1 files changed, 315 insertions, 44 deletions

diff --git a/kernel/sched.c b/kernel/sched.c
index 26efa475bdc1..14c447ae5d53 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -72,13 +72,15 @@
 #include <linux/debugfs.h>
 #include <linux/ctype.h>
 #include <linux/ftrace.h>
-#include <trace/sched.h>
 
 #include <asm/tlb.h>
 #include <asm/irq_regs.h>
 
 #include "sched_cpupri.h"
 
+#define CREATE_TRACE_POINTS
+#include <trace/events/sched.h>
+
 /*
  * Convert user-nice values [ -20 ... 0 ... 19 ]
  * to static priority [ MAX_RT_PRIO..MAX_PRIO-1 ],
@@ -118,12 +120,6 @@
  */
 #define RUNTIME_INF	((u64)~0ULL)
 
-DEFINE_TRACE(sched_wait_task);
-DEFINE_TRACE(sched_wakeup);
-DEFINE_TRACE(sched_wakeup_new);
-DEFINE_TRACE(sched_switch);
-DEFINE_TRACE(sched_migrate_task);
-
 #ifdef CONFIG_SMP
 
 static void double_rq_lock(struct rq *rq1, struct rq *rq2);
@@ -630,6 +626,10 @@ struct rq {
 	struct list_head migration_queue;
 #endif
 
+	/* calc_load related fields */
+	unsigned long calc_load_update;
+	long calc_load_active;
+
 #ifdef CONFIG_SCHED_HRTICK
 #ifdef CONFIG_SMP
 	int hrtick_csd_pending;
@@ -1728,6 +1728,8 @@ static void cfs_rq_set_shares(struct cfs_rq *cfs_rq, unsigned long shares)
 }
 #endif
 
+static void calc_load_account_active(struct rq *this_rq);
+
 #include "sched_stats.h"
 #include "sched_idletask.c"
 #include "sched_fair.c"
@@ -1958,7 +1960,7 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
 
 	clock_offset = old_rq->clock - new_rq->clock;
 
-	trace_sched_migrate_task(p, task_cpu(p), new_cpu);
+	trace_sched_migrate_task(p, new_cpu);
 
 #ifdef CONFIG_SCHEDSTATS
 	if (p->se.wait_start)
@@ -2015,6 +2017,49 @@ migrate_task(struct task_struct *p, int dest_cpu, struct migration_req *req)
 }
 
 /*
+ * wait_task_context_switch -	wait for a thread to complete at least one
+ *				context switch.
+ *
+ * @p must not be current.
+ */
+void wait_task_context_switch(struct task_struct *p)
+{
+	unsigned long nvcsw, nivcsw, flags;
+	int running;
+	struct rq *rq;
+
+	nvcsw	= p->nvcsw;
+	nivcsw	= p->nivcsw;
+	for (;;) {
+		/*
+		 * The runqueue is assigned before the actual context
+		 * switch. We need to take the runqueue lock.
+		 *
+		 * We could check initially without the lock but it is
+		 * very likely that we need to take the lock in every
+		 * iteration.
+		 */
+		rq = task_rq_lock(p, &flags);
+		running = task_running(rq, p);
+		task_rq_unlock(rq, &flags);
+
+		if (likely(!running))
+			break;
+		/*
+		 * The switch count is incremented before the actual
+		 * context switch. We thus wait for two switches to be
+		 * sure at least one completed.
+		 */
+		if ((p->nvcsw - nvcsw) > 1)
+			break;
+		if ((p->nivcsw - nivcsw) > 1)
+			break;
+
+		cpu_relax();
+	}
+}
+
+/*
  * wait_task_inactive - wait for a thread to unschedule.
  *
  * If @match_state is nonzero, it's the @p->state value just checked and
@@ -2458,6 +2503,17 @@ out:
 	return success;
 }
 
+/**
+ * wake_up_process - Wake up a specific process
+ * @p: The process to be woken up.
+ *
+ * Attempt to wake up the nominated process and move it to the set of runnable
+ * processes.  Returns 1 if the process was woken up, 0 if it was already
+ * running.
+ *
+ * It may be assumed that this function implies a write memory barrier before
+ * changing the task state if and only if any tasks are woken up.
+ */
 int wake_up_process(struct task_struct *p)
 {
 	return try_to_wake_up(p, TASK_ALL, 0);
@@ -2766,7 +2822,7 @@ context_switch(struct rq *rq, struct task_struct *prev,
 	 * combine the page table reload and the switch backend into
 	 * one hypercall.
 	 */
-	arch_enter_lazy_cpu_mode();
+	arch_start_context_switch(prev);
 
 	if (unlikely(!mm)) {
 		next->active_mm = oldmm;
@@ -2856,19 +2912,72 @@ unsigned long nr_iowait(void)
 	return sum;
 }
 
-unsigned long nr_active(void)
+/* Variables and functions for calc_load */
+static atomic_long_t calc_load_tasks;
+static unsigned long calc_load_update;
+unsigned long avenrun[3];
+EXPORT_SYMBOL(avenrun);
+
+/**
+ * get_avenrun - get the load average array
+ * @loads:	pointer to dest load array
+ * @offset:	offset to add
+ * @shift:	shift count to shift the result left
+ *
+ * These values are estimates at best, so no need for locking.
+ */
+void get_avenrun(unsigned long *loads, unsigned long offset, int shift)
+{
+	loads[0] = (avenrun[0] + offset) << shift;
+	loads[1] = (avenrun[1] + offset) << shift;
+	loads[2] = (avenrun[2] + offset) << shift;
+}
+
+static unsigned long
+calc_load(unsigned long load, unsigned long exp, unsigned long active)
 {
-	unsigned long i, running = 0, uninterruptible = 0;
+	load *= exp;
+	load += active * (FIXED_1 - exp);
+	return load >> FSHIFT;
+}
 
-	for_each_online_cpu(i) {
-		running += cpu_rq(i)->nr_running;
-		uninterruptible += cpu_rq(i)->nr_uninterruptible;
-	}
+/*
+ * calc_load - update the avenrun load estimates 10 ticks after the
+ * CPUs have updated calc_load_tasks.
+ */
+void calc_global_load(void)
+{
+	unsigned long upd = calc_load_update + 10;
+	long active;
 
-	if (unlikely((long)uninterruptible < 0))
-		uninterruptible = 0;
+	if (time_before(jiffies, upd))
+		return;
 
-	return running + uninterruptible;
+	active = atomic_long_read(&calc_load_tasks);
+	active = active > 0 ? active * FIXED_1 : 0;
+
+	avenrun[0] = calc_load(avenrun[0], EXP_1, active);
+	avenrun[1] = calc_load(avenrun[1], EXP_5, active);
+	avenrun[2] = calc_load(avenrun[2], EXP_15, active);
+
+	calc_load_update += LOAD_FREQ;
+}
+
+/*
+ * Either called from update_cpu_load() or from a cpu going idle
+ */
+static void calc_load_account_active(struct rq *this_rq)
+{
+	long nr_active, delta;
+
+	nr_active = this_rq->nr_running;
+	nr_active += (long) this_rq->nr_uninterruptible;
+
+	if (nr_active != this_rq->calc_load_active) {
+		delta = nr_active - this_rq->calc_load_active;
+		this_rq->calc_load_active = nr_active;
+		atomic_long_add(delta, &calc_load_tasks);
+	}
 }
 
 /*
@@ -2899,6 +3008,11 @@ static void update_cpu_load(struct rq *this_rq)
 			new_load += scale-1;
 		this_rq->cpu_load[i] = (old_load*(scale-1) + new_load) >> i;
 	}
+
+	if (time_after_eq(jiffies, this_rq->calc_load_update)) {
+		this_rq->calc_load_update += LOAD_FREQ;
+		calc_load_account_active(this_rq);
+	}
 }
 
 #ifdef CONFIG_SMP
@@ -4240,10 +4354,126 @@ static void active_load_balance(struct rq *busiest_rq, int busiest_cpu)
 static struct {
 	atomic_t load_balancer;
 	cpumask_var_t cpu_mask;
+	cpumask_var_t ilb_grp_nohz_mask;
 } nohz ____cacheline_aligned = {
 	.load_balancer = ATOMIC_INIT(-1),
 };
 
+#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT)
+/**
+ * lowest_flag_domain - Return lowest sched_domain containing flag.
+ * @cpu:	The cpu whose lowest level of sched domain is to
+ *		be returned.
+ * @flag:	The flag to check for the lowest sched_domain
+ *		for the given cpu.
+ *
+ * Returns the lowest sched_domain of a cpu which contains the given flag.
+ */
+static inline struct sched_domain *lowest_flag_domain(int cpu, int flag)
+{
+	struct sched_domain *sd;
+
+	for_each_domain(cpu, sd)
+		if (sd && (sd->flags & flag))
+			break;
+
+	return sd;
+}
+
+/**
+ * for_each_flag_domain - Iterates over sched_domains containing the flag.
+ * @cpu:	The cpu whose domains we're iterating over.
+ * @sd:		variable holding the value of the power_savings_sd
+ *		for cpu.
+ * @flag:	The flag to filter the sched_domains to be iterated.
+ *
+ * Iterates over all the scheduler domains for a given cpu that has the 'flag'
+ * set, starting from the lowest sched_domain to the highest.
+ */
+#define for_each_flag_domain(cpu, sd, flag) \
+	for (sd = lowest_flag_domain(cpu, flag); \
+		(sd && (sd->flags & flag)); sd = sd->parent)
+
+/**
+ * is_semi_idle_group - Checks if the given sched_group is semi-idle.
+ * @ilb_group:	group to be checked for semi-idleness
+ *
+ * Returns:	1 if the group is semi-idle. 0 otherwise.
+ *
+ * We define a sched_group to be semi idle if it has atleast one idle-CPU
+ * and atleast one non-idle CPU. This helper function checks if the given
+ * sched_group is semi-idle or not.
+ */
+static inline int is_semi_idle_group(struct sched_group *ilb_group)
+{
+	cpumask_and(nohz.ilb_grp_nohz_mask, nohz.cpu_mask,
+					sched_group_cpus(ilb_group));
+
+	/*
+	 * A sched_group is semi-idle when it has atleast one busy cpu
+	 * and atleast one idle cpu.
+	 */
+	if (cpumask_empty(nohz.ilb_grp_nohz_mask))
+		return 0;
+
+	if (cpumask_equal(nohz.ilb_grp_nohz_mask, sched_group_cpus(ilb_group)))
+		return 0;
+
+	return 1;
+}
+/**
+ * find_new_ilb - Finds the optimum idle load balancer for nomination.
+ * @cpu:	The cpu which is nominating a new idle_load_balancer.
+ *
+ * Returns:	Returns the id of the idle load balancer if it exists,
+ *		Else, returns >= nr_cpu_ids.
+ *
+ * This algorithm picks the idle load balancer such that it belongs to a
+ * semi-idle powersavings sched_domain. The idea is to try and avoid
+ * completely idle packages/cores just for the purpose of idle load balancing
+ * when there are other idle cpu's which are better suited for that job.
+ */
+static int find_new_ilb(int cpu)
+{
+	struct sched_domain *sd;
+	struct sched_group *ilb_group;
+
+	/*
+	 * Have idle load balancer selection from semi-idle packages only
+	 * when power-aware load balancing is enabled
+	 */
+	if (!(sched_smt_power_savings || sched_mc_power_savings))
+		goto out_done;
+
+	/*
+	 * Optimize for the case when we have no idle CPUs or only one
+	 * idle CPU. Don't walk the sched_domain hierarchy in such cases
+	 */
+	if (cpumask_weight(nohz.cpu_mask) < 2)
+		goto out_done;
+
+	for_each_flag_domain(cpu, sd, SD_POWERSAVINGS_BALANCE) {
+		ilb_group = sd->groups;
+
+		do {
+			if (is_semi_idle_group(ilb_group))
+				return cpumask_first(nohz.ilb_grp_nohz_mask);
+
+			ilb_group = ilb_group->next;
+
+		} while (ilb_group != sd->groups);
+	}
+
+out_done:
+	return cpumask_first(nohz.cpu_mask);
+}
+#else /*  (CONFIG_SCHED_MC || CONFIG_SCHED_SMT) */
+static inline int find_new_ilb(int call_cpu)
+{
+	return cpumask_first(nohz.cpu_mask);
+}
+#endif
+
 /*
  * This routine will try to nominate the ilb (idle load balancing)
  * owner among the cpus whose ticks are stopped. ilb owner will do the idle
@@ -4298,8 +4528,24 @@ int select_nohz_load_balancer(int stop_tick)
 			/* make me the ilb owner */
 			if (atomic_cmpxchg(&nohz.load_balancer, -1, cpu) == -1)
 				return 1;
-		} else if (atomic_read(&nohz.load_balancer) == cpu)
+		} else if (atomic_read(&nohz.load_balancer) == cpu) {
+			int new_ilb;
+
+			if (!(sched_smt_power_savings ||
+						sched_mc_power_savings))
+				return 1;
+			/*
+			 * Check to see if there is a more power-efficient
+			 * ilb.
+			 */
+			new_ilb = find_new_ilb(cpu);
+			if (new_ilb < nr_cpu_ids && new_ilb != cpu) {
+				atomic_set(&nohz.load_balancer, -1);
+				resched_cpu(new_ilb);
+				return 0;
+			}
 			return 1;
+		}
 	} else {
 		if (!cpumask_test_cpu(cpu, nohz.cpu_mask))
 			return 0;
@@ -4468,15 +4714,7 @@ static inline void trigger_load_balance(struct rq *rq, int cpu)
 		}
 
 		if (atomic_read(&nohz.load_balancer) == -1) {
-			/*
-			 * simple selection for now: Nominate the
-			 * first cpu in the nohz list to be the next
-			 * ilb owner.
-			 *
-			 * TBD: Traverse the sched domains and nominate
-			 * the nearest cpu in the nohz.cpu_mask.
-			 */
-			int ilb = cpumask_first(nohz.cpu_mask);
+			int ilb = find_new_ilb(cpu);
 
 			if (ilb < nr_cpu_ids)
 				resched_cpu(ilb);
@@ -5007,13 +5245,15 @@ pick_next_task(struct rq *rq)
 /*
  * schedule() is the main scheduler function.
  */
-asmlinkage void __sched __schedule(void)
+asmlinkage void __sched schedule(void)
 {
 	struct task_struct *prev, *next;
 	unsigned long *switch_count;
 	struct rq *rq;
 	int cpu;
 
+need_resched:
+	preempt_disable();
 	cpu = smp_processor_id();
 	rq = cpu_rq(cpu);
 	rcu_qsctr_inc(cpu);
@@ -5070,15 +5310,9 @@ need_resched_nonpreemptible:
 
 	if (unlikely(reacquire_kernel_lock(current) < 0))
 		goto need_resched_nonpreemptible;
-}
 
-asmlinkage void __sched schedule(void)
-{
-need_resched:
-	preempt_disable();
-	__schedule();
 	preempt_enable_no_resched();
-	if (unlikely(test_thread_flag(TIF_NEED_RESCHED)))
+	if (need_resched())
 		goto need_resched;
 }
 EXPORT_SYMBOL(schedule);
@@ -5221,7 +5455,7 @@ EXPORT_SYMBOL(default_wake_function);
  * started to run but is not in state TASK_RUNNING. try_to_wake_up() returns
  * zero in this (rare) case, and we handle it by continuing to scan the queue.
  */
-void __wake_up_common(wait_queue_head_t *q, unsigned int mode,
+static void __wake_up_common(wait_queue_head_t *q, unsigned int mode,
 			int nr_exclusive, int sync, void *key)
 {
 	wait_queue_t *curr, *next;
@@ -5241,6 +5475,9 @@ void __wake_up_common(wait_queue_head_t *q, unsigned int mode,
  * @mode: which threads
  * @nr_exclusive: how many wake-one or wake-many threads to wake up
  * @key: is directly passed to the wakeup function
+ *
+ * It may be assumed that this function implies a write memory barrier before
+ * changing the task state if and only if any tasks are woken up.
  */
 void __wake_up(wait_queue_head_t *q, unsigned int mode,
 			int nr_exclusive, void *key)
@@ -5279,6 +5516,9 @@ void __wake_up_locked_key(wait_queue_head_t *q, unsigned int mode, void *key)
  * with each other. This can prevent needless bouncing between CPUs.
  *
  * On UP it can prevent extra preemption.
+ *
+ * It may be assumed that this function implies a write memory barrier before
+ * changing the task state if and only if any tasks are woken up.
  */
 void __wake_up_sync_key(wait_queue_head_t *q, unsigned int mode,
 			int nr_exclusive, void *key)
@@ -5315,6 +5555,9 @@ EXPORT_SYMBOL_GPL(__wake_up_sync);	/* For internal use only */
  * awakened in the same order in which they were queued.
  *
  * See also complete_all(), wait_for_completion() and related routines.
+ *
+ * It may be assumed that this function implies a write memory barrier before
+ * changing the task state if and only if any tasks are woken up.
  */
 void complete(struct completion *x)
 {
@@ -5332,6 +5575,9 @@ EXPORT_SYMBOL(complete);
  * @x:  holds the state of this particular completion
  *
  * This will wake up all threads waiting on this particular completion event.
+ *
+ * It may be assumed that this function implies a write memory barrier before
+ * changing the task state if and only if any tasks are woken up.
  */
 void complete_all(struct completion *x)
 {
@@ -6490,8 +6736,9 @@ void sched_show_task(struct task_struct *p)
 #ifdef CONFIG_DEBUG_STACK_USAGE
 	free = stack_not_used(p);
 #endif
-	printk(KERN_CONT "%5lu %5d %6d\n", free,
-		task_pid_nr(p), task_pid_nr(p->real_parent));
+	printk(KERN_CONT "%5lu %5d %6d 0x%08lx\n", free,
+		task_pid_nr(p), task_pid_nr(p->real_parent),
+		(unsigned long)task_thread_info(p)->flags);
 
 	show_stack(p, NULL);
 }
@@ -6970,6 +7217,14 @@ static void migrate_dead_tasks(unsigned int dead_cpu)
 
 	}
 }
+
+/*
+ * remove the tasks which were accounted by rq from calc_load_tasks.
+ */
+static void calc_global_load_remove(struct rq *rq)
+{
+	atomic_long_sub(rq->calc_load_active, &calc_load_tasks);
+}
 #endif /* CONFIG_HOTPLUG_CPU */
 
 #if defined(CONFIG_SCHED_DEBUG) && defined(CONFIG_SYSCTL)
@@ -7204,6 +7459,8 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu)
 		/* Update our root-domain */
 		rq = cpu_rq(cpu);
 		spin_lock_irqsave(&rq->lock, flags);
+		rq->calc_load_update = calc_load_update;
+		rq->calc_load_active = 0;
 		if (rq->rd) {
 			BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span));
 
@@ -7243,7 +7500,7 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu)
 		cpuset_unlock();
 		migrate_nr_uninterruptible(rq);
 		BUG_ON(rq->nr_running != 0);
-
+		calc_global_load_remove(rq);
 		/*
 		 * No need to migrate the tasks: it was best-effort if
 		 * they didn't take sched_hotcpu_mutex. Just wake up
@@ -7753,8 +8010,9 @@ int sched_smt_power_savings = 0, sched_mc_power_savings = 0;
 
 /*
  * The cpus mask in sched_group and sched_domain hangs off the end.
- * FIXME: use cpumask_var_t or dynamic percpu alloc to avoid wasting space
- * for nr_cpu_ids < CONFIG_NR_CPUS.
+ *
+ * ( See the the comments in include/linux/sched.h:struct sched_group
+ *   and struct sched_domain. )
  */
 struct static_sched_group {
 	struct sched_group sg;
@@ -7875,7 +8133,7 @@ static void init_numa_sched_groups_power(struct sched_group *group_head)
 			struct sched_domain *sd;
 
 			sd = &per_cpu(phys_domains, j).sd;
-			if (j != cpumask_first(sched_group_cpus(sd->groups))) {
+			if (j != group_first_cpu(sd->groups)) {
 				/*
 				 * Only add "power" once for each
 				 * physical package.
@@ -7953,7 +8211,7 @@ static void init_sched_groups_power(int cpu, struct sched_domain *sd)
 
 	WARN_ON(!sd || !sd->groups);
 
-	if (cpu != cpumask_first(sched_group_cpus(sd->groups)))
+	if (cpu != group_first_cpu(sd->groups))
 		return;
 
 	child = sd->child;
@@ -8938,6 +9196,8 @@ void __init sched_init(void)
 		rq = cpu_rq(i);
 		spin_lock_init(&rq->lock);
 		rq->nr_running = 0;
+		rq->calc_load_active = 0;
+		rq->calc_load_update = jiffies + LOAD_FREQ;
 		init_cfs_rq(&rq->cfs, rq);
 		init_rt_rq(&rq->rt, rq);
 #ifdef CONFIG_FAIR_GROUP_SCHED
@@ -9045,6 +9305,9 @@ void __init sched_init(void)
 	 * when this runqueue becomes "idle".
 	 */
 	init_idle(current, smp_processor_id());
+
+	calc_load_update = jiffies + LOAD_FREQ;
+
 	/*
 	 * During early bootup we pretend to be a normal task:
 	 */
@@ -9055,6 +9318,7 @@ void __init sched_init(void)
 #ifdef CONFIG_SMP
 #ifdef CONFIG_NO_HZ
 	alloc_bootmem_cpumask_var(&nohz.cpu_mask);
+	alloc_bootmem_cpumask_var(&nohz.ilb_grp_nohz_mask);
 #endif
 	alloc_bootmem_cpumask_var(&cpu_isolated_map);
 #endif /* SMP */
@@ -9800,6 +10064,13 @@ static int sched_rt_global_constraints(void)
 	if (sysctl_sched_rt_period <= 0)
 		return -EINVAL;
 
+	/*
+	 * There's always some RT tasks in the root group
+	 * -- migration, kstopmachine etc..
+	 */
+	if (sysctl_sched_rt_runtime == 0)
+		return -EBUSY;
+
 	spin_lock_irqsave(&def_rt_bandwidth.rt_runtime_lock, flags);
 	for_each_possible_cpu(i) {
 		struct rt_rq *rt_rq = &cpu_rq(i)->rt;