Merge branch 'nohz-for-tip-2' of git://github.com/fweisbec/linux-dynticks into timers/core

9 files changed, 310 insertions, 167 deletions

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/sched/core.c b/kernel/sched/core.c
index c46958e26121..d5594a4268d4 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -5556,15 +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)
@@ -5604,7 +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");
@@ -5652,7 +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) {
@@ -5673,6 +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)
@@ -5994,6 +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)
 {
@@ -6012,6 +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));
 
@@ -6019,8 +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));
@@ -6030,13 +6086,24 @@ build_overlap_sched_groups(struct sched_domain *sd, int cpu)
 		cpumask_or(covered, covered, sg_span);
 
 		sg->sgp = *per_cpu_ptr(sdd->sgp, i);
-		atomic_inc(&sg->sgp->ref);
+		if (atomic_inc_return(&sg->sgp->ref) == 1)
+			build_group_mask(sd, sg);
 
+		/*
+		 * 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)) ||
-			       cpumask_first(sg_span) == cpu) {
-			WARN_ON_ONCE(!cpumask_test_cpu(cpu, sg_span));
+		    group_balance_cpu(sg) == cpu)
 			groups = sg;
-		}
 
 		if (!first)
 			first = sg;
@@ -6109,6 +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)
@@ -6150,7 +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);
@@ -6200,11 +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;
 }
@@ -6314,14 +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;
@@ -6379,6 +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);
@@ -6386,7 +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;
@@ -6397,23 +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
@@ -6525,7 +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;
@@ -6578,7 +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;
@@ -6586,6 +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;
 }
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index b2a2d236f27b..c099cc6eebe3 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -3602,7 +3602,7 @@ void update_group_power(struct sched_domain *sd, int cpu)
 		} while (group != child->groups);
 	}
 
-	sdg->sgp->power = power;
+	sdg->sgp->power_orig = sdg->sgp->power = power;
 }
 
 /*
@@ -3632,7 +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.
@@ -3652,7 +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;
@@ -3667,7 +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;
 			}
@@ -3741,11 +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.
@@ -3783,9 +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.
@@ -3874,10 +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)
 {
@@ -3903,9 +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)
@@ -4048,11 +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 2a4e8dffbd6b..573e1ca01102 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -1562,7 +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;
 			}
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/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/tick-sched.c b/kernel/time/tick-sched.c
index da70c6db496c..60c9c60e9108 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -271,49 +271,15 @@ u64 get_cpu_iowait_time_us(int cpu, u64 *last_update_time)
 }
 EXPORT_SYMBOL_GPL(get_cpu_iowait_time_us);
 
-static void tick_nohz_stop_sched_tick(struct tick_sched *ts)
+static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts,
+					 ktime_t now, int cpu)
 {
 	unsigned long seq, last_jiffies, next_jiffies, delta_jiffies;
-	ktime_t last_update, expires, now;
+	ktime_t last_update, expires, ret = { .tv64 = 0 };
 	struct clock_event_device *dev = __get_cpu_var(tick_cpu_device).evtdev;
 	u64 time_delta;
-	int cpu;
-
-	cpu = smp_processor_id();
-	ts = &per_cpu(tick_cpu_sched, cpu);
-
-	now = tick_nohz_start_idle(cpu, ts);
-
-	/*
-	 * If this cpu is offline and it is the one which updates
-	 * jiffies, then give up the assignment and let it be taken by
-	 * the cpu which runs the tick timer next. If we don't drop
-	 * this here the jiffies might be stale and do_timer() never
-	 * invoked.
-	 */
-	if (unlikely(!cpu_online(cpu))) {
-		if (cpu == tick_do_timer_cpu)
-			tick_do_timer_cpu = TICK_DO_TIMER_NONE;
-	}
-
-	if (unlikely(ts->nohz_mode == NOHZ_MODE_INACTIVE))
-		return;
 
-	if (need_resched())
-		return;
-
-	if (unlikely(local_softirq_pending() && cpu_online(cpu))) {
-		static int ratelimit;
-
-		if (ratelimit < 10) {
-			printk(KERN_ERR "NOHZ: local_softirq_pending %02x\n",
-			       (unsigned int) local_softirq_pending());
-			ratelimit++;
-		}
-		return;
-	}
 
-	ts->idle_calls++;
 	/* Read jiffies and the time when jiffies were updated last */
 	do {
 		seq = read_seqbegin(&xtime_lock);
@@ -392,6 +358,8 @@ static void tick_nohz_stop_sched_tick(struct tick_sched *ts)
 		if (ts->tick_stopped && ktime_equal(expires, dev->next_event))
 			goto out;
 
+		ret = expires;
+
 		/*
 		 * nohz_stop_sched_tick can be called several times before
 		 * the nohz_restart_sched_tick is called. This happens when
@@ -402,16 +370,10 @@ static void tick_nohz_stop_sched_tick(struct tick_sched *ts)
 		if (!ts->tick_stopped) {
 			select_nohz_load_balancer(1);
 
-			ts->idle_tick = hrtimer_get_expires(&ts->sched_timer);
+			ts->last_tick = hrtimer_get_expires(&ts->sched_timer);
 			ts->tick_stopped = 1;
-			ts->idle_jiffies = last_jiffies;
 		}
 
-		ts->idle_sleeps++;
-
-		/* Mark expires */
-		ts->idle_expires = expires;
-
 		/*
 		 * If the expiration time == KTIME_MAX, then
 		 * in this case we simply stop the tick timer.
@@ -442,6 +404,65 @@ out:
 	ts->next_jiffies = next_jiffies;
 	ts->last_jiffies = last_jiffies;
 	ts->sleep_length = ktime_sub(dev->next_event, now);
+
+	return ret;
+}
+
+static bool can_stop_idle_tick(int cpu, struct tick_sched *ts)
+{
+	/*
+	 * If this cpu is offline and it is the one which updates
+	 * jiffies, then give up the assignment and let it be taken by
+	 * the cpu which runs the tick timer next. If we don't drop
+	 * this here the jiffies might be stale and do_timer() never
+	 * invoked.
+	 */
+	if (unlikely(!cpu_online(cpu))) {
+		if (cpu == tick_do_timer_cpu)
+			tick_do_timer_cpu = TICK_DO_TIMER_NONE;
+	}
+
+	if (unlikely(ts->nohz_mode == NOHZ_MODE_INACTIVE))
+		return false;
+
+	if (need_resched())
+		return false;
+
+	if (unlikely(local_softirq_pending() && cpu_online(cpu))) {
+		static int ratelimit;
+
+		if (ratelimit < 10) {
+			printk(KERN_ERR "NOHZ: local_softirq_pending %02x\n",
+			       (unsigned int) local_softirq_pending());
+			ratelimit++;
+		}
+		return false;
+	}
+
+	return true;
+}
+
+static void __tick_nohz_idle_enter(struct tick_sched *ts)
+{
+	ktime_t now, expires;
+	int cpu = smp_processor_id();
+
+	now = tick_nohz_start_idle(cpu, ts);
+
+	if (can_stop_idle_tick(cpu, ts)) {
+		int was_stopped = ts->tick_stopped;
+
+		ts->idle_calls++;
+
+		expires = tick_nohz_stop_sched_tick(ts, now, cpu);
+		if (expires.tv64 > 0LL) {
+			ts->idle_sleeps++;
+			ts->idle_expires = expires;
+		}
+
+		if (!was_stopped && ts->tick_stopped)
+			ts->idle_jiffies = ts->last_jiffies;
+	}
 }
 
 /**
@@ -479,7 +500,7 @@ void tick_nohz_idle_enter(void)
 	 * update of the idle time accounting in tick_nohz_start_idle().
 	 */
 	ts->inidle = 1;
-	tick_nohz_stop_sched_tick(ts);
+	__tick_nohz_idle_enter(ts);
 
 	local_irq_enable();
 }
@@ -499,7 +520,7 @@ void tick_nohz_irq_exit(void)
 	if (!ts->inidle)
 		return;
 
-	tick_nohz_stop_sched_tick(ts);
+	__tick_nohz_idle_enter(ts);
 }
 
 /**
@@ -517,7 +538,7 @@ ktime_t tick_nohz_get_sleep_length(void)
 static void tick_nohz_restart(struct tick_sched *ts, ktime_t now)
 {
 	hrtimer_cancel(&ts->sched_timer);
-	hrtimer_set_expires(&ts->sched_timer, ts->idle_tick);
+	hrtimer_set_expires(&ts->sched_timer, ts->last_tick);
 
 	while (1) {
 		/* Forward the time to expire in the future */
@@ -540,6 +561,41 @@ static void tick_nohz_restart(struct tick_sched *ts, ktime_t now)
 	}
 }
 
+static void tick_nohz_restart_sched_tick(struct tick_sched *ts, ktime_t now)
+{
+	/* Update jiffies first */
+	select_nohz_load_balancer(0);
+	tick_do_update_jiffies64(now);
+	update_cpu_load_nohz();
+
+	touch_softlockup_watchdog();
+	/*
+	 * Cancel the scheduled timer and restore the tick
+	 */
+	ts->tick_stopped  = 0;
+	ts->idle_exittime = now;
+
+	tick_nohz_restart(ts, now);
+}
+
+static void tick_nohz_account_idle_ticks(struct tick_sched *ts)
+{
+#ifndef CONFIG_VIRT_CPU_ACCOUNTING
+	unsigned long ticks;
+	/*
+	 * We stopped the tick in idle. Update process times would miss the
+	 * time we slept as update_process_times does only a 1 tick
+	 * accounting. Enforce that this is accounted to idle !
+	 */
+	ticks = jiffies - ts->idle_jiffies;
+	/*
+	 * We might be one off. Do not randomly account a huge number of ticks!
+	 */
+	if (ticks && ticks < LONG_MAX)
+		account_idle_ticks(ticks);
+#endif
+}
+
 /**
  * tick_nohz_idle_exit - restart the idle tick from the idle task
  *
@@ -551,9 +607,6 @@ void tick_nohz_idle_exit(void)
 {
 	int cpu = smp_processor_id();
 	struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
-#ifndef CONFIG_VIRT_CPU_ACCOUNTING
-	unsigned long ticks;
-#endif
 	ktime_t now;
 
 	local_irq_disable();
@@ -568,39 +621,11 @@ void tick_nohz_idle_exit(void)
 	if (ts->idle_active)
 		tick_nohz_stop_idle(cpu, now);
 
-	if (!ts->tick_stopped) {
-		local_irq_enable();
-		return;
+	if (ts->tick_stopped) {
+		tick_nohz_restart_sched_tick(ts, now);
+		tick_nohz_account_idle_ticks(ts);
 	}
 
-	/* Update jiffies first */
-	select_nohz_load_balancer(0);
-	tick_do_update_jiffies64(now);
-	update_cpu_load_nohz();
-
-#ifndef CONFIG_VIRT_CPU_ACCOUNTING
-	/*
-	 * We stopped the tick in idle. Update process times would miss the
-	 * time we slept as update_process_times does only a 1 tick
-	 * accounting. Enforce that this is accounted to idle !
-	 */
-	ticks = jiffies - ts->idle_jiffies;
-	/*
-	 * We might be one off. Do not randomly account a huge number of ticks!
-	 */
-	if (ticks && ticks < LONG_MAX)
-		account_idle_ticks(ticks);
-#endif
-
-	touch_softlockup_watchdog();
-	/*
-	 * Cancel the scheduled timer and restore the tick
-	 */
-	ts->tick_stopped  = 0;
-	ts->idle_exittime = now;
-
-	tick_nohz_restart(ts, now);
-
 	local_irq_enable();
 }
 
@@ -804,7 +829,8 @@ static enum hrtimer_restart tick_sched_timer(struct hrtimer *timer)
 		 */
 		if (ts->tick_stopped) {
 			touch_softlockup_watchdog();
-			ts->idle_jiffies++;
+			if (idle_cpu(cpu))
+				ts->idle_jiffies++;
 		}
 		update_process_times(user_mode(regs));
 		profile_tick(CPU_PROFILING);
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);
diff --git a/kernel/time/timer_list.c b/kernel/time/timer_list.c
index 3258455549f4..af5a7e9f164b 100644
--- a/kernel/time/timer_list.c
+++ b/kernel/time/timer_list.c
@@ -167,7 +167,7 @@ static void print_cpu(struct seq_file *m, int cpu, u64 now)
 	{
 		struct tick_sched *ts = tick_get_tick_sched(cpu);
 		P(nohz_mode);
-		P_ns(idle_tick);
+		P_ns(last_tick);
 		P(tick_stopped);
 		P(idle_jiffies);
 		P(idle_calls);
@@ -259,7 +259,7 @@ static int timer_list_show(struct seq_file *m, void *v)
 	u64 now = ktime_to_ns(ktime_get());
 	int cpu;
 
-	SEQ_printf(m, "Timer List Version: v0.6\n");
+	SEQ_printf(m, "Timer List Version: v0.7\n");
 	SEQ_printf(m, "HRTIMER_MAX_CLOCK_BASES: %d\n", HRTIMER_MAX_CLOCK_BASES);
 	SEQ_printf(m, "now at %Ld nsecs\n", (unsigned long long)now);