Merge branch 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (27 commits)
  sched: Use correct macro to display sched_child_runs_first in /proc/sched_debug
  sched: No need for bootmem special cases
  sched: Revert nohz_ratelimit() for now
  sched: Reduce update_group_power() calls
  sched: Update rq->clock for nohz balanced cpus
  sched: Fix spelling of sibling
  sched, cpuset: Drop __cpuexit from cpu hotplug callbacks
  sched: Fix the racy usage of thread_group_cputimer() in fastpath_timer_check()
  sched: run_posix_cpu_timers: Don't check ->exit_state, use lock_task_sighand()
  sched: thread_group_cputime: Simplify, document the "alive" check
  sched: Remove the obsolete exit_state/signal hacks
  sched: task_tick_rt: Remove the obsolete ->signal != NULL check
  sched: __sched_setscheduler: Read the RLIMIT_RTPRIO value lockless
  sched: Fix comments to make them DocBook happy
  sched: Fix fix_small_capacity
  powerpc: Exclude arch_sd_sibiling_asym_packing() on UP
  powerpc: Enable asymmetric SMT scheduling on POWER7
  sched: Add asymmetric group packing option for sibling domain
  sched: Fix capacity calculations for SMT4
  sched: Change nohz idle load balancing logic to push model
  ...

28 files changed, 877 insertions, 410 deletions

diff --git a/arch/parisc/kernel/ftrace.c b/arch/parisc/kernel/ftrace.c
index 9877372ffdb..5beb97bafbb 100644
--- a/arch/parisc/kernel/ftrace.c
+++ b/arch/parisc/kernel/ftrace.c
@@ -82,7 +82,7 @@ unsigned long ftrace_return_to_handler(unsigned long retval0,
 	unsigned long ret;
 
 	pop_return_trace(&trace, &ret);
-	trace.rettime = cpu_clock(raw_smp_processor_id());
+	trace.rettime = local_clock();
 	ftrace_graph_return(&trace);
 
 	if (unlikely(!ret)) {
@@ -126,7 +126,7 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr)
 		return;
 	}
 
-	calltime = cpu_clock(raw_smp_processor_id());
+	calltime = local_clock();
 
 	if (push_return_trace(old, calltime,
 				self_addr, &trace.depth) == -EBUSY) {
diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h
index 5e2e2cfcc81..3a40a992e59 100644
--- a/arch/powerpc/include/asm/cputable.h
+++ b/arch/powerpc/include/asm/cputable.h
@@ -197,6 +197,7 @@ extern const char *powerpc_base_platform;
 #define CPU_FTR_SAO			LONG_ASM_CONST(0x0020000000000000)
 #define CPU_FTR_CP_USE_DCBTZ		LONG_ASM_CONST(0x0040000000000000)
 #define CPU_FTR_UNALIGNED_LD_STD	LONG_ASM_CONST(0x0080000000000000)
+#define CPU_FTR_ASYM_SMT		LONG_ASM_CONST(0x0100000000000000)
 
 #ifndef __ASSEMBLY__
 
@@ -412,7 +413,7 @@ extern const char *powerpc_base_platform;
 	    CPU_FTR_MMCRA | CPU_FTR_SMT | \
 	    CPU_FTR_COHERENT_ICACHE | CPU_FTR_LOCKLESS_TLBIE | \
 	    CPU_FTR_PURR | CPU_FTR_SPURR | CPU_FTR_REAL_LE | \
-	    CPU_FTR_DSCR | CPU_FTR_SAO)
+	    CPU_FTR_DSCR | CPU_FTR_SAO  | CPU_FTR_ASYM_SMT)
 #define CPU_FTRS_CELL	(CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \
 	    CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \
 	    CPU_FTR_ALTIVEC_COMP | CPU_FTR_MMCRA | CPU_FTR_SMT | \
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 551f6713ff4..e78a5add7f1 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -1299,3 +1299,14 @@ unsigned long randomize_et_dyn(unsigned long base)
 
 	return ret;
 }
+
+#ifdef CONFIG_SMP
+int arch_sd_sibling_asym_packing(void)
+{
+	if (cpu_has_feature(CPU_FTR_ASYM_SMT)) {
+		printk_once(KERN_INFO "Enabling Asymmetric SMT scheduling\n");
+		return SD_ASYM_PACKING;
+	}
+	return 0;
+}
+#endif
diff --git a/include/linux/cpu.h b/include/linux/cpu.h
index e287863ac05..de6b1722cdc 100644
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -48,6 +48,31 @@ extern ssize_t arch_cpu_release(const char *, size_t);
 #endif
 struct notifier_block;
 
+/*
+ * CPU notifier priorities.
+ */
+enum {
+	/*
+	 * SCHED_ACTIVE marks a cpu which is coming up active during
+	 * CPU_ONLINE and CPU_DOWN_FAILED and must be the first
+	 * notifier.  CPUSET_ACTIVE adjusts cpuset according to
+	 * cpu_active mask right after SCHED_ACTIVE.  During
+	 * CPU_DOWN_PREPARE, SCHED_INACTIVE and CPUSET_INACTIVE are
+	 * ordered in the similar way.
+	 *
+	 * This ordering guarantees consistent cpu_active mask and
+	 * migration behavior to all cpu notifiers.
+	 */
+	CPU_PRI_SCHED_ACTIVE	= INT_MAX,
+	CPU_PRI_CPUSET_ACTIVE	= INT_MAX - 1,
+	CPU_PRI_SCHED_INACTIVE	= INT_MIN + 1,
+	CPU_PRI_CPUSET_INACTIVE	= INT_MIN,
+
+	/* migration should happen before other stuff but after perf */
+	CPU_PRI_PERF		= 20,
+	CPU_PRI_MIGRATION	= 10,
+};
+
 #ifdef CONFIG_SMP
 /* Need to know about CPUs going up/down? */
 #if defined(CONFIG_HOTPLUG_CPU) || !defined(MODULE)
diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h
index 457ed765a11..f20eb8f1602 100644
--- a/include/linux/cpuset.h
+++ b/include/linux/cpuset.h
@@ -20,6 +20,7 @@ extern int number_of_cpusets;	/* How many cpusets are defined in system? */
 
 extern int cpuset_init(void);
 extern void cpuset_init_smp(void);
+extern void cpuset_update_active_cpus(void);
 extern void cpuset_cpus_allowed(struct task_struct *p, struct cpumask *mask);
 extern int cpuset_cpus_allowed_fallback(struct task_struct *p);
 extern nodemask_t cpuset_mems_allowed(struct task_struct *p);
@@ -132,6 +133,11 @@ static inline void set_mems_allowed(nodemask_t nodemask)
 static inline int cpuset_init(void) { return 0; }
 static inline void cpuset_init_smp(void) {}
 
+static inline void cpuset_update_active_cpus(void)
+{
+	partition_sched_domains(1, NULL, NULL);
+}
+
 static inline void cpuset_cpus_allowed(struct task_struct *p,
 				       struct cpumask *mask)
 {
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 937495c2507..716f99b682c 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -1067,7 +1067,7 @@ static inline void perf_event_disable(struct perf_event *event)		{ }
 #define perf_cpu_notifier(fn)					\
 do {								\
 	static struct notifier_block fn##_nb __cpuinitdata =	\
-		{ .notifier_call = fn, .priority = 20 };	\
+		{ .notifier_call = fn, .priority = CPU_PRI_PERF }; \
 	fn(&fn##_nb, (unsigned long)CPU_UP_PREPARE,		\
 		(void *)(unsigned long)smp_processor_id());	\
 	fn(&fn##_nb, (unsigned long)CPU_STARTING,		\
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 3992f50de61..9591907c4f7 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -272,19 +272,10 @@ extern int runqueue_is_locked(int cpu);
 
 extern cpumask_var_t nohz_cpu_mask;
 #if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ)
-extern int select_nohz_load_balancer(int cpu);
-extern int get_nohz_load_balancer(void);
-extern int nohz_ratelimit(int cpu);
+extern void select_nohz_load_balancer(int stop_tick);
+extern int get_nohz_timer_target(void);
 #else
-static inline int select_nohz_load_balancer(int cpu)
-{
-	return 0;
-}
-
-static inline int nohz_ratelimit(int cpu)
-{
-	return 0;
-}
+static inline void select_nohz_load_balancer(int stop_tick) { }
 #endif
 
 /*
@@ -801,7 +792,7 @@ enum cpu_idle_type {
 #define SD_POWERSAVINGS_BALANCE	0x0100	/* Balance for power savings */
 #define SD_SHARE_PKG_RESOURCES	0x0200	/* Domain members share cpu pkg resources */
 #define SD_SERIALIZE		0x0400	/* Only a single load balancing instance */
-
+#define SD_ASYM_PACKING		0x0800  /* Place busy groups earlier in the domain */
 #define SD_PREFER_SIBLING	0x1000	/* Prefer to place tasks in a sibling domain */
 
 enum powersavings_balance_level {
@@ -836,6 +827,8 @@ static inline int sd_balance_for_package_power(void)
 	return SD_PREFER_SIBLING;
 }
 
+extern int __weak arch_sd_sibiling_asym_packing(void);
+
 /*
  * Optimise SD flags for power savings:
  * SD_BALANCE_NEWIDLE helps agressive task consolidation and power savings.
@@ -857,7 +850,7 @@ struct sched_group {
 	 * CPU power of this group, SCHED_LOAD_SCALE being max power for a
 	 * single CPU.
 	 */
-	unsigned int cpu_power;
+	unsigned int cpu_power, cpu_power_orig;
 
 	/*
 	 * The CPUs this group covers.
@@ -1693,6 +1686,7 @@ extern void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *
 #define PF_EXITING	0x00000004	/* getting shut down */
 #define PF_EXITPIDONE	0x00000008	/* pi exit done on shut down */
 #define PF_VCPU		0x00000010	/* I'm a virtual CPU */
+#define PF_WQ_WORKER	0x00000020	/* I'm a workqueue worker */
 #define PF_FORKNOEXEC	0x00000040	/* forked but didn't exec */
 #define PF_MCE_PROCESS  0x00000080      /* process policy on mce errors */
 #define PF_SUPERPRIV	0x00000100	/* used super-user privileges */
@@ -1787,20 +1781,23 @@ static inline int set_cpus_allowed(struct task_struct *p, cpumask_t new_mask)
 #endif
 
 /*
- * Architectures can set this to 1 if they have specified
- * CONFIG_HAVE_UNSTABLE_SCHED_CLOCK in their arch Kconfig,
- * but then during bootup it turns out that sched_clock()
- * is reliable after all:
+ * Do not use outside of architecture code which knows its limitations.
+ *
+ * sched_clock() has no promise of monotonicity or bounded drift between
+ * CPUs, use (which you should not) requires disabling IRQs.
+ *
+ * Please use one of the three interfaces below.
  */
-#ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
-extern int sched_clock_stable;
-#endif
-
-/* ftrace calls sched_clock() directly */
 extern unsigned long long notrace sched_clock(void);
+/*
+ * See the comment in kernel/sched_clock.c
+ */
+extern u64 cpu_clock(int cpu);
+extern u64 local_clock(void);
+extern u64 sched_clock_cpu(int cpu);
+
 
 extern void sched_clock_init(void);
-extern u64 sched_clock_cpu(int cpu);
 
 #ifndef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
 static inline void sched_clock_tick(void)
@@ -1815,17 +1812,19 @@ static inline void sched_clock_idle_wakeup_event(u64 delta_ns)
 {
 }
 #else
+/*
+ * Architectures can set this to 1 if they have specified
+ * CONFIG_HAVE_UNSTABLE_SCHED_CLOCK in their arch Kconfig,
+ * but then during bootup it turns out that sched_clock()
+ * is reliable after all:
+ */
+extern int sched_clock_stable;
+
 extern void sched_clock_tick(void);
 extern void sched_clock_idle_sleep_event(void);
 extern void sched_clock_idle_wakeup_event(u64 delta_ns);
 #endif
 
-/*
- * For kernel-internal use: high-speed (but slightly incorrect) per-cpu
- * clock constructed from sched_clock():
- */
-extern unsigned long long cpu_clock(int cpu);
-
 extern unsigned long long
 task_sched_runtime(struct task_struct *task);
 extern unsigned long long thread_group_sched_runtime(struct task_struct *task);
diff --git a/include/linux/topology.h b/include/linux/topology.h
index c44df50a05a..b572e432d2f 100644
--- a/include/linux/topology.h
+++ b/include/linux/topology.h
@@ -103,6 +103,7 @@ int arch_update_cpu_topology(void);
 				| 1*SD_SHARE_PKG_RESOURCES		\
 				| 0*SD_SERIALIZE			\
 				| 0*SD_PREFER_SIBLING			\
+				| arch_sd_sibling_asym_packing()	\
 				,					\
 	.last_balance		= jiffies,				\
 	.balance_interval	= 1,					\
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 97d1b426a4a..f6e726f1849 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -235,11 +235,8 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen)
 		return -EINVAL;
 
 	cpu_hotplug_begin();
-	set_cpu_active(cpu, false);
 	err = __cpu_notify(CPU_DOWN_PREPARE | mod, hcpu, -1, &nr_calls);
 	if (err) {
-		set_cpu_active(cpu, true);
-
 		nr_calls--;
 		__cpu_notify(CPU_DOWN_FAILED | mod, hcpu, nr_calls, NULL);
 		printk("%s: attempt to take down CPU %u failed\n",
@@ -249,7 +246,6 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen)
 
 	err = __stop_machine(take_cpu_down, &tcd_param, cpumask_of(cpu));
 	if (err) {
-		set_cpu_active(cpu, true);
 		/* CPU didn't die: tell everyone.  Can't complain. */
 		cpu_notify_nofail(CPU_DOWN_FAILED | mod, hcpu);
 
@@ -321,8 +317,6 @@ static int __cpuinit _cpu_up(unsigned int cpu, int tasks_frozen)
 		goto out_notify;
 	BUG_ON(!cpu_online(cpu));
 
-	set_cpu_active(cpu, true);
-
 	/* Now call notifier in preparation. */
 	cpu_notify(CPU_ONLINE | mod, hcpu);
 
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 7cb37d86a00..b23c0979bbe 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -2113,31 +2113,17 @@ static void scan_for_empty_cpusets(struct cpuset *root)
  * but making no active use of cpusets.
  *
  * This routine ensures that top_cpuset.cpus_allowed tracks
- * cpu_online_map on each CPU hotplug (cpuhp) event.
+ * cpu_active_mask on each CPU hotplug (cpuhp) event.
  *
  * Called within get_online_cpus().  Needs to call cgroup_lock()
  * before calling generate_sched_domains().
  */
-static int cpuset_track_online_cpus(struct notifier_block *unused_nb,
-				unsigned long phase, void *unused_cpu)
+void cpuset_update_active_cpus(void)
 {
 	struct sched_domain_attr *attr;
 	cpumask_var_t *doms;
 	int ndoms;
 
-	switch (phase) {
-	case CPU_ONLINE:
-	case CPU_ONLINE_FROZEN:
-	case CPU_DOWN_PREPARE:
-	case CPU_DOWN_PREPARE_FROZEN:
-	case CPU_DOWN_FAILED:
-	case CPU_DOWN_FAILED_FROZEN:
-		break;
-
-	default:
-		return NOTIFY_DONE;
-	}
-
 	cgroup_lock();
 	mutex_lock(&callback_mutex);
 	cpumask_copy(top_cpuset.cpus_allowed, cpu_active_mask);
@@ -2148,8 +2134,6 @@ static int cpuset_track_online_cpus(struct notifier_block *unused_nb,
 
 	/* Have scheduler rebuild the domains */
 	partition_sched_domains(ndoms, doms, attr);
-
-	return NOTIFY_OK;
 }
 
 #ifdef CONFIG_MEMORY_HOTPLUG
@@ -2203,7 +2187,6 @@ void __init cpuset_init_smp(void)
 	cpumask_copy(top_cpuset.cpus_allowed, cpu_active_mask);
 	top_cpuset.mems_allowed = node_states[N_HIGH_MEMORY];
 
-	hotcpu_notifier(cpuset_track_online_cpus, 0);
 	hotplug_memory_notifier(cpuset_track_online_nodes, 10);
 
 	cpuset_wq = create_singlethread_workqueue("cpuset");
diff --git a/kernel/fork.c b/kernel/fork.c
index b6cce14ba04..a82a65cef74 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -907,7 +907,7 @@ static void copy_flags(unsigned long clone_flags, struct task_struct *p)
 {
 	unsigned long new_flags = p->flags;
 
-	new_flags &= ~PF_SUPERPRIV;
+	new_flags &= ~(PF_SUPERPRIV | PF_WQ_WORKER);
 	new_flags |= PF_FORKNOEXEC;
 	new_flags |= PF_STARTING;
 	p->flags = new_flags;
diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index 5c69e996bd0..e934339fbbe 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -144,12 +144,8 @@ struct hrtimer_clock_base *lock_hrtimer_base(const struct hrtimer *timer,
 static int hrtimer_get_target(int this_cpu, int pinned)
 {
 #ifdef CONFIG_NO_HZ
-	if (!pinned && get_sysctl_timer_migration() && idle_cpu(this_cpu)) {
-		int preferred_cpu = get_nohz_load_balancer();
-
-		if (preferred_cpu >= 0)
-			return preferred_cpu;
-	}
+	if (!pinned && get_sysctl_timer_migration() && idle_cpu(this_cpu))
+		return get_nohz_timer_target();
 #endif
 	return this_cpu;
 }
diff --git a/kernel/lockdep.c b/kernel/lockdep.c
index 54286798c37..f2852a51023 100644
--- a/kernel/lockdep.c
+++ b/kernel/lockdep.c
@@ -146,7 +146,7 @@ static DEFINE_PER_CPU(struct lock_class_stats[MAX_LOCKDEP_KEYS],
 
 static inline u64 lockstat_clock(void)
 {
-	return cpu_clock(smp_processor_id());
+	return local_clock();
 }
 
 static int lock_point(unsigned long points[], unsigned long ip)
diff --git a/kernel/perf_event.c b/kernel/perf_event.c
index c772a3d4000..403d1804b19 100644
--- a/kernel/perf_event.c
+++ b/kernel/perf_event.c
@@ -214,7 +214,7 @@ static void perf_unpin_context(struct perf_event_context *ctx)
 
 static inline u64 perf_clock(void)
 {
-	return cpu_clock(raw_smp_processor_id());
+	return local_clock();
 }
 
 /*
diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c
index 9829646d399..f66bdd33a6c 100644
--- a/kernel/posix-cpu-timers.c
+++ b/kernel/posix-cpu-timers.c
@@ -232,31 +232,24 @@ static int cpu_clock_sample(const clockid_t which_clock, struct task_struct *p,
 
 void thread_group_cputime(struct task_struct *tsk, struct task_cputime *times)
 {
-	struct sighand_struct *sighand;
-	struct signal_struct *sig;
+	struct signal_struct *sig = tsk->signal;
 	struct task_struct *t;
 
-	*times = INIT_CPUTIME;
+	times->utime = sig->utime;
+	times->stime = sig->stime;
+	times->sum_exec_runtime = sig->sum_sched_runtime;
 
 	rcu_read_lock();
-	sighand = rcu_dereference(tsk->sighand);
-	if (!sighand)
+	/* make sure we can trust tsk->thread_group list */
+	if (!likely(pid_alive(tsk)))
 		goto out;
 
-	sig = tsk->signal;
-
 	t = tsk;
 	do {
 		times->utime = cputime_add(times->utime, t->utime);
 		times->stime = cputime_add(times->stime, t->stime);
 		times->sum_exec_runtime += t->se.sum_exec_runtime;
-
-		t = next_thread(t);
-	} while (t != tsk);
-
-	times->utime = cputime_add(times->utime, sig->utime);
-	times->stime = cputime_add(times->stime, sig->stime);
-	times->sum_exec_runtime += sig->sum_sched_runtime;
+	} while_each_thread(tsk, t);
 out:
 	rcu_read_unlock();
 }
@@ -1279,10 +1272,6 @@ static inline int fastpath_timer_check(struct task_struct *tsk)
 {
 	struct signal_struct *sig;
 
-	/* tsk == current, ensure it is safe to use ->signal/sighand */
-	if (unlikely(tsk->exit_state))
-		return 0;
-
 	if (!task_cputime_zero(&tsk->cputime_expires)) {
 		struct task_cputime task_sample = {
 			.utime = tsk->utime,
@@ -1298,7 +1287,10 @@ static inline int fastpath_timer_check(struct task_struct *tsk)
 	if (sig->cputimer.running) {
 		struct task_cputime group_sample;
 
-		thread_group_cputimer(tsk, &group_sample);
+		spin_lock(&sig->cputimer.lock);
+		group_sample = sig->cputimer.cputime;
+		spin_unlock(&sig->cputimer.lock);
+
 		if (task_cputime_expired(&group_sample, &sig->cputime_expires))
 			return 1;
 	}
@@ -1315,6 +1307,7 @@ void run_posix_cpu_timers(struct task_struct *tsk)
 {
 	LIST_HEAD(firing);
 	struct k_itimer *timer, *next;
+	unsigned long flags;
 
 	BUG_ON(!irqs_disabled());
 
@@ -1325,7 +1318,8 @@ void run_posix_cpu_timers(struct task_struct *tsk)
 	if (!fastpath_timer_check(tsk))
 		return;
 
-	spin_lock(&tsk->sighand->siglock);
+	if (!lock_task_sighand(tsk, &flags))
+		return;
 	/*
 	 * Here we take off tsk->signal->cpu_timers[N] and
 	 * tsk->cpu_timers[N] all the timers that are firing, and
@@ -1347,7 +1341,7 @@ void run_posix_cpu_timers(struct task_struct *tsk)
 	 * that gets the timer lock before we do will give it up and
 	 * spin until we've taken care of that timer below.
 	 */
-	spin_unlock(&tsk->sighand->siglock);
+	unlock_task_sighand(tsk, &flags);
 
 	/*
 	 * Now that all the timers on our list have the firing flag,
diff --git a/kernel/rcutorture.c b/kernel/rcutorture.c
index 6535ac8bc6a..2e2726d790b 100644
--- a/kernel/rcutorture.c
+++ b/kernel/rcutorture.c
@@ -239,8 +239,7 @@ static unsigned long
 rcu_random(struct rcu_random_state *rrsp)
 {
 	if (--rrsp->rrs_count < 0) {
-		rrsp->rrs_state +=
-			(unsigned long)cpu_clock(raw_smp_processor_id());
+		rrsp->rrs_state += (unsigned long)local_clock();
 		rrsp->rrs_count = RCU_RANDOM_REFRESH;
 	}
 	rrsp->rrs_state = rrsp->rrs_state * RCU_RANDOM_MULT + RCU_RANDOM_ADD;
diff --git a/kernel/sched.c b/kernel/sched.c
index 265cf3a2b5d..41541d79e3c 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -77,6 +77,7 @@
 #include <asm/irq_regs.h>
 
 #include "sched_cpupri.h"
+#include "workqueue_sched.h"
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/sched.h>
@@ -456,9 +457,10 @@ struct rq {
 	unsigned long nr_running;
 	#define CPU_LOAD_IDX_MAX 5
 	unsigned long cpu_load[CPU_LOAD_IDX_MAX];
+	unsigned long last_load_update_tick;
 #ifdef CONFIG_NO_HZ
 	u64 nohz_stamp;
-	unsigned char in_nohz_recently;
+	unsigned char nohz_balance_kick;
 #endif
 	unsigned int skip_clock_update;
 
@@ -1193,6 +1195,27 @@ static void resched_cpu(int cpu)
 
 #ifdef CONFIG_NO_HZ
 /*
+ * In the semi idle case, use the nearest busy cpu for migrating timers
+ * from an idle cpu.  This is good for power-savings.
+ *
+ * We don't do similar optimization for completely idle system, as
+ * selecting an idle cpu will add more delays to the timers than intended
+ * (as that cpu's timer base may not be uptodate wrt jiffies etc).
+ */
+int get_nohz_timer_target(void)
+{
+	int cpu = smp_processor_id();
+	int i;
+	struct sched_domain *sd;
+
+	for_each_domain(cpu, sd) {
+		for_each_cpu(i, sched_domain_span(sd))
+			if (!idle_cpu(i))
+				return i;
+	}
+	return cpu;
+}
+/*
  * When add_timer_on() enqueues a timer into the timer wheel of an
  * idle CPU then this timer might expire before the next timer event
  * which is scheduled to wake up that CPU. In case of a completely
@@ -1232,16 +1255,6 @@ void wake_up_idle_cpu(int cpu)
 		smp_send_reschedule(cpu);
 }
 
-int nohz_ratelimit(int cpu)
-{
-	struct rq *rq = cpu_rq(cpu);
-	u64 diff = rq->clock - rq->nohz_stamp;
-
-	rq->nohz_stamp = rq->clock;
-
-	return diff < (NSEC_PER_SEC / HZ) >> 1;
-}
-
 #endif /* CONFIG_NO_HZ */
 
 static u64 sched_avg_period(void)
@@ -1652,7 +1665,7 @@ static void update_shares(struct sched_domain *sd)
 	if (root_task_group_empty())
 		return;
 
-	now = cpu_clock(raw_smp_processor_id());
+	now = local_clock();
 	elapsed = now - sd->last_update;
 
 	if (elapsed >= (s64)(u64)sysctl_sched_shares_ratelimit) {
@@ -1805,6 +1818,7 @@ static void cfs_rq_set_shares(struct cfs_rq *cfs_rq, unsigned long shares)
 static void calc_load_account_idle(struct rq *this_rq);
 static void update_sysctl(void);
 static int get_update_sysctl_factor(void);
+static void update_cpu_load(struct rq *this_rq);
 
 static inline void __set_task_cpu(struct task_struct *p, unsigned int cpu)
 {
@@ -2267,11 +2281,55 @@ static void update_avg(u64 *avg, u64 sample)
 }
 #endif
 
-/***
+static inline void ttwu_activate(struct task_struct *p, struct rq *rq,
+				 bool is_sync, bool is_migrate, bool is_local,
+				 unsigned long en_flags)
+{
+	schedstat_inc(p, se.statistics.nr_wakeups);
+	if (is_sync)
+		schedstat_inc(p, se.statistics.nr_wakeups_sync);
+	if (is_migrate)
+		schedstat_inc(p, se.statistics.nr_wakeups_migrate);
+	if (is_local)
+		schedstat_inc(p, se.statistics.nr_wakeups_local);
+	else
+		schedstat_inc(p, se.statistics.nr_wakeups_remote);
+
+	activate_task(rq, p, en_flags);
+}
+
+static inline void ttwu_post_activation(struct task_struct *p, struct rq *rq,
+					int wake_flags, bool success)
+{
+	trace_sched_wakeup(p, success);
+	check_preempt_curr(rq, p, wake_flags);
+
+	p->state = TASK_RUNNING;
+#ifdef CONFIG_SMP
+	if (p->sched_class->task_woken)
+		p->sched_class->task_woken(rq, p);
+
+	if (unlikely(rq->idle_stamp)) {
+		u64 delta = rq->clock - rq->idle_stamp;
+		u64 max = 2*sysctl_sched_migration_cost;
+
+		if (delta > max)
+			rq->avg_idle = max;
+		else
+			update_avg(&rq->avg_idle, delta);
+		rq->idle_stamp = 0;
+	}
+#endif
+	/* if a worker is waking up, notify workqueue */
+	if ((p->flags & PF_WQ_WORKER) && success)
+		wq_worker_waking_up(p, cpu_of(rq));
+}
+
+/**
  * try_to_wake_up - wake up a thread
- * @p: the to-be-woken-up thread
+ * @p: the thread to be awakened
  * @state: the mask of task states that can be woken
- * @sync: do a synchronous wakeup?
+ * @wake_flags: wake modifier flags (WF_*)
  *
  * Put it on the run-queue if it's not already there. The "current"
  * thread is always on the run-queue (except when the actual
@@ -2279,7 +2337,8 @@ static void update_avg(u64 *avg, u64 sample)
  * the simpler "current->state = TASK_RUNNING" to mark yourself
  * runnable without the overhead of this.
  *
- * returns failure only if the task is already active.
+ * Returns %true if @p was woken up, %false if it was already running
+ * or @state didn't match @p's state.
  */
 static int try_to_wake_up(struct task_struct *p, unsigned int state,
 			  int wake_flags)
@@ -2359,38 +2418,11 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state,
 
 out_activate:
 #endif /* CONFIG_SMP */
-	schedstat_inc(p, se.statistics.nr_wakeups);
-	if (wake_flags & WF_SYNC)
-		schedstat_inc(p, se.statistics.nr_wakeups_sync);
-	if (orig_cpu != cpu)
-		schedstat_inc(p, se.statistics.nr_wakeups_migrate);
-	if (cpu == this_cpu)
-		schedstat_inc(p, se.statistics.nr_wakeups_local);
-	else
-		schedstat_inc(p, se.statistics.nr_wakeups_remote);
-	activate_task(rq, p, en_flags);
+	ttwu_activate(p, rq, wake_flags & WF_SYNC, orig_cpu != cpu,
+		      cpu == this_cpu, en_flags);
 	success = 1;
-
 out_running:
-	trace_sched_wakeup(p, success);
-	check_preempt_curr(rq, p, wake_flags);
-
-	p->state = TASK_RUNNING;
-#ifdef CONFIG_SMP
-	if (p->sched_class->task_woken)
-		p->sched_class->task_woken(rq, p);
-
-	if (unlikely(rq->idle_stamp)) {
-		u64 delta = rq->clock - rq->idle_stamp;
-		u64 max = 2*sysctl_sched_migration_cost;
-
-		if (delta > max)
-			rq->avg_idle = max;
-		else
-			update_avg(&rq->avg_idle, delta);
-		rq->idle_stamp = 0;
-	}
-#endif
+	ttwu_post_activation(p, rq, wake_flags, success);
 out:
 	task_rq_unlock(rq, &flags);
 	put_cpu();
@@ -2399,6 +2431,37 @@ out:
 }
 
 /**
+ * try_to_wake_up_local - try to wake up a local task with rq lock held
+ * @p: the thread to be awakened
+ *
+ * Put @p on the run-queue if it's not alredy there.  The caller must
+ * ensure that this_rq() is locked, @p is bound to this_rq() and not
+ * the current task.  this_rq() stays locked over invocation.
+ */
+static void try_to_wake_up_local(struct task_struct *p)
+{
+	struct rq *rq = task_rq(p);
+	bool success = false;
+
+	BUG_ON(rq != this_rq());
+	BUG_ON(p == current);
+	lockdep_assert_held(&rq->lock);
+
+	if (!(p->state & TASK_NORMAL))
+		return;
+
+	if (!p->se.on_rq) {
+		if (likely(!task_running(rq, p))) {
+			schedstat_inc(rq, ttwu_count);
+			schedstat_inc(rq, ttwu_local);
+		}
+		ttwu_activate(p, rq, false, false, true, ENQUEUE_WAKEUP);
+		success = true;
+	}
+	ttwu_post_activation(p, rq, 0, success);
+}
+
+/**
  * wake_up_process - Wake up a specific process
  * @p: The process to be woken up.
  *
@@ -3012,23 +3075,102 @@ static void calc_load_account_active(struct rq *this_rq)
 }
 
 /*
+ * The exact cpuload at various idx values, calculated at every tick would be
+ * load = (2^idx - 1) / 2^idx * load + 1 / 2^idx * cur_load
+ *
+ * If a cpu misses updates for n-1 ticks (as it was idle) and update gets called
+ * on nth tick when cpu may be busy, then we have:
+ * load = ((2^idx - 1) / 2^idx)^(n-1) * load
+ * load = (2^idx - 1) / 2^idx) * load + 1 / 2^idx * cur_load
+ *
+ * decay_load_missed() below does efficient calculation of
+ * load = ((2^idx - 1) / 2^idx)^(n-1) * load
+ * avoiding 0..n-1 loop doing load = ((2^idx - 1) / 2^idx) * load
+ *
+ * The calculation is approximated on a 128 point scale.
+ * degrade_zero_ticks is the number of ticks after which load at any
+ * particular idx is approximated to be zero.
+ * degrade_factor is a precomputed table, a row for each load idx.
+ * Each column corresponds to degradation factor for a power of two ticks,
+ * based on 128 point scale.
+ * Example:
+ * row 2, col 3 (=12) says that the degradation at load idx 2 after
+ * 8 ticks is 12/128 (which is an approximation of exact factor 3^8/4^8).
+ *
+ * With this power of 2 load factors, we can degrade the load n times
+ * by looking at 1 bits in n and doing as many mult/shift instead of
+ * n mult/shifts needed by the exact degradation.
+ */
+#define DEGRADE_SHIFT		7
+static const unsigned char
+		degrade_zero_ticks[CPU_LOAD_IDX_MAX] = {0, 8, 32, 64, 128};
+static const unsigned char
+		degrade_factor[CPU_LOAD_IDX_MAX][DEGRADE_SHIFT + 1] = {
+					{0, 0, 0, 0, 0, 0, 0, 0},
+					{64, 32, 8, 0, 0, 0, 0, 0},
+					{96, 72, 40, 12, 1, 0, 0},
+					{112, 98, 75, 43, 15, 1, 0},
+					{120, 112, 98, 76, 45, 16, 2} };
+
+/*
+ * Update cpu_load for any missed ticks, due to tickless idle. The backlog
+ * would be when CPU is idle and so we just decay the o