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

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (30 commits)
  sched: Change wait_for_completion_*_timeout() to return a signed long
  sched, autogroup: Fix reference leak
  sched, autogroup: Fix potential access to freed memory
  sched: Remove redundant CONFIG_CGROUP_SCHED ifdef
  sched: Fix interactivity bug by charging unaccounted run-time on entity re-weight
  sched: Move periodic share updates to entity_tick()
  printk: Use this_cpu_{read|write} api on printk_pending
  sched: Make pushable_tasks CONFIG_SMP dependant
  sched: Add 'autogroup' scheduling feature: automated per session task groups
  sched: Fix unregister_fair_sched_group()
  sched: Remove unused argument dest_cpu to migrate_task()
  mutexes, sched: Introduce arch_mutex_cpu_relax()
  sched: Add some clock info to sched_debug
  cpu: Remove incorrect BUG_ON
  cpu: Remove unused variable
  sched: Fix UP build breakage
  sched: Make task dump print all 15 chars of proc comm
  sched: Update tg->shares after cpu.shares write
  sched: Allow update_cfs_load() to update global load
  sched: Implement demand based update_cfs_load()
  ...

Documentation/kernel-parameters.txt

@@ -1614,6 +1614,8 @@ and is between 256 and 4096 characters. It is defined in the file
 	noapic		[SMP,APIC] Tells the kernel to not make use of any
 			IOAPICs that may be present in the system.
 
+	noautogroup	Disable scheduler automatic task group creation.
+
 	nobats		[PPC] Do not use BATs for mapping kernel lowmem
 			on "Classic" PPC cores.
 

arch/Kconfig

@@ -175,4 +175,7 @@ config HAVE_PERF_EVENTS_NMI
 config HAVE_ARCH_JUMP_LABEL
 	bool
 
+config HAVE_ARCH_MUTEX_CPU_RELAX
+	bool
+
 source "kernel/gcov/Kconfig"

arch/s390/Kconfig

@@ -99,6 +99,7 @@ config S390
 	select HAVE_KERNEL_LZMA
 	select HAVE_KERNEL_LZO
 	select HAVE_GET_USER_PAGES_FAST
+	select HAVE_ARCH_MUTEX_CPU_RELAX
 	select ARCH_INLINE_SPIN_TRYLOCK
 	select ARCH_INLINE_SPIN_TRYLOCK_BH
 	select ARCH_INLINE_SPIN_LOCK

arch/s390/include/asm/mutex.h

@@ -7,3 +7,5 @@
  */
 
 #include <asm-generic/mutex-dec.h>
+
+#define arch_mutex_cpu_relax()	barrier()

fs/proc/base.c

@@ -1407,6 +1407,82 @@ static const struct file_operations proc_pid_sched_operations = {
 
 #endif
 
+#ifdef CONFIG_SCHED_AUTOGROUP
+/*
+ * Print out autogroup related information:
+ */
+static int sched_autogroup_show(struct seq_file *m, void *v)
+{
+	struct inode *inode = m->private;
+	struct task_struct *p;
+
+	p = get_proc_task(inode);
+	if (!p)
+		return -ESRCH;
+	proc_sched_autogroup_show_task(p, m);
+
+	put_task_struct(p);
+
+	return 0;
+}
+
+static ssize_t
+sched_autogroup_write(struct file *file, const char __user *buf,
+	    size_t count, loff_t *offset)
+{
+	struct inode *inode = file->f_path.dentry->d_inode;
+	struct task_struct *p;
+	char buffer[PROC_NUMBUF];
+	long nice;
+	int err;
+
+	memset(buffer, 0, sizeof(buffer));
+	if (count > sizeof(buffer) - 1)
+		count = sizeof(buffer) - 1;
+	if (copy_from_user(buffer, buf, count))
+		return -EFAULT;
+
+	err = strict_strtol(strstrip(buffer), 0, &nice);
+	if (err)
+		return -EINVAL;
+
+	p = get_proc_task(inode);
+	if (!p)
+		return -ESRCH;
+
+	err = nice;
+	err = proc_sched_autogroup_set_nice(p, &err);
+	if (err)
+		count = err;
+
+	put_task_struct(p);
+
+	return count;
+}
+
+static int sched_autogroup_open(struct inode *inode, struct file *filp)
+{
+	int ret;
+
+	ret = single_open(filp, sched_autogroup_show, NULL);
+	if (!ret) {
+		struct seq_file *m = filp->private_data;
+
+		m->private = inode;
+	}
+	return ret;
+}
+
+static const struct file_operations proc_pid_sched_autogroup_operations = {
+	.open		= sched_autogroup_open,
+	.read		= seq_read,
+	.write		= sched_autogroup_write,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+#endif /* CONFIG_SCHED_AUTOGROUP */
+
 static ssize_t comm_write(struct file *file, const char __user *buf,
 				size_t count, loff_t *offset)
 {
@@ -2732,6 +2808,9 @@ static const struct pid_entry tgid_base_stuff[] = {
 	INF("limits",	  S_IRUGO, proc_pid_limits),
 #ifdef CONFIG_SCHED_DEBUG
 	REG("sched",      S_IRUGO|S_IWUSR, proc_pid_sched_operations),
+#endif
+#ifdef CONFIG_SCHED_AUTOGROUP
+	REG("autogroup",  S_IRUGO|S_IWUSR, proc_pid_sched_autogroup_operations),
 #endif
 	REG("comm",      S_IRUGO|S_IWUSR, proc_pid_set_comm_operations),
 #ifdef CONFIG_HAVE_ARCH_TRACEHOOK

include/linux/completion.h

@@ -81,10 +81,10 @@ extern int wait_for_completion_interruptible(struct completion *x);
 extern int wait_for_completion_killable(struct completion *x);
 extern unsigned long wait_for_completion_timeout(struct completion *x,
 						   unsigned long timeout);
-extern unsigned long wait_for_completion_interruptible_timeout(
-			struct completion *x, unsigned long timeout);
-extern unsigned long wait_for_completion_killable_timeout(
-			struct completion *x, unsigned long timeout);
+extern long wait_for_completion_interruptible_timeout(
+	struct completion *x, unsigned long timeout);
+extern long wait_for_completion_killable_timeout(
+	struct completion *x, unsigned long timeout);
 extern bool try_wait_for_completion(struct completion *x);
 extern bool completion_done(struct completion *x);
 

include/linux/init_task.h

@@ -12,6 +12,13 @@
 #include <linux/securebits.h>
 #include <net/net_namespace.h>
 
+#ifdef CONFIG_SMP
+# define INIT_PUSHABLE_TASKS(tsk)					\
+	.pushable_tasks = PLIST_NODE_INIT(tsk.pushable_tasks, MAX_PRIO),
+#else
+# define INIT_PUSHABLE_TASKS(tsk)
+#endif
+
 extern struct files_struct init_files;
 extern struct fs_struct init_fs;
 
@@ -144,7 +151,7 @@ extern struct cred init_cred;
 		.nr_cpus_allowed = NR_CPUS,				\
 	},								\
 	.tasks		= LIST_HEAD_INIT(tsk.tasks),			\
-	.pushable_tasks = PLIST_NODE_INIT(tsk.pushable_tasks, MAX_PRIO), \
+	INIT_PUSHABLE_TASKS(tsk)					\
 	.ptraced	= LIST_HEAD_INIT(tsk.ptraced),			\
 	.ptrace_entry	= LIST_HEAD_INIT(tsk.ptrace_entry),		\
 	.real_parent	= &tsk,						\

include/linux/mutex.h

@@ -160,4 +160,8 @@ extern int mutex_trylock(struct mutex *lock);
 extern void mutex_unlock(struct mutex *lock);
 extern int atomic_dec_and_mutex_lock(atomic_t *cnt, struct mutex *lock);
 
+#ifndef CONFIG_HAVE_ARCH_MUTEX_CPU_RELAX
+#define arch_mutex_cpu_relax()	cpu_relax()
+#endif
+
 #endif

include/linux/sched.h

@@ -513,6 +513,8 @@ struct thread_group_cputimer {
 	spinlock_t lock;
 };
 
+struct autogroup;
+
 /*
  * NOTE! "signal_struct" does not have it's own
  * locking, because a shared signal_struct always
@@ -580,6 +582,9 @@ struct signal_struct {
 
 	struct tty_struct *tty; /* NULL if no tty */
 
+#ifdef CONFIG_SCHED_AUTOGROUP
+	struct autogroup *autogroup;
+#endif
 	/*
 	 * Cumulative resource counters for dead threads in the group,
 	 * and for reaped dead child processes forked by this group.
@@ -1242,7 +1247,9 @@ struct task_struct {
 #endif
 
 	struct list_head tasks;
+#ifdef CONFIG_SMP
 	struct plist_node pushable_tasks;
+#endif
 
 	struct mm_struct *mm, *active_mm;
 #if defined(SPLIT_RSS_COUNTING)
@@ -1883,14 +1890,11 @@ extern void sched_clock_idle_sleep_event(void);
 extern void sched_clock_idle_wakeup_event(u64 delta_ns);
 
 #ifdef CONFIG_HOTPLUG_CPU
-extern void move_task_off_dead_cpu(int dead_cpu, struct task_struct *p);
 extern void idle_task_exit(void);
 #else
 static inline void idle_task_exit(void) {}
 #endif
 
-extern void sched_idle_next(void);
-
 #if defined(CONFIG_NO_HZ) && defined(CONFIG_SMP)
 extern void wake_up_idle_cpu(int cpu);
 #else
@@ -1900,8 +1904,6 @@ static inline void wake_up_idle_cpu(int cpu) { }
 extern unsigned int sysctl_sched_latency;
 extern unsigned int sysctl_sched_min_granularity;
 extern unsigned int sysctl_sched_wakeup_granularity;
-extern unsigned int sysctl_sched_shares_ratelimit;
-extern unsigned int sysctl_sched_shares_thresh;
 extern unsigned int sysctl_sched_child_runs_first;
 
 enum sched_tunable_scaling {
@@ -1917,6 +1919,7 @@ extern unsigned int sysctl_sched_migration_cost;
 extern unsigned int sysctl_sched_nr_migrate;
 extern unsigned int sysctl_sched_time_avg;
 extern unsigned int sysctl_timer_migration;
+extern unsigned int sysctl_sched_shares_window;
 
 int sched_proc_update_handler(struct ctl_table *table, int write,
 		void __user *buffer, size_t *length,
@@ -1942,6 +1945,24 @@ int sched_rt_handler(struct ctl_table *table, int write,
 
 extern unsigned int sysctl_sched_compat_yield;
 
+#ifdef CONFIG_SCHED_AUTOGROUP
+extern unsigned int sysctl_sched_autogroup_enabled;
+
+extern void sched_autogroup_create_attach(struct task_struct *p);
+extern void sched_autogroup_detach(struct task_struct *p);
+extern void sched_autogroup_fork(struct signal_struct *sig);
+extern void sched_autogroup_exit(struct signal_struct *sig);
+#ifdef CONFIG_PROC_FS
+extern void proc_sched_autogroup_show_task(struct task_struct *p, struct seq_file *m);
+extern int proc_sched_autogroup_set_nice(struct task_struct *p, int *nice);
+#endif
+#else
+static inline void sched_autogroup_create_attach(struct task_struct *p) { }
+static inline void sched_autogroup_detach(struct task_struct *p) { }
+static inline void sched_autogroup_fork(struct signal_struct *sig) { }
+static inline void sched_autogroup_exit(struct signal_struct *sig) { }
+#endif
+
 #ifdef CONFIG_RT_MUTEXES
 extern int rt_mutex_getprio(struct task_struct *p);
 extern void rt_mutex_setprio(struct task_struct *p, int prio);
@@ -1960,9 +1981,10 @@ extern int task_nice(const struct task_struct *p);
 extern int can_nice(const struct task_struct *p, const int nice);
 extern int task_curr(const struct task_struct *p);
 extern int idle_cpu(int cpu);
-extern int sched_setscheduler(struct task_struct *, int, struct sched_param *);
+extern int sched_setscheduler(struct task_struct *, int,
+			      const struct sched_param *);
 extern int sched_setscheduler_nocheck(struct task_struct *, int,
-				      struct sched_param *);
+				      const struct sched_param *);
 extern struct task_struct *idle_task(int cpu);
 extern struct task_struct *curr_task(int cpu);
 extern void set_curr_task(int cpu, struct task_struct *p);

init/Kconfig

@@ -794,6 +794,19 @@ config NET_NS
 
 endif # NAMESPACES
 
+config SCHED_AUTOGROUP
+	bool "Automatic process group scheduling"
+	select EVENTFD
+	select CGROUPS
+	select CGROUP_SCHED
+	select FAIR_GROUP_SCHED
+	help
+	  This option optimizes the scheduler for common desktop workloads by
+	  automatically creating and populating task groups.  This separation
+	  of workloads isolates aggressive CPU burners (like build jobs) from
+	  desktop applications.  Task group autogeneration is currently based
+	  upon task session.
+
 config MM_OWNER
 	bool
 

kernel/cpu.c

@@ -189,7 +189,6 @@ static inline void check_for_tasks(int cpu)
 }
 
 struct take_cpu_down_param {
-	struct task_struct *caller;
 	unsigned long mod;
 	void *hcpu;
 };
@@ -198,7 +197,6 @@ struct take_cpu_down_param {
 static int __ref take_cpu_down(void *_param)
 {
 	struct take_cpu_down_param *param = _param;
-	unsigned int cpu = (unsigned long)param->hcpu;
 	int err;
 
 	/* Ensure this CPU doesn't handle any more interrupts. */
@@ -208,11 +206,6 @@ static int __ref take_cpu_down(void *_param)
 
 	cpu_notify(CPU_DYING | param->mod, param->hcpu);
 
-	if (task_cpu(param->caller) == cpu)
-		move_task_off_dead_cpu(cpu, param->caller);
-	/* Force idle task to run as soon as we yield: it should
-	   immediately notice cpu is offline and die quickly. */
-	sched_idle_next();
 	return 0;
 }
 
@@ -223,7 +216,6 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen)
 	void *hcpu = (void *)(long)cpu;
 	unsigned long mod = tasks_frozen ? CPU_TASKS_FROZEN : 0;
 	struct take_cpu_down_param tcd_param = {
-		.caller = current,
 		.mod = mod,
 		.hcpu = hcpu,
 	};
@@ -253,9 +245,15 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen)
 	}
 	BUG_ON(cpu_online(cpu));
 
-	/* Wait for it to sleep (leaving idle task). */
+	/*
+	 * The migration_call() CPU_DYING callback will have removed all
+	 * runnable tasks from the cpu, there's only the idle task left now
+	 * that the migration thread is done doing the stop_machine thing.
+	 *
+	 * Wait for the stop thread to go away.
+	 */
 	while (!idle_cpu(cpu))
-		yield();
+		cpu_relax();
 
 	/* This actually kills the CPU. */
 	__cpu_die(cpu);

kernel/fork.c

@@ -174,8 +174,10 @@ static inline void free_signal_struct(struct signal_struct *sig)
 
 static inline void put_signal_struct(struct signal_struct *sig)
 {
-	if (atomic_dec_and_test(&sig->sigcnt))
+	if (atomic_dec_and_test(&sig->sigcnt)) {
+		sched_autogroup_exit(sig);
 		free_signal_struct(sig);
+	}
 }
 
 void __put_task_struct(struct task_struct *tsk)
@@ -905,6 +907,7 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
 	posix_cpu_timers_init_group(sig);
 
 	tty_audit_fork(sig);
+	sched_autogroup_fork(sig);
 
 	sig->oom_adj = current->signal->oom_adj;
 	sig->oom_score_adj = current->signal->oom_score_adj;
@@ -1315,7 +1318,7 @@ bad_fork_cleanup_mm:
 	}
 bad_fork_cleanup_signal:
 	if (!(clone_flags & CLONE_THREAD))
-		free_signal_struct(p->signal);
+		put_signal_struct(p->signal);
 bad_fork_cleanup_sighand:
 	__cleanup_sighand(p->sighand);
 bad_fork_cleanup_fs:

kernel/irq/manage.c

@@ -577,7 +577,9 @@ irq_thread_check_affinity(struct irq_desc *desc, struct irqaction *action) { }
  */
 static int irq_thread(void *data)
 {
-	struct sched_param param = { .sched_priority = MAX_USER_RT_PRIO/2, };
+	static struct sched_param param = {
+		.sched_priority = MAX_USER_RT_PRIO/2,
+	};
 	struct irqaction *action = data;
 	struct irq_desc *desc = irq_to_desc(action->irq);
 	int wake, oneshot = desc->status & IRQ_ONESHOT;

kernel/kthread.c

@@ -148,7 +148,7 @@ struct task_struct *kthread_create(int (*threadfn)(void *data),
 	wait_for_completion(&create.done);
 
 	if (!IS_ERR(create.result)) {
-		struct sched_param param = { .sched_priority = 0 };
+		static struct sched_param param = { .sched_priority = 0 };
 		va_list args;
 
 		va_start(args, namefmt);

kernel/mutex.c

@@ -199,7 +199,7 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
 		 * memory barriers as we'll eventually observe the right
 		 * values at the cost of a few extra spins.
 		 */
-		cpu_relax();
+		arch_mutex_cpu_relax();
 	}
 #endif
 	spin_lock_mutex(&lock->wait_lock, flags);

kernel/printk.c

@@ -1074,17 +1074,17 @@ static DEFINE_PER_CPU(int, printk_pending);
 
 void printk_tick(void)
 {
-	if (__get_cpu_var(printk_pending)) {
-		__get_cpu_var(printk_pending) = 0;
+	if (__this_cpu_read(printk_pending)) {
+		__this_cpu_write(printk_pending, 0);
 		wake_up_interruptible(&log_wait);
 	}
 }
 
 int printk_needs_cpu(int cpu)
 {
-	if (unlikely(cpu_is_offline(cpu)))
+	if (cpu_is_offline(cpu))
 		printk_tick();
-	return per_cpu(printk_pending, cpu);
+	return __this_cpu_read(printk_pending);
 }
 
 void wake_up_klogd(void)

kernel/sched.c

@@ -75,9 +75,11 @@
 
 #include <asm/tlb.h>
 #include <asm/irq_regs.h>
+#include <asm/mutex.h>
 
 #include "sched_cpupri.h"
 #include "workqueue_sched.h"
+#include "sched_autogroup.h"
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/sched.h>
@@ -253,6 +255,8 @@ struct task_group {
 	/* runqueue "owned" by this group on each cpu */
 	struct cfs_rq **cfs_rq;
 	unsigned long shares;
+
+	atomic_t load_weight;
 #endif
 
 #ifdef CONFIG_RT_GROUP_SCHED
@@ -268,24 +272,19 @@ struct task_group {
 	struct task_group *parent;
 	struct list_head siblings;
 	struct list_head children;
+
+#ifdef CONFIG_SCHED_AUTOGROUP
+	struct autogroup *autogroup;
+#endif
 };
 
 #define root_task_group init_task_group
 
-/* task_group_lock serializes add/remove of task groups and also changes to
- * a task group's cpu shares.
- */
+/* task_group_lock serializes the addition/removal of task groups */
 static DEFINE_SPINLOCK(task_group_lock);
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
 
-#ifdef CONFIG_SMP
-static int root_task_group_empty(void)
-{
-	return list_empty(&root_task_group.children);
-}
-#endif
-
 # define INIT_TASK_GROUP_LOAD	NICE_0_LOAD
 
 /*
@@ -342,6 +341,7 @@ struct cfs_rq {
 	 * leaf_cfs_rq_list ties together list of leaf cfs_rq's in a cpu. This
 	 * list is used during load balance.
 	 */
+	int on_list;
 	struct list_head leaf_cfs_rq_list;
 	struct task_group *tg;	/* group that "owns" this runqueue */
 
@@ -360,14 +360,17 @@ struct cfs_rq {
 	unsigned long h_load;
 
 	/*
-	 * this cpu's part of tg->shares
+	 * Maintaining per-cpu shares distribution for group scheduling
+	 *
+	 * load_stamp is the last time we updated the load average
+	 * load_last is the last time we updated the load average and saw load
+	 * load_unacc_exec_time is currently unaccounted execution time
 	 */
-	unsigned long shares;
+	u64 load_avg;
+	u64 load_period;
+	u64 load_stamp, load_last, load_unacc_exec_time;
 
-	/*
-	 * load.weight at the time we set shares
-	 */
-	unsigned long rq_weight;
+	unsigned long load_contribution;
 #endif
 #endif
 };
@@ -605,11 +608,14 @@ static inline int cpu_of(struct rq *rq)
  */
 static inline struct task_group *task_group(struct task_struct *p)
 {
+	struct task_group *tg;
 	struct cgroup_subsys_state *css;
 
 	css = task_subsys_state_check(p, cpu_cgroup_subsys_id,
 			lockdep_is_held(&task_rq(p)->lock));
-	return container_of(css, struct task_group, css);
+	tg = container_of(css, struct task_group, css);
+
+	return autogroup_task_group(p, tg);
 }
 
 /* Change a task's cfs_rq and parent entity if it moves across CPUs/groups */
@@ -792,20 +798,6 @@ late_initcall(sched_init_debug);
  */
 const_debug unsigned int sysctl_sched_nr_migrate = 32;
 
-/*
- * ratelimit for updating the group shares.
- * default: 0.25ms
- */
-unsigned int sysctl_sched_shares_ratelimit = 250000;
-unsigned int normalized_sysctl_sched_shares_ratelimit = 250000;
-
-/*
- * Inject some fuzzyness into changing the per-cpu group shares
- * this avoids remote rq-locks at the expense of fairness.
- * default: 4
- */
-unsigned int sysctl_sched_shares_thresh = 4;
-
 /*
  * period over which we average the RT time consumption, measured
  * in ms.
@@ -1355,6 +1347,12 @@ static inline void update_load_sub(struct load_weight *lw, unsigned long dec)
 	lw->inv_weight = 0;
 }
 
+static inline void update_load_set(struct load_weight *lw, unsigned long w)
+{
+	lw->weight = w;
+	lw->inv_weight = 0;
+}
+
 /*
  * To aid in avoiding the subversion of "niceness" due to uneven distribution
  * of tasks with abnormal "nice" values across CPUs the contribution that
@@ -1543,101 +1541,6 @@ static unsigned long cpu_avg_load_per_task(int cpu)
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
 
-static __read_mostly unsigned long __percpu *update_shares_data;
-
-static void __set_se_shares(struct sched_entity *se, unsigned long shares);
-
-/*
- * Calculate and set the cpu's group shares.
- */
-static void update_group_shares_cpu(struct task_group *tg, int cpu,
-				    unsigned long sd_shares,
-				    unsigned long sd_rq_weight,
-				    unsigned long *usd_rq_weight)
-{
-	unsigned long shares, rq_weight;
-	int boost = 0;
-
-	rq_weight = usd_rq_weight[cpu];
-	if (!rq_weight) {
-		boost = 1;
-		rq_weight = NICE_0_LOAD;
-	}
-
-	/*
-	 *             \Sum_j shares_j * rq_weight_i
-	 * shares_i =  -----------------------------
-	 *                  \Sum_j rq_weight_j
-	 */
-	shares = (sd_shares * rq_weight) / sd_rq_weight;
-	shares = clamp_t(unsigned long, shares, MIN_SHARES, MAX_SHARES);
-
-	if (abs(shares - tg->se[cpu]->load.weight) >
-			sysctl_sched_shares_thresh) {
-		struct rq *rq = cpu_rq(cpu);
-		unsigned long flags;
-
-		raw_spin_lock_irqsave(&rq->lock, flags);
-		tg->cfs_rq[cpu]->rq_weight = boost ? 0 : rq_weight;
-		tg->cfs_rq[cpu]->shares = boost ? 0 : shares;
-		__set_se_shares(tg->se[cpu], shares);
-		raw_spin_unlock_irqrestore(&rq->lock, flags);
-	}
-}
-
-/*
- * Re-compute the task group their per cpu shares over the given domain.
- * This needs to be done in a bottom-up fashion because the rq weight of a
- * parent group depends on the shares of its child groups.
- */
-static int tg_shares_up(struct task_group *tg, void *data)
-{
-	unsigned long weight, rq_weight = 0, sum_weight = 0, shares = 0;
-	unsigned long *usd_rq_weight;
-	struct sched_domain *sd = data;
-	unsigned long flags;
-	int i;
-
-	if (!tg->se[0])
-		return 0;
-
-	local_irq_save(flags);
-	usd_rq_weight = per_cpu_ptr(update_shares_data, smp_processor_id());
-
-	for_each_cpu(i, sched_domain_span(sd)) {
-		weight = tg->cfs_rq[i]->load.weight;
-		usd_rq_weight[i] = weight;
-
-		rq_weight += weight;
-		/*
-		 * If there are currently no tasks on the cpu pretend there
-		 * is one of average load so that when a new task gets to
-		 * run here it will not get delayed by group starvation.
-		 */
-		if (!weight)
-			weight = NICE_0_LOAD;
-
-		sum_weight += weight;
-		shares += tg->cfs_rq[i]->shares;
-	}
-
-	if (!rq_weight)
-		rq_weight = sum_weight;
-
-	if ((!shares && rq_weight) || shares > tg->shares)
-		shares = tg->shares;
-
-	if (!sd->parent || !(sd->parent->flags & SD_LOAD_BALANCE))
-		shares = tg->shares;
-
-	for_each_cpu(i, sched_domain_span(sd))
-		update_group_shares_cpu(tg, i, shares, rq_weight, usd_rq_weight);
-
-	local_irq_restore(flags);
-
-	return 0;
-}
-
 /*
  * Compute the cpu's hierarchical load factor for each task group.
  * This needs to be done in a top-down fashion because the load of a child
@@ -1652,7 +1555,7 @@ static int tg_load_down(struct task_group *tg, void *data)
 		load = cpu_rq(cpu)->load.weight;
 	} else {
 		load = tg->parent->cfs_rq[cpu]->h_load;
-		load *= tg->cfs_rq[cpu]->shares;
+		load *= tg->se[cpu]->load.weight;
 		load /= tg->parent->cfs_rq[cpu]->load.weight + 1;
 	}
 
@@ -1661,34 +1564,11 @@ static int tg_load_down(struct task_group *tg, void *data)
 	return 0;
 }
 
-static void update_shares(struct sched_domain *sd)
-{
-	s64 elapsed;
-	u64 now;
-
-	if (root_task_group_empty())
-		return;
-
-	now = local_clock();
-	elapsed = now - sd->last_update;
-
-	if (elapsed >= (s64)(u64)sysctl_sched_shares_ratelimit) {
-		sd->last_update = now;
-		walk_tg_tree(tg_nop, tg_shares_up, sd);
-	}
-}
-
 static void update_h_load(long cpu)
 {
 	walk_tg_tree(tg_load_down, tg_nop, (void *)cpu);
 }
 
-#else
-
-static inline void update_shares(struct sched_domain *sd)
-{
-}
-
 #endif
 
 #ifdef CONFIG_PREEMPT
@@ -1810,15 +1690,6 @@ static void double_rq_unlock(struct rq *rq1, struct rq *rq2)
 
 #endif
 
-#ifdef CONFIG_FAIR_GROUP_SCHED
-static void cfs_rq_set_shares(struct cfs_rq *cfs_rq, unsigned long shares)
-{
-#ifdef CONFIG_SMP
-	cfs_rq->shares = shares;
-#endif
-}
-#endif
-
 static void calc_load_account_idle(struct rq *this_rq);
 static void update_sysctl(void);
 static int get_update_sysctl_factor(void);
@@ -2063,6 +1934,7 @@ static void update_rq_clock_task(struct rq *rq, s64 delta)
 #include "sched_idletask.c"
 #include "sched_fair.c"
 #include "sched_rt.c"
+#include "sched_autogroup.c"
 #include "sched_stoptask.c"
 #ifdef CONFIG_SCHED_DEBUG
 # include "sched_debug.c"
@@ -2255,10 +2127,8 @@ static int migration_cpu_stop(void *data);
  * The task's runqueue lock must be held.
  * Returns true if you have to wait for migration thread.
  */
-static bool migrate_task(struct task_struct *p, int dest_cpu)
+static bool migrate_task(struct task_struct *p, struct rq *rq)
 {
-	struct rq *rq = task_rq(p);
-
 	/*
 	 * If the task is not on a runqueue (and not running), then
 	 * the next wake-up will properly place the task.
@@ -2438,18 +2308,15 @@ static int select_fallback_rq(int cpu, struct task_struct *p)
 		return dest_cpu;
 
 	/* No more Mr. Nice Guy. */
-	if (unlikely(dest_cpu >= nr_cpu_ids)) {
-		dest_cpu = cpuset_cpus_allowed_fallback(p);
-		/*
-		 * Don't tell them about moving exiting tasks or
-		 * kernel threads (both mm NULL), since they never
-		 * leave kernel.
-		 */
-		if (p->mm && printk_ratelimit()) {
-			printk(KERN_INFO "process %d (%s) no "
-			       "longer affine to cpu%d\n",
-			       task_pid_nr(p), p->comm, cpu);
-		}
+	dest_cpu = cpuset_cpus_allowed_fallback(p);
+	/*
+	 * Don't tell them about moving exiting tasks or
+	 * kernel threads (both mm NULL), since they never
+	 * leave kernel.
+	 */
+	if (p->mm && printk_ratelimit()) {
+		printk(KERN_INFO "process %d (%s) no longer affine to cpu%d\n",
+				task_pid_nr(p), p->comm, cpu);
 	}
 
 	return dest_cpu;
@@ -2785,7 +2652,9 @@ void sched_fork(struct task_struct *p, int clone_flags)
 	/* Want to start with kernel preemption disabled. */
 	task_thread_info(p)->preempt_count = 1;
 #endif
+#ifdef CONFIG_SMP
 	plist_node_init(&p->pushable_tasks, MAX_PRIO);
+#endif
 
 	put_cpu();
 }
@@ -3549,7 +3418,7 @@ void sched_exec(void)
 	 * select_task_rq() can race against ->cpus_allowed
 	 */
 	if (cpumask_test_cpu(dest_cpu, &p->cpus_allowed) &&
-	    likely(cpu_active(dest_cpu)) && migrate_task(p, dest_cpu)) {
+	    likely(cpu_active(dest_cpu)) && migrate_task(p, rq)) {
 		struct migration_arg arg = { p, dest_cpu };
 
 		task_rq_unlock(rq, &flags);
@@ -4214,7 +4083,7 @@ int mutex_spin_on_owner(struct mutex *lock, struct thread_info *owner)
 		if (task_thread_info(rq->curr) != owner || need_resched())
 			return 0;
 
-		cpu_relax();
+		arch_mutex_cpu_relax();
 	}
 
 	return 1;
@@ -4526,7 +4395,7 @@ EXPORT_SYMBOL(wait_for_completion_interruptible);
  * This waits for either a completion of a specific task to be signaled or for a
  * specified timeout to expire. It is interruptible. The timeout is in jiffies.
  */
-unsigned long __sched
+long __sched
 wait_for_completion_interruptible_timeout(struct completion *x,
 					  unsigned long timeout)
 {
@@ -4559,7 +4428,7 @@ EXPORT_SYMBOL(wait_for_completion_killable);
  * signaled or for a specified timeout to expire. It can be
  * interrupted by a kill signal. The timeout is in jiffies.
  */
-unsigned long __sched
+long __sched
 wait_for_completion_killable_timeout(struct completion *x,
 				     unsigned long timeout)
 {
@@ -4901,7 +4770,7 @@ static bool check_same_owner(struct task_struct *p)
 }
 
 static int __sched_setscheduler(struct task_struct *p, int policy,
-				struct sched_param *param, bool user)
+				const struct sched_param *param, bool user)
 {
 	int retval, oldprio, oldpolicy = -1, on_rq, running;
 	unsigned long flags;
@@ -5056,7 +4925,7 @@ recheck:
  * NOTE that the task may be already dead.
  */
 int sched_setscheduler(struct task_struct *p, int policy,
-		       struct sched_param *param)
+		       const struct sched_param *param)
 {
 	return __sched_setscheduler(p, policy, param, true);
 }
@@ -5074,7 +4943,7 @@ EXPORT_SYMBOL_GPL(sched_setscheduler);
  * but our caller might not have that capability.
  */
 int sched_setscheduler_nocheck(struct task_struct *p, int policy,
-			       struct sched_param *param)
+			       const struct sched_param *param)
 {
 	return __sched_setscheduler(p, policy, param, false);
 }
@@ -5590,7 +5459,7 @@ void sched_show_task(struct task_struct *p)
 	unsigned state;
 
 	state = p->state ? __ffs(p->state) + 1 : 0;
-	printk(KERN_INFO "%-13.13s %c", p->comm,
+	printk(KERN_INFO "%-15.15s %c", p->comm,
 		state < sizeof(stat_nam) - 1 ? stat_nam[state] : '?');
 #if BITS_PER_LONG == 32
 	if (state == TASK_RUNNING)
@@ -5754,7 +5623,6 @@ static void update_sysctl(void)
 	SET_SYSCTL(sched_min_granularity);
 	SET_SYSCTL(sched_latency);
 	SET_SYSCTL(sched_wakeup_granularity);
-	SET_SYSCTL(sched_shares_ratelimit);
 #undef SET_SYSCTL
 }
 
@@ -5830,7 +5698,7 @@ again:
 		goto out;
 
 	dest_cpu = cpumask_any_and(cpu_active_mask, new_mask);
-	if (migrate_task(p, dest_cpu)) {
+	if (migrate_task(p, rq)) {
 		struct migration_arg arg = { p, dest_cpu };
 		/* Need help from migration thread: drop lock and wait. */
 		task_rq_unlock(rq, &flags);
@@ -5912,29 +5780,20 @@ static int migration_cpu_stop(void *data)
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
+
 /*
- * Figure out where task on dead CPU should go, use force if necessary.
+ * Ensures that the idle task is using init_mm right before its cpu goes
+ * offline.
  */
-void move_task_off_dead_cpu(int dead_cpu, struct task_struct *p)
+void idle_task_exit(void)
 {
-	struct rq *rq = cpu_rq(dead_cpu);
-	int needs_cpu, uninitialized_var(dest_cpu);
-	unsigned long flags;
+	struct mm_struct *mm = current->active_mm;
 
-	local_irq_save(flags);
+	BUG_ON(cpu_online(smp_processor_id()));
 
-	raw_spin_lock(&rq->lock);
-	needs_cpu = (task_cpu(p) == dead_cpu) && (p->state != TASK_WAKING);
-	if (needs_cpu)
-		dest_cpu = select_fallback_rq(dead_cpu, p);
-	raw_spin_unlock(&rq->lock);
-	/*
-	 * It can only fail if we race with set_cpus_allowed(),
-	 * in the racer should migrate the task anyway.
-	 */
-	if (needs_cpu)
-		__migrate_task(p, dead_cpu, dest_cpu);
-	local_irq_restore(flags);
+	if (mm != &init_mm)
+		switch_mm(mm, &init_mm, current);
+	mmdrop(mm);
 }
 
 /*
@@ -5947,128 +5806,69 @@ void move_task_off_dead_cpu(int dead_cpu, struct task_struct *p)
 static void migrate_nr_uninterruptible(struct rq *rq_src)
 {
 	struct rq *rq_dest = cpu_rq(cpumask_any(cpu_active_mask));
-	unsigned long flags;
 
-	local_irq_save(flags);
-	double_rq_lock(rq_src, rq_dest);
 	rq_dest->nr_uninterruptible += rq_src->nr_uninterruptible;
 	rq_src->nr_uninterruptible = 0;
-	double_rq_unlock(rq_src, rq_dest);
-	local_irq_restore(flags);
-}
-
-/* Run through task list and migrate tasks from the dead cpu. */
-static void migrate_live_tasks(int src_cpu)
-{
-	struct task_struct *p, *t;
-
-	read_lock(&tasklist_lock);
-
-	do_each_thread(t, p) {
-		if (p == current)
-			continue;
-
-		if (task_cpu(p) == src_cpu)
-			move_task_off_dead_cpu(src_cpu, p);
-	} while_each_thread(t, p);
-
-	read_unlock(&tasklist_lock);
 }
 
 /*
- * Schedules idle task to be the next runnable task on current CPU.
- * It does so by boosting its priority to highest possible.
- * Used by CPU offline code.
+ * remove the tasks which were accounted by rq from calc_load_tasks.
  */
-void sched_idle_next(void)
+static void calc_global_load_remove(struct rq *rq)
 {
-	int this_cpu = smp_processor_id();
-	struct rq *rq = cpu_rq(this_cpu);
-	struct task_struct *p = rq->idle;
-	unsigned long flags;
-
-	/* cpu has to be offline */
-	BUG_ON(cpu_online(this_cpu));
-
-	/*
-	 * Strictly not necessary since rest of the CPUs are stopped by now
-	 * and interrupts disabled on the current cpu.
-	 */
-	raw_spin_lock_irqsave(&rq->lock, flags);
-
-	__setscheduler(rq, p, SCHED_FIFO, MAX_RT_PRIO-1);
-
-	activate_task(rq, p, 0);
-
-	raw_spin_unlock_irqrestore(&rq->lock, flags);
+	atomic_long_sub(rq->calc_load_active, &calc_load_tasks);
+	rq->calc_load_active = 0;
 }
 
 /*
- * Ensures that the idle task is using init_mm right before its cpu goes
- * offline.
+ * Migrate all tasks from the rq, sleeping tasks will be migrated by
+ * try_to_wake_up()->select_task_rq().
+ *
+ * Called with rq->lock held even though we'er in stop_machine() and
+ * there's no concurrency possible, we hold the required locks anyway
+ * because of lock validation efforts.
  */
-void idle_task_exit(void)
-{
-	struct mm_struct *mm = current->active_mm;
-
-	BUG_ON(cpu_online(smp_processor_id()));
-
-	if (mm != &init_mm)
-		switch_mm(mm, &init_mm, current);
-	mmdrop(mm);
-}
-
-/* called under rq->lock with disabled interrupts */
-static void migrate_dead(unsigned int dead_cpu, struct task_struct *p)
+static void migrate_tasks(unsigned int dead_cpu)
 {
 	struct rq *rq = cpu_rq(dead_cpu);
-
-	/* Must be exiting, otherwise would be on tasklist. */
-	BUG_ON(!p->exit_state);
-
-	/* Cannot have done final schedule yet: would have vanished. */
-	BUG_ON(p->state == TASK_DEAD);
-
-	get_task_struct(p);
+	struct task_struct *next, *stop = rq->stop;
+	int dest_cpu;
 
 	/*
-	 * Drop lock around migration; if someone else moves it,
-	 * that's OK. No task can be added to this CPU, so iteration is
-	 * fine.
+	 * Fudge the rq selection such that the below task selection loop
+	 * doesn't get stuck on the currently eligible stop task.
+	 *
+	 * We're currently inside stop_machine() and the rq is either stuck
+	 * in the stop_machine_cpu_stop() loop, or we're executing this code,
+	 * either way we should never end up calling schedule() until we're
+	 * done here.
 	 */
-	raw_spin_unlock_irq(&rq->lock);
-	move_task_off_dead_cpu(dead_cpu, p);
-	raw_spin_lock_irq(&rq->lock);
-
-	put_task_struct(p);
-}
-
-/* release_task() removes task from tasklist, so we won't find dead tasks. */
-static void migrate_dead_tasks(unsigned int dead_cpu)
-{
-	struct rq *rq = cpu_rq(dead_cpu);
-	struct task_struct *next;
+	rq->stop = NULL;
 
 	for ( ; ; ) {
-		if (!rq->nr_running)
+		/*
+		 * There's this thread running, bail when that's the only
+		 * remaining thread.
+		 */
+		if (rq->nr_running == 1)
 			break;
+
 		next = pick_next_task(rq);
-		if (!next)
-			break;
+		BUG_ON(!next);
 		next->sched_class->put_prev_task(rq, next);
-		migrate_dead(dead_cpu, next);
 
+		/* Find suitable destination for @next, with force if needed. */
+		dest_cpu = select_fallback_rq(dead_cpu, next);
+		raw_spin_unlock(&rq->lock);
+
+		__migrate_task(next, dead_cpu, dest_cpu);
+
+		raw_spin_lock(&rq->lock);
 	}
-}
 
-/*
- * remove the tasks which were accounted by rq from calc_load_tasks.
- */
-static void calc_global_load_remove(struct rq *rq)
-{
-	atomic_long_sub(rq->calc_load_active, &calc_load_tasks);
-	rq->calc_load_active = 0;
+	rq->stop = stop;
 }
+
 #endif /* CONFIG_HOTPLUG_CPU */
 
 #if defined(CONFIG_SCHED_DEBUG) && defined(CONFIG_SYSCTL)
@@ -6278,15 +6078,13 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu)
 	unsigned long flags;
 	struct rq *rq = cpu_rq(cpu);
 
-	switch (action) {
+	switch (action & ~CPU_TASKS_FROZEN) {
 
 	case CPU_UP_PREPARE:
-	case CPU_UP_PREPARE_FROZEN:
 		rq->calc_load_update = calc_load_update;
 		break;
 
 	case CPU_ONLINE:
-	case CPU_ONLINE_FROZEN:
 		/* Update our root-domain */
 		raw_spin_lock_irqsave(&rq->lock, flags);
 		if (rq->rd) {
@@ -6298,30 +6096,19 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu)
 		break;
 
 #ifdef CONFIG_HOTPLUG_CPU
-	case CPU_DEAD:
-	case CPU_DEAD_FROZEN:
-		migrate_live_tasks(cpu);
-		/* Idle task back to normal (off runqueue, low prio) */
-		raw_spin_lock_irq(&rq->lock);
-		deactivate_task(rq, rq->idle, 0);
-		__setscheduler(rq, rq->idle, SCHED_NORMAL, 0);
-		rq->idle->sched_class = &idle_sched_class;
-		migrate_dead_tasks(cpu);
-		raw_spin_unlock_irq(&rq->lock);
-		migrate_nr_uninterruptible(rq);
-		BUG_ON(rq->nr_running != 0);
-		calc_global_load_remove(rq);
-		break;
-
 	case CPU_DYING:
-	case CPU_DYING_FROZEN:
 		/* Update our root-domain */
 		raw_spin_lock_irqsave(&rq->lock, flags);
 		if (rq->rd) {
 			BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span));
 			set_rq_offline(rq);
 		}
+		migrate_tasks(cpu);
+		BUG_ON(rq->nr_running != 1); /* the migration thread */
 		raw_spin_unlock_irqrestore(&rq->lock, flags);
+
+		migrate_nr_uninterruptible(rq);
+		calc_global_load_remove(rq);
 		break;
 #endif
 	}
@@ -8052,15 +7839,13 @@ static void init_rt_rq(struct rt_rq *rt_rq, struct rq *rq)
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
 static void init_tg_cfs_entry(struct task_group *tg, struct cfs_rq *cfs_rq,
-				struct sched_entity *se, int cpu, int add,
+				struct sched_entity *se, int cpu,
 				struct sched_entity *parent)
 {
 	struct rq *rq = cpu_rq(cpu);
 	tg->cfs_rq[cpu] = cfs_rq;
 	init_cfs_rq(cfs_rq, rq);
 	cfs_rq->tg = tg;
-	if (add)
-		list_add(&cfs_rq->leaf_cfs_rq_list, &rq->leaf_cfs_rq_list);
 
 	tg->se[cpu] = se;
 	/* se could be NULL for init_task_group */
@@ -8073,15 +7858,14 @@ static void init_tg_cfs_entry(struct task_group *tg, struct cfs_rq *cfs_rq,
 		se->cfs_rq = parent->my_q;
 
 	se->my_q = cfs_rq;
-	se->load.weight = tg->shares;
-	se->load.inv_weight = 0;
+	update_load_set(&se->load, 0);
 	se->parent = parent;
 }
 #endif
 
 #ifdef CONFIG_RT_GROUP_SCHED
 static void init_tg_rt_entry(struct task_group *tg, struct rt_rq *rt_rq,
-		struct sched_rt_entity *rt_se, int cpu, int add,
+		struct sched_rt_entity *rt_se, int cpu,
 		struct sched_rt_entity *parent)
 {
 	struct rq *rq = cpu_rq(cpu);
@@ -8090,8 +7874,6 @@ static void init_tg_rt_entry(struct task_group *tg, struct rt_rq *rt_rq,
 	init_rt_rq(rt_rq, rq);
 	rt_rq->tg = tg;
 	rt_rq->rt_runtime = tg->rt_bandwidth.rt_runtime;
-	if (add)
-		list_add(&rt_rq->leaf_rt_rq_list, &rq->leaf_rt_rq_list);
 
 	tg->rt_se[cpu] = rt_se;
 	if (!rt_se)
@@ -8164,13 +7946,9 @@ void __init sched_init(void)
 #ifdef CONFIG_CGROUP_SCHED
 	list_add(&init_task_group.list, &task_groups);
 	INIT_LIST_HEAD(&init_task_group.children);
-
+	autogroup_init(&init_task);
 #endif /* CONFIG_CGROUP_SCHED */
 
-#if defined CONFIG_FAIR_GROUP_SCHED && defined CONFIG_SMP
-	update_shares_data = __alloc_percpu(nr_cpu_ids * sizeof(unsigned long),
-					    __alignof__(unsigned long));
-#endif
 	for_each_possible_cpu(i) {
 		struct rq *rq;
 
@@ -8184,7 +7962,6 @@ void __init sched_init(void)
 #ifdef CONFIG_FAIR_GROUP_SCHED
 		init_task_group.shares = init_task_group_load;
 		INIT_LIST_HEAD(&rq->leaf_cfs_rq_list);
-#ifdef CONFIG_CGROUP_SCHED
 		/*
 		 * How much cpu bandwidth does init_task_group get?
 		 *
@@ -8204,16 +7981,13 @@ void __init sched_init(void)
 		 * We achieve this by letting init_task_group's tasks sit
 		 * directly in rq->cfs (i.e init_task_group->se[] = NULL).
 		 */
-		init_tg_cfs_entry(&init_task_group, &rq->cfs, NULL, i, 1, NULL);
-#endif
+		init_tg_cfs_entry(&init_task_group, &rq->cfs, NULL, i, NULL);
 #endif /* CONFIG_FAIR_GROUP_SCHED */
 
 		rq->rt.rt_runtime = def_rt_bandwidth.rt_runtime;
 #ifdef CONFIG_RT_GROUP_SCHED
 		INIT_LIST_HEAD(&rq->leaf_rt_rq_list);
-#ifdef CONFIG_CGROUP_SCHED
-		init_tg_rt_entry(&init_task_group, &rq->rt, NULL, i, 1, NULL);
-#endif
+		init_tg_rt_entry(&init_task_group, &rq->rt, NULL, i, NULL);
 #endif
 
 		for (j = 0; j < CPU_LOAD_IDX_MAX; j++)
@@ -8486,7 +8260,7 @@ int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent)
 		if (!se)
 			goto err_free_rq;
 
-		init_tg_cfs_entry(tg, cfs_rq, se, i, 0, parent->se[i]);
+		init_tg_cfs_entry(tg, cfs_rq, se, i, parent->se[i]);
 	}
 
 	return 1;
@@ -8497,15 +8271,21 @@ err:
 	return 0;
 }
 
-static inline void register_fair_sched_group(struct task_group *tg, int cpu)
-{
-	list_add_rcu(&tg->cfs_rq[cpu]->leaf_cfs_rq_list,
-			&cpu_rq(cpu)->leaf_cfs_rq_list);
-}
-
 static inline void unregister_fair_sched_group(struct task_group *tg, int cpu)
 {
-	list_del_rcu(&tg->cfs_rq[cpu]->leaf_cfs_rq_list);
+	struct rq *rq = cpu_rq(cpu);
+	unsigned long flags;
+
+	/*
+	* Only empty task groups can be destroyed; so we can speculatively
+	* check on_list without danger of it being re-added.
+	*/
+	if (!tg->cfs_rq[cpu]->on_list)
+		return;
+
+	raw_spin_lock_irqsave(&rq->lock, flags);
+	list_del_leaf_cfs_rq(tg->cfs_rq[cpu]);
+	raw_spin_unlock_irqrestore(&rq->lock, flags);
 }
 #else /* !CONFG_FAIR_GROUP_SCHED */
 static inline void free_fair_sched_group(struct task_group *tg)
@@ -8518,10 +8298,6 @@ int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent)
 	return 1;
 }
 
-static inline void register_fair_sched_group(struct task_group *tg, int cpu)
-{
-}
-
 static inline void unregister_fair_sched_group(struct task_group *tg, int cpu)
 {
 }
@@ -8576,7 +8352,7 @@ int alloc_rt_sched_group(struct task_group *tg, struct task_group *parent)
 		if (!rt_se)
 			goto err_free_rq;
 
-		init_tg_rt_entry(tg, rt_rq, rt_se, i, 0, parent->rt_se[i]);
+		init_tg_rt_entry(tg, rt_rq, rt_se, i, parent->rt_se[i]);
 	}
 
 	return 1;
@@ -8586,17 +8362,6 @@ err_free_rq:
 err:
 	return 0;
 }
-
-static inline void register_rt_sched_group(struct task_group *tg, int cpu)
-{
-	list_add_rcu(&tg->rt_rq[cpu]->leaf_rt_rq_list,
-			&cpu_rq(cpu)->leaf_rt_rq_list);
-}
-
-static inline void unregister_rt_sched_group(struct task_group *tg, int cpu)
-{
-	list_del_rcu(&tg->rt_rq[cpu]->leaf_rt_rq_list);
-}
 #else /* !CONFIG_RT_GROUP_SCHED */
 static inline void free_rt_sched_group(struct task_group *tg)
 {
@@ -8607,14 +8372,6 @@ int alloc_rt_sched_group(struct task_group *tg, struct task_group *parent)
 {
 	return 1;
 }
-
-static inline void register_rt_sched_group(struct task_group *tg, int cpu)
-{
-}
-
-static inline void unregister_rt_sched_group(struct task_group *tg, int cpu)
-{
-}
 #endif /* CONFIG_RT_GROUP_SCHED */
 
 #ifdef CONFIG_CGROUP_SCHED
@@ -8630,7 +8387,6 @@ struct task_group *sched_create_group(struct task_group *parent)
 {
 	struct task_group *tg;
 	unsigned long flags;
-	int i;
 
 	tg = kzalloc(sizeof(*tg), GFP_KERNEL);
 	if (!tg)
@@ -8643,10 +8399,6 @@ struct task_group *sched_create_group(struct task_group *parent)
 		goto err;
 
 	spin_lock_irqsave(&task_group_lock, flags);
-	for_each_possible_cpu(i) {
-		register_fair_sched_group(tg, i);
-		register_rt_sched_group(tg, i);
-	}
 	list_add_rcu(&tg->list, &task_groups);
 
 	WARN_ON(!parent); /* root should already exist */
@@ -8676,11 +8428,11 @@ void sched_destroy_group(struct task_group *tg)
 	unsigned long flags;
 	int i;
 
-	spin_lock_irqsave(&task_group_lock, flags);
-	for_each_possible_cpu(i) {
+	/* end participation in shares distribution */
+	for_each_possible_cpu(i)
 		unregister_fair_sched_group(tg, i);
-		unregister_rt_sched_group(tg, i);
-	}
+
+	spin_lock_irqsave(&task_group_lock, flags);
 	list_del_rcu(&tg->list);
 	list_del_rcu(&tg->siblings);
 	spin_unlock_irqrestore(&task_group_lock, flags);
@@ -8727,33 +8479,6 @@ void sched_move_task(struct task_struct *tsk)
 #endif /* CONFIG_CGROUP_SCHED */
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
-static void __set_se_shares(struct sched_entity *se, unsigned long shares)
-{
-	struct cfs_rq *cfs_rq = se->cfs_rq;
-	int on_rq;
-
-	on_rq = se->on_rq;
-	if (on_rq)
-		dequeue_entity(cfs_rq, se, 0);
-
-	se->load.weight = shares;
-	se->load.inv_weight = 0;
-
-	if (on_rq)
-		enqueue_entity(cfs_rq, se, 0);
-}
-
-static void set_se_shares(struct sched_entity *se, unsigned long shares)
-{
-	struct cfs_rq *cfs_rq = se->cfs_rq;
-	struct rq *rq = cfs_rq->rq;
-	unsigned long flags;
-
-	raw_spin_lock_irqsave(&rq->lock, flags);
-	__set_se_shares(se, shares);
-	raw_spin_unlock_irqrestore(&rq->lock, flags);
-}
-
 static DEFINE_MUTEX(shares_mutex);
 
 int sched_group_set_shares(struct task_group *tg, unsigned long shares)
@@ -8776,37 +8501,19 @@ int sched_group_set_shares(struct task_group *tg, unsigned long shares)
 	if (tg->shares == shares)
 		goto done;
 
-	spin_lock_irqsave(&task_group_lock, flags);
-	for_each_possible_cpu(i)
-		unregister_fair_sched_group(tg, i);
-	list_del_rcu(&tg->siblings);
-	spin_unlock_irqrestore(&task_group_lock, flags);
-
-	/* wait for any ongoing reference to this group to finish */
-	synchronize_sched();
-
-	/*
-	 * Now we are free to modify the group's share on each cpu
-	 * w/o tripping rebalance_share or load_balance_fair.
-	 */
 	tg->shares = shares;
 	for_each_possible_cpu(i) {
-		/*
-		 * force a rebalance
-		 */
-		cfs_rq_set_shares(tg->cfs_rq[i], 0);
-		set_se_shares(tg->se[i], shares);
+		struct rq *rq = cpu_rq(i);
+		struct sched_entity *se;
+
+		se = tg->se[i];
+		/* Propagate contribution to hierarchy */
+		raw_spin_lock_irqsave(&rq->lock, flags);
+		for_each_sched_entity(se)
+			update_cfs_shares(group_cfs_rq(se), 0);
+		raw_spin_unlock_irqrestore(&rq->lock, flags);
 	}
 
-	/*
-	 * Enable load balance activity on this group, by inserting it back on
-	 * each cpu's rq->leaf_cfs_rq_list.
-	 */
-	spin_lock_irqsave(&task_group_lock, flags);
-	for_each_possible_cpu(i)
-		register_fair_sched_group(tg, i);
-	list_add_rcu(&tg->siblings, &tg->parent->children);
-	spin_unlock_irqrestore(&task_group_lock, flags);
 done:
 	mutex_unlock(&shares_mutex);
 	return 0;

kernel/sched_autogroup.c

@@ -0,0 +1,238 @@
+#ifdef CONFIG_SCHED_AUTOGROUP
+
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
+#include <linux/kallsyms.h>
+#include <linux/utsname.h>
+
+unsigned int __read_mostly sysctl_sched_autogroup_enabled = 1;
+static struct autogroup autogroup_default;
+static atomic_t autogroup_seq_nr;
+
+static void autogroup_init(struct task_struct *init_task)
+{
+	autogroup_default.tg = &init_task_group;
+	init_task_group.autogroup = &autogroup_default;
+	kref_init(&autogroup_default.kref);
+	init_rwsem(&autogroup_default.lock);
+	init_task->signal->autogroup = &autogroup_default;
+}
+
+static inline void autogroup_free(struct task_group *tg)
+{
+	kfree(tg->autogroup);
+}
+
+static inline void autogroup_destroy(struct kref *kref)
+{
+	struct autogroup *ag = container_of(kref, struct autogroup, kref);
+
+	sched_destroy_group(ag->tg);
+}
+
+static inline void autogroup_kref_put(struct autogroup *ag)
+{
+	kref_put(&ag->kref, autogroup_destroy);
+}
+
+static inline struct autogroup *autogroup_kref_get(struct autogroup *ag)
+{
+	kref_get(&ag->kref);
+	return ag;
+}
+
+static inline struct autogroup *autogroup_task_get(struct task_struct *p)
+{
+	struct autogroup *ag;
+	unsigned long flags;
+
+	if (!lock_task_sighand(p, &flags))
+		return autogroup_kref_get(&autogroup_default);
+
+	ag = autogroup_kref_get(p->signal->autogroup);
+	unlock_task_sighand(p, &flags);
+
+	return ag;
+}
+
+static inline struct autogroup *autogroup_create(void)
+{
+	struct autogroup *ag = kzalloc(sizeof(*ag), GFP_KERNEL);
+	struct task_group *tg;
+
+	if (!ag)
+		goto out_fail;
+
+	tg = sched_create_group(&init_task_group);
+
+	if (IS_ERR(tg))
+		goto out_free;
+
+	kref_init(&ag->kref);
+	init_rwsem(&ag->lock);
+	ag->id = atomic_inc_return(&autogroup_seq_nr);
+	ag->tg = tg;
+	tg->autogroup = ag;
+
+	return ag;
+
+out_free:
+	kfree(ag);
+out_fail:
+	if (printk_ratelimit()) {
+		printk(KERN_WARNING "autogroup_create: %s failure.\n",
+			ag ? "sched_create_group()" : "kmalloc()");
+	}
+
+	return autogroup_kref_get(&autogroup_default);
+}
+
+static inline bool
+task_wants_autogroup(struct task_struct *p, struct task_group *tg)
+{
+	if (tg != &root_task_group)
+		return false;
+
+	if (p->sched_class != &fair_sched_class)
+		return false;
+
+	/*
+	 * We can only assume the task group can't go away on us if
+	 * autogroup_move_group() can see us on ->thread_group list.
+	 */
+	if (p->flags & PF_EXITING)
+		return false;
+
+	return true;
+}
+
+static inline struct task_group *
+autogroup_task_group(struct task_struct *p, struct task_group *tg)
+{
+	int enabled = ACCESS_ONCE(sysctl_sched_autogroup_enabled);
+
+	if (enabled && task_wants_autogroup(p, tg))
+		return p->signal->autogroup->tg;
+
+	return tg;
+}
+
+static void
+autogroup_move_group(struct task_struct *p, struct autogroup *ag)
+{
+	struct autogroup *prev;
+	struct task_struct *t;
+	unsigned long flags;
+
+	BUG_ON(!lock_task_sighand(p, &flags));
+
+	prev = p->signal->autogroup;
+	if (prev == ag) {
+		unlock_task_sighand(p, &flags);
+		return;
+	}
+
+	p->signal->autogroup = autogroup_kref_get(ag);
+
+	t = p;
+	do {
+		sched_move_task(t);
+	} while_each_thread(p, t);
+
+	unlock_task_sighand(p, &flags);
+	autogroup_kref_put(prev);
+}
+
+/* Allocates GFP_KERNEL, cannot be called under any spinlock */
+void sched_autogroup_create_attach(struct task_struct *p)
+{
+	struct autogroup *ag = autogroup_create();
+
+	autogroup_move_group(p, ag);
+	/* drop extra refrence added by autogroup_create() */
+	autogroup_kref_put(ag);
+}
+EXPORT_SYMBOL(sched_autogroup_create_attach);
+
+/* Cannot be called under siglock.  Currently has no users */
+void sched_autogroup_detach(struct task_struct *p)
+{
+	autogroup_move_group(p, &autogroup_default);
+}
+EXPORT_SYMBOL(sched_autogroup_detach);
+
+void sched_autogroup_fork(struct signal_struct *sig)
+{
+	sig->autogroup = autogroup_task_get(current);
+}
+
+void sched_autogroup_exit(struct signal_struct *sig)
+{
+	autogroup_kref_put(sig->autogroup);
+}
+
+static int __init setup_autogroup(char *str)
+{
+	sysctl_sched_autogroup_enabled = 0;
+
+	return 1;
+}
+
+__setup("noautogroup", setup_autogroup);
+
+#ifdef CONFIG_PROC_FS
+
+int proc_sched_autogroup_set_nice(struct task_struct *p, int *nice)
+{
+	static unsigned long next = INITIAL_JIFFIES;
+	struct autogroup *ag;
+	int err;
+
+	if (*nice < -20 || *nice > 19)
+		return -EINVAL;
+
+	err = security_task_setnice(current, *nice);
+	if (err)
+		return err;
+
+	if (*nice < 0 && !can_nice(current, *nice))
+		return -EPERM;
+
+	/* this is a heavy operation taking global locks.. */
+	if (!capable(CAP_SYS_ADMIN) && time_before(jiffies, next))
+		return -EAGAIN;
+
+	next = HZ / 10 + jiffies;
+	ag = autogroup_task_get(p);
+
+	down_write(&ag->lock);
+	err = sched_group_set_shares(ag->tg, prio_to_weight[*nice + 20]);
+	if (!err)
+		ag->nice = *nice;
+	up_write(&ag->lock);
+
+	autogroup_kref_put(ag);
+
+	return err;
+}
+
+void proc_sched_autogroup_show_task(struct task_struct *p, struct seq_file *m)
+{
+	struct autogroup *ag = autogroup_task_get(p);
+
+	down_read(&ag->lock);
+	seq_printf(m, "/autogroup-%ld nice %d\n", ag->id, ag->nice);
+	up_read(&ag->lock);
+
+	autogroup_kref_put(ag);
+}
+#endif /* CONFIG_PROC_FS */
+
+#ifdef CONFIG_SCHED_DEBUG
+static inline int autogroup_path(struct task_group *tg, char *buf, int buflen)
+{
+	return snprintf(buf, buflen, "%s-%ld", "/autogroup", tg->autogroup->id);
+}
+#endif /* CONFIG_SCHED_DEBUG */
+
+#endif /* CONFIG_SCHED_AUTOGROUP */

kernel/sched_autogroup.h

@@ -0,0 +1,32 @@
+#ifdef CONFIG_SCHED_AUTOGROUP
+
+struct autogroup {
+	struct kref		kref;
+	struct task_group	*tg;
+	struct rw_semaphore	lock;
+	unsigned long		id;
+	int			nice;
+};
+
+static inline struct task_group *
+autogroup_task_group(struct task_struct *p, struct task_group *tg);
+
+#else /* !CONFIG_SCHED_AUTOGROUP */
+
+static inline void autogroup_init(struct task_struct *init_task) {  }
+static inline void autogroup_free(struct task_group *tg) { }
+
+static inline struct task_group *
+autogroup_task_group(struct task_struct *p, struct task_group *tg)
+{
+	return tg;
+}
+
+#ifdef CONFIG_SCHED_DEBUG
+static inline int autogroup_path(struct task_group *tg, char *buf, int buflen)
+{
+	return 0;
+}
+#endif
+
+#endif /* CONFIG_SCHED_AUTOGROUP */

kernel/sched_clock.c

@@ -79,7 +79,7 @@ unsigned long long __attribute__((weak)) sched_clock(void)
 }
 EXPORT_SYMBOL_GPL(sched_clock);
 
-static __read_mostly int sched_clock_running;
+__read_mostly int sched_clock_running;
 
 #ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
 __read_mostly int sched_clock_stable;

kernel/sched_debug.c

@@ -54,8 +54,7 @@ static unsigned long nsec_low(unsigned long long nsec)
 #define SPLIT_NS(x) nsec_high(x), nsec_low(x)
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
-static void print_cfs_group_stats(struct seq_file *m, int cpu,
-		struct task_group *tg)
+static void print_cfs_group_stats(struct seq_file *m, int cpu, struct task_group *tg)
 {
 	struct sched_entity *se = tg->se[cpu];
 	if (!se)
@@ -110,16 +109,6 @@ print_task(struct seq_file *m, struct rq *rq, struct task_struct *p)
 		0LL, 0LL, 0LL, 0L, 0LL, 0L, 0LL, 0L);
 #endif
 
-#ifdef CONFIG_CGROUP_SCHED
-	{
-		char path[64];
-
-		rcu_read_lock();
-		cgroup_path(task_group(p)->css.cgroup, path, sizeof(path));
-		rcu_read_unlock();
-		SEQ_printf(m, " %s", path);
-	}
-#endif
 	SEQ_printf(m, "\n");
 }
 
@@ -147,19 +136,6 @@ static void print_rq(struct seq_file *m, struct rq *rq, int rq_cpu)
 	read_unlock_irqrestore(&tasklist_lock, flags);
 }
 
-#if defined(CONFIG_CGROUP_SCHED) && \
-	(defined(CONFIG_FAIR_GROUP_SCHED) || defined(CONFIG_RT_GROUP_SCHED))
-static void task_group_path(struct task_group *tg, char *buf, int buflen)
-{
-	/* may be NULL if the underlying cgroup isn't fully-created yet */
-	if (!tg->css.cgroup) {
-		buf[0] = '\0';
-		return;
-	}
-	cgroup_path(tg->css.cgroup, buf, buflen);
-}
-#endif
-
 void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
 {
 	s64 MIN_vruntime = -1, min_vruntime, max_vruntime = -1,
@@ -168,16 +144,7 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
 	struct sched_entity *last;
 	unsigned long flags;
 
-#if defined(CONFIG_CGROUP_SCHED) && defined(CONFIG_FAIR_GROUP_SCHED)
-	char path[128];
-	struct task_group *tg = cfs_rq->tg;
-
-	task_group_path(tg, path, sizeof(path));
-
-	SEQ_printf(m, "\ncfs_rq[%d]:%s\n", cpu, path);
-#else
 	SEQ_printf(m, "\ncfs_rq[%d]:\n", cpu);
-#endif
 	SEQ_printf(m, "  .%-30s: %Ld.%06ld\n", "exec_clock",
 			SPLIT_NS(cfs_rq->exec_clock));
 
@@ -202,32 +169,29 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
 	spread0 = min_vruntime - rq0_min_vruntime;
 	SEQ_printf(m, "  .%-30s: %Ld.%06ld\n", "spread0",
 			SPLIT_NS(spread0));
-	SEQ_printf(m, "  .%-30s: %ld\n", "nr_running", cfs_rq->nr_running);
-	SEQ_printf(m, "  .%-30s: %ld\n", "load", cfs_rq->load.weight);
-
 	SEQ_printf(m, "  .%-30s: %d\n", "nr_spread_over",
 			cfs_rq->nr_spread_over);
+	SEQ_printf(m, "  .%-30s: %ld\n", "nr_running", cfs_rq->nr_running);
+	SEQ_printf(m, "  .%-30s: %ld\n", "load", cfs_rq->load.weight);
 #ifdef CONFIG_FAIR_GROUP_SCHED
 #ifdef CONFIG_SMP
-	SEQ_printf(m, "  .%-30s: %lu\n", "shares", cfs_rq->shares);
+	SEQ_printf(m, "  .%-30s: %Ld.%06ld\n", "load_avg",
+			SPLIT_NS(cfs_rq->load_avg));
+	SEQ_printf(m, "  .%-30s: %Ld.%06ld\n", "load_period",
+			SPLIT_NS(cfs_rq->load_period));
+	SEQ_printf(m, "  .%-30s: %ld\n", "load_contrib",
+			cfs_rq->load_contribution);
+	SEQ_printf(m, "  .%-30s: %d\n", "load_tg",
+			atomic_read(&cfs_rq->tg->load_weight));
 #endif
+
 	print_cfs_group_stats(m, cpu, cfs_rq->tg);
 #endif
 }
 
 void print_rt_rq(struct seq_file *m, int cpu, struct rt_rq *rt_rq)
 {
-#if defined(CONFIG_CGROUP_SCHED) && defined(CONFIG_RT_GROUP_SCHED)
-	char path[128];
-	struct task_group *tg = rt_rq->tg;
-
-	task_group_path(tg, path, sizeof(path));
-
-	SEQ_printf(m, "\nrt_rq[%d]:%s\n", cpu, path);
-#else
 	SEQ_printf(m, "\nrt_rq[%d]:\n", cpu);
-#endif
-
 
 #define P(x) \
 	SEQ_printf(m, "  .%-30s: %Ld\n", #x, (long long)(rt_rq->x))
@@ -243,6 +207,8 @@ void print_rt_rq(struct seq_file *m, int cpu, struct rt_rq *rt_rq)
 #undef P
 }
 
+extern __read_mostly int sched_clock_running;
+
 static void print_cpu(struct seq_file *m, int cpu)
 {
 	struct rq *rq = cpu_rq(cpu);
@@ -314,21 +280,42 @@ static const char *sched_tunable_scaling_names[] = {
 
 static int sched_debug_show(struct seq_file *m, void *v)
 {
-	u64 now = ktime_to_ns(ktime_get());
+	u64 ktime, sched_clk, cpu_clk;
+	unsigned long flags;
 	int cpu;
 
-	SEQ_printf(m, "Sched Debug Version: v0.09, %s %.*s\n",
+	local_irq_save(flags);
+	ktime = ktime_to_ns(ktime_get());
+	sched_clk = sched_clock();
+	cpu_clk = local_clock();
+	local_irq_restore(flags);
+
+	SEQ_printf(m, "Sched Debug Version: v0.10, %s %.*s\n",
 		init_utsname()->release,
 		(int)strcspn(init_utsname()->version, " "),
 		init_utsname()->version);
 
-	SEQ_printf(m, "now at %Lu.%06ld msecs\n", SPLIT_NS(now));
+#define P(x) \
+	SEQ_printf(m, "%-40s: %Ld\n", #x, (long long)(x))
+#define PN(x) \
+	SEQ_printf(m, "%-40s: %Ld.%06ld\n", #x, SPLIT_NS(x))
+	PN(ktime);
+	PN(sched_clk);
+	PN(cpu_clk);
+	P(jiffies);
+#ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
+	P(sched_clock_stable);
+#endif
+#undef PN
+#undef P
+
+	SEQ_printf(m, "\n");
+	SEQ_printf(m, "sysctl_sched\n");
 
 #define P(x) \
 	SEQ_printf(m, "  .%-40s: %Ld\n", #x, (long long)(x))
 #define PN(x) \
 	SEQ_printf(m, "  .%-40s: %Ld.%06ld\n", #x, SPLIT_NS(x))
-	P(jiffies);
 	PN(sysctl_sched_latency);
 	PN(sysctl_sched_min_granularity);
 	PN(sysctl_sched_wakeup_granularity);

kernel/sched_fair.c

@@ -89,6 +89,13 @@ unsigned int normalized_sysctl_sched_wakeup_granularity = 1000000UL;
 
 const_debug unsigned int sysctl_sched_migration_cost = 500000UL;
 
+/*
+ * The exponential sliding  window over which load is averaged for shares
+ * distribution.
+ * (default: 10msec)
+ */
+unsigned int __read_mostly sysctl_sched_shares_window = 10000000UL;
+
 static const struct sched_class fair_sched_class;
 
 /**************************************************************
@@ -143,6 +150,36 @@ static inline struct cfs_rq *cpu_cfs_rq(struct cfs_rq *cfs_rq, int this_cpu)
 	return cfs_rq->tg->cfs_rq[this_cpu];
 }
 
+static inline void list_add_leaf_cfs_rq(struct cfs_rq *cfs_rq)
+{
+	if (!cfs_rq->on_list) {
+		/*
+		 * Ensure we either appear before our parent (if already
+		 * enqueued) or force our parent to appear after us when it is
+		 * enqueued.  The fact that we always enqueue bottom-up
+		 * reduces this to two cases.
+		 */
+		if (cfs_rq->tg->parent &&
+		    cfs_rq->tg->parent->cfs_rq[cpu_of(rq_of(cfs_rq))]->on_list) {
+			list_add_rcu(&cfs_rq->leaf_cfs_rq_list,
+				&rq_of(cfs_rq)->leaf_cfs_rq_list);
+		} else {
+			list_add_tail_rcu(&cfs_rq->leaf_cfs_rq_list,
+				&rq_of(cfs_rq)->leaf_cfs_rq_list);
+		}
+
+		cfs_rq->on_list = 1;
+	}
+}
+
+static inline void list_del_leaf_cfs_rq(struct cfs_rq *cfs_rq)
+{
+	if (cfs_rq->on_list) {
+		list_del_rcu(&cfs_rq->leaf_cfs_rq_list);
+		cfs_rq->on_list = 0;
+	}
+}
+
 /* Iterate thr' all leaf cfs_rq's on a runqueue */
 #define for_each_leaf_cfs_rq(rq, cfs_rq) \
 	list_for_each_entry_rcu(cfs_rq, &rq->leaf_cfs_rq_list, leaf_cfs_rq_list)
@@ -246,6 +283,14 @@ static inline struct cfs_rq *cpu_cfs_rq(struct cfs_rq *cfs_rq, int this_cpu)
 	return &cpu_rq(this_cpu)->cfs;
 }
 
+static inline void list_add_leaf_cfs_rq(struct cfs_rq *cfs_rq)
+{
+}
+
+static inline void list_del_leaf_cfs_rq(struct cfs_rq *cfs_rq)
+{
+}
+
 #define for_each_leaf_cfs_rq(rq, cfs_rq) \
 		for (cfs_rq = &rq->cfs; cfs_rq; cfs_rq = NULL)
 
@@ -417,7 +462,6 @@ int sched_proc_update_handler(struct ctl_table *table, int write,
 	WRT_SYSCTL(sched_min_granularity);
 	WRT_SYSCTL(sched_latency);
 	WRT_SYSCTL(sched_wakeup_granularity);
-	WRT_SYSCTL(sched_shares_ratelimit);
 #undef WRT_SYSCTL
 
 	return 0;
@@ -495,6 +539,9 @@ static u64 sched_vslice(struct cfs_rq *cfs_rq, struct sched_entity *se)
 	return calc_delta_fair(sched_slice(cfs_rq, se), se);
 }
 
+static void update_cfs_load(struct cfs_rq *cfs_rq, int global_update);
+static void update_cfs_shares(struct cfs_rq *cfs_rq, long weight_delta);
+
 /*
  * Update the current task's runtime statistics. Skip current tasks that
  * are not in our scheduling class.
@@ -514,6 +561,10 @@ __update_curr(struct cfs_rq *cfs_rq, struct sched_entity *curr,
 
 	curr->vruntime += delta_exec_weighted;
 	update_min_vruntime(cfs_rq);
+
+#if defined CONFIG_SMP && defined CONFIG_FAIR_GROUP_SCHED
+	cfs_rq->load_unacc_exec_time += delta_exec;
+#endif
 }
 
 static void update_curr(struct cfs_rq *cfs_rq)
@@ -633,7 +684,6 @@ account_entity_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se)
 		list_add(&se->group_node, &cfs_rq->tasks);
 	}
 	cfs_rq->nr_running++;
-	se->on_rq = 1;
 }
 
 static void
@@ -647,9 +697,140 @@ account_entity_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se)
 		list_del_init(&se->group_node);
 	}
 	cfs_rq->nr_running--;
-	se->on_rq = 0;
 }
 
+#if defined CONFIG_SMP && defined CONFIG_FAIR_GROUP_SCHED
+static void update_cfs_rq_load_contribution(struct cfs_rq *cfs_rq,
+					    int global_update)
+{
+	struct task_group *tg = cfs_rq->tg;
+	long load_avg;
+
+	load_avg = div64_u64(cfs_rq->load_avg, cfs_rq->load_period+1);
+	load_avg -= cfs_rq->load_contribution;
+
+	if (global_update || abs(load_avg) > cfs_rq->load_contribution / 8) {
+		atomic_add(load_avg, &tg->load_weight);
+		cfs_rq->load_contribution += load_avg;
+	}
+}
+
+static void update_cfs_load(struct cfs_rq *cfs_rq, int global_update)
+{
+	u64 period = sysctl_sched_shares_window;
+	u64 now, delta;
+	unsigned long load = cfs_rq->load.weight;
+
+	if (!cfs_rq)
+		return;
+
+	now = rq_of(cfs_rq)->clock;
+	delta = now - cfs_rq->load_stamp;
+
+	/* truncate load history at 4 idle periods */
+	if (cfs_rq->load_stamp > cfs_rq->load_last &&
+	    now - cfs_rq->load_last > 4 * period) {
+		cfs_rq->load_period = 0;
+		cfs_rq->load_avg = 0;
+	}
+
+	cfs_rq->load_stamp = now;
+	cfs_rq->load_unacc_exec_time = 0;
+	cfs_rq->load_period += delta;
+	if (load) {
+		cfs_rq->load_last = now;
+		cfs_rq->load_avg += delta * load;
+	}
+
+	/* consider updating load contribution on each fold or truncate */
+	if (global_update || cfs_rq->load_period > period
+	    || !cfs_rq->load_period)
+		update_cfs_rq_load_contribution(cfs_rq, global_update);
+
+	while (cfs_rq->load_period > period) {
+		/*
+		 * Inline assembly required to prevent the compiler
+		 * optimising this loop into a divmod call.
+		 * See __iter_div_u64_rem() for another example of this.
+		 */
+		asm("" : "+rm" (cfs_rq->load_period));
+		cfs_rq->load_period /= 2;
+		cfs_rq->load_avg /= 2;
+	}
+
+	if (!cfs_rq->curr && !cfs_rq->nr_running && !cfs_rq->load_avg)
+		list_del_leaf_cfs_rq(cfs_rq);
+}
+
+static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se,
+			    unsigned long weight)
+{
+	if (se->on_rq) {
+		/* commit outstanding execution time */
+		if (cfs_rq->curr == se)
+			update_curr(cfs_rq);
+		account_entity_dequeue(cfs_rq, se);
+	}
+
+	update_load_set(&se->load, weight);
+
+	if (se->on_rq)
+		account_entity_enqueue(cfs_rq, se);
+}
+
+static void update_cfs_shares(struct cfs_rq *cfs_rq, long weight_delta)
+{
+	struct task_group *tg;
+	struct sched_entity *se;
+	long load_weight, load, shares;
+
+	if (!cfs_rq)
+		return;
+
+	tg = cfs_rq->tg;
+	se = tg->se[cpu_of(rq_of(cfs_rq))];
+	if (!se)
+		return;
+
+	load = cfs_rq->load.weight + weight_delta;
+
+	load_weight = atomic_read(&tg->load_weight);
+	load_weight -= cfs_rq->load_contribution;
+	load_weight += load;
+
+	shares = (tg->shares * load);
+	if (load_weight)
+		shares /= load_weight;
+
+	if (shares < MIN_SHARES)
+		shares = MIN_SHARES;
+	if (shares > tg->shares)
+		shares = tg->shares;
+
+	reweight_entity(cfs_rq_of(se), se, shares);
+}
+
+static void update_entity_shares_tick(struct cfs_rq *cfs_rq)
+{
+	if (cfs_rq->load_unacc_exec_time > sysctl_sched_shares_window) {
+		update_cfs_load(cfs_rq, 0);
+		update_cfs_shares(cfs_rq, 0);
+	}
+}
+#else /* CONFIG_FAIR_GROUP_SCHED */
+static void update_cfs_load(struct cfs_rq *cfs_rq, int global_update)
+{
+}
+
+static inline void update_cfs_shares(struct cfs_rq *cfs_rq, long weight_delta)
+{
+}
+
+static inline void update_entity_shares_tick(struct cfs_rq *cfs_rq)
+{
+}
+#endif /* CONFIG_FAIR_GROUP_SCHED */
+
 static void enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
 #ifdef CONFIG_SCHEDSTATS
@@ -771,6 +952,8 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 	 * Update run-time statistics of the 'current'.
 	 */
 	update_curr(cfs_rq);
+	update_cfs_load(cfs_rq, 0);
+	update_cfs_shares(cfs_rq, se->load.weight);
 	account_entity_enqueue(cfs_rq, se);
 
 	if (flags & ENQUEUE_WAKEUP) {
@@ -782,6 +965,10 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 	check_spread(cfs_rq, se);
 	if (se != cfs_rq->curr)
 		__enqueue_entity(cfs_rq, se);
+	se->on_rq = 1;
+
+	if (cfs_rq->nr_running == 1)
+		list_add_leaf_cfs_rq(cfs_rq);
 }
 
 static void __clear_buddies(struct cfs_rq *cfs_rq, struct sched_entity *se)
@@ -825,8 +1012,11 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 
 	if (se != cfs_rq->curr)
 		__dequeue_entity(cfs_rq, se);
+	se->on_rq = 0;
+	update_cfs_load(cfs_rq, 0);
 	account_entity_dequeue(cfs_rq, se);
 	update_min_vruntime(cfs_rq);
+	update_cfs_shares(cfs_rq, 0);
 
 	/*
 	 * Normalize the entity after updating the min_vruntime because the
@@ -955,6 +1145,11 @@ entity_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr, int queued)
 	 */
 	update_curr(cfs_rq);
 
+	/*
+	 * Update share accounting for long-running entities.
+	 */
+	update_entity_shares_tick(cfs_rq);
+
 #ifdef CONFIG_SCHED_HRTICK
 	/*
 	 * queued ticks are scheduled to match the slice, so don't bother
@@ -1055,6 +1250,13 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 		flags = ENQUEUE_WAKEUP;
 	}
 
+	for_each_sched_entity(se) {
+		struct cfs_rq *cfs_rq = cfs_rq_of(se);
+
+		update_cfs_load(cfs_rq, 0);
+		update_cfs_shares(cfs_rq, 0);
+	}
+
 	hrtick_update(rq);
 }
 
@@ -1071,12 +1273,20 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 	for_each_sched_entity(se) {
 		cfs_rq = cfs_rq_of(se);
 		dequeue_entity(cfs_rq, se, flags);
+
 		/* Don't dequeue parent if it has other entities besides us */
 		if (cfs_rq->load.weight)
 			break;
 		flags |= DEQUEUE_SLEEP;
 	}
 
+	for_each_sched_entity(se) {
+		struct cfs_rq *cfs_rq = cfs_rq_of(se);
+
+		update_cfs_load(cfs_rq, 0);
+		update_cfs_shares(cfs_rq, 0);
+	}
+
 	hrtick_update(rq);
 }
 
@@ -1143,51 +1353,20 @@ static void task_waking_fair(struct rq *rq, struct task_struct *p)
  * Adding load to a group doesn't make a group heavier, but can cause movement
  * of group shares between cpus. Assuming the shares were perfectly aligned one
  * can calculate the shift in shares.
- *
- * The problem is that perfectly aligning the shares is rather expensive, hence
- * we try to avoid doing that too often - see update_shares(), which ratelimits
- * this change.
- *
- * We compensate this by not only taking the current delta into account, but
- * also considering the delta between when the shares were last adjusted and
- * now.
- *
- * We still saw a performance dip, some tracing learned us that between
- * cgroup:/ and cgroup:/foo balancing the number of affine wakeups increased
- * significantly. Therefore try to bias the error in direction of failing
- * the affine wakeup.
- *
  */
-static long effective_load(struct task_group *tg, int cpu,
-		long wl, long wg)
+static long effective_load(struct task_group *tg, int cpu, long wl, long wg)
 {
 	struct sched_entity *se = tg->se[cpu];
 
 	if (!tg->parent)
 		return wl;
 
-	/*
-	 * By not taking the decrease of shares on the other cpu into
-	 * account our error leans towards reducing the affine wakeups.
-	 */
-	if (!wl && sched_feat(ASYM_EFF_LOAD))
-		return wl;
-
 	for_each_sched_entity(se) {
 		long S, rw, s, a, b;
-		long more_w;
-
-		/*
-		 * Instead of using this increment, also add the difference
-		 * between when the shares were last updated and now.
-		 */
-		more_w = se->my_q->load.weight - se->my_q->rq_weight;
-		wl += more_w;
-		wg += more_w;
 
 		S = se->my_q->tg->shares;
-		s = se->my_q->shares;
-		rw = se->my_q->rq_weight;
+		s = se->load.weight;
+		rw = se->my_q->load.weight;
 
 		a = S*(rw + wl);
 		b = S*rw + s*wg;
@@ -1508,23 +1687,6 @@ select_task_rq_fair(struct rq *rq, struct task_struct *p, int sd_flag, int wake_
 			sd = tmp;
 	}
 
-#ifdef CONFIG_FAIR_GROUP_SCHED
-	if (sched_feat(LB_SHARES_UPDATE)) {
-		/*
-		 * Pick the largest domain to update shares over
-		 */
-		tmp = sd;
-		if (affine_sd && (!tmp || affine_sd->span_weight > sd->span_weight))
-			tmp = affine_sd;
-
-		if (tmp) {
-			raw_spin_unlock(&rq->lock);
-			update_shares(tmp);
-			raw_spin_lock(&rq->lock);
-		}
-	}
-#endif
-
 	if (affine_sd) {
 		if (cpu == prev_cpu || wake_affine(affine_sd, p, sync))
 			return select_idle_sibling(p, cpu);
@@ -1909,6 +2071,48 @@ out:
 }
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
+/*
+ * update tg->load_weight by folding this cpu's load_avg
+ */
+static int update_shares_cpu(struct task_group *tg, int cpu)
+{
+	struct cfs_rq *cfs_rq;
+	unsigned long flags;
+	struct rq *rq;
+
+	if (!tg->se[cpu])
+		return 0;
+
+	rq = cpu_rq(cpu);
+	cfs_rq = tg->cfs_rq[cpu];
+
+	raw_spin_lock_irqsave(&rq->lock, flags);
+
+	update_rq_clock(rq);
+	update_cfs_load(cfs_rq, 1);
+
+	/*
+	 * We need to update shares after updating tg->load_weight in
+	 * order to adjust the weight of groups with long running tasks.
+	 */
+	update_cfs_shares(cfs_rq, 0);
+
+	raw_spin_unlock_irqrestore(&rq->lock, flags);
+
+	return 0;
+}
+
+static void update_shares(int cpu)
+{
+	struct cfs_rq *cfs_rq;
+	struct rq *rq = cpu_rq(cpu);
+
+	rcu_read_lock();
+	for_each_leaf_cfs_rq(rq, cfs_rq)
+		update_shares_cpu(cfs_rq->tg, cpu);
+	rcu_read_unlock();
+}
+
 static unsigned long
 load_balance_fair(struct rq *this_rq, int this_cpu, struct rq *busiest,
 		  unsigned long max_load_move,
@@ -1956,6 +2160,10 @@ load_balance_fair(struct rq *this_rq, int this_cpu, struct rq *busiest,
 	return max_load_move - rem_load_move;
 }
 #else
+static inline void update_shares(int cpu)
+{
+}
+
 static unsigned long
 load_balance_fair(struct rq *this_rq, int this_cpu, struct rq *busiest,
 		  unsigned long max_load_move,
@@ -3032,7 +3240,6 @@ static int load_balance(int this_cpu, struct rq *this_rq,
 	schedstat_inc(sd, lb_count[idle]);
 
 redo:
-	update_shares(sd);
 	group = find_busiest_group(sd, this_cpu, &imbalance, idle, &sd_idle,
 				   cpus, balance);
 
@@ -3174,8 +3381,6 @@ out_one_pinned:
 	else
 		ld_moved = 0;
 out:
-	if (ld_moved)
-		update_shares(sd);
 	return ld_moved;
 }
 
@@ -3199,6 +3404,7 @@ static void idle_balance(int this_cpu, struct rq *this_rq)
 	 */
 	raw_spin_unlock(&this_rq->lock);
 
+	update_shares(this_cpu);
 	for_each_domain(this_cpu, sd) {
 		unsigned long interval;
 		int balance = 1;
@@ -3569,6 +3775,8 @@ static void rebalance_domains(int cpu, enum cpu_idle_type idle)
 	int update_next_balance = 0;
 	int need_serialize;
 
+	update_shares(cpu);
+
 	for_each_domain(cpu, sd) {
 		if (!(sd->flags & SD_LOAD_BALANCE))
 			continue;

kernel/sched_features.h

@@ -52,8 +52,6 @@ SCHED_FEAT(ARCH_POWER, 0)
 SCHED_FEAT(HRTICK, 0)
 SCHED_FEAT(DOUBLE_TICK, 0)
 SCHED_FEAT(LB_BIAS, 1)
-SCHED_FEAT(LB_SHARES_UPDATE, 1)
-SCHED_FEAT(ASYM_EFF_LOAD, 1)
 
 /*
  * Spin-wait on mutex acquisition when the mutex owner is running on

kernel/sched_rt.c

@@ -183,6 +183,17 @@ static inline u64 sched_rt_period(struct rt_rq *rt_rq)
 	return ktime_to_ns(rt_rq->tg->rt_bandwidth.rt_period);
 }
 
+static inline void list_add_leaf_rt_rq(struct rt_rq *rt_rq)
+{
+	list_add_rcu(&rt_rq->leaf_rt_rq_list,
+			&rq_of_rt_rq(rt_rq)->leaf_rt_rq_list);
+}
+
+static inline void list_del_leaf_rt_rq(struct rt_rq *rt_rq)
+{
+	list_del_rcu(&rt_rq->leaf_rt_rq_list);
+}
+
 #define for_each_leaf_rt_rq(rt_rq, rq) \
 	list_for_each_entry_rcu(rt_rq, &rq->leaf_rt_rq_list, leaf_rt_rq_list)
 
@@ -276,6 +287,14 @@ static inline u64 sched_rt_period(struct rt_rq *rt_rq)
 	return ktime_to_ns(def_rt_bandwidth.rt_period);
 }
 
+static inline void list_add_leaf_rt_rq(struct rt_rq *rt_rq)
+{
+}
+
+static inline void list_del_leaf_rt_rq(struct rt_rq *rt_rq)
+{
+}
+
 #define for_each_leaf_rt_rq(rt_rq, rq) \
 	for (rt_rq = &rq->rt; rt_rq; rt_rq = NULL)
 
@@ -825,6 +844,9 @@ static void __enqueue_rt_entity(struct sched_rt_entity *rt_se, bool head)
 	if (group_rq && (rt_rq_throttled(group_rq) || !group_rq->rt_nr_running))
 		return;
 
+	if (!rt_rq->rt_nr_running)
+		list_add_leaf_rt_rq(rt_rq);
+
 	if (head)
 		list_add(&rt_se->run_list, queue);
 	else
@@ -844,6 +866,8 @@ static void __dequeue_rt_entity(struct sched_rt_entity *rt_se)
 		__clear_bit(rt_se_prio(rt_se), array->bitmap);
 
 	dec_rt_tasks(rt_se, rt_rq);
+	if (!rt_rq->rt_nr_running)
+		list_del_leaf_rt_rq(rt_rq);
 }
 
 /*

kernel/softirq.c

@@ -853,7 +853,9 @@ static int __cpuinit cpu_callback(struct notifier_block *nfb,
 			     cpumask_any(cpu_online_mask));
 	case CPU_DEAD:
 	case CPU_DEAD_FROZEN: {
-		struct sched_param param = { .sched_priority = MAX_RT_PRIO-1 };
+		static struct sched_param param = {
+			.sched_priority = MAX_RT_PRIO-1
+		};
 
 		p = per_cpu(ksoftirqd, hotcpu);
 		per_cpu(ksoftirqd, hotcpu) = NULL;

kernel/sys.c

@@ -1080,8 +1080,10 @@ SYSCALL_DEFINE0(setsid)
 	err = session;
 out:
 	write_unlock_irq(&tasklist_lock);
-	if (err > 0)
+	if (err > 0) {
 		proc_sid_connector(group_leader);
+		sched_autogroup_create_attach(group_leader);
+	}
 	return err;
 }
 

kernel/sysctl.c

@@ -259,8 +259,6 @@ static int min_wakeup_granularity_ns;			/* 0 usecs */
 static int max_wakeup_granularity_ns = NSEC_PER_SEC;	/* 1 second */
 static int min_sched_tunable_scaling = SCHED_TUNABLESCALING_NONE;
 static int max_sched_tunable_scaling = SCHED_TUNABLESCALING_END-1;
-static int min_sched_shares_ratelimit = 100000; /* 100 usec */
-static int max_sched_shares_ratelimit = NSEC_PER_SEC; /* 1 second */
 #endif
 
 #ifdef CONFIG_COMPACTION
@@ -304,15 +302,6 @@ static struct ctl_table kern_table[] = {
 		.extra1		= &min_wakeup_granularity_ns,
 		.extra2		= &max_wakeup_granularity_ns,
 	},
-	{
-		.procname	= "sched_shares_ratelimit",
-		.data		= &sysctl_sched_shares_ratelimit,
-		.maxlen		= sizeof(unsigned int),
-		.mode		= 0644,
-		.proc_handler	= sched_proc_update_handler,
-		.extra1		= &min_sched_shares_ratelimit,
-		.extra2		= &max_sched_shares_ratelimit,
-	},
 	{
 		.procname	= "sched_tunable_scaling",
 		.data		= &sysctl_sched_tunable_scaling,
@@ -322,14 +311,6 @@ static struct ctl_table kern_table[] = {
 		.extra1		= &min_sched_tunable_scaling,
 		.extra2		= &max_sched_tunable_scaling,
 	},
-	{
-		.procname	= "sched_shares_thresh",
-		.data		= &sysctl_sched_shares_thresh,
-		.maxlen		= sizeof(unsigned int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &zero,
-	},
 	{
 		.procname	= "sched_migration_cost",
 		.data		= &sysctl_sched_migration_cost,
@@ -351,6 +332,13 @@ static struct ctl_table kern_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec,
 	},
+	{
+		.procname	= "sched_shares_window",
+		.data		= &sysctl_sched_shares_window,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
 	{
 		.procname	= "timer_migration",
 		.data		= &sysctl_timer_migration,
@@ -382,6 +370,17 @@ static struct ctl_table kern_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec,
 	},
+#ifdef CONFIG_SCHED_AUTOGROUP
+	{
+		.procname	= "sched_autogroup_enabled",
+		.data		= &sysctl_sched_autogroup_enabled,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+		.extra1		= &zero,
+		.extra2		= &one,
+	},
+#endif
 #ifdef CONFIG_PROVE_LOCKING
 	{
 		.procname	= "prove_locking",

kernel/trace/trace_selftest.c

@@ -558,7 +558,7 @@ trace_selftest_startup_nop(struct tracer *trace, struct trace_array *tr)
 static int trace_wakeup_test_thread(void *data)
 {
 	/* Make this a RT thread, doesn't need to be too high */
-	struct sched_param param = { .sched_priority = 5 };
+	static struct sched_param param = { .sched_priority = 5 };
 	struct completion *x = data;
 
 	sched_setscheduler(current, SCHED_FIFO, &param);

kernel/watchdog.c

@@ -309,7 +309,7 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
  */
 static int watchdog(void *unused)
 {
-	struct sched_param param = { .sched_priority = MAX_RT_PRIO-1 };
+	static struct sched_param param = { .sched_priority = MAX_RT_PRIO-1 };
 	struct hrtimer *hrtimer = &__raw_get_cpu_var(watchdog_hrtimer);
 
 	sched_setscheduler(current, SCHED_FIFO, &param);