(int i)
 }
 #endif
 
-static inline
-void __dl_clear(struct dl_bw *dl_b, u64 tsk_bw)
-{
-	dl_b->total_bw -= tsk_bw;
-}
-
-static inline
-void __dl_add(struct dl_bw *dl_b, u64 tsk_bw)
-{
-	dl_b->total_bw += tsk_bw;
-}
-
-static inline
-bool __dl_overflow(struct dl_bw *dl_b, int cpus, u64 old_bw, u64 new_bw)
-{
-	return dl_b->bw != -1 &&
-	       dl_b->bw * cpus < dl_b->total_bw - old_bw + new_bw;
-}
-
 /*
  * We must be sure that accepting a new task (or allowing changing the
  * parameters of an existing one) is consistent with the bandwidth
@@ -2221,7 +2205,6 @@ prepare_task_switch(struct rq *rq, struct task_struct *prev,
 
 /**
  * finish_task_switch - clean up after a task-switch
- * @rq: runqueue associated with task-switch
  * @prev: the thread we just switched away from.
  *
  * finish_task_switch must be called after the context switch, paired
@@ -2233,10 +2216,16 @@ prepare_task_switch(struct rq *rq, struct task_struct *prev,
  * so, we finish that here outside of the runqueue lock. (Doing it
  * with the lock held can cause deadlocks; see schedule() for
  * details.)
+ *
+ * The context switch have flipped the stack from under us and restored the
+ * local variables which were saved when this task called schedule() in the
+ * past. prev == current is still correct but we need to recalculate this_rq
+ * because prev may have moved to another CPU.
  */
-static void finish_task_switch(struct rq *rq, struct task_struct *prev)
+static struct rq *finish_task_switch(struct task_struct *prev)
 	__releases(rq->lock)
 {
+	struct rq *rq = this_rq();
 	struct mm_struct *mm = rq->prev_mm;
 	long prev_state;
 
@@ -2276,6 +2265,7 @@ static void finish_task_switch(struct rq *rq, struct task_struct *prev)
 	}
 
 	tick_nohz_task_switch(current);
+	return rq;
 }
 
 #ifdef CONFIG_SMP
@@ -2310,25 +2300,22 @@ static inline void post_schedule(struct rq *rq)
 asmlinkage __visible void schedule_tail(struct task_struct *prev)
 	__releases(rq->lock)
 {
-	struct rq *rq = this_rq();
-
-	finish_task_switch(rq, prev);
+	struct rq *rq;
 
-	/*
-	 * FIXME: do we need to worry about rq being invalidated by the
-	 * task_switch?
-	 */
+	/* finish_task_switch() drops rq->lock and enables preemtion */
+	preempt_disable();
+	rq = finish_task_switch(prev);
 	post_schedule(rq);
+	preempt_enable();
 
 	if (current->set_child_tid)
 		put_user(task_pid_vnr(current), current->set_child_tid);
 }
 
 /*
- * context_switch - switch to the new MM and the new
- * thread's register state.
+ * context_switch - switch to the new MM and the new thread's register state.
  */
-static inline void
+static inline struct rq *
 context_switch(struct rq *rq, struct task_struct *prev,
 	       struct task_struct *next)
 {
@@ -2367,14 +2354,9 @@ context_switch(struct rq *rq, struct task_struct *prev,
 	context_tracking_task_switch(prev, next);
 	/* Here we just switch the register state and the stack. */
 	switch_to(prev, next, prev);
-
 	barrier();
-	/*
-	 * this_rq must be evaluated again because prev may have moved
-	 * CPUs since it called schedule(), thus the 'rq' on its stack
-	 * frame will be invalid.
-	 */
-	finish_task_switch(this_rq(), prev);
+
+	return finish_task_switch(prev);
 }
 
 /*
@@ -2856,15 +2838,8 @@ need_resched:
 		rq->curr = next;
 		++*switch_count;
 
-		context_switch(rq, prev, next); /* unlocks the rq */
-		/*
-		 * The context switch have flipped the stack from under us
-		 * and restored the local variables which were saved when
-		 * this task called schedule() in the past. prev == current
-		 * is still correct, but it can be moved to another cpu/rq.
-		 */
-		cpu = smp_processor_id();
-		rq = cpu_rq(cpu);
+		rq = context_switch(rq, prev, next); /* unlocks the rq */
+		cpu = cpu_of(rq);
 	} else
 		raw_spin_unlock_irq(&rq->lock);
 
@@ -2952,6 +2927,47 @@ asmlinkage __visible void __sched notrace preempt_schedule(void)
 }
 NOKPROBE_SYMBOL(preempt_schedule);
 EXPORT_SYMBOL(preempt_schedule);
+
+#ifdef CONFIG_CONTEXT_TRACKING
+/**
+ * preempt_schedule_context - preempt_schedule called by tracing
+ *
+ * The tracing infrastructure uses preempt_enable_notrace to prevent
+ * recursion and tracing preempt enabling caused by the tracing
+ * infrastructure itself. But as tracing can happen in areas coming
+ * from userspace or just about to enter userspace, a preempt enable
+ * can occur before user_exit() is called. This will cause the scheduler
+ * to be called when the system is still in usermode.
+ *
+ * To prevent this, the preempt_enable_notrace will use this function
+ * instead of preempt_schedule() to exit user context if needed before
+ * calling the scheduler.
+ */
+asmlinkage __visible void __sched notrace preempt_schedule_context(void)
+{
+	enum ctx_state prev_ctx;
+
+	if (likely(!preemptible()))
+		return;
+
+	do {
+		__preempt_count_add(PREEMPT_ACTIVE);
+		/*
+		 * Needs preempt disabled in case user_exit() is traced
+		 * and the tracer calls preempt_enable_notrace() causing
+		 * an infinite recursion.
+		 */
+		prev_ctx = exception_enter();
+		__schedule();
+		exception_exit(prev_ctx);
+
+		__preempt_count_sub(PREEMPT_ACTIVE);
+		barrier();
+	} while (need_resched());
+}
+EXPORT_SYMBOL_GPL(preempt_schedule_context);
+#endif /* CONFIG_CONTEXT_TRACKING */
+
 #endif /* CONFIG_PREEMPT */
 
 /*
@@ -4642,6 +4658,81 @@ void init_idle(struct task_struct *idle, int cpu)
 #endif
 }
 
+int cpuset_cpumask_can_shrink(const struct cpumask *cur,
+			      const struct cpumask *trial)
+{
+	int ret = 1, trial_cpus;
+	struct dl_bw *cur_dl_b;
+	unsigned long flags;
+
+	rcu_read_lock_sched();
+	cur_dl_b = dl_bw_of(cpumask_any(cur));
+	trial_cpus = cpumask_weight(trial);
+
+	raw_spin_lock_irqsave(&cur_dl_b->lock, flags);
+	if (cur_dl_b->bw != -1 &&
+	    cur_dl_b->bw * trial_cpus < cur_dl_b->total_bw)
+		ret = 0;
+	raw_spin_unlock_irqrestore(&cur_dl_b->lock, flags);
+	rcu_read_unlock_sched();
+
+	return ret;
+}
+
+int task_can_attach(struct task_struct *p,
+		    const struct cpumask *cs_cpus_allowed)
+{
+	int ret = 0;
+
+	/*
+	 * Kthreads which disallow setaffinity shouldn't be moved
+	 * to a new cpuset; we don't want to change their cpu
+	 * affinity and isolating such threads by their set of
+	 * allowed nodes is unnecessary.  Thus, cpusets are not
+	 * applicable for such threads.  This prevents checking for
+	 * success of set_cpus_allowed_ptr() on all attached tasks
+	 * before cpus_allowed may be changed.
+	 */
+	if (p->flags & PF_NO_SETAFFINITY) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+#ifdef CONFIG_SMP
+	if (dl_task(p) && !cpumask_intersects(task_rq(p)->rd->span,
+					      cs_cpus_allowed)) {
+		unsigned int dest_cpu = cpumask_any_and(cpu_active_mask,
+							cs_cpus_allowed);
+		struct dl_bw *dl_b;
+		bool overflow;
+		int cpus;
+		unsigned long flags;
+
+		rcu_read_lock_sched();
+		dl_b = dl_bw_of(dest_cpu);
+		raw_spin_lock_irqsave(&dl_b->lock, flags);
+		cpus = dl_bw_cpus(dest_cpu);
+		overflow = __dl_overflow(dl_b, cpus, 0, p->dl.dl_bw);
+		if (overflow)
+			ret = -EBUSY;
+		else {
+			/*
+			 * We reserve space for this task in the destination
+			 * root_domain, as we can't fail after this point.
+			 * We will free resources in the source root_domain
+			 * later on (see set_cpus_allowed_dl()).
+			 */
+			__dl_add(dl_b, p->dl.dl_bw);
+		}
+		raw_spin_unlock_irqrestore(&dl_b->lock, flags);
+		rcu_read_unlock_sched();
+
+	}
+#endif
+out:
+	return ret;
+}
+
 #ifdef CONFIG_SMP
 /*
  * move_queued_task - move a queued task to new rq.
@@ -5374,17 +5465,6 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level,
 			break;
 		}
 
-		/*
-		 * Even though we initialize ->capacity to something semi-sane,
-		 * we leave capacity_orig unset. This allows us to detect if
-		 * domain iteration is still funny without causing /0 traps.
-		 */
-		if (!group->sgc->capacity_orig) {
-			printk(KERN_CONT "\n");
-			printk(KERN_ERR "ERROR: domain->cpu_capacity not set\n");
-			break;
-		}
-
 		if (!cpumask_weight(sched_group_cpus(group))) {
 			printk(KERN_CONT "\n");
 			printk(KERN_ERR "ERROR: empty group\n");
@@ -5869,7 +5949,6 @@ build_overlap_sched_groups(struct sched_domain *sd, int cpu)
 		 * die on a /0 trap.
 		 */
 		sg->sgc->capacity = SCHED_CAPACITY_SCALE * cpumask_weight(sg_span);
-		sg->sgc->capacity_orig = sg->sgc->capacity;
 
 		/*
 		 * Make sure the first group of this domain contains the
@@ -6092,7 +6171,9 @@ static void claim_allocations(int cpu, struct sched_domain *sd)
 
 #ifdef CONFIG_NUMA
 static int sched_domains_numa_levels;
+enum numa_topology_type sched_numa_topology_type;
 static int *sched_domains_numa_distance;
+int sched_max_numa_distance;
 static struct cpumask ***sched_domains_numa_masks;
 static int sched_domains_curr_level;
 #endif
@@ -6178,6 +6259,7 @@ sd_init(struct sched_domain_topology_level *tl, int cpu)
 	 */
 
 	if (sd->flags & SD_SHARE_CPUCAPACITY) {
+		sd->flags |= SD_PREFER_SIBLING;
 		sd->imbalance_pct = 110;
 		sd->smt_gain = 1178; /* ~15% */
 
@@ -6264,7 +6346,7 @@ static void sched_numa_warn(const char *str)
 	printk(KERN_WARNING "\n");
 }
 
-static bool find_numa_distance(int distance)
+bool find_numa_distance(int distance)
 {
 	int i;
 
@@ -6279,6 +6361,56 @@ static bool find_numa_distance(int distance)
 	return false;
 }
 
+/*
+ * A system can have three types of NUMA topology:
+ * NUMA_DIRECT: all nodes are directly connected, or not a NUMA system
+ * NUMA_GLUELESS_MESH: some nodes reachable through intermediary nodes
+ * NUMA_BACKPLANE: nodes can reach other nodes through a backplane
+ *
+ * The difference between a glueless mesh topology and a backplane
+ * topology lies in whether communication between not directly
+ * connected nodes goes through intermediary nodes (where programs
+ * could run), or through backplane controllers. This affects
+ * placement of programs.
+ *
+ * The type of topology can be discerned with the following tests:
+ * - If the maximum distance between any nodes is 1 hop, the system
+ *   is directly connected.
+ * - If for two nodes A and B, located N > 1 hops away from each other,
+ *   there is an intermediary node C, which is < N hops away from both
+ *   nodes A and B, the system is a glueless mesh.
+ */
+static void init_numa_topology_type(void)
+{
+	int a, b, c, n;
+
+	n = sched_max_numa_distance;
+
+	if (n <= 1)
+		sched_numa_topology_type = NUMA_DIRECT;
+
+	for_each_online_node(a) {
+		for_each_online_node(b) {
+			/* Find two nodes furthest removed from each other. */
+			if (node_distance(a, b) < n)
+				continue;
+
+			/* Is there an intermediary node between a and b? */
+			for_each_online_node(c) {
+				if (node_distance(a, c) < n &&
+				    node_distance(b, c) < n) {
+					sched_numa_topology_type =
+							NUMA_GLUELESS_MESH;
+					return;
+				}
+			}
+
+			sched_numa_topology_type = NUMA_BACKPLANE;
+			return;
+		}
+	}
+}
+
 static void sched_init_numa(void)
 {
 	int next_distance, curr_distance = node_distance(0, 0);
@@ -6411,6 +6543,9 @@ static void sched_init_numa(void)
 	sched_domain_topology = tl;
 
 	sched_domains_numa_levels = level;
+	sched_max_numa_distance = sched_domains_numa_distance[level - 1];
+
+	init_numa_topology_type();
 }
 
 static void sched_domains_numa_masks_set(int cpu)
@@ -7090,7 +7225,7 @@ void __init sched_init(void)
 #ifdef CONFIG_SMP
 		rq->sd = NULL;
 		rq->rd = NULL;
-		rq->cpu_capacity = SCHED_CAPACITY_SCALE;
+		rq->cpu_capacity = rq->cpu_capacity_orig = SCHED_CAPACITY_SCALE;
 		rq->post_schedule = 0;
 		rq->active_balance = 0;
 		rq->next_balance = jiffies;
@@ -7165,6 +7300,25 @@ static inline int preempt_count_equals(int preempt_offset)
 
 void __might_sleep(const char *file, int line, int preempt_offset)
 {
+	/*
+	 * Blocking primitives will set (and therefore destroy) current->state,
+	 * since we will exit with TASK_RUNNING make sure we enter with it,
+	 * otherwise we will destroy state.
+	 */
+	if (WARN_ONCE(current->state != TASK_RUNNING,
+			"do not call blocking ops when !TASK_RUNNING; "
+			"state=%lx set at [<%p>] %pS\n",
+			current->state,
+			(void *)current->task_state_change,
+			(void *)current->task_state_change))
+		__set_current_state(TASK_RUNNING);
+
+	___might_sleep(file, line, preempt_offset);
+}
+EXPORT_SYMBOL(__might_sleep);
+
+void ___might_sleep(const char *file, int line, int preempt_offset)
+{
 	static unsigned long prev_jiffy;	/* ratelimiting */
 
 	rcu_sleep_check(); /* WARN_ON_ONCE() by default, no rate limit reqd. */
@@ -7196,7 +7350,7 @@ void __might_sleep(const char *file, int line, int preempt_offset)
 #endif
 	dump_stack();
 }
-EXPORT_SYMBOL(__might_sleep);
+EXPORT_SYMBOL(___might_sleep);
 #endif
 
 #ifdef CONFIG_MAGIC_SYSRQ
@@ -7840,6 +7994,11 @@ static void cpu_cgroup_css_offline(struct cgroup_subsys_state *css)
 	sched_offline_group(tg);
 }
 
+static void cpu_cgroup_fork(struct task_struct *task)
+{
+	sched_move_task(task);
+}
+
 static int cpu_cgroup_can_attach(struct cgroup_subsys_state *css,
 				 struct cgroup_taskset *tset)
 {
@@ -8212,6 +8371,7 @@ struct cgroup_subsys cpu_cgrp_subsys = {
 	.css_free	= cpu_cgroup_css_free,
 	.css_online	= cpu_cgroup_css_online,
 	.css_offline	= cpu_cgroup_css_offline,
+	.fork		= cpu_cgroup_fork,
 	.can_attach	= cpu_cgroup_can_attach,
 	.attach		= cpu_cgroup_attach,
 	.exit		= cpu_cgroup_exit,
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 256e577faf1b..f3d7776656ee 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -518,12 +518,20 @@ again:
 	}
 
 	/*
-	 * We need to take care of a possible races here. In fact, the
-	 * task might have changed its scheduling policy to something
-	 * different from SCHED_DEADLINE or changed its reservation
-	 * parameters (through sched_setattr()).
+	 * We need to take care of several possible races here:
+	 *
+	 *   - the task might have changed its scheduling policy
+	 *     to something different than SCHED_DEADLINE
+	 *   - the task might have changed its reservation parameters
+	 *     (through sched_setattr())
+	 *   - the task might have been boosted by someone else and
+	 *     might be in the boosting/deboosting path
+	 *
+	 * In all this cases we bail out, as the task is already
+	 * in the runqueue or is going to be enqueued back anyway.
 	 */
-	if (!dl_task(p) || dl_se->dl_new)
+	if (!dl_task(p) || dl_se->dl_new ||
+	    dl_se->dl_boosted || !dl_se->dl_throttled)
 		goto unlock;
 
 	sched_clock_tick();
@@ -532,7 +540,7 @@ again:
 	dl_se->dl_yielded = 0;
 	if (task_on_rq_queued(p)) {
 		enqueue_task_dl(rq, p, ENQUEUE_REPLENISH);
-		if (task_has_dl_policy(rq->curr))
+		if (dl_task(rq->curr))
 			check_preempt_curr_dl(rq, p, 0);
 		else
 			resched_curr(rq);
@@ -555,11 +563,6 @@ void init_dl_task_timer(struct sched_dl_entity *dl_se)
 {
 	struct hrtimer *timer = &dl_se->dl_timer;
 
-	if (hrtimer_active(timer)) {
-		hrtimer_try_to_cancel(timer);
-		return;
-	}
-
 	hrtimer_init(timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	timer->function = dl_task_timer;
 }
@@ -625,7 +628,7 @@ static void update_curr_dl(struct rq *rq)
 
 	sched_rt_avg_update(rq, delta_exec);
 
-	dl_se->runtime -= delta_exec;
+	dl_se->runtime -= dl_se->dl_yielded ? 0 : delta_exec;
 	if (dl_runtime_exceeded(rq, dl_se)) {
 		__dequeue_task_dl(rq, curr, 0);
 		if (likely(start_dl_timer(dl_se, curr->dl.dl_boosted)))
@@ -847,8 +850,19 @@ static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags)
 	 * smaller than our one... OTW we keep our runtime and
 	 * deadline.
 	 */
-	if (pi_task && p->dl.dl_boosted && dl_prio(pi_task->normal_prio))
+	if (pi_task && p->dl.dl_boosted && dl_prio(pi_task->normal_prio)) {
 		pi_se = &pi_task->dl;
+	} else if (!dl_prio(p->normal_prio)) {
+		/*
+		 * Special case in which we have a !SCHED_DEADLINE task
+		 * that is going to be deboosted, but exceedes its
+		 * runtime while doing so. No point in replenishing
+		 * it, as it's going to return back to its original
+		 * scheduling class after this.
+		 */
+		BUG_ON(!p->dl.dl_boosted || flags != ENQUEUE_REPLENISH);
+		return;
+	}
 
 	/*
 	 * If p is throttled, we do nothing. In fact, if it exhausted
@@ -914,7 +928,10 @@ select_task_rq_dl(struct task_struct *p, int cpu, int sd_flag, int flags)
 	struct task_struct *curr;
 	struct rq *rq;
 
-	if (sd_flag != SD_BALANCE_WAKE && sd_flag != SD_BALANCE_FORK)
+	if (p->nr_cpus_allowed == 1)
+		goto out;
+
+	if (sd_flag != SD_BALANCE_WAKE)
 		goto out;
 
 	rq = cpu_rq(cpu);
@@ -1489,7 +1506,7 @@ static void task_woken_dl(struct rq *rq, struct task_struct *p)
 	    p->nr_cpus_allowed > 1 &&
 	    dl_task(rq->curr) &&
 	    (rq->curr->nr_cpus_allowed < 2 ||
-	     dl_entity_preempt(&rq->curr->dl, &p->dl))) {
+	     !dl_entity_preempt(&p->dl, &rq->curr->dl))) {
 		push_dl_tasks(rq);
 	}
 }
@@ -1498,10 +1515,33 @@ static void set_cpus_allowed_dl(struct task_struct *p,
 				const struct cpumask *new_mask)
 {
 	struct rq *rq;
+	struct root_domain *src_rd;
 	int weight;
 
 	BUG_ON(!dl_task(p));
 
+	rq = task_rq(p);
+	src_rd = rq->rd;
+	/*
+	 * Migrating a SCHED_DEADLINE task between exclusive
+	 * cpusets (different root_domains) entails a bandwidth
+	 * update. We already made space for us in the destination
+	 * domain (see cpuset_can_attach()).
+	 */
+	if (!cpumask_intersects(src_rd->span, new_mask)) {
+		struct dl_bw *src_dl_b;
+
+		src_dl_b = dl_bw_of(cpu_of(rq));
+		/*
+		 * We now free resources of the root_domain we are migrating
+		 * off. In the worst case, sched_setattr() may temporary fail
+		 * until we complete the update.
+		 */
+		raw_spin_lock(&src_dl_b->lock);
+		__dl_clear(src_dl_b, p->dl.dl_bw);
+		raw_spin_unlock(&src_dl_b->lock);
+	}
+
 	/*
 	 * Update only if the task is actually running (i.e.,
 	 * it is on the rq AND it is not throttled).
@@ -1518,8 +1558,6 @@ static void set_cpus_allowed_dl(struct task_struct *p,
 	if ((p->nr_cpus_allowed > 1) == (weight > 1))
 		return;
 
-	rq = task_rq(p);
-
 	/*
 	 * The process used to be able to migrate OR it can now migrate
 	 */
@@ -1567,22 +1605,48 @@ void init_sched_dl_class(void)
 
 #endif /* CONFIG_SMP */
 
+/*
+ *  Ensure p's dl_timer is cancelled. May drop rq->lock for a while.
+ */
+static void cancel_dl_timer(struct rq *rq, struct task_struct *p)
+{
+	struct hrtimer *dl_timer = &p->dl.dl_timer;
+
+	/* Nobody will change task's class if pi_lock is held */
+	lockdep_assert_held(&p->pi_lock);
+
+	if (hrtimer_active(dl_timer)) {
+		int ret = hrtimer_try_to_cancel(dl_timer);
+
+		if (unlikely(ret == -1)) {
+			/*
+			 * Note, p may migrate OR new deadline tasks
+			 * may appear in rq when we are unlocking it.
+			 * A caller of us must be fine with that.
+			 */
+			raw_spin_unlock(&rq->lock);
+			hrtimer_cancel(dl_timer);
+			raw_spin_lock(&rq->lock);
+		}
+	}
+}
+
 static void switched_from_dl(struct rq *rq, struct task_struct *p)
 {
-	if (hrtimer_active(&p->dl.dl_timer) && !dl_policy(p->policy))
-		hrtimer_try_to_cancel(&p->dl.dl_timer);
+	cancel_dl_timer(rq, p);
 
 	__dl_clear_params(p);
 
-#ifdef CONFIG_SMP
 	/*
 	 * Since this might be the only -deadline task on the rq,
 	 * this is the right place to try to pull some other one
 	 * from an overloaded cpu, if any.
 	 */
-	if (!rq->dl.dl_nr_running)
-		pull_dl_task(rq);
-#endif
+	if (!task_on_rq_queued(p) || rq->dl.dl_nr_running)
+		return;
+
+	if (pull_dl_task(rq))
+		resched_curr(rq);
 }
 
 /*
@@ -1603,12 +1667,17 @@ static void switched_to_dl(struct rq *rq, struct task_struct *p)
 
 	if (task_on_rq_queued(p) && rq->curr != p) {
 #ifdef CONFIG_SMP
-		if (rq->dl.overloaded && push_dl_task(rq) && rq != task_rq(p))
+		if (p->nr_cpus_allowed > 1 && rq->dl.overloaded &&
+			push_dl_task(rq) && rq != task_rq(p))
 			/* Only reschedule if pushing failed */
 			check_resched = 0;
 #endif /* CONFIG_SMP */
-		if (check_resched && task_has_dl_policy(rq->curr))
-			check_preempt_curr_dl(rq, p, 0);
+		if (check_resched) {
+			if (dl_task(rq->curr))
+				check_preempt_curr_dl(rq, p, 0);
+			else
+				resched_curr(rq);
+		}
 	}
 }
 
@@ -1679,3 +1748,12 @@ const struct sched_class dl_sched_class = {
 	.switched_from		= switched_from_dl,
 	.switched_to		= switched_to_dl,
 };
+
+#ifdef CONFIG_SCHED_DEBUG
+extern void print_dl_rq(struct seq_file *m, int cpu, struct dl_rq *dl_rq);
+
+void print_dl_stats(struct seq_file *m, int cpu)
+{
+	print_dl_rq(m, cpu, &cpu_rq(cpu)->dl);
+}
+#endif /* CONFIG_SCHED_DEBUG */
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index ce33780d8f20..9dce8b5abeea 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -71,7 +71,7 @@ static void print_cfs_group_stats(struct seq_file *m, int cpu, struct task_group
 	if (!se) {
 		struct sched_avg *avg = &cpu_rq(cpu)->avg;
 		P(avg->runnable_avg_sum);
-		P(avg->runnable_avg_period);
+		P(avg->avg_period);
 		return;
 	}
 
@@ -94,8 +94,10 @@ static void print_cfs_group_stats(struct seq_file *m, int cpu, struct task_group
 	P(se->load.weight);
 #ifdef CONFIG_SMP
 	P(se->avg.runnable_avg_sum);
-	P(se->avg.runnable_avg_period);
+	P(se->avg.running_avg_sum);
+	P(se->avg.avg_period);
 	P(se->avg.load_avg_contrib);
+	P(se->avg.utilization_avg_contrib);
 	P(se->avg.decay_count);
 #endif
 #undef PN
@@ -214,6 +216,8 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
 			cfs_rq->runnable_load_avg);
 	SEQ_printf(m, "  .%-30s: %ld\n", "blocked_load_avg",
 			cfs_rq->blocked_load_avg);
+	SEQ_printf(m, "  .%-30s: %ld\n", "utilization_load_avg",
+			cfs_rq->utilization_load_avg);
 #ifdef CONFIG_FAIR_GROUP_SCHED
 	SEQ_printf(m, "  .%-30s: %ld\n", "tg_load_contrib",
 			cfs_rq->tg_load_contrib);
@@ -261,6 +265,12 @@ void print_rt_rq(struct seq_file *m, int cpu, struct rt_rq *rt_rq)
 #undef P
 }
 
+void print_dl_rq(struct seq_file *m, int cpu, struct dl_rq *dl_rq)
+{
+	SEQ_printf(m, "\ndl_rq[%d]:\n", cpu);
+	SEQ_printf(m, "  .%-30s: %ld\n", "dl_nr_running", dl_rq->dl_nr_running);
+}
+
 extern __read_mostly int sched_clock_running;
 
 static void print_cpu(struct seq_file *m, int cpu)
@@ -329,6 +339,7 @@ do {									\
 	spin_lock_irqsave(&sched_debug_lock, flags);
 	print_cfs_stats(m, cpu);
 	print_rt_stats(m, cpu);
+	print_dl_stats(m, cpu);
 
 	print_rq(m, rq, cpu);
 	spin_unlock_irqrestore(&sched_debug_lock, flags);
@@ -528,8 +539,8 @@ static void sched_show_numa(struct task_struct *p, struct seq_file *m)
 			unsigned long nr_faults = -1;
 			int cpu_current, home_node;
 
-			if (p->numa_faults_memory)
-				nr_faults = p->numa_faults_memory[2*node + i];
+			if (p->numa_faults)
+				nr_faults = p->numa_faults[2*node + i];
 
 			cpu_current = !i ? (task_node(p) == node) :
 				(pol && node_isset(node, pol->v.nodes));
@@ -628,8 +639,10 @@ void proc_sched_show_task(struct task_struct *p, struct seq_file *m)
 	P(se.load.weight);
 #ifdef CONFIG_SMP
 	P(se.avg.runnable_avg_sum);
-	P(se.avg.runnable_avg_period);
+	P(se.avg.running_avg_sum);
+	P(se.avg.avg_period);
 	P(se.avg.load_avg_contrib);
+	P(se.avg.utilization_avg_contrib);
 	P(se.avg.decay_count);
 #endif
 	P(policy);
diff --git a/kernel/sched/energy_model.c b/kernel/sched/energy_model.c
new file mode 100644
index 000000000000..1599fe5dbbb1
--- /dev/null
+++ b/kernel/sched/energy_model.c
@@ -0,0 +1,341 @@
+/*
+ *  Copyright (C)  2014 Michael Turquette <mturquette@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/cpufreq.h>
+#include <linux/module.h>
+#include <linux/kthread.h>
+
+#include "sched.h"
+
+#define THROTTLE_MSEC		50
+#define UP_THRESHOLD		80
+#define DOWN_THRESHOLD		20
+
+/**
+ * em_data - per-policy data used by energy_mode
+ * @throttle: bail if current time is less than than ktime_throttle.
+ * 		    Derived from THROTTLE_MSEC
+ * @up_threshold:   table of normalized capacity states to determine if cpu
+ * 		    should run faster. Derived from UP_THRESHOLD
+ * @down_threshold: table of normalized capacity states to determine if cpu
+ * 		    should run slower. Derived from DOWN_THRESHOLD
+ *
+ * struct em_data is the per-policy energy_model-specific data structure. A
+ * per-policy instance of it is created when the energy_model governor receives
+ * the CPUFREQ_GOV_START condition and a pointer to it exists in the gov_data
+ * member of struct cpufreq_policy.
+ *
+ * Readers of this data must call down_read(policy->rwsem). Writers must
+ * call down_write(policy->rwsem).
+ */
+struct em_data {
+	/* per-policy throttling */
+	ktime_t throttle;
+	unsigned int *up_threshold;
+	unsigned int *down_threshold;
+	struct task_struct *task;
+	atomic_long_t target_freq;
+	atomic_t need_wake_task;
+};
+
+/*
+ * we pass in struct cpufreq_policy. This is safe because changing out the
+ * policy requires a call to __cpufreq_governor(policy, CPUFREQ_GOV_STOP),
+ * which tears all of the data structures down and __cpufreq_governor(policy,
+ * CPUFREQ_GOV_START) will do a full rebuild, including this kthread with the
+ * new policy pointer
+ */
+static int energy_model_thread(void *data)
+{
+	struct sched_param param;
+	struct cpufreq_policy *policy;
+	struct em_data *em;
+	int ret;
+
+	policy = (struct cpufreq_policy *) data;
+	if (!policy) {
+		pr_warn("%s: missing policy\n", __func__);
+		do_exit(-EINVAL);
+	}
+
+	em = policy->gov_data;
+	if (!em) {
+		pr_warn("%s: missing governor data\n", __func__);
+		do_exit(-EINVAL);
+	}
+
+	param.sched_priority = 0;
+	sched_setscheduler(current, SCHED_FIFO, &param);
+
+
+	do {
+		down_write(&policy->rwsem);
+		if (!atomic_read(&em->need_wake_task))  {
+			up_write(&policy->rwsem);
+			set_current_state(TASK_INTERRUPTIBLE);
+			schedule();
+			continue;
+		}
+
+		ret = __cpufreq_driver_target(policy, atomic_read(&em->target_freq),
+				CPUFREQ_RELATION_H);
+		if (ret)
+			pr_debug("%s: __cpufreq_driver_target returned %d\n",
+					__func__, ret);
+
+		em->throttle = ktime_get();
+		atomic_set(&em->need_wake_task, 0);
+		up_write(&policy->rwsem);
+	} while (!kthread_should_stop());
+
+	do_exit(0);
+}
+
+static void em_wake_up_process(struct task_struct *task)
+{
+	/* this is null during early boot */
+	if (IS_ERR_OR_NULL(task)) {
+		return;
+	}
+
+	wake_up_process(task);
+}
+
+void arch_scale_cpu_freq(void)
+{
+	struct cpufreq_policy *policy;
+	struct em_data *em;
+	int cpu;
+
+	for_each_online_cpu(cpu) {
+		policy = cpufreq_cpu_get(cpu);
+		if (IS_ERR_OR_NULL(policy))
+			continue;
+
+		em = policy->gov_data;
+		if (!em)
+			continue;
+
+		/*
+		 * FIXME replace the atomic stuff by holding write-locks
+		 * in arch_eval_cpu_freq?
+		 */
+		if (atomic_read(&em->need_wake_task)) {
+			em_wake_up_process(em->task);
+		}
+
+		cpufreq_cpu_put(policy);
+	}
+}
+
+/**
+ * arch_eval_cpu_freq - scale cpu frequency based on CFS utilization
+ * @update_cpus: mask of CPUs with updated utilization and capacity
+ *
+ * Declared and weakly defined in kernel/sched/fair.c This definition overrides
+ * the default. In the case of CONFIG_FAIR_GROUP_SCHED, update_cpus may
+ * contains cpus that are not in the same policy. Otherwise update_cpus will be
+ * a single cpu.
+ *
+ * Holds read lock for policy->rw_sem.
+ *
+ * FIXME weak arch function means that only one definition of this function can
+ * be linked. How to support multiple energy model policies?
+ */
+void arch_eval_cpu_freq(struct cpumask *update_cpus)
+{
+	struct cpufreq_policy *policy;
+	struct em_data *em;
+	int index;
+	unsigned int cpu, tmp;
+	unsigned long percent_util = 0, max_util = 0, cap = 0, util = 0;
+
+	/*
+	 * In the case of CONFIG_FAIR_GROUP_SCHED, policy->cpus may be a subset
+	 * of update_cpus. In such case take the first cpu in update_cpus, get
+	 * its policy and try to scale the affects cpus. Then we clear the
+	 * corresponding bits from update_cpus and try again. If a policy does
+	 * not exist for a cpu then we remove that bit as well, preventing an
+	 * infinite loop.
+	 */
+	while (!cpumask_empty(update_cpus)) {
+		percent_util = 0;
+		max_util = 0;
+		cap = 0;
+		util = 0;
+
+		cpu = cpumask_first(update_cpus);
+		policy = cpufreq_cpu_get(cpu);
+		if (IS_ERR_OR_NULL(policy)) {
+			cpumask_clear_cpu(cpu, update_cpus);
+			continue;
+		}
+
+		if (!policy->gov_data)
+			return;
+
+		em = policy->gov_data;
+
+		if (ktime_before(ktime_get(), em->throttle)) {
+			trace_printk("THROTTLED");
+			goto bail;
+		}
+
+		/*
+		 * try scaling cpus
+		 *
+		 * algorithm assumptions & description:
+		 * 	all cpus in a policy run at the same rate/capacity.
+		 * 	choose frequency target based on most utilized cpu.
+		 * 	do not care about aggregating cpu utilization.
+		 * 	do not track any historical trends beyond utilization
+		 * 	if max_util > 80% of current capacity,
+		 * 		go to max capacity
+		 * 	if max_util < 20% of current capacity,
+		 * 		go to the next lowest capacity
+		 * 	otherwise, stay at the same capacity state
+		 */
+		for_each_cpu(tmp, policy->cpus) {
+			util = get_cpu_usage(cpu);
+			if (util > max_util)
+				max_util = util;
+		}
+
+		cap = capacity_of(cpu);
+		if (!cap) {
+			goto bail;
+		}
+
+		index = cpufreq_frequency_table_get_index(policy, policy->cur);
+		if (max_util > em->up_threshold[index]) {
+			/* write em->target_freq with read lock held */
+			atomic_long_set(&em->target_freq, policy->max);
+			/*
+			 * FIXME this is gross. convert arch_eval_cpu_freq to
+			 * hold the write lock?
+			 */
+			atomic_set(&em->need_wake_task, 1);
+		} else if (max_util < em->down_threshold[index]) {
+			/* write em->target_freq with read lock held */
+			atomic_long_set(&em->target_freq, policy->cur - 1);
+			/*
+			 * FIXME this is gross. convert arch_eval_cpu_freq to
+			 * hold the write lock?
+			 */
+			atomic_set(&em->need_wake_task, 1);
+		}
+
+bail:
+		/* remove policy->cpus fromm update_cpus */
+		cpumask_andnot(update_cpus, update_cpus, policy->cpus);
+		cpufreq_cpu_put(policy);
+	}
+
+	return;
+}
+
+static void em_start(struct cpufreq_policy *policy)
+{
+	int index = 0, count = 0;
+	unsigned int capacity;
+	struct em_data *em;
+	struct cpufreq_frequency_table *pos;
+
+	/* prepare per-policy private data */
+	em = kzalloc(sizeof(*em), GFP_KERNEL);
+	if (!em) {
+		pr_debug("%s: failed to allocate private data\n", __func__);
+		return;
+	}
+
+	policy->gov_data = em;
+
+	/* how many entries in the frequency table? */
+	cpufreq_for_each_entry(pos, policy->freq_table)
+		count++;
+
+	/* pre-compute thresholds */
+	em->up_threshold = kcalloc(count, sizeof(unsigned int), GFP_KERNEL);
+	em->down_threshold = kcalloc(count, sizeof(unsigned int), GFP_KERNEL);
+
+	cpufreq_for_each_entry(pos, policy->freq_table) {
+		/* FIXME capacity below is not scaled for uarch */
+		capacity = pos->frequency * SCHED_CAPACITY_SCALE / policy->max;
+		em->up_threshold[index] = capacity * UP_THRESHOLD / 100;
+		em->down_threshold[index] = capacity * DOWN_THRESHOLD / 100;
+		pr_debug("%s: cpu = %u index = %d capacity = %u up = %u down = %u\n",
+				__func__, cpumask_first(policy->cpus), index,
+				capacity, em->up_threshold[index],
+				em->down_threshold[index]);
+		index++;
+	}
+
+	/* init per-policy kthread */
+	em->task = kthread_create(energy_model_thread, policy, "kenergy_model_task");
+	if (IS_ERR_OR_NULL(em->task))
+		pr_err("%s: failed to create kenergy_model_task thread\n", __func__);
+}
+
+
+static void em_stop(struct cpufreq_policy *policy)
+{
+	struct em_data *em;
+
+	em = policy->gov_data;
+
+	kthread_stop(em->task);
+
+	/* replace with devm counterparts */
+	kfree(em->up_threshold);
+	kfree(em->down_threshold);
+	kfree(em);
+}
+
+static int energy_model_setup(struct cpufreq_policy *policy, unsigned int event)
+{
+	switch (event) {
+		case CPUFREQ_GOV_START:
+			/* Start managing the frequency */
+			em_start(policy);
+			return 0;
+
+		case CPUFREQ_GOV_STOP:
+			em_stop(policy);
+			return 0;
+
+		case CPUFREQ_GOV_LIMITS:	/* unused */
+		case CPUFREQ_GOV_POLICY_INIT:	/* unused */
+		case CPUFREQ_GOV_POLICY_EXIT:	/* unused */
+			break;
+	}
+	return 0;
+}
+
+#ifndef CONFIG_CPU_FREQ_DEFAULT_GOV_ENERGY_MODEL
+static
+#endif
+struct cpufreq_governor cpufreq_gov_energy_model = {
+	.name			= "energy_model",
+	.governor		= energy_model_setup,
+	.owner			= THIS_MODULE,
+};
+
+static int __init energy_model_init(void)
+{
+	return cpufreq_register_governor(&cpufreq_gov_energy_model);
+}
+
+static void __exit energy_model_exit(void)
+{
+	cpufreq_unregister_governor(&cpufreq_gov_energy_model);
+}
+
+/* Try to make this the default governor */
+fs_initcall(energy_model_init);
+
+MODULE_LICENSE("GPL");
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 5cc44f21fe5a..5f3056215e41 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -674,6 +674,7 @@ static int select_idle_sibling(struct task_struct *p, int cpu);
 static unsigned long task_h_load(struct task_struct *p);
 
 static inline void __update_task_entity_contrib(struct sched_entity *se);
+static inline void __update_task_entity_utilization(struct sched_entity *se);
 
 /* Give new task start runnable values to heavy its load in infant time */
 void init_task_runnable_average(struct task_struct *p)
@@ -682,9 +683,10 @@ void init_task_runnable_average(struct task_struct *p)
 
 	p->se.avg.decay_count = 0;
 	slice = sched_slice(task_cfs_rq(p), &p->se) >> 10;
-	p->se.avg.runnable_avg_sum = slice;
-	p->se.avg.runnable_avg_period = slice;
+	p->se.avg.runnable_avg_sum = p->se.avg.running_avg_sum = slice;
+	p->se.avg.avg_period = slice;
 	__update_task_entity_contrib(&p->se);
+	__update_task_entity_utilization(&p->se);
 }
 #else
 void init_task_runnable_average(struct task_struct *p)
@@ -832,11 +834,12 @@ static unsigned int task_nr_scan_windows(struct task_struct *p)
 
 static unsigned int task_scan_min(struct task_struct *p)
 {
+	unsigned int scan_size = ACCESS_ONCE(sysctl_numa_balancing_scan_size);
 	unsigned int scan, floor;
 	unsigned int windows = 1;
 
-	if (sysctl_numa_balancing_scan_size < MAX_SCAN_WINDOW)
-		windows = MAX_SCAN_WINDOW / sysctl_numa_balancing_scan_size;
+	if (scan_size < MAX_SCAN_WINDOW)
+		windows = MAX_SCAN_WINDOW / scan_size;
 	floor = 1000 / windows;
 
 	scan = sysctl_numa_balancing_scan_period_min / task_nr_scan_windows(p);
@@ -899,18 +902,24 @@ pid_t task_numa_group_id(struct task_struct *p)
 	return p->numa_group ? p->numa_group->gid : 0;
 }
 
-static inline int task_faults_idx(int nid, int priv)
+/*
+ * The averaged statistics, shared & private, memory & cpu,
+ * occupy the first half of the array. The second half of the
+ * array is for current counters, which are averaged into the
+ * first set by task_numa_placement.
+ */
+static inline int task_faults_idx(enum numa_faults_stats s, int nid, int priv)
 {
-	return NR_NUMA_HINT_FAULT_TYPES * nid + priv;
+	return NR_NUMA_HINT_FAULT_TYPES * (s * nr_node_ids + nid) + priv;
 }
 
 static inline unsigned long task_faults(struct task_struct *p, int nid)
 {
-	if (!p->numa_faults_memory)
+	if (!p->numa_faults)
 		return 0;
 
-	return p->numa_faults_memory[task_faults_idx(nid, 0)] +
-		p->numa_faults_memory[task_faults_idx(nid, 1)];
+	return p->numa_faults[task_faults_idx(NUMA_MEM, nid, 0)] +
+		p->numa_faults[task_faults_idx(NUMA_MEM, nid, 1)];
 }
 
 static inline unsigned long group_faults(struct task_struct *p, int nid)
@@ -918,14 +927,79 @@ static inline unsigned long group_faults(struct task_struct *p, int nid)
 	if (!p->numa_group)
 		return 0;
 
-	return p->numa_group->faults[task_faults_idx(nid, 0)] +
-		p->numa_group->faults[task_faults_idx(nid, 1)];
+	return p->numa_group->faults[task_faults_idx(NUMA_MEM, nid, 0)] +
+		p->numa_group->faults[task_faults_idx(NUMA_MEM, nid, 1)];
 }
 
 static inline unsigned long group_faults_cpu(struct numa_group *group, int nid)
 {
-	return group->faults_cpu[task_faults_idx(nid, 0)] +
-		group->faults_cpu[task_faults_idx(nid, 1)];
+	return group->faults_cpu[task_faults_idx(NUMA_MEM, nid, 0)] +
+		group->faults_cpu[task_faults_idx(NUMA_MEM, nid, 1)];
+}
+
+/* Handle placement on systems where not all nodes are directly connected. */
+static unsigned long score_nearby_nodes(struct task_struct *p, int nid,
+					int maxdist, bool task)
+{
+	unsigned long score = 0;
+	int node;
+
+	/*
+	 * All nodes are directly connected, and the same distance
+	 * from each other. No need for fancy placement algorithms.
+	 */
+	if (sched_numa_topology_type == NUMA_DIRECT)
+		return 0;
+
+	/*
+	 * This code is called for each node, introducing N^2 complexity,
+	 * which should be ok given the number of nodes rarely exceeds 8.
+	 */
+	for_each_online_node(node) {
+		unsigned long faults;
+		int dist = node_distance(nid, node);
+
+		/*
+		 * The furthest away nodes in the system are not interesting
+		 * for placement; nid was already counted.
+		 */
+		if (dist == sched_max_numa_distance || node == nid)
+			continue;
+
+		/*
+		 * On systems with a backplane NUMA topology, compare groups
+		 * of nodes, and move tasks towards the group with the most
+		 * memory accesses. When comparing two nodes at distance
+		 * "hoplimit", only nodes closer by than "hoplimit" are part
+		 * of each group. Skip other nodes.
+		 */
+		if (sched_numa_topology_type == NUMA_BACKPLANE &&
+					dist > maxdist)
+			continue;
+
+		/* Add up the faults from nearby nodes. */
+		if (task)
+			faults = task_faults(p, node);
+		else
+			faults = group_faults(p, node);
+
+		/*
+		 * On systems with a glueless mesh NUMA topology, there are
+		 * no fixed "groups of nodes". Instead, nodes that are not
+		 * directly connected bounce traffic through intermediate
+		 * nodes; a numa_group can occupy any set of nodes.
+		 * The further away a node is, the less the faults count.
+		 * This seems to result in good task placement.
+		 */
+		if (sched_numa_topology_type == NUMA_GLUELESS_MESH) {
+			faults *= (sched_max_numa_distance - dist);
+			faults /= (sched_max_numa_distance - LOCAL_DISTANCE);
+		}
+
+		score += faults;
+	}
+
+	return score;
 }
 
 /*
@@ -934,11 +1008,12 @@ static inline unsigned long group_faults_cpu(struct numa_group *group, int nid)
  * larger multiplier, in order to group tasks together that are almost
  * evenly spread out between numa nodes.
  */
-static inline unsigned long task_weight(struct task_struct *p, int nid)
+static inline unsigned long task_weight(struct task_struct *p, int nid,
+					int dist)
 {
-	unsigned long total_faults;
+	unsigned long faults, total_faults;
 
-	if (!p->numa_faults_memory)
+	if (!p->numa_faults)
 		return 0;
 
 	total_faults = p->total_numa_faults;
@@ -946,15 +1021,29 @@ static inline unsigned long task_weight(struct task_struct *p, int nid)
 	if (!total_faults)
 		return 0;
 
-	return 1000 * task_faults(p, nid) / total_faults;
+	faults = task_faults(p, nid);
+	faults += score_nearby_nodes(p, nid, dist, true);
+
+	return 1000 * faults / total_faults;
 }
 
-static inline unsigned long group_weight(struct task_struct *p, int nid)
+static inline unsigned long group_weight(struct task_struct *p, int nid,
+					 int dist)
 {
-	if (!p->numa_group || !p->numa_group->total_faults)
+	unsigned long faults, total_faults;
+
+	if (!p->numa_group)
 		return 0;
 
-	return 1000 * group_faults(p, nid) / p->numa_group->total_faults;
+	total_faults = p->numa_group->total_faults;
+
+	if (!total_faults)
+		return 0;
+
+	faults = group_faults(p, nid);
+	faults += score_nearby_nodes(p, nid, dist, false);
+
+	return 1000 * faults / total_faults;
 }
 
 bool should_numa_migrate_memory(struct task_struct *p, struct page * page,
@@ -1023,7 +1112,6 @@ bool should_numa_migrate_memory(struct task_struct *p, struct page * page,
 static unsigned long weighted_cpuload(const int cpu);
 static unsigned long source_load(int cpu, int type);
 static unsigned long target_load(int cpu, int type);
-static unsigned long capacity_of(int cpu);
 static long effective_load(struct task_group *tg, int cpu, long wl, long wg);
 
 /* Cached statistics for all CPUs within a node */
@@ -1087,6 +1175,7 @@ struct task_numa_env {
 	struct numa_stats src_stats, dst_stats;
 
 	int imbalance_pct;
+	int dist;
 
 	struct task_struct *best_task;
 	long best_imp;
@@ -1166,11 +1255,22 @@ static void task_numa_compare(struct task_numa_env *env,
 	long load;
 	long imp = env->p->numa_group ? groupimp : taskimp;
 	long moveimp = imp;
+	int dist = env->dist;
 
 	rcu_read_lock();
-	cur = ACCESS_ONCE(dst_rq->curr);
-	if (cur->pid == 0) /* idle */
+
+	raw_spin_lock_irq(&dst_rq->lock);
+	cur = dst_rq->curr;
+	/*
+	 * No need to move the exiting task, and this ensures that ->curr
+	 * wasn't reaped and thus get_task_struct() in task_numa_assign()
+	 * is safe under RCU read lock.
+	 * Note that rcu_read_lock() itself can't protect from the final
+	 * put_task_struct() after the last schedule().
+	 */
+	if ((cur->flags & PF_EXITING) || is_idle_task(cur))
 		cur = NULL;
+	raw_spin_unlock_irq(&dst_rq->lock);
 
 	/*
 	 * "imp" is the fault differential for the source task between the
@@ -1189,8 +1289,8 @@ static void task_numa_compare(struct task_numa_env *env,
 		 * in any group then look only at task weights.
 		 */
 		if (cur->numa_group == env->p->numa_group) {
-			imp = taskimp + task_weight(cur, env->src_nid) -
-			      task_weight(cur, env->dst_nid);
+			imp = taskimp + task_weight(cur, env->src_nid, dist) -
+			      task_weight(cur, env->dst_nid, dist);
 			/*
 			 * Add some hysteresis to prevent swapping the
 			 * tasks within a group over tiny differences.
@@ -1204,11 +1304,11 @@ static void task_numa_compare(struct task_numa_env *env,
 			 * instead.
 			 */
 			if (cur->numa_group)
-				imp += group_weight(cur, env->src_nid) -
-				       group_weight(cur, env->dst_nid);
+				imp += group_weight(cur, env->src_nid, dist) -
+				       group_weight(cur, env->dst_nid, dist);
 			else
-				imp += task_weight(cur, env->src_nid) -
-				       task_weight(cur, env->dst_nid);
+				imp += task_weight(cur, env->src_nid, dist) -
+				       task_weight(cur, env->dst_nid, dist);
 		}
 	}
 
@@ -1307,7 +1407,7 @@ static int task_numa_migrate(struct task_struct *p)
 	};
 	struct sched_domain *sd;
 	unsigned long taskweight, groupweight;
-	int nid, ret;
+	int nid, ret, dist;
 	long taskimp, groupimp;
 
 	/*
@@ -1335,29 +1435,45 @@ static int task_numa_migrate(struct task_struct *p)
 		return -EINVAL;
 	}
 
-	taskweight = task_weight(p, env.src_nid);
-	groupweight = group_weight(p, env.src_nid);
-	update_numa_stats(&env.src_stats, env.src_nid);
 	env.dst_nid = p->numa_preferred_nid;
-	taskimp = task_weight(p, env.dst_nid) - taskweight;
-	groupimp = group_weight(p, env.dst_nid) - groupweight;
+	dist = env.dist = node_distance(env.src_nid, env.dst_nid);
+	taskweight = task_weight(p, env.src_nid, dist);
+	groupweight = group_weight(p, env.src_nid, dist);
+	update_numa_stats(&env.src_stats, env.src_nid);
+	taskimp = task_weight(p, env.dst_nid, dist) - taskweight;
+	groupimp = group_weight(p, env.dst_nid, dist) - groupweight;
 	update_numa_stats(&env.dst_stats, env.dst_nid);
 
 	/* Try to find a spot on the preferred nid. */
 	task_numa_find_cpu(&env, taskimp, groupimp);
 
-	/* No space available on the preferred nid. Look elsewhere. */
-	if (env.best_cpu == -1) {
+	/*
+	 * Look at other nodes in these cases:
+	 * - there is no space available on the preferred_nid
+	 * - the task is part of a numa_group that is interleaved across
+	 *   multiple NUMA nodes; in order to better consolidate the group,
+	 *   we need to check other locations.
+	 */
+	if (env.best_cpu == -1 || (p->numa_group &&
+			nodes_weight(p->numa_group->active_nodes) > 1)) {
 		for_each_online_node(nid) {
 			if (nid == env.src_nid || nid == p->numa_preferred_nid)
 				continue;
 
+			dist = node_distance(env.src_nid, env.dst_nid);
+			if (sched_numa_topology_type == NUMA_BACKPLANE &&
+						dist != env.dist) {
+				taskweight = task_weight(p, env.src_nid, dist);
+				groupweight = group_weight(p, env.src_nid, dist);
+			}
+
 			/* Only consider nodes where both task and groups benefit */
-			taskimp = task_weight(p, nid) - taskweight;
-			groupimp = group_weight(p, nid) - groupweight;
+			taskimp = task_weight(p, nid, dist) - taskweight;
+			groupimp = group_weight(p, nid, dist) - groupweight;
 			if (taskimp < 0 && groupimp < 0)
 				continue;
 
+			env.dist = dist;
 			env.dst_nid = nid;
 			update_numa_stats(&env.dst_stats, env.dst_nid);
 			task_numa_find_cpu(&env, taskimp, groupimp);
@@ -1412,7 +1528,7 @@ static void numa_migrate_preferred(struct task_struct *p)
 	unsigned long interval = HZ;
 
 	/* This task has no NUMA fault statistics yet */
-	if (unlikely(p->numa_preferred_nid == -1 || !p->numa_faults_memory))
+	if (unlikely(p->numa_preferred_nid == -1 || !p->numa_faults))
 		return;
 
 	/* Periodically retry migrating the task to the preferred node */
@@ -1524,7 +1640,7 @@ static void update_task_scan_period(struct task_struct *p,
 		 * scanning faster if shared accesses dominate as it may
 		 * simply bounce migrations uselessly
 		 */
-		ratio = DIV_ROUND_UP(private * NUMA_PERIOD_SLOTS, (private + shared));
+		ratio = DIV_ROUND_UP(private * NUMA_PERIOD_SLOTS, (private + shared + 1));
 		diff = (diff * ratio) / NUMA_PERIOD_SLOTS;
 	}
 
@@ -1552,7 +1668,7 @@ static u64 numa_get_avg_runtime(struct task_struct *p, u64 *period)
 		*period = now - p->last_task_numa_placement;
 	} else {
 		delta = p->se.avg.runnable_avg_sum;
-		*period = p->se.avg.runnable_avg_period;
+		*period = p->se.avg.avg_period;
 	}
 
 	p->last_sum_exec_runtime = runtime;
@@ -1561,6 +1677,92 @@ static u64 numa_get_avg_runtime(struct task_struct *p, u64 *period)
 	return delta;
 }
 
+/*
+ * Determine the preferred nid for a task in a numa_group. This needs to
+ * be done in a way that produces consistent results with group_weight,
+ * otherwise workloads might not converge.
+ */
+static int preferred_group_nid(struct task_struct *p, int nid)
+{
+	nodemask_t nodes;
+	int dist;
+
+	/* Direct connections between all NUMA nodes. */
+	if (sched_numa_topology_type == NUMA_DIRECT)
+		return nid;
+
+	/*
+	 * On a system with glueless mesh NUMA topology, group_weight
+	 * scores nodes according to the number of NUMA hinting faults on
+	 * both the node itself, and on nearby nodes.
+	 */
+	if (sched_numa_topology_type == NUMA_GLUELESS_MESH) {
+		unsigned long score, max_score = 0;
+		int node, max_node = nid;
+
+		dist = sched_max_numa_distance;
+
+		for_each_online_node(node) {
+			score = group_weight(p, node, dist);
+			if (score > max_score) {
+				max_score = score;
+				max_node = node;
+			}
+		}
+		return max_node;
+	}
+
+	/*
+	 * Finding the preferred nid in a system with NUMA backplane
+	 * interconnect topology is more involved. The goal is to locate
+	 * tasks from numa_groups near each other in the system, and
+	 * untangle workloads from different sides of the system. This requires
+	 * searching down the hierarchy of node groups, recursively searching
+	 * inside the highest scoring group of nodes. The nodemask tricks
+	 * keep the complexity of the search down.
+	 */
+	nodes = node_online_map;
+	for (dist = sched_max_numa_distance; dist > LOCAL_DISTANCE; dist--) {
+		unsigned long max_faults = 0;
+		nodemask_t max_group;
+		int a, b;
+
+		/* Are there nodes at this distance from each other? */
+		if (!find_numa_distance(dist))
+			continue;
+
+		for_each_node_mask(a, nodes) {
+			unsigned long faults = 0;
+			nodemask_t this_group;
+			nodes_clear(this_group);
+
+			/* Sum group's NUMA faults; includes a==b case. */
+			for_each_node_mask(b, nodes) {
+				if (node_distance(a, b) < dist) {
+					faults += group_faults(p, b);
+					node_set(b, this_group);
+					node_clear(b, nodes);
+				}
+			}
+
+			/* Remember the top group. */
+			if (faults > max_faults) {
+				max_faults = faults;
+				max_group = this_group;
+				/*
+				 * subtle: at the smallest distance there is
+				 * just one node left in each "group", the
+				 * winner is the preferred nid.
+				 */
+				nid = a;
+			}
+		}
+		/* Next round, evaluate the nodes within max_group. */
+		nodes = max_group;
+	}
+	return nid;
+}
+
 static void task_numa_placement(struct task_struct *p)
 {
 	int seq, nid, max_nid = -1, max_group_nid = -1;
@@ -1588,18 +1790,23 @@ static void task_numa_placement(struct task_struct *p)
 
 	/* Find the node with the highest number of faults */
 	for_each_online_node(nid) {
+		/* Keep track of the offsets in numa_faults array */
+		int mem_idx, membuf_idx, cpu_idx, cpubuf_idx;
 		unsigned long faults = 0, group_faults = 0;
-		int priv, i;
+		int priv;
 
 		for (priv = 0; priv < NR_NUMA_HINT_FAULT_TYPES; priv++) {
 			long diff, f_diff, f_weight;
 
-			i = task_faults_idx(nid, priv);
+			mem_idx = task_faults_idx(NUMA_MEM, nid, priv);
+			membuf_idx = task_faults_idx(NUMA_MEMBUF, nid, priv);
+			cpu_idx = task_faults_idx(NUMA_CPU, nid, priv);
+			cpubuf_idx = task_faults_idx(NUMA_CPUBUF, nid, priv);
 
 			/* Decay existing window, copy faults since last scan */
-			diff = p->numa_faults_buffer_memory[i] - p->numa_faults_memory[i] / 2;
-			fault_types[priv] += p->numa_faults_buffer_memory[i];
-			p->numa_faults_buffer_memory[i] = 0;
+			diff = p->numa_faults[membuf_idx] - p->numa_faults[mem_idx] / 2;
+			fault_types[priv] += p->numa_faults[membuf_idx];
+			p->numa_faults[membuf_idx] = 0;
 
 			/*
 			 * Normalize the faults_from, so all tasks in a group
@@ -1609,21 +1816,27 @@ static void task_numa_placement(struct task_struct *p)
 			 * faults are less important.
 			 */
 			f_weight = div64_u64(runtime << 16, period + 1);
-			f_weight = (f_weight * p->numa_faults_buffer_cpu[i]) /
+			f_weight = (f_weight * p->numa_faults[cpubuf_idx]) /
 				   (total_faults + 1);
-			f_diff = f_weight - p->numa_faults_cpu[i] / 2;
-			p->numa_faults_buffer_cpu[i] = 0;
+			f_diff = f_weight - p->numa_faults[cpu_idx] / 2;
+			p->numa_faults[cpubuf_idx] = 0;
 
-			p->numa_faults_memory[i] += diff;
-			p->numa_faults_cpu[i] += f_diff;
-			faults += p->numa_faults_memory[i];
+			p->numa_faults[mem_idx] += diff;
+			p->numa_faults[cpu_idx] += f_diff;
+			faults += p->numa_faults[mem_idx];
 			p->total_numa_faults += diff;
 			if (p->numa_group) {
-				/* safe because we can only change our own group */
-				p->numa_group->faults[i] += diff;
-				p->numa_group->faults_cpu[i] += f_diff;
+				/*
+				 * safe because we can only change our own group
+				 *
+				 * mem_idx represents the offset for a given
+				 * nid and priv in a specific region because it
+				 * is at the beginning of the numa_faults array.
+				 */
+				p->numa_group->faults[mem_idx] += diff;
+				p->numa_group->faults_cpu[mem_idx] += f_diff;
 				p->numa_group->total_faults += diff;
-				group_faults += p->numa_group->faults[i];
+				group_faults += p->numa_group->faults[mem_idx];
 			}
 		}
 
@@ -1643,7 +1856,7 @@ static void task_numa_placement(struct task_struct *p)
 	if (p->numa_group) {
 		update_numa_active_node_mask(p->numa_group);
 		spin_unlock_irq(group_lock);
-		max_nid = max_group_nid;
+		max_nid = preferred_group_nid(p, max_group_nid);
 	}
 
 	if (max_faults) {
@@ -1695,7 +1908,7 @@ static void task_numa_group(struct task_struct *p, int cpupid, int flags,
 		node_set(task_node(current), grp->active_nodes);
 
 		for (i = 0; i < NR_NUMA_HINT_FAULT_STATS * nr_node_ids; i++)
-			grp->faults[i] = p->numa_faults_memory[i];
+			grp->faults[i] = p->numa_faults[i];
 
 		grp->total_faults = p->total_numa_faults;
 
@@ -1754,8 +1967,8 @@ static void task_numa_group(struct task_struct *p, int cpupid, int flags,
 	double_lock_irq(&my_grp->lock, &grp->lock);
 
 	for (i = 0; i < NR_NUMA_HINT_FAULT_STATS * nr_node_ids; i++) {
-		my_grp->faults[i] -= p->numa_faults_memory[i];
-		grp->faults[i] += p->numa_faults_memory[i];
+		my_grp->faults[i] -= p->numa_faults[i];
+		grp->faults[i] += p->numa_faults[i];
 	}
 	my_grp->total_faults -= p->total_numa_faults;
 	grp->total_faults += p->total_numa_faults;
@@ -1780,14 +1993,14 @@ no_join:
 void task_numa_free(struct task_struct *p)
 {
 	struct numa_group *grp = p->numa_group;
-	void *numa_faults = p->numa_faults_memory;
+	void *numa_faults = p->numa_faults;
 	unsigned long flags;
 	int i;
 
 	if (grp) {
 		spin_lock_irqsave(&grp->lock, flags);
 		for (i = 0; i < NR_NUMA_HINT_FAULT_STATS * nr_node_ids; i++)
-			grp->faults[i] -= p->numa_faults_memory[i];
+			grp->faults[i] -= p->numa_faults[i];
 		grp->total_faults -= p->total_numa_faults;
 
 		list_del(&p->numa_entry);
@@ -1797,10 +2010,7 @@ void task_numa_free(struct task_struct *p)
 		put_numa_group(grp);
 	}
 
-	p->numa_faults_memory = NULL;
-	p->numa_faults_buffer_memory = NULL;
-	p->numa_faults_cpu= NULL;
-	p->numa_faults_buffer_cpu = NULL;
+	p->numa_faults = NULL;
 	kfree(numa_faults);
 }
 
@@ -1823,24 +2033,14 @@ void task_numa_fault(int last_cpupid, int mem_node, int pages, int flags)
 		return;
 
 	/* Allocate buffer to track faults on a per-node basis */
-	if (unlikely(!p->numa_faults_memory)) {
-		int size = sizeof(*p->numa_faults_memory) *
+	if (unlikely(!p->numa_faults)) {
+		int size = sizeof(*p->numa_faults) *
 			   NR_NUMA_HINT_FAULT_BUCKETS * nr_node_ids;
 
-		p->numa_faults_memory = kzalloc(size, GFP_KERNEL|__GFP_NOWARN);
-		if (!p->numa_faults_memory)
+		p->numa_faults = kzalloc(size, GFP_KERNEL|__GFP_NOWARN);
+		if (!p->numa_faults)
 			return;
 
-		BUG_ON(p->numa_faults_buffer_memory);
-		/*
-		 * The averaged statistics, shared & private, memory & cpu,
-		 * occupy the first half of the array. The second half of the
-		 * array is for current counters, which are averaged into the
-		 * first set by task_numa_placement.
-		 */
-		p->numa_faults_cpu = p->numa_faults_memory + (2 * nr_node_ids);
-		p->numa_faults_buffer_memory = p->numa_faults_memory + (4 * nr_node_ids);
-		p->numa_faults_buffer_cpu = p->numa_faults_memory + (6 * nr_node_ids);
 		p->total_numa_faults = 0;
 		memset(p->numa_faults_locality, 0, sizeof(p->numa_faults_locality));
 	}
@@ -1880,8 +2080,8 @@ void task_numa_fault(int last_cpupid, int mem_node, int pages, int flags)
 	if (migrated)
 		p->numa_pages_migrated += pages;
 
-	p->numa_faults_buffer_memory[task_faults_idx(mem_node, priv)] += pages;
-	p->numa_faults_buffer_cpu[task_faults_idx(cpu_node, priv)] += pages;
+	p->numa_faults[task_faults_idx(NUMA_MEMBUF, mem_node, priv)] += pages;
+	p->numa_faults[task_faults_idx(NUMA_CPUBUF, cpu_node, priv)] += pages;
 	p->numa_faults_locality[local] += pages;
 }
 
@@ -2064,6 +2264,11 @@ static inline void account_numa_dequeue(struct rq *rq, struct task_struct *p)
 }
 #endif /* CONFIG_NUMA_BALANCING */
 
+#ifdef CONFIG_SMP
+unsigned long capacity_of(int cpu);
+//unsigned long usage_util_of(int cpu);
+#endif /* CONFIG_SMP */
+
 static void
 account_entity_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
@@ -2268,6 +2473,10 @@ static u32 __compute_runnable_contrib(u64 n)
 	return contrib + runnable_avg_yN_sum[n];
 }
 
+unsigned long __weak arch_scale_freq_capacity(struct sched_domain *sd, int cpu);
+void arch_eval_cpu_freq(struct cpumask *cpus);
+void arch_scale_cpu_freq(void);
+
 /*
  * We can represent the historical contribution to runnable average as the
  * coefficients of a geometric series.  To do this we sub-divide our runnable
@@ -2296,13 +2505,15 @@ static u32 __compute_runnable_contrib(u64 n)
  *   load_avg = u_0` + y*(u_0 + u_1*y + u_2*y^2 + ... )
  *            = u_0 + u_1*y + u_2*y^2 + ... [re-labeling u_i --> u_{i+1}]
  */
-static __always_inline int __update_entity_runnable_avg(u64 now,
+static __always_inline int __update_entity_runnable_avg(u64 now, int cpu,
 							struct sched_avg *sa,
-							int runnable)
+							int runnable,
+							int running)
 {
 	u64 delta, periods;
 	u32 runnable_contrib;
 	int delta_w, decayed = 0;
+	unsigned long scale_freq = arch_scale_freq_capacity(NULL, cpu);
 
 	delta = now - sa->last_runnable_update;
 	/*
@@ -2324,7 +2535,7 @@ static __always_inline int __update_entity_runnable_avg(u64 now,
 	sa->last_runnable_update = now;
 
 	/* delta_w is the amount already accumulated against our next period */
-	delta_w = sa->runnable_avg_period % 1024;
+	delta_w = sa->avg_period % 1024;
 	if (delta + delta_w >= 1024) {
 		/* period roll-over */
 		decayed = 1;
@@ -2337,7 +2548,10 @@ static __always_inline int __update_entity_runnable_avg(u64 now,
 		delta_w = 1024 - delta_w;
 		if (runnable)
 			sa->runnable_avg_sum += delta_w;
-		sa->runnable_avg_period += delta_w;
+		if (running)
+			sa->running_avg_sum += delta_w * scale_freq
+				>> SCHED_CAPACITY_SHIFT;
+		sa->avg_period += delta_w;
 
 		delta -= delta_w;
 
@@ -2347,20 +2561,28 @@ static __always_inline int __update_entity_runnable_avg(u64 now,
 
 		sa->runnable_avg_sum = decay_load(sa->runnable_avg_sum,
 						  periods + 1);
-		sa->runnable_avg_period = decay_load(sa->runnable_avg_period,
+		sa->running_avg_sum = decay_load(sa->running_avg_sum,
+						  periods + 1);
+		sa->avg_period = decay_load(sa->avg_period,
 						     periods + 1);
 
 		/* Efficiently calculate \sum (1..n_period) 1024*y^i */
 		runnable_contrib = __compute_runnable_contrib(periods);
 		if (runnable)
 			sa->runnable_avg_sum += runnable_contrib;
-		sa->runnable_avg_period += runnable_contrib;
+		if (running)
+			sa->running_avg_sum += runnable_contrib * scale_freq
+				>> SCHED_CAPACITY_SHIFT;
+		sa->avg_period += runnable_contrib;
 	}
 
 	/* Remainder of delta accrued against u_0` */
 	if (runnable)
 		sa->runnable_avg_sum += delta;
-	sa->runnable_avg_period += delta;
+	if (running)
+		sa->running_avg_sum += delta * scale_freq
+			>> SCHED_CAPACITY_SHIFT;
+	sa->avg_period += delta;
 
 	return decayed;
 }
@@ -2376,6 +2598,8 @@ static inline u64 __synchronize_entity_decay(struct sched_entity *se)
 		return 0;
 
 	se->avg.load_avg_contrib = decay_load(se->avg.load_avg_contrib, decays);
+	se->avg.utilization_avg_contrib =
+		decay_load(se->avg.utilization_avg_contrib, decays);
 	se->avg.decay_count = 0;
 
 	return decays;
@@ -2412,7 +2636,7 @@ static inline void __update_tg_runnable_avg(struct sched_avg *sa,
 
 	/* The fraction of a cpu used by this cfs_rq */
 	contrib = div_u64((u64)sa->runnable_avg_sum << NICE_0_SHIFT,
-			  sa->runnable_avg_period + 1);
+			  sa->avg_period + 1);
 	contrib -= cfs_rq->tg_runnable_contrib;
 
 	if (abs(contrib) > cfs_rq->tg_runnable_contrib / 64) {
@@ -2465,7 +2689,8 @@ static inline void __update_group_entity_contrib(struct sched_entity *se)
 
 static inline void update_rq_runnable_avg(struct rq *rq, int runnable)
 {
-	__update_entity_runnable_avg(rq_clock_task(rq), &rq->avg, runnable);
+	__update_entity_runnable_avg(rq_clock_task(rq), cpu_of(rq), &rq->avg,
+			runnable, runnable);
 	__update_tg_runnable_avg(&rq->avg, &rq->cfs);
 }
 #else /* CONFIG_FAIR_GROUP_SCHED */
@@ -2483,7 +2708,7 @@ static inline void __update_task_entity_contrib(struct sched_entity *se)
 
 	/* avoid overflowing a 32-bit type w/ SCHED_LOAD_SCALE */
 	contrib = se->avg.runnable_avg_sum * scale_load_down(se->load.weight);
-	contrib /= (se->avg.runnable_avg_period + 1);
+	contrib /= (se->avg.avg_period + 1);
 	se->avg.load_avg_contrib = scale_load(contrib);
 }
 
@@ -2502,6 +2727,30 @@ static long __update_entity_load_avg_contrib(struct sched_entity *se)
 	return se->avg.load_avg_contrib - old_contrib;
 }
 
+
+static inline void __update_task_entity_utilization(struct sched_entity *se)
+{
+	u32 contrib;
+
+	/* avoid overflowing a 32-bit type w/ SCHED_LOAD_SCALE */
+	contrib = se->avg.running_avg_sum * scale_load_down(SCHED_LOAD_SCALE);
+	contrib /= (se->avg.avg_period + 1);
+	se->avg.utilization_avg_contrib = scale_load(contrib);
+}
+
+static long __update_entity_utilization_avg_contrib(struct sched_entity *se)
+{
+	long old_contrib = se->avg.utilization_avg_contrib;
+
+	if (entity_is_task(se))
+		__update_task_entity_utilization(se);
+	else
+		se->avg.utilization_avg_contrib =
+					group_cfs_rq(se)->utilization_load_avg;
+
+	return se->avg.utilization_avg_contrib - old_contrib;
+}
+
 static inline void subtract_blocked_load_contrib(struct cfs_rq *cfs_rq,
 						 long load_contrib)
 {
@@ -2518,7 +2767,8 @@ static inline void update_entity_load_avg(struct sched_entity *se,
 					  int update_cfs_rq)
 {
 	struct cfs_rq *cfs_rq = cfs_rq_of(se);
-	long contrib_delta;
+	long contrib_delta, utilization_delta;
+	int cpu = cpu_of(rq_of(cfs_rq));
 	u64 now;
 
 	/*
@@ -2530,18 +2780,22 @@ static inline void update_entity_load_avg(struct sched_entity *se,
 	else
 		now = cfs_rq_clock_task(group_cfs_rq(se));
 
-	if (!__update_entity_runnable_avg(now, &se->avg, se->on_rq))
+	if (!__update_entity_runnable_avg(now, cpu, &se->avg, se->on_rq,
+					cfs_rq->curr == se))
 		return;
 
 	contrib_delta = __update_entity_load_avg_contrib(se);
+	utilization_delta = __update_entity_utilization_avg_contrib(se);
 
 	if (!update_cfs_rq)
 		return;
 
-	if (se->on_rq)
+	if (se->on_rq) {
 		cfs_rq->runnable_load_avg += contrib_delta;
-	else
+		cfs_rq->utilization_load_avg += utilization_delta;
+	} else {
 		subtract_blocked_load_contrib(cfs_rq, -contrib_delta);
+	}
 }
 
 /*
@@ -2616,6 +2870,7 @@ static inline void enqueue_entity_load_avg(struct cfs_rq *cfs_rq,
 	}
 
 	cfs_rq->runnable_load_avg += se->avg.load_avg_contrib;
+	cfs_rq->utilization_load_avg += se->avg.utilization_avg_contrib;
 	/* we force update consideration on load-balancer moves */
 	update_cfs_rq_blocked_load(cfs_rq, !wakeup);
 }
@@ -2634,6 +2889,7 @@ static inline void dequeue_entity_load_avg(struct cfs_rq *cfs_rq,
 	update_cfs_rq_blocked_load(cfs_rq, !sleep);
 
 	cfs_rq->runnable_load_avg -= se->avg.load_avg_contrib;
+	cfs_rq->utilization_load_avg -= se->avg.utilization_avg_contrib;
 	if (sleep) {
 		cfs_rq->blocked_load_avg += se->avg.load_avg_contrib;
 		se->avg.decay_count = atomic64_read(&cfs_rq->decay_counter);
@@ -2971,6 +3227,7 @@ set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
 		 */
 		update_stats_wait_end(cfs_rq, se);
 		__dequeue_entity(cfs_rq, se);
+		update_entity_load_avg(se, 1);
 	}
 
 	update_stats_curr_start(cfs_rq, se);
@@ -3939,6 +4196,11 @@ static inline void hrtick_update(struct rq *rq)
 }
 #endif
 
+static inline bool energy_aware(void)
+{
+	return sched_feat(ENERGY_AWARE);
+}
+
 /*
  * The enqueue_task method is called before nr_running is
  * increased. Here we update the fair scheduling stats and
@@ -3949,6 +4211,9 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 {
 	struct cfs_rq *cfs_rq;
 	struct sched_entity *se = &p->se;
+	struct cpumask update_cpus;
+
+	cpumask_clear(&update_cpus);
 
 	for_each_sched_entity(se) {
 		if (se->on_rq)
@@ -3978,12 +4243,27 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 
 		update_cfs_shares(cfs_rq);
 		update_entity_load_avg(se, 1);
+		/* track cpus that need to be re-evaluated */
+		cpumask_set_cpu(cpu_of(rq_of(cfs_rq)), &update_cpus);
 	}
 
+	/* !CONFIG_FAIR_GROUP_SCHED */
 	if (!se) {
 		update_rq_runnable_avg(rq, rq->nr_running);
 		add_nr_running(rq, 1);
+
+		/*
+		 * FIXME for !CONFIG_FAIR_GROUP_SCHED it might be nice to
+		 * typedef update_cpus into an int and skip all of the cpumask
+		 * stuff
+		 */
+		cpumask_set_cpu(cpu_of(rq), &update_cpus);
 	}
+
+	if (energy_aware())
+		if (!cpumask_empty(&update_cpus))
+			arch_eval_cpu_freq(&update_cpus);
+
 	hrtick_update(rq);
 }
 
@@ -3999,6 +4279,9 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 	struct cfs_rq *cfs_rq;
 	struct sched_entity *se = &p->se;
 	int task_sleep = flags & DEQUEUE_SLEEP;
+	struct cpumask update_cpus;
+
+	cpumask_clear(&update_cpus);
 
 	for_each_sched_entity(se) {
 		cfs_rq = cfs_rq_of(se);
@@ -4039,12 +4322,27 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 
 		update_cfs_shares(cfs_rq);
 		update_entity_load_avg(se, 1);
+		/* track runqueues/cpus that need to be re-evaluated */
+		cpumask_set_cpu(cpu_of(rq_of(cfs_rq)), &update_cpus);
 	}
 
+	/* !CONFIG_FAIR_GROUP_SCHED */
 	if (!se) {
 		sub_nr_running(rq, 1);
 		update_rq_runnable_avg(rq, 1);
+
+		/*
+		 * FIXME for !CONFIG_FAIR_GROUP_SCHED it might be nice to
+		 * typedef update_cpus into an int and skip all of the cpumask
+		 * stuff
+		 */
+		cpumask_set_cpu(cpu_of(rq), &update_cpus);
 	}
+
+	if (energy_aware())
+		if (!cpumask_empty(&update_cpus))
+			arch_eval_cpu_freq(&update_cpus);
+
 	hrtick_update(rq);
 }
 
@@ -4088,11 +4386,16 @@ static unsigned long target_load(int cpu, int type)
 	return max(rq->cpu_load[type-1], total);
 }
 
-static unsigned long capacity_of(int cpu)
+unsigned long capacity_of(int cpu)
 {
 	return cpu_rq(cpu)->cpu_capacity;
 }
 
+static unsigned long capacity_orig_of(int cpu)
+{
+	return cpu_rq(cpu)->cpu_capacity_orig;
+}
+
 static unsigned long cpu_avg_load_per_task(int cpu)
 {
 	struct rq *rq = cpu_rq(cpu);
@@ -4450,7 +4753,7 @@ find_idlest_cpu(struct sched_group *group, struct task_struct *p, int this_cpu)
 				latest_idle_timestamp = rq->idle_stamp;
 				shallowest_idle_cpu = i;
 			}
-		} else {
+		} else if (shallowest_idle_cpu == -1) {
 			load = weighted_cpuload(i);
 			if (load < min_load || (load == min_load && i == this_cpu)) {
 				min_load = load;
@@ -4506,6 +4809,33 @@ next:
 done:
 	return target;
 }
+/*
+ * get_cpu_usage returns the amount of capacity of a CPU that is used by CFS
+ * tasks. The unit of the return value must capacity so we can compare the
+ * usage with the capacity of the CPU that is available for CFS task (ie
+ * cpu_capacity).
+ * cfs.utilization_load_avg is the sum of running time of runnable tasks on a
+ * CPU. It represents the amount of utilization of a CPU in the range
+ * [0..SCHED_LOAD_SCALE].  The usage of a CPU can't be higher than the full
+ * capacity of the CPU because it's about the running time on this CPU.
+ * Nevertheless, cfs.utilization_load_avg can be higher than SCHED_LOAD_SCALE
+ * because of unfortunate rounding in avg_period and running_load_avg or just
+ * after migrating tasks until the average stabilizes with the new running
+ * time. So we need to check that the usage stays into the range
+ * [0..cpu_capacity_orig] and cap if necessary.
+ * Without capping the usage, a group could be seen as overloaded (CPU0 usage
+ * at 121% + CPU1 usage at 80%) whereas CPU1 has 20% of available capacity/
+ */
+int get_cpu_usage(int cpu)
+{
+	unsigned long usage = cpu_rq(cpu)->cfs.utilization_load_avg;
+	unsigned long capacity = capacity_orig_of(cpu);
+
+	if (usage >= SCHED_LOAD_SCALE)
+		return capacity;
+
+	return (usage * capacity) >> SCHED_LOAD_SHIFT;
+}
 
 /*
  * select_task_rq_fair: Select target runqueue for the waking task in domains
@@ -5170,7 +5500,7 @@ static bool migrate_improves_locality(struct task_struct *p, struct lb_env *env)
 	struct numa_group *numa_group = rcu_dereference(p->numa_group);
 	int src_nid, dst_nid;
 
-	if (!sched_feat(NUMA_FAVOUR_HIGHER) || !p->numa_faults_memory ||
+	if (!sched_feat(NUMA_FAVOUR_HIGHER) || !p->numa_faults ||
 	    !(env->sd->flags & SD_NUMA)) {
 		return false;
 	}
@@ -5209,7 +5539,7 @@ static bool migrate_degrades_locality(struct task_struct *p, struct lb_env *env)
 	if (!sched_feat(NUMA) || !sched_feat(NUMA_RESIST_LOWER))
 		return false;
 
-	if (!p->numa_faults_memory || !(env->sd->flags & SD_NUMA))
+	if (!p->numa_faults || !(env->sd->flags & SD_NUMA))
 		return false;
 
 	src_nid = cpu_to_node(env->src_cpu);
@@ -5635,12 +5965,12 @@ struct sg_lb_stats {
 	unsigned long sum_weighted_load; /* Weighted load of group's tasks */
 	unsigned long load_per_task;
 	unsigned long group_capacity;
+	unsigned long group_usage; /* Total usage of the group */
 	unsigned int sum_nr_running; /* Nr tasks running in the group */
-	unsigned int group_capacity_factor;
 	unsigned int idle_cpus;
 	unsigned int group_weight;
 	enum group_type group_type;
-	int group_has_free_capacity;
+	int group_no_capacity;
 #ifdef CONFIG_NUMA_BALANCING
 	unsigned int nr_numa_running;
 	unsigned int nr_preferred_running;
@@ -5734,10 +6064,20 @@ unsigned long __weak arch_scale_cpu_capacity(struct sched_domain *sd, int cpu)
 	return default_scale_cpu_capacity(sd, cpu);
 }
 
+void __weak arch_eval_cpu_freq(struct cpumask *cpus)
+{
+	return;
+}
+
+void __weak arch_scale_cpu_freq(void)
+{
+	return;
+}
+
 static unsigned long scale_rt_capacity(int cpu)
 {
 	struct rq *rq = cpu_rq(cpu);
-	u64 total, available, age_stamp, avg;
+	u64 total, used, age_stamp, avg;
 	s64 delta;
 
 	/*
@@ -5753,19 +6093,12 @@ static unsigned long scale_rt_capacity(int cpu)
 
 	total = sched_avg_period() + delta;
 
-	if (unlikely(total < avg)) {
-		/* Ensures that capacity won't end up being negative */
-		available = 0;
-	} else {
-		available = total - avg;
-	}
-
-	if (unlikely((s64)total < SCHED_CAPACITY_SCALE))
-		total = SCHED_CAPACITY_SCALE;
+	used = div_u64(avg, total);
 
-	total >>= SCHED_CAPACITY_SHIFT;
+	if (likely(used < SCHED_CAPACITY_SCALE))
+		return SCHED_CAPACITY_SCALE - used;
 
-	return div_u64(available, total);
+	return 1;
 }
 
 static void update_cpu_capacity(struct sched_domain *sd, int cpu)
@@ -5780,14 +6113,7 @@ static void update_cpu_capacity(struct sched_domain *sd, int cpu)
 
 	capacity >>= SCHED_CAPACITY_SHIFT;
 
-	sdg->sgc->capacity_orig = capacity;
-
-	if (sched_feat(ARCH_CAPACITY))
-		capacity *= arch_scale_freq_capacity(sd, cpu);
-	else
-		capacity *= default_scale_capacity(sd, cpu);
-
-	capacity >>= SCHED_CAPACITY_SHIFT;
+	cpu_rq(cpu)->cpu_capacity_orig = capacity;
 
 	capacity *= scale_rt_capacity(cpu);
 	capacity >>= SCHED_CAPACITY_SHIFT;
@@ -5803,7 +6129,7 @@ void update_group_capacity(struct sched_domain *sd, int cpu)
 {
 	struct sched_domain *child = sd->child;
 	struct sched_group *group, *sdg = sd->groups;
-	unsigned long capacity, capacity_orig;
+	unsigned long capacity;
 	unsigned long interval;
 
 	interval = msecs_to_jiffies(sd->balance_interval);
@@ -5815,7 +6141,7 @@ void update_group_capacity(struct sched_domain *sd, int cpu)
 		return;
 	}
 
-	capacity_orig = capacity = 0;
+	capacity = 0;
 
 	if (child->flags & SD_OVERLAP) {
 		/*
@@ -5835,19 +6161,15 @@ void update_group_capacity(struct sched_domain *sd, int cpu)
 			 * Use capacity_of(), which is set irrespective of domains
 			 * in update_cpu_capacity().
 			 *
-			 * This avoids capacity/capacity_orig from being 0 and
+			 * This avoids capacity from being 0 and
 			 * causing divide-by-zero issues on boot.
-			 *
-			 * Runtime updates will correct capacity_orig.
 			 */
 			if (unlikely(!rq->sd)) {
-				capacity_orig += capacity_of(cpu);
 				capacity += capacity_of(cpu);
 				continue;
 			}
 
 			sgc = rq->sd->groups->sgc;
-			capacity_orig += sgc->capacity_orig;
 			capacity += sgc->capacity;
 		}
 	} else  {
@@ -5858,39 +6180,24 @@ void update_group_capacity(struct sched_domain *sd, int cpu)
 
 		group = child->groups;
 		do {
-			capacity_orig += group->sgc->capacity_orig;
 			capacity += group->sgc->capacity;
 			group = group->next;
 		} while (group != child->groups);
 	}
 
-	sdg->sgc->capacity_orig = capacity_orig;
 	sdg->sgc->capacity = capacity;
 }
 
 /*
- * Try and fix up capacity for tiny siblings, this is needed when
- * things like SD_ASYM_PACKING need f_b_g to select another sibling
- * which on its own isn't powerful enough.
- *
- * See update_sd_pick_busiest() and check_asym_packing().
+ * Check whether the capacity of the rq has been noticeably reduced by side
+ * activity. The imbalance_pct is used for the threshold.
+ * Return true is the capacity is reduced
  */
 static inline int
-fix_small_capacity(struct sched_domain *sd, struct sched_group *group)
+check_cpu_capacity(struct rq *rq, struct sched_domain *sd)
 {
-	/*
-	 * Only siblings can have significantly less than SCHED_CAPACITY_SCALE
-	 */
-	if (!(sd->flags & SD_SHARE_CPUCAPACITY))
-		return 0;
-
-	/*
-	 * If ~90% of the cpu_capacity is still there, we're good.
-	 */
-	if (group->sgc->capacity * 32 > group->sgc->capacity_orig * 29)
-		return 1;
-
-	return 0;
+	return ((rq->cpu_capacity * sd->imbalance_pct) <
+				(rq->cpu_capacity_orig * 100));
 }
 
 /*
@@ -5928,37 +6235,54 @@ static inline int sg_imbalanced(struct sched_group *group)
 }
 
 /*
- * Compute the group capacity factor.
- *
- * Avoid the issue where N*frac(smt_capacity) >= 1 creates 'phantom' cores by
- * first dividing out the smt factor and computing the actual number of cores
- * and limit unit capacity with that.
+ * group_has_capacity returns true if the group has spare capacity that could
+ * be used by some tasks. We consider that a group has spare capacity if the
+ * number of task is smaller than the number of CPUs or if the usage is lower
+ * than the available capacity for CFS tasks. For the latter, we use a
+ * threshold to stabilize the state, to take into account the variance of the
+ * tasks' load and to return true if the available capacity in meaningful for
+ * the load balancer. As an example, an available capacity of 1% can appear
+ * but it doesn't make any benefit for the load balance.
  */
-static inline int sg_capacity_factor(struct lb_env *env, struct sched_group *group)
+static inline bool
+group_has_capacity(struct lb_env *env, struct sg_lb_stats *sgs)
 {
-	unsigned int capacity_factor, smt, cpus;
-	unsigned int capacity, capacity_orig;
+	if ((sgs->group_capacity * 100) >
+			(sgs->group_usage * env->sd->imbalance_pct))
+		return true;
 
-	capacity = group->sgc->capacity;
-	capacity_orig = group->sgc->capacity_orig;
-	cpus = group->group_weight;
+	if (sgs->sum_nr_running < sgs->group_weight)
+		return true;
 
-	/* smt := ceil(cpus / capacity), assumes: 1 < smt_capacity < 2 */
-	smt = DIV_ROUND_UP(SCHED_CAPACITY_SCALE * cpus, capacity_orig);
-	capacity_factor = cpus / smt; /* cores */
+	return false;
+}
+
+/*
+ *  group_is_overloaded returns true if the group has more tasks than it can
+ *  handle. We consider that a group is overloaded if the number of tasks is
+ *  greater than the number of CPUs and the tasks already use all available
+ *  capacity for CFS tasks. For the latter, we use a threshold to stabilize
+ *  the state, to take into account the variance of tasks' load and to return
+ *  true if available capacity is no more meaningful for load balancer
+ */
+static inline bool
+group_is_overloaded(struct lb_env *env, struct sg_lb_stats *sgs)
+{
+	if (sgs->sum_nr_running <= sgs->group_weight)
+		return false;
 
-	capacity_factor = min_t(unsigned,
-		capacity_factor, DIV_ROUND_CLOSEST(capacity, SCHED_CAPACITY_SCALE));
-	if (!capacity_factor)
-		capacity_factor = fix_small_capacity(env->sd, group);
+	if ((sgs->group_capacity * 100) <
+			(sgs->group_usage * env->sd->imbalance_pct))
+		return true;
 
-	return capacity_factor;
+	return false;
 }
 
-static enum group_type
-group_classify(struct sched_group *group, struct sg_lb_stats *sgs)
+static enum group_type group_classify(struct lb_env *env,
+		struct sched_group *group,
+		struct sg_lb_stats *sgs)
 {
-	if (sgs->sum_nr_running > sgs->group_capacity_factor)
+	if (sgs->group_no_capacity)
 		return group_overloaded;
 
 	if (sg_imbalanced(group))
@@ -5996,6 +6320,7 @@ static inline void update_sg_lb_stats(struct lb_env *env,
 			load = source_load(i, load_idx);
 
 		sgs->group_load += load;
+		sgs->group_usage += get_cpu_usage(i);
 		sgs->sum_nr_running += rq->cfs.h_nr_running;
 
 		if (rq->nr_running > 1)
@@ -6018,11 +6343,9 @@ static inline void update_sg_lb_stats(struct lb_env *env,
 		sgs->load_per_task = sgs->sum_weighted_load / sgs->sum_nr_running;
 
 	sgs->group_weight = group->group_weight;
-	sgs->group_capacity_factor = sg_capacity_factor(env, group);
-	sgs->group_type = group_classify(group, sgs);
 
-	if (sgs->group_capacity_factor > sgs->sum_nr_running)
-		sgs->group_has_free_capacity = 1;
+	sgs->group_no_capacity = group_is_overloaded(env, sgs);
+	sgs->group_type = group_classify(env, group, sgs);
 }
 
 /**
@@ -6144,17 +6467,20 @@ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sd
 
 		/*
 		 * In case the child domain prefers tasks go to siblings
-		 * first, lower the sg capacity factor to one so that we'll try
+		 * first, lower the sg capacity so that we'll try
 		 * and move all the excess tasks away. We lower the capacity
 		 * of a group only if the local group has the capacity to fit
-		 * these excess tasks, i.e. nr_running < group_capacity_factor. The
-		 * extra check prevents the case where you always pull from the
-		 * heaviest group when it is already under-utilized (possible
-		 * with a large weight task outweighs the tasks on the system).
+		 * these excess tasks. The extra check prevents the case where
+		 * you always pull from the heaviest group when it is already
+		 * under-utilized (possible with a large weight task outweighs
+		 * the tasks on the system).
 		 */
 		if (prefer_sibling && sds->local &&
-		    sds->local_stat.group_has_free_capacity)
-			sgs->group_capacity_factor = min(sgs->group_capacity_factor, 1U);
+		    group_has_capacity(env, &sds->local_stat) &&
+		    (sgs->sum_nr_running > 1)) {
+			sgs->group_no_capacity = 1;
+			sgs->group_type = group_overloaded;
+		}
 
 		if (update_sd_pick_busiest(env, sds, sg, sgs)) {
 			sds->busiest = sg;
@@ -6333,11 +6659,12 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s
 	 */
 	if (busiest->group_type == group_overloaded &&
 	    local->group_type   == group_overloaded) {
-		load_above_capacity =
-			(busiest->sum_nr_running - busiest->group_capacity_factor);
-
-		load_above_capacity *= (SCHED_LOAD_SCALE * SCHED_CAPACITY_SCALE);
-		load_above_capacity /= busiest->group_capacity;
+		load_above_capacity = busiest->sum_nr_running *
+					SCHED_LOAD_SCALE;
+		if (load_above_capacity > busiest->group_capacity)
+			load_above_capacity -= busiest->group_capacity;
+		else
+			load_above_capacity = ~0UL;
 	}
 
 	/*
@@ -6400,6 +6727,7 @@ static struct sched_group *find_busiest_group(struct lb_env *env)
 	local = &sds.local_stat;
 	busiest = &sds.busiest_stat;
 
+	/* ASYM feature bypasses nice load balance check */
 	if ((env->idle == CPU_IDLE || env->idle == CPU_NEWLY_IDLE) &&
 	    check_asym_packing(env, &sds))
 		return sds.busiest;
@@ -6420,8 +6748,8 @@ static struct sched_group *find_busiest_group(struct lb_env *env)
 		goto force_balance;
 
 	/* SD_BALANCE_NEWIDLE trumps SMP nice when underutilized */
-	if (env->idle == CPU_NEWLY_IDLE && local->group_has_free_capacity &&
-	    !busiest->group_has_free_capacity)
+	if (env->idle == CPU_NEWLY_IDLE && group_has_capacity(env, local) &&
+	    busiest->group_no_capacity)
 		goto force_balance;
 
 	/*
@@ -6480,7 +6808,7 @@ static struct rq *find_busiest_queue(struct lb_env *env,
 	int i;
 
 	for_each_cpu_and(i, sched_group_cpus(group), env->cpus) {
-		unsigned long capacity, capacity_factor, wl;
+		unsigned long capacity, wl;
 		enum fbq_type rt;
 
 		rq = cpu_rq(i);
@@ -6509,9 +6837,6 @@ static struct rq *find_busiest_queue(struct lb_env *env,
 			continue;
 
 		capacity = capacity_of(i);
-		capacity_factor = DIV_ROUND_CLOSEST(capacity, SCHED_CAPACITY_SCALE);
-		if (!capacity_factor)
-			capacity_factor = fix_small_capacity(env->sd, group);
 
 		wl = weighted_cpuload(i);
 
@@ -6519,7 +6844,9 @@ static struct rq *find_busiest_queue(struct lb_env *env,
 		 * When comparing with imbalance, use weighted_cpuload()
 		 * which is not scaled with the cpu capacity.
 		 */
-		if (capacity_factor && rq->nr_running == 1 && wl > env->imbalance)
+
+		if (rq->nr_running == 1 && wl > env->imbalance &&
+		    !check_cpu_capacity(rq, env->sd))
 			continue;
 
 		/*
@@ -6567,6 +6894,28 @@ static int need_active_balance(struct lb_env *env)
 			return 1;
 	}
 
+	/*
+	 * The dst_cpu is idle and the src_cpu CPU has only 1 CFS task.
+	 * It's worth migrating the task if the src_cpu's capacity is reduced
+	 * because of other sched_class or IRQs whereas capacity stays
+	 * available on dst_cpu.
+	 */
+	if ((env->idle != CPU_NOT_IDLE) &&
+			(env->src_rq->cfs.h_nr_running == 1)) {
+		unsigned long src_eff_capacity, dst_eff_capacity;
+
+		dst_eff_capacity = 100;
+		dst_eff_capacity *= capacity_of(env->dst_cpu);
+		dst_eff_capacity *= capacity_orig_of(env->src_cpu);
+
+		src_eff_capacity = sd->imbalance_pct;
+		src_eff_capacity *= capacity_of(env->src_cpu);
+		src_eff_capacity *= capacity_orig_of(env->dst_cpu);
+
+		if (src_eff_capacity < dst_eff_capacity)
+			return 1;
+	}
+
 	return unlikely(sd->nr_balance_failed > sd->cache_nice_tries+2);
 }
 
@@ -6666,6 +7015,9 @@ redo:
 
 	schedstat_add(sd, lb_imbalance[idle], env.imbalance);
 
+	env.src_cpu = busiest->cpu;
+	env.src_rq = busiest;
+
 	ld_moved = 0;
 	if (busiest->nr_running > 1) {
 		/*
@@ -6675,8 +7027,6 @@ redo:
 		 * correctly treated as an imbalance.
 		 */
 		env.flags |= LBF_ALL_PINNED;
-		env.src_cpu   = busiest->cpu;
-		env.src_rq    = busiest;
 		env.loop_max  = min(sysctl_sched_nr_migrate, busiest->nr_running);
 
 more_balance:
@@ -7376,22 +7726,25 @@ end:
 
 /*
  * Current heuristic for kicking the idle load balancer in the presence
- * of an idle cpu is the system.
+ * of an idle cpu in the system.
  *   - This rq has more than one task.
- *   - At any scheduler domain level, this cpu's scheduler group has multiple
- *     busy cpu's exceeding the group's capacity.
+ *   - This rq has at least one CFS task and the capacity of the CPU is
+ *     significantly reduced because of RT tasks or IRQs.
+ *   - At parent of LLC scheduler domain level, this cpu's scheduler group has
+ *     multiple busy cpu.
  *   - For SD_ASYM_PACKING, if the lower numbered cpu's in the scheduler
  *     domain span are idle.
  */
-static inline int nohz_kick_needed(struct rq *rq)
+static inline bool nohz_kick_needed(struct rq *rq)
 {
 	unsigned long now = jiffies;
 	struct sched_domain *sd;
 	struct sched_group_capacity *sgc;
 	int nr_busy, cpu = rq->cpu;
+	bool kick = false;
 
 	if (unlikely(rq->idle_balance))
-		return 0;
+		return false;
 
        /*
 	* We may be recently in ticked or tickless idle mode. At the first
@@ -7405,38 +7758,44 @@ static inline int nohz_kick_needed(struct rq *rq)
 	 * balancing.
 	 */
 	if (likely(!atomic_read(&nohz.nr_cpus)))
-		return 0;
+		return false;
 
 	if (time_before(now, nohz.next_balance))
-		return 0;
+		return false;
 
 	if (rq->nr_running >= 2)
-		goto need_kick;
+		return true;
 
 	rcu_read_lock();
 	sd = rcu_dereference(per_cpu(sd_busy, cpu));
-
 	if (sd) {
 		sgc = sd->groups->sgc;
 		nr_busy = atomic_read(&sgc->nr_busy_cpus);
 
-		if (nr_busy > 1)
-			goto need_kick_unlock;
+		if (nr_busy > 1) {
+			kick = true;
+			goto unlock;
+		}
+
 	}
 
-	sd = rcu_dereference(per_cpu(sd_asym, cpu));
+	sd = rcu_dereference(rq->sd);
+	if (sd) {
+		if ((rq->cfs.h_nr_running >= 1) &&
+				check_cpu_capacity(rq, sd)) {
+			kick = true;
+			goto unlock;
+		}
+	}
 
+	sd = rcu_dereference(per_cpu(sd_asym, cpu));
 	if (sd && (cpumask_first_and(nohz.idle_cpus_mask,
 				  sched_domain_span(sd)) < cpu))
-		goto need_kick_unlock;
+		kick = true;
 
+unlock:
 	rcu_read_unlock();
-	return 0;
-
-need_kick_unlock:
-	rcu_read_unlock();
-need_kick:
-	return 1;
+	return kick;
 }
 #else
 static void nohz_idle_balance(struct rq *this_rq, enum cpu_idle_type idle) { }
@@ -7460,6 +7819,9 @@ static void run_rebalance_domains(struct softirq_action *h)
 	 * stopped.
 	 */
 	nohz_idle_balance(this_rq, idle);
+
+	if (energy_aware())
+		arch_scale_cpu_freq();
 }
 
 /*
diff --git a/kernel/sched/features.h b/kernel/sched/features.h
index 90284d117fe6..199ee3a62fbc 100644
--- a/kernel/sched/features.h
+++ b/kernel/sched/features.h
@@ -83,3 +83,9 @@ SCHED_FEAT(NUMA_FAVOUR_HIGHER, true)
  */
 SCHED_FEAT(NUMA_RESIST_LOWER, false)
 #endif
+
+/*
+ * Energy aware scheduling. Use platform energy model to guide scheduling
+ * decisions optimizing for energy efficiency.
+ */
+SCHED_FEAT(ENERGY_AWARE, false)
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index d024e6ce30ba..3d14312db7ea 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -1351,16 +1351,22 @@ out:
 
 static void check_preempt_equal_prio(struct rq *rq, struct task_struct *p)
 {
-	if (rq->curr->nr_cpus_allowed == 1)
+	/*
+	 * Current can't be migrated, useless to reschedule,
+	 * let's hope p can move out.
+	 */
+	if (rq->curr->nr_cpus_allowed == 1 ||
+	    !cpupri_find(&rq->rd->cpupri, rq->curr, NULL))
 		return;
 
+	/*
+	 * p is migratable, so let's not schedule it and
+	 * see if it is pushed or pulled somewhere else.
+	 */
 	if (p->nr_cpus_allowed != 1
 	    && cpupri_find(&rq->rd->cpupri, p, NULL))
 		return;
 
-	if (!cpupri_find(&rq->rd->cpupri, rq->curr, NULL))
-		return;
-
 	/*
 	 * There appears to be other cpus that can accept
 	 * current and none to run 'p', so lets reschedule
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 24156c8434d1..770c18cd6bee 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -176,6 +176,25 @@ struct dl_bw {
 	u64 bw, total_bw;
 };
 
+static inline
+void __dl_clear(struct dl_bw *dl_b, u64 tsk_bw)
+{
+	dl_b->total_bw -= tsk_bw;
+}
+
+static inline
+void __dl_add(struct dl_bw *dl_b, u64 tsk_bw)
+{
+	dl_b->total_bw += tsk_bw;
+}
+
+static inline
+bool __dl_overflow(struct dl_bw *dl_b, int cpus, u64 old_bw, u64 new_bw)
+{
+	return dl_b->bw != -1 &&
+	       dl_b->bw * cpus < dl_b->total_bw - old_bw + new_bw;
+}
+
 extern struct mutex sched_domains_mutex;
 
 #ifdef CONFIG_CGROUP_SCHED
@@ -313,6 +332,9 @@ struct cfs_bandwidth { };
 
 #endif	/* CONFIG_CGROUP_SCHED */
 
+extern unsigned long capacity_of(int cpu);
+extern int get_cpu_usage(int cpu);
+
 /* CFS-related fields in a runqueue */
 struct cfs_rq {
 	struct load_weight load;
@@ -343,8 +365,14 @@ struct cfs_rq {
 	 * Under CFS, load is tracked on a per-entity basis and aggregated up.
 	 * This allows for the description of both thread and group usage (in
 	 * the FAIR_GROUP_SCHED case).
+	 * runnable_load_avg is the sum of the load_avg_contrib of the
+	 * sched_entities on the rq.
+	 * blocked_load_avg is similar to runnable_load_avg except that its
+	 * the blocked sched_entities on the rq.
+	 * utilization_load_avg is the sum of the average running time of the
+	 * sched_entities on the rq.
 	 */
-	unsigned long runnable_load_avg, blocked_load_avg;
+	unsigned long runnable_load_avg, blocked_load_avg, utilization_load_avg;
 	atomic64_t decay_counter;
 	u64 last_decay;
 	atomic_long_t removed_load;
@@ -579,6 +607,7 @@ struct rq {
 	struct sched_domain *sd;
 
 	unsigned long cpu_capacity;
+	unsigned long cpu_capacity_orig;
 
 	unsigned char idle_balance;
 	/* For active balancing */
@@ -678,7 +707,25 @@ static inline u64 rq_clock_task(struct rq *rq)
 	return rq->clock_task;
 }
 
+#ifdef CONFIG_NUMA
+enum numa_topology_type {
+	NUMA_DIRECT,
+	NUMA_GLUELESS_MESH,
+	NUMA_BACKPLANE,
+};
+extern enum numa_topology_type sched_numa_topology_type;
+extern int sched_max_numa_distance;
+extern bool find_numa_distance(int distance);
+#endif
+
 #ifdef CONFIG_NUMA_BALANCING
+/* The regions in numa_faults array from task_struct */
+enum numa_faults_stats {
+	NUMA_MEM = 0,
+	NUMA_CPU,
+	NUMA_MEMBUF,
+	NUMA_CPUBUF
+};
 extern void sched_setnuma(struct task_struct *p, int node);
 extern int migrate_task_to(struct task_struct *p, int cpu);
 extern int migrate_swap(struct task_struct *, struct task_struct *);
@@ -752,7 +799,7 @@ struct sched_group_capacity {
 	 * CPU capacity of this group, SCHED_LOAD_SCALE being max capacity
 	 * for a single CPU.
 	 */
-	unsigned int capacity, capacity_orig;
+	unsigned int capacity;
 	unsigned long next_update;
 	int imbalance; /* XXX unrelated to capacity but shared group state */
 	/*
@@ -1127,6 +1174,11 @@ struct sched_class {
 	void (*task_fork) (struct task_struct *p);
 	void (*task_dead) (struct task_struct *p);
 
+	/*
+	 * The switched_from() call is allowed to drop rq->lock, therefore we
+	 * cannot assume the switched_from/switched_to pair is serliazed by
+	 * rq->lock. They are however serialized by p->pi_lock.
+	 */
 	void (*switched_from) (struct rq *this_rq, struct task_struct *task);
 	void (*switched_to) (struct rq *this_rq, struct task_struct *task);
 	void (*prio_changed) (struct rq *this_rq, struct task_struct *task,
@@ -1306,9 +1358,11 @@ static inline int hrtick_enabled(struct rq *rq)
 
 #ifdef CONFIG_SMP
 extern void sched_avg_update(struct rq *rq);
+extern unsigned long arch_scale_freq_capacity(struct sched_domain *sd, int cpu);
+
 static inline void sched_rt_avg_update(struct rq *rq, u64 rt_delta)
 {
-	rq->rt_avg += rt_delta;
+	rq->rt_avg += rt_delta * arch_scale_freq_capacity(NULL, cpu_of(rq));
 	sched_avg_update(rq);
 }
 #else
@@ -1502,6 +1556,7 @@ extern struct sched_entity *__pick_first_entity(struct cfs_rq *cfs_rq);
 extern struct sched_entity *__pick_last_entity(struct cfs_rq *cfs_rq);
 extern void print_cfs_stats(struct seq_file *m, int cpu);
 extern void print_rt_stats(struct seq_file *m, int cpu);
+extern void print_dl_stats(struct seq_file *m, int cpu);
 
 extern void init_cfs_rq(struct cfs_rq *cfs_rq);
 extern void init_rt_rq(struct rt_rq *rt_rq, struct rq *rq);
diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c
index 5a62915f47a8..852143a79f36 100644
--- a/kernel/sched/wait.c
+++ b/kernel/sched/wait.c
@@ -9,6 +9,7 @@
 #include <linux/mm.h>
 #include <linux/wait.h>
 #include <linux/hash.h>
+#include <linux/kthread.h>
 
 void __init_waitqueue_head(wait_queue_head_t *q, const char *name, struct lock_class_key *key)
 {
@@ -297,6 +298,71 @@ int autoremove_wake_function(wait_queue_t *wait, unsigned mode, int sync, void *
 }
 EXPORT_SYMBOL(autoremove_wake_function);
 
+static inline bool is_kthread_should_stop(void)
+{
+	return (current->flags & PF_KTHREAD) && kthread_should_stop();
+}
+
+/*
+ * DEFINE_WAIT_FUNC(wait, woken_wake_func);
+ *
+ * add_wait_queue(&wq, &wait);
+ * for (;;) {
+ *     if (condition)
+ *         break;
+ *
+ *     p->state = mode;				condition = true;
+ *     smp_mb(); // A				smp_wmb(); // C
+ *     if (!wait->flags & WQ_FLAG_WOKEN)	wait->flags |= WQ_FLAG_WOKEN;
+ *         schedule()				try_to_wake_up();
+ *     p->state = TASK_RUNNING;		    ~~~~~~~~~~~~~~~~~~
+ *     wait->flags &= ~WQ_FLAG_WOKEN;		condition = true;
+ *     smp_mb() // B				smp_wmb(); // C
+ *						wait->flags |= WQ_FLAG_WOKEN;
+ * }
+ * remove_wait_queue(&wq, &wait);
+ *
+ */
+long wait_woken(wait_queue_t *wait, unsigned mode, long timeout)
+{
+	set_current_state(mode); /* A */
+	/*
+	 * The above implies an smp_mb(), which matches with the smp_wmb() from
+	 * woken_wake_function() such that if we observe WQ_FLAG_WOKEN we must
+	 * also observe all state before the wakeup.
+	 */
+	if (!(wait->flags & WQ_FLAG_WOKEN) && !is_kthread_should_stop())
+		timeout = schedule_timeout(timeout);
+	__set_current_state(TASK_RUNNING);
+
+	/*
+	 * The below implies an smp_mb(), it too pairs with the smp_wmb() from
+	 * woken_wake_function() such that we must either observe the wait
+	 * condition being true _OR_ WQ_FLAG_WOKEN such that we will not miss
+	 * an event.
+	 */
+	set_mb(wait->flags, wait->flags & ~WQ_FLAG_WOKEN); /* B */
+
+	return timeout;
+}
+EXPORT_SYMBOL(wait_woken);
+
+int woken_wake_function(wait_queue_t *wait, unsigned mode, int sync, void *key)
+{
+	/*
+	 * Although this function is called under waitqueue lock, LOCK
+	 * doesn't imply write barrier and the users expects write
+	 * barrier semantics on wakeup functions.  The following
+	 * smp_wmb() is equivalent to smp_wmb() in try_to_wake_up()
+	 * and is paired with set_mb() in wait_woken().
+	 */
+	smp_wmb(); /* C */
+	wait->flags |= WQ_FLAG_WOKEN;
+
+	return default_wake_function(wait, mode, sync, key);
+}
+EXPORT_SYMBOL(woken_wake_function);
+
 int wake_bit_function(wait_queue_t *wait, unsigned mode, int sync, void *arg)
 {
 	struct wait_bit_key *key = arg;
diff --git a/kernel/smpboot.c b/kernel/smpboot.c
index eb89e1807408..f032fb5284e3 100644
--- a/kernel/smpboot.c
+++ b/kernel/smpboot.c
@@ -110,7 +110,7 @@ static int smpboot_thread_fn(void *data)
 		set_current_state(TASK_INTERRUPTIBLE);
 		preempt_disable();
 		if (kthread_should_stop()) {
-			set_current_state(TASK_RUNNING);
+			__set_current_state(TASK_RUNNING);
 			preempt_enable();
 			if (ht->cleanup)
 				ht->cleanup(td->cpu, cpu_online(td->cpu));
@@ -136,26 +136,27 @@ static int smpboot_thread_fn(void *data)
 		/* Check for state change setup */
 		switch (td->status) {
 		case HP_THREAD_NONE:
+			__set_current_state(TASK_RUNNING);
 			preempt_enable();
 			if (ht->setup)
 				ht->setup(td->cpu);
 			td->status = HP_THREAD_ACTIVE;
-			preempt_disable();
-			break;
+			continue;
+
 		case HP_THREAD_PARKED:
+			__set_current_state(TASK_RUNNING);
 			preempt_enable();
 			if (ht->unpark)
 				ht->unpark(td->cpu);
 			td->status = HP_THREAD_ACTIVE;
-			preempt_disable();
-			break;
+			continue;
 		}
 
 		if (!ht->thread_should_run(td->cpu)) {
-			preempt_enable();
+			preempt_enable_no_resched();
 			schedule();
 		} else {
-			set_current_state(TASK_RUNNING);
+			__set_current_state(TASK_RUNNING);
 			preempt_enable();
 			ht->thread_fn(td->cpu);
 		}
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index f33527ba62ca..947663d2935a 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -398,7 +398,8 @@ static struct ctl_table kern_table[] = {
 		.data		= &sysctl_numa_balancing_scan_size,
 		.maxlen		= sizeof(unsigned int),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &one,
 	},
 	{
 		.procname	= "numa_balancing",
diff --git a/net/bluetooth/rfcomm/core.c b/net/bluetooth/rfcomm/core.c
index af73bc3acb40..410dd5e76c41 100644
--- a/net/bluetooth/rfcomm/core.c
+++ b/net/bluetooth/rfcomm/core.c
@@ -101,11 +101,11 @@ static struct rfcomm_session *rfcomm_session_del(struct rfcomm_session *s);
 #define __get_rpn_stop_bits(line) (((line) >> 2) & 0x1)
 #define __get_rpn_parity(line)    (((line) >> 3) & 0x7)
 
+static DECLARE_WAIT_QUEUE_HEAD(rfcomm_wq);
+
 static void rfcomm_schedule(void)
 {
-	if (!rfcomm_thread)
-		return;
-	wake_up_process(rfcomm_thread);
+	wake_up_all(&rfcomm_wq);
 }
 
 /* ---- RFCOMM FCS computation ---- */
@@ -2086,24 +2086,22 @@ static void rfcomm_kill_listener(void)
 
 static int rfcomm_run(void *unused)
 {
+	DEFINE_WAIT_FUNC(wait, woken_wake_function);
 	BT_DBG("");
 
 	set_user_nice(current, -10);
 
 	rfcomm_add_listener(BDADDR_ANY);
 
-	while (1) {
-		set_current_state(TASK_INTERRUPTIBLE);
-
-		if (kthread_should_stop())
-			break;
+	add_wait_queue(&rfcomm_wq, &wait);
+	while (!kthread_should_stop()) {
 
 		/* Process stuff */
 		rfcomm_process_sessions();
 
-		schedule();
+		wait_woken(&wait, TASK_INTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT);
 	}
-	__set_current_state(TASK_RUNNING);
+	remove_wait_queue(&rfcomm_wq, &wait);
 
 	rfcomm_kill_listener();
 
diff --git a/net/core/dev.c b/net/core/dev.c
index b793e3521a36..c5a9d73147a6 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -7196,11 +7196,10 @@ static void __net_exit rtnl_lock_unregistering(struct list_head *net_list)
 	 */
 	struct net *net;
 	bool unregistering;
-	DEFINE_WAIT(wait);
+	DEFINE_WAIT_FUNC(wait, woken_wake_function);
 
+	add_wait_queue(&netdev_unregistering_wq, &wait);
 	for (;;) {
-		prepare_to_wait(&netdev_unregistering_wq, &wait,
-				TASK_UNINTERRUPTIBLE);
 		unregistering = false;
 		rtnl_lock();
 		list_for_each_entry(net, net_list, exit_list) {
@@ -7212,9 +7211,10 @@ static void __net_exit rtnl_lock_unregistering(struct list_head *net_list)
 		if (!unregistering)
 			break;
 		__rtnl_unlock();
-		schedule();
+
+		wait_woken(&wait, TASK_UNINTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT);
 	}
-	finish_wait(&netdev_unregistering_wq, &wait);
+	remove_wait_queue(&netdev_unregistering_wq, &wait);
 }
 
 static void __net_exit default_device_exit_batch(struct list_head *net_list)
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index a6882686ca3a..b095296f711f 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -365,11 +365,10 @@ static void rtnl_lock_unregistering_all(void)
 {
 	struct net *net;
 	bool unregistering;
-	DEFINE_WAIT(wait);
+	DEFINE_WAIT_FUNC(wait, woken_wake_function);
 
+	add_wait_queue(&netdev_unregistering_wq, &wait);
 	for (;;) {
-		prepare_to_wait(&netdev_unregistering_wq, &wait,
-				TASK_UNINTERRUPTIBLE);
 		unregistering = false;
 		rtnl_lock();
 		for_each_net(net) {
@@ -381,9 +380,10 @@ static void rtnl_lock_unregistering_all(void)
 		if (!unregistering)
 			break;
 		__rtnl_unlock();
-		schedule();
+
+		wait_woken(&wait, TASK_UNINTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT);
 	}
-	finish_wait(&netdev_unregistering_wq, &wait);
+	remove_wait_queue(&netdev_unregistering_wq, &wait);
 }
 
 /**