Merge commit 'v2.6.30-rc5' into sched/core
Merge reason: sched/core was on .30-rc1 before, update to latest fixes
Signed-off-by: Ingo Molnar <mingo@elte.hu>
diff --git a/Documentation/scheduler/sched-rt-group.txt b/Documentation/scheduler/sched-rt-group.txt
index 5ba4d3f..eb74b01 100644
--- a/Documentation/scheduler/sched-rt-group.txt
+++ b/Documentation/scheduler/sched-rt-group.txt
@@ -4,6 +4,7 @@
CONTENTS
========
+0. WARNING
1. Overview
1.1 The problem
1.2 The solution
@@ -14,6 +15,23 @@
3. Future plans
+0. WARNING
+==========
+
+ Fiddling with these settings can result in an unstable system, the knobs are
+ root only and assumes root knows what he is doing.
+
+Most notable:
+
+ * very small values in sched_rt_period_us can result in an unstable
+ system when the period is smaller than either the available hrtimer
+ resolution, or the time it takes to handle the budget refresh itself.
+
+ * very small values in sched_rt_runtime_us can result in an unstable
+ system when the runtime is so small the system has difficulty making
+ forward progress (NOTE: the migration thread and kstopmachine both
+ are real-time processes).
+
1. Overview
===========
diff --git a/include/linux/wait.h b/include/linux/wait.h
index bc02463..6788e1a 100644
--- a/include/linux/wait.h
+++ b/include/linux/wait.h
@@ -132,8 +132,6 @@
list_del(&old->task_list);
}
-void __wake_up_common(wait_queue_head_t *q, unsigned int mode,
- int nr_exclusive, int sync, void *key);
void __wake_up(wait_queue_head_t *q, unsigned int mode, int nr, void *key);
void __wake_up_locked_key(wait_queue_head_t *q, unsigned int mode, void *key);
void __wake_up_sync_key(wait_queue_head_t *q, unsigned int mode, int nr,
diff --git a/kernel/mutex.c b/kernel/mutex.c
index 507cf2b..6ca5fe9 100644
--- a/kernel/mutex.c
+++ b/kernel/mutex.c
@@ -249,7 +249,9 @@
/* didnt get the lock, go to sleep: */
spin_unlock_mutex(&lock->wait_lock, flags);
- __schedule();
+ preempt_enable_no_resched();
+ schedule();
+ preempt_disable();
spin_lock_mutex(&lock->wait_lock, flags);
}
diff --git a/kernel/sched.c b/kernel/sched.c
index 26efa47..8908d19 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -4240,10 +4240,126 @@
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 +4414,24 @@
/* 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 +4600,7 @@
}
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 +5131,15 @@
/*
* 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 +5196,9 @@
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 +5341,7 @@
* 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;
@@ -6490,8 +6610,9 @@
#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);
}
@@ -7875,7 +7996,7 @@
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 +8074,7 @@
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;
@@ -9055,6 +9176,7 @@
#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 +9922,13 @@
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;
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 3816f21..5f9650e 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -1487,17 +1487,10 @@
find_matching_se(&se, &pse);
- while (se) {
- BUG_ON(!pse);
+ BUG_ON(!pse);
- if (wakeup_preempt_entity(se, pse) == 1) {
- resched_task(curr);
- break;
- }
-
- se = parent_entity(se);
- pse = parent_entity(pse);
- }
+ if (wakeup_preempt_entity(se, pse) == 1)
+ resched_task(curr);
}
static struct task_struct *pick_next_task_fair(struct rq *rq)
diff --git a/kernel/wait.c b/kernel/wait.c
index 42a2dbc..ea7c3b4 100644
--- a/kernel/wait.c
+++ b/kernel/wait.c
@@ -154,7 +154,7 @@
if (!list_empty(&wait->task_list))
list_del_init(&wait->task_list);
else if (waitqueue_active(q))
- __wake_up_common(q, mode, 1, 0, key);
+ __wake_up_locked_key(q, mode, key);
spin_unlock_irqrestore(&q->lock, flags);
}
EXPORT_SYMBOL(abort_exclusive_wait);