Merge branch 'sched-v28-for-linus' of...

Merge branch 'sched-v28-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'sched-v28-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (38 commits)
  sched debug: add name to sched_domain sysctl entries
  sched: sync wakeups vs avg_overlap
  sched: remove redundant code in cpu_cgroup_create()
  sched_rt.c: resch needed in rt_rq_enqueue() for the root rt_rq
  cpusets: scan_for_empty_cpusets(), cpuset doesn't seem to be so const
  sched: minor optimizations in wake_affine and select_task_rq_fair
  sched: maintain only task entities in cfs_rq->tasks list
  sched: fixup buddy selection
  sched: more sanity checks on the bandwidth settings
  sched: add some comments to the bandwidth code
  sched: fixlet for group load balance
  sched: rework wakeup preemption
  CFS scheduler: documentation about scheduling policies
  sched: clarify ifdef tangle
  sched: fix list traversal to use _rcu variant
  sched: turn off WAKEUP_OVERLAP
  sched: wakeup preempt when small overlap
  kernel/cpu.c: create a CPU_STARTING cpu_chain notifier
  kernel/cpu.c: Move the CPU_DYING notifiers
  sched: fix __load_balance_iterator() for cfq with only one task
  ...

Documentation/kernel-doc-nano-HOWTO.txt

@@ -168,10 +168,10 @@ if ($#ARGV < 0) {
 mkdir $ARGV[0],0777;
 $state = 0;
 while (<STDIN>) {
-    if (/^\.TH \"[^\"]*\" 4 \"([^\"]*)\"/) {
+    if (/^\.TH \"[^\"]*\" 9 \"([^\"]*)\"/) {
 	if ($state == 1) { close OUT }
 	$state = 1;
-	$fn = "$ARGV[0]/$1.4";
+	$fn = "$ARGV[0]/$1.9";
 	print STDERR "Creating $fn\n";
 	open OUT, ">$fn" or die "can't open $fn: $!\n";
 	print OUT $_;

arch/alpha/kernel/smp.c

@@ -149,6 +149,9 @@ smp_callin(void)
 	atomic_inc(&init_mm.mm_count);
 	current->active_mm = &init_mm;
 
+	/* inform the notifiers about the new cpu */
+	notify_cpu_starting(cpuid);
+
 	/* Must have completely accurate bogos.  */
 	local_irq_enable();
 

arch/arm/kernel/smp.c

@@ -277,6 +277,7 @@ asmlinkage void __cpuinit secondary_start_kernel(void)
 	/*
 	 * Enable local interrupts.
 	 */
+	notify_cpu_starting(cpu);
 	local_irq_enable();
 	local_fiq_enable();
 

arch/cris/arch-v32/kernel/smp.c

@@ -178,6 +178,7 @@ void __init smp_callin(void)
 	unmask_irq(IPI_INTR_VECT);
 	unmask_irq(TIMER0_INTR_VECT);
 	preempt_disable();
+	notify_cpu_starting(cpu);
 	local_irq_enable();
 
 	cpu_set(cpu, cpu_online_map);

arch/ia64/kernel/smpboot.c

@@ -401,6 +401,7 @@ smp_callin (void)
 	spin_lock(&vector_lock);
 	/* Setup the per cpu irq handling data structures */
 	__setup_vector_irq(cpuid);
+	notify_cpu_starting(cpuid);
 	cpu_set(cpuid, cpu_online_map);
 	per_cpu(cpu_state, cpuid) = CPU_ONLINE;
 	spin_unlock(&vector_lock);

arch/m32r/kernel/smpboot.c

@@ -498,6 +498,8 @@ static void __init smp_online(void)
 {
 	int cpu_id = smp_processor_id();
 
+	notify_cpu_starting(cpu_id);
+
 	local_irq_enable();
 
 	/* Get our bogomips. */

arch/mips/kernel/smp.c

@@ -121,6 +121,8 @@ asmlinkage __cpuinit void start_secondary(void)
 	cpu = smp_processor_id();
 	cpu_data[cpu].udelay_val = loops_per_jiffy;
 
+	notify_cpu_starting(cpu);
+
 	mp_ops->smp_finish();
 	set_cpu_sibling_map(cpu);
 

arch/powerpc/kernel/smp.c

@@ -453,6 +453,7 @@ int __devinit start_secondary(void *unused)
 	secondary_cpu_time_init();
 
 	ipi_call_lock();
+	notify_cpu_starting(cpu);
 	cpu_set(cpu, cpu_online_map);
 	/* Update sibling maps */
 	base = cpu_first_thread_in_core(cpu);

arch/s390/kernel/smp.c

@@ -585,6 +585,8 @@ int __cpuinit start_secondary(void *cpuvoid)
 	/* Enable pfault pseudo page faults on this cpu. */
 	pfault_init();
 
+	/* call cpu notifiers */
+	notify_cpu_starting(smp_processor_id());
 	/* Mark this cpu as online */
 	spin_lock(&call_lock);
 	cpu_set(smp_processor_id(), cpu_online_map);

arch/sh/kernel/smp.c

@@ -82,6 +82,8 @@ asmlinkage void __cpuinit start_secondary(void)
 
 	preempt_disable();
 
+	notify_cpu_starting(smp_processor_id());
+
 	local_irq_enable();
 
 	calibrate_delay();

arch/sparc/kernel/sun4d_smp.c

@@ -88,6 +88,7 @@ void __init smp4d_callin(void)
 	local_flush_cache_all();
 	local_flush_tlb_all();
 
+	notify_cpu_starting(cpuid);
 	/*
 	 * Unblock the master CPU _only_ when the scheduler state
 	 * of all secondary CPUs will be up-to-date, so after

arch/sparc/kernel/sun4m_smp.c

@@ -71,6 +71,8 @@ void __cpuinit smp4m_callin(void)
 	local_flush_cache_all();
 	local_flush_tlb_all();
 
+	notify_cpu_starting(cpuid);
+
 	/* Get our local ticker going. */
 	smp_setup_percpu_timer();
 

arch/um/kernel/smp.c

@@ -85,6 +85,7 @@ static int idle_proc(void *cpup)
 	while (!cpu_isset(cpu, smp_commenced_mask))
 		cpu_relax();
 
+	notify_cpu_starting(cpu);
 	cpu_set(cpu, cpu_online_map);
 	default_idle();
 	return 0;

arch/x86/kernel/smpboot.c

@@ -257,6 +257,7 @@ static void __cpuinit smp_callin(void)
 	end_local_APIC_setup();
 	map_cpu_to_logical_apicid();
 
+	notify_cpu_starting(cpuid);
 	/*
 	 * Get our bogomips.
 	 *

arch/x86/mach-voyager/voyager_smp.c

@@ -448,6 +448,8 @@ static void __init start_secondary(void *unused)
 
 	VDEBUG(("VOYAGER SMP: CPU%d, stack at about %p\n", cpuid, &cpuid));
 
+	notify_cpu_starting(cpuid);
+
 	/* enable interrupts */
 	local_irq_enable();
 

include/linux/completion.h

@@ -10,6 +10,18 @@
 
 #include <linux/wait.h>
 
+/**
+ * struct completion - structure used to maintain state for a "completion"
+ *
+ * This is the opaque structure used to maintain the state for a "completion".
+ * Completions currently use a FIFO to queue threads that have to wait for
+ * the "completion" event.
+ *
+ * See also:  complete(), wait_for_completion() (and friends _timeout,
+ * _interruptible, _interruptible_timeout, and _killable), init_completion(),
+ * and macros DECLARE_COMPLETION(), DECLARE_COMPLETION_ONSTACK(), and
+ * INIT_COMPLETION().
+ */
 struct completion {
 	unsigned int done;
 	wait_queue_head_t wait;
@@ -21,6 +33,14 @@ struct completion {
 #define COMPLETION_INITIALIZER_ONSTACK(work) \
 	({ init_completion(&work); work; })
 
+/**
+ * DECLARE_COMPLETION: - declare and initialize a completion structure
+ * @work:  identifier for the completion structure
+ *
+ * This macro declares and initializes a completion structure. Generally used
+ * for static declarations. You should use the _ONSTACK variant for automatic
+ * variables.
+ */
 #define DECLARE_COMPLETION(work) \
 	struct completion work = COMPLETION_INITIALIZER(work)
 
@@ -29,6 +49,13 @@ struct completion {
  * completions - so we use the _ONSTACK() variant for those that
  * are on the kernel stack:
  */
+/**
+ * DECLARE_COMPLETION_ONSTACK: - declare and initialize a completion structure
+ * @work:  identifier for the completion structure
+ *
+ * This macro declares and initializes a completion structure on the kernel
+ * stack.
+ */
 #ifdef CONFIG_LOCKDEP
 # define DECLARE_COMPLETION_ONSTACK(work) \
 	struct completion work = COMPLETION_INITIALIZER_ONSTACK(work)
@@ -36,6 +63,13 @@ struct completion {
 # define DECLARE_COMPLETION_ONSTACK(work) DECLARE_COMPLETION(work)
 #endif
 
+/**
+ * init_completion: - Initialize a dynamically allocated completion
+ * @x:  completion structure that is to be initialized
+ *
+ * This inline function will initialize a dynamically created completion
+ * structure.
+ */
 static inline void init_completion(struct completion *x)
 {
 	x->done = 0;
@@ -55,6 +89,13 @@ extern bool completion_done(struct completion *x);
 extern void complete(struct completion *);
 extern void complete_all(struct completion *);
 
+/**
+ * INIT_COMPLETION: - reinitialize a completion structure
+ * @x:  completion structure to be reinitialized
+ *
+ * This macro should be used to reinitialize a completion structure so it can
+ * be reused. This is especially important after complete_all() is used.
+ */
 #define INIT_COMPLETION(x)	((x).done = 0)
 
 

include/linux/cpu.h

@@ -69,6 +69,7 @@ static inline void unregister_cpu_notifier(struct notifier_block *nb)
 #endif
 
 int cpu_up(unsigned int cpu);
+void notify_cpu_starting(unsigned int cpu);
 extern void cpu_hotplug_init(void);
 extern void cpu_maps_update_begin(void);
 extern void cpu_maps_update_done(void);

include/linux/notifier.h

@@ -213,9 +213,16 @@ static inline int notifier_to_errno(int ret)
 #define CPU_DOWN_FAILED		0x0006 /* CPU (unsigned)v NOT going down */
 #define CPU_DEAD		0x0007 /* CPU (unsigned)v dead */
 #define CPU_DYING		0x0008 /* CPU (unsigned)v not running any task,
-				        * not handling interrupts, soon dead */
+					* not handling interrupts, soon dead.
+					* Called on the dying cpu, interrupts
+					* are already disabled. Must not
+					* sleep, must not fail */
 #define CPU_POST_DEAD		0x0009 /* CPU (unsigned)v dead, cpu_hotplug
 					* lock is dropped */
+#define CPU_STARTING		0x000A /* CPU (unsigned)v soon running.
+					* Called on the new cpu, just before
+					* enabling interrupts. Must not sleep,
+					* must not fail */
 
 /* Used for CPU hotplug events occuring while tasks are frozen due to a suspend
  * operation in progress
@@ -229,6 +236,7 @@ static inline int notifier_to_errno(int ret)
 #define CPU_DOWN_FAILED_FROZEN	(CPU_DOWN_FAILED | CPU_TASKS_FROZEN)
 #define CPU_DEAD_FROZEN		(CPU_DEAD | CPU_TASKS_FROZEN)
 #define CPU_DYING_FROZEN	(CPU_DYING | CPU_TASKS_FROZEN)
+#define CPU_STARTING_FROZEN	(CPU_STARTING | CPU_TASKS_FROZEN)
 
 /* Hibernation and suspend events */
 #define PM_HIBERNATION_PREPARE	0x0001 /* Going to hibernate */

include/linux/proportions.h

@@ -104,8 +104,8 @@ struct prop_local_single {
 	 * snapshot of the last seen global state
 	 * and a lock protecting this state
 	 */
-	int shift;
 	unsigned long period;
+	int shift;
 	spinlock_t lock;		/* protect the snapshot state */
 };
 

include/linux/sched.h

@@ -451,8 +451,8 @@ struct signal_struct {
 	 * - everyone except group_exit_task is stopped during signal delivery
 	 *   of fatal signals, group_exit_task processes the signal.
 	 */
-	struct task_struct	*group_exit_task;
 	int			notify_count;
+	struct task_struct	*group_exit_task;
 
 	/* thread group stop support, overloads group_exit_code too */
 	int			group_stop_count;
@@ -824,6 +824,9 @@ struct sched_domain {
 	unsigned int ttwu_move_affine;
 	unsigned int ttwu_move_balance;
 #endif
+#ifdef CONFIG_SCHED_DEBUG
+	char *name;
+#endif
 };
 
 extern void partition_sched_domains(int ndoms_new, cpumask_t *doms_new,
@@ -897,7 +900,7 @@ struct sched_class {
 	void (*yield_task) (struct rq *rq);
 	int  (*select_task_rq)(struct task_struct *p, int sync);
 
-	void (*check_preempt_curr) (struct rq *rq, struct task_struct *p);
+	void (*check_preempt_curr) (struct rq *rq, struct task_struct *p, int sync);
 
 	struct task_struct * (*pick_next_task) (struct rq *rq);
 	void (*put_prev_task) (struct rq *rq, struct task_struct *p);
@@ -1010,8 +1013,8 @@ struct sched_entity {
 
 struct sched_rt_entity {
 	struct list_head run_list;
-	unsigned int time_slice;
 	unsigned long timeout;
+	unsigned int time_slice;
 	int nr_cpus_allowed;
 
 	struct sched_rt_entity *back;

kernel/cpu.c

@@ -199,13 +199,14 @@ static int __ref take_cpu_down(void *_param)
 	struct take_cpu_down_param *param = _param;
 	int err;
 
-	raw_notifier_call_chain(&cpu_chain, CPU_DYING | param->mod,
-				param->hcpu);
 	/* Ensure this CPU doesn't handle any more interrupts. */
 	err = __cpu_disable();
 	if (err < 0)
 		return err;
 
+	raw_notifier_call_chain(&cpu_chain, CPU_DYING | param->mod,
+				param->hcpu);
+
 	/* Force idle task to run as soon as we yield: it should
 	   immediately notice cpu is offline and die quickly. */
 	sched_idle_next();
@@ -453,6 +454,25 @@ out:
 }
 #endif /* CONFIG_PM_SLEEP_SMP */
 
+/**
+ * notify_cpu_starting(cpu) - call the CPU_STARTING notifiers
+ * @cpu: cpu that just started
+ *
+ * This function calls the cpu_chain notifiers with CPU_STARTING.
+ * It must be called by the arch code on the new cpu, before the new cpu
+ * enables interrupts and before the "boot" cpu returns from __cpu_up().
+ */
+void notify_cpu_starting(unsigned int cpu)
+{
+	unsigned long val = CPU_STARTING;
+
+#ifdef CONFIG_PM_SLEEP_SMP
+	if (cpu_isset(cpu, frozen_cpus))
+		val = CPU_STARTING_FROZEN;
+#endif /* CONFIG_PM_SLEEP_SMP */
+	raw_notifier_call_chain(&cpu_chain, val, (void *)(long)cpu);
+}
+
 #endif /* CONFIG_SMP */
 
 /*

kernel/cpuset.c

@@ -1921,7 +1921,7 @@ static void remove_tasks_in_empty_cpuset(struct cpuset *cs)
  * that has tasks along with an empty 'mems'.  But if we did see such
  * a cpuset, we'd handle it just like we do if its 'cpus' was empty.
  */
-static void scan_for_empty_cpusets(const struct cpuset *root)
+static void scan_for_empty_cpusets(struct cpuset *root)
 {
 	LIST_HEAD(queue);
 	struct cpuset *cp;	/* scans cpusets being updated */

kernel/sched_features.h

@@ -11,3 +11,4 @@ SCHED_FEAT(ASYM_GRAN, 1)
 SCHED_FEAT(LB_BIAS, 1)
 SCHED_FEAT(LB_WAKEUP_UPDATE, 1)
 SCHED_FEAT(ASYM_EFF_LOAD, 1)
+SCHED_FEAT(WAKEUP_OVERLAP, 0)

kernel/sched_idletask.c

@@ -14,7 +14,7 @@ static int select_task_rq_idle(struct task_struct *p, int sync)
 /*
  * Idle tasks are unconditionally rescheduled:
  */
-static void check_preempt_curr_idle(struct rq *rq, struct task_struct *p)
+static void check_preempt_curr_idle(struct rq *rq, struct task_struct *p, int sync)
 {
 	resched_task(rq->idle);
 }
@@ -76,7 +76,7 @@ static void switched_to_idle(struct rq *rq, struct task_struct *p,
 	if (running)
 		resched_task(rq->curr);
 	else
-		check_preempt_curr(rq, p);
+		check_preempt_curr(rq, p, 0);
 }
 
 static void prio_changed_idle(struct rq *rq, struct task_struct *p,
@@ -93,7 +93,7 @@ static void prio_changed_idle(struct rq *rq, struct task_struct *p,
 		if (p->prio > oldprio)
 			resched_task(rq->curr);
 	} else
-		check_preempt_curr(rq, p);
+		check_preempt_curr(rq, p, 0);
 }
 
 /*

kernel/sched_rt.c

@@ -102,12 +102,12 @@ static void dequeue_rt_entity(struct sched_rt_entity *rt_se);
 
 static void sched_rt_rq_enqueue(struct rt_rq *rt_rq)
 {
+	struct task_struct *curr = rq_of_rt_rq(rt_rq)->curr;
 	struct sched_rt_entity *rt_se = rt_rq->rt_se;
 
-	if (rt_se && !on_rt_rq(rt_se) && rt_rq->rt_nr_running) {
-		struct task_struct *curr = rq_of_rt_rq(rt_rq)->curr;
-
-		enqueue_rt_entity(rt_se);
+	if (rt_rq->rt_nr_running) {
+		if (rt_se && !on_rt_rq(rt_se))
+			enqueue_rt_entity(rt_se);
 		if (rt_rq->highest_prio < curr->prio)
 			resched_task(curr);
 	}
@@ -231,6 +231,9 @@ static inline struct rt_bandwidth *sched_rt_bandwidth(struct rt_rq *rt_rq)
 #endif /* CONFIG_RT_GROUP_SCHED */
 
 #ifdef CONFIG_SMP
+/*
+ * We ran out of runtime, see if we can borrow some from our neighbours.
+ */
 static int do_balance_runtime(struct rt_rq *rt_rq)
 {
 	struct rt_bandwidth *rt_b = sched_rt_bandwidth(rt_rq);
@@ -250,9 +253,18 @@ static int do_balance_runtime(struct rt_rq *rt_rq)
 			continue;
 
 		spin_lock(&iter->rt_runtime_lock);
+		/*
+		 * Either all rqs have inf runtime and there's nothing to steal
+		 * or __disable_runtime() below sets a specific rq to inf to
+		 * indicate its been disabled and disalow stealing.
+		 */
 		if (iter->rt_runtime == RUNTIME_INF)
 			goto next;
 
+		/*
+		 * From runqueues with spare time, take 1/n part of their
+		 * spare time, but no more than our period.
+		 */
 		diff = iter->rt_runtime - iter->rt_time;
 		if (diff > 0) {
 			diff = div_u64((u64)diff, weight);
@@ -274,6 +286,9 @@ next:
 	return more;
 }
 
+/*
+ * Ensure this RQ takes back all the runtime it lend to its neighbours.
+ */
 static void __disable_runtime(struct rq *rq)
 {
 	struct root_domain *rd = rq->rd;
@@ -289,17 +304,33 @@ static void __disable_runtime(struct rq *rq)
 
 		spin_lock(&rt_b->rt_runtime_lock);
 		spin_lock(&rt_rq->rt_runtime_lock);
+		/*
+		 * Either we're all inf and nobody needs to borrow, or we're
+		 * already disabled and thus have nothing to do, or we have
+		 * exactly the right amount of runtime to take out.
+		 */
 		if (rt_rq->rt_runtime == RUNTIME_INF ||
 				rt_rq->rt_runtime == rt_b->rt_runtime)
 			goto balanced;
 		spin_unlock(&rt_rq->rt_runtime_lock);
 
+		/*
+		 * Calculate the difference between what we started out with
+		 * and what we current have, that's the amount of runtime
+		 * we lend and now have to reclaim.
+		 */
 		want = rt_b->rt_runtime - rt_rq->rt_runtime;
 
+		/*
+		 * Greedy reclaim, take back as much as we can.
+		 */
 		for_each_cpu_mask(i, rd->span) {
 			struct rt_rq *iter = sched_rt_period_rt_rq(rt_b, i);
 			s64 diff;
 
+			/*
+			 * Can't reclaim from ourselves or disabled runqueues.
+			 */
 			if (iter == rt_rq || iter->rt_runtime == RUNTIME_INF)
 				continue;
 
@@ -319,8 +350,16 @@ static void __disable_runtime(struct rq *rq)
 		}
 
 		spin_lock(&rt_rq->rt_runtime_lock);
+		/*
+		 * We cannot be left wanting - that would mean some runtime
+		 * leaked out of the system.
+		 */
 		BUG_ON(want);
 balanced:
+		/*
+		 * Disable all the borrow logic by pretending we have inf
+		 * runtime - in which case borrowing doesn't make sense.
+		 */
 		rt_rq->rt_runtime = RUNTIME_INF;
 		spin_unlock(&rt_rq->rt_runtime_lock);
 		spin_unlock(&rt_b->rt_runtime_lock);
@@ -343,6 +382,9 @@ static void __enable_runtime(struct rq *rq)
 	if (unlikely(!scheduler_running))
 		return;
 
+	/*
+	 * Reset each runqueue's bandwidth settings
+	 */
 	for_each_leaf_rt_rq(rt_rq, rq) {
 		struct rt_bandwidth *rt_b = sched_rt_bandwidth(rt_rq);
 
@@ -389,7 +431,7 @@ static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun)
 	int i, idle = 1;
 	cpumask_t span;
 
-	if (rt_b->rt_runtime == RUNTIME_INF)
+	if (!rt_bandwidth_enabled() || rt_b->rt_runtime == RUNTIME_INF)
 		return 1;
 
 	span = sched_rt_period_mask();
@@ -487,6 +529,9 @@ static void update_curr_rt(struct rq *rq)
 	curr->se.exec_start = rq->clock;
 	cpuacct_charge(curr, delta_exec);
 
+	if (!rt_bandwidth_enabled())
+		return;
+
 	for_each_sched_rt_entity(rt_se) {
 		rt_rq = rt_rq_of_se(rt_se);
 
@@ -784,7 +829,7 @@ static void check_preempt_equal_prio(struct rq *rq, struct task_struct *p)
 /*
  * Preempt the current task with a newly woken task if needed:
  */
-static void check_preempt_curr_rt(struct rq *rq, struct task_struct *p)
+static void check_preempt_curr_rt(struct rq *rq, struct task_struct *p, int sync)
 {
 	if (p->prio < rq->curr->prio) {
 		resched_task(rq->curr);

kernel/user.c

@@ -169,7 +169,7 @@ static ssize_t cpu_rt_runtime_show(struct kobject *kobj,
 {
 	struct user_struct *up = container_of(kobj, struct user_struct, kobj);
 
-	return sprintf(buf, "%lu\n", sched_group_rt_runtime(up->tg));
+	return sprintf(buf, "%ld\n", sched_group_rt_runtime(up->tg));
 }
 
 static ssize_t cpu_rt_runtime_store(struct kobject *kobj,
@@ -180,7 +180,7 @@ static ssize_t cpu_rt_runtime_store(struct kobject *kobj,
 	unsigned long rt_runtime;
 	int rc;
 
-	sscanf(buf, "%lu", &rt_runtime);
+	sscanf(buf, "%ld", &rt_runtime);
 
 	rc = sched_group_set_rt_runtime(up->tg, rt_runtime);