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

* 'sched/for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
  sched: hrtick_enabled() should use cpu_active()
  sched, x86: clean up hrtick implementation
  sched: fix build error, provide partition_sched_domains() unconditionally
  sched: fix warning in inc_rt_tasks() to not declare variable 'rq' if it's not needed
  cpu hotplug: Make cpu_active_map synchronization dependency clear
  cpu hotplug, sched: Introduce cpu_active_map and redo sched domain managment (take 2)
  sched: rework of "prioritize non-migratable tasks over migratable ones"
  sched: reduce stack size in isolated_cpu_setup()
  Revert parts of "ftrace: do not trace scheduler functions"

Fixed up conflicts in include/asm-x86/thread_info.h (due to the
TIF_SINGLESTEP unification vs TIF_HRTICK_RESCHED removal) and
kernel/sched_fair.c (due to cpu_active_map vs for_each_cpu_mask_nr()
introduction).

arch/x86/kernel/signal_32.c

@@ -661,8 +661,5 @@ do_notify_resume(struct pt_regs *regs, void *unused, __u32 thread_info_flags)
 	if (thread_info_flags & _TIF_SIGPENDING)
 		do_signal(regs);
 
-	if (thread_info_flags & _TIF_HRTICK_RESCHED)
-		hrtick_resched();
-
 	clear_thread_flag(TIF_IRET);
 }

arch/x86/kernel/signal_64.c

@@ -496,9 +496,6 @@ void do_notify_resume(struct pt_regs *regs, void *unused,
 	/* deal with pending signal delivery */
 	if (thread_info_flags & _TIF_SIGPENDING)
 		do_signal(regs);
-
-	if (thread_info_flags & _TIF_HRTICK_RESCHED)
-		hrtick_resched();
 }
 
 void signal_fault(struct pt_regs *regs, void __user *frame, char *where)

include/asm-x86/thread_info.h

@@ -79,7 +79,6 @@ struct thread_info {
 #define TIF_SYSCALL_AUDIT	7	/* syscall auditing active */
 #define TIF_SECCOMP		8	/* secure computing */
 #define TIF_MCE_NOTIFY		10	/* notify userspace of an MCE */
-#define TIF_HRTICK_RESCHED	11	/* reprogram hrtick timer */
 #define TIF_NOTSC		16	/* TSC is not accessible in userland */
 #define TIF_IA32		17	/* 32bit process */
 #define TIF_FORK		18	/* ret_from_fork */
@@ -102,7 +101,6 @@ struct thread_info {
 #define _TIF_SYSCALL_AUDIT	(1 << TIF_SYSCALL_AUDIT)
 #define _TIF_SECCOMP		(1 << TIF_SECCOMP)
 #define _TIF_MCE_NOTIFY		(1 << TIF_MCE_NOTIFY)
-#define _TIF_HRTICK_RESCHED	(1 << TIF_HRTICK_RESCHED)
 #define _TIF_NOTSC		(1 << TIF_NOTSC)
 #define _TIF_IA32		(1 << TIF_IA32)
 #define _TIF_FORK		(1 << TIF_FORK)
@@ -135,7 +133,7 @@ struct thread_info {
 
 /* Only used for 64 bit */
 #define _TIF_DO_NOTIFY_MASK						\
-	(_TIF_SIGPENDING|_TIF_MCE_NOTIFY|_TIF_HRTICK_RESCHED)
+	(_TIF_SIGPENDING|_TIF_MCE_NOTIFY)
 
 /* flags to check in __switch_to() */
 #define _TIF_WORK_CTXSW							\

include/linux/cpumask.h

@@ -458,13 +458,14 @@ int __next_cpu_nr(int n, const cpumask_t *srcp);
 
 /*
  * The following particular system cpumasks and operations manage
- * possible, present and online cpus.  Each of them is a fixed size
+ * possible, present, active and online cpus.  Each of them is a fixed size
  * bitmap of size NR_CPUS.
  *
  *  #ifdef CONFIG_HOTPLUG_CPU
  *     cpu_possible_map - has bit 'cpu' set iff cpu is populatable
  *     cpu_present_map  - has bit 'cpu' set iff cpu is populated
  *     cpu_online_map   - has bit 'cpu' set iff cpu available to scheduler
+ *     cpu_active_map   - has bit 'cpu' set iff cpu available to migration
  *  #else
  *     cpu_possible_map - has bit 'cpu' set iff cpu is populated
  *     cpu_present_map  - copy of cpu_possible_map
@@ -515,6 +516,7 @@ int __next_cpu_nr(int n, const cpumask_t *srcp);
 extern cpumask_t cpu_possible_map;
 extern cpumask_t cpu_online_map;
 extern cpumask_t cpu_present_map;
+extern cpumask_t cpu_active_map;
 
 #if NR_CPUS > 1
 #define num_online_cpus()	cpus_weight_nr(cpu_online_map)
@@ -523,6 +525,7 @@ extern cpumask_t cpu_present_map;
 #define cpu_online(cpu)		cpu_isset((cpu), cpu_online_map)
 #define cpu_possible(cpu)	cpu_isset((cpu), cpu_possible_map)
 #define cpu_present(cpu)	cpu_isset((cpu), cpu_present_map)
+#define cpu_active(cpu)		cpu_isset((cpu), cpu_active_map)
 #else
 #define num_online_cpus()	1
 #define num_possible_cpus()	1
@@ -530,6 +533,7 @@ extern cpumask_t cpu_present_map;
 #define cpu_online(cpu)		((cpu) == 0)
 #define cpu_possible(cpu)	((cpu) == 0)
 #define cpu_present(cpu)	((cpu) == 0)
+#define cpu_active(cpu)		((cpu) == 0)
 #endif
 
 #define cpu_is_offline(cpu)	unlikely(!cpu_online(cpu))

include/linux/cpuset.h

@@ -78,6 +78,8 @@ extern void cpuset_track_online_nodes(void);
 
 extern int current_cpuset_is_being_rebound(void);
 
+extern void rebuild_sched_domains(void);
+
 #else /* !CONFIG_CPUSETS */
 
 static inline int cpuset_init_early(void) { return 0; }
@@ -156,6 +158,11 @@ static inline int current_cpuset_is_being_rebound(void)
 	return 0;
 }
 
+static inline void rebuild_sched_domains(void)
+{
+	partition_sched_domains(0, NULL, NULL);
+}
+
 #endif /* !CONFIG_CPUSETS */
 
 #endif /* _LINUX_CPUSET_H */

include/linux/sched.h

@@ -825,7 +825,16 @@ extern void partition_sched_domains(int ndoms_new, cpumask_t *doms_new,
 				    struct sched_domain_attr *dattr_new);
 extern int arch_reinit_sched_domains(void);
 
-#endif	/* CONFIG_SMP */
+#else /* CONFIG_SMP */
+
+struct sched_domain_attr;
+
+static inline void
+partition_sched_domains(int ndoms_new, cpumask_t *doms_new,
+			struct sched_domain_attr *dattr_new)
+{
+}
+#endif	/* !CONFIG_SMP */
 
 struct io_context;			/* See blkdev.h */
 #define NGROUPS_SMALL		32

init/main.c

@@ -415,6 +415,13 @@ static void __init smp_init(void)
 {
 	unsigned int cpu;
 
+	/*
+	 * Set up the current CPU as possible to migrate to.
+	 * The other ones will be done by cpu_up/cpu_down()
+	 */
+	cpu = smp_processor_id();
+	cpu_set(cpu, cpu_active_map);
+
 	/* FIXME: This should be done in userspace --RR */
 	for_each_present_cpu(cpu) {
 		if (num_online_cpus() >= setup_max_cpus)

kernel/Kconfig.hz

@@ -55,4 +55,4 @@ config HZ
 	default 1000 if HZ_1000
 
 config SCHED_HRTICK
-	def_bool HIGH_RES_TIMERS && X86
+	def_bool HIGH_RES_TIMERS

kernel/Makefile

@@ -11,6 +11,8 @@ obj-y     = sched.o fork.o exec_domain.o panic.o printk.o profile.o \
 	    hrtimer.o rwsem.o nsproxy.o srcu.o semaphore.o \
 	    notifier.o ksysfs.o pm_qos_params.o sched_clock.o
 
+CFLAGS_REMOVE_sched.o = -mno-spe
+
 ifdef CONFIG_FTRACE
 # Do not trace debug files and internal ftrace files
 CFLAGS_REMOVE_lockdep.o = -pg

kernel/cpu.c

@@ -64,6 +64,8 @@ void __init cpu_hotplug_init(void)
 	cpu_hotplug.refcount = 0;
 }
 
+cpumask_t cpu_active_map;
+
 #ifdef CONFIG_HOTPLUG_CPU
 
 void get_online_cpus(void)
@@ -291,11 +293,30 @@ int __ref cpu_down(unsigned int cpu)
 	int err = 0;
 
 	cpu_maps_update_begin();
-	if (cpu_hotplug_disabled)
+
+	if (cpu_hotplug_disabled) {
 		err = -EBUSY;
-	else
-		err = _cpu_down(cpu, 0);
+		goto out;
+	}
+
+	cpu_clear(cpu, cpu_active_map);
+
+	/*
+	 * Make sure the all cpus did the reschedule and are not
+	 * using stale version of the cpu_active_map.
+	 * This is not strictly necessary becuase stop_machine()
+	 * that we run down the line already provides the required
+	 * synchronization. But it's really a side effect and we do not
+	 * want to depend on the innards of the stop_machine here.
+	 */
+	synchronize_sched();
+
+	err = _cpu_down(cpu, 0);
 
+	if (cpu_online(cpu))
+		cpu_set(cpu, cpu_active_map);
+
+out:
 	cpu_maps_update_done();
 	return err;
 }
@@ -355,11 +376,18 @@ int __cpuinit cpu_up(unsigned int cpu)
 	}
 
 	cpu_maps_update_begin();
-	if (cpu_hotplug_disabled)
+
+	if (cpu_hotplug_disabled) {
 		err = -EBUSY;
-	else
-		err = _cpu_up(cpu, 0);
+		goto out;
+	}
+
+	err = _cpu_up(cpu, 0);
 
+	if (cpu_online(cpu))
+		cpu_set(cpu, cpu_active_map);
+
+out:
 	cpu_maps_update_done();
 	return err;
 }

kernel/cpuset.c

@@ -564,7 +564,7 @@ update_domain_attr(struct sched_domain_attr *dattr, struct cpuset *c)
  *	partition_sched_domains().
  */
 
-static void rebuild_sched_domains(void)
+void rebuild_sched_domains(void)
 {
 	struct kfifo *q;	/* queue of cpusets to be scanned */
 	struct cpuset *cp;	/* scans q */

kernel/sched_fair.c

@@ -878,7 +878,6 @@ entity_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr, int queued)
 #ifdef CONFIG_SCHED_HRTICK
 static void hrtick_start_fair(struct rq *rq, struct task_struct *p)
 {
-	int requeue = rq->curr == p;
 	struct sched_entity *se = &p->se;
 	struct cfs_rq *cfs_rq = cfs_rq_of(se);
 
@@ -899,10 +898,10 @@ static void hrtick_start_fair(struct rq *rq, struct task_struct *p)
 		 * Don't schedule slices shorter than 10000ns, that just
 		 * doesn't make sense. Rely on vruntime for fairness.
 		 */
-		if (!requeue)
+		if (rq->curr != p)
 			delta = max(10000LL, delta);
 
-		hrtick_start(rq, delta, requeue);
+		hrtick_start(rq, delta);
 	}
 }
 #else /* !CONFIG_SCHED_HRTICK */
@@ -1004,6 +1003,8 @@ static void yield_task_fair(struct rq *rq)
  * not idle and an idle cpu is available.  The span of cpus to
  * search starts with cpus closest then further out as needed,
  * so we always favor a closer, idle cpu.
+ * Domains may include CPUs that are not usable for migration,
+ * hence we need to mask them out (cpu_active_map)
  *
  * Returns the CPU we should wake onto.
  */
@@ -1031,6 +1032,7 @@ static int wake_idle(int cpu, struct task_struct *p)
 		    || ((sd->flags & SD_WAKE_IDLE_FAR)
 			&& !task_hot(p, task_rq(p)->clock, sd))) {
 			cpus_and(tmp, sd->span, p->cpus_allowed);
+			cpus_and(tmp, tmp, cpu_active_map);
 			for_each_cpu_mask_nr(i, tmp) {
 				if (idle_cpu(i)) {
 					if (i != task_cpu(p)) {

kernel/sched_rt.c

@@ -505,7 +505,9 @@ void inc_rt_tasks(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
 	rt_rq->rt_nr_running++;
 #if defined CONFIG_SMP || defined CONFIG_RT_GROUP_SCHED
 	if (rt_se_prio(rt_se) < rt_rq->highest_prio) {
+#ifdef CONFIG_SMP
 		struct rq *rq = rq_of_rt_rq(rt_rq);
+#endif
 
 		rt_rq->highest_prio = rt_se_prio(rt_se);
 #ifdef CONFIG_SMP
@@ -599,11 +601,7 @@ static void __enqueue_rt_entity(struct sched_rt_entity *rt_se)
 	if (group_rq && (rt_rq_throttled(group_rq) || !group_rq->rt_nr_running))
 		return;
 
-	if (rt_se->nr_cpus_allowed == 1)
-		list_add(&rt_se->run_list, queue);
-	else
-		list_add_tail(&rt_se->run_list, queue);
-
+	list_add_tail(&rt_se->run_list, queue);
 	__set_bit(rt_se_prio(rt_se), array->bitmap);
 
 	inc_rt_tasks(rt_se, rt_rq);
@@ -688,32 +686,34 @@ static void dequeue_task_rt(struct rq *rq, struct task_struct *p, int sleep)
  * Put task to the end of the run list without the overhead of dequeue
  * followed by enqueue.
  */
-static
-void requeue_rt_entity(struct rt_rq *rt_rq, struct sched_rt_entity *rt_se)
+static void
+requeue_rt_entity(struct rt_rq *rt_rq, struct sched_rt_entity *rt_se, int head)
 {
-	struct rt_prio_array *array = &rt_rq->active;
-
 	if (on_rt_rq(rt_se)) {
-		list_del_init(&rt_se->run_list);
-		list_add_tail(&rt_se->run_list,
-			      array->queue + rt_se_prio(rt_se));
+		struct rt_prio_array *array = &rt_rq->active;
+		struct list_head *queue = array->queue + rt_se_prio(rt_se);
+
+		if (head)
+			list_move(&rt_se->run_list, queue);
+		else
+			list_move_tail(&rt_se->run_list, queue);
 	}
 }
 
-static void requeue_task_rt(struct rq *rq, struct task_struct *p)
+static void requeue_task_rt(struct rq *rq, struct task_struct *p, int head)
 {
 	struct sched_rt_entity *rt_se = &p->rt;
 	struct rt_rq *rt_rq;
 
 	for_each_sched_rt_entity(rt_se) {
 		rt_rq = rt_rq_of_se(rt_se);
-		requeue_rt_entity(rt_rq, rt_se);
+		requeue_rt_entity(rt_rq, rt_se, head);
 	}
 }
 
 static void yield_task_rt(struct rq *rq)
 {
-	requeue_task_rt(rq, rq->curr);
+	requeue_task_rt(rq, rq->curr, 0);
 }
 
 #ifdef CONFIG_SMP
@@ -753,6 +753,30 @@ static int select_task_rq_rt(struct task_struct *p, int sync)
 	 */
 	return task_cpu(p);
 }
+
+static void check_preempt_equal_prio(struct rq *rq, struct task_struct *p)
+{
+	cpumask_t mask;
+
+	if (rq->curr->rt.nr_cpus_allowed == 1)
+		return;
+
+	if (p->rt.nr_cpus_allowed != 1
+	    && cpupri_find(&rq->rd->cpupri, p, &mask))
+		return;
+
+	if (!cpupri_find(&rq->rd->cpupri, rq->curr, &mask))
+		return;
+
+	/*
+	 * There appears to be other cpus that can accept
+	 * current and none to run 'p', so lets reschedule
+	 * to try and push current away:
+	 */
+	requeue_task_rt(rq, p, 1);
+	resched_task(rq->curr);
+}
+
 #endif /* CONFIG_SMP */
 
 /*
@@ -778,18 +802,8 @@ static void check_preempt_curr_rt(struct rq *rq, struct task_struct *p)
 	 * to move current somewhere else, making room for our non-migratable
 	 * task.
 	 */
-	if((p->prio == rq->curr->prio)
-	   && p->rt.nr_cpus_allowed == 1
-	   && rq->curr->rt.nr_cpus_allowed != 1) {
-		cpumask_t mask;
-
-		if (cpupri_find(&rq->rd->cpupri, rq->curr, &mask))
-			/*
-			 * There appears to be other cpus that can accept
-			 * current, so lets reschedule to try and push it away
-			 */
-			resched_task(rq->curr);
-	}
+	if (p->prio == rq->curr->prio && !need_resched())
+		check_preempt_equal_prio(rq, p);
 #endif
 }
 
@@ -921,6 +935,13 @@ static int find_lowest_rq(struct task_struct *task)
 	if (!cpupri_find(&task_rq(task)->rd->cpupri, task, lowest_mask))
 		return -1; /* No targets found */
 
+	/*
+	 * Only consider CPUs that are usable for migration.
+	 * I guess we might want to change cpupri_find() to ignore those
+	 * in the first place.
+	 */
+	cpus_and(*lowest_mask, *lowest_mask, cpu_active_map);
+
 	/*
 	 * At this point we have built a mask of cpus representing the
 	 * lowest priority tasks in the system.  Now we want to elect
@@ -1415,7 +1436,7 @@ static void task_tick_rt(struct rq *rq, struct task_struct *p, int queued)
 	 * on the queue:
 	 */
 	if (p->rt.run_list.prev != p->rt.run_list.next) {
-		requeue_task_rt(rq, p);
+		requeue_task_rt(rq, p, 0);
 		set_tsk_need_resched(p);
 	}
 }