Merge branch 'sched/core' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip into cputime-tip

Conflicts:
	drivers/cpufreq/cpufreq_conservative.c
	drivers/cpufreq/cpufreq_ondemand.c
	drivers/macintosh/rack-meter.c
	fs/proc/stat.c
	fs/proc/uptime.c
	kernel/sched/core.c

kernel/sched/Makefile

@@ -0,0 +1,20 @@
+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 := $(PROFILING) -fno-omit-frame-pointer
+endif
+
+obj-y += core.o clock.o idle_task.o fair.o rt.o stop_task.o
+obj-$(CONFIG_SMP) += cpupri.o
+obj-$(CONFIG_SCHED_AUTOGROUP) += auto_group.o
+obj-$(CONFIG_SCHEDSTATS) += stats.o
+obj-$(CONFIG_SCHED_DEBUG) += debug.o
+
+

kernel/sched/auto_group.c

@@ -0,0 +1,258 @@
+#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_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.  Thereafter, task_group()
+	 * returns &root_task_group, so zero bandwidth is required.
+	 */
+	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;
+
+	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;
+
+	if (p->sched_class != &fair_sched_class)
+		return false;
+
+	/*
+	 * We can only assume the task group can't go away on us if
+	 * autogroup_move_group() can see us on ->thread_group list.
+	 */
+	if (p->flags & PF_EXITING)
+		return false;
+
+	return true;
+}
+
+static 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;
+
+	t = p;
+	do {
+		sched_move_task(t);
+	} while_each_thread(p, 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 < -20 || *nice > 19)
+		return -EINVAL;
+
+	err = security_task_setnice(current, *nice);
+	if (err)
+		return err;
+
+	if (*nice < 0 && !can_nice(current, *nice))
+		return -EPERM;
+
+	/* this is a heavy operation taking global locks.. */
+	if (!capable(CAP_SYS_ADMIN) && time_before(jiffies, next))
+		return -EAGAIN;
+
+	next = HZ / 10 + jiffies;
+	ag = autogroup_task_get(p);
+
+	down_write(&ag->lock);
+	err = sched_group_set_shares(ag->tg, prio_to_weight[*nice + 20]);
+	if (!err)
+		ag->nice = *nice;
+	up_write(&ag->lock);
+
+	autogroup_kref_put(ag);
+
+	return err;
+}
+
+void proc_sched_autogroup_show_task(struct task_struct *p, struct seq_file *m)
+{
+	struct autogroup *ag = autogroup_task_get(p);
+
+	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 +1,350 @@
+/*
+ * 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.
+ * sched_clock_cpu(i) -- must be used with local IRQs disabled (implied by NMI)
+ * local_clock()      -- is cpu_clock() on the current cpu.
+ *
+ * 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).
+ *
+ *
+ * Notes:
+ *
+ * The !IRQ-safetly of sched_clock() and sched_clock_cpu() comes from things
+ * like cpufreq interrupts that can change the base clock (TSC) multiplier
+ * and cause funny jumps in time -- although the filtering provided by
+ * sched_clock_cpu() should mitigate serious artifacts we cannot rely on it
+ * in general since for !CONFIG_HAVE_UNSTABLE_SCHED_CLOCK we fully rely on
+ * sched_clock().
+ */
+#include <linux/spinlock.h>
+#include <linux/hardirq.h>
+#include <linux/export.h>
+#include <linux/percpu.h>
+#include <linux/ktime.h>
+#include <linux/sched.h>
+
+/*
+ * Scheduler clock - returns current time in nanosec units.
+ * This is default implementation.
+ * Architectures and sub-architectures can override this.
+ */
+unsigned long long __attribute__((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
+__read_mostly int sched_clock_stable;
+
+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 &__get_cpu_var(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;
+}
+
+/*
+ * 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;
+
+	sched_clock_local(my_scd);
+again:
+	this_clock = my_scd->clock;
+	remote_clock = scd->clock;
+
+	/*
+	 * 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;
+
+	WARN_ON_ONCE(!irqs_disabled());
+
+	if (sched_clock_stable)
+		return sched_clock();
+
+	if (unlikely(!sched_clock_running))
+		return 0ull;
+
+	scd = cpu_sdc(cpu);
+
+	if (cpu != smp_processor_id())
+		clock = sched_clock_remote(scd);
+	else
+		clock = sched_clock_local(scd);
+
+	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)
+{
+	u64 clock;
+	unsigned long flags;
+
+	local_irq_save(flags);
+	clock = sched_clock_cpu(cpu);
+	local_irq_restore(flags);
+
+	return 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)
+{
+	u64 clock;
+	unsigned long flags;
+
+	local_irq_save(flags);
+	clock = sched_clock_cpu(smp_processor_id());
+	local_irq_restore(flags);
+
+	return 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_cpu(cpu);
+}
+
+u64 local_clock(void)
+{
+	return sched_clock_cpu(0);
+}
+
+#endif /* CONFIG_HAVE_UNSTABLE_SCHED_CLOCK */
+
+EXPORT_SYMBOL_GPL(cpu_clock);
+EXPORT_SYMBOL_GPL(local_clock);

kernel/sched/cpupri.c

@@ -0,0 +1,241 @@
+/*
+ *  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 "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.
+ *
+ * Returns: (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);
+
+	if (task_pri >= MAX_RT_PRIO)
+		return 0;
+
+	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
+ * @pri: 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_inc();
+		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_inc();
+
+		/*
+		 * 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_inc();
+		cpumask_clear_cpu(cpu, vec->mask);
+	}
+
+	*currpri = newpri;
+}
+
+/**
+ * cpupri_init - initialize the cpupri structure
+ * @cp: The cpupri context
+ * @bootmem: true if allocations need to use bootmem
+ *
+ * Returns: -ENOMEM if memory fails.
+ */
+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;
+	}
+
+	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;
+
+	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[NR_CPUS];
+};
+
+#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/debug.c

@@ -0,0 +1,510 @@
+/*
+ * 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 "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];
+	if (!se)
+		return;
+
+#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))
+
+	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);
+#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;
+
+	/*
+	 * May be NULL if the underlying cgroup isn't fully-created yet
+	 */
+	if (!tg->css.cgroup) {
+		group_path[0] = '\0';
+		return group_path;
+	}
+	cgroup_path(tg->css.cgroup, group_path, PATH_MAX);
+	return group_path;
+}
+#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, p->pid,
+		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_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;
+	unsigned long flags;
+
+	SEQ_printf(m,
+	"\nrunnable tasks:\n"
+	"            task   PID         tree-key  switches  prio"
+	"     exec-runtime         sum-exec        sum-sleep\n"
+	"------------------------------------------------------"
+	"----------------------------------------------------\n");
+
+	read_lock_irqsave(&tasklist_lock, flags);
+
+	do_each_thread(g, p) {
+		if (!p->on_rq || task_cpu(p) != rq_cpu)
+			continue;
+
+		print_task(m, rq, p);
+	} while_each_thread(g, p);
+
+	read_unlock_irqrestore(&tasklist_lock, flags);
+}
+
+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: %ld\n", "nr_running", cfs_rq->nr_running);
+	SEQ_printf(m, "  .%-30s: %ld\n", "load", cfs_rq->load.weight);
+#ifdef CONFIG_FAIR_GROUP_SCHED
+#ifdef CONFIG_SMP
+	SEQ_printf(m, "  .%-30s: %Ld.%06ld\n", "load_avg",
+			SPLIT_NS(cfs_rq->load_avg));
+	SEQ_printf(m, "  .%-30s: %Ld.%06ld\n", "load_period",
+			SPLIT_NS(cfs_rq->load_period));
+	SEQ_printf(m, "  .%-30s: %ld\n", "load_contrib",
+			cfs_rq->load_contribution);
+	SEQ_printf(m, "  .%-30s: %d\n", "load_tg",
+			atomic_read(&cfs_rq->tg->load_weight));
+#endif
+
+	print_cfs_group_stats(m, cpu, cfs_rq->tg);
+#endif
+}
+
+void print_rt_rq(struct seq_file *m, int cpu, struct rt_rq *rt_rq)
+{
+#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, "\ncpu#%d, %u.%03u MHz\n",
+			   cpu, freq / 1000, (freq % 1000));
+	}
+#else
+	SEQ_printf(m, "\ncpu#%d\n", cpu);
+#endif
+
+#define P(x) \
+	SEQ_printf(m, "  .%-30s: %Ld\n", #x, (long long)(rq->x))
+#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);
+	P(curr->pid);
+	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_switch);
+	P(sched_count);
+	P(sched_goidle);
+#ifdef CONFIG_SMP
+	P64(avg_idle);
+#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);
+
+	rcu_read_lock();
+	print_rq(m, rq, cpu);
+	rcu_read_unlock();
+	spin_unlock_irqrestore(&sched_debug_lock, flags);
+}
+
+static const char *sched_tunable_scaling_names[] = {
+	"none",
+	"logaritmic",
+	"linear"
+};
+
+static int sched_debug_show(struct seq_file *m, void *v)
+{
+	u64 ktime, sched_clk, cpu_clk;
+	unsigned long flags;
+	int cpu;
+
+	local_irq_save(flags);
+	ktime = ktime_to_ns(ktime_get());
+	sched_clk = sched_clock();
+	cpu_clk = local_clock();
+	local_irq_restore(flags);
+
+	SEQ_printf(m, "Sched Debug Version: v0.10, %s %.*s\n",
+		init_utsname()->release,
+		(int)strcspn(init_utsname()->version, " "),
+		init_utsname()->version);
+
+#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]);
+
+	for_each_online_cpu(cpu)
+		print_cpu(m, cpu);
+
+	SEQ_printf(m, "\n");
+
+	return 0;
+}
+
+void sysrq_sched_debug_show(void)
+{
+	sched_debug_show(NULL, NULL);
+}
+
+static int sched_debug_open(struct inode *inode, struct file *filp)
+{
+	return single_open(filp, sched_debug_show, NULL);
+}
+
+static const struct file_operations sched_debug_fops = {
+	.open		= sched_debug_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_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);
+
+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, p->pid,
+						get_nr_threads(p));
+	SEQ_printf(m,
+		"---------------------------------------------------------\n");
+#define __P(F) \
+	SEQ_printf(m, "%-35s:%21Ld\n", #F, (long long)F)
+#define P(F) \
+	SEQ_printf(m, "%-35s:%21Ld\n", #F, (long long)p->F)
+#define __PN(F) \
+	SEQ_printf(m, "%-35s:%14Ld.%06ld\n", #F, SPLIT_NS((long long)F))
+#define PN(F) \
+	SEQ_printf(m, "%-35s:%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)
+			do_div(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, "%-35s:%21Ld\n",
+		   "nr_voluntary_switches", (long long)p->nvcsw);
+	SEQ_printf(m, "%-35s:%21Ld\n",
+		   "nr_involuntary_switches", (long long)p->nivcsw);
+
+	P(se.load.weight);
+	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, "%-35s:%21Ld\n",
+			   "clock-delta", (long long)(t1-t0));
+	}
+}
+
+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 +1,70 @@
+/*
+ * 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)
+
+/*
+ * Based on load and program behaviour, see if it makes sense to place
+ * a newly woken task on the same cpu as the task that woke it --
+ * improve cache locality. Typically used with SYNC wakeups as
+ * generated by pipes and the like, see also SYNC_WAKEUPS.
+ */
+SCHED_FEAT(AFFINE_WAKEUPS, 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)
+
+/*
+ * Use arch dependent cpu power functions
+ */
+SCHED_FEAT(ARCH_POWER, false)
+
+SCHED_FEAT(HRTICK, false)
+SCHED_FEAT(DOUBLE_TICK, false)
+SCHED_FEAT(LB_BIAS, true)
+
+/*
+ * Spin-wait on mutex acquisition when the mutex owner is running on
+ * another cpu -- assumes that when the owner is running, it will soon
+ * release the lock. Decreases scheduling overhead.
+ */
+SCHED_FEAT(OWNER_SPIN, true)
+
+/*
+ * Decrement CPU power based on time not spent running tasks
+ */
+SCHED_FEAT(NONTASK_POWER, 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)

kernel/sched/idle_task.c

@@ -0,0 +1,99 @@
+#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 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_task(rq->idle);
+}
+
+static struct task_struct *pick_next_task_idle(struct rq *rq)
+{
+	schedstat_inc(rq, sched_goidle);
+	calc_load_account_idle(rq);
+	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)
+{
+}
+
+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;
+}
+
+/*
+ * 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,
+};

kernel/sched/stats.c

@@ -0,0 +1,111 @@
+
+#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;
+
+	seq_printf(seq, "version %d\n", SCHEDSTAT_VERSION);
+	seq_printf(seq, "timestamp %lu\n", jiffies);
+	for_each_online_cpu(cpu) {
+		struct rq *rq = cpu_rq(cpu);
+#ifdef CONFIG_SMP
+		struct sched_domain *sd;
+		int dcount = 0;
+#endif
+
+		/* runqueue-specific stats */
+		seq_printf(seq,
+		    "cpu%d %u %u %u %u %u %u %llu %llu %lu",
+		    cpu, rq->yld_count,
+		    rq->sched_switch, 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;
+}
+
+static int schedstat_open(struct inode *inode, struct file *file)
+{
+	unsigned int size = PAGE_SIZE * (1 + num_online_cpus() / 32);
+	char *buf = kmalloc(size, GFP_KERNEL);
+	struct seq_file *m;
+	int res;
+
+	if (!buf)
+		return -ENOMEM;
+	res = single_open(file, show_schedstat, NULL);
+	if (!res) {
+		m = file->private_data;
+		m->buf = buf;
+		m->size = size;
+	} else
+		kfree(buf);
+	return res;
+}
+
+static const struct file_operations proc_schedstat_operations = {
+	.open    = schedstat_open,
+	.read    = seq_read,
+	.llseek  = seq_lseek,
+	.release = single_release,
+};
+
+static int __init proc_schedstat_init(void)
+{
+	proc_create("schedstat", 0, NULL, &proc_schedstat_operations);
+	return 0;
+}
+module_init(proc_schedstat_init);

kernel/sched/stats.h

@@ -0,0 +1,231 @@
+
+#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 task_struct *t)
+{
+	unsigned long long now = task_rq(t)->clock, 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(task_rq(t), 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 task_struct *t)
+{
+	unsigned long long now = task_rq(t)->clock, 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(task_rq(t), 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 task_struct *t)
+{
+	if (unlikely(sched_info_on()))
+		if (!t->sched_info.last_queued)
+			t->sched_info.last_queued = task_rq(t)->clock;
+}
+
+/*
+ * Called when a process ceases being the active-running process, either
+ * voluntarily or involuntarily.  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 task_struct *t)
+{
+	unsigned long long delta = task_rq(t)->clock -
+					t->sched_info.last_arrival;
+
+	rq_sched_info_depart(task_rq(t), delta);
+
+	if (t->state == TASK_RUNNING)
+		sched_info_queued(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 task_struct *prev, struct task_struct *next)
+{
+	struct rq *rq = task_rq(prev);
+
+	/*
+	 * 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(prev);
+
+	if (next != rq->idle)
+		sched_info_arrive(next);
+}
+static inline void
+sched_info_switch(struct task_struct *prev, struct task_struct *next)
+{
+	if (unlikely(sched_info_on()))
+		__sched_info_switch(prev, next);
+}
+#else
+#define sched_info_queued(t)			do { } while (0)
+#define sched_info_reset_dequeued(t)	do { } while (0)
+#define sched_info_dequeued(t)			do { } while (0)
+#define sched_info_switch(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.
+ */
+
+/**
+ * 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)
+		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)
+		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)
+		return;
+
+	raw_spin_lock(&cputimer->lock);
+	cputimer->cputime.sum_exec_runtime += ns;
+	raw_spin_unlock(&cputimer->lock);
+}

kernel/sched/stop_task.c

@@ -0,0 +1,108 @@
+#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 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 *stop = rq->stop;
+
+	if (stop && stop->on_rq)
+		return stop;
+
+	return NULL;
+}
+
+static void
+enqueue_task_stop(struct rq *rq, struct task_struct *p, int flags)
+{
+	inc_nr_running(rq);
+}
+
+static void
+dequeue_task_stop(struct rq *rq, struct task_struct *p, int flags)
+{
+	dec_nr_running(rq);
+}
+
+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)
+{
+}
+
+static void task_tick_stop(struct rq *rq, struct task_struct *curr, int queued)
+{
+}
+
+static void set_curr_task_stop(struct rq *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;
+}
+
+/*
+ * Simple, special scheduling class for the per-CPU stop tasks:
+ */
+const struct sched_class stop_sched_class = {
+	.next			= &rt_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,
+};