Merge branch 'linus' into sched/core

Merge reason: pick up the latest scheduler fixes.

Signed-off-by: Ingo Molnar <mingo@elte.hu>

11 files changed, 450 insertions, 122 deletions

diff --git a/kernel/irq/generic-chip.c b/kernel/irq/generic-chip.c
index 31a9db7..3a2cab4 100644
--- a/kernel/irq/generic-chip.c
+++ b/kernel/irq/generic-chip.c
@@ -101,10 +101,10 @@ void irq_gc_unmask_enable_reg(struct irq_data *d)
 }
 
 /**
- * irq_gc_ack - Ack pending interrupt
+ * irq_gc_ack_set_bit - Ack pending interrupt via setting bit
  * @d: irq_data
  */
-void irq_gc_ack(struct irq_data *d)
+void irq_gc_ack_set_bit(struct irq_data *d)
 {
 	struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d);
 	u32 mask = 1 << (d->irq - gc->irq_base);
@@ -115,6 +115,20 @@ void irq_gc_ack(struct irq_data *d)
 }
 
 /**
+ * irq_gc_ack_clr_bit - Ack pending interrupt via clearing bit
+ * @d: irq_data
+ */
+void irq_gc_ack_clr_bit(struct irq_data *d)
+{
+	struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d);
+	u32 mask = ~(1 << (d->irq - gc->irq_base));
+
+	irq_gc_lock(gc);
+	irq_reg_writel(mask, gc->reg_base + cur_regs(d)->ack);
+	irq_gc_unlock(gc);
+}
+
+/**
  * irq_gc_mask_disable_reg_and_ack- Mask and ack pending interrupt
  * @d: irq_data
  */
diff --git a/kernel/jump_label.c b/kernel/jump_label.c
index fa27e75..a8ce450 100644
--- a/kernel/jump_label.c
+++ b/kernel/jump_label.c
@@ -375,15 +375,19 @@ int jump_label_text_reserved(void *start, void *end)
 
 static void jump_label_update(struct jump_label_key *key, int enable)
 {
-	struct jump_entry *entry = key->entries;
-
-	/* if there are no users, entry can be NULL */
-	if (entry)
-		__jump_label_update(key, entry, __stop___jump_table, enable);
+	struct jump_entry *entry = key->entries, *stop = __stop___jump_table;
 
 #ifdef CONFIG_MODULES
+	struct module *mod = __module_address((jump_label_t)key);
+
 	__jump_label_mod_update(key, enable);
+
+	if (mod)
+		stop = mod->jump_entries + mod->num_jump_entries;
 #endif
+	/* if there are no users, entry can be NULL */
+	if (entry)
+		__jump_label_update(key, entry, stop, enable);
 }
 
 #endif
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index ace5588..06efa54 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -1211,7 +1211,11 @@ static void free_unnecessary_pages(void)
 		to_free_highmem = alloc_highmem - save;
 	} else {
 		to_free_highmem = 0;
-		to_free_normal -= save - alloc_highmem;
+		save -= alloc_highmem;
+		if (to_free_normal > save)
+			to_free_normal -= save;
+		else
+			to_free_normal = 0;
 	}
 
 	memory_bm_position_reset(&copy_bm);
diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index 7e59ffb..ba06207 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -84,9 +84,32 @@ DEFINE_PER_CPU(struct rcu_data, rcu_bh_data);
 
 static struct rcu_state *rcu_state;
 
+/*
+ * The rcu_scheduler_active variable transitions from zero to one just
+ * before the first task is spawned.  So when this variable is zero, RCU
+ * can assume that there is but one task, allowing RCU to (for example)
+ * optimized synchronize_sched() to a simple barrier().  When this variable
+ * is one, RCU must actually do all the hard work required to detect real
+ * grace periods.  This variable is also used to suppress boot-time false
+ * positives from lockdep-RCU error checking.
+ */
 int rcu_scheduler_active __read_mostly;
 EXPORT_SYMBOL_GPL(rcu_scheduler_active);
 
+/*
+ * The rcu_scheduler_fully_active variable transitions from zero to one
+ * during the early_initcall() processing, which is after the scheduler
+ * is capable of creating new tasks.  So RCU processing (for example,
+ * creating tasks for RCU priority boosting) must be delayed until after
+ * rcu_scheduler_fully_active transitions from zero to one.  We also
+ * currently delay invocation of any RCU callbacks until after this point.
+ *
+ * It might later prove better for people registering RCU callbacks during
+ * early boot to take responsibility for these callbacks, but one step at
+ * a time.
+ */
+static int rcu_scheduler_fully_active __read_mostly;
+
 #ifdef CONFIG_RCU_BOOST
 
 /*
@@ -98,7 +121,6 @@ DEFINE_PER_CPU(unsigned int, rcu_cpu_kthread_status);
 DEFINE_PER_CPU(int, rcu_cpu_kthread_cpu);
 DEFINE_PER_CPU(unsigned int, rcu_cpu_kthread_loops);
 DEFINE_PER_CPU(char, rcu_cpu_has_work);
-static char rcu_kthreads_spawnable;
 
 #endif /* #ifdef CONFIG_RCU_BOOST */
 
@@ -1467,6 +1489,8 @@ static void rcu_process_callbacks(struct softirq_action *unused)
  */
 static void invoke_rcu_callbacks(struct rcu_state *rsp, struct rcu_data *rdp)
 {
+	if (unlikely(!ACCESS_ONCE(rcu_scheduler_fully_active)))
+		return;
 	if (likely(!rsp->boost)) {
 		rcu_do_batch(rsp, rdp);
 		return;
diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h
index 14dc7dd..8aafbb8 100644
--- a/kernel/rcutree_plugin.h
+++ b/kernel/rcutree_plugin.h
@@ -68,6 +68,7 @@ struct rcu_state rcu_preempt_state = RCU_STATE_INITIALIZER(rcu_preempt_state);
 DEFINE_PER_CPU(struct rcu_data, rcu_preempt_data);
 static struct rcu_state *rcu_state = &rcu_preempt_state;
 
+static void rcu_read_unlock_special(struct task_struct *t);
 static int rcu_preempted_readers_exp(struct rcu_node *rnp);
 
 /*
@@ -147,7 +148,7 @@ static void rcu_preempt_note_context_switch(int cpu)
 	struct rcu_data *rdp;
 	struct rcu_node *rnp;
 
-	if (t->rcu_read_lock_nesting &&
+	if (t->rcu_read_lock_nesting > 0 &&
 	    (t->rcu_read_unlock_special & RCU_READ_UNLOCK_BLOCKED) == 0) {
 
 		/* Possibly blocking in an RCU read-side critical section. */
@@ -190,6 +191,14 @@ static void rcu_preempt_note_context_switch(int cpu)
 				rnp->gp_tasks = &t->rcu_node_entry;
 		}
 		raw_spin_unlock_irqrestore(&rnp->lock, flags);
+	} else if (t->rcu_read_lock_nesting < 0 &&
+		   t->rcu_read_unlock_special) {
+
+		/*
+		 * Complete exit from RCU read-side critical section on
+		 * behalf of preempted instance of __rcu_read_unlock().
+		 */
+		rcu_read_unlock_special(t);
 	}
 
 	/*
@@ -284,7 +293,7 @@ static struct list_head *rcu_next_node_entry(struct task_struct *t,
  * notify RCU core processing or task having blocked during the RCU
  * read-side critical section.
  */
-static void rcu_read_unlock_special(struct task_struct *t)
+static noinline void rcu_read_unlock_special(struct task_struct *t)
 {
 	int empty;
 	int empty_exp;
@@ -309,7 +318,7 @@ static void rcu_read_unlock_special(struct task_struct *t)
 	}
 
 	/* Hardware IRQ handlers cannot block. */
-	if (in_irq()) {
+	if (in_irq() || in_serving_softirq()) {
 		local_irq_restore(flags);
 		return;
 	}
@@ -342,6 +351,11 @@ static void rcu_read_unlock_special(struct task_struct *t)
 #ifdef CONFIG_RCU_BOOST
 		if (&t->rcu_node_entry == rnp->boost_tasks)
 			rnp->boost_tasks = np;
+		/* Snapshot and clear ->rcu_boosted with rcu_node lock held. */
+		if (t->rcu_boosted) {
+			special |= RCU_READ_UNLOCK_BOOSTED;
+			t->rcu_boosted = 0;
+		}
 #endif /* #ifdef CONFIG_RCU_BOOST */
 		t->rcu_blocked_node = NULL;
 
@@ -358,7 +372,6 @@ static void rcu_read_unlock_special(struct task_struct *t)
 #ifdef CONFIG_RCU_BOOST
 		/* Unboost if we were boosted. */
 		if (special & RCU_READ_UNLOCK_BOOSTED) {
-			t->rcu_read_unlock_special &= ~RCU_READ_UNLOCK_BOOSTED;
 			rt_mutex_unlock(t->rcu_boost_mutex);
 			t->rcu_boost_mutex = NULL;
 		}
@@ -387,13 +400,22 @@ void __rcu_read_unlock(void)
 	struct task_struct *t = current;
 
 	barrier();  /* needed if we ever invoke rcu_read_unlock in rcutree.c */
-	--t->rcu_read_lock_nesting;
-	barrier();  /* decrement before load of ->rcu_read_unlock_special */
-	if (t->rcu_read_lock_nesting == 0 &&
-	    unlikely(ACCESS_ONCE(t->rcu_read_unlock_special)))
-		rcu_read_unlock_special(t);
+	if (t->rcu_read_lock_nesting != 1)
+		--t->rcu_read_lock_nesting;
+	else {
+		t->rcu_read_lock_nesting = INT_MIN;
+		barrier();  /* assign before ->rcu_read_unlock_special load */
+		if (unlikely(ACCESS_ONCE(t->rcu_read_unlock_special)))
+			rcu_read_unlock_special(t);
+		barrier();  /* ->rcu_read_unlock_special load before assign */
+		t->rcu_read_lock_nesting = 0;
+	}
 #ifdef CONFIG_PROVE_LOCKING
-	WARN_ON_ONCE(ACCESS_ONCE(t->rcu_read_lock_nesting) < 0);
+	{
+		int rrln = ACCESS_ONCE(t->rcu_read_lock_nesting);
+
+		WARN_ON_ONCE(rrln < 0 && rrln > INT_MIN / 2);
+	}
 #endif /* #ifdef CONFIG_PROVE_LOCKING */
 }
 EXPORT_SYMBOL_GPL(__rcu_read_unlock);
@@ -589,7 +611,8 @@ static void rcu_preempt_check_callbacks(int cpu)
 		rcu_preempt_qs(cpu);
 		return;
 	}
-	if (per_cpu(rcu_preempt_data, cpu).qs_pending)
+	if (t->rcu_read_lock_nesting > 0 &&
+	    per_cpu(rcu_preempt_data, cpu).qs_pending)
 		t->rcu_read_unlock_special |= RCU_READ_UNLOCK_NEED_QS;
 }
 
@@ -695,9 +718,12 @@ static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp)
 
 	raw_spin_lock_irqsave(&rnp->lock, flags);
 	for (;;) {
-		if (!sync_rcu_preempt_exp_done(rnp))
+		if (!sync_rcu_preempt_exp_done(rnp)) {
+			raw_spin_unlock_irqrestore(&rnp->lock, flags);
 			break;
+		}
 		if (rnp->parent == NULL) {
+			raw_spin_unlock_irqrestore(&rnp->lock, flags);
 			wake_up(&sync_rcu_preempt_exp_wq);
 			break;
 		}
@@ -707,7 +733,6 @@ static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp)
 		raw_spin_lock(&rnp->lock); /* irqs already disabled */
 		rnp->expmask &= ~mask;
 	}
-	raw_spin_unlock_irqrestore(&rnp->lock, flags);
 }
 
 /*
@@ -1174,7 +1199,7 @@ static int rcu_boost(struct rcu_node *rnp)
 	t = container_of(tb, struct task_struct, rcu_node_entry);
 	rt_mutex_init_proxy_locked(&mtx, t);
 	t->rcu_boost_mutex = &mtx;
-	t->rcu_read_unlock_special |= RCU_READ_UNLOCK_BOOSTED;
+	t->rcu_boosted = 1;
 	raw_spin_unlock_irqrestore(&rnp->lock, flags);
 	rt_mutex_lock(&mtx);  /* Side effect: boosts task t's priority. */
 	rt_mutex_unlock(&mtx);  /* Keep lockdep happy. */
@@ -1532,7 +1557,7 @@ static int __cpuinit rcu_spawn_one_cpu_kthread(int cpu)
 	struct sched_param sp;
 	struct task_struct *t;
 
-	if (!rcu_kthreads_spawnable ||
+	if (!rcu_scheduler_fully_active ||
 	    per_cpu(rcu_cpu_kthread_task, cpu) != NULL)
 		return 0;
 	t = kthread_create(rcu_cpu_kthread, (void *)(long)cpu, "rcuc%d", cpu);
@@ -1639,7 +1664,7 @@ static int __cpuinit rcu_spawn_one_node_kthread(struct rcu_state *rsp,
 	struct sched_param sp;
 	struct task_struct *t;
 
-	if (!rcu_kthreads_spawnable ||
+	if (!rcu_scheduler_fully_active ||
 	    rnp->qsmaskinit == 0)
 		return 0;
 	if (rnp->node_kthread_task == NULL) {
@@ -1665,7 +1690,7 @@ static int __init rcu_spawn_kthreads(void)
 	int cpu;
 	struct rcu_node *rnp;
 
-	rcu_kthreads_spawnable = 1;
+	rcu_scheduler_fully_active = 1;
 	for_each_possible_cpu(cpu) {
 		per_cpu(rcu_cpu_has_work, cpu) = 0;
 		if (cpu_online(cpu))
@@ -1687,7 +1712,7 @@ static void __cpuinit rcu_prepare_kthreads(int cpu)
 	struct rcu_node *rnp = rdp->mynode;
 
 	/* Fire up the incoming CPU's kthread and leaf rcu_node kthread. */
-	if (rcu_kthreads_spawnable) {
+	if (rcu_scheduler_fully_active) {
 		(void)rcu_spawn_one_cpu_kthread(cpu);
 		if (rnp->node_kthread_task == NULL)
 			(void)rcu_spawn_one_node_kthread(rcu_state, rnp);
@@ -1726,6 +1751,13 @@ static void rcu_cpu_kthread_setrt(int cpu, int to_rt)
 {
 }
 
+static int __init rcu_scheduler_really_started(void)
+{
+	rcu_scheduler_fully_active = 1;
+	return 0;
+}
+early_initcall(rcu_scheduler_really_started);
+
 static void __cpuinit rcu_prepare_kthreads(int cpu)
 {
 }
diff --git a/kernel/resource.c b/kernel/resource.c
index 798e2fa..3ff4017 100644
--- a/kernel/resource.c
+++ b/kernel/resource.c
@@ -38,6 +38,14 @@ struct resource iomem_resource = {
 };
 EXPORT_SYMBOL(iomem_resource);
 
+/* constraints to be met while allocating resources */
+struct resource_constraint {
+	resource_size_t min, max, align;
+	resource_size_t (*alignf)(void *, const struct resource *,
+			resource_size_t, resource_size_t);
+	void *alignf_data;
+};
+
 static DEFINE_RWLOCK(resource_lock);
 
 static void *r_next(struct seq_file *m, void *v, loff_t *pos)
@@ -384,16 +392,13 @@ static bool resource_contains(struct resource *res1, struct resource *res2)
 }
 
 /*
- * Find empty slot in the resource tree given range and alignment.
+ * Find empty slot in the resource tree with the given range and
+ * alignment constraints
  */
-static int find_resource(struct resource *root, struct resource *new,
-			 resource_size_t size, resource_size_t min,
-			 resource_size_t max, resource_size_t align,
-			 resource_size_t (*alignf)(void *,
-						   const struct resource *,
-						   resource_size_t,
-						   resource_size_t),
-			 void *alignf_data)
+static int __find_resource(struct resource *root, struct resource *old,
+			 struct resource *new,
+			 resource_size_t  size,
+			 struct resource_constraint *constraint)
 {
 	struct resource *this = root->child;
 	struct resource tmp = *new, avail, alloc;
@@ -404,25 +409,26 @@ static int find_resource(struct resource *root, struct resource *new,
 	 * Skip past an allocated resource that starts at 0, since the assignment
 	 * of this->start - 1 to tmp->end below would cause an underflow.
 	 */
-	if (this && this->start == 0) {
-		tmp.start = this->end + 1;
+	if (this && this->start == root->start) {
+		tmp.start = (this == old) ? old->start : this->end + 1;
 		this = this->sibling;
 	}
 	for(;;) {
 		if (this)
-			tmp.end = this->start - 1;
+			tmp.end = (this == old) ?  this->end : this->start - 1;
 		else
 			tmp.end = root->end;
 
-		resource_clip(&tmp, min, max);
+		resource_clip(&tmp, constraint->min, constraint->max);
 		arch_remove_reservations(&tmp);
 
 		/* Check for overflow after ALIGN() */
 		avail = *new;
-		avail.start = ALIGN(tmp.start, align);
+		avail.start = ALIGN(tmp.start, constraint->align);
 		avail.end = tmp.end;
 		if (avail.start >= tmp.start) {
-			alloc.start = alignf(alignf_data, &avail, size, align);
+			alloc.start = constraint->alignf(constraint->alignf_data, &avail,
+					size, constraint->align);
 			alloc.end = alloc.start + size - 1;
 			if (resource_contains(&avail, &alloc)) {
 				new->start = alloc.start;
@@ -432,14 +438,75 @@ static int find_resource(struct resource *root, struct resource *new,
 		}
 		if (!this)
 			break;
-		tmp.start = this->end + 1;
+		if (this != old)
+			tmp.start = this->end + 1;
 		this = this->sibling;
 	}
 	return -EBUSY;
 }
 
+/*
+ * Find empty slot in the resource tree given range and alignment.
+ */
+static int find_resource(struct resource *root, struct resource *new,
+			resource_size_t size,
+			struct resource_constraint  *constraint)
+{
+	return  __find_resource(root, NULL, new, size, constraint);
+}
+
 /**
- * allocate_resource - allocate empty slot in the resource tree given range & alignment
+ * reallocate_resource - allocate a slot in the resource tree given range & alignment.
+ *	The resource will be relocated if the new size cannot be reallocated in the
+ *	current location.
+ *
+ * @root: root resource descriptor
+ * @old:  resource descriptor desired by caller
+ * @newsize: new size of the resource descriptor
+ * @constraint: the size and alignment constraints to be met.
+ */
+int reallocate_resource(struct resource *root, struct resource *old,
+			resource_size_t newsize,
+			struct resource_constraint  *constraint)
+{
+	int err=0;
+	struct resource new = *old;
+	struct resource *conflict;
+
+	write_lock(&resource_lock);
+
+	if ((err = __find_resource(root, old, &new, newsize, constraint)))
+		goto out;
+
+	if (resource_contains(&new, old)) {
+		old->start = new.start;
+		old->end = new.end;
+		goto out;
+	}
+
+	if (old->child) {
+		err = -EBUSY;
+		goto out;
+	}
+
+	if (resource_contains(old, &new)) {
+		old->start = new.start;
+		old->end = new.end;
+	} else {
+		__release_resource(old);
+		*old = new;
+		conflict = __request_resource(root, old);
+		BUG_ON(conflict);
+	}
+out:
+	write_unlock(&resource_lock);
+	return err;
+}
+
+
+/**
+ * allocate_resource - allocate empty slot in the resource tree given range & alignment.
+ * 	The resource will be reallocated with a new size if it was already allocated
  * @root: root resource descriptor
  * @new: resource descriptor desired by caller
  * @size: requested resource region size
@@ -459,12 +526,25 @@ int allocate_resource(struct resource *root, struct resource *new,
 		      void *alignf_data)
 {
 	int err;
+	struct resource_constraint constraint;
 
 	if (!alignf)
 		alignf = simple_align_resource;
 
+	constraint.min = min;
+	constraint.max = max;
+	constraint.align = align;
+	constraint.alignf = alignf;
+	constraint.alignf_data = alignf_data;
+
+	if ( new->parent ) {
+		/* resource is already allocated, try reallocating with
+		   the new constraints */
+		return reallocate_resource(root, new, size, &constraint);
+	}
+
 	write_lock(&resource_lock);
-	err = find_resource(root, new, size, min, max, align, alignf, alignf_data);
+	err = find_resource(root, new, size, &constraint);
 	if (err >= 0 && __request_resource(root, new))
 		err = -EBUSY;
 	write_unlock(&resource_lock);
diff --git a/kernel/sched.c b/kernel/sched.c
index 4380a80..b0e7ad7 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -292,8 +292,8 @@ static DEFINE_SPINLOCK(task_group_lock);
  * (The default weight is 1024 - so there's no practical
  *  limitation from this.)
  */
-#define MIN_SHARES	2
-#define MAX_SHARES	(1UL << (18 + SCHED_LOAD_RESOLUTION))
+#define MIN_SHARES	(1UL <<  1)
+#define MAX_SHARES	(1UL << 18)
 
 static int root_task_group_load = ROOT_TASK_GROUP_LOAD;
 #endif
@@ -2544,13 +2544,9 @@ static int ttwu_remote(struct task_struct *p, int wake_flags)
 }
 
 #ifdef CONFIG_SMP
-static void sched_ttwu_pending(void)
+static void sched_ttwu_do_pending(struct task_struct *list)
 {
 	struct rq *rq = this_rq();
-	struct task_struct *list = xchg(&rq->wake_list, NULL);
-
-	if (!list)
-		return;
 
 	raw_spin_lock(&rq->lock);
 
@@ -2563,9 +2559,45 @@ static void sched_ttwu_pending(void)
 	raw_spin_unlock(&rq->lock);
 }
 
+#ifdef CONFIG_HOTPLUG_CPU
+
+static void sched_ttwu_pending(void)
+{
+	struct rq *rq = this_rq();
+	struct task_struct *list = xchg(&rq->wake_list, NULL);
+
+	if (!list)
+		return;
+
+	sched_ttwu_do_pending(list);
+}
+
+#endif /* CONFIG_HOTPLUG_CPU */
+
 void scheduler_ipi(void)
 {
-	sched_ttwu_pending();
+	struct rq *rq = this_rq();
+	struct task_struct *list = xchg(&rq->wake_list, NULL);
+
+	if (!list)
+		return;
+
+	/*
+	 * Not all reschedule IPI handlers call irq_enter/irq_exit, since
+	 * traditionally all their work was done from the interrupt return
+	 * path. Now that we actually do some work, we need to make sure
+	 * we do call them.
+	 *
+	 * Some archs already do call them, luckily irq_enter/exit nest
+	 * properly.
+	 *
+	 * Arguably we should visit all archs and update all handlers,
+	 * however a fair share of IPIs are still resched only so this would
+	 * somewhat pessimize the simple resched case.
+	 */
+	irq_enter();
+	sched_ttwu_do_pending(list);
+	irq_exit();
 }
 
 static void ttwu_queue_remote(struct task_struct *p, int cpu)
@@ -6550,7 +6582,7 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level,
 			break;
 		}
 
-		if (!group->cpu_power) {
+		if (!group->sgp->power) {
 			printk(KERN_CONT "\n");
 			printk(KERN_ERR "ERROR: domain->cpu_power not "
 					"set\n");
@@ -6574,9 +6606,9 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level,
 		cpulist_scnprintf(str, sizeof(str), sched_group_cpus(group));
 
 		printk(KERN_CONT " %s", str);
-		if (group->cpu_power != SCHED_POWER_SCALE) {
+		if (group->sgp->power != SCHED_POWER_SCALE) {
 			printk(KERN_CONT " (cpu_power = %d)",
-				group->cpu_power);
+				group->sgp->power);
 		}
 
 		group = group->next;
@@ -6767,11 +6799,39 @@ static struct root_domain *alloc_rootdomain(void)
 	return rd;
 }
 
+static void free_sched_groups(struct sched_group *sg, int free_sgp)
+{
+	struct sched_group *tmp, *first;
+
+	if (!sg)
+		return;
+
+	first = sg;
+	do {
+		tmp = sg->next;
+
+		if (free_sgp && atomic_dec_and_test(&sg->sgp->ref))
+			kfree(sg->sgp);
+
+		kfree(sg);
+		sg = tmp;
+	} while (sg != first);
+}
+
 static void free_sched_domain(struct rcu_head *rcu)
 {
 	struct sched_domain *sd = container_of(rcu, struct sched_domain, rcu);
-	if (atomic_dec_and_test(&sd->groups->ref))
+
+	/*
+	 * If its an overlapping domain it has private groups, iterate and
+	 * nuke them all.
+	 */
+	if (sd->flags & SD_OVERLAP) {
+		free_sched_groups(sd->groups, 1);
+	} else if (atomic_dec_and_test(&sd->groups->ref)) {
+		kfree(sd->groups->sgp);
 		kfree(sd->groups);
+	}
 	kfree(sd);
 }
 
@@ -6938,6 +6998,7 @@ int sched_smt_power_savings = 0, sched_mc_power_savings = 0;
 struct sd_data {
 	struct sched_domain **__percpu sd;
 	struct sched_group **__percpu sg;
+	struct sched_group_power **__percpu sgp;
 };
 
 struct s_data {
@@ -6957,15 +7018,73 @@ struct sched_domain_topology_level;
 typedef struct sched_domain *(*sched_domain_init_f)(struct sched_domain_topology_level *tl, int cpu);
 typedef const struct cpumask *(*sched_domain_mask_f)(int cpu);
 
+#define SDTL_OVERLAP	0x01
+
 struct sched_domain_topology_level {
 	sched_domain_init_f init;
 	sched_domain_mask_f mask;
+	int		    flags;
 	struct sd_data      data;
 };
 
-/*
- * Assumes the sched_domain tree is fully constructed
- */
+static int
+build_overlap_sched_groups(struct sched_domain *sd, int cpu)
+{
+	struct sched_group *first = NULL, *last = NULL, *groups = NULL, *sg;
+	const struct cpumask *span = sched_domain_span(sd);
+	struct cpumask *covered = sched_domains_tmpmask;
+	struct sd_data *sdd = sd->private;
+	struct sched_domain *child;
+	int i;
+
+	cpumask_clear(covered);
+
+	for_each_cpu(i, span) {
+		struct cpumask *sg_span;
+
+		if (cpumask_test_cpu(i, covered))
+			continue;
+
+		sg = kzalloc_node(sizeof(struct sched_group) + cpumask_size(),
+				GFP_KERNEL, cpu_to_node(i));
+
+		if (!sg)
+			goto fail;
+
+		sg_span = sched_group_cpus(sg);
+
+		child = *per_cpu_ptr(sdd->sd, i);
+		if (child->child) {
+			child = child->child;
+			cpumask_copy(sg_span, sched_domain_span(child));
+		} else
+			cpumask_set_cpu(i, sg_span);
+
+		cpumask_or(covered, covered, sg_span);
+
+		sg->sgp = *per_cpu_ptr(sdd->sgp, cpumask_first(sg_span));
+		atomic_inc(&sg->sgp->ref);
+
+		if (cpumask_test_cpu(cpu, sg_span))
+			groups = sg;
+
+		if (!first)
+			first = sg;
+		if (last)
+			last->next = sg;
+		last = sg;
+		last->next = first;
+	}
+	sd->groups = groups;
+
+	return 0;
+
+fail:
+	free_sched_groups(first, 0);
+
+	return -ENOMEM;
+}
+
 static int get_group(int cpu, struct sd_data *sdd, struct sched_group **sg)
 {
 	struct sched_domain *sd = *per_cpu_ptr(sdd->sd, cpu);
@@ -6974,24 +7093,24 @@ static int get_group(int cpu, struct sd_data *sdd, struct sched_group **sg)
 	if (child)
 		cpu = cpumask_first(sched_domain_span(child));
 
-	if (sg)
+	if (sg) {
 		*sg = *per_cpu_ptr(sdd->sg, cpu);
+		(*sg)->sgp = *per_cpu_ptr(sdd->sgp, cpu);
+		atomic_set(&(*sg)->sgp->ref, 1); /* for claim_allocations */
+	}
 
 	return cpu;
 }
 
 /*
- * build_sched_groups takes the cpumask we wish to span, and a pointer
- * to a function which identifies what group(along with sched group) a CPU
- * belongs to. The return value of group_fn must be a >= 0 and < nr_cpu_ids
- * (due to the fact that we keep track of groups covered with a struct cpumask).
- *
  * build_sched_groups will build a circular linked list of the groups
  * covered by the given span, and will set each group's ->cpumask correctly,
  * and ->cpu_power to 0.
+ *
+ * Assumes the sched_domain tree is fully constructed
  */
-static void
-build_sched_groups(struct sched_domain *sd)
+static int
+build_sched_groups(struct sched_domain *sd, int cpu)
 {
 	struct sched_group *first = NULL, *last = NULL;
 	struct sd_data *sdd = sd->private;
@@ -6999,6 +7118,12 @@ build_sched_groups(struct sched_domain *sd)
 	struct cpumask *covered;
 	int i;
 
+	get_group(cpu, sdd, &sd->groups);
+	atomic_inc(&sd->groups->ref);
+
+	if (cpu != cpumask_first(sched_domain_span(sd)))
+		return 0;
+
 	lockdep_assert_held(&sched_domains_mutex);
 	covered = sched_domains_tmpmask;
 
@@ -7013,7 +7138,7 @@ build_sched_groups(struct sched_domain *sd)
 			continue;
 
 		cpumask_clear(sched_group_cpus(sg));
-		sg->cpu_power = 0;
+		sg->sgp->power = 0;
 
 		for_each_cpu(j, span) {
 			if (get_group(j, sdd, NULL) != group)
@@ -7030,6 +7155,8 @@ build_sched_groups(struct sched_domain *sd)
 		last = sg;
 	}
 	last->next = first;
+
+	return 0;
 }
 
 /*
@@ -7044,12 +7171,17 @@ build_sched_groups(struct sched_domain *sd)
  */
 static void init_sched_groups_power(int cpu, struct sched_domain *sd)
 {
-	WARN_ON(!sd || !sd->groups);
+	struct sched_group *sg = sd->groups;
 
-	if (cpu != group_first_cpu(sd->groups))
-		return;
+	WARN_ON(!sd || !sg);
+
+	do {
+		sg->group_weight = cpumask_weight(sched_group_cpus(sg));
+		sg = sg->next;
+	} while (sg != sd->groups);
 
-	sd->groups->group_weight = cpumask_weight(sched_group_cpus(sd->groups));
+	if (cpu != group_first_cpu(sg))
+		return;
 
 	update_group_power(sd, cpu);
 }
@@ -7170,15 +7302,15 @@ static enum s_alloc __visit_domain_allocation_hell(struct s_data *d,
 static void claim_allocations(int cpu, struct sched_domain *sd)
 {
 	struct sd_data *sdd = sd->private;
-	struct sched_group *sg = sd->groups;
 
 	WARN_ON_ONCE(*per_cpu_ptr(sdd->sd, cpu) != sd);
 	*per_cpu_ptr(sdd->sd, cpu) = NULL;
 
-	if (cpu == cpumask_first(sched_group_cpus(sg))) {
-		WARN_ON_ONCE(*per_cpu_ptr(sdd->sg, cpu) != sg);
+	if (atomic_read(&(*per_cpu_ptr(sdd->sg, cpu))->ref))
 		*per_cpu_ptr(sdd->sg, cpu) = NULL;
-	}
+
+	if (atomic_read(&(*per_cpu_ptr(sdd->sgp, cpu))->ref))
+		*per_cpu_ptr(sdd->sgp, cpu) = NULL;
 }
 
 #ifdef CONFIG_SCHED_SMT
@@ -7203,7 +7335,7 @@ static struct sched_domain_topology_level default_topology[] = {
 #endif
 	{ sd_init_CPU, cpu_cpu_mask, },
 #ifdef CONFIG_NUMA
-	{ sd_init_NODE, cpu_node_mask, },
+	{ sd_init_NODE, cpu_node_mask, SDTL_OVERLAP, },
 	{ sd_init_ALLNODES, cpu_allnodes_mask, },
 #endif
 	{ NULL, },
@@ -7227,9 +7359,14 @@ static int __sdt_alloc(const struct cpumask *cpu_map)
 		if (!sdd->sg)
 			return -ENOMEM;
 
+		sdd->sgp = alloc_percpu(struct sched_group_power *);
+		if (!sdd->sgp)
+			return -ENOMEM;
+
 		for_each_cpu(j, cpu_map) {
 			struct sched_domain *sd;
 			struct sched_group *sg;
+			struct sched_group_power *sgp;
 
 		       	sd = kzalloc_node(sizeof(struct sched_domain) + cpumask_size(),
 					GFP_KERNEL, cpu_to_node(j));
@@ -7244,6 +7381,13 @@ static int __sdt_alloc(const struct cpumask *cpu_map)
 				return -ENOMEM;
 
 			*per_cpu_ptr(sdd->sg, j) = sg;
+
+			sgp = kzalloc_node(sizeof(struct sched_group_power),
+					GFP_KERNEL, cpu_to_node(j));
+			if (!sgp)
+				return -ENOMEM;
+
+			*per_cpu_ptr(sdd->sgp, j) = sgp;
 		}
 	}
 
@@ -7259,11 +7403,15 @@ static void __sdt_free(const struct cpumask *cpu_map)
 		struct sd_data *sdd = &tl->data;
 
 		for_each_cpu(j, cpu_map) {
-			kfree(*per_cpu_ptr(sdd->sd, j));
+			struct sched_domain *sd = *per_cpu_ptr(sdd->sd, j);
+			if (sd && (sd->flags & SD_OVERLAP))
+				free_sched_groups(sd->groups, 0);
 			kfree(*per_cpu_ptr(sdd->sg, j));
+			kfree(*per_cpu_ptr(sdd->sgp, j));
 		}
 		free_percpu(sdd->sd);
 		free_percpu(sdd->sg);
+		free_percpu(sdd->sgp);
 	}
 }
 
@@ -7309,8 +7457,13 @@ static int build_sched_domains(const struct cpumask *cpu_map,
 		struct sched_domain_topology_level *tl;
 
 		sd = NULL;
-		for (tl = sched_domain_topology; tl->init; tl++)
+		for (tl = sched_domain_topology; tl->init; tl++) {
 			sd = build_sched_domain(tl, &d, cpu_map, attr, sd, i);
+			if (tl->flags & SDTL_OVERLAP || sched_feat(FORCE_SD_OVERLAP))
+				sd->flags |= SD_OVERLAP;
+			if (cpumask_equal(cpu_map, sched_domain_span(sd)))
+				break;
+		}
 
 		while (sd->child)
 			sd = sd->child;
@@ -7322,13 +7475,13 @@ static int build_sched_domains(const struct cpumask *cpu_map,
 	for_each_cpu(i, cpu_map) {
 		for (sd = *per_cpu_ptr(d.sd, i); sd; sd = sd->parent) {
 			sd->span_weight = cpumask_weight(sched_domain_span(sd));
-			get_group(i, sd->private, &sd->groups);
-			atomic_inc(&sd->groups->ref);
-
-			if (i != cpumask_first(sched_domain_span(sd)))
-				continue;
-
-			build_sched_groups(sd);
+			if (sd->flags & SD_OVERLAP) {
+				if (build_overlap_sched_groups(sd, i))
+					goto error;
+			} else {
+				if (build_sched_groups(sd, i))
+					goto error;
+			}
 		}
 	}
 
@@ -7750,6 +7903,9 @@ static void init_cfs_rq(struct cfs_rq *cfs_rq, struct rq *rq)
 #endif
 #endif
 	cfs_rq->min_vruntime = (u64)(-(1LL << 20));
+#ifndef CONFIG_64BIT
+	cfs_rq->min_vruntime_copy = cfs_rq->min_vruntime;
+#endif
 }
 
 static void init_rt_rq(struct rt_rq *rt_rq, struct rq *rq)
@@ -8441,10 +8597,7 @@ int sched_group_set_shares(struct task_group *tg, unsigned long shares)
 	if (!tg->se[0])
 		return -EINVAL;
 
-	if (shares < MIN_SHARES)
-		shares = MIN_SHARES;
-	else if (shares > MAX_SHARES)
-		shares = MAX_SHARES;
+	shares = clamp(shares, scale_load(MIN_SHARES), scale_load(MAX_SHARES));
 
 	mutex_lock(&shares_mutex);
 	if (tg->shares == shares)
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index eb98f77..e7d67a9 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -1583,7 +1583,7 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p,
 		}
 
 		/* Adjust by relative CPU power of the group */
-		avg_load = (avg_load * SCHED_POWER_SCALE) / group->cpu_power;
+		avg_load = (avg_load * SCHED_POWER_SCALE) / group->sgp->power;
 
 		if (local_group) {
 			this_load = avg_load;
@@ -2629,7 +2629,7 @@ static void update_cpu_power(struct sched_domain *sd, int cpu)
 		power >>= SCHED_POWER_SHIFT;
 	}
 
-	sdg->cpu_power_orig = power;
+	sdg->sgp->power_orig = power;
 
 	if (sched_feat(ARCH_POWER))
 		power *= arch_scale_freq_power(sd, cpu);
@@ -2645,7 +2645,7 @@ static void update_cpu_power(struct sched_domain *sd, int cpu)
 		power = 1;
 
 	cpu_rq(cpu)->cpu_power = power;
-	sdg->cpu_power = power;
+	sdg->sgp->power = power;
 }
 
 static void update_group_power(struct sched_domain *sd, int cpu)
@@ -2663,11 +2663,11 @@ static void update_group_power(struct sched_domain *sd, int cpu)
 
 	group = child->groups;
 	do {
-		power += group->cpu_power;
+		power += group->sgp->power;
 		group = group->next;
 	} while (group != child->groups);
 
-	sdg->cpu_power = power;
+	sdg->sgp->power = power;
 }
 
 /*
@@ -2689,7 +2689,7 @@ fix_small_capacity(struct sched_domain *sd, struct sched_group *group)
 	/*
 	 * If ~90% of the cpu_power is still there, we're good.
 	 */
-	if (group->cpu_power * 32 > group->cpu_power_orig * 29)
+	if (group->sgp->power * 32 > group->sgp->power_orig * 29)
 		return 1;
 
 	return 0;
@@ -2769,7 +2769,7 @@ static inline void update_sg_lb_stats(struct sched_domain *sd,
 	}
 
 	/* Adjust by relative CPU power of the group */
-	sgs->avg_load = (sgs->group_load*SCHED_POWER_SCALE) / group->cpu_power;
+	sgs->avg_load = (sgs->group_load*SCHED_POWER_SCALE) / group->sgp->power;
 
 	/*
 	 * Consider the group unbalanced when the imbalance is larger
@@ -2786,7 +2786,7 @@ static inline void update_sg_lb_stats(struct sched_domain *sd,
 	if ((max_cpu_load - min_cpu_load) >= avg_load_per_task && max_nr_running > 1)
 		sgs->group_imb = 1;
 
-	sgs->group_capacity = DIV_ROUND_CLOSEST(group->cpu_power,
+	sgs->group_capacity = DIV_ROUND_CLOSEST(group->sgp->power,
 						SCHED_POWER_SCALE);
 	if (!sgs->group_capacity)
 		sgs->group_capacity = fix_small_capacity(sd, group);
@@ -2875,7 +2875,7 @@ static inline void update_sd_lb_stats(struct sched_domain *sd, int this_cpu,
 			return;
 
 		sds->total_load += sgs.group_load;
-		sds->total_pwr += sg->cpu_power;
+		sds->total_pwr += sg->sgp->power;
 
 		/*
 		 * In case the child domain prefers tasks go to siblings
@@ -2960,7 +2960,7 @@ static int check_asym_packing(struct sched_domain *sd,
 	if (this_cpu > busiest_cpu)
 		return 0;
 
-	*imbalance = DIV_ROUND_CLOSEST(sds->max_load * sds->busiest->cpu_power,
+	*imbalance = DIV_ROUND_CLOSEST(sds->max_load * sds->busiest->sgp->power,
 				       SCHED_POWER_SCALE);
 	return 1;
 }
@@ -2991,7 +2991,7 @@ static inline void fix_small_imbalance(struct sd_lb_stats *sds,
 
 	scaled_busy_load_per_task = sds->busiest_load_per_task
 					 * SCHED_POWER_SCALE;
-	scaled_busy_load_per_task /= sds->busiest->cpu_power;
+	scaled_busy_load_per_task /= sds->busiest->sgp->power;
 
 	if (sds->max_load - sds->this_load + scaled_busy_load_per_task >=
 			(scaled_busy_load_per_task * imbn)) {
@@ -3005,28 +3005,28 @@ static inline void fix_small_imbalance(struct sd_lb_stats *sds,
 	 * moving them.
 	 */
 
-	pwr_now += sds->busiest->cpu_power *
+	pwr_now += sds->busiest->sgp->power *
 			min(sds->busiest_load_per_task, sds->max_load);
-	pwr_now += sds->this->cpu_power *
+	pwr_now += sds->this->sgp->power *
 			min(sds->this_load_per_task, sds->this_load);
 	pwr_now /= SCHED_POWER_SCALE;
 
 	/* Amount of load we'd subtract */
 	tmp = (sds->busiest_load_per_task * SCHED_POWER_SCALE) /
-		sds->busiest->cpu_power;
+		sds->busiest->sgp->power;
 	if (sds->max_load > tmp)
-		pwr_move += sds->busiest->cpu_power *
+		pwr_move += sds->busiest->sgp->power *
 			min(sds->busiest_load_per_task, sds->max_load - tmp);
 
 	/* Amount of load we'd add */
-	if (sds->max_load * sds->busiest->cpu_power <
+	if (sds->max_load * sds->busiest->sgp->power <
 		sds->busiest_load_per_task * SCHED_POWER_SCALE)
-		tmp = (sds->max_load * sds->busiest->cpu_power) /
-			sds->this->cpu_power;
+		tmp = (sds->max_load * sds->busiest->sgp->power) /
+			sds->this->sgp->power;
 	else
 		tmp = (sds->busiest_load_per_task * SCHED_POWER_SCALE) /
-			sds->this->cpu_power;
-	pwr_move += sds->this->cpu_power *
+			sds->this->sgp->power;
+	pwr_move += sds->this->sgp->power *
 			min(sds->this_load_per_task, sds->this_load + tmp);
 	pwr_move /= SCHED_POWER_SCALE;
 
@@ -3072,7 +3072,7 @@ static inline void calculate_imbalance(struct sd_lb_stats *sds, int this_cpu,
 
 		load_above_capacity *= (SCHED_LOAD_SCALE * SCHED_POWER_SCALE);
 
-		load_above_capacity /= sds->busiest->cpu_power;
+		load_above_capacity /= sds->busiest->sgp->power;
 	}
 
 	/*
@@ -3088,8 +3088,8 @@ static inline void calculate_imbalance(struct sd_lb_stats *sds, int this_cpu,
 	max_pull = min(sds->max_load - sds->avg_load, load_above_capacity);
 
 	/* How much load to actually move to equalise the imbalance */
-	*imbalance = min(max_pull * sds->busiest->cpu_power,
-		(sds->avg_load - sds->this_load) * sds->this->cpu_power)
+	*imbalance = min(max_pull * sds->busiest->sgp->power,
+		(sds->avg_load - sds->this_load) * sds->this->sgp->power)
 			/ SCHED_POWER_SCALE;
 
 	/*
diff --git a/kernel/sched_features.h b/kernel/sched_features.h
index be40f73..1e7066d 100644
--- a/kernel/sched_features.h
+++ b/kernel/sched_features.h
@@ -70,3 +70,5 @@ SCHED_FEAT(NONIRQ_POWER, 1)
  * using the scheduler IPI. Reduces rq->lock contention/bounces.
  */
 SCHED_FEAT(TTWU_QUEUE, 1)
+
+SCHED_FEAT(FORCE_SD_OVERLAP, 0)
diff --git a/kernel/signal.c b/kernel/signal.c
index ff76786..415d85d 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -1178,18 +1178,25 @@ struct sighand_struct *__lock_task_sighand(struct task_struct *tsk,
 {
 	struct sighand_struct *sighand;
 
-	rcu_read_lock();
 	for (;;) {
+		local_irq_save(*flags);
+		rcu_read_lock();
 		sighand = rcu_dereference(tsk->sighand);
-		if (unlikely(sighand == NULL))
+		if (unlikely(sighand == NULL)) {
+			rcu_read_unlock();
+			local_irq_restore(*flags);
 			break;
+		}
 
-		spin_lock_irqsave(&sighand->siglock, *flags);
-		if (likely(sighand == tsk->sighand))
+		spin_lock(&sighand->siglock);
+		if (likely(sighand == tsk->sighand)) {
+			rcu_read_unlock();
 			break;
-		spin_unlock_irqrestore(&sighand->siglock, *flags);
+		}
+		spin_unlock(&sighand->siglock);
+		rcu_read_unlock();
+		local_irq_restore(*flags);
 	}
-	rcu_read_unlock();
 
 	return sighand;
 }
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 40cf63d..fca82c3 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -315,16 +315,24 @@ static inline void invoke_softirq(void)
 {
 	if (!force_irqthreads)
 		__do_softirq();
-	else
+	else {
+		__local_bh_disable((unsigned long)__builtin_return_address(0),
+				SOFTIRQ_OFFSET);
 		wakeup_softirqd();
+		__local_bh_enable(SOFTIRQ_OFFSET);
+	}
 }
 #else
 static inline void invoke_softirq(void)
 {
 	if (!force_irqthreads)
 		do_softirq();
-	else
+	else {
+		__local_bh_disable((unsigned long)__builtin_return_address(0),
+				SOFTIRQ_OFFSET);
 		wakeup_softirqd();
+		__local_bh_enable(SOFTIRQ_OFFSET);
+	}
 }
 #endif