15 files changed, 389 insertions, 168 deletions

diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 0f3527d6184a..72fcd3069a90 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -896,10 +896,13 @@ static void cgroup_diput(struct dentry *dentry, struct inode *inode)
 		mutex_unlock(&cgroup_mutex);
 
 		/*
-		 * Drop the active superblock reference that we took when we
-		 * created the cgroup
+		 * We want to drop the active superblock reference from the
+		 * cgroup creation after all the dentry refs are gone -
+		 * kill_sb gets mighty unhappy otherwise.  Mark
+		 * dentry->d_fsdata with cgroup_diput() to tell
+		 * cgroup_d_release() to call deactivate_super().
 		 */
-		deactivate_super(cgrp->root->sb);
+		dentry->d_fsdata = cgroup_diput;
 
 		/*
 		 * if we're getting rid of the cgroup, refcount should ensure
@@ -925,6 +928,13 @@ static int cgroup_delete(const struct dentry *d)
 	return 1;
 }
 
+static void cgroup_d_release(struct dentry *dentry)
+{
+	/* did cgroup_diput() tell me to deactivate super? */
+	if (dentry->d_fsdata == cgroup_diput)
+		deactivate_super(dentry->d_sb);
+}
+
 static void remove_dir(struct dentry *d)
 {
 	struct dentry *parent = dget(d->d_parent);
@@ -1532,6 +1542,7 @@ static int cgroup_get_rootdir(struct super_block *sb)
 	static const struct dentry_operations cgroup_dops = {
 		.d_iput = cgroup_diput,
 		.d_delete = cgroup_delete,
+		.d_release = cgroup_d_release,
 	};
 
 	struct inode *inode =
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 5b06cbbf6931..f85c0154b333 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -3181,7 +3181,6 @@ static void perf_event_for_each(struct perf_event *event,
 	event = event->group_leader;
 
 	perf_event_for_each_child(event, func);
-	func(event);
 	list_for_each_entry(sibling, &event->sibling_list, group_entry)
 		perf_event_for_each_child(sibling, func);
 	mutex_unlock(&ctx->mutex);
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index fc275e4f629b..eebd6d5cfb44 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -275,8 +275,10 @@ void handle_nested_irq(unsigned int irq)
 	kstat_incr_irqs_this_cpu(irq, desc);
 
 	action = desc->action;
-	if (unlikely(!action || irqd_irq_disabled(&desc->irq_data)))
+	if (unlikely(!action || irqd_irq_disabled(&desc->irq_data))) {
+		desc->istate |= IRQS_PENDING;
 		goto out_unlock;
+	}
 
 	irqd_set(&desc->irq_data, IRQD_IRQ_INPROGRESS);
 	raw_spin_unlock_irq(&desc->lock);
@@ -324,8 +326,10 @@ handle_simple_irq(unsigned int irq, struct irq_desc *desc)
 	desc->istate &= ~(IRQS_REPLAY | IRQS_WAITING);
 	kstat_incr_irqs_this_cpu(irq, desc);
 
-	if (unlikely(!desc->action || irqd_irq_disabled(&desc->irq_data)))
+	if (unlikely(!desc->action || irqd_irq_disabled(&desc->irq_data))) {
+		desc->istate |= IRQS_PENDING;
 		goto out_unlock;
+	}
 
 	handle_irq_event(desc);
 
diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h
index 8e5c56b3b7d9..001fa5bab490 100644
--- a/kernel/irq/internals.h
+++ b/kernel/irq/internals.h
@@ -101,6 +101,9 @@ extern int irq_select_affinity_usr(unsigned int irq, struct cpumask *mask);
 
 extern void irq_set_thread_affinity(struct irq_desc *desc);
 
+extern int irq_do_set_affinity(struct irq_data *data,
+			       const struct cpumask *dest, bool force);
+
 /* Inline functions for support of irq chips on slow busses */
 static inline void chip_bus_lock(struct irq_desc *desc)
 {
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index ea0c6c2ae6f7..8c548232ba39 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -142,6 +142,25 @@ static inline void
 irq_get_pending(struct cpumask *mask, struct irq_desc *desc) { }
 #endif
 
+int irq_do_set_affinity(struct irq_data *data, const struct cpumask *mask,
+			bool force)
+{
+	struct irq_desc *desc = irq_data_to_desc(data);
+	struct irq_chip *chip = irq_data_get_irq_chip(data);
+	int ret;
+
+	ret = chip->irq_set_affinity(data, mask, false);
+	switch (ret) {
+	case IRQ_SET_MASK_OK:
+		cpumask_copy(data->affinity, mask);
+	case IRQ_SET_MASK_OK_NOCOPY:
+		irq_set_thread_affinity(desc);
+		ret = 0;
+	}
+
+	return ret;
+}
+
 int __irq_set_affinity_locked(struct irq_data *data, const struct cpumask *mask)
 {
 	struct irq_chip *chip = irq_data_get_irq_chip(data);
@@ -152,14 +171,7 @@ int __irq_set_affinity_locked(struct irq_data *data, const struct cpumask *mask)
 		return -EINVAL;
 
 	if (irq_can_move_pcntxt(data)) {
-		ret = chip->irq_set_affinity(data, mask, false);
-		switch (ret) {
-		case IRQ_SET_MASK_OK:
-			cpumask_copy(data->affinity, mask);
-		case IRQ_SET_MASK_OK_NOCOPY:
-			irq_set_thread_affinity(desc);
-			ret = 0;
-		}
+		ret = irq_do_set_affinity(data, mask, false);
 	} else {
 		irqd_set_move_pending(data);
 		irq_copy_pending(desc, mask);
@@ -283,9 +295,8 @@ EXPORT_SYMBOL_GPL(irq_set_affinity_notifier);
 static int
 setup_affinity(unsigned int irq, struct irq_desc *desc, struct cpumask *mask)
 {
-	struct irq_chip *chip = irq_desc_get_chip(desc);
 	struct cpumask *set = irq_default_affinity;
-	int ret, node = desc->irq_data.node;
+	int node = desc->irq_data.node;
 
 	/* Excludes PER_CPU and NO_BALANCE interrupts */
 	if (!irq_can_set_affinity(irq))
@@ -311,13 +322,7 @@ setup_affinity(unsigned int irq, struct irq_desc *desc, struct cpumask *mask)
 		if (cpumask_intersects(mask, nodemask))
 			cpumask_and(mask, mask, nodemask);
 	}
-	ret = chip->irq_set_affinity(&desc->irq_data, mask, false);
-	switch (ret) {
-	case IRQ_SET_MASK_OK:
-		cpumask_copy(desc->irq_data.affinity, mask);
-	case IRQ_SET_MASK_OK_NOCOPY:
-		irq_set_thread_affinity(desc);
-	}
+	irq_do_set_affinity(&desc->irq_data, mask, false);
 	return 0;
 }
 #else
diff --git a/kernel/irq/migration.c b/kernel/irq/migration.c
index c3c89751b327..ca3f4aaff707 100644
--- a/kernel/irq/migration.c
+++ b/kernel/irq/migration.c
@@ -42,17 +42,8 @@ void irq_move_masked_irq(struct irq_data *idata)
 	 * For correct operation this depends on the caller
 	 * masking the irqs.
 	 */
-	if (likely(cpumask_any_and(desc->pending_mask, cpu_online_mask)
-		   < nr_cpu_ids)) {
-		int ret = chip->irq_set_affinity(&desc->irq_data,
-						 desc->pending_mask, false);
-		switch (ret) {
-		case IRQ_SET_MASK_OK:
-			cpumask_copy(desc->irq_data.affinity, desc->pending_mask);
-		case IRQ_SET_MASK_OK_NOCOPY:
-			irq_set_thread_affinity(desc);
-		}
-	}
+	if (cpumask_any_and(desc->pending_mask, cpu_online_mask) < nr_cpu_ids)
+		irq_do_set_affinity(&desc->irq_data, desc->pending_mask, false);
 
 	cpumask_clear(desc->pending_mask);
 }
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 39eb6011bc38..d5594a4268d4 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -142,9 +142,8 @@ const_debug unsigned int sysctl_sched_features =
 #define SCHED_FEAT(name, enabled)	\
 	#name ,
 
-static __read_mostly char *sched_feat_names[] = {
+static const char * const sched_feat_names[] = {
 #include "features.h"
-	NULL
 };
 
 #undef SCHED_FEAT
@@ -2517,25 +2516,32 @@ static void __update_cpu_load(struct rq *this_rq, unsigned long this_load,
 	sched_avg_update(this_rq);
 }
 
+#ifdef CONFIG_NO_HZ
+/*
+ * There is no sane way to deal with nohz on smp when using jiffies because the
+ * cpu doing the jiffies update might drift wrt the cpu doing the jiffy reading
+ * causing off-by-one errors in observed deltas; {0,2} instead of {1,1}.
+ *
+ * Therefore we cannot use the delta approach from the regular tick since that
+ * would seriously skew the load calculation. However we'll make do for those
+ * updates happening while idle (nohz_idle_balance) or coming out of idle
+ * (tick_nohz_idle_exit).
+ *
+ * This means we might still be one tick off for nohz periods.
+ */
+
 /*
  * Called from nohz_idle_balance() to update the load ratings before doing the
  * idle balance.
  */
 void update_idle_cpu_load(struct rq *this_rq)
 {
-	unsigned long curr_jiffies = jiffies;
+	unsigned long curr_jiffies = ACCESS_ONCE(jiffies);
 	unsigned long load = this_rq->load.weight;
 	unsigned long pending_updates;
 
 	/*
-	 * Bloody broken means of dealing with nohz, but better than nothing..
-	 * jiffies is updated by one cpu, another cpu can drift wrt the jiffy
-	 * update and see 0 difference the one time and 2 the next, even though
-	 * we ticked at roughtly the same rate.
-	 *
-	 * Hence we only use this from nohz_idle_balance() and skip this
-	 * nonsense when called from the scheduler_tick() since that's
-	 * guaranteed a stable rate.
+	 * bail if there's load or we're actually up-to-date.
 	 */
 	if (load || curr_jiffies == this_rq->last_load_update_tick)
 		return;
@@ -2547,12 +2553,38 @@ void update_idle_cpu_load(struct rq *this_rq)
 }
 
 /*
+ * Called from tick_nohz_idle_exit() -- try and fix up the ticks we missed.
+ */
+void update_cpu_load_nohz(void)
+{
+	struct rq *this_rq = this_rq();
+	unsigned long curr_jiffies = ACCESS_ONCE(jiffies);
+	unsigned long pending_updates;
+
+	if (curr_jiffies == this_rq->last_load_update_tick)
+		return;
+
+	raw_spin_lock(&this_rq->lock);
+	pending_updates = curr_jiffies - this_rq->last_load_update_tick;
+	if (pending_updates) {
+		this_rq->last_load_update_tick = curr_jiffies;
+		/*
+		 * We were idle, this means load 0, the current load might be
+		 * !0 due to remote wakeups and the sort.
+		 */
+		__update_cpu_load(this_rq, 0, pending_updates);
+	}
+	raw_spin_unlock(&this_rq->lock);
+}
+#endif /* CONFIG_NO_HZ */
+
+/*
  * Called from scheduler_tick()
  */
 static void update_cpu_load_active(struct rq *this_rq)
 {
 	/*
-	 * See the mess in update_idle_cpu_load().
+	 * See the mess around update_idle_cpu_load() / update_cpu_load_nohz().
 	 */
 	this_rq->last_load_update_tick = jiffies;
 	__update_cpu_load(this_rq, this_rq->load.weight, 1);
@@ -4982,7 +5014,7 @@ void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask)
 		p->sched_class->set_cpus_allowed(p, new_mask);
 
 	cpumask_copy(&p->cpus_allowed, new_mask);
-	p->rt.nr_cpus_allowed = cpumask_weight(new_mask);
+	p->nr_cpus_allowed = cpumask_weight(new_mask);
 }
 
 /*
@@ -5524,15 +5556,20 @@ static cpumask_var_t sched_domains_tmpmask; /* sched_domains_mutex */
 
 #ifdef CONFIG_SCHED_DEBUG
 
-static __read_mostly int sched_domain_debug_enabled;
+static __read_mostly int sched_debug_enabled;
 
-static int __init sched_domain_debug_setup(char *str)
+static int __init sched_debug_setup(char *str)
 {
-	sched_domain_debug_enabled = 1;
+	sched_debug_enabled = 1;
 
 	return 0;
 }
-early_param("sched_debug", sched_domain_debug_setup);
+early_param("sched_debug", sched_debug_setup);
+
+static inline bool sched_debug(void)
+{
+	return sched_debug_enabled;
+}
 
 static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level,
 				  struct cpumask *groupmask)
@@ -5572,7 +5609,12 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level,
 			break;
 		}
 
-		if (!group->sgp->power) {
+		/*
+		 * Even though we initialize ->power to something semi-sane,
+		 * we leave power_orig unset. This allows us to detect if
+		 * domain iteration is still funny without causing /0 traps.
+		 */
+		if (!group->sgp->power_orig) {
 			printk(KERN_CONT "\n");
 			printk(KERN_ERR "ERROR: domain->cpu_power not "
 					"set\n");
@@ -5620,7 +5662,7 @@ static void sched_domain_debug(struct sched_domain *sd, int cpu)
 {
 	int level = 0;
 
-	if (!sched_domain_debug_enabled)
+	if (!sched_debug_enabled)
 		return;
 
 	if (!sd) {
@@ -5641,6 +5683,10 @@ static void sched_domain_debug(struct sched_domain *sd, int cpu)
 }
 #else /* !CONFIG_SCHED_DEBUG */
 # define sched_domain_debug(sd, cpu) do { } while (0)
+static inline bool sched_debug(void)
+{
+	return false;
+}
 #endif /* CONFIG_SCHED_DEBUG */
 
 static int sd_degenerate(struct sched_domain *sd)
@@ -5962,6 +6008,44 @@ struct sched_domain_topology_level {
 	struct sd_data      data;
 };
 
+/*
+ * Build an iteration mask that can exclude certain CPUs from the upwards
+ * domain traversal.
+ *
+ * Asymmetric node setups can result in situations where the domain tree is of
+ * unequal depth, make sure to skip domains that already cover the entire
+ * range.
+ *
+ * In that case build_sched_domains() will have terminated the iteration early
+ * and our sibling sd spans will be empty. Domains should always include the
+ * cpu they're built on, so check that.
+ *
+ */
+static void build_group_mask(struct sched_domain *sd, struct sched_group *sg)
+{
+	const struct cpumask *span = sched_domain_span(sd);
+	struct sd_data *sdd = sd->private;
+	struct sched_domain *sibling;
+	int i;
+
+	for_each_cpu(i, span) {
+		sibling = *per_cpu_ptr(sdd->sd, i);
+		if (!cpumask_test_cpu(i, sched_domain_span(sibling)))
+			continue;
+
+		cpumask_set_cpu(i, sched_group_mask(sg));
+	}
+}
+
+/*
+ * Return the canonical balance cpu for this group, this is the first cpu
+ * of this group that's also in the iteration mask.
+ */
+int group_balance_cpu(struct sched_group *sg)
+{
+	return cpumask_first_and(sched_group_cpus(sg), sched_group_mask(sg));
+}
+
 static int
 build_overlap_sched_groups(struct sched_domain *sd, int cpu)
 {
@@ -5980,6 +6064,12 @@ build_overlap_sched_groups(struct sched_domain *sd, int cpu)
 		if (cpumask_test_cpu(i, covered))
 			continue;
 
+		child = *per_cpu_ptr(sdd->sd, i);
+
+		/* See the comment near build_group_mask(). */
+		if (!cpumask_test_cpu(i, sched_domain_span(child)))
+			continue;
+
 		sg = kzalloc_node(sizeof(struct sched_group) + cpumask_size(),
 				GFP_KERNEL, cpu_to_node(cpu));
 
@@ -5987,8 +6077,6 @@ build_overlap_sched_groups(struct sched_domain *sd, int cpu)
 			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));
@@ -5997,10 +6085,24 @@ build_overlap_sched_groups(struct sched_domain *sd, int cpu)
 
 		cpumask_or(covered, covered, sg_span);
 
-		sg->sgp = *per_cpu_ptr(sdd->sgp, cpumask_first(sg_span));
-		atomic_inc(&sg->sgp->ref);
+		sg->sgp = *per_cpu_ptr(sdd->sgp, i);
+		if (atomic_inc_return(&sg->sgp->ref) == 1)
+			build_group_mask(sd, sg);
 
-		if (cpumask_test_cpu(cpu, sg_span))
+		/*
+		 * Initialize sgp->power such that even if we mess up the
+		 * domains and no possible iteration will get us here, we won't
+		 * die on a /0 trap.
+		 */
+		sg->sgp->power = SCHED_POWER_SCALE * cpumask_weight(sg_span);
+
+		/*
+		 * Make sure the first group of this domain contains the
+		 * canonical balance cpu. Otherwise the sched_domain iteration
+		 * breaks. See update_sg_lb_stats().
+		 */
+		if ((!groups && cpumask_test_cpu(cpu, sg_span)) ||
+		    group_balance_cpu(sg) == cpu)
 			groups = sg;
 
 		if (!first)
@@ -6074,6 +6176,7 @@ build_sched_groups(struct sched_domain *sd, int cpu)
 
 		cpumask_clear(sched_group_cpus(sg));
 		sg->sgp->power = 0;
+		cpumask_setall(sched_group_mask(sg));
 
 		for_each_cpu(j, span) {
 			if (get_group(j, sdd, NULL) != group)
@@ -6115,7 +6218,7 @@ static void init_sched_groups_power(int cpu, struct sched_domain *sd)
 		sg = sg->next;
 	} while (sg != sd->groups);
 
-	if (cpu != group_first_cpu(sg))
+	if (cpu != group_balance_cpu(sg))
 		return;
 
 	update_group_power(sd, cpu);
@@ -6165,11 +6268,8 @@ int sched_domain_level_max;
 
 static int __init setup_relax_domain_level(char *str)
 {
-	unsigned long val;
-
-	val = simple_strtoul(str, NULL, 0);
-	if (val < sched_domain_level_max)
-		default_relax_domain_level = val;
+	if (kstrtoint(str, 0, &default_relax_domain_level))
+		pr_warn("Unable to set relax_domain_level\n");
 
 	return 1;
 }
@@ -6279,14 +6379,13 @@ static struct sched_domain_topology_level *sched_domain_topology = default_topol
 #ifdef CONFIG_NUMA
 
 static int sched_domains_numa_levels;
-static int sched_domains_numa_scale;
 static int *sched_domains_numa_distance;
 static struct cpumask ***sched_domains_numa_masks;
 static int sched_domains_curr_level;
 
 static inline int sd_local_flags(int level)
 {
-	if (sched_domains_numa_distance[level] > REMOTE_DISTANCE)
+	if (sched_domains_numa_distance[level] > RECLAIM_DISTANCE)
 		return 0;
 
 	return SD_BALANCE_EXEC | SD_BALANCE_FORK | SD_WAKE_AFFINE;
@@ -6344,6 +6443,42 @@ static const struct cpumask *sd_numa_mask(int cpu)
 	return sched_domains_numa_masks[sched_domains_curr_level][cpu_to_node(cpu)];
 }
 
+static void sched_numa_warn(const char *str)
+{
+	static int done = false;
+	int i,j;
+
+	if (done)
+		return;
+
+	done = true;
+
+	printk(KERN_WARNING "ERROR: %s\n\n", str);
+
+	for (i = 0; i < nr_node_ids; i++) {
+		printk(KERN_WARNING "  ");
+		for (j = 0; j < nr_node_ids; j++)
+			printk(KERN_CONT "%02d ", node_distance(i,j));
+		printk(KERN_CONT "\n");
+	}
+	printk(KERN_WARNING "\n");
+}
+
+static bool find_numa_distance(int distance)
+{
+	int i;
+
+	if (distance == node_distance(0, 0))
+		return true;
+
+	for (i = 0; i < sched_domains_numa_levels; i++) {
+		if (sched_domains_numa_distance[i] == distance)
+			return true;
+	}
+
+	return false;
+}
+
 static void sched_init_numa(void)
 {
 	int next_distance, curr_distance = node_distance(0, 0);
@@ -6351,7 +6486,6 @@ static void sched_init_numa(void)
 	int level = 0;
 	int i, j, k;
 
-	sched_domains_numa_scale = curr_distance;
 	sched_domains_numa_distance = kzalloc(sizeof(int) * nr_node_ids, GFP_KERNEL);
 	if (!sched_domains_numa_distance)
 		return;
@@ -6362,23 +6496,41 @@ static void sched_init_numa(void)
 	 *
 	 * Assumes node_distance(0,j) includes all distances in
 	 * node_distance(i,j) in order to avoid cubic time.
-	 *
-	 * XXX: could be optimized to O(n log n) by using sort()
 	 */
 	next_distance = curr_distance;
 	for (i = 0; i < nr_node_ids; i++) {
 		for (j = 0; j < nr_node_ids; j++) {
-			int distance = node_distance(0, j);
-			if (distance > curr_distance &&
-					(distance < next_distance ||
-					 next_distance == curr_distance))
-				next_distance = distance;
+			for (k = 0; k < nr_node_ids; k++) {
+				int distance = node_distance(i, k);
+
+				if (distance > curr_distance &&
+				    (distance < next_distance ||
+				     next_distance == curr_distance))
+					next_distance = distance;
+
+				/*
+				 * While not a strong assumption it would be nice to know
+				 * about cases where if node A is connected to B, B is not
+				 * equally connected to A.
+				 */
+				if (sched_debug() && node_distance(k, i) != distance)
+					sched_numa_warn("Node-distance not symmetric");
+
+				if (sched_debug() && i && !find_numa_distance(distance))
+					sched_numa_warn("Node-0 not representative");
+			}
+			if (next_distance != curr_distance) {
+				sched_domains_numa_distance[level++] = next_distance;
+				sched_domains_numa_levels = level;
+				curr_distance = next_distance;
+			} else break;
 		}
-		if (next_distance != curr_distance) {
-			sched_domains_numa_distance[level++] = next_distance;
-			sched_domains_numa_levels = level;
-			curr_distance = next_distance;
-		} else break;
+
+		/*
+		 * In case of sched_debug() we verify the above assumption.
+		 */
+		if (!sched_debug())
+			break;
 	}
 	/*
 	 * 'level' contains the number of unique distances, excluding the
@@ -6403,7 +6555,7 @@ static void sched_init_numa(void)
 			return;
 
 		for (j = 0; j < nr_node_ids; j++) {
-			struct cpumask *mask = kzalloc_node(cpumask_size(), GFP_KERNEL, j);
+			struct cpumask *mask = kzalloc(cpumask_size(), GFP_KERNEL);
 			if (!mask)
 				return;
 
@@ -6490,7 +6642,7 @@ static int __sdt_alloc(const struct cpumask *cpu_map)
 
 			*per_cpu_ptr(sdd->sg, j) = sg;
 
-			sgp = kzalloc_node(sizeof(struct sched_group_power),
+			sgp = kzalloc_node(sizeof(struct sched_group_power) + cpumask_size(),
 					GFP_KERNEL, cpu_to_node(j));
 			if (!sgp)
 				return -ENOMEM;
@@ -6543,7 +6695,6 @@ struct sched_domain *build_sched_domain(struct sched_domain_topology_level *tl,
 	if (!sd)
 		return child;
 
-	set_domain_attribute(sd, attr);
 	cpumask_and(sched_domain_span(sd), cpu_map, tl->mask(cpu));
 	if (child) {
 		sd->level = child->level + 1;
@@ -6551,6 +6702,7 @@ struct sched_domain *build_sched_domain(struct sched_domain_topology_level *tl,
 		child->parent = sd;
 	}
 	sd->child = child;
+	set_domain_attribute(sd, attr);
 
 	return sd;
 }
@@ -6691,7 +6843,6 @@ static int init_sched_domains(const struct cpumask *cpu_map)
 	if (!doms_cur)
 		doms_cur = &fallback_doms;
 	cpumask_andnot(doms_cur[0], cpu_map, cpu_isolated_map);
-	dattr_cur = NULL;
 	err = build_sched_domains(doms_cur[0], NULL);
 	register_sched_domain_sysctl();
 
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 940e6d17cf96..c099cc6eebe3 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -2703,7 +2703,7 @@ select_task_rq_fair(struct task_struct *p, int sd_flag, int wake_flags)
 	int want_sd = 1;
 	int sync = wake_flags & WF_SYNC;
 
-	if (p->rt.nr_cpus_allowed == 1)
+	if (p->nr_cpus_allowed == 1)
 		return prev_cpu;
 
 	if (sd_flag & SD_BALANCE_WAKE) {
@@ -3503,15 +3503,22 @@ unsigned long __weak arch_scale_smt_power(struct sched_domain *sd, int cpu)
 unsigned long scale_rt_power(int cpu)
 {
 	struct rq *rq = cpu_rq(cpu);
-	u64 total, available;
+	u64 total, available, age_stamp, avg;
 
-	total = sched_avg_period() + (rq->clock - rq->age_stamp);
+	/*
+	 * Since we're reading these variables without serialization make sure
+	 * we read them once before doing sanity checks on them.
+	 */
+	age_stamp = ACCESS_ONCE(rq->age_stamp);
+	avg = ACCESS_ONCE(rq->rt_avg);
+
+	total = sched_avg_period() + (rq->clock - age_stamp);
 
-	if (unlikely(total < rq->rt_avg)) {
+	if (unlikely(total < avg)) {
 		/* Ensures that power won't end up being negative */
 		available = 0;
 	} else {
-		available = total - rq->rt_avg;
+		available = total - avg;
 	}
 
 	if (unlikely((s64)total < SCHED_POWER_SCALE))
@@ -3574,13 +3581,28 @@ void update_group_power(struct sched_domain *sd, int cpu)
 
 	power = 0;
 
-	group = child->groups;
-	do {
-		power += group->sgp->power;
-		group = group->next;
-	} while (group != child->groups);
+	if (child->flags & SD_OVERLAP) {
+		/*
+		 * SD_OVERLAP domains cannot assume that child groups
+		 * span the current group.
+		 */
 
-	sdg->sgp->power = power;
+		for_each_cpu(cpu, sched_group_cpus(sdg))
+			power += power_of(cpu);
+	} else  {
+		/*
+		 * !SD_OVERLAP domains can assume that child groups
+		 * span the current group.
+		 */ 
+
+		group = child->groups;
+		do {
+			power += group->sgp->power;
+			group = group->next;
+		} while (group != child->groups);
+	}
+
+	sdg->sgp->power_orig = sdg->sgp->power = power;
 }
 
 /*
@@ -3610,7 +3632,7 @@ fix_small_capacity(struct sched_domain *sd, struct sched_group *group)
 
 /**
  * update_sg_lb_stats - Update sched_group's statistics for load balancing.
- * @sd: The sched_domain whose statistics are to be updated.
+ * @env: The load balancing environment.
  * @group: sched_group whose statistics are to be updated.
  * @load_idx: Load index of sched_domain of this_cpu for load calc.
  * @local_group: Does group contain this_cpu.
@@ -3630,7 +3652,7 @@ static inline void update_sg_lb_stats(struct lb_env *env,
 	int i;
 
 	if (local_group)
-		balance_cpu = group_first_cpu(group);
+		balance_cpu = group_balance_cpu(group);
 
 	/* Tally up the load of all CPUs in the group */
 	max_cpu_load = 0;
@@ -3645,7 +3667,8 @@ static inline void update_sg_lb_stats(struct lb_env *env,
 
 		/* Bias balancing toward cpus of our domain */
 		if (local_group) {
-			if (idle_cpu(i) && !first_idle_cpu) {
+			if (idle_cpu(i) && !first_idle_cpu &&
+					cpumask_test_cpu(i, sched_group_mask(group))) {
 				first_idle_cpu = 1;
 				balance_cpu = i;
 			}
@@ -3719,11 +3742,10 @@ static inline void update_sg_lb_stats(struct lb_env *env,
 
 /**
  * update_sd_pick_busiest - return 1 on busiest group
- * @sd: sched_domain whose statistics are to be checked
+ * @env: The load balancing environment.
  * @sds: sched_domain statistics
  * @sg: sched_group candidate to be checked for being the busiest
  * @sgs: sched_group statistics
- * @this_cpu: the current cpu
  *
  * Determine if @sg is a busier group than the previously selected
  * busiest group.
@@ -3761,9 +3783,7 @@ static bool update_sd_pick_busiest(struct lb_env *env,
 
 /**
  * update_sd_lb_stats - Update sched_domain's statistics for load balancing.
- * @sd: sched_domain whose statistics are to be updated.
- * @this_cpu: Cpu for which load balance is currently performed.
- * @idle: Idle status of this_cpu
+ * @env: The load balancing environment.
  * @cpus: Set of cpus considered for load balancing.
  * @balance: Should we balance.
  * @sds: variable to hold the statistics for this sched_domain.
@@ -3852,10 +3872,8 @@ static inline void update_sd_lb_stats(struct lb_env *env,
  * Returns 1 when packing is required and a task should be moved to
  * this CPU.  The amount of the imbalance is returned in *imbalance.
  *
- * @sd: The sched_domain whose packing is to be checked.
+ * @env: The load balancing environment.
  * @sds: Statistics of the sched_domain which is to be packed
- * @this_cpu: The cpu at whose sched_domain we're performing load-balance.
- * @imbalance: returns amount of imbalanced due to packing.
  */
 static int check_asym_packing(struct lb_env *env, struct sd_lb_stats *sds)
 {
@@ -3881,9 +3899,8 @@ static int check_asym_packing(struct lb_env *env, struct sd_lb_stats *sds)
  * fix_small_imbalance - Calculate the minor imbalance that exists
  *			amongst the groups of a sched_domain, during
  *			load balancing.
+ * @env: The load balancing environment.
  * @sds: Statistics of the sched_domain whose imbalance is to be calculated.
- * @this_cpu: The cpu at whose sched_domain we're performing load-balance.
- * @imbalance: Variable to store the imbalance.
  */
 static inline
 void fix_small_imbalance(struct lb_env *env, struct sd_lb_stats *sds)
@@ -4026,11 +4043,7 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s
  * Also calculates the amount of weighted load which should be moved
  * to restore balance.
  *
- * @sd: The sched_domain whose busiest group is to be returned.
- * @this_cpu: The cpu for which load balancing is currently being performed.
- * @imbalance: Variable which stores amount of weighted load which should
- *		be moved to restore balance/put a group to idle.
- * @idle: The idle status of this_cpu.
+ * @env: The load balancing environment.
  * @cpus: The set of CPUs under consideration for load-balancing.
  * @balance: Pointer to a variable indicating if this_cpu
  *	is the appropriate cpu to perform load balancing at this_level.
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index c5565c3c515f..573e1ca01102 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -274,13 +274,16 @@ static void update_rt_migration(struct rt_rq *rt_rq)
 
 static void inc_rt_migration(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
 {
+	struct task_struct *p;
+
 	if (!rt_entity_is_task(rt_se))
 		return;
 
+	p = rt_task_of(rt_se);
 	rt_rq = &rq_of_rt_rq(rt_rq)->rt;
 
 	rt_rq->rt_nr_total++;
-	if (rt_se->nr_cpus_allowed > 1)
+	if (p->nr_cpus_allowed > 1)
 		rt_rq->rt_nr_migratory++;
 
 	update_rt_migration(rt_rq);
@@ -288,13 +291,16 @@ static void inc_rt_migration(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
 
 static void dec_rt_migration(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
 {
+	struct task_struct *p;
+
 	if (!rt_entity_is_task(rt_se))
 		return;
 
+	p = rt_task_of(rt_se);
 	rt_rq = &rq_of_rt_rq(rt_rq)->rt;
 
 	rt_rq->rt_nr_total--;
-	if (rt_se->nr_cpus_allowed > 1)
+	if (p->nr_cpus_allowed > 1)
 		rt_rq->rt_nr_migratory--;
 
 	update_rt_migration(rt_rq);
@@ -1161,7 +1167,7 @@ enqueue_task_rt(struct rq *rq, struct task_struct *p, int flags)
 
 	enqueue_rt_entity(rt_se, flags & ENQUEUE_HEAD);
 
-	if (!task_current(rq, p) && p->rt.nr_cpus_allowed > 1)
+	if (!task_current(rq, p) && p->nr_cpus_allowed > 1)
 		enqueue_pushable_task(rq, p);
 
 	inc_nr_running(rq);
@@ -1225,7 +1231,7 @@ select_task_rq_rt(struct task_struct *p, int sd_flag, int flags)
 
 	cpu = task_cpu(p);
 
-	if (p->rt.nr_cpus_allowed == 1)
+	if (p->nr_cpus_allowed == 1)
 		goto out;
 
 	/* For anything but wake ups, just return the task_cpu */
@@ -1260,9 +1266,9 @@ select_task_rq_rt(struct task_struct *p, int sd_flag, int flags)
 	 * will have to sort it out.
 	 */
 	if (curr && unlikely(rt_task(curr)) &&
-	    (curr->rt.nr_cpus_allowed < 2 ||
+	    (curr->nr_cpus_allowed < 2 ||
 	     curr->prio <= p->prio) &&
-	    (p->rt.nr_cpus_allowed > 1)) {
+	    (p->nr_cpus_allowed > 1)) {
 		int target = find_lowest_rq(p);
 
 		if (target != -1)
@@ -1276,10 +1282,10 @@ out:
 
 static void check_preempt_equal_prio(struct rq *rq, struct task_struct *p)
 {
-	if (rq->curr->rt.nr_cpus_allowed == 1)
+	if (rq->curr->nr_cpus_allowed == 1)
 		return;
 
-	if (p->rt.nr_cpus_allowed != 1
+	if (p->nr_cpus_allowed != 1
 	    && cpupri_find(&rq->rd->cpupri, p, NULL))
 		return;
 
@@ -1395,7 +1401,7 @@ static void put_prev_task_rt(struct rq *rq, struct task_struct *p)
 	 * The previous task needs to be made eligible for pushing
 	 * if it is still active
 	 */
-	if (on_rt_rq(&p->rt) && p->rt.nr_cpus_allowed > 1)
+	if (on_rt_rq(&p->rt) && p->nr_cpus_allowed > 1)
 		enqueue_pushable_task(rq, p);
 }
 
@@ -1408,7 +1414,7 @@ static int pick_rt_task(struct rq *rq, struct task_struct *p, int cpu)
 {
 	if (!task_running(rq, p) &&
 	    (cpu < 0 || cpumask_test_cpu(cpu, tsk_cpus_allowed(p))) &&
-	    (p->rt.nr_cpus_allowed > 1))
+	    (p->nr_cpus_allowed > 1))
 		return 1;
 	return 0;
 }
@@ -1464,7 +1470,7 @@ static int find_lowest_rq(struct task_struct *task)
 	if (unlikely(!lowest_mask))
 		return -1;
 
-	if (task->rt.nr_cpus_allowed == 1)
+	if (task->nr_cpus_allowed == 1)
 		return -1; /* No other targets possible */
 
 	if (!cpupri_find(&task_rq(task)->rd->cpupri, task, lowest_mask))
@@ -1556,7 +1562,7 @@ static struct rq *find_lock_lowest_rq(struct task_struct *task, struct rq *rq)
 				     task_running(rq, task) ||
 				     !task->on_rq)) {
 
-				raw_spin_unlock(&lowest_rq->lock);
+				double_unlock_balance(rq, lowest_rq);
 				lowest_rq = NULL;
 				break;
 			}
@@ -1586,7 +1592,7 @@ static struct task_struct *pick_next_pushable_task(struct rq *rq)
 
 	BUG_ON(rq->cpu != task_cpu(p));
 	BUG_ON(task_current(rq, p));
-	BUG_ON(p->rt.nr_cpus_allowed <= 1);
+	BUG_ON(p->nr_cpus_allowed <= 1);
 
 	BUG_ON(!p->on_rq);
 	BUG_ON(!rt_task(p));
@@ -1793,9 +1799,9 @@ static void task_woken_rt(struct rq *rq, struct task_struct *p)
 	if (!task_running(rq, p) &&
 	    !test_tsk_need_resched(rq->curr) &&
 	    has_pushable_tasks(rq) &&
-	    p->rt.nr_cpus_allowed > 1 &&
+	    p->nr_cpus_allowed > 1 &&
 	    rt_task(rq->curr) &&
-	    (rq->curr->rt.nr_cpus_allowed < 2 ||
+	    (rq->curr->nr_cpus_allowed < 2 ||
 	     rq->curr->prio <= p->prio))
 		push_rt_tasks(rq);
 }
@@ -1817,7 +1823,7 @@ static void set_cpus_allowed_rt(struct task_struct *p,
 	 * Only update if the process changes its state from whether it
 	 * can migrate or not.
 	 */
-	if ((p->rt.nr_cpus_allowed > 1) == (weight > 1))
+	if ((p->nr_cpus_allowed > 1) == (weight > 1))
 		return;
 
 	rq = task_rq(p);
@@ -1979,6 +1985,8 @@ static void watchdog(struct rq *rq, struct task_struct *p)
 
 static void task_tick_rt(struct rq *rq, struct task_struct *p, int queued)
 {
+	struct sched_rt_entity *rt_se = &p->rt;
+
 	update_curr_rt(rq);
 
 	watchdog(rq, p);
@@ -1996,12 +2004,15 @@ static void task_tick_rt(struct rq *rq, struct task_struct *p, int queued)
 	p->rt.time_slice = RR_TIMESLICE;
 
 	/*
-	 * Requeue to the end of queue if we are not the only element
-	 * on the queue:
+	 * Requeue to the end of queue if we (and all of our ancestors) are the
+	 * only element on the queue
 	 */
-	if (p->rt.run_list.prev != p->rt.run_list.next) {
-		requeue_task_rt(rq, p, 0);
-		set_tsk_need_resched(p);
+	for_each_sched_rt_entity(rt_se) {
+		if (rt_se->run_list.prev != rt_se->run_list.next) {
+			requeue_task_rt(rq, p, 0);
+			set_tsk_need_resched(p);
+			return;
+		}
 	}
 }
 
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index ba9dccfd24ce..6d52cea7f33d 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -526,6 +526,8 @@ static inline struct sched_domain *highest_flag_domain(int cpu, int flag)
 DECLARE_PER_CPU(struct sched_domain *, sd_llc);
 DECLARE_PER_CPU(int, sd_llc_id);
 
+extern int group_balance_cpu(struct sched_group *sg);
+
 #endif /* CONFIG_SMP */
 
 #include "stats.h"
diff --git a/kernel/smpboot.c b/kernel/smpboot.c
index e1a797e028a3..98f60c5caa1b 100644
--- a/kernel/smpboot.c
+++ b/kernel/smpboot.c
@@ -31,6 +31,12 @@ void __init idle_thread_set_boot_cpu(void)
 	per_cpu(idle_threads, smp_processor_id()) = current;
 }
 
+/**
+ * idle_init - Initialize the idle thread for a cpu
+ * @cpu:	The cpu for which the idle thread should be initialized
+ *
+ * Creates the thread if it does not exist.
+ */
 static inline void idle_init(unsigned int cpu)
 {
 	struct task_struct *tsk = per_cpu(idle_threads, cpu);
@@ -45,17 +51,16 @@ static inline void idle_init(unsigned int cpu)
 }
 
 /**
- * idle_thread_init - Initialize the idle thread for a cpu
- * @cpu:	The cpu for which the idle thread should be initialized
- *
- * Creates the thread if it does not exist.
+ * idle_threads_init - Initialize idle threads for all cpus
  */
 void __init idle_threads_init(void)
 {
-	unsigned int cpu;
+	unsigned int cpu, boot_cpu;
+
+	boot_cpu = smp_processor_id();
 
 	for_each_possible_cpu(cpu) {
-		if (cpu != smp_processor_id())
+		if (cpu != boot_cpu)
 			idle_init(cpu);
 	}
 }
diff --git a/kernel/sys.c b/kernel/sys.c
index 9ff89cb9657a..f0ec44dcd415 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -1786,27 +1786,13 @@ SYSCALL_DEFINE1(umask, int, mask)
 }
 
 #ifdef CONFIG_CHECKPOINT_RESTORE
-static bool vma_flags_mismatch(struct vm_area_struct *vma,
-			       unsigned long required,
-			       unsigned long banned)
-{
-	return (vma->vm_flags & required) != required ||
-		(vma->vm_flags & banned);
-}
-
 static int prctl_set_mm_exe_file(struct mm_struct *mm, unsigned int fd)
 {
+	struct vm_area_struct *vma;
 	struct file *exe_file;
 	struct dentry *dentry;
 	int err;
 
-	/*
-	 * Setting new mm::exe_file is only allowed when no VM_EXECUTABLE vma's
-	 * remain. So perform a quick test first.
-	 */
-	if (mm->num_exe_file_vmas)
-		return -EBUSY;
-
 	exe_file = fget(fd);
 	if (!exe_file)
 		return -EBADF;
@@ -1827,17 +1813,30 @@ static int prctl_set_mm_exe_file(struct mm_struct *mm, unsigned int fd)
 	if (err)
 		goto exit;
 
+	down_write(&mm->mmap_sem);
+
+	/*
+	 * Forbid mm->exe_file change if there are mapped other files.
+	 */
+	err = -EBUSY;
+	for (vma = mm->mmap; vma; vma = vma->vm_next) {
+		if (vma->vm_file && !path_equal(&vma->vm_file->f_path,
+						&exe_file->f_path))
+			goto exit_unlock;
+	}
+
 	/*
 	 * The symlink can be changed only once, just to disallow arbitrary
 	 * transitions malicious software might bring in. This means one
 	 * could make a snapshot over all processes running and monitor
 	 * /proc/pid/exe changes to notice unusual activity if needed.
 	 */
-	down_write(&mm->mmap_sem);
-	if (likely(!mm->exe_file))
-		set_mm_exe_file(mm, exe_file);
-	else
-		err = -EBUSY;
+	err = -EPERM;
+	if (test_and_set_bit(MMF_EXE_FILE_CHANGED, &mm->flags))
+		goto exit_unlock;
+
+	set_mm_exe_file(mm, exe_file);
+exit_unlock:
 	up_write(&mm->mmap_sem);
 
 exit:
@@ -1862,7 +1861,7 @@ static int prctl_set_mm(int opt, unsigned long addr,
 	if (opt == PR_SET_MM_EXE_FILE)
 		return prctl_set_mm_exe_file(mm, (unsigned int)addr);
 
-	if (addr >= TASK_SIZE)
+	if (addr >= TASK_SIZE || addr < mmap_min_addr)
 		return -EINVAL;
 
 	error = -EINVAL;
@@ -1924,12 +1923,6 @@ static int prctl_set_mm(int opt, unsigned long addr,
 			error = -EFAULT;
 			goto out;
 		}
-#ifdef CONFIG_STACK_GROWSUP
-		if (vma_flags_mismatch(vma, VM_READ | VM_WRITE | VM_GROWSUP, 0))
-#else
-		if (vma_flags_mismatch(vma, VM_READ | VM_WRITE | VM_GROWSDOWN, 0))
-#endif
-			goto out;
 		if (opt == PR_SET_MM_START_STACK)
 			mm->start_stack = addr;
 		else if (opt == PR_SET_MM_ARG_START)
@@ -1981,12 +1974,22 @@ out:
 	up_read(&mm->mmap_sem);
 	return error;
 }
+
+static int prctl_get_tid_address(struct task_struct *me, int __user **tid_addr)
+{
+	return put_user(me->clear_child_tid, tid_addr);
+}
+
 #else /* CONFIG_CHECKPOINT_RESTORE */
 static int prctl_set_mm(int opt, unsigned long addr,
 			unsigned long arg4, unsigned long arg5)
 {
 	return -EINVAL;
 }
+static int prctl_get_tid_address(struct task_struct *me, int __user **tid_addr)
+{
+	return -EINVAL;
+}
 #endif
 
 SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
@@ -2124,6 +2127,9 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
 				else
 					return -EINVAL;
 				break;
+		case PR_GET_TID_ADDRESS:
+			error = prctl_get_tid_address(me, (int __user **)arg2);
+			break;
 			default:
 				return -EINVAL;
 			}
diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c
index 9cd928f7a7c6..7e1ce012a851 100644
--- a/kernel/time/clockevents.c
+++ b/kernel/time/clockevents.c
@@ -297,8 +297,7 @@ void clockevents_register_device(struct clock_event_device *dev)
 }
 EXPORT_SYMBOL_GPL(clockevents_register_device);
 
-static void clockevents_config(struct clock_event_device *dev,
-			       u32 freq)
+void clockevents_config(struct clock_event_device *dev, u32 freq)
 {
 	u64 sec;
 
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 6a3a5b9ff561..da70c6db496c 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -576,6 +576,7 @@ void tick_nohz_idle_exit(void)
 	/* Update jiffies first */
 	select_nohz_load_balancer(0);
 	tick_do_update_jiffies64(now);
+	update_cpu_load_nohz();
 
 #ifndef CONFIG_VIRT_CPU_ACCOUNTING
 	/*
@@ -814,6 +815,16 @@ static enum hrtimer_restart tick_sched_timer(struct hrtimer *timer)
 	return HRTIMER_RESTART;
 }
 
+static int sched_skew_tick;
+
+static int __init skew_tick(char *str)
+{
+	get_option(&str, &sched_skew_tick);
+
+	return 0;
+}
+early_param("skew_tick", skew_tick);
+
 /**
  * tick_setup_sched_timer - setup the tick emulation timer
  */
@@ -831,6 +842,14 @@ void tick_setup_sched_timer(void)
 	/* Get the next period (per cpu) */
 	hrtimer_set_expires(&ts->sched_timer, tick_init_jiffy_update());
 
+	/* Offset the tick to avert xtime_lock contention. */
+	if (sched_skew_tick) {
+		u64 offset = ktime_to_ns(tick_period) >> 1;
+		do_div(offset, num_possible_cpus());
+		offset *= smp_processor_id();
+		hrtimer_add_expires_ns(&ts->sched_timer, offset);
+	}
+
 	for (;;) {
 		hrtimer_forward(&ts->sched_timer, now, tick_period);
 		hrtimer_start_expires(&ts->sched_timer,
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 6e46cacf5969..6f46a00a1e8a 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -962,6 +962,7 @@ static cycle_t logarithmic_accumulation(cycle_t offset, int shift)
 		timekeeper.xtime.tv_sec++;
 		leap = second_overflow(timekeeper.xtime.tv_sec);
 		timekeeper.xtime.tv_sec += leap;
+		timekeeper.wall_to_monotonic.tv_sec -= leap;
 	}
 
 	/* Accumulate raw time */
@@ -1077,6 +1078,7 @@ static void update_wall_time(void)
 		timekeeper.xtime.tv_sec++;
 		leap = second_overflow(timekeeper.xtime.tv_sec);
 		timekeeper.xtime.tv_sec += leap;
+		timekeeper.wall_to_monotonic.tv_sec -= leap;
 	}
 
 	timekeeping_update(false);