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

* 'sched/for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (76 commits)
  sched_clock: and multiplier for TSC to gtod drift
  sched_clock: record TSC after gtod
  sched_clock: only update deltas with local reads.
  sched_clock: fix calculation of other CPU
  sched_clock: stop maximum check on NO HZ
  sched_clock: widen the max and min time
  sched_clock: record from last tick
  sched: fix accounting in task delay accounting & migration
  sched: add avg-overlap support to RT tasks
  sched: terminate newidle balancing once at least one task has moved over
  sched: fix warning
  sched: build fix
  sched: sched_clock_cpu() based cpu_clock(), lockdep fix
  sched: export cpu_clock
  sched: make sched_{rt,fair}.c ifdefs more readable
  sched: bias effective_load() error towards failing wake_affine().
  sched: incremental effective_load()
  sched: correct wakeup weight calculations
  sched: fix mult overflow
  sched: update shares on wakeup
  ...

Documentation/scheduler/sched-domains.txt

@@ -61,10 +61,7 @@ builder by #define'ing ARCH_HASH_SCHED_DOMAIN, and exporting your
 arch_init_sched_domains function. This function will attach domains to all
 CPUs using cpu_attach_domain.
 
-Implementors should change the line
-#undef SCHED_DOMAIN_DEBUG
-to
-#define SCHED_DOMAIN_DEBUG
-in kernel/sched.c as this enables an error checking parse of the sched domains
+The sched-domains debugging infrastructure can be enabled by enabling
+CONFIG_SCHED_DEBUG. This enables an error checking parse of the sched domains
 which should catch most possible errors (described above). It also prints out
 the domain structure in a visual format.

Documentation/scheduler/sched-rt-group.txt

@@ -51,9 +51,9 @@ needs only about 3% CPU time to do so, it can do with a 0.03 * 0.005s =
 0.00015s. So this group can be scheduled with a period of 0.005s and a run time
 of 0.00015s.
 
-The remaining CPU time will be used for user input and other tass. Because
+The remaining CPU time will be used for user input and other tasks. Because
 realtime tasks have explicitly allocated the CPU time they need to perform
-their tasks, buffer underruns in the graphocs or audio can be eliminated.
+their tasks, buffer underruns in the graphics or audio can be eliminated.
 
 NOTE: the above example is not fully implemented as of yet (2.6.25). We still
 lack an EDF scheduler to make non-uniform periods usable.

include/linux/sched.h

@@ -134,7 +134,6 @@ extern unsigned long nr_running(void);
 extern unsigned long nr_uninterruptible(void);
 extern unsigned long nr_active(void);
 extern unsigned long nr_iowait(void);
-extern unsigned long weighted_cpuload(const int cpu);
 
 struct seq_file;
 struct cfs_rq;
@@ -784,6 +783,8 @@ struct sched_domain {
 	unsigned int balance_interval;	/* initialise to 1. units in ms. */
 	unsigned int nr_balance_failed; /* initialise to 0 */
 
+	u64 last_update;
+
 #ifdef CONFIG_SCHEDSTATS
 	/* load_balance() stats */
 	unsigned int lb_count[CPU_MAX_IDLE_TYPES];
@@ -823,23 +824,6 @@ extern int arch_reinit_sched_domains(void);
 
 #endif	/* CONFIG_SMP */
 
-/*
- * A runqueue laden with a single nice 0 task scores a weighted_cpuload of
- * SCHED_LOAD_SCALE. This function returns 1 if any cpu is laden with a
- * task of nice 0 or enough lower priority tasks to bring up the
- * weighted_cpuload
- */
-static inline int above_background_load(void)
-{
-	unsigned long cpu;
-
-	for_each_online_cpu(cpu) {
-		if (weighted_cpuload(cpu) >= SCHED_LOAD_SCALE)
-			return 1;
-	}
-	return 0;
-}
-
 struct io_context;			/* See blkdev.h */
 #define NGROUPS_SMALL		32
 #define NGROUPS_PER_BLOCK	((unsigned int)(PAGE_SIZE / sizeof(gid_t)))
@@ -921,8 +905,8 @@ struct sched_class {
 	void (*set_cpus_allowed)(struct task_struct *p,
 				 const cpumask_t *newmask);
 
-	void (*join_domain)(struct rq *rq);
-	void (*leave_domain)(struct rq *rq);
+	void (*rq_online)(struct rq *rq);
+	void (*rq_offline)(struct rq *rq);
 
 	void (*switched_from) (struct rq *this_rq, struct task_struct *task,
 			       int running);
@@ -1039,6 +1023,7 @@ struct task_struct {
 #endif
 
 	int prio, static_prio, normal_prio;
+	unsigned int rt_priority;
 	const struct sched_class *sched_class;
 	struct sched_entity se;
 	struct sched_rt_entity rt;
@@ -1122,7 +1107,6 @@ struct task_struct {
 	int __user *set_child_tid;		/* CLONE_CHILD_SETTID */
 	int __user *clear_child_tid;		/* CLONE_CHILD_CLEARTID */
 
-	unsigned int rt_priority;
 	cputime_t utime, stime, utimescaled, stimescaled;
 	cputime_t gtime;
 	cputime_t prev_utime, prev_stime;
@@ -1141,12 +1125,12 @@ struct task_struct {
 	gid_t gid,egid,sgid,fsgid;
 	struct group_info *group_info;
 	kernel_cap_t   cap_effective, cap_inheritable, cap_permitted, cap_bset;
-	unsigned securebits;
 	struct user_struct *user;
+	unsigned securebits;
 #ifdef CONFIG_KEYS
+	unsigned char jit_keyring;	/* default keyring to attach requested keys to */
 	struct key *request_key_auth;	/* assumed request_key authority */
 	struct key *thread_keyring;	/* keyring private to this thread */
-	unsigned char jit_keyring;	/* default keyring to attach requested keys to */
 #endif
 	char comm[TASK_COMM_LEN]; /* executable name excluding path
 				     - access with [gs]et_task_comm (which lock
@@ -1233,8 +1217,8 @@ struct task_struct {
 # define MAX_LOCK_DEPTH 48UL
 	u64 curr_chain_key;
 	int lockdep_depth;
-	struct held_lock held_locks[MAX_LOCK_DEPTH];
 	unsigned int lockdep_recursion;
+	struct held_lock held_locks[MAX_LOCK_DEPTH];
 #endif
 
 /* journalling filesystem info */
@@ -1262,10 +1246,6 @@ struct task_struct {
 	u64 acct_vm_mem1;	/* accumulated virtual memory usage */
 	cputime_t acct_stimexpd;/* stime since last update */
 #endif
-#ifdef CONFIG_NUMA
-  	struct mempolicy *mempolicy;
-	short il_next;
-#endif
 #ifdef CONFIG_CPUSETS
 	nodemask_t mems_allowed;
 	int cpuset_mems_generation;
@@ -1284,6 +1264,10 @@ struct task_struct {
 #endif
 	struct list_head pi_state_list;
 	struct futex_pi_state *pi_state_cache;
+#endif
+#ifdef CONFIG_NUMA
+	struct mempolicy *mempolicy;
+	short il_next;
 #endif
 	atomic_t fs_excl;	/* holding fs exclusive resources */
 	struct rcu_head rcu;
@@ -1504,6 +1488,7 @@ static inline void put_task_struct(struct task_struct *t)
 #define PF_SWAPWRITE	0x00800000	/* Allowed to write to swap */
 #define PF_SPREAD_PAGE	0x01000000	/* Spread page cache over cpuset */
 #define PF_SPREAD_SLAB	0x02000000	/* Spread some slab caches over cpuset */
+#define PF_THREAD_BOUND	0x04000000	/* Thread bound to specific cpu */
 #define PF_MEMPOLICY	0x10000000	/* Non-default NUMA mempolicy */
 #define PF_MUTEX_TESTER	0x20000000	/* Thread belongs to the rt mutex tester */
 #define PF_FREEZER_SKIP	0x40000000	/* Freezer should not count it as freezeable */
@@ -1573,13 +1558,28 @@ static inline void sched_clock_idle_sleep_event(void)
 static inline void sched_clock_idle_wakeup_event(u64 delta_ns)
 {
 }
-#else
+
+#ifdef CONFIG_NO_HZ
+static inline void sched_clock_tick_stop(int cpu)
+{
+}
+
+static inline void sched_clock_tick_start(int cpu)
+{
+}
+#endif
+
+#else /* CONFIG_HAVE_UNSTABLE_SCHED_CLOCK */
 extern void sched_clock_init(void);
 extern u64 sched_clock_cpu(int cpu);
 extern void sched_clock_tick(void);
 extern void sched_clock_idle_sleep_event(void);
 extern void sched_clock_idle_wakeup_event(u64 delta_ns);
+#ifdef CONFIG_NO_HZ
+extern void sched_clock_tick_stop(int cpu);
+extern void sched_clock_tick_start(int cpu);
 #endif
+#endif /* CONFIG_HAVE_UNSTABLE_SCHED_CLOCK */
 
 /*
  * For kernel-internal use: high-speed (but slightly incorrect) per-cpu
@@ -1622,6 +1622,7 @@ extern unsigned int sysctl_sched_child_runs_first;
 extern unsigned int sysctl_sched_features;
 extern unsigned int sysctl_sched_migration_cost;
 extern unsigned int sysctl_sched_nr_migrate;
+extern unsigned int sysctl_sched_shares_ratelimit;
 
 int sched_nr_latency_handler(struct ctl_table *table, int write,
 		struct file *file, void __user *buffer, size_t *length,

kernel/Makefile

@@ -3,7 +3,7 @@
 #
 
 obj-y     = sched.o fork.o exec_domain.o panic.o printk.o profile.o \
-	    exit.o itimer.o time.o softirq.o resource.o \
+	    cpu.o exit.o itimer.o time.o softirq.o resource.o \
 	    sysctl.o capability.o ptrace.o timer.o user.o \
 	    signal.o sys.o kmod.o workqueue.o pid.o \
 	    rcupdate.o extable.o params.o posix-timers.o \
@@ -27,7 +27,7 @@ obj-$(CONFIG_RT_MUTEXES) += rtmutex.o
 obj-$(CONFIG_DEBUG_RT_MUTEXES) += rtmutex-debug.o
 obj-$(CONFIG_RT_MUTEX_TESTER) += rtmutex-tester.o
 obj-$(CONFIG_GENERIC_ISA_DMA) += dma.o
-obj-$(CONFIG_SMP) += cpu.o spinlock.o
+obj-$(CONFIG_SMP) += spinlock.o
 obj-$(CONFIG_DEBUG_SPINLOCK) += spinlock.o
 obj-$(CONFIG_PROVE_LOCKING) += spinlock.o
 obj-$(CONFIG_UID16) += uid16.o
@@ -69,6 +69,7 @@ obj-$(CONFIG_TASK_DELAY_ACCT) += delayacct.o
 obj-$(CONFIG_TASKSTATS) += taskstats.o tsacct.o
 obj-$(CONFIG_MARKERS) += marker.o
 obj-$(CONFIG_LATENCYTOP) += latencytop.o
+obj-$(CONFIG_SMP) += sched_cpupri.o
 
 ifneq ($(CONFIG_SCHED_NO_NO_OMIT_FRAME_POINTER),y)
 # According to Alan Modra <alan@linuxcare.com.au>, the -fno-omit-frame-pointer is

kernel/cpu.c

@@ -15,6 +15,28 @@
 #include <linux/stop_machine.h>
 #include <linux/mutex.h>
 
+/*
+ * Represents all cpu's present in the system
+ * In systems capable of hotplug, this map could dynamically grow
+ * as new cpu's are detected in the system via any platform specific
+ * method, such as ACPI for e.g.
+ */
+cpumask_t cpu_present_map __read_mostly;
+EXPORT_SYMBOL(cpu_present_map);
+
+#ifndef CONFIG_SMP
+
+/*
+ * Represents all cpu's that are currently online.
+ */
+cpumask_t cpu_online_map __read_mostly = CPU_MASK_ALL;
+EXPORT_SYMBOL(cpu_online_map);
+
+cpumask_t cpu_possible_map __read_mostly = CPU_MASK_ALL;
+EXPORT_SYMBOL(cpu_possible_map);
+
+#else /* CONFIG_SMP */
+
 /* Serializes the updates to cpu_online_map, cpu_present_map */
 static DEFINE_MUTEX(cpu_add_remove_lock);
 
@@ -403,3 +425,5 @@ out:
 	cpu_maps_update_done();
 }
 #endif /* CONFIG_PM_SLEEP_SMP */
+
+#endif /* CONFIG_SMP */

kernel/cpuset.c

@@ -1194,6 +1194,15 @@ static int cpuset_can_attach(struct cgroup_subsys *ss,
 
 	if (cpus_empty(cs->cpus_allowed) || nodes_empty(cs->mems_allowed))
 		return -ENOSPC;
+	if (tsk->flags & PF_THREAD_BOUND) {
+		cpumask_t mask;
+
+		mutex_lock(&callback_mutex);
+		mask = cs->cpus_allowed;
+		mutex_unlock(&callback_mutex);
+		if (!cpus_equal(tsk->cpus_allowed, mask))
+			return -EINVAL;
+	}
 
 	return security_task_setscheduler(tsk, 0, NULL);
 }
@@ -1207,11 +1216,14 @@ static void cpuset_attach(struct cgroup_subsys *ss,
 	struct mm_struct *mm;
 	struct cpuset *cs = cgroup_cs(cont);
 	struct cpuset *oldcs = cgroup_cs(oldcont);
+	int err;
 
 	mutex_lock(&callback_mutex);
 	guarantee_online_cpus(cs, &cpus);
-	set_cpus_allowed_ptr(tsk, &cpus);
+	err = set_cpus_allowed_ptr(tsk, &cpus);
 	mutex_unlock(&callback_mutex);
+	if (err)
+		return;
 
 	from = oldcs->mems_allowed;
 	to = cs->mems_allowed;

kernel/kthread.c

@@ -180,6 +180,7 @@ void kthread_bind(struct task_struct *k, unsigned int cpu)
 	set_task_cpu(k, cpu);
 	k->cpus_allowed = cpumask_of_cpu(cpu);
 	k->rt.nr_cpus_allowed = 1;
+	k->flags |= PF_THREAD_BOUND;
 }
 EXPORT_SYMBOL(kthread_bind);
 

kernel/sched_clock.c

@@ -3,6 +3,9 @@
  *
  *  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>
@@ -32,6 +35,11 @@
 
 #ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
 
+#define MULTI_SHIFT 15
+/* Max is double, Min is 1/2 */
+#define MAX_MULTI (2LL << MULTI_SHIFT)
+#define MIN_MULTI (1LL << (MULTI_SHIFT-1))
+
 struct sched_clock_data {
 	/*
 	 * Raw spinlock - this is a special case: this might be called
@@ -40,11 +48,15 @@ struct sched_clock_data {
 	 */
 	raw_spinlock_t		lock;
 
-	unsigned long		prev_jiffies;
+	unsigned long		tick_jiffies;
 	u64			prev_raw;
 	u64			tick_raw;
 	u64			tick_gtod;
 	u64			clock;
+	s64			multi;
+#ifdef CONFIG_NO_HZ
+	int			check_max;
+#endif
 };
 
 static DEFINE_PER_CPU_SHARED_ALIGNED(struct sched_clock_data, sched_clock_data);
@@ -71,41 +83,91 @@ void sched_clock_init(void)
 		struct sched_clock_data *scd = cpu_sdc(cpu);
 
 		scd->lock = (raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED;
-		scd->prev_jiffies = now_jiffies;
+		scd->tick_jiffies = now_jiffies;
 		scd->prev_raw = 0;
 		scd->tick_raw = 0;
 		scd->tick_gtod = ktime_now;
 		scd->clock = ktime_now;
+		scd->multi = 1 << MULTI_SHIFT;
+#ifdef CONFIG_NO_HZ
+		scd->check_max = 1;
+#endif
 	}
 
 	sched_clock_running = 1;
 }
 
+#ifdef CONFIG_NO_HZ
+/*
+ * The dynamic ticks makes the delta jiffies inaccurate. This
+ * prevents us from checking the maximum time update.
+ * Disable the maximum check during stopped ticks.
+ */
+void sched_clock_tick_stop(int cpu)
+{
+	struct sched_clock_data *scd = cpu_sdc(cpu);
+
+	scd->check_max = 0;
+}
+
+void sched_clock_tick_start(int cpu)
+{
+	struct sched_clock_data *scd = cpu_sdc(cpu);
+
+	scd->check_max = 1;
+}
+
+static int check_max(struct sched_clock_data *scd)
+{
+	return scd->check_max;
+}
+#else
+static int check_max(struct sched_clock_data *scd)
+{
+	return 1;
+}
+#endif /* CONFIG_NO_HZ */
+
 /*
  * update the percpu scd from the raw @now value
  *
  *  - filter out backward motion
  *  - use jiffies to generate a min,max window to clip the raw values
  */
-static void __update_sched_clock(struct sched_clock_data *scd, u64 now)
+static void __update_sched_clock(struct sched_clock_data *scd, u64 now, u64 *time)
 {
 	unsigned long now_jiffies = jiffies;
-	long delta_jiffies = now_jiffies - scd->prev_jiffies;
+	long delta_jiffies = now_jiffies - scd->tick_jiffies;
 	u64 clock = scd->clock;
 	u64 min_clock, max_clock;
 	s64 delta = now - scd->prev_raw;
 
 	WARN_ON_ONCE(!irqs_disabled());
-	min_clock = scd->tick_gtod + delta_jiffies * TICK_NSEC;
+
+	/*
+	 * At schedule tick the clock can be just under the gtod. We don't
+	 * want to push it too prematurely.
+	 */
+	min_clock = scd->tick_gtod + (delta_jiffies * TICK_NSEC);
+	if (min_clock > TICK_NSEC)
+		min_clock -= TICK_NSEC / 2;
 
 	if (unlikely(delta < 0)) {
 		clock++;
 		goto out;
 	}
 
-	max_clock = min_clock + TICK_NSEC;
+	/*
+	 * The clock must stay within a jiffie of the gtod.
+	 * But since we may be at the start of a jiffy or the end of one
+	 * we add another jiffy buffer.
+	 */
+	max_clock = scd->tick_gtod + (2 + delta_jiffies) * TICK_NSEC;
+
+	delta *= scd->multi;
+	delta >>= MULTI_SHIFT;
 
-	if (unlikely(clock + delta > max_clock)) {
+	if (unlikely(clock + delta > max_clock) && check_max(scd)) {
 		if (clock < max_clock)
 			clock = max_clock;
 		else
@@ -118,9 +180,12 @@ static void __update_sched_clock(struct sched_clock_data *scd, u64 now)
 	if (unlikely(clock < min_clock))
 		clock = min_clock;
 
-	scd->prev_raw = now;
-	scd->prev_jiffies = now_jiffies;
-	scd->clock = clock;
+	if (time)
+		*time = clock;
+	else {
+		scd->prev_raw = now;
+		scd->clock = clock;
+	}
 }
 
 static void lock_double_clock(struct sched_clock_data *data1,
@@ -160,25 +225,30 @@ u64 sched_clock_cpu(int cpu)
 		now -= my_scd->tick_raw;
 		now += scd->tick_raw;
 
-		now -= my_scd->tick_gtod;
-		now += scd->tick_gtod;
+		now += my_scd->tick_gtod;
+		now -= scd->tick_gtod;
 
 		__raw_spin_unlock(&my_scd->lock);
+
+		__update_sched_clock(scd, now, &clock);
+
+		__raw_spin_unlock(&scd->lock);
+
 	} else {
 		__raw_spin_lock(&scd->lock);
+		__update_sched_clock(scd, now, NULL);
+		clock = scd->clock;
+		__raw_spin_unlock(&scd->lock);
 	}
 
-	__update_sched_clock(scd, now);
-	clock = scd->clock;
-
-	__raw_spin_unlock(&scd->lock);
-
 	return clock;
 }
 
 void sched_clock_tick(void)
 {
 	struct sched_clock_data *scd = this_scd();
+	unsigned long now_jiffies = jiffies;
+	s64 mult, delta_gtod, delta_raw;
 	u64 now, now_gtod;
 
 	if (unlikely(!sched_clock_running))
@@ -186,18 +256,33 @@ void sched_clock_tick(void)
 
 	WARN_ON_ONCE(!irqs_disabled());
 
-	now = sched_clock();
 	now_gtod = ktime_to_ns(ktime_get());
+	now = sched_clock();
 
 	__raw_spin_lock(&scd->lock);
-	__update_sched_clock(scd, now);
+	__update_sched_clock(scd, now, NULL);
 	/*
 	 * update tick_gtod after __update_sched_clock() because that will
 	 * already observe 1 new jiffy; adding a new tick_gtod to that would
 	 * increase the clock 2 jiffies.
 	 */
+	delta_gtod = now_gtod - scd->tick_gtod;
+	delta_raw = now - scd->tick_raw;
+
+	if ((long)delta_raw > 0) {
+		mult = delta_gtod << MULTI_SHIFT;
+		do_div(mult, delta_raw);
+		scd->multi = mult;
+		if (scd->multi > MAX_MULTI)
+			scd->multi = MAX_MULTI;
+		else if (scd->multi < MIN_MULTI)
+			scd->multi = MIN_MULTI;
+	} else
+		scd->multi = 1 << MULTI_SHIFT;
+
 	scd->tick_raw = now;
 	scd->tick_gtod = now_gtod;
+	scd->tick_jiffies = now_jiffies;
 	__raw_spin_unlock(&scd->lock);
 }
 
@@ -227,6 +312,7 @@ void sched_clock_idle_wakeup_event(u64 delta_ns)
 	__raw_spin_lock(&scd->lock);
 	scd->prev_raw = now;
 	scd->clock += delta_ns;
+	scd->multi = 1 << MULTI_SHIFT;
 	__raw_spin_unlock(&scd->lock);
 
 	touch_softlockup_watchdog();
@@ -244,3 +330,16 @@ unsigned long long __attribute__((weak)) sched_clock(void)
 {
 	return (unsigned long long)jiffies * (NSEC_PER_SEC / HZ);
 }
+
+unsigned long long cpu_clock(int cpu)
+{
+	unsigned long long clock;
+	unsigned long flags;
+
+	local_irq_save(flags);
+	clock = sched_clock_cpu(cpu);
+	local_irq_restore(flags);
+
+	return clock;
+}
+EXPORT_SYMBOL_GPL(cpu_clock);

kernel/sched_cpupri.c

@@ -0,0 +1,174 @@
+/*
+ *  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 "sched_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;
+}
+
+#define for_each_cpupri_active(array, idx)                    \
+  for (idx = find_first_bit(array, CPUPRI_NR_PRIORITIES);     \
+       idx < CPUPRI_NR_PRIORITIES;                            \
+       idx = find_next_bit(array, CPUPRI_NR_PRIORITIES, idx+1))
+
+/**
+ * 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
+ *
+ * Note: This function returns the recommended CPUs as calculated during the
+ * current invokation.  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,
+		cpumask_t *lowest_mask)
+{
+	int                  idx      = 0;
+	int                  task_pri = convert_prio(p->prio);
+
+	for_each_cpupri_active(cp->pri_active, idx) {
+		struct cpupri_vec *vec  = &cp->pri_to_cpu[idx];
+		cpumask_t mask;
+
+		if (idx >= task_pri)
+			break;
+
+		cpus_and(mask, p->cpus_allowed, vec->mask);
+
+		if (cpus_empty(mask))
+			continue;
+
+		*lowest_mask = mask;
+		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;
+	unsigned long        flags;
+
+	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
+	 * first need to unmap the old value
+	 */
+	if (likely(oldpri != CPUPRI_INVALID)) {
+		struct cpupri_vec *vec  = &cp->pri_to_cpu[oldpri];
+
+		spin_lock_irqsave(&vec->lock, flags);
+
+		vec->count--;
+		if (!vec->count)
+			clear_bit(oldpri, cp->pri_active);
+		cpu_clear(cpu, vec->mask);
+
+		spin_unlock_irqrestore(&vec->lock, flags);
+	}
+
+	if (likely(newpri != CPUPRI_INVALID)) {
+		struct cpupri_vec *vec = &cp->pri_to_cpu[newpri];
+
+		spin_lock_irqsave(&vec->lock, flags);
+
+		cpu_set(cpu, vec->mask);
+		vec->count++;
+		if (vec->count == 1)
+			set_bit(newpri, cp->pri_active);
+
+		spin_unlock_irqrestore(&vec->lock, flags);
+	}
+
+	*currpri = newpri;
+}
+
+/**
+ * cpupri_init - initialize the cpupri structure
+ * @cp: The cpupri context
+ *
+ * Returns: (void)
+ */
+void 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];
+
+		spin_lock_init(&vec->lock);
+		vec->count = 0;
+		cpus_clear(vec->mask);
+	}
+
+	for_each_possible_cpu(i)
+		cp->cpu_to_pri[i] = CPUPRI_INVALID;
+}
+
+

kernel/sched_cpupri.h

@@ -0,0 +1,36 @@
+#ifndef _LINUX_CPUPRI_H
+#define _LINUX_CPUPRI_H
+
+#include <linux/sched.h>
+
+#define CPUPRI_NR_PRIORITIES	(MAX_RT_PRIO + 2)
+#define CPUPRI_NR_PRI_WORDS	BITS_TO_LONGS(CPUPRI_NR_PRIORITIES)
+
+#define CPUPRI_INVALID -1
+#define CPUPRI_IDLE     0
+#define CPUPRI_NORMAL   1
+/* values 2-101 are RT priorities 0-99 */
+
+struct cpupri_vec {
+	spinlock_t lock;
+	int        count;
+	cpumask_t  mask;
+};
+
+struct cpupri {
+	struct cpupri_vec pri_to_cpu[CPUPRI_NR_PRIORITIES];
+	long              pri_active[CPUPRI_NR_PRI_WORDS];
+	int               cpu_to_pri[NR_CPUS];
+};
+
+#ifdef CONFIG_SMP
+int  cpupri_find(struct cpupri *cp,
+		 struct task_struct *p, cpumask_t *lowest_mask);
+void cpupri_set(struct cpupri *cp, int cpu, int pri);
+void cpupri_init(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

@@ -119,9 +119,7 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
 	struct sched_entity *last;
 	unsigned long flags;
 
-#if !defined(CONFIG_CGROUP_SCHED) || !defined(CONFIG_USER_SCHED)
-	SEQ_printf(m, "\ncfs_rq[%d]:\n", cpu);
-#else
+#if defined(CONFIG_CGROUP_SCHED) && defined(CONFIG_FAIR_GROUP_SCHED)
 	char path[128] = "";
 	struct cgroup *cgroup = NULL;
 	struct task_group *tg = cfs_rq->tg;
@@ -133,6 +131,8 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
 		cgroup_path(cgroup, path, sizeof(path));
 
 	SEQ_printf(m, "\ncfs_rq[%d]:%s\n", cpu, path);
+#else
+	SEQ_printf(m, "\ncfs_rq[%d]:\n", cpu);
 #endif
 
 	SEQ_printf(m, "  .%-30s: %Ld.%06ld\n", "exec_clock",
@@ -162,11 +162,64 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
 	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_SCHEDSTATS
-	SEQ_printf(m, "  .%-30s: %d\n", "bkl_count",
-			rq->bkl_count);
+#define P(n) SEQ_printf(m, "  .%-30s: %d\n", #n, rq->n);
+
+	P(yld_exp_empty);
+	P(yld_act_empty);
+	P(yld_both_empty);
+	P(yld_count);
+
+	P(sched_switch);
+	P(sched_count);
+	P(sched_goidle);
+
+	P(ttwu_count);
+	P(ttwu_local);
+
+	P(bkl_count);
+
+#undef P
 #endif
 	SEQ_printf(m, "  .%-30s: %ld\n", "nr_spread_over",
 			cfs_rq->nr_spread_over);
+#ifdef CONFIG_FAIR_GROUP_SCHED
+#ifdef CONFIG_SMP
+	SEQ_printf(m, "  .%-30s: %lu\n", "shares", cfs_rq->shares);
+#endif
+#endif
+}
+
+void print_rt_rq(struct seq_file *m, int cpu, struct rt_rq *rt_rq)
+{
+#if defined(CONFIG_CGROUP_SCHED) && defined(CONFIG_RT_GROUP_SCHED)
+	char path[128] = "";
+	struct cgroup *cgroup = NULL;
+	struct task_group *tg = rt_rq->tg;
+
+	if (tg)
+		cgroup = tg->css.cgroup;
+
+	if (cgroup)
+		cgroup_path(cgroup, path, sizeof(path));
+
+	SEQ_printf(m, "\nrt_rq[%d]:%s\n", cpu, path);
+#else
+	SEQ_printf(m, "\nrt_rq[%d]:\n", cpu);
+#endif
+
+
+#define P(x) \
+	SEQ_printf(m, "  .%-30s: %Ld\n", #x, (long long)(rt_rq->x))
+#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
 }
 
 static void print_cpu(struct seq_file *m, int cpu)
@@ -208,6 +261,7 @@ static void print_cpu(struct seq_file *m, int cpu)
 #undef PN
 
 	print_cfs_stats(m, cpu);
+	print_rt_stats(m, cpu);
 
 	print_rq(m, rq, cpu);
 }

kernel/sched_fair.c

@@ -63,13 +63,13 @@ unsigned int __read_mostly sysctl_sched_compat_yield;
 
 /*
  * SCHED_OTHER wake-up granularity.
- * (default: 10 msec * (1 + ilog(ncpus)), units: nanoseconds)
+ * (default: 5 msec * (1 + ilog(ncpus)), units: nanoseconds)
  *
  * This option delays the preemption effects of decoupled workloads
  * and reduces their over-scheduling. Synchronous workloads will still
  * have immediate wakeup/sleep latencies.
  */
-unsigned int sysctl_sched_wakeup_granularity = 10000000UL;
+unsigned int sysctl_sched_wakeup_granularity = 5000000UL;
 
 const_debug unsigned int sysctl_sched_migration_cost = 500000UL;
 
@@ -333,6 +333,34 @@ int sched_nr_latency_handler(struct ctl_table *table, int write,
 }
 #endif
 
+/*
+ * delta *= w / rw
+ */
+static inline unsigned long
+calc_delta_weight(unsigned long delta, struct sched_entity *se)
+{
+	for_each_sched_entity(se) {
+		delta = calc_delta_mine(delta,
+				se->load.weight, &cfs_rq_of(se)->load);
+	}
+
+	return delta;
+}
+
+/*
+ * delta *= rw / w
+ */
+static inline unsigned long
+calc_delta_fair(unsigned long delta, struct sched_entity *se)
+{
+	for_each_sched_entity(se) {
+		delta = calc_delta_mine(delta,
+				cfs_rq_of(se)->load.weight, &se->load);
+	}
+
+	return delta;
+}
+
 /*
  * The idea is to set a period in which each task runs once.
  *
@@ -362,47 +390,80 @@ static u64 __sched_period(unsigned long nr_running)
  */
 static u64 sched_slice(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
-	u64 slice = __sched_period(cfs_rq->nr_running);
-
-	for_each_sched_entity(se) {
-		cfs_rq = cfs_rq_of(se);
-
-		slice *= se->load.weight;
-		do_div(slice, cfs_rq->load.weight);
-	}
-
-
-	return slice;
+	return calc_delta_weight(__sched_period(cfs_rq->nr_running), se);
 }
 
 /*
  * We calculate the vruntime slice of a to be inserted task
  *
- * vs = s/w = p/rw
+ * vs = s*rw/w = p
  */
 static u64 sched_vslice_add(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
 	unsigned long nr_running = cfs_rq->nr_running;
-	unsigned long weight;
-	u64 vslice;
 
 	if (!se->on_rq)
 		nr_running++;
 
-	vslice = __sched_period(nr_running);
+	return __sched_period(nr_running);
+}
+
+/*
+ * The goal of calc_delta_asym() is to be asymmetrically around NICE_0_LOAD, in
+ * that it favours >=0 over <0.
+ *
+ *   -20         |
+ *               |
+ *     0 --------+-------
+ *             .'
+ *    19     .'
+ *
+ */
+static unsigned long
+calc_delta_asym(unsigned long delta, struct sched_entity *se)
+{
+	struct load_weight lw = {
+		.weight = NICE_0_LOAD,
+		.inv_weight = 1UL << (WMULT_SHIFT-NICE_0_SHIFT)
+	};
 
 	for_each_sched_entity(se) {
-		cfs_rq = cfs_rq_of(se);
+		struct load_weight *se_lw = &se->load;
+		unsigned long rw = cfs_rq_of(se)->load.weight;
+
+#ifdef CONFIG_FAIR_SCHED_GROUP
+		struct cfs_rq *cfs_rq = se->my_q;
+		struct task_group *tg = NULL
+
+		if (cfs_rq)
+			tg = cfs_rq->tg;
+
+		if (tg && tg->shares < NICE_0_LOAD) {
+			/*
+			 * scale shares to what it would have been had
+			 * tg->weight been NICE_0_LOAD:
+			 *
+			 *   weight = 1024 * shares / tg->weight
+			 */
+			lw.weight *= se->load.weight;
+			lw.weight /= tg->shares;
+
+			lw.inv_weight = 0;
+
+			se_lw = &lw;
+			rw += lw.weight - se->load.weight;
+		} else
+#endif
 
-		weight = cfs_rq->load.weight;
-		if (!se->on_rq)
-			weight += se->load.weight;
+		if (se->load.weight < NICE_0_LOAD) {
+			se_lw = &lw;
+			rw += NICE_0_LOAD - se->load.weight;
+		}
 
-		vslice *= NICE_0_LOAD;
-		do_div(vslice, weight);
+		delta = calc_delta_mine(delta, rw, se_lw);
 	}
 
-	return vslice;
+	return delta;
 }
 
 /*
@@ -419,11 +480,7 @@ __update_curr(struct cfs_rq *cfs_rq, struct sched_entity *curr,
 
 	curr->sum_exec_runtime += delta_exec;
 	schedstat_add(cfs_rq, exec_clock, delta_exec);
-	delta_exec_weighted = delta_exec;
-	if (unlikely(curr->load.weight != NICE_0_LOAD)) {
-		delta_exec_weighted = calc_delta_fair(delta_exec_weighted,
-							&curr->load);
-	}
+	delta_exec_weighted = calc_delta_fair(delta_exec, curr);
 	curr->vruntime += delta_exec_weighted;
 }
 
@@ -510,10 +567,27 @@ update_stats_curr_start(struct cfs_rq *cfs_rq, struct sched_entity *se)
  * Scheduling class queueing methods:
  */
 
+#if defined CONFIG_SMP && defined CONFIG_FAIR_GROUP_SCHED
+static void
+add_cfs_task_weight(struct cfs_rq *cfs_rq, unsigned long weight)
+{
+	cfs_rq->task_weight += weight;
+}
+#else
+static inline void
+add_cfs_task_weight(struct cfs_rq *cfs_rq, unsigned long weight)
+{
+}
+#endif
+
 static void
 account_entity_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
 	update_load_add(&cfs_rq->load, se->load.weight);
+	if (!parent_entity(se))
+		inc_cpu_load(rq_of(cfs_rq), se->load.weight);
+	if (entity_is_task(se))
+		add_cfs_task_weight(cfs_rq, se->load.weight);
 	cfs_rq->nr_running++;
 	se->on_rq = 1;
 	list_add(&se->group_node, &cfs_rq->tasks);
@@ -523,6 +597,10 @@ static void
 account_entity_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
 	update_load_sub(&cfs_rq->load, se->load.weight);
+	if (!parent_entity(se))
+		dec_cpu_load(rq_of(cfs_rq), se->load.weight);
+	if (entity_is_task(se))
+		add_cfs_task_weight(cfs_rq, -se->load.weight);
 	cfs_rq->nr_running--;
 	se->on_rq = 0;
 	list_del_init(&se->group_node);
@@ -609,8 +687,17 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial)
 
 	if (!initial) {
 		/* sleeps upto a single latency don't count. */
-		if (sched_feat(NEW_FAIR_SLEEPERS))
-			vruntime -= sysctl_sched_latency;
+		if (sched_feat(NEW_FAIR_SLEEPERS)) {
+			unsigned long thresh = sysctl_sched_latency;
+
+			/*
+			 * convert the sleeper threshold into virtual time
+			 */
+			if (sched_feat(NORMALIZED_SLEEPER))
+				thresh = calc_delta_fair(thresh, se);
+
+			vruntime -= thresh;
+		}
 
 		/* ensure we never gain time by being placed backwards. */
 		vruntime = max_vruntime(se->vruntime, vruntime);
@@ -639,21 +726,6 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int wakeup)
 		__enqueue_entity(cfs_rq, se);
 }
 
-static void update_avg(u64 *avg, u64 sample)
-{
-	s64 diff = sample - *avg;
-	*avg += diff >> 3;
-}
-
-static void update_avg_stats(struct cfs_rq *cfs_rq, struct sched_entity *se)
-{
-	if (!se->last_wakeup)
-		return;
-
-	update_avg(&se->avg_overlap, se->sum_exec_runtime - se->last_wakeup);
-	se->last_wakeup = 0;
-}
-
 static void
 dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int sleep)
 {
@@ -664,7 +736,6 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int sleep)
 
 	update_stats_dequeue(cfs_rq, se);
 	if (sleep) {
-		update_avg_stats(cfs_rq, se);
 #ifdef CONFIG_SCHEDSTATS
 		if (entity_is_task(se)) {
 			struct task_struct *tsk = task_of(se);
@@ -726,17 +797,16 @@ set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
 	se->prev_sum_exec_runtime = se->sum_exec_runtime;
 }
 
-static int
-wakeup_preempt_entity(struct sched_entity *curr, struct sched_entity *se);
-
 static struct sched_entity *
 pick_next(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
-	if (!cfs_rq->next)
-		return se;
+	struct rq *rq = rq_of(cfs_rq);
+	u64 pair_slice = rq->clock - cfs_rq->pair_start;
 
-	if (wakeup_preempt_entity(cfs_rq->next, se) != 0)
+	if (!cfs_rq->next || pair_slice > sched_slice(cfs_rq, cfs_rq->next)) {
+		cfs_rq->pair_start = rq->clock;
 		return se;
+	}
 
 	return cfs_rq->next;
 }
@@ -835,7 +905,7 @@ static void hrtick_start_fair(struct rq *rq, struct task_struct *p)
 		hrtick_start(rq, delta, requeue);
 	}
 }
-#else
+#else /* !CONFIG_SCHED_HRTICK */
 static inline void
 hrtick_start_fair(struct rq *rq, struct task_struct *p)
 {
@@ -976,7 +1046,7 @@ static int wake_idle(int cpu, struct task_struct *p)
 	}
 	return cpu;
 }
-#else
+#else /* !ARCH_HAS_SCHED_WAKE_IDLE*/
 static inline int wake_idle(int cpu, struct task_struct *p)
 {
 	return cpu;
@@ -987,6 +1057,89 @@ static inline int wake_idle(int cpu, struct task_struct *p)
 
 static const struct sched_class fair_sched_class;
 
+#ifdef CONFIG_FAIR_GROUP_SCHED
+/*
+ * effective_load() calculates the load change as seen from the root_task_group
+ *
+ * Adding load to a group doesn't make a group heavier, but can cause movement
+ * of group shares between cpus. Assuming the shares were perfectly aligned one
+ * can calculate the shift in shares.
+ *
+ * The problem is that perfectly aligning the shares is rather expensive, hence
+ * we try to avoid doing that too often - see update_shares(), which ratelimits
+ * this change.
+ *
+ * We compensate this by not only taking the current delta into account, but
+ * also considering the delta between when the shares were last adjusted and
+ * now.
+ *
+ * We still saw a performance dip, some tracing learned us that between
+ * cgroup:/ and cgroup:/foo balancing the number of affine wakeups increased
+ * significantly. Therefore try to bias the error in direction of failing
+ * the affine wakeup.
+ *
+ */
+static long effective_load(struct task_group *tg, int cpu,
+		long wl, long wg)
+{
+	struct sched_entity *se = tg->se[cpu];
+	long more_w;
+
+	if (!tg->parent)
+		return wl;
+
+	/*
+	 * By not taking the decrease of shares on the other cpu into
+	 * account our error leans towards reducing the affine wakeups.
+	 */
+	if (!wl && sched_feat(ASYM_EFF_LOAD))
+		return wl;
+
+	/*
+	 * Instead of using this increment, also add the difference
+	 * between when the shares were last updated and now.
+	 */
+	more_w = se->my_q->load.weight - se->my_q->rq_weight;
+	wl += more_w;
+	wg += more_w;
+
+	for_each_sched_entity(se) {
+#define D(n) (likely(n) ? (n) : 1)
+
+		long S, rw, s, a, b;
+
+		S = se->my_q->tg->shares;
+		s = se->my_q->shares;
+		rw = se->my_q->rq_weight;
+
+		a = S*(rw + wl);
+		b = S*rw + s*wg;
+
+		wl = s*(a-b)/D(b);
+		/*
+		 * Assume the group is already running and will
+		 * thus already be accounted for in the weight.
+		 *
+		 * That is, moving shares between CPUs, does not
+		 * alter the group weight.
+		 */
+		wg = 0;
+#undef D
+	}
+
+	return wl;
+}
+
+#else
+
+static inline unsigned long effective_load(struct task_group *tg, int cpu,
+		unsigned long wl, unsigned long wg)
+{
+	return wl;
+}
+
+#endif
+
 static int
 wake_affine(struct rq *rq, struct sched_domain *this_sd, struct rq *this_rq,
 	    struct task_struct *p, int prev_cpu, int this_cpu, int sync,
@@ -994,8 +1147,10 @@ wake_affine(struct rq *rq, struct sched_domain *this_sd, struct rq *this_rq,
 	    unsigned int imbalance)
 {
 	struct task_struct *curr = this_rq->curr;
+	struct task_group *tg;
 	unsigned long tl = this_load;
 	unsigned long tl_per_task;
+	unsigned long weight;
 	int balanced;
 
 	if (!(this_sd->flags & SD_WAKE_AFFINE) || !sched_feat(AFFINE_WAKEUPS))
@@ -1006,19 +1161,28 @@ wake_affine(struct rq *rq, struct sched_domain *this_sd, struct rq *this_rq,
 	 * effect of the currently running task from the load
 	 * of the current CPU:
 	 */
-	if (sync)
-		tl -= current->se.load.weight;
+	if (sync) {
+		tg = task_group(current);
+		weight = current->se.load.weight;
+
+		tl += effective_load(tg, this_cpu, -weight, -weight);
+		load += effective_load(tg, prev_cpu, 0, -weight);
+	}
 
-	balanced = 100*(tl + p->se.load.weight) <= imbalance*load;
+	tg = task_group(p);
+	weight = p->se.load.weight;
+
+	balanced = 100*(tl + effective_load(tg, this_cpu, weight, weight)) <=
+		imbalance*(load + effective_load(tg, prev_cpu, 0, weight));
 
 	/*
 	 * If the currently running task will sleep within
 	 * a reasonable amount of time then attract this newly
 	 * woken task:
 	 */
-	if (sync && balanced && curr->sched_class == &fair_sched_class) {
+	if (sync && balanced) {
 		if (curr->se.avg_overlap < sysctl_sched_migration_cost &&
-				p->se.avg_overlap < sysctl_sched_migration_cost)
+		    p->se.avg_overlap < sysctl_sched_migration_cost)
 			return 1;
 	}
 
@@ -1111,11 +1275,13 @@ static unsigned long wakeup_gran(struct sched_entity *se)
 	unsigned long gran = sysctl_sched_wakeup_granularity;
 
 	/*
-	 * More easily preempt - nice tasks, while not making
-	 * it harder for + nice tasks.
+	 * More easily preempt - nice tasks, while not making it harder for
+	 * + nice tasks.
 	 */
-	if (unlikely(se->load.weight > NICE_0_LOAD))
-		gran = calc_delta_fair(gran, &se->load);
+	if (sched_feat(ASYM_GRAN))
+		gran = calc_delta_asym(sysctl_sched_wakeup_granularity, se);
+	else
+		gran = calc_delta_fair(sysctl_sched_wakeup_granularity, se);
 
 	return gran;
 }
@@ -1177,7 +1343,6 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p)
 		return;
 	}
 
-	se->last_wakeup = se->sum_exec_runtime;
 	if (unlikely(se == pse))
 		return;
 
@@ -1275,23 +1440,18 @@ __load_balance_iterator(struct cfs_rq *cfs_rq, struct list_head *next)
 	struct task_struct *p = NULL;
 	struct sched_entity *se;
 
-	if (next == &cfs_rq->tasks)
-		return NULL;
-
-	/* Skip over entities that are not tasks */
-	do {
+	while (next != &cfs_rq->tasks) {
 		se = list_entry(next, struct sched_entity, group_node);
 		next = next->next;
-	} while (next != &cfs_rq->tasks && !entity_is_task(se));
 
-	if (next == &cfs_rq->tasks)
-		return NULL;
+		/* Skip over entities that are not tasks */
+		if (entity_is_task(se)) {
+			p = task_of(se);
+			break;
+		}
+	}
 
 	cfs_rq->balance_iterator = next;
-
-	if (entity_is_task(se))
-		p = task_of(se);
-
 	return p;
 }
 
@@ -1309,75 +1469,82 @@ static struct task_struct *load_balance_next_fair(void *arg)
 	return __load_balance_iterator(cfs_rq, cfs_rq->balance_iterator);
 }
 
-#ifdef CONFIG_FAIR_GROUP_SCHED
-static int cfs_rq_best_prio(struct cfs_rq *cfs_rq)
+static unsigned long
+__load_balance_fair(struct rq *this_rq, int this_cpu, struct rq *busiest,
+		unsigned long max_load_move, struct sched_domain *sd,
+		enum cpu_idle_type idle, int *all_pinned, int *this_best_prio,
+		struct cfs_rq *cfs_rq)
 {
-	struct sched_entity *curr;
-	struct task_struct *p;
-
-	if (!cfs_rq->nr_running || !first_fair(cfs_rq))
-		return MAX_PRIO;
-
-	curr = cfs_rq->curr;
-	if (!curr)
-		curr = __pick_next_entity(cfs_rq);
+	struct rq_iterator cfs_rq_iterator;
 
-	p = task_of(curr);
+	cfs_rq_iterator.start = load_balance_start_fair;
+	cfs_rq_iterator.next = load_balance_next_fair;
+	cfs_rq_iterator.arg = cfs_rq;
 
-	return p->prio;
+	return balance_tasks(this_rq, this_cpu, busiest,
+			max_load_move, sd, idle, all_pinned,
+			this_best_prio, &cfs_rq_iterator);
 }
-#endif
 
+#ifdef CONFIG_FAIR_GROUP_SCHED
 static unsigned long
 load_balance_fair(struct rq *this_rq, int this_cpu, struct rq *busiest,
 		  unsigned long max_load_move,
 		  struct sched_domain *sd, enum cpu_idle_type idle,
 		  int *all_pinned, int *this_best_prio)
 {
-	struct cfs_rq *busy_cfs_rq;
 	long rem_load_move = max_load_move;
-	struct rq_iterator cfs_rq_iterator;
-
-	cfs_rq_iterator.start = load_balance_start_fair;
-	cfs_rq_iterator.next = load_balance_next_fair;
+	int busiest_cpu = cpu_of(busiest);
+	struct task_group *tg;
 
-	for_each_leaf_cfs_rq(busiest, busy_cfs_rq) {
-#ifdef CONFIG_FAIR_GROUP_SCHED
-		struct cfs_rq *this_cfs_rq;
-		long imbalance;
-		unsigned long maxload;
+	rcu_read_lock();
+	update_h_load(busiest_cpu);
 
-		this_cfs_rq = cpu_cfs_rq(busy_cfs_rq, this_cpu);
+	list_for_each_entry(tg, &task_groups, list) {
+		struct cfs_rq *busiest_cfs_rq = tg->cfs_rq[busiest_cpu];
+		unsigned long busiest_h_load = busiest_cfs_rq->h_load;
+		unsigned long busiest_weight = busiest_cfs_rq->load.weight;
+		u64 rem_load, moved_load;
 
-		imbalance = busy_cfs_rq->load.weight - this_cfs_rq->load.weight;
-		/* Don't pull if this_cfs_rq has more load than busy_cfs_rq */
-		if (imbalance <= 0)
+		/*
+		 * empty group
+		 */
+		if (!busiest_cfs_rq->task_weight)
 			continue;
 
-		/* Don't pull more than imbalance/2 */
-		imbalance /= 2;
-		maxload = min(rem_load_move, imbalance);
+		rem_load = (u64)rem_load_move * busiest_weight;
+		rem_load = div_u64(rem_load, busiest_h_load + 1);
 
-		*this_best_prio = cfs_rq_best_prio(this_cfs_rq);
-#else
-# define maxload rem_load_move
-#endif
-		/*
-		 * pass busy_cfs_rq argument into
-		 * load_balance_[start|next]_fair iterators
-		 */
-		cfs_rq_iterator.arg = busy_cfs_rq;
-		rem_load_move -= balance_tasks(this_rq, this_cpu, busiest,
-					       maxload, sd, idle, all_pinned,
-					       this_best_prio,
-					       &cfs_rq_iterator);
+		moved_load = __load_balance_fair(this_rq, this_cpu, busiest,
+				rem_load, sd, idle, all_pinned, this_best_prio,
+				tg->cfs_rq[busiest_cpu]);
+
+		if (!moved_load)
+			continue;
+
+		moved_load *= busiest_h_load;
+		moved_load = div_u64(moved_load, busiest_weight + 1);
 
-		if (rem_load_move <= 0)
+		rem_load_move -= moved_load;
+		if (rem_load_move < 0)
 			break;
 	}
+	rcu_read_unlock();
 
 	return max_load_move - rem_load_move;
 }
+#else
+static unsigned long
+load_balance_fair(struct rq *this_rq, int this_cpu, struct rq *busiest,
+		  unsigned long max_load_move,
+		  struct sched_domain *sd, enum cpu_idle_type idle,
+		  int *all_pinned, int *this_best_prio)
+{
+	return __load_balance_fair(this_rq, this_cpu, busiest,
+			max_load_move, sd, idle, all_pinned,
+			this_best_prio, &busiest->cfs);
+}
+#endif
 
 static int
 move_one_task_fair(struct rq *this_rq, int this_cpu, struct rq *busiest,
@@ -1402,7 +1569,7 @@ move_one_task_fair(struct rq *this_rq, int this_cpu, struct rq *busiest,
 
 	return 0;
 }
-#endif
+#endif /* CONFIG_SMP */
 
 /*
  * scheduler tick hitting a task of our scheduling class:

kernel/sched_features.h

@@ -1,4 +1,5 @@
 SCHED_FEAT(NEW_FAIR_SLEEPERS, 1)
+SCHED_FEAT(NORMALIZED_SLEEPER, 1)
 SCHED_FEAT(WAKEUP_PREEMPT, 1)
 SCHED_FEAT(START_DEBIT, 1)
 SCHED_FEAT(AFFINE_WAKEUPS, 1)
@@ -6,5 +7,7 @@ SCHED_FEAT(CACHE_HOT_BUDDY, 1)
 SCHED_FEAT(SYNC_WAKEUPS, 1)
 SCHED_FEAT(HRTICK, 1)
 SCHED_FEAT(DOUBLE_TICK, 0)
-SCHED_FEAT(NORMALIZED_SLEEPER, 1)
-SCHED_FEAT(DEADLINE, 1)
+SCHED_FEAT(ASYM_GRAN, 1)
+SCHED_FEAT(LB_BIAS, 0)
+SCHED_FEAT(LB_WAKEUP_UPDATE, 1)
+SCHED_FEAT(ASYM_EFF_LOAD, 1)

kernel/sched_rt.c

@@ -12,6 +12,9 @@ static inline int rt_overloaded(struct rq *rq)
 
 static inline void rt_set_overload(struct rq *rq)
 {
+	if (!rq->online)
+		return;
+
 	cpu_set(rq->cpu, rq->rd->rto_mask);
 	/*
 	 * Make sure the mask is visible before we set
@@ -26,6 +29,9 @@ static inline void rt_set_overload(struct rq *rq)
 
 static inline void rt_clear_overload(struct rq *rq)
 {
+	if (!rq->online)
+		return;
+
 	/* the order here really doesn't matter */
 	atomic_dec(&rq->rd->rto_count);
 	cpu_clear(rq->cpu, rq->rd->rto_mask);
@@ -155,7 +161,7 @@ static inline struct rt_bandwidth *sched_rt_bandwidth(struct rt_rq *rt_rq)
 	return &rt_rq->tg->rt_bandwidth;
 }
 
-#else
+#else /* !CONFIG_RT_GROUP_SCHED */
 
 static inline u64 sched_rt_runtime(struct rt_rq *rt_rq)
 {
@@ -220,49 +226,10 @@ static inline struct rt_bandwidth *sched_rt_bandwidth(struct rt_rq *rt_rq)
 	return &def_rt_bandwidth;
 }
 
-#endif
-
-static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun)
-{
-	int i, idle = 1;
-	cpumask_t span;
-
-	if (rt_b->rt_runtime == RUNTIME_INF)
-		return 1;
-
-	span = sched_rt_period_mask();
-	for_each_cpu_mask(i, span) {
-		int enqueue = 0;
-		struct rt_rq *rt_rq = sched_rt_period_rt_rq(rt_b, i);
-		struct rq *rq = rq_of_rt_rq(rt_rq);
-
-		spin_lock(&rq->lock);
-		if (rt_rq->rt_time) {
-			u64 runtime;
-
-			spin_lock(&rt_rq->rt_runtime_lock);
-			runtime = rt_rq->rt_runtime;
-			rt_rq->rt_time -= min(rt_rq->rt_time, overrun*runtime);
-			if (rt_rq->rt_throttled && rt_rq->rt_time < runtime) {
-				rt_rq->rt_throttled = 0;
-				enqueue = 1;
-			}
-			if (rt_rq->rt_time || rt_rq->rt_nr_running)
-				idle = 0;
-			spin_unlock(&rt_rq->rt_runtime_lock);
-		} else if (rt_rq->rt_nr_running)
-			idle = 0;
-
-		if (enqueue)
-			sched_rt_rq_enqueue(rt_rq);
-		spin_unlock(&rq->lock);
-	}
-
-	return idle;
-}
+#endif /* CONFIG_RT_GROUP_SCHED */
 
 #ifdef CONFIG_SMP
-static int balance_runtime(struct rt_rq *rt_rq)
+static int do_balance_runtime(struct rt_rq *rt_rq)
 {
 	struct rt_bandwidth *rt_b = sched_rt_bandwidth(rt_rq);
 	struct root_domain *rd = cpu_rq(smp_processor_id())->rd;
@@ -281,6 +248,9 @@ static int balance_runtime(struct rt_rq *rt_rq)
 			continue;
 
 		spin_lock(&iter->rt_runtime_lock);
+		if (iter->rt_runtime == RUNTIME_INF)
+			goto next;
+
 		diff = iter->rt_runtime - iter->rt_time;
 		if (diff > 0) {
 			do_div(diff, weight);
@@ -294,13 +264,163 @@ static int balance_runtime(struct rt_rq *rt_rq)
 				break;
 			}
 		}
+next:
 		spin_unlock(&iter->rt_runtime_lock);
 	}
 	spin_unlock(&rt_b->rt_runtime_lock);
 
 	return more;
 }
-#endif
+
+static void __disable_runtime(struct rq *rq)
+{
+	struct root_domain *rd = rq->rd;
+	struct rt_rq *rt_rq;
+
+	if (unlikely(!scheduler_running))
+		return;
+
+	for_each_leaf_rt_rq(rt_rq, rq) {
+		struct rt_bandwidth *rt_b = sched_rt_bandwidth(rt_rq);
+		s64 want;
+		int i;
+
+		spin_lock(&rt_b->rt_runtime_lock);
+		spin_lock(&rt_rq->rt_runtime_lock);
+		if (rt_rq->rt_runtime == RUNTIME_INF ||
+				rt_rq->rt_runtime == rt_b->rt_runtime)
+			goto balanced;
+		spin_unlock(&rt_rq->rt_runtime_lock);
+
+		want = rt_b->rt_runtime - rt_rq->rt_runtime;
+
+		for_each_cpu_mask(i, rd->span) {
+			struct rt_rq *iter = sched_rt_period_rt_rq(rt_b, i);
+			s64 diff;
+
+			if (iter == rt_rq)
+				continue;
+
+			spin_lock(&iter->rt_runtime_lock);
+			if (want > 0) {
+				diff = min_t(s64, iter->rt_runtime, want);
+				iter->rt_runtime -= diff;
+				want -= diff;
+			} else {
+				iter->rt_runtime -= want;
+				want -= want;
+			}
+			spin_unlock(&iter->rt_runtime_lock);
+
+			if (!want)
+				break;
+		}
+
+		spin_lock(&rt_rq->rt_runtime_lock);
+		BUG_ON(want);
+balanced:
+		rt_rq->rt_runtime = RUNTIME_INF;
+		spin_unlock(&rt_rq->rt_runtime_lock);
+		spin_unlock(&rt_b->rt_runtime_lock);
+	}
+}
+
+static void disable_runtime(struct rq *rq)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&rq->lock, flags);
+	__disable_runtime(rq);
+	spin_unlock_irqrestore(&rq->lock, flags);
+}
+
+static void __enable_runtime(struct rq *rq)
+{
+	struct rt_rq *rt_rq;
+
+	if (unlikely(!scheduler_running))
+		return;
+
+	for_each_leaf_rt_rq(rt_rq, rq) {
+		struct rt_bandwidth *rt_b = sched_rt_bandwidth(rt_rq);
+
+		spin_lock(&rt_b->rt_runtime_lock);
+		spin_lock(&rt_rq->rt_runtime_lock);
+		rt_rq->rt_runtime = rt_b->rt_runtime;
+		rt_rq->rt_time = 0;
+		spin_unlock(&rt_rq->rt_runtime_lock);
+		spin_unlock(&rt_b->rt_runtime_lock);
+	}
+}
+
+static void enable_runtime(struct rq *rq)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&rq->lock, flags);
+	__enable_runtime(rq);
+	spin_unlock_irqrestore(&rq->lock, flags);
+}
+
+static int balance_runtime(struct rt_rq *rt_rq)
+{
+	int more = 0;
+
+	if (rt_rq->rt_time > rt_rq->rt_runtime) {
+		spin_unlock(&rt_rq->rt_runtime_lock);
+		more = do_balance_runtime(rt_rq);
+		spin_lock(&rt_rq->rt_runtime_lock);
+	}
+
+	return more;
+}
+#else /* !CONFIG_SMP */
+static inline int balance_runtime(struct rt_rq *rt_rq)
+{
+	return 0;
+}
+#endif /* CONFIG_SMP */
+
+static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun)
+{
+	int i, idle = 1;
+	cpumask_t span;
+
+	if (rt_b->rt_runtime == RUNTIME_INF)
+		return 1;
+
+	span = sched_rt_period_mask();
+	for_each_cpu_mask(i, span) {
+		int enqueue = 0;
+		struct rt_rq *rt_rq = sched_rt_period_rt_rq(rt_b, i);
+		struct rq *rq = rq_of_rt_rq(rt_rq);
+
+		spin_lock(&rq->lock);
+		if (rt_rq->rt_time) {
+			u64 runtime;
+
+			spin_lock(&rt_rq->rt_runtime_lock);
+			if (rt_rq->rt_throttled)
+				balance_runtime(rt_rq);
+			runtime = rt_rq->rt_runtime;
+			rt_rq->rt_time -= min(rt_rq->rt_time, overrun*runtime);
+			if (rt_rq->rt_throttled && rt_rq->rt_time < runtime) {
+				rt_rq->rt_throttled = 0;
+				enqueue = 1;
+			}
+			if (rt_rq->rt_time || rt_rq->rt_nr_running)
+				idle = 0;
+			spin_unlock(&rt_rq->rt_runtime_lock);
+		} else if (rt_rq->rt_nr_running)
+			idle = 0;
+
+		if (enqueue)
+			sched_rt_rq_enqueue(rt_rq);
+		spin_unlock(&rq->lock);
+	}
+
+	return idle;
+}
 
 static inline int rt_se_prio(struct sched_rt_entity *rt_se)
 {
@@ -327,18 +447,10 @@ static int sched_rt_runtime_exceeded(struct rt_rq *rt_rq)
 	if (sched_rt_runtime(rt_rq) >= sched_rt_period(rt_rq))
 		return 0;
 
-#ifdef CONFIG_SMP
-	if (rt_rq->rt_time > runtime) {
-		int more;
-
-		spin_unlock(&rt_rq->rt_runtime_lock);
-		more = balance_runtime(rt_rq);
-		spin_lock(&rt_rq->rt_runtime_lock);
-
-		if (more)
-			runtime = sched_rt_runtime(rt_rq);
-	}
-#endif
+	balance_runtime(rt_rq);
+	runtime = sched_rt_runtime(rt_rq);
+	if (runtime == RUNTIME_INF)
+		return 0;
 
 	if (rt_rq->rt_time > runtime) {
 		rt_rq->rt_throttled = 1;
@@ -392,12 +504,21 @@ void inc_rt_tasks(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
 	WARN_ON(!rt_prio(rt_se_prio(rt_se)));
 	rt_rq->rt_nr_running++;
 #if defined CONFIG_SMP || defined CONFIG_RT_GROUP_SCHED
-	if (rt_se_prio(rt_se) < rt_rq->highest_prio)
+	if (rt_se_prio(rt_se) < rt_rq->highest_prio) {
+		struct rq *rq = rq_of_rt_rq(rt_rq);
+
 		rt_rq->highest_prio = rt_se_prio(rt_se);
+#ifdef CONFIG_SMP
+		if (rq->online)
+			cpupri_set(&rq->rd->cpupri, rq->cpu,
+				   rt_se_prio(rt_se));
+#endif
+	}
 #endif
 #ifdef CONFIG_SMP
 	if (rt_se->nr_cpus_allowed > 1) {
 		struct rq *rq = rq_of_rt_rq(rt_rq);
+
 		rq->rt.rt_nr_migratory++;
 	}
 
@@ -417,6 +538,10 @@ void inc_rt_tasks(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
 static inline
 void dec_rt_tasks(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
 {
+#ifdef CONFIG_SMP
+	int highest_prio = rt_rq->highest_prio;
+#endif
+
 	WARN_ON(!rt_prio(rt_se_prio(rt_se)));
 	WARN_ON(!rt_rq->rt_nr_running);
 	rt_rq->rt_nr_running--;
@@ -440,6 +565,14 @@ void dec_rt_tasks(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
 		rq->rt.rt_nr_migratory--;
 	}
 
+	if (rt_rq->highest_prio != highest_prio) {
+		struct rq *rq = rq_of_rt_rq(rt_rq);
+
+		if (rq->online)
+			cpupri_set(&rq->rd->cpupri, rq->cpu,
+				   rt_rq->highest_prio);
+	}
+
 	update_rt_migration(rq_of_rt_rq(rt_rq));
 #endif /* CONFIG_SMP */
 #ifdef CONFIG_RT_GROUP_SCHED
@@ -455,6 +588,7 @@ static void __enqueue_rt_entity(struct sched_rt_entity *rt_se)
 	struct rt_rq *rt_rq = rt_rq_of_se(rt_se);
 	struct rt_prio_array *array = &rt_rq->active;
 	struct rt_rq *group_rq = group_rt_rq(rt_se);
+	struct list_head *queue = array->queue + rt_se_prio(rt_se);
 
 	/*
 	 * Don't enqueue the group if its throttled, or when empty.
@@ -465,7 +599,11 @@ static void __enqueue_rt_entity(struct sched_rt_entity *rt_se)
 	if (group_rq && (rt_rq_throttled(group_rq) || !group_rq->rt_nr_running))
 		return;
 
-	list_add_tail(&rt_se->run_list, array->queue + rt_se_prio(rt_se));
+	if (rt_se->nr_cpus_allowed == 1)
+		list_add(&rt_se->run_list, queue);
+	else
+		list_add_tail(&rt_se->run_list, queue);
+
 	__set_bit(rt_se_prio(rt_se), array->bitmap);
 
 	inc_rt_tasks(rt_se, rt_rq);
@@ -532,6 +670,8 @@ static void enqueue_task_rt(struct rq *rq, struct task_struct *p, int wakeup)
 		rt_se->timeout = 0;
 
 	enqueue_rt_entity(rt_se);
+
+	inc_cpu_load(rq, p->se.load.weight);
 }
 
 static void dequeue_task_rt(struct rq *rq, struct task_struct *p, int sleep)
@@ -540,6 +680,8 @@ static void dequeue_task_rt(struct rq *rq, struct task_struct *p, int sleep)
 
 	update_curr_rt(rq);
 	dequeue_rt_entity(rt_se);
+
+	dec_cpu_load(rq, p->se.load.weight);
 }
 
 /*
@@ -550,10 +692,12 @@ static
 void requeue_rt_entity(struct rt_rq *rt_rq, struct sched_rt_entity *rt_se)
 {
 	struct rt_prio_array *array = &rt_rq->active;
-	struct list_head *queue = array->queue + rt_se_prio(rt_se);
 
-	if (on_rt_rq(rt_se))
-		list_move_tail(&rt_se->run_list, queue);
+	if (on_rt_rq(rt_se)) {
+		list_del_init(&rt_se->run_list);
+		list_add_tail(&rt_se->run_list,
+			      array->queue + rt_se_prio(rt_se));
+	}
 }
 
 static void requeue_task_rt(struct rq *rq, struct task_struct *p)
@@ -616,8 +760,37 @@ static int select_task_rq_rt(struct task_struct *p, int sync)
  */
 static void check_preempt_curr_rt(struct rq *rq, struct task_struct *p)
 {
-	if (p->prio < rq->curr->prio)
+	if (p->prio < rq->curr->prio) {
 		resched_task(rq->curr);
+		return;
+	}
+
+#ifdef CONFIG_SMP
+	/*
+	 * If:
+	 *
+	 * - the newly woken task is of equal priority to the current task
+	 * - the newly woken task is non-migratable while current is migratable
+	 * - current will be preempted on the next reschedule
+	 *
+	 * we should check to see if current can readily move to a different
+	 * cpu.  If so, we will reschedule to allow the push logic to try
+	 * to move current somewhere else, making room for our non-migratable
+	 * task.
+	 */
+	if((p->prio == rq->curr->prio)
+	   && p->rt.nr_cpus_allowed == 1
+	   && rq->curr->rt.nr_cpus_allowed != 1) {
+		cpumask_t mask;
+
+		if (cpupri_find(&rq->rd->cpupri, rq->curr, &mask))
+			/*
+			 * There appears to be other cpus that can accept
+			 * current, so lets reschedule to try and push it away
+			 */
+			resched_task(rq->curr);
+	}
+#endif
 }
 
 static struct sched_rt_entity *pick_next_rt_entity(struct rq *rq,
@@ -720,73 +893,6 @@ static struct task_struct *pick_next_highest_task_rt(struct rq *rq, int cpu)
 
 static DEFINE_PER_CPU(cpumask_t, local_cpu_mask);
 
-static int find_lowest_cpus(struct task_struct *task, cpumask_t *lowest_mask)
-{
-	int       lowest_prio = -1;
-	int       lowest_cpu  = -1;
-	int       count       = 0;
-	int       cpu;
-
-	cpus_and(*lowest_mask, task_rq(task)->rd->online, task->cpus_allowed);
-
-	/*
-	 * Scan each rq for the lowest prio.
-	 */
-	for_each_cpu_mask(cpu, *lowest_mask) {
-		struct rq *rq = cpu_rq(cpu);
-
-		/* We look for lowest RT prio or non-rt CPU */
-		if (rq->rt.highest_prio >= MAX_RT_PRIO) {
-			/*
-			 * if we already found a low RT queue
-			 * and now we found this non-rt queue
-			 * clear the mask and set our bit.
-			 * Otherwise just return the queue as is
-			 * and the count==1 will cause the algorithm
-			 * to use the first bit found.
-			 */
-			if (lowest_cpu != -1) {
-				cpus_clear(*lowest_mask);
-				cpu_set(rq->cpu, *lowest_mask);
-			}
-			return 1;
-		}
-
-		/* no locking for now */
-		if ((rq->rt.highest_prio > task->prio)
-		    && (rq->rt.highest_prio >= lowest_prio)) {
-			if (rq->rt.highest_prio > lowest_prio) {
-				/* new low - clear old data */
-				lowest_prio = rq->rt.highest_prio;
-				lowest_cpu = cpu;
-				count = 0;
-			}
-			count++;
-		} else
-			cpu_clear(cpu, *lowest_mask);
-	}
-
-	/*
-	 * Clear out all the set bits that represent
-	 * runqueues that were of higher prio than
-	 * the lowest_prio.
-	 */
-	if (lowest_cpu > 0) {
-		/*
-		 * Perhaps we could add another cpumask op to
-		 * zero out bits. Like cpu_zero_bits(cpumask, nrbits);
-		 * Then that could be optimized to use memset and such.
-		 */
-		for_each_cpu_mask(cpu, *lowest_mask) {
-			if (cpu >= lowest_cpu)
-				break;
-			cpu_clear(cpu, *lowest_mask);
-		}
-	}
-
-	return count;
-}
-
 static inline int pick_optimal_cpu(int this_cpu, cpumask_t *mask)
 {
 	int first;
@@ -808,17 +914,12 @@ static int find_lowest_rq(struct task_struct *task)
 	cpumask_t *lowest_mask = &__get_cpu_var(local_cpu_mask);
 	int this_cpu = smp_processor_id();
 	int cpu      = task_cpu(task);
-	int count    = find_lowest_cpus(task, lowest_mask);
 
-	if (!count)
-		return -1; /* No targets found */
+	if (task->rt.nr_cpus_allowed == 1)
+		return -1; /* No other targets possible */
 
-	/*
-	 * There is no sense in performing an optimal search if only one
-	 * target is found.
-	 */
-	if (count == 1)
-		return first_cpu(*lowest_mask);
+	if (!cpupri_find(&task_rq(task)->rd->cpupri, task, lowest_mask))
+		return -1; /* No targets found */
 
 	/*
 	 * At this point we have built a mask of cpus representing the
@@ -1163,17 +1264,25 @@ static void set_cpus_allowed_rt(struct task_struct *p,
 }
 
 /* Assumes rq->lock is held */
-static void join_domain_rt(struct rq *rq)
+static void rq_online_rt(struct rq *rq)
 {
 	if (rq->rt.overloaded)
 		rt_set_overload(rq);
+
+	__enable_runtime(rq);
+
+	cpupri_set(&rq->rd->cpupri, rq->cpu, rq->rt.highest_prio);
 }
 
 /* Assumes rq->lock is held */
-static void leave_domain_rt(struct rq *rq)
+static void rq_offline_rt(struct rq *rq)
 {
 	if (rq->rt.overloaded)
 		rt_clear_overload(rq);
+
+	__disable_runtime(rq);
+
+	cpupri_set(&rq->rd->cpupri, rq->cpu, CPUPRI_INVALID);
 }
 
 /*
@@ -1336,8 +1445,8 @@ static const struct sched_class rt_sched_class = {
 	.load_balance		= load_balance_rt,
 	.move_one_task		= move_one_task_rt,
 	.set_cpus_allowed       = set_cpus_allowed_rt,
-	.join_domain            = join_domain_rt,
-	.leave_domain           = leave_domain_rt,
+	.rq_online              = rq_online_rt,
+	.rq_offline             = rq_offline_rt,
 	.pre_schedule		= pre_schedule_rt,
 	.post_schedule		= post_schedule_rt,
 	.task_wake_up		= task_wake_up_rt,
@@ -1350,3 +1459,17 @@ static const struct sched_class rt_sched_class = {
 	.prio_changed		= prio_changed_rt,
 	.switched_to		= switched_to_rt,
 };
+
+#ifdef CONFIG_SCHED_DEBUG
+extern void print_rt_rq(struct seq_file *m, int cpu, struct rt_rq *rt_rq);
+
+static void print_rt_stats(struct seq_file *m, int cpu)
+{
+	struct rt_rq *rt_rq;
+
+	rcu_read_lock();
+	for_each_leaf_rt_rq(rt_rq, cpu_rq(cpu))
+		print_rt_rq(m, cpu, rt_rq);
+	rcu_read_unlock();
+}
+#endif /* CONFIG_SCHED_DEBUG */

kernel/sched_stats.h

@@ -118,6 +118,13 @@ rq_sched_info_depart(struct rq *rq, unsigned long long delta)
 	if (rq)
 		rq->rq_sched_info.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)
@@ -126,6 +133,9 @@ 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)
@@ -134,6 +144,11 @@ rq_sched_info_depart(struct rq *rq, unsigned long long delta)
 #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;
+}
+
 /*
  * Called when a process is dequeued from the active array and given
  * the cpu.  We should note that with the exception of interactive
@@ -143,15 +158,22 @@ rq_sched_info_depart(struct rq *rq, unsigned long long delta)
  * active queue, thus delaying tasks in the expired queue from running;
  * see scheduler_tick()).
  *
- * This function is only called from sched_info_arrive(), rather than
- * dequeue_task(). Even though a task may be queued and dequeued multiple
- * times as it is shuffled about, we're really interested in knowing how
- * long it was from the *first* time it was queued to the time that it
- * finally hit a cpu.
+ * Though 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)
 {
-	t->sched_info.last_queued = 0;
+	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);
 }
 
 /*
@@ -165,7 +187,7 @@ static void sched_info_arrive(struct task_struct *t)
 
 	if (t->sched_info.last_queued)
 		delta = now - t->sched_info.last_queued;
-	sched_info_dequeued(t);
+	sched_info_reset_dequeued(t);
 	t->sched_info.run_delay += delta;
 	t->sched_info.last_arrival = now;
 	t->sched_info.pcount++;
@@ -242,7 +264,9 @@ sched_info_switch(struct task_struct *prev, struct task_struct *next)
 		__sched_info_switch(prev, next);
 }
 #else
-#define sched_info_queued(t)		do { } while (0)
-#define sched_info_switch(t, next)	do { } while (0)
+#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 */
 

kernel/sysctl.c

@@ -264,6 +264,14 @@ static struct ctl_table kern_table[] = {
 		.extra1		= &min_wakeup_granularity_ns,
 		.extra2		= &max_wakeup_granularity_ns,
 	},
+	{
+		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "sched_shares_ratelimit",
+		.data		= &sysctl_sched_shares_ratelimit,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec,
+	},
 	{
 		.ctl_name	= CTL_UNNUMBERED,
 		.procname	= "sched_child_runs_first",

kernel/time/tick-sched.c

@@ -276,6 +276,7 @@ void tick_nohz_stop_sched_tick(void)
 			ts->tick_stopped = 1;
 			ts->idle_jiffies = last_jiffies;
 			rcu_enter_nohz();
+			sched_clock_tick_stop(cpu);
 		}
 
 		/*
@@ -375,6 +376,7 @@ void tick_nohz_restart_sched_tick(void)
 	select_nohz_load_balancer(0);
 	now = ktime_get();
 	tick_do_update_jiffies64(now);
+	sched_clock_tick_start(cpu);
 	cpu_clear(cpu, nohz_cpu_mask);
 
 	/*