Merge branch 'devel' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-2.6-trace into tracing/urgent

10 files changed, 235 insertions, 70 deletions

diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 35eebd5510c..358e77564e6 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -2497,7 +2497,6 @@ static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry)
 	list_del(&cgrp->sibling);
 	spin_lock(&cgrp->dentry->d_lock);
 	d = dget(cgrp->dentry);
-	cgrp->dentry = NULL;
 	spin_unlock(&d->d_lock);
 
 	cgroup_d_remove_dir(d);
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 86d49045dae..5a732c5ef08 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -499,3 +499,6 @@ const unsigned long cpu_bit_bitmap[BITS_PER_LONG+1][BITS_TO_LONGS(NR_CPUS)] = {
 #endif
 };
 EXPORT_SYMBOL_GPL(cpu_bit_bitmap);
+
+const DECLARE_BITMAP(cpu_all_bits, NR_CPUS) = CPU_BITS_ALL;
+EXPORT_SYMBOL(cpu_all_bits);
diff --git a/kernel/sched.c b/kernel/sched.c
index e8819bc6f46..57c933ffbee 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -397,7 +397,7 @@ struct cfs_rq {
 	 * 'curr' points to currently running entity on this cfs_rq.
 	 * It is set to NULL otherwise (i.e when none are currently running).
 	 */
-	struct sched_entity *curr, *next;
+	struct sched_entity *curr, *next, *last;
 
 	unsigned long nr_spread_over;
 
@@ -1805,7 +1805,9 @@ task_hot(struct task_struct *p, u64 now, struct sched_domain *sd)
 	/*
 	 * Buddy candidates are cache hot:
 	 */
-	if (sched_feat(CACHE_HOT_BUDDY) && (&p->se == cfs_rq_of(&p->se)->next))
+	if (sched_feat(CACHE_HOT_BUDDY) &&
+			(&p->se == cfs_rq_of(&p->se)->next ||
+			 &p->se == cfs_rq_of(&p->se)->last))
 		return 1;
 
 	if (p->sched_class != &fair_sched_class)
@@ -6875,15 +6877,17 @@ cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu)
 	struct sched_domain *tmp;
 
 	/* Remove the sched domains which do not contribute to scheduling. */
-	for (tmp = sd; tmp; tmp = tmp->parent) {
+	for (tmp = sd; tmp; ) {
 		struct sched_domain *parent = tmp->parent;
 		if (!parent)
 			break;
+
 		if (sd_parent_degenerate(tmp, parent)) {
 			tmp->parent = parent->parent;
 			if (parent->parent)
 				parent->parent->child = tmp;
-		}
+		} else
+			tmp = tmp->parent;
 	}
 
 	if (sd && sd_degenerate(sd)) {
@@ -7672,6 +7676,7 @@ static int __build_sched_domains(const cpumask_t *cpu_map,
 error:
 	free_sched_groups(cpu_map, tmpmask);
 	SCHED_CPUMASK_FREE((void *)allmasks);
+	kfree(rd);
 	return -ENOMEM;
 #endif
 }
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index ce514afd78f..51aa3e102ac 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -341,23 +341,20 @@ static void __dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
 		cfs_rq->rb_leftmost = next_node;
 	}
 
-	if (cfs_rq->next == se)
-		cfs_rq->next = NULL;
-
 	rb_erase(&se->run_node, &cfs_rq->tasks_timeline);
 }
 
-static inline struct rb_node *first_fair(struct cfs_rq *cfs_rq)
-{
-	return cfs_rq->rb_leftmost;
-}
-
 static struct sched_entity *__pick_next_entity(struct cfs_rq *cfs_rq)
 {
-	return rb_entry(first_fair(cfs_rq), struct sched_entity, run_node);
+	struct rb_node *left = cfs_rq->rb_leftmost;
+
+	if (!left)
+		return NULL;
+
+	return rb_entry(left, struct sched_entity, run_node);
 }
 
-static inline struct sched_entity *__pick_last_entity(struct cfs_rq *cfs_rq)
+static struct sched_entity *__pick_last_entity(struct cfs_rq *cfs_rq)
 {
 	struct rb_node *last = rb_last(&cfs_rq->tasks_timeline);
 
@@ -741,6 +738,12 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int sleep)
 #endif
 	}
 
+	if (cfs_rq->last == se)
+		cfs_rq->last = NULL;
+
+	if (cfs_rq->next == se)
+		cfs_rq->next = NULL;
+
 	if (se != cfs_rq->curr)
 		__dequeue_entity(cfs_rq, se);
 	account_entity_dequeue(cfs_rq, se);
@@ -794,24 +797,15 @@ set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
 static int
 wakeup_preempt_entity(struct sched_entity *curr, struct sched_entity *se);
 
-static struct sched_entity *
-pick_next(struct cfs_rq *cfs_rq, struct sched_entity *se)
-{
-	if (!cfs_rq->next || wakeup_preempt_entity(cfs_rq->next, se) == 1)
-		return se;
-
-	return cfs_rq->next;
-}
-
 static struct sched_entity *pick_next_entity(struct cfs_rq *cfs_rq)
 {
-	struct sched_entity *se = NULL;
+	struct sched_entity *se = __pick_next_entity(cfs_rq);
 
-	if (first_fair(cfs_rq)) {
-		se = __pick_next_entity(cfs_rq);
-		se = pick_next(cfs_rq, se);
-		set_next_entity(cfs_rq, se);
-	}
+	if (cfs_rq->next && wakeup_preempt_entity(cfs_rq->next, se) < 1)
+		return cfs_rq->next;
+
+	if (cfs_rq->last && wakeup_preempt_entity(cfs_rq->last, se) < 1)
+		return cfs_rq->last;
 
 	return se;
 }
@@ -1325,26 +1319,53 @@ wakeup_preempt_entity(struct sched_entity *curr, struct sched_entity *se)
 	return 0;
 }
 
+static void set_last_buddy(struct sched_entity *se)
+{
+	for_each_sched_entity(se)
+		cfs_rq_of(se)->last = se;
+}
+
+static void set_next_buddy(struct sched_entity *se)
+{
+	for_each_sched_entity(se)
+		cfs_rq_of(se)->next = se;
+}
+
 /*
  * Preempt the current task with a newly woken task if needed:
  */
 static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int sync)
 {
 	struct task_struct *curr = rq->curr;
-	struct cfs_rq *cfs_rq = task_cfs_rq(curr);
 	struct sched_entity *se = &curr->se, *pse = &p->se;
 
 	if (unlikely(rt_prio(p->prio))) {
+		struct cfs_rq *cfs_rq = task_cfs_rq(curr);
+
 		update_rq_clock(rq);
 		update_curr(cfs_rq);
 		resched_task(curr);
 		return;
 	}
 
+	if (unlikely(p->sched_class != &fair_sched_class))
+		return;
+
 	if (unlikely(se == pse))
 		return;
 
-	cfs_rq_of(pse)->next = pse;
+	/*
+	 * Only set the backward buddy when the current task is still on the
+	 * rq. This can happen when a wakeup gets interleaved with schedule on
+	 * the ->pre_schedule() or idle_balance() point, either of which can
+	 * drop the rq lock.
+	 *
+	 * Also, during early boot the idle thread is in the fair class, for
+	 * obvious reasons its a bad idea to schedule back to the idle thread.
+	 */
+	if (sched_feat(LAST_BUDDY) && likely(se->on_rq && curr != rq->idle))
+		set_last_buddy(se);
+	set_next_buddy(pse);
 
 	/*
 	 * We can come here with TIF_NEED_RESCHED already set from new task
@@ -1396,6 +1417,7 @@ static struct task_struct *pick_next_task_fair(struct rq *rq)
 
 	do {
 		se = pick_next_entity(cfs_rq);
+		set_next_entity(cfs_rq, se);
 		cfs_rq = group_cfs_rq(se);
 	} while (cfs_rq);
 
diff --git a/kernel/sched_features.h b/kernel/sched_features.h
index fda01621829..da5d93b5d2c 100644
--- a/kernel/sched_features.h
+++ b/kernel/sched_features.h
@@ -12,3 +12,4 @@ SCHED_FEAT(LB_BIAS, 1)
 SCHED_FEAT(LB_WAKEUP_UPDATE, 1)
 SCHED_FEAT(ASYM_EFF_LOAD, 1)
 SCHED_FEAT(WAKEUP_OVERLAP, 0)
+SCHED_FEAT(LAST_BUDDY, 1)
diff --git a/kernel/smp.c b/kernel/smp.c
index f362a855377..75c8dde58c5 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -51,10 +51,6 @@ static void csd_flag_wait(struct call_single_data *data)
 {
 	/* Wait for response */
 	do {
-		/*
-		 * We need to see the flags store in the IPI handler
-		 */
-		smp_mb();
 		if (!(data->flags & CSD_FLAG_WAIT))
 			break;
 		cpu_relax();
@@ -76,6 +72,11 @@ static void generic_exec_single(int cpu, struct call_single_data *data)
 	list_add_tail(&data->list, &dst->list);
 	spin_unlock_irqrestore(&dst->lock, flags);
 
+	/*
+	 * Make the list addition visible before sending the ipi.
+	 */
+	smp_mb();
+
 	if (ipi)
 		arch_send_call_function_single_ipi(cpu);
 
@@ -157,7 +158,7 @@ void generic_smp_call_function_single_interrupt(void)
 	 * Need to see other stores to list head for checking whether
 	 * list is empty without holding q->lock
 	 */
-	smp_mb();
+	smp_read_barrier_depends();
 	while (!list_empty(&q->list)) {
 		unsigned int data_flags;
 
@@ -191,7 +192,7 @@ void generic_smp_call_function_single_interrupt(void)
 		/*
 		 * See comment on outer loop
 		 */
-		smp_mb();
+		smp_read_barrier_depends();
 	}
 }
 
@@ -370,6 +371,11 @@ int smp_call_function_mask(cpumask_t mask, void (*func)(void *), void *info,
 	list_add_tail_rcu(&data->csd.list, &call_function_queue);
 	spin_unlock_irqrestore(&call_function_lock, flags);
 
+	/*
+	 * Make the list addition visible before sending the ipi.
+	 */
+	smp_mb();
+
 	/* Send a message to all CPUs in the map */
 	arch_send_call_function_ipi(mask);
 
diff --git a/kernel/timer.c b/kernel/timer.c
index 56becf373c5..dbd50fabe4c 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -112,27 +112,8 @@ timer_set_base(struct timer_list *timer, struct tvec_base *new_base)
 				      tbase_get_deferrable(timer->base));
 }
 
-/**
- * __round_jiffies - function to round jiffies to a full second
- * @j: the time in (absolute) jiffies that should be rounded
- * @cpu: the processor number on which the timeout will happen
- *
- * __round_jiffies() rounds an absolute time in the future (in jiffies)
- * up or down to (approximately) full seconds. This is useful for timers
- * for which the exact time they fire does not matter too much, as long as
- * they fire approximately every X seconds.
- *
- * By rounding these timers to whole seconds, all such timers will fire
- * at the same time, rather than at various times spread out. The goal
- * of this is to have the CPU wake up less, which saves power.
- *
- * The exact rounding is skewed for each processor to avoid all
- * processors firing at the exact same time, which could lead
- * to lock contention or spurious cache line bouncing.
- *
- * The return value is the rounded version of the @j parameter.
- */
-unsigned long __round_jiffies(unsigned long j, int cpu)
+static unsigned long round_jiffies_common(unsigned long j, int cpu,
+		bool force_up)
 {
 	int rem;
 	unsigned long original = j;
@@ -154,8 +135,9 @@ unsigned long __round_jiffies(unsigned long j, int cpu)
 	 * due to delays of the timer irq, long irq off times etc etc) then
 	 * we should round down to the whole second, not up. Use 1/4th second
 	 * as cutoff for this rounding as an extreme upper bound for this.
+	 * But never round down if @force_up is set.
 	 */
-	if (rem < HZ/4) /* round down */
+	if (rem < HZ/4 && !force_up) /* round down */
 		j = j - rem;
 	else /* round up */
 		j = j - rem + HZ;
@@ -167,6 +149,31 @@ unsigned long __round_jiffies(unsigned long j, int cpu)
 		return original;
 	return j;
 }
+
+/**
+ * __round_jiffies - function to round jiffies to a full second
+ * @j: the time in (absolute) jiffies that should be rounded
+ * @cpu: the processor number on which the timeout will happen
+ *
+ * __round_jiffies() rounds an absolute time in the future (in jiffies)
+ * up or down to (approximately) full seconds. This is useful for timers
+ * for which the exact time they fire does not matter too much, as long as
+ * they fire approximately every X seconds.
+ *
+ * By rounding these timers to whole seconds, all such timers will fire
+ * at the same time, rather than at various times spread out. The goal
+ * of this is to have the CPU wake up less, which saves power.
+ *
+ * The exact rounding is skewed for each processor to avoid all
+ * processors firing at the exact same time, which could lead
+ * to lock contention or spurious cache line bouncing.
+ *
+ * The return value is the rounded version of the @j parameter.
+ */
+unsigned long __round_jiffies(unsigned long j, int cpu)
+{
+	return round_jiffies_common(j, cpu, false);
+}
 EXPORT_SYMBOL_GPL(__round_jiffies);
 
 /**
@@ -191,13 +198,10 @@ EXPORT_SYMBOL_GPL(__round_jiffies);
  */
 unsigned long __round_jiffies_relative(unsigned long j, int cpu)
 {
-	/*
-	 * In theory the following code can skip a jiffy in case jiffies
-	 * increments right between the addition and the later subtraction.
-	 * However since the entire point of this function is to use approximate
-	 * timeouts, it's entirely ok to not handle that.
-	 */
-	return  __round_jiffies(j + jiffies, cpu) - jiffies;
+	unsigned long j0 = jiffies;
+
+	/* Use j0 because jiffies might change while we run */
+	return round_jiffies_common(j + j0, cpu, false) - j0;
 }
 EXPORT_SYMBOL_GPL(__round_jiffies_relative);
 
@@ -218,7 +222,7 @@ EXPORT_SYMBOL_GPL(__round_jiffies_relative);
  */
 unsigned long round_jiffies(unsigned long j)
 {
-	return __round_jiffies(j, raw_smp_processor_id());
+	return round_jiffies_common(j, raw_smp_processor_id(), false);
 }
 EXPORT_SYMBOL_GPL(round_jiffies);
 
@@ -243,6 +247,71 @@ unsigned long round_jiffies_relative(unsigned long j)
 }
 EXPORT_SYMBOL_GPL(round_jiffies_relative);
 
+/**
+ * __round_jiffies_up - function to round jiffies up to a full second
+ * @j: the time in (absolute) jiffies that should be rounded
+ * @cpu: the processor number on which the timeout will happen
+ *
+ * This is the same as __round_jiffies() except that it will never
+ * round down.  This is useful for timeouts for which the exact time
+ * of firing does not matter too much, as long as they don't fire too
+ * early.
+ */
+unsigned long __round_jiffies_up(unsigned long j, int cpu)
+{
+	return round_jiffies_common(j, cpu, true);
+}
+EXPORT_SYMBOL_GPL(__round_jiffies_up);
+
+/**
+ * __round_jiffies_up_relative - function to round jiffies up to a full second
+ * @j: the time in (relative) jiffies that should be rounded
+ * @cpu: the processor number on which the timeout will happen
+ *
+ * This is the same as __round_jiffies_relative() except that it will never
+ * round down.  This is useful for timeouts for which the exact time
+ * of firing does not matter too much, as long as they don't fire too
+ * early.
+ */
+unsigned long __round_jiffies_up_relative(unsigned long j, int cpu)
+{
+	unsigned long j0 = jiffies;
+
+	/* Use j0 because jiffies might change while we run */
+	return round_jiffies_common(j + j0, cpu, true) - j0;
+}
+EXPORT_SYMBOL_GPL(__round_jiffies_up_relative);
+
+/**
+ * round_jiffies_up - function to round jiffies up to a full second
+ * @j: the time in (absolute) jiffies that should be rounded
+ *
+ * This is the same as round_jiffies() except that it will never
+ * round down.  This is useful for timeouts for which the exact time
+ * of firing does not matter too much, as long as they don't fire too
+ * early.
+ */
+unsigned long round_jiffies_up(unsigned long j)
+{
+	return round_jiffies_common(j, raw_smp_processor_id(), true);
+}
+EXPORT_SYMBOL_GPL(round_jiffies_up);
+
+/**
+ * round_jiffies_up_relative - function to round jiffies up to a full second
+ * @j: the time in (relative) jiffies that should be rounded
+ *
+ * This is the same as round_jiffies_relative() except that it will never
+ * round down.  This is useful for timeouts for which the exact time
+ * of firing does not matter too much, as long as they don't fire too
+ * early.
+ */
+unsigned long round_jiffies_up_relative(unsigned long j)
+{
+	return __round_jiffies_up_relative(j, raw_smp_processor_id());
+}
+EXPORT_SYMBOL_GPL(round_jiffies_up_relative);
+
 
 static inline void set_running_timer(struct tvec_base *base,
 					struct timer_list *timer)
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 3f338063864..2f76193c348 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -1060,7 +1060,7 @@ rb_reserve_next_event(struct ring_buffer_per_cpu *cpu_buffer,
 
 		/* Did the write stamp get updated already? */
 		if (unlikely(ts < cpu_buffer->write_stamp))
-			goto again;
+			delta = 0;
 
 		if (test_time_stamp(delta)) {
 
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 974973e39e8..697eda36b86 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -2676,7 +2676,7 @@ tracing_entries_write(struct file *filp, const char __user *ubuf,
 {
 	unsigned long val;
 	char buf[64];
-	int ret;
+	int ret, cpu;
 	struct trace_array *tr = filp->private_data;
 
 	if (cnt >= sizeof(buf))
@@ -2704,6 +2704,14 @@ tracing_entries_write(struct file *filp, const char __user *ubuf,
 		goto out;
 	}
 
+	/* disable all cpu buffers */
+	for_each_tracing_cpu(cpu) {
+		if (global_trace.data[cpu])
+			atomic_inc(&global_trace.data[cpu]->disabled);
+		if (max_tr.data[cpu])
+			atomic_inc(&max_tr.data[cpu]->disabled);
+	}
+
 	if (val != global_trace.entries) {
 		ret = ring_buffer_resize(global_trace.buffer, val);
 		if (ret < 0) {
@@ -2735,6 +2743,13 @@ tracing_entries_write(struct file *filp, const char __user *ubuf,
 	if (tracing_disabled)
 		cnt = -ENOMEM;
  out:
+	for_each_tracing_cpu(cpu) {
+		if (global_trace.data[cpu])
+			atomic_dec(&global_trace.data[cpu]->disabled);
+		if (max_tr.data[cpu])
+			atomic_dec(&max_tr.data[cpu]->disabled);
+	}
+
 	max_tr.entries = global_trace.entries;
 	mutex_unlock(&trace_types_lock);
 
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index f928f2a87b9..d4dc69ddebd 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -970,6 +970,51 @@ undo:
 	return ret;
 }
 
+#ifdef CONFIG_SMP
+struct work_for_cpu {
+	struct work_struct work;
+	long (*fn)(void *);
+	void *arg;
+	long ret;
+};
+
+static void do_work_for_cpu(struct work_struct *w)
+{
+	struct work_for_cpu *wfc = container_of(w, struct work_for_cpu, work);
+
+	wfc->ret = wfc->fn(wfc->arg);
+}
+
+/**
+ * work_on_cpu - run a function in user context on a particular cpu
+ * @cpu: the cpu to run on
+ * @fn: the function to run
+ * @arg: the function arg
+ *
+ * This will return -EINVAL in the cpu is not online, or the return value
+ * of @fn otherwise.
+ */
+long work_on_cpu(unsigned int cpu, long (*fn)(void *), void *arg)
+{
+	struct work_for_cpu wfc;
+
+	INIT_WORK(&wfc.work, do_work_for_cpu);
+	wfc.fn = fn;
+	wfc.arg = arg;
+	get_online_cpus();
+	if (unlikely(!cpu_online(cpu)))
+		wfc.ret = -EINVAL;
+	else {
+		schedule_work_on(cpu, &wfc.work);
+		flush_work(&wfc.work);
+	}
+	put_online_cpus();
+
+	return wfc.ret;
+}
+EXPORT_SYMBOL_GPL(work_on_cpu);
+#endif /* CONFIG_SMP */
+
 void __init init_workqueues(void)
 {
 	cpu_populated_map = cpu_online_map;