Merge branch 'sched-core-for-linus' of git://git.kernel.org/pub/scm/l…

…inux/kernel/git/tip/tip

Pull scheduler changes from Ingo Molnar:
 "The biggest change is a performance improvement on SMP systems:

  | 4 socket 40 core + SMT Westmere box, single 30 sec tbench
  | runs, higher is better:
  |
  | clients     1       2       4        8       16       32       64      128
  |..........................................................................
  | pre        30      41     118      645     3769     6214    12233    14312
  | post      299     603    1211     2418     4697     6847    11606    14557
  |
  | A nice increase in performance.

  which speedup is particularly noticeable on heavily interacting
  few-tasks workloads, so the changes should help desktop-style Xorg
  workloads and interactivity as well, on multi-core CPUs.

  There are also cpuset suspend behavior fixes/restructuring and various
  smaller tweaks."

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  sched: Fix race in task_group()
  sched: Improve balance_cpu() to consider other cpus in its group as target of (pinned) task
  sched: Reset loop counters if all tasks are pinned and we need to redo load balance
  sched: Reorder 'struct lb_env' members to reduce its size
  sched: Improve scalability via 'CPU buddies', which withstand random perturbations
  cpusets: Remove/update outdated comments
  cpusets, hotplug: Restructure functions that are invoked during hotplug
  cpusets, hotplug: Implement cpuset tree traversal in a helper function
  CPU hotplug, cpusets, suspend: Don't modify cpusets during suspend/resume
  sched/x86: Remove broken power estimation

arch/x86/kernel/cpu/Makefile

@@ -14,7 +14,7 @@ CFLAGS_common.o		:= $(nostackp)
 
 obj-y			:= intel_cacheinfo.o scattered.o topology.o
 obj-y			+= proc.o capflags.o powerflags.o common.o
-obj-y			+= vmware.o hypervisor.o sched.o mshyperv.o
+obj-y			+= vmware.o hypervisor.o mshyperv.o
 obj-y			+= rdrand.o
 obj-y			+= match.o
 

include/linux/cpuset.h

@@ -20,7 +20,7 @@ extern int number_of_cpusets;	/* How many cpusets are defined in system? */
 
 extern int cpuset_init(void);
 extern void cpuset_init_smp(void);
-extern void cpuset_update_active_cpus(void);
+extern void cpuset_update_active_cpus(bool cpu_online);
 extern void cpuset_cpus_allowed(struct task_struct *p, struct cpumask *mask);
 extern void cpuset_cpus_allowed_fallback(struct task_struct *p);
 extern nodemask_t cpuset_mems_allowed(struct task_struct *p);
@@ -124,7 +124,7 @@ static inline void set_mems_allowed(nodemask_t nodemask)
 static inline int cpuset_init(void) { return 0; }
 static inline void cpuset_init_smp(void) {}
 
-static inline void cpuset_update_active_cpus(void)
+static inline void cpuset_update_active_cpus(bool cpu_online)
 {
 	partition_sched_domains(1, NULL, NULL);
 }

include/linux/init_task.h

@@ -123,8 +123,17 @@ extern struct group_info init_groups;
 
 extern struct cred init_cred;
 
+extern struct task_group root_task_group;
+
+#ifdef CONFIG_CGROUP_SCHED
+# define INIT_CGROUP_SCHED(tsk)						\
+	.sched_task_group = &root_task_group,
+#else
+# define INIT_CGROUP_SCHED(tsk)
+#endif
+
 #ifdef CONFIG_PERF_EVENTS
-# define INIT_PERF_EVENTS(tsk)					\
+# define INIT_PERF_EVENTS(tsk)						\
 	.perf_event_mutex = 						\
 		 __MUTEX_INITIALIZER(tsk.perf_event_mutex),		\
 	.perf_event_list = LIST_HEAD_INIT(tsk.perf_event_list),
@@ -161,6 +170,7 @@ extern struct cred init_cred;
 	},								\
 	.tasks		= LIST_HEAD_INIT(tsk.tasks),			\
 	INIT_PUSHABLE_TASKS(tsk)					\
+	INIT_CGROUP_SCHED(tsk)						\
 	.ptraced	= LIST_HEAD_INIT(tsk.ptraced),			\
 	.ptrace_entry	= LIST_HEAD_INIT(tsk.ptrace_entry),		\
 	.real_parent	= &tsk,						\

include/linux/sched.h

@@ -949,6 +949,7 @@ struct sched_domain {
 	unsigned int smt_gain;
 	int flags;			/* See SD_* */
 	int level;
+	int idle_buddy;			/* cpu assigned to select_idle_sibling() */
 
 	/* Runtime fields. */
 	unsigned long last_balance;	/* init to jiffies. units in jiffies */
@@ -1244,6 +1245,9 @@ struct task_struct {
 	const struct sched_class *sched_class;
 	struct sched_entity se;
 	struct sched_rt_entity rt;
+#ifdef CONFIG_CGROUP_SCHED
+	struct task_group *sched_task_group;
+#endif
 
 #ifdef CONFIG_PREEMPT_NOTIFIERS
 	/* list of struct preempt_notifier: */
@@ -2721,7 +2725,7 @@ extern int sched_group_set_rt_period(struct task_group *tg,
 extern long sched_group_rt_period(struct task_group *tg);
 extern int sched_rt_can_attach(struct task_group *tg, struct task_struct *tsk);
 #endif
-#endif
+#endif /* CONFIG_CGROUP_SCHED */
 
 extern int task_can_switch_user(struct user_struct *up,
 					struct task_struct *tsk);

kernel/cpuset.c

@@ -147,6 +147,12 @@ typedef enum {
 	CS_SPREAD_SLAB,
 } cpuset_flagbits_t;
 
+/* the type of hotplug event */
+enum hotplug_event {
+	CPUSET_CPU_OFFLINE,
+	CPUSET_MEM_OFFLINE,
+};
+
 /* convenient tests for these bits */
 static inline int is_cpu_exclusive(const struct cpuset *cs)
 {
@@ -1990,8 +1996,36 @@ static void remove_tasks_in_empty_cpuset(struct cpuset *cs)
 }
 
 /*
- * Walk the specified cpuset subtree and look for empty cpusets.
- * The tasks of such cpuset must be moved to a parent cpuset.
+ * Helper function to traverse cpusets.
+ * It can be used to walk the cpuset tree from top to bottom, completing
+ * one layer before dropping down to the next (thus always processing a
+ * node before any of its children).
+ */
+static struct cpuset *cpuset_next(struct list_head *queue)
+{
+	struct cpuset *cp;
+	struct cpuset *child;	/* scans child cpusets of cp */
+	struct cgroup *cont;
+
+	if (list_empty(queue))
+		return NULL;
+
+	cp = list_first_entry(queue, struct cpuset, stack_list);
+	list_del(queue->next);
+	list_for_each_entry(cont, &cp->css.cgroup->children, sibling) {
+		child = cgroup_cs(cont);
+		list_add_tail(&child->stack_list, queue);
+	}
+
+	return cp;
+}
+
+
+/*
+ * Walk the specified cpuset subtree upon a hotplug operation (CPU/Memory
+ * online/offline) and update the cpusets accordingly.
+ * For regular CPU/Mem hotplug, look for empty cpusets; the tasks of such
+ * cpuset must be moved to a parent cpuset.
  *
  * Called with cgroup_mutex held.  We take callback_mutex to modify
  * cpus_allowed and mems_allowed.
@@ -2000,50 +2034,61 @@ static void remove_tasks_in_empty_cpuset(struct cpuset *cs)
  * before dropping down to the next.  It always processes a node before
  * any of its children.
  *
- * For now, since we lack memory hot unplug, we'll never see a cpuset
- * 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.
+ * In the case of memory hot-unplug, it will remove nodes from N_HIGH_MEMORY
+ * if all present pages from a node are offlined.
  */
-static void scan_for_empty_cpusets(struct cpuset *root)
+static void
+scan_cpusets_upon_hotplug(struct cpuset *root, enum hotplug_event event)
 {
 	LIST_HEAD(queue);
-	struct cpuset *cp;	/* scans cpusets being updated */
-	struct cpuset *child;	/* scans child cpusets of cp */
-	struct cgroup *cont;
+	struct cpuset *cp;		/* scans cpusets being updated */
 	static nodemask_t oldmems;	/* protected by cgroup_mutex */
 
 	list_add_tail((struct list_head *)&root->stack_list, &queue);
 
-	while (!list_empty(&queue)) {
-		cp = list_first_entry(&queue, struct cpuset, stack_list);
-		list_del(queue.next);
-		list_for_each_entry(cont, &cp->css.cgroup->children, sibling) {
-			child = cgroup_cs(cont);
-			list_add_tail(&child->stack_list, &queue);
+	switch (event) {
+	case CPUSET_CPU_OFFLINE:
+		while ((cp = cpuset_next(&queue)) != NULL) {
+
+			/* Continue past cpusets with all cpus online */
+			if (cpumask_subset(cp->cpus_allowed, cpu_active_mask))
+				continue;
+
+			/* Remove offline cpus from this cpuset. */
+			mutex_lock(&callback_mutex);
+			cpumask_and(cp->cpus_allowed, cp->cpus_allowed,
+							cpu_active_mask);
+			mutex_unlock(&callback_mutex);
+
+			/* Move tasks from the empty cpuset to a parent */
+			if (cpumask_empty(cp->cpus_allowed))
+				remove_tasks_in_empty_cpuset(cp);
+			else
+				update_tasks_cpumask(cp, NULL);
 		}
+		break;
 
-		/* Continue past cpusets with all cpus, mems online */
-		if (cpumask_subset(cp->cpus_allowed, cpu_active_mask) &&
-		    nodes_subset(cp->mems_allowed, node_states[N_HIGH_MEMORY]))
-			continue;
+	case CPUSET_MEM_OFFLINE:
+		while ((cp = cpuset_next(&queue)) != NULL) {
 
-		oldmems = cp->mems_allowed;
+			/* Continue past cpusets with all mems online */
+			if (nodes_subset(cp->mems_allowed,
+					node_states[N_HIGH_MEMORY]))
+				continue;
 
-		/* Remove offline cpus and mems from this cpuset. */
-		mutex_lock(&callback_mutex);
-		cpumask_and(cp->cpus_allowed, cp->cpus_allowed,
-			    cpu_active_mask);
-		nodes_and(cp->mems_allowed, cp->mems_allowed,
+			oldmems = cp->mems_allowed;
+
+			/* Remove offline mems from this cpuset. */
+			mutex_lock(&callback_mutex);
+			nodes_and(cp->mems_allowed, cp->mems_allowed,
 						node_states[N_HIGH_MEMORY]);
-		mutex_unlock(&callback_mutex);
+			mutex_unlock(&callback_mutex);
 
-		/* Move tasks from the empty cpuset to a parent */
-		if (cpumask_empty(cp->cpus_allowed) ||
-		     nodes_empty(cp->mems_allowed))
-			remove_tasks_in_empty_cpuset(cp);
-		else {
-			update_tasks_cpumask(cp, NULL);
-			update_tasks_nodemask(cp, &oldmems, NULL);
+			/* Move tasks from the empty cpuset to a parent */
+			if (nodes_empty(cp->mems_allowed))
+				remove_tasks_in_empty_cpuset(cp);
+			else
+				update_tasks_nodemask(cp, &oldmems, NULL);
 		}
 	}
 }
@@ -2054,13 +2099,19 @@ static void scan_for_empty_cpusets(struct cpuset *root)
  * (of no affect) on systems that are actively using CPU hotplug
  * but making no active use of cpusets.
  *
+ * The only exception to this is suspend/resume, where we don't
+ * modify cpusets at all.
+ *
  * This routine ensures that top_cpuset.cpus_allowed tracks
  * cpu_active_mask on each CPU hotplug (cpuhp) event.
  *
  * Called within get_online_cpus().  Needs to call cgroup_lock()
  * before calling generate_sched_domains().
+ *
+ * @cpu_online: Indicates whether this is a CPU online event (true) or
+ * a CPU offline event (false).
  */
-void cpuset_update_active_cpus(void)
+void cpuset_update_active_cpus(bool cpu_online)
 {
 	struct sched_domain_attr *attr;
 	cpumask_var_t *doms;
@@ -2070,7 +2121,10 @@ void cpuset_update_active_cpus(void)
 	mutex_lock(&callback_mutex);
 	cpumask_copy(top_cpuset.cpus_allowed, cpu_active_mask);
 	mutex_unlock(&callback_mutex);
-	scan_for_empty_cpusets(&top_cpuset);
+
+	if (!cpu_online)
+		scan_cpusets_upon_hotplug(&top_cpuset, CPUSET_CPU_OFFLINE);
+
 	ndoms = generate_sched_domains(&doms, &attr);
 	cgroup_unlock();
 
@@ -2082,7 +2136,7 @@ void cpuset_update_active_cpus(void)
 /*
  * Keep top_cpuset.mems_allowed tracking node_states[N_HIGH_MEMORY].
  * Call this routine anytime after node_states[N_HIGH_MEMORY] changes.
- * See also the previous routine cpuset_track_online_cpus().
+ * See cpuset_update_active_cpus() for CPU hotplug handling.
  */
 static int cpuset_track_online_nodes(struct notifier_block *self,
 				unsigned long action, void *arg)
@@ -2101,9 +2155,9 @@ static int cpuset_track_online_nodes(struct notifier_block *self,
 	case MEM_OFFLINE:
 		/*
 		 * needn't update top_cpuset.mems_allowed explicitly because
-		 * scan_for_empty_cpusets() will update it.
+		 * scan_cpusets_upon_hotplug() will update it.
 		 */
-		scan_for_empty_cpusets(&top_cpuset);
+		scan_cpusets_upon_hotplug(&top_cpuset, CPUSET_MEM_OFFLINE);
 		break;
 	default:
 		break;