Fixed MTP to work with TWRP

kernel/sched/Makefile

@@ -0,0 +1,21 @@
+ifdef CONFIG_FUNCTION_TRACER
+CFLAGS_REMOVE_clock.o = -pg
+endif
+
+ifneq ($(CONFIG_SCHED_OMIT_FRAME_POINTER),y)
+# According to Alan Modra <alan@linuxcare.com.au>, the -fno-omit-frame-pointer is
+# needed for x86 only.  Why this used to be enabled for all architectures is beyond
+# me.  I suspect most platforms don't need this, but until we know that for sure
+# I turn this off for IA-64 only.  Andreas Schwab says it's also needed on m68k
+# to get a correct value for the wait-channel (WCHAN in ps). --davidm
+CFLAGS_core.o := $(PROFILING) -fno-omit-frame-pointer
+endif
+
+obj-y += core.o proc.o clock.o cputime.o
+obj-y += idle_task.o fair.o rt.o deadline.o stop_task.o
+obj-y += wait.o completion.o idle.o
+obj-$(CONFIG_SMP) += cpupri.o cpudeadline.o
+obj-$(CONFIG_SCHED_AUTOGROUP) += auto_group.o
+obj-$(CONFIG_SCHEDSTATS) += stats.o
+obj-$(CONFIG_SCHED_DEBUG) += debug.o
+obj-$(CONFIG_CGROUP_CPUACCT) += cpuacct.o

kernel/sched/auto_group.c

@@ -0,0 +1,253 @@
+#ifdef CONFIG_SCHED_AUTOGROUP
+
+#include "sched.h"
+
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
+#include <linux/kallsyms.h>
+#include <linux/utsname.h>
+#include <linux/security.h>
+#include <linux/export.h>
+
+unsigned int __read_mostly sysctl_sched_autogroup_enabled = 1;
+static struct autogroup autogroup_default;
+static atomic_t autogroup_seq_nr;
+
+void __init autogroup_init(struct task_struct *init_task)
+{
+	autogroup_default.tg = &root_task_group;
+	kref_init(&autogroup_default.kref);
+	init_rwsem(&autogroup_default.lock);
+	init_task->signal->autogroup = &autogroup_default;
+}
+
+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);
+
+#ifdef CONFIG_RT_GROUP_SCHED
+	/* We've redirected RT tasks to the root task group... */
+	ag->tg->rt_se = NULL;
+	ag->tg->rt_rq = NULL;
+#endif
+	sched_offline_group(ag->tg);
+	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(&root_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;
+#ifdef CONFIG_RT_GROUP_SCHED
+	/*
+	 * Autogroup RT tasks are redirected to the root task group
+	 * so we don't have to move tasks around upon policy change,
+	 * or flail around trying to allocate bandwidth on the fly.
+	 * A bandwidth exception in __sched_setscheduler() allows
+	 * the policy change to proceed.
+	 */
+	free_rt_sched_group(tg);
+	tg->rt_se = root_task_group.rt_se;
+	tg->rt_rq = root_task_group.rt_rq;
+#endif
+	tg->autogroup = ag;
+
+	sched_online_group(tg, &root_task_group);
+	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);
+}
+
+bool task_wants_autogroup(struct task_struct *p, struct task_group *tg)
+{
+	if (tg != &root_task_group)
+		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 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);
+
+	if (!ACCESS_ONCE(sysctl_sched_autogroup_enabled))
+		goto out;
+
+	for_each_thread(p, t)
+		sched_move_task(t);
+out:
+	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 reference 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 < MIN_NICE || nice > MAX_NICE)
+		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);
+
+	if (!task_group_is_autogroup(ag->tg))
+		goto out;
+
+	down_read(&ag->lock);
+	seq_printf(m, "/autogroup-%ld nice %d\n", ag->id, ag->nice);
+	up_read(&ag->lock);
+
+out:
+	autogroup_kref_put(ag);
+}
+#endif /* CONFIG_PROC_FS */
+
+#ifdef CONFIG_SCHED_DEBUG
+int autogroup_path(struct task_group *tg, char *buf, int buflen)
+{
+	if (!task_group_is_autogroup(tg))
+		return 0;
+
+	return snprintf(buf, buflen, "%s-%ld", "/autogroup", tg->autogroup->id);
+}
+#endif /* CONFIG_SCHED_DEBUG */
+
+#endif /* CONFIG_SCHED_AUTOGROUP */

kernel/sched/auto_group.h

@@ -0,0 +1,64 @@
+#ifdef CONFIG_SCHED_AUTOGROUP
+
+#include <linux/kref.h>
+#include <linux/rwsem.h>
+
+struct autogroup {
+	/*
+	 * reference doesn't mean how many thread attach to this
+	 * autogroup now. It just stands for the number of task
+	 * could use this autogroup.
+	 */
+	struct kref		kref;
+	struct task_group	*tg;
+	struct rw_semaphore	lock;
+	unsigned long		id;
+	int			nice;
+};
+
+extern void autogroup_init(struct task_struct *init_task);
+extern void autogroup_free(struct task_group *tg);
+
+static inline bool task_group_is_autogroup(struct task_group *tg)
+{
+	return !!tg->autogroup;
+}
+
+extern bool task_wants_autogroup(struct task_struct *p, struct task_group *tg);
+
+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;
+}
+
+extern int autogroup_path(struct task_group *tg, char *buf, int buflen);
+
+#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 bool task_group_is_autogroup(struct task_group *tg)
+{
+	return 0;
+}
+
+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

@@ -0,0 +1,422 @@
+/*
+ * sched_clock for unstable cpu clocks
+ *
+ *  Copyright (C) 2008 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ *
+ *  Updates and enhancements:
+ *    Copyright (C) 2008 Red Hat, Inc. Steven Rostedt <srostedt@redhat.com>
+ *
+ * Based on code by:
+ *   Ingo Molnar <mingo@redhat.com>
+ *   Guillaume Chazarain <guichaz@gmail.com>
+ *
+ *
+ * What:
+ *
+ * cpu_clock(i) provides a fast (execution time) high resolution
+ * clock with bounded drift between CPUs. The value of cpu_clock(i)
+ * is monotonic for constant i. The timestamp returned is in nanoseconds.
+ *
+ * ######################### BIG FAT WARNING ##########################
+ * # when comparing cpu_clock(i) to cpu_clock(j) for i != j, time can #
+ * # go backwards !!                                                  #
+ * ####################################################################
+ *
+ * There is no strict promise about the base, although it tends to start
+ * at 0 on boot (but people really shouldn't rely on that).
+ *
+ * cpu_clock(i)       -- can be used from any context, including NMI.
+ * local_clock()      -- is cpu_clock() on the current cpu.
+ *
+ * sched_clock_cpu(i)
+ *
+ * How:
+ *
+ * The implementation either uses sched_clock() when
+ * !CONFIG_HAVE_UNSTABLE_SCHED_CLOCK, which means in that case the
+ * sched_clock() is assumed to provide these properties (mostly it means
+ * the architecture provides a globally synchronized highres time source).
+ *
+ * Otherwise it tries to create a semi stable clock from a mixture of other
+ * clocks, including:
+ *
+ *  - GTOD (clock monotomic)
+ *  - sched_clock()
+ *  - explicit idle events
+ *
+ * We use GTOD as base and use sched_clock() deltas to improve resolution. The
+ * deltas are filtered to provide monotonicity and keeping it within an
+ * expected window.
+ *
+ * Furthermore, explicit sleep and wakeup hooks allow us to account for time
+ * that is otherwise invisible (TSC gets stopped).
+ *
+ */
+#include <linux/spinlock.h>
+#include <linux/hardirq.h>
+#include <linux/export.h>
+#include <linux/percpu.h>
+#include <linux/ktime.h>
+#include <linux/sched.h>
+#include <linux/static_key.h>
+#include <linux/workqueue.h>
+#include <linux/compiler.h>
+
+/*
+ * Scheduler clock - returns current time in nanosec units.
+ * This is default implementation.
+ * Architectures and sub-architectures can override this.
+ */
+unsigned long long __weak sched_clock(void)
+{
+	return (unsigned long long)(jiffies - INITIAL_JIFFIES)
+					* (NSEC_PER_SEC / HZ);
+}
+EXPORT_SYMBOL_GPL(sched_clock);
+
+__read_mostly int sched_clock_running;
+
+#ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
+static struct static_key __sched_clock_stable = STATIC_KEY_INIT;
+static int __sched_clock_stable_early;
+
+int sched_clock_stable(void)
+{
+	return static_key_false(&__sched_clock_stable);
+}
+
+static void __set_sched_clock_stable(void)
+{
+	if (!sched_clock_stable())
+		static_key_slow_inc(&__sched_clock_stable);
+}
+
+void set_sched_clock_stable(void)
+{
+	__sched_clock_stable_early = 1;
+
+	smp_mb(); /* matches sched_clock_init() */
+
+	if (!sched_clock_running)
+		return;
+
+	__set_sched_clock_stable();
+}
+
+static void __clear_sched_clock_stable(struct work_struct *work)
+{
+	/* XXX worry about clock continuity */
+	if (sched_clock_stable())
+		static_key_slow_dec(&__sched_clock_stable);
+}
+
+static DECLARE_WORK(sched_clock_work, __clear_sched_clock_stable);
+
+void clear_sched_clock_stable(void)
+{
+	__sched_clock_stable_early = 0;
+
+	smp_mb(); /* matches sched_clock_init() */
+
+	if (!sched_clock_running)
+		return;
+
+	schedule_work(&sched_clock_work);
+}
+
+struct sched_clock_data {
+	u64			tick_raw;
+	u64			tick_gtod;
+	u64			clock;
+};
+
+static DEFINE_PER_CPU_SHARED_ALIGNED(struct sched_clock_data, sched_clock_data);
+
+static inline struct sched_clock_data *this_scd(void)
+{
+	return this_cpu_ptr(&sched_clock_data);
+}
+
+static inline struct sched_clock_data *cpu_sdc(int cpu)
+{
+	return &per_cpu(sched_clock_data, cpu);
+}
+
+void sched_clock_init(void)
+{
+	u64 ktime_now = ktime_to_ns(ktime_get());
+	int cpu;
+
+	for_each_possible_cpu(cpu) {
+		struct sched_clock_data *scd = cpu_sdc(cpu);
+
+		scd->tick_raw = 0;
+		scd->tick_gtod = ktime_now;
+		scd->clock = ktime_now;
+	}
+
+	sched_clock_running = 1;
+
+	/*
+	 * Ensure that it is impossible to not do a static_key update.
+	 *
+	 * Either {set,clear}_sched_clock_stable() must see sched_clock_running
+	 * and do the update, or we must see their __sched_clock_stable_early
+	 * and do the update, or both.
+	 */
+	smp_mb(); /* matches {set,clear}_sched_clock_stable() */
+
+	if (__sched_clock_stable_early)
+		__set_sched_clock_stable();
+	else
+		__clear_sched_clock_stable(NULL);
+}
+
+/*
+ * min, max except they take wrapping into account
+ */
+
+static inline u64 wrap_min(u64 x, u64 y)
+{
+	return (s64)(x - y) < 0 ? x : y;
+}
+
+static inline u64 wrap_max(u64 x, u64 y)
+{
+	return (s64)(x - y) > 0 ? x : y;
+}
+
+/*
+ * update the percpu scd from the raw @now value
+ *
+ *  - filter out backward motion
+ *  - use the GTOD tick value to create a window to filter crazy TSC values
+ */
+static u64 sched_clock_local(struct sched_clock_data *scd)
+{
+	u64 now, clock, old_clock, min_clock, max_clock;
+	s64 delta;
+
+again:
+	now = sched_clock();
+	delta = now - scd->tick_raw;
+	if (unlikely(delta < 0))
+		delta = 0;
+
+	old_clock = scd->clock;
+
+	/*
+	 * scd->clock = clamp(scd->tick_gtod + delta,
+	 *		      max(scd->tick_gtod, scd->clock),
+	 *		      scd->tick_gtod + TICK_NSEC);
+	 */
+
+	clock = scd->tick_gtod + delta;
+	min_clock = wrap_max(scd->tick_gtod, old_clock);
+	max_clock = wrap_max(old_clock, scd->tick_gtod + TICK_NSEC);
+
+	clock = wrap_max(clock, min_clock);
+	clock = wrap_min(clock, max_clock);
+
+	if (cmpxchg64(&scd->clock, old_clock, clock) != old_clock)
+		goto again;
+
+	return clock;
+}
+
+static u64 sched_clock_remote(struct sched_clock_data *scd)
+{
+	struct sched_clock_data *my_scd = this_scd();
+	u64 this_clock, remote_clock;
+	u64 *ptr, old_val, val;
+
+#if BITS_PER_LONG != 64
+again:
+	/*
+	 * Careful here: The local and the remote clock values need to
+	 * be read out atomic as we need to compare the values and
+	 * then update either the local or the remote side. So the
+	 * cmpxchg64 below only protects one readout.
+	 *
+	 * We must reread via sched_clock_local() in the retry case on
+	 * 32bit as an NMI could use sched_clock_local() via the
+	 * tracer and hit between the readout of
+	 * the low32bit and the high 32bit portion.
+	 */
+	this_clock = sched_clock_local(my_scd);
+	/*
+	 * We must enforce atomic readout on 32bit, otherwise the
+	 * update on the remote cpu can hit inbetween the readout of
+	 * the low32bit and the high 32bit portion.
+	 */
+	remote_clock = cmpxchg64(&scd->clock, 0, 0);
+#else
+	/*
+	 * On 64bit the read of [my]scd->clock is atomic versus the
+	 * update, so we can avoid the above 32bit dance.
+	 */
+	sched_clock_local(my_scd);
+again:
+	this_clock = my_scd->clock;
+	remote_clock = scd->clock;
+#endif
+
+	/*
+	 * Use the opportunity that we have both locks
+	 * taken to couple the two clocks: we take the
+	 * larger time as the latest time for both
+	 * runqueues. (this creates monotonic movement)
+	 */
+	if (likely((s64)(remote_clock - this_clock) < 0)) {
+		ptr = &scd->clock;
+		old_val = remote_clock;
+		val = this_clock;
+	} else {
+		/*
+		 * Should be rare, but possible:
+		 */
+		ptr = &my_scd->clock;
+		old_val = this_clock;
+		val = remote_clock;
+	}
+
+	if (cmpxchg64(ptr, old_val, val) != old_val)
+		goto again;
+
+	return val;
+}
+
+/*
+ * Similar to cpu_clock(), but requires local IRQs to be disabled.
+ *
+ * See cpu_clock().
+ */
+u64 sched_clock_cpu(int cpu)
+{
+	struct sched_clock_data *scd;
+	u64 clock;
+
+	if (sched_clock_stable())
+		return sched_clock();
+
+	if (unlikely(!sched_clock_running))
+		return 0ull;
+
+	preempt_disable_notrace();
+	scd = cpu_sdc(cpu);
+
+	if (cpu != smp_processor_id())
+		clock = sched_clock_remote(scd);
+	else
+		clock = sched_clock_local(scd);
+	preempt_enable_notrace();
+
+	return clock;
+}
+
+void sched_clock_tick(void)
+{
+	struct sched_clock_data *scd;
+	u64 now, now_gtod;
+
+	if (sched_clock_stable())
+		return;
+
+	if (unlikely(!sched_clock_running))
+		return;
+
+	WARN_ON_ONCE(!irqs_disabled());
+
+	scd = this_scd();
+	now_gtod = ktime_to_ns(ktime_get());
+	now = sched_clock();
+
+	scd->tick_raw = now;
+	scd->tick_gtod = now_gtod;
+	sched_clock_local(scd);
+}
+
+/*
+ * We are going deep-idle (irqs are disabled):
+ */
+void sched_clock_idle_sleep_event(void)
+{
+	sched_clock_cpu(smp_processor_id());
+}
+EXPORT_SYMBOL_GPL(sched_clock_idle_sleep_event);
+
+/*
+ * We just idled delta nanoseconds (called with irqs disabled):
+ */
+void sched_clock_idle_wakeup_event(u64 delta_ns)
+{
+	if (timekeeping_suspended)
+		return;
+
+	sched_clock_tick();
+	touch_softlockup_watchdog();
+}
+EXPORT_SYMBOL_GPL(sched_clock_idle_wakeup_event);
+
+/*
+ * As outlined at the top, provides a fast, high resolution, nanosecond
+ * time source that is monotonic per cpu argument and has bounded drift
+ * between cpus.
+ *
+ * ######################### BIG FAT WARNING ##########################
+ * # when comparing cpu_clock(i) to cpu_clock(j) for i != j, time can #
+ * # go backwards !!                                                  #
+ * ####################################################################
+ */
+u64 cpu_clock(int cpu)
+{
+	if (!sched_clock_stable())
+		return sched_clock_cpu(cpu);
+
+	return sched_clock();
+}
+
+/*
+ * Similar to cpu_clock() for the current cpu. Time will only be observed
+ * to be monotonic if care is taken to only compare timestampt taken on the
+ * same CPU.
+ *
+ * See cpu_clock().
+ */
+u64 local_clock(void)
+{
+	if (!sched_clock_stable())
+		return sched_clock_cpu(raw_smp_processor_id());
+
+	return sched_clock();
+}
+
+#else /* CONFIG_HAVE_UNSTABLE_SCHED_CLOCK */
+
+void sched_clock_init(void)
+{
+	sched_clock_running = 1;
+}
+
+u64 sched_clock_cpu(int cpu)
+{
+	if (unlikely(!sched_clock_running))
+		return 0;
+
+	return sched_clock();
+}
+
+u64 cpu_clock(int cpu)
+{
+	return sched_clock();
+}
+
+u64 local_clock(void)
+{
+	return sched_clock();
+}
+
+#endif /* CONFIG_HAVE_UNSTABLE_SCHED_CLOCK */
+
+EXPORT_SYMBOL_GPL(cpu_clock);
+EXPORT_SYMBOL_GPL(local_clock);

kernel/sched/completion.c

@@ -0,0 +1,299 @@
+/*
+ * Generic wait-for-completion handler;
+ *
+ * It differs from semaphores in that their default case is the opposite,
+ * wait_for_completion default blocks whereas semaphore default non-block. The
+ * interface also makes it easy to 'complete' multiple waiting threads,
+ * something which isn't entirely natural for semaphores.
+ *
+ * But more importantly, the primitive documents the usage. Semaphores would
+ * typically be used for exclusion which gives rise to priority inversion.
+ * Waiting for completion is a typically sync point, but not an exclusion point.
+ */
+
+#include <linux/sched.h>
+#include <linux/completion.h>
+
+/**
+ * complete: - signals a single thread waiting on this completion
+ * @x:  holds the state of this particular completion
+ *
+ * This will wake up a single thread waiting on this completion. Threads will be
+ * awakened in the same order in which they were queued.
+ *
+ * See also complete_all(), wait_for_completion() and related routines.
+ *
+ * It may be assumed that this function implies a write memory barrier before
+ * changing the task state if and only if any tasks are woken up.
+ */
+void complete(struct completion *x)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&x->wait.lock, flags);
+	x->done++;
+	__wake_up_locked(&x->wait, TASK_NORMAL, 1);
+	spin_unlock_irqrestore(&x->wait.lock, flags);
+}
+EXPORT_SYMBOL(complete);
+
+/**
+ * complete_all: - signals all threads waiting on this completion
+ * @x:  holds the state of this particular completion
+ *
+ * This will wake up all threads waiting on this particular completion event.
+ *
+ * It may be assumed that this function implies a write memory barrier before
+ * changing the task state if and only if any tasks are woken up.
+ */
+void complete_all(struct completion *x)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&x->wait.lock, flags);
+	x->done += UINT_MAX/2;
+	__wake_up_locked(&x->wait, TASK_NORMAL, 0);
+	spin_unlock_irqrestore(&x->wait.lock, flags);
+}
+EXPORT_SYMBOL(complete_all);
+
+static inline long __sched
+do_wait_for_common(struct completion *x,
+		   long (*action)(long), long timeout, int state)
+{
+	if (!x->done) {
+		DECLARE_WAITQUEUE(wait, current);
+
+		__add_wait_queue_tail_exclusive(&x->wait, &wait);
+		do {
+			if (signal_pending_state(state, current)) {
+				timeout = -ERESTARTSYS;
+				break;
+			}
+			__set_current_state(state);
+			spin_unlock_irq(&x->wait.lock);
+			timeout = action(timeout);
+			spin_lock_irq(&x->wait.lock);
+		} while (!x->done && timeout);
+		__remove_wait_queue(&x->wait, &wait);
+		if (!x->done)
+			return timeout;
+	}
+	x->done--;
+	return timeout ?: 1;
+}
+
+static inline long __sched
+__wait_for_common(struct completion *x,
+		  long (*action)(long), long timeout, int state)
+{
+	might_sleep();
+
+	spin_lock_irq(&x->wait.lock);
+	timeout = do_wait_for_common(x, action, timeout, state);
+	spin_unlock_irq(&x->wait.lock);
+	return timeout;
+}
+
+static long __sched
+wait_for_common(struct completion *x, long timeout, int state)
+{
+	return __wait_for_common(x, schedule_timeout, timeout, state);
+}
+
+static long __sched
+wait_for_common_io(struct completion *x, long timeout, int state)
+{
+	return __wait_for_common(x, io_schedule_timeout, timeout, state);
+}
+
+/**
+ * wait_for_completion: - waits for completion of a task
+ * @x:  holds the state of this particular completion
+ *
+ * This waits to be signaled for completion of a specific task. It is NOT
+ * interruptible and there is no timeout.
+ *
+ * See also similar routines (i.e. wait_for_completion_timeout()) with timeout
+ * and interrupt capability. Also see complete().
+ */
+void __sched wait_for_completion(struct completion *x)
+{
+	wait_for_common(x, MAX_SCHEDULE_TIMEOUT, TASK_UNINTERRUPTIBLE);
+}
+EXPORT_SYMBOL(wait_for_completion);
+
+/**
+ * wait_for_completion_timeout: - waits for completion of a task (w/timeout)
+ * @x:  holds the state of this particular completion
+ * @timeout:  timeout value in jiffies
+ *
+ * This waits for either a completion of a specific task to be signaled or for a
+ * specified timeout to expire. The timeout is in jiffies. It is not
+ * interruptible.
+ *
+ * Return: 0 if timed out, and positive (at least 1, or number of jiffies left
+ * till timeout) if completed.
+ */
+unsigned long __sched
+wait_for_completion_timeout(struct completion *x, unsigned long timeout)
+{
+	return wait_for_common(x, timeout, TASK_UNINTERRUPTIBLE);
+}
+EXPORT_SYMBOL(wait_for_completion_timeout);
+
+/**
+ * wait_for_completion_io: - waits for completion of a task
+ * @x:  holds the state of this particular completion
+ *
+ * This waits to be signaled for completion of a specific task. It is NOT
+ * interruptible and there is no timeout. The caller is accounted as waiting
+ * for IO.
+ */
+void __sched wait_for_completion_io(struct completion *x)
+{
+	wait_for_common_io(x, MAX_SCHEDULE_TIMEOUT, TASK_UNINTERRUPTIBLE);
+}
+EXPORT_SYMBOL(wait_for_completion_io);
+
+/**
+ * wait_for_completion_io_timeout: - waits for completion of a task (w/timeout)
+ * @x:  holds the state of this particular completion
+ * @timeout:  timeout value in jiffies
+ *
+ * This waits for either a completion of a specific task to be signaled or for a
+ * specified timeout to expire. The timeout is in jiffies. It is not
+ * interruptible. The caller is accounted as waiting for IO.
+ *
+ * Return: 0 if timed out, and positive (at least 1, or number of jiffies left
+ * till timeout) if completed.
+ */
+unsigned long __sched
+wait_for_completion_io_timeout(struct completion *x, unsigned long timeout)
+{
+	return wait_for_common_io(x, timeout, TASK_UNINTERRUPTIBLE);
+}
+EXPORT_SYMBOL(wait_for_completion_io_timeout);
+
+/**
+ * wait_for_completion_interruptible: - waits for completion of a task (w/intr)
+ * @x:  holds the state of this particular completion
+ *
+ * This waits for completion of a specific task to be signaled. It is
+ * interruptible.
+ *
+ * Return: -ERESTARTSYS if interrupted, 0 if completed.
+ */
+int __sched wait_for_completion_interruptible(struct completion *x)
+{
+	long t = wait_for_common(x, MAX_SCHEDULE_TIMEOUT, TASK_INTERRUPTIBLE);
+	if (t == -ERESTARTSYS)
+		return t;
+	return 0;
+}
+EXPORT_SYMBOL(wait_for_completion_interruptible);
+
+/**
+ * wait_for_completion_interruptible_timeout: - waits for completion (w/(to,intr))
+ * @x:  holds the state of this particular completion
+ * @timeout:  timeout value in jiffies
+ *
+ * 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.
+ *
+ * Return: -ERESTARTSYS if interrupted, 0 if timed out, positive (at least 1,
+ * or number of jiffies left till timeout) if completed.
+ */
+long __sched
+wait_for_completion_interruptible_timeout(struct completion *x,
+					  unsigned long timeout)
+{
+	return wait_for_common(x, timeout, TASK_INTERRUPTIBLE);
+}
+EXPORT_SYMBOL(wait_for_completion_interruptible_timeout);
+
+/**
+ * wait_for_completion_killable: - waits for completion of a task (killable)
+ * @x:  holds the state of this particular completion
+ *
+ * This waits to be signaled for completion of a specific task. It can be
+ * interrupted by a kill signal.
+ *
+ * Return: -ERESTARTSYS if interrupted, 0 if completed.
+ */
+int __sched wait_for_completion_killable(struct completion *x)
+{
+	long t = wait_for_common(x, MAX_SCHEDULE_TIMEOUT, TASK_KILLABLE);
+	if (t == -ERESTARTSYS)
+		return t;
+	return 0;
+}
+EXPORT_SYMBOL(wait_for_completion_killable);
+
+/**
+ * wait_for_completion_killable_timeout: - waits for completion of a task (w/(to,killable))
+ * @x:  holds the state of this particular completion
+ * @timeout:  timeout value in jiffies
+ *
+ * This waits for either a completion of a specific task to be
+ * signaled or for a specified timeout to expire. It can be
+ * interrupted by a kill signal. The timeout is in jiffies.
+ *
+ * Return: -ERESTARTSYS if interrupted, 0 if timed out, positive (at least 1,
+ * or number of jiffies left till timeout) if completed.
+ */
+long __sched
+wait_for_completion_killable_timeout(struct completion *x,
+				     unsigned long timeout)
+{
+	return wait_for_common(x, timeout, TASK_KILLABLE);
+}
+EXPORT_SYMBOL(wait_for_completion_killable_timeout);
+
+/**
+ *	try_wait_for_completion - try to decrement a completion without blocking
+ *	@x:	completion structure
+ *
+ *	Return: 0 if a decrement cannot be done without blocking
+ *		 1 if a decrement succeeded.
+ *
+ *	If a completion is being used as a counting completion,
+ *	attempt to decrement the counter without blocking. This
+ *	enables us to avoid waiting if the resource the completion
+ *	is protecting is not available.
+ */
+bool try_wait_for_completion(struct completion *x)
+{
+	unsigned long flags;
+	int ret = 1;
+
+	spin_lock_irqsave(&x->wait.lock, flags);
+	if (!x->done)
+		ret = 0;
+	else
+		x->done--;
+	spin_unlock_irqrestore(&x->wait.lock, flags);
+	return ret;
+}
+EXPORT_SYMBOL(try_wait_for_completion);
+
+/**
+ *	completion_done - Test to see if a completion has any waiters
+ *	@x:	completion structure
+ *
+ *	Return: 0 if there are waiters (wait_for_completion() in progress)
+ *		 1 if there are no waiters.
+ *
+ */
+bool completion_done(struct completion *x)
+{
+	unsigned long flags;
+	int ret = 1;
+
+	spin_lock_irqsave(&x->wait.lock, flags);
+	if (!x->done)
+		ret = 0;
+	spin_unlock_irqrestore(&x->wait.lock, flags);
+	return ret;
+}
+EXPORT_SYMBOL(completion_done);

kernel/sched/cpuacct.c

@@ -0,0 +1,283 @@
+#include <linux/cgroup.h>
+#include <linux/slab.h>
+#include <linux/percpu.h>
+#include <linux/spinlock.h>
+#include <linux/cpumask.h>
+#include <linux/seq_file.h>
+#include <linux/rcupdate.h>
+#include <linux/kernel_stat.h>
+#include <linux/err.h>
+
+#include "sched.h"
+
+/*
+ * CPU accounting code for task groups.
+ *
+ * Based on the work by Paul Menage (menage@google.com) and Balbir Singh
+ * (balbir@in.ibm.com).
+ */
+
+/* Time spent by the tasks of the cpu accounting group executing in ... */
+enum cpuacct_stat_index {
+	CPUACCT_STAT_USER,	/* ... user mode */
+	CPUACCT_STAT_SYSTEM,	/* ... kernel mode */
+
+	CPUACCT_STAT_NSTATS,
+};
+
+/* track cpu usage of a group of tasks and its child groups */
+struct cpuacct {
+	struct cgroup_subsys_state css;
+	/* cpuusage holds pointer to a u64-type object on every cpu */
+	u64 __percpu *cpuusage;
+	struct kernel_cpustat __percpu *cpustat;
+};
+
+static inline struct cpuacct *css_ca(struct cgroup_subsys_state *css)
+{
+	return css ? container_of(css, struct cpuacct, css) : NULL;
+}
+
+/* return cpu accounting group to which this task belongs */
+static inline struct cpuacct *task_ca(struct task_struct *tsk)
+{
+	return css_ca(task_css(tsk, cpuacct_cgrp_id));
+}
+
+static inline struct cpuacct *parent_ca(struct cpuacct *ca)
+{
+	return css_ca(ca->css.parent);
+}
+
+static DEFINE_PER_CPU(u64, root_cpuacct_cpuusage);
+static struct cpuacct root_cpuacct = {
+	.cpustat	= &kernel_cpustat,
+	.cpuusage	= &root_cpuacct_cpuusage,
+};
+
+/* create a new cpu accounting group */
+static struct cgroup_subsys_state *
+cpuacct_css_alloc(struct cgroup_subsys_state *parent_css)
+{
+	struct cpuacct *ca;
+
+	if (!parent_css)
+		return &root_cpuacct.css;
+
+	ca = kzalloc(sizeof(*ca), GFP_KERNEL);
+	if (!ca)
+		goto out;
+
+	ca->cpuusage = alloc_percpu(u64);
+	if (!ca->cpuusage)
+		goto out_free_ca;
+
+	ca->cpustat = alloc_percpu(struct kernel_cpustat);
+	if (!ca->cpustat)
+		goto out_free_cpuusage;
+
+	return &ca->css;
+
+out_free_cpuusage:
+	free_percpu(ca->cpuusage);
+out_free_ca:
+	kfree(ca);
+out:
+	return ERR_PTR(-ENOMEM);
+}
+
+/* destroy an existing cpu accounting group */
+static void cpuacct_css_free(struct cgroup_subsys_state *css)
+{
+	struct cpuacct *ca = css_ca(css);
+
+	free_percpu(ca->cpustat);
+	free_percpu(ca->cpuusage);
+	kfree(ca);
+}
+
+static u64 cpuacct_cpuusage_read(struct cpuacct *ca, int cpu)
+{
+	u64 *cpuusage = per_cpu_ptr(ca->cpuusage, cpu);
+	u64 data;
+
+#ifndef CONFIG_64BIT
+	/*
+	 * Take rq->lock to make 64-bit read safe on 32-bit platforms.
+	 */
+	raw_spin_lock_irq(&cpu_rq(cpu)->lock);
+	data = *cpuusage;
+	raw_spin_unlock_irq(&cpu_rq(cpu)->lock);
+#else
+	data = *cpuusage;
+#endif
+
+	return data;
+}
+
+static void cpuacct_cpuusage_write(struct cpuacct *ca, int cpu, u64 val)
+{
+	u64 *cpuusage = per_cpu_ptr(ca->cpuusage, cpu);
+
+#ifndef CONFIG_64BIT
+	/*
+	 * Take rq->lock to make 64-bit write safe on 32-bit platforms.
+	 */
+	raw_spin_lock_irq(&cpu_rq(cpu)->lock);
+	*cpuusage = val;
+	raw_spin_unlock_irq(&cpu_rq(cpu)->lock);
+#else
+	*cpuusage = val;
+#endif
+}
+
+/* return total cpu usage (in nanoseconds) of a group */
+static u64 cpuusage_read(struct cgroup_subsys_state *css, struct cftype *cft)
+{
+	struct cpuacct *ca = css_ca(css);
+	u64 totalcpuusage = 0;
+	int i;
+
+	for_each_present_cpu(i)
+		totalcpuusage += cpuacct_cpuusage_read(ca, i);
+
+	return totalcpuusage;
+}
+
+static int cpuusage_write(struct cgroup_subsys_state *css, struct cftype *cft,
+			  u64 reset)
+{
+	struct cpuacct *ca = css_ca(css);
+	int err = 0;
+	int i;
+
+	if (reset) {
+		err = -EINVAL;
+		goto out;
+	}
+
+	for_each_present_cpu(i)
+		cpuacct_cpuusage_write(ca, i, 0);
+
+out:
+	return err;
+}
+
+static int cpuacct_percpu_seq_show(struct seq_file *m, void *V)
+{
+	struct cpuacct *ca = css_ca(seq_css(m));
+	u64 percpu;
+	int i;
+
+	for_each_present_cpu(i) {
+		percpu = cpuacct_cpuusage_read(ca, i);
+		seq_printf(m, "%llu ", (unsigned long long) percpu);
+	}
+	seq_printf(m, "\n");
+	return 0;
+}
+
+static const char * const cpuacct_stat_desc[] = {
+	[CPUACCT_STAT_USER] = "user",
+	[CPUACCT_STAT_SYSTEM] = "system",
+};
+
+static int cpuacct_stats_show(struct seq_file *sf, void *v)
+{
+	struct cpuacct *ca = css_ca(seq_css(sf));
+	int cpu;
+	s64 val = 0;
+
+	for_each_online_cpu(cpu) {
+		struct kernel_cpustat *kcpustat = per_cpu_ptr(ca->cpustat, cpu);
+		val += kcpustat->cpustat[CPUTIME_USER];
+		val += kcpustat->cpustat[CPUTIME_NICE];
+	}
+	val = cputime64_to_clock_t(val);
+	seq_printf(sf, "%s %lld\n", cpuacct_stat_desc[CPUACCT_STAT_USER], val);
+
+	val = 0;
+	for_each_online_cpu(cpu) {
+		struct kernel_cpustat *kcpustat = per_cpu_ptr(ca->cpustat, cpu);
+		val += kcpustat->cpustat[CPUTIME_SYSTEM];
+		val += kcpustat->cpustat[CPUTIME_IRQ];
+		val += kcpustat->cpustat[CPUTIME_SOFTIRQ];
+	}
+
+	val = cputime64_to_clock_t(val);
+	seq_printf(sf, "%s %lld\n", cpuacct_stat_desc[CPUACCT_STAT_SYSTEM], val);
+
+	return 0;
+}
+
+static struct cftype files[] = {
+	{
+		.name = "usage",
+		.read_u64 = cpuusage_read,
+		.write_u64 = cpuusage_write,
+	},
+	{
+		.name = "usage_percpu",
+		.seq_show = cpuacct_percpu_seq_show,
+	},
+	{
+		.name = "stat",
+		.seq_show = cpuacct_stats_show,
+	},
+	{ }	/* terminate */
+};
+
+/*
+ * charge this task's execution time to its accounting group.
+ *
+ * called with rq->lock held.
+ */
+void cpuacct_charge(struct task_struct *tsk, u64 cputime)
+{
+	struct cpuacct *ca;
+	int cpu;
+
+	cpu = task_cpu(tsk);
+
+	rcu_read_lock();
+
+	ca = task_ca(tsk);
+
+	while (true) {
+		u64 *cpuusage = per_cpu_ptr(ca->cpuusage, cpu);
+		*cpuusage += cputime;
+
+		ca = parent_ca(ca);
+		if (!ca)
+			break;
+	}
+
+	rcu_read_unlock();
+}
+
+/*
+ * Add user/system time to cpuacct.
+ *
+ * Note: it's the caller that updates the account of the root cgroup.
+ */
+void cpuacct_account_field(struct task_struct *p, int index, u64 val)
+{
+	struct kernel_cpustat *kcpustat;
+	struct cpuacct *ca;
+
+	rcu_read_lock();
+	ca = task_ca(p);
+	while (ca != &root_cpuacct) {
+		kcpustat = this_cpu_ptr(ca->cpustat);
+		kcpustat->cpustat[index] += val;
+		ca = parent_ca(ca);
+	}
+	rcu_read_unlock();
+}
+
+struct cgroup_subsys cpuacct_cgrp_subsys = {
+	.css_alloc	= cpuacct_css_alloc,
+	.css_free	= cpuacct_css_free,
+	.legacy_cftypes	= files,
+	.early_init	= 1,
+};

kernel/sched/cpuacct.h

@@ -0,0 +1,17 @@
+#ifdef CONFIG_CGROUP_CPUACCT
+
+extern void cpuacct_charge(struct task_struct *tsk, u64 cputime);
+extern void cpuacct_account_field(struct task_struct *p, int index, u64 val);
+
+#else
+
+static inline void cpuacct_charge(struct task_struct *tsk, u64 cputime)
+{
+}
+
+static inline void
+cpuacct_account_field(struct task_struct *p, int index, u64 val)
+{
+}
+
+#endif

kernel/sched/cpudeadline.c

@@ -0,0 +1,227 @@
+/*
+ *  kernel/sched/cpudl.c
+ *
+ *  Global CPU deadline management
+ *
+ *  Author: Juri Lelli <j.lelli@sssup.it>
+ *
+ *  This program is free software; you can redistribute it and/or
+ *  modify it under the terms of the GNU General Public License
+ *  as published by the Free Software Foundation; version 2
+ *  of the License.
+ */
+
+#include <linux/gfp.h>
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include "cpudeadline.h"
+
+static inline int parent(int i)
+{
+	return (i - 1) >> 1;
+}
+
+static inline int left_child(int i)
+{
+	return (i << 1) + 1;
+}
+
+static inline int right_child(int i)
+{
+	return (i << 1) + 2;
+}
+
+static inline int dl_time_before(u64 a, u64 b)
+{
+	return (s64)(a - b) < 0;
+}
+
+static void cpudl_exchange(struct cpudl *cp, int a, int b)
+{
+	int cpu_a = cp->elements[a].cpu, cpu_b = cp->elements[b].cpu;
+
+	swap(cp->elements[a].cpu, cp->elements[b].cpu);
+	swap(cp->elements[a].dl , cp->elements[b].dl );
+
+	swap(cp->elements[cpu_a].idx, cp->elements[cpu_b].idx);
+}
+
+static void cpudl_heapify(struct cpudl *cp, int idx)
+{
+	int l, r, largest;
+
+	/* adapted from lib/prio_heap.c */
+	while(1) {
+		l = left_child(idx);
+		r = right_child(idx);
+		largest = idx;
+
+		if ((l < cp->size) && dl_time_before(cp->elements[idx].dl,
+							cp->elements[l].dl))
+			largest = l;
+		if ((r < cp->size) && dl_time_before(cp->elements[largest].dl,
+							cp->elements[r].dl))
+			largest = r;
+		if (largest == idx)
+			break;
+
+		/* Push idx down the heap one level and bump one up */
+		cpudl_exchange(cp, largest, idx);
+		idx = largest;
+	}
+}
+
+static void cpudl_change_key(struct cpudl *cp, int idx, u64 new_dl)
+{
+	WARN_ON(idx == IDX_INVALID || !cpu_present(idx));
+
+	if (dl_time_before(new_dl, cp->elements[idx].dl)) {
+		cp->elements[idx].dl = new_dl;
+		cpudl_heapify(cp, idx);
+	} else {
+		cp->elements[idx].dl = new_dl;
+		while (idx > 0 && dl_time_before(cp->elements[parent(idx)].dl,
+					cp->elements[idx].dl)) {
+			cpudl_exchange(cp, idx, parent(idx));
+			idx = parent(idx);
+		}
+	}
+}
+
+static inline int cpudl_maximum(struct cpudl *cp)
+{
+	return cp->elements[0].cpu;
+}
+
+/*
+ * cpudl_find - find the best (later-dl) CPU in the system
+ * @cp: the cpudl max-heap context
+ * @p: the task
+ * @later_mask: a mask to fill in with the selected CPUs (or NULL)
+ *
+ * Returns: int - best CPU (heap maximum if suitable)
+ */
+int cpudl_find(struct cpudl *cp, struct task_struct *p,
+	       struct cpumask *later_mask)
+{
+	int best_cpu = -1;
+	const struct sched_dl_entity *dl_se = &p->dl;
+
+	if (later_mask && cpumask_and(later_mask, later_mask, cp->free_cpus)) {
+		best_cpu = cpumask_any(later_mask);
+		goto out;
+	} else if (cpumask_test_cpu(cpudl_maximum(cp), &p->cpus_allowed) &&
+			dl_time_before(dl_se->deadline, cp->elements[0].dl)) {
+		best_cpu = cpudl_maximum(cp);
+		if (later_mask)
+			cpumask_set_cpu(best_cpu, later_mask);
+	}
+
+out:
+	WARN_ON(best_cpu != -1 && !cpu_present(best_cpu));
+
+	return best_cpu;
+}
+
+/*
+ * cpudl_set - update the cpudl max-heap
+ * @cp: the cpudl max-heap context
+ * @cpu: the target cpu
+ * @dl: the new earliest deadline for this cpu
+ *
+ * Notes: assumes cpu_rq(cpu)->lock is locked
+ *
+ * Returns: (void)
+ */
+void cpudl_set(struct cpudl *cp, int cpu, u64 dl, int is_valid)
+{
+	int old_idx, new_cpu;
+	unsigned long flags;
+
+	WARN_ON(!cpu_present(cpu));
+
+	raw_spin_lock_irqsave(&cp->lock, flags);
+	old_idx = cp->elements[cpu].idx;
+	if (!is_valid) {
+		/* remove item */
+		if (old_idx == IDX_INVALID) {
+			/*
+			 * Nothing to remove if old_idx was invalid.
+			 * This could happen if a rq_offline_dl is
+			 * called for a CPU without -dl tasks running.
+			 */
+			goto out;
+		}
+		new_cpu = cp->elements[cp->size - 1].cpu;
+		cp->elements[old_idx].dl = cp->elements[cp->size - 1].dl;
+		cp->elements[old_idx].cpu = new_cpu;
+		cp->size--;
+		cp->elements[new_cpu].idx = old_idx;
+		cp->elements[cpu].idx = IDX_INVALID;
+		while (old_idx > 0 && dl_time_before(
+				cp->elements[parent(old_idx)].dl,
+				cp->elements[old_idx].dl)) {
+			cpudl_exchange(cp, old_idx, parent(old_idx));
+			old_idx = parent(old_idx);
+		}
+		cpumask_set_cpu(cpu, cp->free_cpus);
+                cpudl_heapify(cp, old_idx);
+
+		goto out;
+	}
+
+	if (old_idx == IDX_INVALID) {
+		cp->size++;
+		cp->elements[cp->size - 1].dl = 0;
+		cp->elements[cp->size - 1].cpu = cpu;
+		cp->elements[cpu].idx = cp->size - 1;
+		cpudl_change_key(cp, cp->size - 1, dl);
+		cpumask_clear_cpu(cpu, cp->free_cpus);
+	} else {
+		cpudl_change_key(cp, old_idx, dl);
+	}
+
+out:
+	raw_spin_unlock_irqrestore(&cp->lock, flags);
+}
+
+/*
+ * cpudl_init - initialize the cpudl structure
+ * @cp: the cpudl max-heap context
+ */
+int cpudl_init(struct cpudl *cp)
+{
+	int i;
+
+	memset(cp, 0, sizeof(*cp));
+	raw_spin_lock_init(&cp->lock);
+	cp->size = 0;
+
+	cp->elements = kcalloc(nr_cpu_ids,
+			       sizeof(struct cpudl_item),
+			       GFP_KERNEL);
+	if (!cp->elements)
+		return -ENOMEM;
+
+	if (!alloc_cpumask_var(&cp->free_cpus, GFP_KERNEL)) {
+		kfree(cp->elements);
+		return -ENOMEM;
+	}
+
+	for_each_possible_cpu(i)
+		cp->elements[i].idx = IDX_INVALID;
+
+	cpumask_setall(cp->free_cpus);
+
+	return 0;
+}
+
+/*
+ * cpudl_cleanup - clean up the cpudl structure
+ * @cp: the cpudl max-heap context
+ */
+void cpudl_cleanup(struct cpudl *cp)
+{
+	free_cpumask_var(cp->free_cpus);
+	kfree(cp->elements);
+}

kernel/sched/cpudeadline.h

@@ -0,0 +1,33 @@
+#ifndef _LINUX_CPUDL_H
+#define _LINUX_CPUDL_H
+
+#include <linux/sched.h>
+
+#define IDX_INVALID     -1
+
+struct cpudl_item {
+	u64 dl;
+	int cpu;
+	int idx;
+};
+
+struct cpudl {
+	raw_spinlock_t lock;
+	int size;
+	cpumask_var_t free_cpus;
+	struct cpudl_item *elements;
+};
+
+
+#ifdef CONFIG_SMP
+int cpudl_find(struct cpudl *cp, struct task_struct *p,
+	       struct cpumask *later_mask);
+void cpudl_set(struct cpudl *cp, int cpu, u64 dl, int is_valid);
+int cpudl_init(struct cpudl *cp);
+void cpudl_cleanup(struct cpudl *cp);
+#else
+#define cpudl_set(cp, cpu, dl) do { } while (0)
+#define cpudl_init() do { } while (0)
+#endif /* CONFIG_SMP */
+
+#endif /* _LINUX_CPUDL_H */

kernel/sched/cpupri.c

@@ -0,0 +1,248 @@
+/*
+ *  kernel/sched/cpupri.c
+ *
+ *  CPU priority management
+ *
+ *  Copyright (C) 2007-2008 Novell
+ *
+ *  Author: Gregory Haskins <ghaskins@novell.com>
+ *
+ *  This code tracks the priority of each CPU so that global migration
+ *  decisions are easy to calculate.  Each CPU can be in a state as follows:
+ *
+ *                 (INVALID), IDLE, NORMAL, RT1, ... RT99
+ *
+ *  going from the lowest priority to the highest.  CPUs in the INVALID state
+ *  are not eligible for routing.  The system maintains this state with
+ *  a 2 dimensional bitmap (the first for priority class, the second for cpus
+ *  in that class).  Therefore a typical application without affinity
+ *  restrictions can find a suitable CPU with O(1) complexity (e.g. two bit
+ *  searches).  For tasks with affinity restrictions, the algorithm has a
+ *  worst case complexity of O(min(102, nr_domcpus)), though the scenario that
+ *  yields the worst case search is fairly contrived.
+ *
+ *  This program is free software; you can redistribute it and/or
+ *  modify it under the terms of the GNU General Public License
+ *  as published by the Free Software Foundation; version 2
+ *  of the License.
+ */
+
+#include <linux/gfp.h>
+#include <linux/sched.h>
+#include <linux/sched/rt.h>
+#include <linux/slab.h>
+#include "cpupri.h"
+
+/* Convert between a 140 based task->prio, and our 102 based cpupri */
+static int convert_prio(int prio)
+{
+	int cpupri;
+
+	if (prio == CPUPRI_INVALID)
+		cpupri = CPUPRI_INVALID;
+	else if (prio == MAX_PRIO)
+		cpupri = CPUPRI_IDLE;
+	else if (prio >= MAX_RT_PRIO)
+		cpupri = CPUPRI_NORMAL;
+	else
+		cpupri = MAX_RT_PRIO - prio + 1;
+
+	return cpupri;
+}
+
+/**
+ * cpupri_find - find the best (lowest-pri) CPU in the system
+ * @cp: The cpupri context
+ * @p: The task
+ * @lowest_mask: A mask to fill in with selected CPUs (or NULL)
+ *
+ * Note: This function returns the recommended CPUs as calculated during the
+ * current invocation.  By the time the call returns, the CPUs may have in
+ * fact changed priorities any number of times.  While not ideal, it is not
+ * an issue of correctness since the normal rebalancer logic will correct
+ * any discrepancies created by racing against the uncertainty of the current
+ * priority configuration.
+ *
+ * Return: (int)bool - CPUs were found
+ */
+int cpupri_find(struct cpupri *cp, struct task_struct *p,
+		struct cpumask *lowest_mask)
+{
+	int idx = 0;
+	int task_pri = convert_prio(p->prio);
+
+	BUG_ON(task_pri >= CPUPRI_NR_PRIORITIES);
+
+	for (idx = 0; idx < task_pri; idx++) {
+		struct cpupri_vec *vec  = &cp->pri_to_cpu[idx];
+		int skip = 0;
+
+		if (!atomic_read(&(vec)->count))
+			skip = 1;
+		/*
+		 * When looking at the vector, we need to read the counter,
+		 * do a memory barrier, then read the mask.
+		 *
+		 * Note: This is still all racey, but we can deal with it.
+		 *  Ideally, we only want to look at masks that are set.
+		 *
+		 *  If a mask is not set, then the only thing wrong is that we
+		 *  did a little more work than necessary.
+		 *
+		 *  If we read a zero count but the mask is set, because of the
+		 *  memory barriers, that can only happen when the highest prio
+		 *  task for a run queue has left the run queue, in which case,
+		 *  it will be followed by a pull. If the task we are processing
+		 *  fails to find a proper place to go, that pull request will
+		 *  pull this task if the run queue is running at a lower
+		 *  priority.
+		 */
+		smp_rmb();
+
+		/* Need to do the rmb for every iteration */
+		if (skip)
+			continue;
+
+		if (cpumask_any_and(&p->cpus_allowed, vec->mask) >= nr_cpu_ids)
+			continue;
+
+		if (lowest_mask) {
+			cpumask_and(lowest_mask, &p->cpus_allowed, vec->mask);
+
+			/*
+			 * We have to ensure that we have at least one bit
+			 * still set in the array, since the map could have
+			 * been concurrently emptied between the first and
+			 * second reads of vec->mask.  If we hit this
+			 * condition, simply act as though we never hit this
+			 * priority level and continue on.
+			 */
+			if (cpumask_any(lowest_mask) >= nr_cpu_ids)
+				continue;
+		}
+
+		return 1;
+	}
+
+	return 0;
+}
+
+/**
+ * cpupri_set - update the cpu priority setting
+ * @cp: The cpupri context
+ * @cpu: The target cpu
+ * @newpri: The priority (INVALID-RT99) to assign to this CPU
+ *
+ * Note: Assumes cpu_rq(cpu)->lock is locked
+ *
+ * Returns: (void)
+ */
+void cpupri_set(struct cpupri *cp, int cpu, int newpri)
+{
+	int *currpri = &cp->cpu_to_pri[cpu];
+	int oldpri = *currpri;
+	int do_mb = 0;
+
+	newpri = convert_prio(newpri);
+
+	BUG_ON(newpri >= CPUPRI_NR_PRIORITIES);
+
+	if (newpri == oldpri)
+		return;
+
+	/*
+	 * If the cpu was currently mapped to a different value, we
+	 * need to map it to the new value then remove the old value.
+	 * Note, we must add the new value first, otherwise we risk the
+	 * cpu being missed by the priority loop in cpupri_find.
+	 */
+	if (likely(newpri != CPUPRI_INVALID)) {
+		struct cpupri_vec *vec = &cp->pri_to_cpu[newpri];
+
+		cpumask_set_cpu(cpu, vec->mask);
+		/*
+		 * When adding a new vector, we update the mask first,
+		 * do a write memory barrier, and then update the count, to
+		 * make sure the vector is visible when count is set.
+		 */
+		smp_mb__before_atomic();
+		atomic_inc(&(vec)->count);
+		do_mb = 1;
+	}
+	if (likely(oldpri != CPUPRI_INVALID)) {
+		struct cpupri_vec *vec  = &cp->pri_to_cpu[oldpri];
+
+		/*
+		 * Because the order of modification of the vec->count
+		 * is important, we must make sure that the update
+		 * of the new prio is seen before we decrement the
+		 * old prio. This makes sure that the loop sees
+		 * one or the other when we raise the priority of
+		 * the run queue. We don't care about when we lower the
+		 * priority, as that will trigger an rt pull anyway.
+		 *
+		 * We only need to do a memory barrier if we updated
+		 * the new priority vec.
+		 */
+		if (do_mb)
+			smp_mb__after_atomic();
+
+		/*
+		 * When removing from the vector, we decrement the counter first
+		 * do a memory barrier and then clear the mask.
+		 */
+		atomic_dec(&(vec)->count);
+		smp_mb__after_atomic();
+		cpumask_clear_cpu(cpu, vec->mask);
+	}
+
+	*currpri = newpri;
+}
+
+/**
+ * cpupri_init - initialize the cpupri structure
+ * @cp: The cpupri context
+ *
+ * Return: -ENOMEM on memory allocation failure.
+ */
+int cpupri_init(struct cpupri *cp)
+{
+	int i;
+
+	memset(cp, 0, sizeof(*cp));
+
+	for (i = 0; i < CPUPRI_NR_PRIORITIES; i++) {
+		struct cpupri_vec *vec = &cp->pri_to_cpu[i];
+
+		atomic_set(&vec->count, 0);
+		if (!zalloc_cpumask_var(&vec->mask, GFP_KERNEL))
+			goto cleanup;
+	}
+
+	cp->cpu_to_pri = kcalloc(nr_cpu_ids, sizeof(int), GFP_KERNEL);
+	if (!cp->cpu_to_pri)
+		goto cleanup;
+
+	for_each_possible_cpu(i)
+		cp->cpu_to_pri[i] = CPUPRI_INVALID;
+
+	return 0;
+
+cleanup:
+	for (i--; i >= 0; i--)
+		free_cpumask_var(cp->pri_to_cpu[i].mask);
+	return -ENOMEM;
+}
+
+/**
+ * cpupri_cleanup - clean up the cpupri structure
+ * @cp: The cpupri context
+ */
+void cpupri_cleanup(struct cpupri *cp)
+{
+	int i;
+
+	kfree(cp->cpu_to_pri);
+	for (i = 0; i < CPUPRI_NR_PRIORITIES; i++)
+		free_cpumask_var(cp->pri_to_cpu[i].mask);
+}

kernel/sched/cpupri.h

@@ -0,0 +1,34 @@
+#ifndef _LINUX_CPUPRI_H
+#define _LINUX_CPUPRI_H
+
+#include <linux/sched.h>
+
+#define CPUPRI_NR_PRIORITIES	(MAX_RT_PRIO + 2)
+
+#define CPUPRI_INVALID -1
+#define CPUPRI_IDLE     0
+#define CPUPRI_NORMAL   1
+/* values 2-101 are RT priorities 0-99 */
+
+struct cpupri_vec {
+	atomic_t	count;
+	cpumask_var_t	mask;
+};
+
+struct cpupri {
+	struct cpupri_vec pri_to_cpu[CPUPRI_NR_PRIORITIES];
+	int *cpu_to_pri;
+};
+
+#ifdef CONFIG_SMP
+int  cpupri_find(struct cpupri *cp,
+		 struct task_struct *p, struct cpumask *lowest_mask);
+void cpupri_set(struct cpupri *cp, int cpu, int pri);
+int cpupri_init(struct cpupri *cp);
+void cpupri_cleanup(struct cpupri *cp);
+#else
+#define cpupri_set(cp, cpu, pri) do { } while (0)
+#define cpupri_init() do { } while (0)
+#endif
+
+#endif /* _LINUX_CPUPRI_H */

kernel/sched/cputime.c

@@ -0,0 +1,852 @@
+#include <linux/export.h>
+#include <linux/sched.h>
+#include <linux/tsacct_kern.h>
+#include <linux/kernel_stat.h>
+#include <linux/static_key.h>
+#include <linux/context_tracking.h>
+#include "sched.h"
+
+
+#ifdef CONFIG_IRQ_TIME_ACCOUNTING
+
+/*
+ * There are no locks covering percpu hardirq/softirq time.
+ * They are only modified in vtime_account, on corresponding CPU
+ * with interrupts disabled. So, writes are safe.
+ * They are read and saved off onto struct rq in update_rq_clock().
+ * This may result in other CPU reading this CPU's irq time and can
+ * race with irq/vtime_account on this CPU. We would either get old
+ * or new value with a side effect of accounting a slice of irq time to wrong
+ * task when irq is in progress while we read rq->clock. That is a worthy
+ * compromise in place of having locks on each irq in account_system_time.
+ */
+DEFINE_PER_CPU(u64, cpu_hardirq_time);
+DEFINE_PER_CPU(u64, cpu_softirq_time);
+
+static DEFINE_PER_CPU(u64, irq_start_time);
+static int sched_clock_irqtime;
+
+void enable_sched_clock_irqtime(void)
+{
+	sched_clock_irqtime = 1;
+}
+
+void disable_sched_clock_irqtime(void)
+{
+	sched_clock_irqtime = 0;
+}
+
+#ifndef CONFIG_64BIT
+DEFINE_PER_CPU(seqcount_t, irq_time_seq);
+#endif /* CONFIG_64BIT */
+
+/*
+ * Called before incrementing preempt_count on {soft,}irq_enter
+ * and before decrementing preempt_count on {soft,}irq_exit.
+ */
+void irqtime_account_irq(struct task_struct *curr)
+{
+	unsigned long flags;
+	s64 delta;
+	int cpu;
+
+	if (!sched_clock_irqtime)
+		return;
+
+	local_irq_save(flags);
+
+	cpu = smp_processor_id();
+	delta = sched_clock_cpu(cpu) - __this_cpu_read(irq_start_time);
+	__this_cpu_add(irq_start_time, delta);
+
+	irq_time_write_begin();
+	/*
+	 * We do not account for softirq time from ksoftirqd here.
+	 * We want to continue accounting softirq time to ksoftirqd thread
+	 * in that case, so as not to confuse scheduler with a special task
+	 * that do not consume any time, but still wants to run.
+	 */
+	if (hardirq_count())
+		__this_cpu_add(cpu_hardirq_time, delta);
+	else if (in_serving_softirq() && curr != this_cpu_ksoftirqd())
+		__this_cpu_add(cpu_softirq_time, delta);
+
+	irq_time_write_end();
+	local_irq_restore(flags);
+}
+EXPORT_SYMBOL_GPL(irqtime_account_irq);
+
+static int irqtime_account_hi_update(void)
+{
+	u64 *cpustat = kcpustat_this_cpu->cpustat;
+	unsigned long flags;
+	u64 latest_ns;
+	int ret = 0;
+
+	local_irq_save(flags);
+	latest_ns = this_cpu_read(cpu_hardirq_time);
+	if (nsecs_to_cputime64(latest_ns) > cpustat[CPUTIME_IRQ])
+		ret = 1;
+	local_irq_restore(flags);
+	return ret;
+}
+
+static int irqtime_account_si_update(void)
+{
+	u64 *cpustat = kcpustat_this_cpu->cpustat;
+	unsigned long flags;
+	u64 latest_ns;
+	int ret = 0;
+
+	local_irq_save(flags);
+	latest_ns = this_cpu_read(cpu_softirq_time);
+	if (nsecs_to_cputime64(latest_ns) > cpustat[CPUTIME_SOFTIRQ])
+		ret = 1;
+	local_irq_restore(flags);
+	return ret;
+}
+
+#else /* CONFIG_IRQ_TIME_ACCOUNTING */
+
+#define sched_clock_irqtime	(0)
+
+#endif /* !CONFIG_IRQ_TIME_ACCOUNTING */
+
+static inline void task_group_account_field(struct task_struct *p, int index,
+					    u64 tmp)
+{
+	/*
+	 * Since all updates are sure to touch the root cgroup, we
+	 * get ourselves ahead and touch it first. If the root cgroup
+	 * is the only cgroup, then nothing else should be necessary.
+	 *
+	 */
+	__this_cpu_add(kernel_cpustat.cpustat[index], tmp);
+
+	cpuacct_account_field(p, index, tmp);
+}
+
+/*
+ * Account user cpu time to a process.
+ * @p: the process that the cpu time gets accounted to
+ * @cputime: the cpu time spent in user space since the last update
+ * @cputime_scaled: cputime scaled by cpu frequency
+ */
+void account_user_time(struct task_struct *p, cputime_t cputime,
+		       cputime_t cputime_scaled)
+{
+	int index;
+
+	/* Add user time to process. */
+	p->utime += cputime;
+	p->utimescaled += cputime_scaled;
+	account_group_user_time(p, cputime);
+
+	index = (task_nice(p) > 0) ? CPUTIME_NICE : CPUTIME_USER;
+
+	/* Add user time to cpustat. */
+	task_group_account_field(p, index, (__force u64) cputime);
+
+	/* Account for user time used */
+	acct_account_cputime(p);
+}
+
+/*
+ * Account guest cpu time to a process.
+ * @p: the process that the cpu time gets accounted to
+ * @cputime: the cpu time spent in virtual machine since the last update
+ * @cputime_scaled: cputime scaled by cpu frequency
+ */
+static void account_guest_time(struct task_struct *p, cputime_t cputime,
+			       cputime_t cputime_scaled)
+{
+	u64 *cpustat = kcpustat_this_cpu->cpustat;
+
+	/* Add guest time to process. */
+	p->utime += cputime;
+	p->utimescaled += cputime_scaled;
+	account_group_user_time(p, cputime);
+	p->gtime += cputime;
+
+	/* Add guest time to cpustat. */
+	if (task_nice(p) > 0) {
+		cpustat[CPUTIME_NICE] += (__force u64) cputime;
+		cpustat[CPUTIME_GUEST_NICE] += (__force u64) cputime;
+	} else {
+		cpustat[CPUTIME_USER] += (__force u64) cputime;
+		cpustat[CPUTIME_GUEST] += (__force u64) cputime;
+	}
+}
+
+/*
+ * Account system cpu time to a process and desired cpustat field
+ * @p: the process that the cpu time gets accounted to
+ * @cputime: the cpu time spent in kernel space since the last update
+ * @cputime_scaled: cputime scaled by cpu frequency
+ * @target_cputime64: pointer to cpustat field that has to be updated
+ */
+static inline
+void __account_system_time(struct task_struct *p, cputime_t cputime,
+			cputime_t cputime_scaled, int index)
+{
+	/* Add system time to process. */
+	p->stime += cputime;
+	p->stimescaled += cputime_scaled;
+	account_group_system_time(p, cputime);
+
+	/* Add system time to cpustat. */
+	task_group_account_field(p, index, (__force u64) cputime);
+
+	/* Account for system time used */
+	acct_account_cputime(p);
+}
+
+/*
+ * Account system cpu time to a process.
+ * @p: the process that the cpu time gets accounted to
+ * @hardirq_offset: the offset to subtract from hardirq_count()
+ * @cputime: the cpu time spent in kernel space since the last update
+ * @cputime_scaled: cputime scaled by cpu frequency
+ */
+void account_system_time(struct task_struct *p, int hardirq_offset,
+			 cputime_t cputime, cputime_t cputime_scaled)
+{
+	int index;
+
+	if ((p->flags & PF_VCPU) && (irq_count() - hardirq_offset == 0)) {
+		account_guest_time(p, cputime, cputime_scaled);
+		return;
+	}
+
+	if (hardirq_count() - hardirq_offset)
+		index = CPUTIME_IRQ;
+	else if (in_serving_softirq())
+		index = CPUTIME_SOFTIRQ;
+	else
+		index = CPUTIME_SYSTEM;
+
+	__account_system_time(p, cputime, cputime_scaled, index);
+}
+
+/*
+ * Account for involuntary wait time.
+ * @cputime: the cpu time spent in involuntary wait
+ */
+void account_steal_time(cputime_t cputime)
+{
+	u64 *cpustat = kcpustat_this_cpu->cpustat;
+
+	cpustat[CPUTIME_STEAL] += (__force u64) cputime;
+}
+
+/*
+ * Account for idle time.
+ * @cputime: the cpu time spent in idle wait
+ */
+void account_idle_time(cputime_t cputime)
+{
+	u64 *cpustat = kcpustat_this_cpu->cpustat;
+	struct rq *rq = this_rq();
+
+	if (atomic_read(&rq->nr_iowait) > 0)
+		cpustat[CPUTIME_IOWAIT] += (__force u64) cputime;
+	else
+		cpustat[CPUTIME_IDLE] += (__force u64) cputime;
+}
+
+static __always_inline bool steal_account_process_tick(void)
+{
+#ifdef CONFIG_PARAVIRT
+	if (static_key_false(&paravirt_steal_enabled)) {
+		u64 steal;
+		cputime_t steal_ct;
+
+		steal = paravirt_steal_clock(smp_processor_id());
+		steal -= this_rq()->prev_steal_time;
+
+		/*
+		 * cputime_t may be less precise than nsecs (eg: if it's
+		 * based on jiffies). Lets cast the result to cputime
+		 * granularity and account the rest on the next rounds.
+		 */
+		steal_ct = nsecs_to_cputime(steal);
+		this_rq()->prev_steal_time += cputime_to_nsecs(steal_ct);
+
+		account_steal_time(steal_ct);
+		return steal_ct;
+	}
+#endif
+	return false;
+}
+
+/*
+ * Accumulate raw cputime values of dead tasks (sig->[us]time) and live
+ * tasks (sum on group iteration) belonging to @tsk's group.
+ */
+void thread_group_cputime(struct task_struct *tsk, struct task_cputime *times)
+{
+	struct signal_struct *sig = tsk->signal;
+	cputime_t utime, stime;
+	struct task_struct *t;
+	unsigned int seq, nextseq;
+	unsigned long flags;
+
+	rcu_read_lock();
+	/* Attempt a lockless read on the first round. */
+	nextseq = 0;
+	do {
+		seq = nextseq;
+		flags = read_seqbegin_or_lock_irqsave(&sig->stats_lock, &seq);
+		times->utime = sig->utime;
+		times->stime = sig->stime;
+		times->sum_exec_runtime = sig->sum_sched_runtime;
+
+		for_each_thread(tsk, t) {
+			task_cputime(t, &utime, &stime);
+			times->utime += utime;
+			times->stime += stime;
+			times->sum_exec_runtime += task_sched_runtime(t);
+		}
+		/* If lockless access failed, take the lock. */
+		nextseq = 1;
+	} while (need_seqretry(&sig->stats_lock, seq));
+	done_seqretry_irqrestore(&sig->stats_lock, seq, flags);
+	rcu_read_unlock();
+}
+
+#ifdef CONFIG_IRQ_TIME_ACCOUNTING
+/*
+ * Account a tick to a process and cpustat
+ * @p: the process that the cpu time gets accounted to
+ * @user_tick: is the tick from userspace
+ * @rq: the pointer to rq
+ *
+ * Tick demultiplexing follows the order
+ * - pending hardirq update
+ * - pending softirq update
+ * - user_time
+ * - idle_time
+ * - system time
+ *   - check for guest_time
+ *   - else account as system_time
+ *
+ * Check for hardirq is done both for system and user time as there is
+ * no timer going off while we are on hardirq and hence we may never get an
+ * opportunity to update it solely in system time.
+ * p->stime and friends are only updated on system time and not on irq
+ * softirq as those do not count in task exec_runtime any more.
+ */
+static void irqtime_account_process_tick(struct task_struct *p, int user_tick,
+					 struct rq *rq, int ticks)
+{
+	cputime_t scaled = cputime_to_scaled(cputime_one_jiffy);
+	u64 cputime = (__force u64) cputime_one_jiffy;
+	u64 *cpustat = kcpustat_this_cpu->cpustat;
+
+	if (steal_account_process_tick())
+		return;
+
+	cputime *= ticks;
+	scaled *= ticks;
+
+	if (irqtime_account_hi_update()) {
+		cpustat[CPUTIME_IRQ] += cputime;
+	} else if (irqtime_account_si_update()) {
+		cpustat[CPUTIME_SOFTIRQ] += cputime;
+	} else if (this_cpu_ksoftirqd() == p) {
+		/*
+		 * ksoftirqd time do not get accounted in cpu_softirq_time.
+		 * So, we have to handle it separately here.
+		 * Also, p->stime needs to be updated for ksoftirqd.
+		 */
+		__account_system_time(p, cputime, scaled, CPUTIME_SOFTIRQ);
+	} else if (user_tick) {
+		account_user_time(p, cputime, scaled);
+	} else if (p == rq->idle) {
+		account_idle_time(cputime);
+	} else if (p->flags & PF_VCPU) { /* System time or guest time */
+		account_guest_time(p, cputime, scaled);
+	} else {
+		__account_system_time(p, cputime, scaled,	CPUTIME_SYSTEM);
+	}
+}
+
+static void irqtime_account_idle_ticks(int ticks)
+{
+	struct rq *rq = this_rq();
+
+	irqtime_account_process_tick(current, 0, rq, ticks);
+}
+#else /* CONFIG_IRQ_TIME_ACCOUNTING */
+static inline void irqtime_account_idle_ticks(int ticks) {}
+static inline void irqtime_account_process_tick(struct task_struct *p, int user_tick,
+						struct rq *rq, int nr_ticks) {}
+#endif /* CONFIG_IRQ_TIME_ACCOUNTING */
+
+/*
+ * Use precise platform statistics if available:
+ */
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING
+
+#ifndef __ARCH_HAS_VTIME_TASK_SWITCH
+void vtime_common_task_switch(struct task_struct *prev)
+{
+	if (is_idle_task(prev))
+		vtime_account_idle(prev);
+	else
+		vtime_account_system(prev);
+
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
+	vtime_account_user(prev);
+#endif
+	arch_vtime_task_switch(prev);
+}
+#endif
+
+/*
+ * Archs that account the whole time spent in the idle task
+ * (outside irq) as idle time can rely on this and just implement
+ * vtime_account_system() and vtime_account_idle(). Archs that
+ * have other meaning of the idle time (s390 only includes the
+ * time spent by the CPU when it's in low power mode) must override
+ * vtime_account().
+ */
+#ifndef __ARCH_HAS_VTIME_ACCOUNT
+void vtime_common_account_irq_enter(struct task_struct *tsk)
+{
+	if (!in_interrupt()) {
+		/*
+		 * If we interrupted user, context_tracking_in_user()
+		 * is 1 because the context tracking don't hook
+		 * on irq entry/exit. This way we know if
+		 * we need to flush user time on kernel entry.
+		 */
+		if (context_tracking_in_user()) {
+			vtime_account_user(tsk);
+			return;
+		}
+
+		if (is_idle_task(tsk)) {
+			vtime_account_idle(tsk);
+			return;
+		}
+	}
+	vtime_account_system(tsk);
+}
+EXPORT_SYMBOL_GPL(vtime_common_account_irq_enter);
+#endif /* __ARCH_HAS_VTIME_ACCOUNT */
+#endif /* CONFIG_VIRT_CPU_ACCOUNTING */
+
+
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
+void task_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st)
+{
+	*ut = p->utime;
+	*st = p->stime;
+}
+
+void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st)
+{
+	struct task_cputime cputime;
+
+	thread_group_cputime(p, &cputime);
+
+	*ut = cputime.utime;
+	*st = cputime.stime;
+}
+#else /* !CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */
+/*
+ * Account a single tick of cpu time.
+ * @p: the process that the cpu time gets accounted to
+ * @user_tick: indicates if the tick is a user or a system tick
+ */
+void account_process_tick(struct task_struct *p, int user_tick)
+{
+	cputime_t one_jiffy_scaled = cputime_to_scaled(cputime_one_jiffy);
+	struct rq *rq = this_rq();
+
+	if (vtime_accounting_enabled())
+		return;
+
+	if (sched_clock_irqtime) {
+		irqtime_account_process_tick(p, user_tick, rq, 1);
+		return;
+	}
+
+	if (steal_account_process_tick())
+		return;
+
+	if (user_tick)
+		account_user_time(p, cputime_one_jiffy, one_jiffy_scaled);
+	else if ((p != rq->idle) || (irq_count() != HARDIRQ_OFFSET))
+		account_system_time(p, HARDIRQ_OFFSET, cputime_one_jiffy,
+				    one_jiffy_scaled);
+	else
+		account_idle_time(cputime_one_jiffy);
+}
+
+/*
+ * Account multiple ticks of steal time.
+ * @p: the process from which the cpu time has been stolen
+ * @ticks: number of stolen ticks
+ */
+void account_steal_ticks(unsigned long ticks)
+{
+	account_steal_time(jiffies_to_cputime(ticks));
+}
+
+/*
+ * Account multiple ticks of idle time.
+ * @ticks: number of stolen ticks
+ */
+void account_idle_ticks(unsigned long ticks)
+{
+
+	if (sched_clock_irqtime) {
+		irqtime_account_idle_ticks(ticks);
+		return;
+	}
+
+	account_idle_time(jiffies_to_cputime(ticks));
+}
+
+/*
+ * Perform (stime * rtime) / total, but avoid multiplication overflow by
+ * loosing precision when the numbers are big.
+ */
+static cputime_t scale_stime(u64 stime, u64 rtime, u64 total)
+{
+	u64 scaled;
+
+	for (;;) {
+		/* Make sure "rtime" is the bigger of stime/rtime */
+		if (stime > rtime)
+			swap(rtime, stime);
+
+		/* Make sure 'total' fits in 32 bits */
+		if (total >> 32)
+			goto drop_precision;
+
+		/* Does rtime (and thus stime) fit in 32 bits? */
+		if (!(rtime >> 32))
+			break;
+
+		/* Can we just balance rtime/stime rather than dropping bits? */
+		if (stime >> 31)
+			goto drop_precision;
+
+		/* We can grow stime and shrink rtime and try to make them both fit */
+		stime <<= 1;
+		rtime >>= 1;
+		continue;
+
+drop_precision:
+		/* We drop from rtime, it has more bits than stime */
+		rtime >>= 1;
+		total >>= 1;
+	}
+
+	/*
+	 * Make sure gcc understands that this is a 32x32->64 multiply,
+	 * followed by a 64/32->64 divide.
+	 */
+	scaled = div_u64((u64) (u32) stime * (u64) (u32) rtime, (u32)total);
+	return (__force cputime_t) scaled;
+}
+
+/*
+ * Atomically advance counter to the new value. Interrupts, vcpu
+ * scheduling, and scaling inaccuracies can cause cputime_advance
+ * to be occasionally called with a new value smaller than counter.
+ * Let's enforce atomicity.
+ *
+ * Normally a caller will only go through this loop once, or not
+ * at all in case a previous caller updated counter the same jiffy.
+ */
+static void cputime_advance(cputime_t *counter, cputime_t new)
+{
+	cputime_t old;
+
+	while (new > (old = ACCESS_ONCE(*counter)))
+		cmpxchg_cputime(counter, old, new);
+}
+
+/*
+ * Adjust tick based cputime random precision against scheduler
+ * runtime accounting.
+ */
+static void cputime_adjust(struct task_cputime *curr,
+			   struct cputime *prev,
+			   cputime_t *ut, cputime_t *st)
+{
+	cputime_t rtime, stime, utime;
+
+	/*
+	 * Tick based cputime accounting depend on random scheduling
+	 * timeslices of a task to be interrupted or not by the timer.
+	 * Depending on these circumstances, the number of these interrupts
+	 * may be over or under-optimistic, matching the real user and system
+	 * cputime with a variable precision.
+	 *
+	 * Fix this by scaling these tick based values against the total
+	 * runtime accounted by the CFS scheduler.
+	 */
+	rtime = nsecs_to_cputime(curr->sum_exec_runtime);
+
+	/*
+	 * Update userspace visible utime/stime values only if actual execution
+	 * time is bigger than already exported. Note that can happen, that we
+	 * provided bigger values due to scaling inaccuracy on big numbers.
+	 */
+	if (prev->stime + prev->utime >= rtime)
+		goto out;
+
+	stime = curr->stime;
+	utime = curr->utime;
+
+	if (utime == 0) {
+		stime = rtime;
+	} else if (stime == 0) {
+		utime = rtime;
+	} else {
+		cputime_t total = stime + utime;
+
+		stime = scale_stime((__force u64)stime,
+				    (__force u64)rtime, (__force u64)total);
+		utime = rtime - stime;
+	}
+
+	cputime_advance(&prev->stime, stime);
+	cputime_advance(&prev->utime, utime);
+
+out:
+	*ut = prev->utime;
+	*st = prev->stime;
+}
+
+void task_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st)
+{
+	struct task_cputime cputime = {
+		.sum_exec_runtime = p->se.sum_exec_runtime,
+	};
+
+	task_cputime(p, &cputime.utime, &cputime.stime);
+	cputime_adjust(&cputime, &p->prev_cputime, ut, st);
+}
+
+void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st)
+{
+	struct task_cputime cputime;
+
+	thread_group_cputime(p, &cputime);
+	cputime_adjust(&cputime, &p->signal->prev_cputime, ut, st);
+}
+#endif /* !CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */
+
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
+static unsigned long long vtime_delta(struct task_struct *tsk)
+{
+	unsigned long long clock;
+
+	clock = local_clock();
+	if (clock < tsk->vtime_snap)
+		return 0;
+
+	return clock - tsk->vtime_snap;
+}
+
+static cputime_t get_vtime_delta(struct task_struct *tsk)
+{
+	unsigned long long delta = vtime_delta(tsk);
+
+	WARN_ON_ONCE(tsk->vtime_snap_whence == VTIME_SLEEPING);
+	tsk->vtime_snap += delta;
+
+	/* CHECKME: always safe to convert nsecs to cputime? */
+	return nsecs_to_cputime(delta);
+}
+
+static void __vtime_account_system(struct task_struct *tsk)
+{
+	cputime_t delta_cpu = get_vtime_delta(tsk);
+
+	account_system_time(tsk, irq_count(), delta_cpu, cputime_to_scaled(delta_cpu));
+}
+
+void vtime_account_system(struct task_struct *tsk)
+{
+	write_seqlock(&tsk->vtime_seqlock);
+	__vtime_account_system(tsk);
+	write_sequnlock(&tsk->vtime_seqlock);
+}
+
+void vtime_gen_account_irq_exit(struct task_struct *tsk)
+{
+	write_seqlock(&tsk->vtime_seqlock);
+	__vtime_account_system(tsk);
+	if (context_tracking_in_user())
+		tsk->vtime_snap_whence = VTIME_USER;
+	write_sequnlock(&tsk->vtime_seqlock);
+}
+
+void vtime_account_user(struct task_struct *tsk)
+{
+	cputime_t delta_cpu;
+
+	write_seqlock(&tsk->vtime_seqlock);
+	delta_cpu = get_vtime_delta(tsk);
+	tsk->vtime_snap_whence = VTIME_SYS;
+	account_user_time(tsk, delta_cpu, cputime_to_scaled(delta_cpu));
+	write_sequnlock(&tsk->vtime_seqlock);
+}
+
+void vtime_user_enter(struct task_struct *tsk)
+{
+	write_seqlock(&tsk->vtime_seqlock);
+	__vtime_account_system(tsk);
+	tsk->vtime_snap_whence = VTIME_USER;
+	write_sequnlock(&tsk->vtime_seqlock);
+}
+
+void vtime_guest_enter(struct task_struct *tsk)
+{
+	/*
+	 * The flags must be updated under the lock with
+	 * the vtime_snap flush and update.
+	 * That enforces a right ordering and update sequence
+	 * synchronization against the reader (task_gtime())
+	 * that can thus safely catch up with a tickless delta.
+	 */
+	write_seqlock(&tsk->vtime_seqlock);
+	__vtime_account_system(tsk);
+	current->flags |= PF_VCPU;
+	write_sequnlock(&tsk->vtime_seqlock);
+}
+EXPORT_SYMBOL_GPL(vtime_guest_enter);
+
+void vtime_guest_exit(struct task_struct *tsk)
+{
+	write_seqlock(&tsk->vtime_seqlock);
+	__vtime_account_system(tsk);
+	current->flags &= ~PF_VCPU;
+	write_sequnlock(&tsk->vtime_seqlock);
+}
+EXPORT_SYMBOL_GPL(vtime_guest_exit);
+
+void vtime_account_idle(struct task_struct *tsk)
+{
+	cputime_t delta_cpu = get_vtime_delta(tsk);
+
+	account_idle_time(delta_cpu);
+}
+
+void arch_vtime_task_switch(struct task_struct *prev)
+{
+	write_seqlock(&prev->vtime_seqlock);
+	prev->vtime_snap_whence = VTIME_SLEEPING;
+	write_sequnlock(&prev->vtime_seqlock);
+
+	write_seqlock(&current->vtime_seqlock);
+	current->vtime_snap_whence = VTIME_SYS;
+	current->vtime_snap = sched_clock_cpu(smp_processor_id());
+	write_sequnlock(&current->vtime_seqlock);
+}
+
+void vtime_init_idle(struct task_struct *t, int cpu)
+{
+	unsigned long flags;
+
+	write_seqlock_irqsave(&t->vtime_seqlock, flags);
+	t->vtime_snap_whence = VTIME_SYS;
+	t->vtime_snap = sched_clock_cpu(cpu);
+	write_sequnlock_irqrestore(&t->vtime_seqlock, flags);
+}
+
+cputime_t task_gtime(struct task_struct *t)
+{
+	unsigned int seq;
+	cputime_t gtime;
+
+	do {
+		seq = read_seqbegin(&t->vtime_seqlock);
+
+		gtime = t->gtime;
+		if (t->flags & PF_VCPU)
+			gtime += vtime_delta(t);
+
+	} while (read_seqretry(&t->vtime_seqlock, seq));
+
+	return gtime;
+}
+
+/*
+ * Fetch cputime raw values from fields of task_struct and
+ * add up the pending nohz execution time since the last
+ * cputime snapshot.
+ */
+static void
+fetch_task_cputime(struct task_struct *t,
+		   cputime_t *u_dst, cputime_t *s_dst,
+		   cputime_t *u_src, cputime_t *s_src,
+		   cputime_t *udelta, cputime_t *sdelta)
+{
+	unsigned int seq;
+	unsigned long long delta;
+
+	do {
+		*udelta = 0;
+		*sdelta = 0;
+
+		seq = read_seqbegin(&t->vtime_seqlock);
+
+		if (u_dst)
+			*u_dst = *u_src;
+		if (s_dst)
+			*s_dst = *s_src;
+
+		/* Task is sleeping, nothing to add */
+		if (t->vtime_snap_whence == VTIME_SLEEPING ||
+		    is_idle_task(t))
+			continue;
+
+		delta = vtime_delta(t);
+
+		/*
+		 * Task runs either in user or kernel space, add pending nohz time to
+		 * the right place.
+		 */
+		if (t->vtime_snap_whence == VTIME_USER || t->flags & PF_VCPU) {
+			*udelta = delta;
+		} else {
+			if (t->vtime_snap_whence == VTIME_SYS)
+				*sdelta = delta;
+		}
+	} while (read_seqretry(&t->vtime_seqlock, seq));
+}
+
+
+void task_cputime(struct task_struct *t, cputime_t *utime, cputime_t *stime)
+{
+	cputime_t udelta, sdelta;
+
+	fetch_task_cputime(t, utime, stime, &t->utime,
+			   &t->stime, &udelta, &sdelta);
+	if (utime)
+		*utime += udelta;
+	if (stime)
+		*stime += sdelta;
+}
+
+void task_cputime_scaled(struct task_struct *t,
+			 cputime_t *utimescaled, cputime_t *stimescaled)
+{
+	cputime_t udelta, sdelta;
+
+	fetch_task_cputime(t, utimescaled, stimescaled,
+			   &t->utimescaled, &t->stimescaled, &udelta, &sdelta);
+	if (utimescaled)
+		*utimescaled += cputime_to_scaled(udelta);
+	if (stimescaled)
+		*stimescaled += cputime_to_scaled(sdelta);
+}
+#endif /* CONFIG_VIRT_CPU_ACCOUNTING_GEN */

kernel/sched/debug.c

@@ -0,0 +1,663 @@
+/*
+ * kernel/sched/debug.c
+ *
+ * Print the CFS rbtree
+ *
+ * Copyright(C) 2007, Red Hat, Inc., Ingo Molnar
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/proc_fs.h>
+#include <linux/sched.h>
+#include <linux/seq_file.h>
+#include <linux/kallsyms.h>
+#include <linux/utsname.h>
+#include <linux/mempolicy.h>
+
+#include "sched.h"
+
+static DEFINE_SPINLOCK(sched_debug_lock);
+
+/*
+ * This allows printing both to /proc/sched_debug and
+ * to the console
+ */
+#define SEQ_printf(m, x...)			\
+ do {						\
+	if (m)					\
+		seq_printf(m, x);		\
+	else					\
+		printk(x);			\
+ } while (0)
+
+/*
+ * Ease the printing of nsec fields:
+ */
+static long long nsec_high(unsigned long long nsec)
+{
+	if ((long long)nsec < 0) {
+		nsec = -nsec;
+		do_div(nsec, 1000000);
+		return -nsec;
+	}
+	do_div(nsec, 1000000);
+
+	return nsec;
+}
+
+static unsigned long nsec_low(unsigned long long nsec)
+{
+	if ((long long)nsec < 0)
+		nsec = -nsec;
+
+	return do_div(nsec, 1000000);
+}
+
+#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)
+{
+	struct sched_entity *se = tg->se[cpu];
+
+#define P(F) \
+	SEQ_printf(m, "  .%-30s: %lld\n", #F, (long long)F)
+#define PN(F) \
+	SEQ_printf(m, "  .%-30s: %lld.%06ld\n", #F, SPLIT_NS((long long)F))
+
+	if (!se) {
+		struct sched_avg *avg = &cpu_rq(cpu)->avg;
+		P(avg->runnable_avg_sum);
+		P(avg->runnable_avg_period);
+		return;
+	}
+
+
+	PN(se->exec_start);
+	PN(se->vruntime);
+	PN(se->sum_exec_runtime);
+#ifdef CONFIG_SCHEDSTATS
+	PN(se->statistics.wait_start);
+	PN(se->statistics.sleep_start);
+	PN(se->statistics.block_start);
+	PN(se->statistics.sleep_max);
+	PN(se->statistics.block_max);
+	PN(se->statistics.exec_max);
+	PN(se->statistics.slice_max);
+	PN(se->statistics.wait_max);
+	PN(se->statistics.wait_sum);
+	P(se->statistics.wait_count);
+#endif
+	P(se->load.weight);
+#ifdef CONFIG_SMP
+	P(se->avg.runnable_avg_sum);
+	P(se->avg.runnable_avg_period);
+	P(se->avg.usage_avg_sum);
+	P(se->avg.load_avg_contrib);
+	P(se->avg.decay_count);
+#endif
+#undef PN
+#undef P
+}
+#endif
+
+#ifdef CONFIG_CGROUP_SCHED
+static char group_path[PATH_MAX];
+
+static char *task_group_path(struct task_group *tg)
+{
+	if (autogroup_path(tg, group_path, PATH_MAX))
+		return group_path;
+
+	return cgroup_path(tg->css.cgroup, group_path, PATH_MAX);
+}
+#endif
+
+static void
+print_task(struct seq_file *m, struct rq *rq, struct task_struct *p)
+{
+	if (rq->curr == p)
+		SEQ_printf(m, "R");
+	else
+		SEQ_printf(m, " ");
+
+	SEQ_printf(m, "%15s %5d %9Ld.%06ld %9Ld %5d ",
+		p->comm, task_pid_nr(p),
+		SPLIT_NS(p->se.vruntime),
+		(long long)(p->nvcsw + p->nivcsw),
+		p->prio);
+#ifdef CONFIG_SCHEDSTATS
+	SEQ_printf(m, "%9Ld.%06ld %9Ld.%06ld %9Ld.%06ld",
+		SPLIT_NS(p->se.vruntime),
+		SPLIT_NS(p->se.sum_exec_runtime),
+		SPLIT_NS(p->se.statistics.sum_sleep_runtime));
+#else
+	SEQ_printf(m, "%15Ld %15Ld %15Ld.%06ld %15Ld.%06ld %15Ld.%06ld",
+		0LL, 0LL, 0LL, 0L, 0LL, 0L, 0LL, 0L);
+#endif
+#ifdef CONFIG_NUMA_BALANCING
+	SEQ_printf(m, " %d", task_node(p));
+#endif
+#ifdef CONFIG_CGROUP_SCHED
+	SEQ_printf(m, " %s", task_group_path(task_group(p)));
+#endif
+
+	SEQ_printf(m, "\n");
+}
+
+static void print_rq(struct seq_file *m, struct rq *rq, int rq_cpu)
+{
+	struct task_struct *g, *p;
+
+	SEQ_printf(m,
+	"\nrunnable tasks:\n"
+	"            task   PID         tree-key  switches  prio"
+	"     exec-runtime         sum-exec        sum-sleep\n"
+	"------------------------------------------------------"
+	"----------------------------------------------------\n");
+
+	rcu_read_lock();
+	for_each_process_thread(g, p) {
+		if (task_cpu(p) != rq_cpu)
+			continue;
+
+		print_task(m, rq, p);
+	}
+	rcu_read_unlock();
+}
+
+void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
+{
+	s64 MIN_vruntime = -1, min_vruntime, max_vruntime = -1,
+		spread, rq0_min_vruntime, spread0;
+	struct rq *rq = cpu_rq(cpu);
+	struct sched_entity *last;
+	unsigned long flags;
+
+#ifdef CONFIG_FAIR_GROUP_SCHED
+	SEQ_printf(m, "\ncfs_rq[%d]:%s\n", cpu, task_group_path(cfs_rq->tg));
+#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));
+
+	raw_spin_lock_irqsave(&rq->lock, flags);
+	if (cfs_rq->rb_leftmost)
+		MIN_vruntime = (__pick_first_entity(cfs_rq))->vruntime;
+	last = __pick_last_entity(cfs_rq);
+	if (last)
+		max_vruntime = last->vruntime;
+	min_vruntime = cfs_rq->min_vruntime;
+	rq0_min_vruntime = cpu_rq(0)->cfs.min_vruntime;
+	raw_spin_unlock_irqrestore(&rq->lock, flags);
+	SEQ_printf(m, "  .%-30s: %Ld.%06ld\n", "MIN_vruntime",
+			SPLIT_NS(MIN_vruntime));
+	SEQ_printf(m, "  .%-30s: %Ld.%06ld\n", "min_vruntime",
+			SPLIT_NS(min_vruntime));
+	SEQ_printf(m, "  .%-30s: %Ld.%06ld\n", "max_vruntime",
+			SPLIT_NS(max_vruntime));
+	spread = max_vruntime - MIN_vruntime;
+	SEQ_printf(m, "  .%-30s: %Ld.%06ld\n", "spread",
+			SPLIT_NS(spread));
+	spread0 = min_vruntime - rq0_min_vruntime;
+	SEQ_printf(m, "  .%-30s: %Ld.%06ld\n", "spread0",
+			SPLIT_NS(spread0));
+	SEQ_printf(m, "  .%-30s: %d\n", "nr_spread_over",
+			cfs_rq->nr_spread_over);
+	SEQ_printf(m, "  .%-30s: %d\n", "nr_running", cfs_rq->nr_running);
+	SEQ_printf(m, "  .%-30s: %ld\n", "load", cfs_rq->load.weight);
+#ifdef CONFIG_SMP
+	SEQ_printf(m, "  .%-30s: %ld\n", "runnable_load_avg",
+			cfs_rq->runnable_load_avg);
+	SEQ_printf(m, "  .%-30s: %ld\n", "blocked_load_avg",
+			cfs_rq->blocked_load_avg);
+#ifdef CONFIG_FAIR_GROUP_SCHED
+	SEQ_printf(m, "  .%-30s: %Ld\n", "tg_load_contrib",
+			cfs_rq->tg_load_contrib);
+	SEQ_printf(m, "  .%-30s: %d\n", "tg_runnable_contrib",
+			cfs_rq->tg_runnable_contrib);
+	SEQ_printf(m, "  .%-30s: %ld\n", "tg_load_avg",
+			atomic_long_read(&cfs_rq->tg->load_avg));
+	SEQ_printf(m, "  .%-30s: %d\n", "tg->runnable_avg",
+			atomic_read(&cfs_rq->tg->runnable_avg));
+	SEQ_printf(m, "  .%-30s: %d\n", "tg->usage_avg",
+			atomic_read(&cfs_rq->tg->usage_avg));
+#endif
+#endif
+#ifdef CONFIG_CFS_BANDWIDTH
+	SEQ_printf(m, "  .%-30s: %d\n", "tg->cfs_bandwidth.timer_active",
+			cfs_rq->tg->cfs_bandwidth.timer_active);
+	SEQ_printf(m, "  .%-30s: %d\n", "throttled",
+			cfs_rq->throttled);
+	SEQ_printf(m, "  .%-30s: %d\n", "throttle_count",
+			cfs_rq->throttle_count);
+#endif
+
+#ifdef CONFIG_FAIR_GROUP_SCHED
+	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)
+{
+#ifdef CONFIG_RT_GROUP_SCHED
+	SEQ_printf(m, "\nrt_rq[%d]:%s\n", cpu, task_group_path(rt_rq->tg));
+#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))
+#define PN(x) \
+	SEQ_printf(m, "  .%-30s: %Ld.%06ld\n", #x, SPLIT_NS(rt_rq->x))
+
+	P(rt_nr_running);
+	P(rt_throttled);
+	PN(rt_time);
+	PN(rt_runtime);
+
+#undef PN
+#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);
+	unsigned long flags;
+
+#ifdef CONFIG_X86
+	{
+		unsigned int freq = cpu_khz ? : 1;
+
+		SEQ_printf(m, "cpu#%d, %u.%03u MHz\n",
+			   cpu, freq / 1000, (freq % 1000));
+	}
+#else
+	SEQ_printf(m, "cpu#%d\n", cpu);
+#endif
+
+#define P(x)								\
+do {									\
+	if (sizeof(rq->x) == 4)						\
+		SEQ_printf(m, "  .%-30s: %ld\n", #x, (long)(rq->x));	\
+	else								\
+		SEQ_printf(m, "  .%-30s: %Ld\n", #x, (long long)(rq->x));\
+} while (0)
+
+#define PN(x) \
+	SEQ_printf(m, "  .%-30s: %Ld.%06ld\n", #x, SPLIT_NS(rq->x))
+
+	P(nr_running);
+	SEQ_printf(m, "  .%-30s: %lu\n", "load",
+		   rq->load.weight);
+	P(nr_switches);
+	P(nr_load_updates);
+	P(nr_uninterruptible);
+	PN(next_balance);
+	SEQ_printf(m, "  .%-30s: %ld\n", "curr->pid", (long)(task_pid_nr(rq->curr)));
+	PN(clock);
+	P(cpu_load[0]);
+	P(cpu_load[1]);
+	P(cpu_load[2]);
+	P(cpu_load[3]);
+	P(cpu_load[4]);
+#undef P
+#undef PN
+
+#ifdef CONFIG_SCHEDSTATS
+#define P(n) SEQ_printf(m, "  .%-30s: %d\n", #n, rq->n);
+#define P64(n) SEQ_printf(m, "  .%-30s: %Ld\n", #n, rq->n);
+
+	P(yld_count);
+
+	P(sched_count);
+	P(sched_goidle);
+#ifdef CONFIG_SMP
+	P64(avg_idle);
+	P64(max_idle_balance_cost);
+#endif
+
+	P(ttwu_count);
+	P(ttwu_local);
+
+#undef P
+#undef P64
+#endif
+	spin_lock_irqsave(&sched_debug_lock, flags);
+	print_cfs_stats(m, cpu);
+	print_rt_stats(m, cpu);
+
+	print_rq(m, rq, cpu);
+	spin_unlock_irqrestore(&sched_debug_lock, flags);
+	SEQ_printf(m, "\n");
+}
+
+static const char *sched_tunable_scaling_names[] = {
+	"none",
+	"logaritmic",
+	"linear"
+};
+
+static void sched_debug_header(struct seq_file *m)
+{
+	u64 ktime, sched_clk, cpu_clk;
+	unsigned long flags;
+
+	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: v0.11, %s %.*s\n",
+		init_utsname()->release,
+		(int)strcspn(init_utsname()->version, " "),
+		init_utsname()->version);
+
+#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))
+	PN(sysctl_sched_latency);
+	PN(sysctl_sched_min_granularity);
+	PN(sysctl_sched_wakeup_granularity);
+	P(sysctl_sched_child_runs_first);
+	P(sysctl_sched_features);
+#undef PN
+#undef P
+
+	SEQ_printf(m, "  .%-40s: %d (%s)\n",
+		"sysctl_sched_tunable_scaling",
+		sysctl_sched_tunable_scaling,
+		sched_tunable_scaling_names[sysctl_sched_tunable_scaling]);
+	SEQ_printf(m, "\n");
+}
+
+static int sched_debug_show(struct seq_file *m, void *v)
+{
+	int cpu = (unsigned long)(v - 2);
+
+	if (cpu != -1)
+		print_cpu(m, cpu);
+	else
+		sched_debug_header(m);
+
+	return 0;
+}
+
+void sysrq_sched_debug_show(void)
+{
+	int cpu;
+
+	sched_debug_header(NULL);
+	for_each_online_cpu(cpu)
+		print_cpu(NULL, cpu);
+
+}
+
+/*
+ * This itererator needs some explanation.
+ * It returns 1 for the header position.
+ * This means 2 is cpu 0.
+ * In a hotplugged system some cpus, including cpu 0, may be missing so we have
+ * to use cpumask_* to iterate over the cpus.
+ */
+static void *sched_debug_start(struct seq_file *file, loff_t *offset)
+{
+	unsigned long n = *offset;
+
+	if (n == 0)
+		return (void *) 1;
+
+	n--;
+
+	if (n > 0)
+		n = cpumask_next(n - 1, cpu_online_mask);
+	else
+		n = cpumask_first(cpu_online_mask);
+
+	*offset = n + 1;
+
+	if (n < nr_cpu_ids)
+		return (void *)(unsigned long)(n + 2);
+	return NULL;
+}
+
+static void *sched_debug_next(struct seq_file *file, void *data, loff_t *offset)
+{
+	(*offset)++;
+	return sched_debug_start(file, offset);
+}
+
+static void sched_debug_stop(struct seq_file *file, void *data)
+{
+}
+
+static const struct seq_operations sched_debug_sops = {
+	.start = sched_debug_start,
+	.next = sched_debug_next,
+	.stop = sched_debug_stop,
+	.show = sched_debug_show,
+};
+
+static int sched_debug_release(struct inode *inode, struct file *file)
+{
+	seq_release(inode, file);
+
+	return 0;
+}
+
+static int sched_debug_open(struct inode *inode, struct file *filp)
+{
+	int ret = 0;
+
+	ret = seq_open(filp, &sched_debug_sops);
+
+	return ret;
+}
+
+static const struct file_operations sched_debug_fops = {
+	.open		= sched_debug_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= sched_debug_release,
+};
+
+static int __init init_sched_debug_procfs(void)
+{
+	struct proc_dir_entry *pe;
+
+	pe = proc_create("sched_debug", 0444, NULL, &sched_debug_fops);
+	if (!pe)
+		return -ENOMEM;
+	return 0;
+}
+
+__initcall(init_sched_debug_procfs);
+
+#define __P(F) \
+	SEQ_printf(m, "%-45s:%21Ld\n", #F, (long long)F)
+#define P(F) \
+	SEQ_printf(m, "%-45s:%21Ld\n", #F, (long long)p->F)
+#define __PN(F) \
+	SEQ_printf(m, "%-45s:%14Ld.%06ld\n", #F, SPLIT_NS((long long)F))
+#define PN(F) \
+	SEQ_printf(m, "%-45s:%14Ld.%06ld\n", #F, SPLIT_NS((long long)p->F))
+
+
+static void sched_show_numa(struct task_struct *p, struct seq_file *m)
+{
+#ifdef CONFIG_NUMA_BALANCING
+	struct mempolicy *pol;
+	int node, i;
+
+	if (p->mm)
+		P(mm->numa_scan_seq);
+
+	task_lock(p);
+	pol = p->mempolicy;
+	if (pol && !(pol->flags & MPOL_F_MORON))
+		pol = NULL;
+	mpol_get(pol);
+	task_unlock(p);
+
+	SEQ_printf(m, "numa_migrations, %ld\n", xchg(&p->numa_pages_migrated, 0));
+
+	for_each_online_node(node) {
+		for (i = 0; i < 2; i++) {
+			unsigned long nr_faults = -1;
+			int cpu_current, home_node;
+
+			if (p->numa_faults_memory)
+				nr_faults = p->numa_faults_memory[2*node + i];
+
+			cpu_current = !i ? (task_node(p) == node) :
+				(pol && node_isset(node, pol->v.nodes));
+
+			home_node = (p->numa_preferred_nid == node);
+
+			SEQ_printf(m, "numa_faults_memory, %d, %d, %d, %d, %ld\n",
+				i, node, cpu_current, home_node, nr_faults);
+		}
+	}
+
+	mpol_put(pol);
+#endif
+}
+
+void proc_sched_show_task(struct task_struct *p, struct seq_file *m)
+{
+	unsigned long nr_switches;
+
+	SEQ_printf(m, "%s (%d, #threads: %d)\n", p->comm, task_pid_nr(p),
+						get_nr_threads(p));
+	SEQ_printf(m,
+		"---------------------------------------------------------"
+		"----------\n");
+#define __P(F) \
+	SEQ_printf(m, "%-45s:%21Ld\n", #F, (long long)F)
+#define P(F) \
+	SEQ_printf(m, "%-45s:%21Ld\n", #F, (long long)p->F)
+#define __PN(F) \
+	SEQ_printf(m, "%-45s:%14Ld.%06ld\n", #F, SPLIT_NS((long long)F))
+#define PN(F) \
+	SEQ_printf(m, "%-45s:%14Ld.%06ld\n", #F, SPLIT_NS((long long)p->F))
+
+	PN(se.exec_start);
+	PN(se.vruntime);
+	PN(se.sum_exec_runtime);
+
+	nr_switches = p->nvcsw + p->nivcsw;
+
+#ifdef CONFIG_SCHEDSTATS
+	PN(se.statistics.wait_start);
+	PN(se.statistics.sleep_start);
+	PN(se.statistics.block_start);
+	PN(se.statistics.sleep_max);
+	PN(se.statistics.block_max);
+	PN(se.statistics.exec_max);
+	PN(se.statistics.slice_max);
+	PN(se.statistics.wait_max);
+	PN(se.statistics.wait_sum);
+	P(se.statistics.wait_count);
+	PN(se.statistics.iowait_sum);
+	P(se.statistics.iowait_count);
+	P(se.nr_migrations);
+	P(se.statistics.nr_migrations_cold);
+	P(se.statistics.nr_failed_migrations_affine);
+	P(se.statistics.nr_failed_migrations_running);
+	P(se.statistics.nr_failed_migrations_hot);
+	P(se.statistics.nr_forced_migrations);
+	P(se.statistics.nr_wakeups);
+	P(se.statistics.nr_wakeups_sync);
+	P(se.statistics.nr_wakeups_migrate);
+	P(se.statistics.nr_wakeups_local);
+	P(se.statistics.nr_wakeups_remote);
+	P(se.statistics.nr_wakeups_affine);
+	P(se.statistics.nr_wakeups_affine_attempts);
+	P(se.statistics.nr_wakeups_passive);
+	P(se.statistics.nr_wakeups_idle);
+
+	{
+		u64 avg_atom, avg_per_cpu;
+
+		avg_atom = p->se.sum_exec_runtime;
+		if (nr_switches)
+			avg_atom = div64_ul(avg_atom, nr_switches);
+		else
+			avg_atom = -1LL;
+
+		avg_per_cpu = p->se.sum_exec_runtime;
+		if (p->se.nr_migrations) {
+			avg_per_cpu = div64_u64(avg_per_cpu,
+						p->se.nr_migrations);
+		} else {
+			avg_per_cpu = -1LL;
+		}
+
+		__PN(avg_atom);
+		__PN(avg_per_cpu);
+	}
+#endif
+	__P(nr_switches);
+	SEQ_printf(m, "%-45s:%21Ld\n",
+		   "nr_voluntary_switches", (long long)p->nvcsw);
+	SEQ_printf(m, "%-45s:%21Ld\n",
+		   "nr_involuntary_switches", (long long)p->nivcsw);
+
+	P(se.load.weight);
+#ifdef CONFIG_SMP
+	P(se.avg.runnable_avg_sum);
+	P(se.avg.runnable_avg_period);
+	P(se.avg.load_avg_contrib);
+	P(se.avg.decay_count);
+#endif
+	P(policy);
+	P(prio);
+#undef PN
+#undef __PN
+#undef P
+#undef __P
+
+	{
+		unsigned int this_cpu = raw_smp_processor_id();
+		u64 t0, t1;
+
+		t0 = cpu_clock(this_cpu);
+		t1 = cpu_clock(this_cpu);
+		SEQ_printf(m, "%-45s:%21Ld\n",
+			   "clock-delta", (long long)(t1-t0));
+	}
+
+	sched_show_numa(p, m);
+}
+
+void proc_sched_set_task(struct task_struct *p)
+{
+#ifdef CONFIG_SCHEDSTATS
+	memset(&p->se.statistics, 0, sizeof(p->se.statistics));
+#endif
+}

kernel/sched/features.h

@@ -0,0 +1,85 @@
+/*
+ * Only give sleepers 50% of their service deficit. This allows
+ * them to run sooner, but does not allow tons of sleepers to
+ * rip the spread apart.
+ */
+SCHED_FEAT(GENTLE_FAIR_SLEEPERS, true)
+
+/*
+ * Place new tasks ahead so that they do not starve already running
+ * tasks
+ */
+SCHED_FEAT(START_DEBIT, true)
+
+/*
+ * Prefer to schedule the task we woke last (assuming it failed
+ * wakeup-preemption), since its likely going to consume data we
+ * touched, increases cache locality.
+ */
+SCHED_FEAT(NEXT_BUDDY, false)
+
+/*
+ * Prefer to schedule the task that ran last (when we did
+ * wake-preempt) as that likely will touch the same data, increases
+ * cache locality.
+ */
+SCHED_FEAT(LAST_BUDDY, true)
+
+/*
+ * Consider buddies to be cache hot, decreases the likelyness of a
+ * cache buddy being migrated away, increases cache locality.
+ */
+SCHED_FEAT(CACHE_HOT_BUDDY, true)
+
+/*
+ * Allow wakeup-time preemption of the current task:
+ */
+SCHED_FEAT(WAKEUP_PREEMPTION, true)
+
+/*
+ * Use arch dependent cpu capacity functions
+ */
+SCHED_FEAT(ARCH_CAPACITY, true)
+
+SCHED_FEAT(HRTICK, false)
+SCHED_FEAT(DOUBLE_TICK, false)
+SCHED_FEAT(LB_BIAS, true)
+
+/*
+ * Decrement CPU capacity based on time not spent running tasks
+ */
+SCHED_FEAT(NONTASK_CAPACITY, true)
+
+/*
+ * Queue remote wakeups on the target CPU and process them
+ * using the scheduler IPI. Reduces rq->lock contention/bounces.
+ */
+SCHED_FEAT(TTWU_QUEUE, true)
+
+SCHED_FEAT(FORCE_SD_OVERLAP, false)
+SCHED_FEAT(RT_RUNTIME_SHARE, true)
+SCHED_FEAT(LB_MIN, false)
+
+/*
+ * Apply the automatic NUMA scheduling policy. Enabled automatically
+ * at runtime if running on a NUMA machine. Can be controlled via
+ * numa_balancing=
+ */
+#ifdef CONFIG_NUMA_BALANCING
+SCHED_FEAT(NUMA,	false)
+
+/*
+ * NUMA_FAVOUR_HIGHER will favor moving tasks towards nodes where a
+ * higher number of hinting faults are recorded during active load
+ * balancing.
+ */
+SCHED_FEAT(NUMA_FAVOUR_HIGHER, true)
+
+/*
+ * NUMA_RESIST_LOWER will resist moving tasks towards nodes where a
+ * lower number of hinting faults have been recorded. As this has
+ * the potential to prevent a task ever migrating to a new node
+ * due to CPU overload it is disabled by default.
+ */
+SCHED_FEAT(NUMA_RESIST_LOWER, false)
+#endif

kernel/sched/idle.c

@@ -0,0 +1,275 @@
+/*
+ * Generic entry point for the idle threads
+ */
+#include <linux/sched.h>
+#include <linux/cpu.h>
+#include <linux/cpuidle.h>
+#include <linux/tick.h>
+#include <linux/mm.h>
+#include <linux/stackprotector.h>
+
+#include <asm/tlb.h>
+
+#include <trace/events/power.h>
+
+#include "sched.h"
+
+static int __read_mostly cpu_idle_force_poll;
+
+void cpu_idle_poll_ctrl(bool enable)
+{
+	if (enable) {
+		cpu_idle_force_poll++;
+	} else {
+		cpu_idle_force_poll--;
+		WARN_ON_ONCE(cpu_idle_force_poll < 0);
+	}
+}
+
+#ifdef CONFIG_GENERIC_IDLE_POLL_SETUP
+static int __init cpu_idle_poll_setup(char *__unused)
+{
+	cpu_idle_force_poll = 1;
+	return 1;
+}
+__setup("nohlt", cpu_idle_poll_setup);
+
+static int __init cpu_idle_nopoll_setup(char *__unused)
+{
+	cpu_idle_force_poll = 0;
+	return 1;
+}
+__setup("hlt", cpu_idle_nopoll_setup);
+#endif
+
+static inline int cpu_idle_poll(void)
+{
+	rcu_idle_enter();
+	trace_cpu_idle_rcuidle(0, smp_processor_id());
+	local_irq_enable();
+	while (!tif_need_resched())
+		cpu_relax();
+	trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id());
+	rcu_idle_exit();
+	return 1;
+}
+
+/* Weak implementations for optional arch specific functions */
+void __weak arch_cpu_idle_prepare(void) { }
+void __weak arch_cpu_idle_enter(void) { }
+void __weak arch_cpu_idle_exit(void) { }
+void __weak arch_cpu_idle_dead(void) { }
+void __weak arch_cpu_idle(void)
+{
+	cpu_idle_force_poll = 1;
+	local_irq_enable();
+}
+
+/**
+ * cpuidle_idle_call - the main idle function
+ *
+ * NOTE: no locks or semaphores should be used here
+ *
+ * On archs that support TIF_POLLING_NRFLAG, is called with polling
+ * set, and it returns with polling set.  If it ever stops polling, it
+ * must clear the polling bit.
+ */
+static void cpuidle_idle_call(void)
+{
+	struct cpuidle_device *dev = __this_cpu_read(cpuidle_devices);
+	struct cpuidle_driver *drv = cpuidle_get_cpu_driver(dev);
+	int next_state, entered_state;
+	unsigned int broadcast;
+
+	/*
+	 * Check if the idle task must be rescheduled. If it is the
+	 * case, exit the function after re-enabling the local irq.
+	 */
+	if (need_resched()) {
+		local_irq_enable();
+		return;
+	}
+
+	/*
+	 * During the idle period, stop measuring the disabled irqs
+	 * critical sections latencies
+	 */
+	stop_critical_timings();
+
+	/*
+	 * Tell the RCU framework we are entering an idle section,
+	 * so no more rcu read side critical sections and one more
+	 * step to the grace period
+	 */
+	rcu_idle_enter();
+
+	/*
+	 * Ask the cpuidle framework to choose a convenient idle state.
+	 * Fall back to the default arch idle method on errors.
+	 */
+	next_state = cpuidle_select(drv, dev);
+	if (next_state < 0) {
+use_default:
+		/*
+		 * We can't use the cpuidle framework, let's use the default
+		 * idle routine.
+		 */
+		if (current_clr_polling_and_test())
+			local_irq_enable();
+		else
+			arch_cpu_idle();
+
+		goto exit_idle;
+	}
+
+
+	/*
+	 * The idle task must be scheduled, it is pointless to
+	 * go to idle, just update no idle residency and get
+	 * out of this function
+	 */
+	if (current_clr_polling_and_test()) {
+		dev->last_residency = 0;
+		entered_state = next_state;
+		local_irq_enable();
+		goto exit_idle;
+	}
+
+	broadcast = drv->states[next_state].flags & CPUIDLE_FLAG_TIMER_STOP;
+
+	/*
+	 * Tell the time framework to switch to a broadcast timer
+	 * because our local timer will be shutdown. If a local timer
+	 * is used from another cpu as a broadcast timer, this call may
+	 * fail if it is not available
+	 */
+	if (broadcast &&
+	    clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_ENTER, &dev->cpu))
+		goto use_default;
+
+	/* Take note of the planned idle state. */
+	idle_set_state(this_rq(), &drv->states[next_state]);
+
+	/*
+	 * Enter the idle state previously returned by the governor decision.
+	 * This function will block until an interrupt occurs and will take
+	 * care of re-enabling the local interrupts
+	 */
+	entered_state = cpuidle_enter(drv, dev, next_state);
+
+	/* The cpu is no longer idle or about to enter idle. */
+	idle_set_state(this_rq(), NULL);
+
+	if (broadcast)
+		clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_EXIT, &dev->cpu);
+
+	/*
+	 * Give the governor an opportunity to reflect on the outcome
+	 */
+	cpuidle_reflect(dev, entered_state);
+
+exit_idle:
+	__current_set_polling();
+
+	/*
+	 * It is up to the idle functions to reenable local interrupts
+	 */
+	if (WARN_ON_ONCE(irqs_disabled()))
+		local_irq_enable();
+
+	rcu_idle_exit();
+	start_critical_timings();
+}
+
+/*
+ * Generic idle loop implementation
+ *
+ * Called with polling cleared.
+ */
+static void cpu_idle_loop(void)
+{
+	while (1) {
+		/*
+		 * If the arch has a polling bit, we maintain an invariant:
+		 *
+		 * Our polling bit is clear if we're not scheduled (i.e. if
+		 * rq->curr != rq->idle).  This means that, if rq->idle has
+		 * the polling bit set, then setting need_resched is
+		 * guaranteed to cause the cpu to reschedule.
+		 */
+
+		__current_set_polling();
+		tick_nohz_idle_enter();
+
+		while (!need_resched()) {
+			check_pgt_cache();
+			rmb();
+
+			if (cpu_is_offline(smp_processor_id()))
+				arch_cpu_idle_dead();
+
+			local_irq_disable();
+			arch_cpu_idle_enter();
+
+			/*
+			 * In poll mode we reenable interrupts and spin.
+			 *
+			 * Also if we detected in the wakeup from idle
+			 * path that the tick broadcast device expired
+			 * for us, we don't want to go deep idle as we
+			 * know that the IPI is going to arrive right
+			 * away
+			 */
+			if (cpu_idle_force_poll || tick_check_broadcast_expired())
+				cpu_idle_poll();
+			else
+				cpuidle_idle_call();
+
+			arch_cpu_idle_exit();
+		}
+
+		/*
+		 * Since we fell out of the loop above, we know
+		 * TIF_NEED_RESCHED must be set, propagate it into
+		 * PREEMPT_NEED_RESCHED.
+		 *
+		 * This is required because for polling idle loops we will
+		 * not have had an IPI to fold the state for us.
+		 */
+		preempt_set_need_resched();
+		tick_nohz_idle_exit();
+		__current_clr_polling();
+
+		/*
+		 * We promise to call sched_ttwu_pending and reschedule
+		 * if need_resched is set while polling is set.  That
+		 * means that clearing polling needs to be visible
+		 * before doing these things.
+		 */
+		smp_mb__after_atomic();
+
+		sched_ttwu_pending();
+		schedule_preempt_disabled();
+	}
+}
+
+void cpu_startup_entry(enum cpuhp_state state)
+{
+	/*
+	 * This #ifdef needs to die, but it's too late in the cycle to
+	 * make this generic (arm and sh have never invoked the canary
+	 * init for the non boot cpus!). Will be fixed in 3.11
+	 */
+#ifdef CONFIG_X86
+	/*
+	 * If we're the non-boot CPU, nothing set the stack canary up
+	 * for us. The boot CPU already has it initialized but no harm
+	 * in doing it again. This is a good place for updating it, as
+	 * we wont ever return from this function (so the invalid
+	 * canaries already on the stack wont ever trigger).
+	 */
+	boot_init_stack_canary();
+#endif
+	arch_cpu_idle_prepare();
+	cpu_idle_loop();
+}

kernel/sched/idle_task.c

@@ -0,0 +1,109 @@
+#include "sched.h"
+
+/*
+ * idle-task scheduling class.
+ *
+ * (NOTE: these are not related to SCHED_IDLE tasks which are
+ *  handled in sched/fair.c)
+ */
+
+#ifdef CONFIG_SMP
+static int
+select_task_rq_idle(struct task_struct *p, int cpu, int sd_flag, int flags)
+{
+	return task_cpu(p); /* IDLE tasks as never migrated */
+}
+#endif /* CONFIG_SMP */
+
+/*
+ * Idle tasks are unconditionally rescheduled:
+ */
+static void check_preempt_curr_idle(struct rq *rq, struct task_struct *p, int flags)
+{
+	resched_curr(rq);
+}
+
+static struct task_struct *
+pick_next_task_idle(struct rq *rq, struct task_struct *prev)
+{
+	put_prev_task(rq, prev);
+
+	schedstat_inc(rq, sched_goidle);
+	return rq->idle;
+}
+
+/*
+ * It is not legal to sleep in the idle task - print a warning
+ * message if some code attempts to do it:
+ */
+static void
+dequeue_task_idle(struct rq *rq, struct task_struct *p, int flags)
+{
+	raw_spin_unlock_irq(&rq->lock);
+	printk(KERN_ERR "bad: scheduling from the idle thread!\n");
+	dump_stack();
+	raw_spin_lock_irq(&rq->lock);
+}
+
+static void put_prev_task_idle(struct rq *rq, struct task_struct *prev)
+{
+	idle_exit_fair(rq);
+	rq_last_tick_reset(rq);
+}
+
+static void task_tick_idle(struct rq *rq, struct task_struct *curr, int queued)
+{
+}
+
+static void set_curr_task_idle(struct rq *rq)
+{
+}
+
+static void switched_to_idle(struct rq *rq, struct task_struct *p)
+{
+	BUG();
+}
+
+static void
+prio_changed_idle(struct rq *rq, struct task_struct *p, int oldprio)
+{
+	BUG();
+}
+
+static unsigned int get_rr_interval_idle(struct rq *rq, struct task_struct *task)
+{
+	return 0;
+}
+
+static void update_curr_idle(struct rq *rq)
+{
+}
+
+/*
+ * Simple, special scheduling class for the per-CPU idle tasks:
+ */
+const struct sched_class idle_sched_class = {
+	/* .next is NULL */
+	/* no enqueue/yield_task for idle tasks */
+
+	/* dequeue is not valid, we print a debug message there: */
+	.dequeue_task		= dequeue_task_idle,
+
+	.check_preempt_curr	= check_preempt_curr_idle,
+
+	.pick_next_task		= pick_next_task_idle,
+	.put_prev_task		= put_prev_task_idle,
+
+#ifdef CONFIG_SMP
+	.select_task_rq		= select_task_rq_idle,
+#endif
+
+	.set_curr_task          = set_curr_task_idle,
+	.task_tick		= task_tick_idle,
+
+	.get_rr_interval	= get_rr_interval_idle,
+
+	.prio_changed		= prio_changed_idle,
+	.switched_to		= switched_to_idle,
+	.update_curr		= update_curr_idle,
+};

kernel/sched/proc.c

@@ -0,0 +1,584 @@
+/*
+ *  kernel/sched/proc.c
+ *
+ *  Kernel load calculations, forked from sched/core.c
+ */
+
+#include <linux/export.h>
+
+#include "sched.h"
+
+/*
+ * Global load-average calculations
+ *
+ * We take a distributed and async approach to calculating the global load-avg
+ * in order to minimize overhead.
+ *
+ * The global load average is an exponentially decaying average of nr_running +
+ * nr_uninterruptible.
+ *
+ * Once every LOAD_FREQ:
+ *
+ *   nr_active = 0;
+ *   for_each_possible_cpu(cpu)
+ *	nr_active += cpu_of(cpu)->nr_running + cpu_of(cpu)->nr_uninterruptible;
+ *
+ *   avenrun[n] = avenrun[0] * exp_n + nr_active * (1 - exp_n)
+ *
+ * Due to a number of reasons the above turns in the mess below:
+ *
+ *  - for_each_possible_cpu() is prohibitively expensive on machines with
+ *    serious number of cpus, therefore we need to take a distributed approach
+ *    to calculating nr_active.
+ *
+ *        \Sum_i x_i(t) = \Sum_i x_i(t) - x_i(t_0) | x_i(t_0) := 0
+ *                      = \Sum_i { \Sum_j=1 x_i(t_j) - x_i(t_j-1) }
+ *
+ *    So assuming nr_active := 0 when we start out -- true per definition, we
+ *    can simply take per-cpu deltas and fold those into a global accumulate
+ *    to obtain the same result. See calc_load_fold_active().
+ *
+ *    Furthermore, in order to avoid synchronizing all per-cpu delta folding
+ *    across the machine, we assume 10 ticks is sufficient time for every
+ *    cpu to have completed this task.
+ *
+ *    This places an upper-bound on the IRQ-off latency of the machine. Then
+ *    again, being late doesn't loose the delta, just wrecks the sample.
+ *
+ *  - cpu_rq()->nr_uninterruptible isn't accurately tracked per-cpu because
+ *    this would add another cross-cpu cacheline miss and atomic operation
+ *    to the wakeup path. Instead we increment on whatever cpu the task ran
+ *    when it went into uninterruptible state and decrement on whatever cpu
+ *    did the wakeup. This means that only the sum of nr_uninterruptible over
+ *    all cpus yields the correct result.
+ *
+ *  This covers the NO_HZ=n code, for extra head-aches, see the comment below.
+ */
+
+/* Variables and functions for calc_load */
+atomic_long_t calc_load_tasks;
+unsigned long calc_load_update;
+unsigned long avenrun[3];
+EXPORT_SYMBOL(avenrun); /* should be removed */
+
+/**
+ * get_avenrun - get the load average array
+ * @loads:	pointer to dest load array
+ * @offset:	offset to add
+ * @shift:	shift count to shift the result left
+ *
+ * These values are estimates at best, so no need for locking.
+ */
+void get_avenrun(unsigned long *loads, unsigned long offset, int shift)
+{
+	loads[0] = (avenrun[0] + offset) << shift;
+	loads[1] = (avenrun[1] + offset) << shift;
+	loads[2] = (avenrun[2] + offset) << shift;
+}
+
+long calc_load_fold_active(struct rq *this_rq)
+{
+	long nr_active, delta = 0;
+
+	nr_active = this_rq->nr_running;
+	nr_active += (long) this_rq->nr_uninterruptible;
+
+	if (nr_active != this_rq->calc_load_active) {
+		delta = nr_active - this_rq->calc_load_active;
+		this_rq->calc_load_active = nr_active;
+	}
+
+	return delta;
+}
+
+/*
+ * a1 = a0 * e + a * (1 - e)
+ */
+static unsigned long
+calc_load(unsigned long load, unsigned long exp, unsigned long active)
+{
+	load *= exp;
+	load += active * (FIXED_1 - exp);
+	load += 1UL << (FSHIFT - 1);
+	return load >> FSHIFT;
+}
+
+#ifdef CONFIG_NO_HZ_COMMON
+/*
+ * Handle NO_HZ for the global load-average.
+ *
+ * Since the above described distributed algorithm to compute the global
+ * load-average relies on per-cpu sampling from the tick, it is affected by
+ * NO_HZ.
+ *
+ * The basic idea is to fold the nr_active delta into a global idle-delta upon
+ * entering NO_HZ state such that we can include this as an 'extra' cpu delta
+ * when we read the global state.
+ *
+ * Obviously reality has to ruin such a delightfully simple scheme:
+ *
+ *  - When we go NO_HZ idle during the window, we can negate our sample
+ *    contribution, causing under-accounting.
+ *
+ *    We avoid this by keeping two idle-delta counters and flipping them
+ *    when the window starts, thus separating old and new NO_HZ load.
+ *
+ *    The only trick is the slight shift in index flip for read vs write.
+ *
+ *        0s            5s            10s           15s
+ *          +10           +10           +10           +10
+ *        |-|-----------|-|-----------|-|-----------|-|
+ *    r:0 0 1           1 0           0 1           1 0
+ *    w:0 1 1           0 0           1 1           0 0
+ *
+ *    This ensures we'll fold the old idle contribution in this window while
+ *    accumlating the new one.
+ *
+ *  - When we wake up from NO_HZ idle during the window, we push up our
+ *    contribution, since we effectively move our sample point to a known
+ *    busy state.
+ *
+ *    This is solved by pushing the window forward, and thus skipping the
+ *    sample, for this cpu (effectively using the idle-delta for this cpu which
+ *    was in effect at the time the window opened). This also solves the issue
+ *    of having to deal with a cpu having been in NOHZ idle for multiple
+ *    LOAD_FREQ intervals.
+ *
+ * When making the ILB scale, we should try to pull this in as well.
+ */
+static atomic_long_t calc_load_idle[2];
+static int calc_load_idx;
+
+static inline int calc_load_write_idx(void)
+{
+	int idx = calc_load_idx;
+
+	/*
+	 * See calc_global_nohz(), if we observe the new index, we also
+	 * need to observe the new update time.
+	 */
+	smp_rmb();
+
+	/*
+	 * If the folding window started, make sure we start writing in the
+	 * next idle-delta.
+	 */
+	if (!time_before(jiffies, calc_load_update))
+		idx++;
+
+	return idx & 1;
+}
+
+static inline int calc_load_read_idx(void)
+{
+	return calc_load_idx & 1;
+}
+
+void calc_load_enter_idle(void)
+{
+	struct rq *this_rq = this_rq();
+	long delta;
+
+	/*
+	 * We're going into NOHZ mode, if there's any pending delta, fold it
+	 * into the pending idle delta.
+	 */
+	delta = calc_load_fold_active(this_rq);
+	if (delta) {
+		int idx = calc_load_write_idx();
+		atomic_long_add(delta, &calc_load_idle[idx]);
+	}
+}
+
+void calc_load_exit_idle(void)
+{
+	struct rq *this_rq = this_rq();
+
+	/*
+	 * If we're still before the sample window, we're done.
+	 */
+	if (time_before(jiffies, this_rq->calc_load_update))
+		return;
+
+	/*
+	 * We woke inside or after the sample window, this means we're already
+	 * accounted through the nohz accounting, so skip the entire deal and
+	 * sync up for the next window.
+	 */
+	this_rq->calc_load_update = calc_load_update;
+	if (time_before(jiffies, this_rq->calc_load_update + 10))
+		this_rq->calc_load_update += LOAD_FREQ;
+}
+
+static long calc_load_fold_idle(void)
+{
+	int idx = calc_load_read_idx();
+	long delta = 0;
+
+	if (atomic_long_read(&calc_load_idle[idx]))
+		delta = atomic_long_xchg(&calc_load_idle[idx], 0);
+
+	return delta;
+}
+
+/**
+ * fixed_power_int - compute: x^n, in O(log n) time
+ *
+ * @x:         base of the power
+ * @frac_bits: fractional bits of @x
+ * @n:         power to raise @x to.
+ *
+ * By exploiting the relation between the definition of the natural power
+ * function: x^n := x*x*...*x (x multiplied by itself for n times), and
+ * the binary encoding of numbers used by computers: n := \Sum n_i * 2^i,
+ * (where: n_i \elem {0, 1}, the binary vector representing n),
+ * we find: x^n := x^(\Sum n_i * 2^i) := \Prod x^(n_i * 2^i), which is
+ * of course trivially computable in O(log_2 n), the length of our binary
+ * vector.
+ */
+static unsigned long
+fixed_power_int(unsigned long x, unsigned int frac_bits, unsigned int n)
+{
+	unsigned long result = 1UL << frac_bits;
+
+	if (n) for (;;) {
+		if (n & 1) {
+			result *= x;
+			result += 1UL << (frac_bits - 1);
+			result >>= frac_bits;
+		}
+		n >>= 1;
+		if (!n)
+			break;
+		x *= x;
+		x += 1UL << (frac_bits - 1);
+		x >>= frac_bits;
+	}
+
+	return result;
+}
+
+/*
+ * a1 = a0 * e + a * (1 - e)
+ *
+ * a2 = a1 * e + a * (1 - e)
+ *    = (a0 * e + a * (1 - e)) * e + a * (1 - e)
+ *    = a0 * e^2 + a * (1 - e) * (1 + e)
+ *
+ * a3 = a2 * e + a * (1 - e)
+ *    = (a0 * e^2 + a * (1 - e) * (1 + e)) * e + a * (1 - e)
+ *    = a0 * e^3 + a * (1 - e) * (1 + e + e^2)
+ *
+ *  ...
+ *
+ * an = a0 * e^n + a * (1 - e) * (1 + e + ... + e^n-1) [1]
+ *    = a0 * e^n + a * (1 - e) * (1 - e^n)/(1 - e)
+ *    = a0 * e^n + a * (1 - e^n)
+ *
+ * [1] application of the geometric series:
+ *
+ *              n         1 - x^(n+1)
+ *     S_n := \Sum x^i = -------------
+ *             i=0          1 - x
+ */
+static unsigned long
+calc_load_n(unsigned long load, unsigned long exp,
+	    unsigned long active, unsigned int n)
+{
+
+	return calc_load(load, fixed_power_int(exp, FSHIFT, n), active);
+}
+
+/*
+ * NO_HZ can leave us missing all per-cpu ticks calling
+ * calc_load_account_active(), but since an idle CPU folds its delta into
+ * calc_load_tasks_idle per calc_load_account_idle(), all we need to do is fold
+ * in the pending idle delta if our idle period crossed a load cycle boundary.
+ *
+ * Once we've updated the global active value, we need to apply the exponential
+ * weights adjusted to the number of cycles missed.
+ */
+static void calc_global_nohz(void)
+{
+	long delta, active, n;
+
+	if (!time_before(jiffies, calc_load_update + 10)) {
+		/*
+		 * Catch-up, fold however many we are behind still
+		 */
+		delta = jiffies - calc_load_update - 10;
+		n = 1 + (delta / LOAD_FREQ);
+
+		active = atomic_long_read(&calc_load_tasks);
+		active = active > 0 ? active * FIXED_1 : 0;
+
+		avenrun[0] = calc_load_n(avenrun[0], EXP_1, active, n);
+		avenrun[1] = calc_load_n(avenrun[1], EXP_5, active, n);
+		avenrun[2] = calc_load_n(avenrun[2], EXP_15, active, n);
+
+		calc_load_update += n * LOAD_FREQ;
+	}
+
+	/*
+	 * Flip the idle index...
+	 *
+	 * Make sure we first write the new time then flip the index, so that
+	 * calc_load_write_idx() will see the new time when it reads the new
+	 * index, this avoids a double flip messing things up.
+	 */
+	smp_wmb();
+	calc_load_idx++;
+}
+#else /* !CONFIG_NO_HZ_COMMON */
+
+static inline long calc_load_fold_idle(void) { return 0; }
+static inline void calc_global_nohz(void) { }
+
+#endif /* CONFIG_NO_HZ_COMMON */
+
+/*
+ * calc_load - update the avenrun load estimates 10 ticks after the
+ * CPUs have updated calc_load_tasks.
+ */
+void calc_global_load(unsigned long ticks)
+{
+	long active, delta;
+
+	if (time_before(jiffies, calc_load_update + 10))
+		return;
+
+	/*
+	 * Fold the 'old' idle-delta to include all NO_HZ cpus.
+	 */
+	delta = calc_load_fold_idle();
+	if (delta)
+		atomic_long_add(delta, &calc_load_tasks);
+
+	active = atomic_long_read(&calc_load_tasks);
+	active = active > 0 ? active * FIXED_1 : 0;
+
+	avenrun[0] = calc_load(avenrun[0], EXP_1, active);
+	avenrun[1] = calc_load(avenrun[1], EXP_5, active);
+	avenrun[2] = calc_load(avenrun[2], EXP_15, active);
+
+	calc_load_update += LOAD_FREQ;
+
+	/*
+	 * In case we idled for multiple LOAD_FREQ intervals, catch up in bulk.
+	 */
+	calc_global_nohz();
+}
+
+/*
+ * Called from update_cpu_load() to periodically update this CPU's
+ * active count.
+ */
+static void calc_load_account_active(struct rq *this_rq)
+{
+	long delta;
+
+	if (time_before(jiffies, this_rq->calc_load_update))
+		return;
+
+	delta  = calc_load_fold_active(this_rq);
+	if (delta)
+		atomic_long_add(delta, &calc_load_tasks);
+
+	this_rq->calc_load_update += LOAD_FREQ;
+}
+
+/*
+ * End of global load-average stuff
+ */
+
+/*
+ * The exact cpuload at various idx values, calculated at every tick would be
+ * load = (2^idx - 1) / 2^idx * load + 1 / 2^idx * cur_load
+ *
+ * If a cpu misses updates for n-1 ticks (as it was idle) and update gets called
+ * on nth tick when cpu may be busy, then we have:
+ * load = ((2^idx - 1) / 2^idx)^(n-1) * load
+ * load = (2^idx - 1) / 2^idx) * load + 1 / 2^idx * cur_load
+ *
+ * decay_load_missed() below does efficient calculation of
+ * load = ((2^idx - 1) / 2^idx)^(n-1) * load
+ * avoiding 0..n-1 loop doing load = ((2^idx - 1) / 2^idx) * load
+ *
+ * The calculation is approximated on a 128 point scale.
+ * degrade_zero_ticks is the number of ticks after which load at any
+ * particular idx is approximated to be zero.
+ * degrade_factor is a precomputed table, a row for each load idx.
+ * Each column corresponds to degradation factor for a power of two ticks,
+ * based on 128 point scale.
+ * Example:
+ * row 2, col 3 (=12) says that the degradation at load idx 2 after
+ * 8 ticks is 12/128 (which is an approximation of exact factor 3^8/4^8).
+ *
+ * With this power of 2 load factors, we can degrade the load n times
+ * by looking at 1 bits in n and doing as many mult/shift instead of
+ * n mult/shifts needed by the exact degradation.
+ */
+#define DEGRADE_SHIFT		7
+static const unsigned char
+		degrade_zero_ticks[CPU_LOAD_IDX_MAX] = {0, 8, 32, 64, 128};
+static const unsigned char
+		degrade_factor[CPU_LOAD_IDX_MAX][DEGRADE_SHIFT + 1] = {
+					{0, 0, 0, 0, 0, 0, 0, 0},
+					{64, 32, 8, 0, 0, 0, 0, 0},
+					{96, 72, 40, 12, 1, 0, 0},
+					{112, 98, 75, 43, 15, 1, 0},
+					{120, 112, 98, 76, 45, 16, 2} };
+
+/*
+ * Update cpu_load for any missed ticks, due to tickless idle. The backlog
+ * would be when CPU is idle and so we just decay the old load without
+ * adding any new load.
+ */
+static unsigned long
+decay_load_missed(unsigned long load, unsigned long missed_updates, int idx)
+{
+	int j = 0;
+
+	if (!missed_updates)
+		return load;
+
+	if (missed_updates >= degrade_zero_ticks[idx])
+		return 0;
+
+	if (idx == 1)
+		return load >> missed_updates;
+
+	while (missed_updates) {
+		if (missed_updates % 2)
+			load = (load * degrade_factor[idx][j]) >> DEGRADE_SHIFT;
+
+		missed_updates >>= 1;
+		j++;
+	}
+	return load;
+}
+
+/*
+ * Update rq->cpu_load[] statistics. This function is usually called every
+ * scheduler tick (TICK_NSEC). With tickless idle this will not be called
+ * every tick. We fix it up based on jiffies.
+ */
+static void __update_cpu_load(struct rq *this_rq, unsigned long this_load,
+			      unsigned long pending_updates)
+{
+	int i, scale;
+
+	this_rq->nr_load_updates++;
+
+	/* Update our load: */
+	this_rq->cpu_load[0] = this_load; /* Fasttrack for idx 0 */
+	for (i = 1, scale = 2; i < CPU_LOAD_IDX_MAX; i++, scale += scale) {
+		unsigned long old_load, new_load;
+
+		/* scale is effectively 1 << i now, and >> i divides by scale */
+
+		old_load = this_rq->cpu_load[i];
+		old_load = decay_load_missed(old_load, pending_updates - 1, i);
+		new_load = this_load;
+		/*
+		 * Round up the averaging division if load is increasing. This
+		 * prevents us from getting stuck on 9 if the load is 10, for
+		 * example.
+		 */
+		if (new_load > old_load)
+			new_load += scale - 1;
+
+		this_rq->cpu_load[i] = (old_load * (scale - 1) + new_load) >> i;
+	}
+
+	sched_avg_update(this_rq);
+}
+
+#ifdef CONFIG_SMP
+static inline unsigned long get_rq_runnable_load(struct rq *rq)
+{
+	return rq->cfs.runnable_load_avg;
+}
+#else
+static inline unsigned long get_rq_runnable_load(struct rq *rq)
+{
+	return rq->load.weight;
+}
+#endif
+
+#ifdef CONFIG_NO_HZ_COMMON
+/*
+ * There is no sane way to deal with nohz on smp when using jiffies because the
+ * cpu doing the jiffies update might drift wrt the cpu doing the jiffy reading
+ * causing off-by-one errors in observed deltas; {0,2} instead of {1,1}.
+ *
+ * Therefore we cannot use the delta approach from the regular tick since that
+ * would seriously skew the load calculation. However we'll make do for those
+ * updates happening while idle (nohz_idle_balance) or coming out of idle
+ * (tick_nohz_idle_exit).
+ *
+ * This means we might still be one tick off for nohz periods.
+ */
+
+/*
+ * Called from nohz_idle_balance() to update the load ratings before doing the
+ * idle balance.
+ */
+void update_idle_cpu_load(struct rq *this_rq)
+{
+	unsigned long curr_jiffies = ACCESS_ONCE(jiffies);
+	unsigned long load = get_rq_runnable_load(this_rq);
+	unsigned long pending_updates;
+
+	/*
+	 * bail if there's load or we're actually up-to-date.
+	 */
+	if (load || curr_jiffies == this_rq->last_load_update_tick)
+		return;
+
+	pending_updates = curr_jiffies - this_rq->last_load_update_tick;
+	this_rq->last_load_update_tick = curr_jiffies;
+
+	__update_cpu_load(this_rq, load, pending_updates);
+}
+
+/*
+ * Called from tick_nohz_idle_exit() -- try and fix up the ticks we missed.
+ */
+void update_cpu_load_nohz(void)
+{
+	struct rq *this_rq = this_rq();
+	unsigned long curr_jiffies = ACCESS_ONCE(jiffies);
+	unsigned long pending_updates;
+
+	if (curr_jiffies == this_rq->last_load_update_tick)
+		return;
+
+	raw_spin_lock(&this_rq->lock);
+	pending_updates = curr_jiffies - this_rq->last_load_update_tick;
+	if (pending_updates) {
+		this_rq->last_load_update_tick = curr_jiffies;
+		/*
+		 * We were idle, this means load 0, the current load might be
+		 * !0 due to remote wakeups and the sort.
+		 */
+		__update_cpu_load(this_rq, 0, pending_updates);
+	}
+	raw_spin_unlock(&this_rq->lock);
+}
+#endif /* CONFIG_NO_HZ */
+
+/*
+ * Called from scheduler_tick()
+ */
+void update_cpu_load_active(struct rq *this_rq)
+{
+	unsigned long load = get_rq_runnable_load(this_rq);
+	/*
+	 * See the mess around update_idle_cpu_load() / update_cpu_load_nohz().
+	 */
+	this_rq->last_load_update_tick = jiffies;
+	__update_cpu_load(this_rq, load, 1);
+
+	calc_load_account_active(this_rq);
+}

kernel/sched/stats.c

@@ -0,0 +1,145 @@
+
+#include <linux/slab.h>
+#include <linux/fs.h>
+#include <linux/seq_file.h>
+#include <linux/proc_fs.h>
+
+#include "sched.h"
+
+/*
+ * bump this up when changing the output format or the meaning of an existing
+ * format, so that tools can adapt (or abort)
+ */
+#define SCHEDSTAT_VERSION 15
+
+static int show_schedstat(struct seq_file *seq, void *v)
+{
+	int cpu;
+	int mask_len = DIV_ROUND_UP(NR_CPUS, 32) * 9;
+	char *mask_str = kmalloc(mask_len, GFP_KERNEL);
+
+	if (mask_str == NULL)
+		return -ENOMEM;
+
+	if (v == (void *)1) {
+		seq_printf(seq, "version %d\n", SCHEDSTAT_VERSION);
+		seq_printf(seq, "timestamp %lu\n", jiffies);
+	} else {
+		struct rq *rq;
+#ifdef CONFIG_SMP
+		struct sched_domain *sd;
+		int dcount = 0;
+#endif
+		cpu = (unsigned long)(v - 2);
+		rq = cpu_rq(cpu);
+
+		/* runqueue-specific stats */
+		seq_printf(seq,
+		    "cpu%d %u 0 %u %u %u %u %llu %llu %lu",
+		    cpu, rq->yld_count,
+		    rq->sched_count, rq->sched_goidle,
+		    rq->ttwu_count, rq->ttwu_local,
+		    rq->rq_cpu_time,
+		    rq->rq_sched_info.run_delay, rq->rq_sched_info.pcount);
+
+		seq_printf(seq, "\n");
+
+#ifdef CONFIG_SMP
+		/* domain-specific stats */
+		rcu_read_lock();
+		for_each_domain(cpu, sd) {
+			enum cpu_idle_type itype;
+
+			cpumask_scnprintf(mask_str, mask_len,
+					  sched_domain_span(sd));
+			seq_printf(seq, "domain%d %s", dcount++, mask_str);
+			for (itype = CPU_IDLE; itype < CPU_MAX_IDLE_TYPES;
+					itype++) {
+				seq_printf(seq, " %u %u %u %u %u %u %u %u",
+				    sd->lb_count[itype],
+				    sd->lb_balanced[itype],
+				    sd->lb_failed[itype],
+				    sd->lb_imbalance[itype],
+				    sd->lb_gained[itype],
+				    sd->lb_hot_gained[itype],
+				    sd->lb_nobusyq[itype],
+				    sd->lb_nobusyg[itype]);
+			}
+			seq_printf(seq,
+				   " %u %u %u %u %u %u %u %u %u %u %u %u\n",
+			    sd->alb_count, sd->alb_failed, sd->alb_pushed,
+			    sd->sbe_count, sd->sbe_balanced, sd->sbe_pushed,
+			    sd->sbf_count, sd->sbf_balanced, sd->sbf_pushed,
+			    sd->ttwu_wake_remote, sd->ttwu_move_affine,
+			    sd->ttwu_move_balance);
+		}
+		rcu_read_unlock();
+#endif
+	}
+	kfree(mask_str);
+	return 0;
+}
+
+/*
+ * This itererator needs some explanation.
+ * It returns 1 for the header position.
+ * This means 2 is cpu 0.
+ * In a hotplugged system some cpus, including cpu 0, may be missing so we have
+ * to use cpumask_* to iterate over the cpus.
+ */
+static void *schedstat_start(struct seq_file *file, loff_t *offset)
+{
+	unsigned long n = *offset;
+
+	if (n == 0)
+		return (void *) 1;
+
+	n--;
+
+	if (n > 0)
+		n = cpumask_next(n - 1, cpu_online_mask);
+	else
+		n = cpumask_first(cpu_online_mask);
+
+	*offset = n + 1;
+
+	if (n < nr_cpu_ids)
+		return (void *)(unsigned long)(n + 2);
+	return NULL;
+}
+
+static void *schedstat_next(struct seq_file *file, void *data, loff_t *offset)
+{
+	(*offset)++;
+	return schedstat_start(file, offset);
+}
+
+static void schedstat_stop(struct seq_file *file, void *data)
+{
+}
+
+static const struct seq_operations schedstat_sops = {
+	.start = schedstat_start,
+	.next  = schedstat_next,
+	.stop  = schedstat_stop,
+	.show  = show_schedstat,
+};
+
+static int schedstat_open(struct inode *inode, struct file *file)
+{
+	return seq_open(file, &schedstat_sops);
+}
+
+static const struct file_operations proc_schedstat_operations = {
+	.open    = schedstat_open,
+	.read    = seq_read,
+	.llseek  = seq_lseek,
+	.release = seq_release,
+};
+
+static int __init proc_schedstat_init(void)
+{
+	proc_create("schedstat", 0, NULL, &proc_schedstat_operations);
+	return 0;
+}
+subsys_initcall(proc_schedstat_init);

kernel/sched/stats.h

@@ -0,0 +1,267 @@
+
+#ifdef CONFIG_SCHEDSTATS
+
+/*
+ * Expects runqueue lock to be held for atomicity of update
+ */
+static inline void
+rq_sched_info_arrive(struct rq *rq, unsigned long long delta)
+{
+	if (rq) {
+		rq->rq_sched_info.run_delay += delta;
+		rq->rq_sched_info.pcount++;
+	}
+}
+
+/*
+ * Expects runqueue lock to be held for atomicity of update
+ */
+static inline void
+rq_sched_info_depart(struct rq *rq, unsigned long long delta)
+{
+	if (rq)
+		rq->rq_cpu_time += delta;
+}
+
+static inline void
+rq_sched_info_dequeued(struct rq *rq, unsigned long long delta)
+{
+	if (rq)
+		rq->rq_sched_info.run_delay += delta;
+}
+# define schedstat_inc(rq, field)	do { (rq)->field++; } while (0)
+# define schedstat_add(rq, field, amt)	do { (rq)->field += (amt); } while (0)
+# define schedstat_set(var, val)	do { var = (val); } while (0)
+#else /* !CONFIG_SCHEDSTATS */
+static inline void
+rq_sched_info_arrive(struct rq *rq, unsigned long long delta)
+{}
+static inline void
+rq_sched_info_dequeued(struct rq *rq, unsigned long long delta)
+{}
+static inline void
+rq_sched_info_depart(struct rq *rq, unsigned long long delta)
+{}
+# define schedstat_inc(rq, field)	do { } while (0)
+# define schedstat_add(rq, field, amt)	do { } while (0)
+# define schedstat_set(var, val)	do { } while (0)
+#endif
+
+#if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT)
+static inline void sched_info_reset_dequeued(struct task_struct *t)
+{
+	t->sched_info.last_queued = 0;
+}
+
+/*
+ * We are interested in knowing how long it was from the *first* time a
+ * task was queued to the time that it finally hit a cpu, we call this routine
+ * from dequeue_task() to account for possible rq->clock skew across cpus. The
+ * delta taken on each cpu would annul the skew.
+ */
+static inline void sched_info_dequeued(struct rq *rq, struct task_struct *t)
+{
+	unsigned long long now = rq_clock(rq), delta = 0;
+
+	if (unlikely(sched_info_on()))
+		if (t->sched_info.last_queued)
+			delta = now - t->sched_info.last_queued;
+	sched_info_reset_dequeued(t);
+	t->sched_info.run_delay += delta;
+
+	rq_sched_info_dequeued(rq, delta);
+}
+
+/*
+ * Called when a task finally hits the cpu.  We can now calculate how
+ * long it was waiting to run.  We also note when it began so that we
+ * can keep stats on how long its timeslice is.
+ */
+static void sched_info_arrive(struct rq *rq, struct task_struct *t)
+{
+	unsigned long long now = rq_clock(rq), delta = 0;
+
+	if (t->sched_info.last_queued)
+		delta = now - t->sched_info.last_queued;
+	sched_info_reset_dequeued(t);
+	t->sched_info.run_delay += delta;
+	t->sched_info.last_arrival = now;
+	t->sched_info.pcount++;
+
+	rq_sched_info_arrive(rq, delta);
+}
+
+/*
+ * This function is only called from enqueue_task(), but also only updates
+ * the timestamp if it is already not set.  It's assumed that
+ * sched_info_dequeued() will clear that stamp when appropriate.
+ */
+static inline void sched_info_queued(struct rq *rq, struct task_struct *t)
+{
+	if (unlikely(sched_info_on()))
+		if (!t->sched_info.last_queued)
+			t->sched_info.last_queued = rq_clock(rq);
+}
+
+/*
+ * Called when a process ceases being the active-running process involuntarily
+ * due, typically, to expiring its time slice (this may also be called when
+ * switching to the idle task).  Now we can calculate how long we ran.
+ * Also, if the process is still in the TASK_RUNNING state, call
+ * sched_info_queued() to mark that it has now again started waiting on
+ * the runqueue.
+ */
+static inline void sched_info_depart(struct rq *rq, struct task_struct *t)
+{
+	unsigned long long delta = rq_clock(rq) -
+					t->sched_info.last_arrival;
+
+	rq_sched_info_depart(rq, delta);
+
+	if (t->state == TASK_RUNNING)
+		sched_info_queued(rq, t);
+}
+
+/*
+ * Called when tasks are switched involuntarily due, typically, to expiring
+ * their time slice.  (This may also be called when switching to or from
+ * the idle task.)  We are only called when prev != next.
+ */
+static inline void
+__sched_info_switch(struct rq *rq,
+		    struct task_struct *prev, struct task_struct *next)
+{
+	/*
+	 * prev now departs the cpu.  It's not interesting to record
+	 * stats about how efficient we were at scheduling the idle
+	 * process, however.
+	 */
+	if (prev != rq->idle)
+		sched_info_depart(rq, prev);
+
+	if (next != rq->idle)
+		sched_info_arrive(rq, next);
+}
+static inline void
+sched_info_switch(struct rq *rq,
+		  struct task_struct *prev, struct task_struct *next)
+{
+	if (unlikely(sched_info_on()))
+		__sched_info_switch(rq, prev, next);
+}
+#else
+#define sched_info_queued(rq, t)		do { } while (0)
+#define sched_info_reset_dequeued(t)	do { } while (0)
+#define sched_info_dequeued(rq, t)		do { } while (0)
+#define sched_info_depart(rq, t)		do { } while (0)
+#define sched_info_arrive(rq, next)		do { } while (0)
+#define sched_info_switch(rq, t, next)		do { } while (0)
+#endif /* CONFIG_SCHEDSTATS || CONFIG_TASK_DELAY_ACCT */
+
+/*
+ * The following are functions that support scheduler-internal time accounting.
+ * These functions are generally called at the timer tick.  None of this depends
+ * on CONFIG_SCHEDSTATS.
+ */
+
+/**
+ * cputimer_running - return true if cputimer is running
+ *
+ * @tsk:	Pointer to target task.
+ */
+static inline bool cputimer_running(struct task_struct *tsk)
+
+{
+	struct thread_group_cputimer *cputimer = &tsk->signal->cputimer;
+
+	if (!cputimer->running)
+		return false;
+
+	/*
+	 * After we flush the task's sum_exec_runtime to sig->sum_sched_runtime
+	 * in __exit_signal(), we won't account to the signal struct further
+	 * cputime consumed by that task, even though the task can still be
+	 * ticking after __exit_signal().
+	 *
+	 * In order to keep a consistent behaviour between thread group cputime
+	 * and thread group cputimer accounting, lets also ignore the cputime
+	 * elapsing after __exit_signal() in any thread group timer running.
+	 *
+	 * This makes sure that POSIX CPU clocks and timers are synchronized, so
+	 * that a POSIX CPU timer won't expire while the corresponding POSIX CPU
+	 * clock delta is behind the expiring timer value.
+	 */
+	if (unlikely(!tsk->sighand))
+		return false;
+
+	return true;
+}
+
+/**
+ * account_group_user_time - Maintain utime for a thread group.
+ *
+ * @tsk:	Pointer to task structure.
+ * @cputime:	Time value by which to increment the utime field of the
+ *		thread_group_cputime structure.
+ *
+ * If thread group time is being maintained, get the structure for the
+ * running CPU and update the utime field there.
+ */
+static inline void account_group_user_time(struct task_struct *tsk,
+					   cputime_t cputime)
+{
+	struct thread_group_cputimer *cputimer = &tsk->signal->cputimer;
+
+	if (!cputimer_running(tsk))
+		return;
+
+	raw_spin_lock(&cputimer->lock);
+	cputimer->cputime.utime += cputime;
+	raw_spin_unlock(&cputimer->lock);
+}
+
+/**
+ * account_group_system_time - Maintain stime for a thread group.
+ *
+ * @tsk:	Pointer to task structure.
+ * @cputime:	Time value by which to increment the stime field of the
+ *		thread_group_cputime structure.
+ *
+ * If thread group time is being maintained, get the structure for the
+ * running CPU and update the stime field there.
+ */
+static inline void account_group_system_time(struct task_struct *tsk,
+					     cputime_t cputime)
+{
+	struct thread_group_cputimer *cputimer = &tsk->signal->cputimer;
+
+	if (!cputimer_running(tsk))
+		return;
+
+	raw_spin_lock(&cputimer->lock);
+	cputimer->cputime.stime += cputime;
+	raw_spin_unlock(&cputimer->lock);
+}
+
+/**
+ * account_group_exec_runtime - Maintain exec runtime for a thread group.
+ *
+ * @tsk:	Pointer to task structure.
+ * @ns:		Time value by which to increment the sum_exec_runtime field
+ *		of the thread_group_cputime structure.
+ *
+ * If thread group time is being maintained, get the structure for the
+ * running CPU and update the sum_exec_runtime field there.
+ */
+static inline void account_group_exec_runtime(struct task_struct *tsk,
+					      unsigned long long ns)
+{
+	struct thread_group_cputimer *cputimer = &tsk->signal->cputimer;
+
+	if (!cputimer_running(tsk))
+		return;
+
+	raw_spin_lock(&cputimer->lock);
+	cputimer->cputime.sum_exec_runtime += ns;
+	raw_spin_unlock(&cputimer->lock);
+}

kernel/sched/stop_task.c

@@ -0,0 +1,136 @@
+#include "sched.h"
+
+/*
+ * stop-task scheduling class.
+ *
+ * The stop task is the highest priority task in the system, it preempts
+ * everything and will be preempted by nothing.
+ *
+ * See kernel/stop_machine.c
+ */
+
+#ifdef CONFIG_SMP
+static int
+select_task_rq_stop(struct task_struct *p, int cpu, int sd_flag, int flags)
+{
+	return task_cpu(p); /* stop tasks as never migrate */
+}
+#endif /* CONFIG_SMP */
+
+static void
+check_preempt_curr_stop(struct rq *rq, struct task_struct *p, int flags)
+{
+	/* we're never preempted */
+}
+
+static struct task_struct *
+pick_next_task_stop(struct rq *rq, struct task_struct *prev)
+{
+	struct task_struct *stop = rq->stop;
+
+	if (!stop || !task_on_rq_queued(stop))
+		return NULL;
+
+	put_prev_task(rq, prev);
+
+	stop->se.exec_start = rq_clock_task(rq);
+
+	return stop;
+}
+
+static void
+enqueue_task_stop(struct rq *rq, struct task_struct *p, int flags)
+{
+	add_nr_running(rq, 1);
+}
+
+static void
+dequeue_task_stop(struct rq *rq, struct task_struct *p, int flags)
+{
+	sub_nr_running(rq, 1);
+}
+
+static void yield_task_stop(struct rq *rq)
+{
+	BUG(); /* the stop task should never yield, its pointless. */
+}
+
+static void put_prev_task_stop(struct rq *rq, struct task_struct *prev)
+{
+	struct task_struct *curr = rq->curr;
+	u64 delta_exec;
+
+	delta_exec = rq_clock_task(rq) - curr->se.exec_start;
+	if (unlikely((s64)delta_exec < 0))
+		delta_exec = 0;
+
+	schedstat_set(curr->se.statistics.exec_max,
+			max(curr->se.statistics.exec_max, delta_exec));
+
+	curr->se.sum_exec_runtime += delta_exec;
+	account_group_exec_runtime(curr, delta_exec);
+
+	curr->se.exec_start = rq_clock_task(rq);
+	cpuacct_charge(curr, delta_exec);
+}
+
+static void task_tick_stop(struct rq *rq, struct task_struct *curr, int queued)
+{
+}
+
+static void set_curr_task_stop(struct rq *rq)
+{
+	struct task_struct *stop = rq->stop;
+
+	stop->se.exec_start = rq_clock_task(rq);
+}
+
+static void switched_to_stop(struct rq *rq, struct task_struct *p)
+{
+	BUG(); /* its impossible to change to this class */
+}
+
+static void
+prio_changed_stop(struct rq *rq, struct task_struct *p, int oldprio)
+{
+	BUG(); /* how!?, what priority? */
+}
+
+static unsigned int
+get_rr_interval_stop(struct rq *rq, struct task_struct *task)
+{
+	return 0;
+}
+
+static void update_curr_stop(struct rq *rq)
+{
+}
+
+/*
+ * Simple, special scheduling class for the per-CPU stop tasks:
+ */
+const struct sched_class stop_sched_class = {
+	.next			= &dl_sched_class,
+
+	.enqueue_task		= enqueue_task_stop,
+	.dequeue_task		= dequeue_task_stop,
+	.yield_task		= yield_task_stop,
+
+	.check_preempt_curr	= check_preempt_curr_stop,
+
+	.pick_next_task		= pick_next_task_stop,
+	.put_prev_task		= put_prev_task_stop,
+
+#ifdef CONFIG_SMP
+	.select_task_rq		= select_task_rq_stop,
+#endif
+
+	.set_curr_task          = set_curr_task_stop,
+	.task_tick		= task_tick_stop,
+
+	.get_rr_interval	= get_rr_interval_stop,
+
+	.prio_changed		= prio_changed_stop,
+	.switched_to		= switched_to_stop,
+	.update_curr		= update_curr_stop,
+};

kernel/sched/wait.c

@@ -0,0 +1,619 @@
+/*
+ * Generic waiting primitives.
+ *
+ * (C) 2004 Nadia Yvette Chambers, Oracle
+ */
+#include <linux/init.h>
+#include <linux/export.h>
+#include <linux/sched.h>
+#include <linux/mm.h>
+#include <linux/wait.h>
+#include <linux/hash.h>
+
+void __init_waitqueue_head(wait_queue_head_t *q, const char *name, struct lock_class_key *key)
+{
+	spin_lock_init(&q->lock);
+	lockdep_set_class_and_name(&q->lock, key, name);
+	INIT_LIST_HEAD(&q->task_list);
+}
+
+EXPORT_SYMBOL(__init_waitqueue_head);
+
+void add_wait_queue(wait_queue_head_t *q, wait_queue_t *wait)
+{
+	unsigned long flags;
+
+	wait->flags &= ~WQ_FLAG_EXCLUSIVE;
+	spin_lock_irqsave(&q->lock, flags);
+	__add_wait_queue(q, wait);
+	spin_unlock_irqrestore(&q->lock, flags);
+}
+EXPORT_SYMBOL(add_wait_queue);
+
+void add_wait_queue_exclusive(wait_queue_head_t *q, wait_queue_t *wait)
+{
+	unsigned long flags;
+
+	wait->flags |= WQ_FLAG_EXCLUSIVE;
+	spin_lock_irqsave(&q->lock, flags);
+	__add_wait_queue_tail(q, wait);
+	spin_unlock_irqrestore(&q->lock, flags);
+}
+EXPORT_SYMBOL(add_wait_queue_exclusive);
+
+void remove_wait_queue(wait_queue_head_t *q, wait_queue_t *wait)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&q->lock, flags);
+	__remove_wait_queue(q, wait);
+	spin_unlock_irqrestore(&q->lock, flags);
+}
+EXPORT_SYMBOL(remove_wait_queue);
+
+
+/*
+ * The core wakeup function. Non-exclusive wakeups (nr_exclusive == 0) just
+ * wake everything up. If it's an exclusive wakeup (nr_exclusive == small +ve
+ * number) then we wake all the non-exclusive tasks and one exclusive task.
+ *
+ * There are circumstances in which we can try to wake a task which has already
+ * started to run but is not in state TASK_RUNNING. try_to_wake_up() returns
+ * zero in this (rare) case, and we handle it by continuing to scan the queue.
+ */
+static void __wake_up_common(wait_queue_head_t *q, unsigned int mode,
+			int nr_exclusive, int wake_flags, void *key)
+{
+	wait_queue_t *curr, *next;
+
+	list_for_each_entry_safe(curr, next, &q->task_list, task_list) {
+		unsigned flags = curr->flags;
+
+		if (curr->func(curr, mode, wake_flags, key) &&
+				(flags & WQ_FLAG_EXCLUSIVE) && !--nr_exclusive)
+			break;
+	}
+}
+
+/**
+ * __wake_up - wake up threads blocked on a waitqueue.
+ * @q: the waitqueue
+ * @mode: which threads
+ * @nr_exclusive: how many wake-one or wake-many threads to wake up
+ * @key: is directly passed to the wakeup function
+ *
+ * It may be assumed that this function implies a write memory barrier before
+ * changing the task state if and only if any tasks are woken up.
+ */
+void __wake_up(wait_queue_head_t *q, unsigned int mode,
+			int nr_exclusive, void *key)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&q->lock, flags);
+	__wake_up_common(q, mode, nr_exclusive, 0, key);
+	spin_unlock_irqrestore(&q->lock, flags);
+}
+EXPORT_SYMBOL(__wake_up);
+
+/*
+ * Same as __wake_up but called with the spinlock in wait_queue_head_t held.
+ */
+void __wake_up_locked(wait_queue_head_t *q, unsigned int mode, int nr)
+{
+	__wake_up_common(q, mode, nr, 0, NULL);
+}
+EXPORT_SYMBOL_GPL(__wake_up_locked);
+
+void __wake_up_locked_key(wait_queue_head_t *q, unsigned int mode, void *key)
+{
+	__wake_up_common(q, mode, 1, 0, key);
+}
+EXPORT_SYMBOL_GPL(__wake_up_locked_key);
+
+/**
+ * __wake_up_sync_key - wake up threads blocked on a waitqueue.
+ * @q: the waitqueue
+ * @mode: which threads
+ * @nr_exclusive: how many wake-one or wake-many threads to wake up
+ * @key: opaque value to be passed to wakeup targets
+ *
+ * The sync wakeup differs that the waker knows that it will schedule
+ * away soon, so while the target thread will be woken up, it will not
+ * be migrated to another CPU - ie. the two threads are 'synchronized'
+ * with each other. This can prevent needless bouncing between CPUs.
+ *
+ * On UP it can prevent extra preemption.
+ *
+ * It may be assumed that this function implies a write memory barrier before
+ * changing the task state if and only if any tasks are woken up.
+ */
+void __wake_up_sync_key(wait_queue_head_t *q, unsigned int mode,
+			int nr_exclusive, void *key)
+{
+	unsigned long flags;
+	int wake_flags = 1; /* XXX WF_SYNC */
+
+	if (unlikely(!q))
+		return;
+
+	if (unlikely(nr_exclusive != 1))
+		wake_flags = 0;
+
+	spin_lock_irqsave(&q->lock, flags);
+	__wake_up_common(q, mode, nr_exclusive, wake_flags, key);
+	spin_unlock_irqrestore(&q->lock, flags);
+}
+EXPORT_SYMBOL_GPL(__wake_up_sync_key);
+
+/*
+ * __wake_up_sync - see __wake_up_sync_key()
+ */
+void __wake_up_sync(wait_queue_head_t *q, unsigned int mode, int nr_exclusive)
+{
+	__wake_up_sync_key(q, mode, nr_exclusive, NULL);
+}
+EXPORT_SYMBOL_GPL(__wake_up_sync);	/* For internal use only */
+
+/*
+ * Note: we use "set_current_state()" _after_ the wait-queue add,
+ * because we need a memory barrier there on SMP, so that any
+ * wake-function that tests for the wait-queue being active
+ * will be guaranteed to see waitqueue addition _or_ subsequent
+ * tests in this thread will see the wakeup having taken place.
+ *
+ * The spin_unlock() itself is semi-permeable and only protects
+ * one way (it only protects stuff inside the critical region and
+ * stops them from bleeding out - it would still allow subsequent
+ * loads to move into the critical region).
+ */
+void
+prepare_to_wait(wait_queue_head_t *q, wait_queue_t *wait, int state)
+{
+	unsigned long flags;
+
+	wait->flags &= ~WQ_FLAG_EXCLUSIVE;
+	spin_lock_irqsave(&q->lock, flags);
+	if (list_empty(&wait->task_list))
+		__add_wait_queue(q, wait);
+	set_current_state(state);
+	spin_unlock_irqrestore(&q->lock, flags);
+}
+EXPORT_SYMBOL(prepare_to_wait);
+
+void
+prepare_to_wait_exclusive(wait_queue_head_t *q, wait_queue_t *wait, int state)
+{
+	unsigned long flags;
+
+	wait->flags |= WQ_FLAG_EXCLUSIVE;
+	spin_lock_irqsave(&q->lock, flags);
+	if (list_empty(&wait->task_list))
+		__add_wait_queue_tail(q, wait);
+	set_current_state(state);
+	spin_unlock_irqrestore(&q->lock, flags);
+}
+EXPORT_SYMBOL(prepare_to_wait_exclusive);
+
+long prepare_to_wait_event(wait_queue_head_t *q, wait_queue_t *wait, int state)
+{
+	unsigned long flags;
+
+	if (signal_pending_state(state, current))
+		return -ERESTARTSYS;
+
+	wait->private = current;
+	wait->func = autoremove_wake_function;
+
+	spin_lock_irqsave(&q->lock, flags);
+	if (list_empty(&wait->task_list)) {
+		if (wait->flags & WQ_FLAG_EXCLUSIVE)
+			__add_wait_queue_tail(q, wait);
+		else
+			__add_wait_queue(q, wait);
+	}
+	set_current_state(state);
+	spin_unlock_irqrestore(&q->lock, flags);
+
+	return 0;
+}
+EXPORT_SYMBOL(prepare_to_wait_event);
+
+/**
+ * finish_wait - clean up after waiting in a queue
+ * @q: waitqueue waited on
+ * @wait: wait descriptor
+ *
+ * Sets current thread back to running state and removes
+ * the wait descriptor from the given waitqueue if still
+ * queued.
+ */
+void finish_wait(wait_queue_head_t *q, wait_queue_t *wait)
+{
+	unsigned long flags;
+
+	__set_current_state(TASK_RUNNING);
+	/*
+	 * We can check for list emptiness outside the lock
+	 * IFF:
+	 *  - we use the "careful" check that verifies both
+	 *    the next and prev pointers, so that there cannot
+	 *    be any half-pending updates in progress on other
+	 *    CPU's that we haven't seen yet (and that might
+	 *    still change the stack area.
+	 * and
+	 *  - all other users take the lock (ie we can only
+	 *    have _one_ other CPU that looks at or modifies
+	 *    the list).
+	 */
+	if (!list_empty_careful(&wait->task_list)) {
+		spin_lock_irqsave(&q->lock, flags);
+		list_del_init(&wait->task_list);
+		spin_unlock_irqrestore(&q->lock, flags);
+	}
+}
+EXPORT_SYMBOL(finish_wait);
+
+/**
+ * abort_exclusive_wait - abort exclusive waiting in a queue
+ * @q: waitqueue waited on
+ * @wait: wait descriptor
+ * @mode: runstate of the waiter to be woken
+ * @key: key to identify a wait bit queue or %NULL
+ *
+ * Sets current thread back to running state and removes
+ * the wait descriptor from the given waitqueue if still
+ * queued.
+ *
+ * Wakes up the next waiter if the caller is concurrently
+ * woken up through the queue.
+ *
+ * This prevents waiter starvation where an exclusive waiter
+ * aborts and is woken up concurrently and no one wakes up
+ * the next waiter.
+ */
+void abort_exclusive_wait(wait_queue_head_t *q, wait_queue_t *wait,
+			unsigned int mode, void *key)
+{
+	unsigned long flags;
+
+	__set_current_state(TASK_RUNNING);
+	spin_lock_irqsave(&q->lock, flags);
+	if (!list_empty(&wait->task_list))
+		list_del_init(&wait->task_list);
+	else if (waitqueue_active(q))
+		__wake_up_locked_key(q, mode, key);
+	spin_unlock_irqrestore(&q->lock, flags);
+}
+EXPORT_SYMBOL(abort_exclusive_wait);
+
+int autoremove_wake_function(wait_queue_t *wait, unsigned mode, int sync, void *key)
+{
+	int ret = default_wake_function(wait, mode, sync, key);
+
+	if (ret)
+		list_del_init(&wait->task_list);
+	return ret;
+}
+EXPORT_SYMBOL(autoremove_wake_function);
+
+
+/*
+ * DEFINE_WAIT_FUNC(wait, woken_wake_func);
+ *
+ * add_wait_queue(&wq, &wait);
+ * for (;;) {
+ *     if (condition)
+ *         break;
+ *
+ *     p->state = mode;				condition = true;
+ *     smp_mb(); // A				smp_wmb(); // C
+ *     if (!wait->flags & WQ_FLAG_WOKEN)	wait->flags |= WQ_FLAG_WOKEN;
+ *         schedule()				try_to_wake_up();
+ *     p->state = TASK_RUNNING;		    ~~~~~~~~~~~~~~~~~~
+ *     wait->flags &= ~WQ_FLAG_WOKEN;		condition = true;
+ *     smp_mb() // B				smp_wmb(); // C
+ *						wait->flags |= WQ_FLAG_WOKEN;
+ * }
+ * remove_wait_queue(&wq, &wait);
+ *
+ */
+long wait_woken(wait_queue_t *wait, unsigned mode, long timeout)
+{
+	set_current_state(mode); /* A */
+	/*
+	 * The above implies an smp_mb(), which matches with the smp_wmb() from
+	 * woken_wake_function() such that if we observe WQ_FLAG_WOKEN we must
+	 * also observe all state before the wakeup.
+	 */
+	if (!(wait->flags & WQ_FLAG_WOKEN))
+		timeout = schedule_timeout(timeout);
+	__set_current_state(TASK_RUNNING);
+
+	/*
+	 * The below implies an smp_mb(), it too pairs with the smp_wmb() from
+	 * woken_wake_function() such that we must either observe the wait
+	 * condition being true _OR_ WQ_FLAG_WOKEN such that we will not miss
+	 * an event.
+	 */
+	set_mb(wait->flags, wait->flags & ~WQ_FLAG_WOKEN); /* B */
+
+	return timeout;
+}
+EXPORT_SYMBOL(wait_woken);
+
+int woken_wake_function(wait_queue_t *wait, unsigned mode, int sync, void *key)
+{
+	/*
+	 * Although this function is called under waitqueue lock, LOCK
+	 * doesn't imply write barrier and the users expects write
+	 * barrier semantics on wakeup functions.  The following
+	 * smp_wmb() is equivalent to smp_wmb() in try_to_wake_up()
+	 * and is paired with set_mb() in wait_woken().
+	 */
+	smp_wmb(); /* C */
+	wait->flags |= WQ_FLAG_WOKEN;
+
+	return default_wake_function(wait, mode, sync, key);
+}
+EXPORT_SYMBOL(woken_wake_function);
+
+int wake_bit_function(wait_queue_t *wait, unsigned mode, int sync, void *arg)
+{
+	struct wait_bit_key *key = arg;
+	struct wait_bit_queue *wait_bit
+		= container_of(wait, struct wait_bit_queue, wait);
+
+	if (wait_bit->key.flags != key->flags ||
+			wait_bit->key.bit_nr != key->bit_nr ||
+			test_bit(key->bit_nr, key->flags))
+		return 0;
+	else
+		return autoremove_wake_function(wait, mode, sync, key);
+}
+EXPORT_SYMBOL(wake_bit_function);
+
+/*
+ * To allow interruptible waiting and asynchronous (i.e. nonblocking)
+ * waiting, the actions of __wait_on_bit() and __wait_on_bit_lock() are
+ * permitted return codes. Nonzero return codes halt waiting and return.
+ */
+int __sched
+__wait_on_bit(wait_queue_head_t *wq, struct wait_bit_queue *q,
+	      wait_bit_action_f *action, unsigned mode)
+{
+	int ret = 0;
+
+	do {
+		prepare_to_wait(wq, &q->wait, mode);
+		if (test_bit(q->key.bit_nr, q->key.flags))
+			ret = (*action)(&q->key, mode);
+	} while (test_bit(q->key.bit_nr, q->key.flags) && !ret);
+	finish_wait(wq, &q->wait);
+	return ret;
+}
+EXPORT_SYMBOL(__wait_on_bit);
+
+int __sched out_of_line_wait_on_bit(void *word, int bit,
+				    wait_bit_action_f *action, unsigned mode)
+{
+	wait_queue_head_t *wq = bit_waitqueue(word, bit);
+	DEFINE_WAIT_BIT(wait, word, bit);
+
+	return __wait_on_bit(wq, &wait, action, mode);
+}
+EXPORT_SYMBOL(out_of_line_wait_on_bit);
+
+int __sched out_of_line_wait_on_bit_timeout(
+	void *word, int bit, wait_bit_action_f *action,
+	unsigned mode, unsigned long timeout)
+{
+	wait_queue_head_t *wq = bit_waitqueue(word, bit);
+	DEFINE_WAIT_BIT(wait, word, bit);
+
+	wait.key.timeout = jiffies + timeout;
+	return __wait_on_bit(wq, &wait, action, mode);
+}
+EXPORT_SYMBOL_GPL(out_of_line_wait_on_bit_timeout);
+
+int __sched
+__wait_on_bit_lock(wait_queue_head_t *wq, struct wait_bit_queue *q,
+			wait_bit_action_f *action, unsigned mode)
+{
+	do {
+		int ret;
+
+		prepare_to_wait_exclusive(wq, &q->wait, mode);
+		if (!test_bit(q->key.bit_nr, q->key.flags))
+			continue;
+		ret = action(&q->key, mode);
+		if (!ret)
+			continue;
+		abort_exclusive_wait(wq, &q->wait, mode, &q->key);
+		return ret;
+	} while (test_and_set_bit(q->key.bit_nr, q->key.flags));
+	finish_wait(wq, &q->wait);
+	return 0;
+}
+EXPORT_SYMBOL(__wait_on_bit_lock);
+
+int __sched out_of_line_wait_on_bit_lock(void *word, int bit,
+					 wait_bit_action_f *action, unsigned mode)
+{
+	wait_queue_head_t *wq = bit_waitqueue(word, bit);
+	DEFINE_WAIT_BIT(wait, word, bit);
+
+	return __wait_on_bit_lock(wq, &wait, action, mode);
+}
+EXPORT_SYMBOL(out_of_line_wait_on_bit_lock);
+
+void __wake_up_bit(wait_queue_head_t *wq, void *word, int bit)
+{
+	struct wait_bit_key key = __WAIT_BIT_KEY_INITIALIZER(word, bit);
+	if (waitqueue_active(wq))
+		__wake_up(wq, TASK_NORMAL, 1, &key);
+}
+EXPORT_SYMBOL(__wake_up_bit);
+
+/**
+ * wake_up_bit - wake up a waiter on a bit
+ * @word: the word being waited on, a kernel virtual address
+ * @bit: the bit of the word being waited on
+ *
+ * There is a standard hashed waitqueue table for generic use. This
+ * is the part of the hashtable's accessor API that wakes up waiters
+ * on a bit. For instance, if one were to have waiters on a bitflag,
+ * one would call wake_up_bit() after clearing the bit.
+ *
+ * In order for this to function properly, as it uses waitqueue_active()
+ * internally, some kind of memory barrier must be done prior to calling
+ * this. Typically, this will be smp_mb__after_atomic(), but in some
+ * cases where bitflags are manipulated non-atomically under a lock, one
+ * may need to use a less regular barrier, such fs/inode.c's smp_mb(),
+ * because spin_unlock() does not guarantee a memory barrier.
+ */
+void wake_up_bit(void *word, int bit)
+{
+	__wake_up_bit(bit_waitqueue(word, bit), word, bit);
+}
+EXPORT_SYMBOL(wake_up_bit);
+
+wait_queue_head_t *bit_waitqueue(void *word, int bit)
+{
+	const int shift = BITS_PER_LONG == 32 ? 5 : 6;
+	const struct zone *zone = page_zone(virt_to_page(word));
+	unsigned long val = (unsigned long)word << shift | bit;
+
+	return &zone->wait_table[hash_long(val, zone->wait_table_bits)];
+}
+EXPORT_SYMBOL(bit_waitqueue);
+
+/*
+ * Manipulate the atomic_t address to produce a better bit waitqueue table hash
+ * index (we're keying off bit -1, but that would produce a horrible hash
+ * value).
+ */
+static inline wait_queue_head_t *atomic_t_waitqueue(atomic_t *p)
+{
+	if (BITS_PER_LONG == 64) {
+		unsigned long q = (unsigned long)p;
+		return bit_waitqueue((void *)(q & ~1), q & 1);
+	}
+	return bit_waitqueue(p, 0);
+}
+
+static int wake_atomic_t_function(wait_queue_t *wait, unsigned mode, int sync,
+				  void *arg)
+{
+	struct wait_bit_key *key = arg;
+	struct wait_bit_queue *wait_bit
+		= container_of(wait, struct wait_bit_queue, wait);
+	atomic_t *val = key->flags;
+
+	if (wait_bit->key.flags != key->flags ||
+	    wait_bit->key.bit_nr != key->bit_nr ||
+	    atomic_read(val) != 0)
+		return 0;
+	return autoremove_wake_function(wait, mode, sync, key);
+}
+
+/*
+ * To allow interruptible waiting and asynchronous (i.e. nonblocking) waiting,
+ * the actions of __wait_on_atomic_t() are permitted return codes.  Nonzero
+ * return codes halt waiting and return.
+ */
+static __sched
+int __wait_on_atomic_t(wait_queue_head_t *wq, struct wait_bit_queue *q,
+		       int (*action)(atomic_t *), unsigned mode)
+{
+	atomic_t *val;
+	int ret = 0;
+
+	do {
+		prepare_to_wait(wq, &q->wait, mode);
+		val = q->key.flags;
+		if (atomic_read(val) == 0)
+			break;
+		ret = (*action)(val);
+	} while (!ret && atomic_read(val) != 0);
+	finish_wait(wq, &q->wait);
+	return ret;
+}
+
+#define DEFINE_WAIT_ATOMIC_T(name, p)					\
+	struct wait_bit_queue name = {					\
+		.key = __WAIT_ATOMIC_T_KEY_INITIALIZER(p),		\
+		.wait	= {						\
+			.private	= current,			\
+			.func		= wake_atomic_t_function,	\
+			.task_list	=				\
+				LIST_HEAD_INIT((name).wait.task_list),	\
+		},							\
+	}
+
+__sched int out_of_line_wait_on_atomic_t(atomic_t *p, int (*action)(atomic_t *),
+					 unsigned mode)
+{
+	wait_queue_head_t *wq = atomic_t_waitqueue(p);
+	DEFINE_WAIT_ATOMIC_T(wait, p);
+
+	return __wait_on_atomic_t(wq, &wait, action, mode);
+}
+EXPORT_SYMBOL(out_of_line_wait_on_atomic_t);
+
+/**
+ * wake_up_atomic_t - Wake up a waiter on a atomic_t
+ * @p: The atomic_t being waited on, a kernel virtual address
+ *
+ * Wake up anyone waiting for the atomic_t to go to zero.
+ *
+ * Abuse the bit-waker function and its waitqueue hash table set (the atomic_t
+ * check is done by the waiter's wake function, not the by the waker itself).
+ */
+void wake_up_atomic_t(atomic_t *p)
+{
+	__wake_up_bit(atomic_t_waitqueue(p), p, WAIT_ATOMIC_T_BIT_NR);
+}
+EXPORT_SYMBOL(wake_up_atomic_t);
+
+__sched int bit_wait(struct wait_bit_key *word, int mode)
+{
+	schedule();
+	if (signal_pending_state(mode, current))
+		return -EINTR;
+	return 0;
+}
+EXPORT_SYMBOL(bit_wait);
+
+__sched int bit_wait_io(struct wait_bit_key *word, int mode)
+{
+	io_schedule();
+	if (signal_pending_state(mode, current))
+		return -EINTR;
+	return 0;
+}
+EXPORT_SYMBOL(bit_wait_io);
+
+__sched int bit_wait_timeout(struct wait_bit_key *word, int mode)
+{
+	unsigned long now = ACCESS_ONCE(jiffies);
+	if (time_after_eq(now, word->timeout))
+		return -EAGAIN;
+	schedule_timeout(word->timeout - now);
+	if (signal_pending_state(mode, current))
+		return -EINTR;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(bit_wait_timeout);
+
+__sched int bit_wait_io_timeout(struct wait_bit_key *word, int mode)
+{
+	unsigned long now = ACCESS_ONCE(jiffies);
+	if (time_after_eq(now, word->timeout))
+		return -EAGAIN;
+	io_schedule_timeout(word->timeout - now);
+	if (signal_pending_state(mode, current))
+		return -EINTR;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(bit_wait_io_timeout);