scheduler fixes
Linus,
Please pull the latest sched-fixes-for-linus git tree from:
git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git sched-fixes-for-linus
Thanks,
Ingo
------------------>
Amit K. Arora (1):
sched: Make sure timers have migrated before killing the migration_thread
Peter Zijlstra (2):
sched: Fix wake_affine() vs RT tasks
sched, trace: Fix sched_switch() prev_state argument
include/trace/events/sched.h | 19 ++++++++++++++++++- kernel/sched.c | 24 ++++++------------------ kernel/sched_fair.c | 22 ++++++++++++++++------ kernel/stop_machine.c | 2 +- 4 files changed, 41 insertions(+), 26 deletions(-)
include/trace/events/sched.h +18 -1
@@ -115,6 +115,23 @@ DEFINE_EVENT(sched_wakeup_template, sched_wakeup_new, TP_PROTO(struct task_struct *p, int success), TP_ARGS(p, success)); +#ifdef CREATE_TRACE_POINTS +static inline long __trace_sched_switch_state (struct task_struct *p) +{ +long state = p->state; + +#ifdef CONFIG_PREEMPT +/* +* For all intents and purposes a preempted task is a running task. +*/ +if (task_thread_info (p)->preempt_count &PREEMPT_ACTIVE ) + state =TASK_RUNNING ; +#endif + +return state; +} +#endif +/* * Tracepoint for task switches, performed by the scheduler: */
@@ -139,7 +156,7 @@ TRACE_EVENT(sched_switch,memcpy (__entry->next_comm, next->comm,TASK_COMM_LEN ); __entry->prev_pid = prev->pid; __entry->prev_prio = prev->prio; - __entry->prev_state = prev->state; + __entry->prev_state =__trace_sched_switch_state (prev);memcpy (__entry->prev_comm, prev->comm,TASK_COMM_LEN ); __entry->next_pid = next->pid; __entry->next_prio = next->prio;
kernel/sched.c +6 -18
@@ -544,6 +544,8 @@ struct rq {struct root_domain *rd;struct sched_domain *sd; +unsigned long cpu_power; +unsigned char idle_at_tick;/* For active balancing */ int post_schedule;
@@ -1499,24 +1501,9 @@ static unsigned long target_load(int cpu, int type)return max (rq->cpu_load[type-1 ], total); } -static struct sched_group *group_of (int cpu) -{ -struct sched_domain *sd =rcu_dereference_sched (cpu_rq (cpu)->sd); - -if (!sd) -return NULL ; - -return sd->groups; -} -static unsigned long power_of (int cpu) { -struct sched_group *group =group_of (cpu); - -if (!group) -return SCHED_LOAD_SCALE ; - -return group->cpu_power; +return cpu_rq (cpu)->cpu_power; }static int task_hot (struct task_struct *p,u64 now,struct sched_domain *sd);
@@ -1854,8 +1841,8 @@ static void dec_nr_running(struct rq *rq)static void set_load_weight (struct task_struct *p) {if (task_has_rt_policy (p)) { - p->se.load.weight = prio_to_weight[0 ] *2 ; - p->se.load.inv_weight = prio_to_wmult[0 ] >>1 ; + p->se.load.weight =0 ; + p->se.load.inv_weight =WMULT_CONST ;return ; }
@@ -7605,6 +7592,7 @@ void __init sched_init(void)#ifdef CONFIG_SMP rq->sd =NULL ; rq->rd =NULL ; + rq->cpu_power =SCHED_LOAD_SCALE ; rq->post_schedule =0 ; rq->active_balance =0 ; rq->next_balance = jiffies;
kernel/sched_fair.c +16 -6
@@ -1225,7 +1225,6 @@ static int wake_affine(struct sched_domain *sd, struct task_struct *p, int sync)unsigned long this_load, load;int idx, this_cpu, prev_cpu;unsigned long tl_per_task; -unsigned int imbalance;struct task_group *tg;unsigned long weight;int balanced;
@@ -1252,8 +1251,6 @@ static int wake_affine(struct sched_domain *sd, struct task_struct *p, int sync) tg =task_group (p); weight = p->se.load.weight; - imbalance =100 + (sd->imbalance_pct -100 ) /2 ; -/* * In low-load situations, where prev_cpu is idle and this_cpu is idle * due to the sync cause above having dropped this_load to 0, we'll
@@ -1263,9 +1260,21 @@ static int wake_affine(struct sched_domain *sd, struct task_struct *p, int sync)* Otherwise check if either cpus are near enough in load to allow this * task to be woken on this_cpu. */ - balanced = !this_load || -100 *(this_load +effective_load (tg, this_cpu, weight, weight)) <= - imbalance*(load +effective_load (tg, prev_cpu,0 , weight)); +if (this_load) { +unsigned long this_eff_load, prev_eff_load; + + this_eff_load =100 ; + this_eff_load *=power_of (prev_cpu); + this_eff_load *= this_load + +effective_load (tg, this_cpu, weight, weight); + + prev_eff_load =100 + (sd->imbalance_pct -100 ) /2 ; + prev_eff_load *=power_of (this_cpu); + prev_eff_load *= load +effective_load (tg, prev_cpu,0 , weight); + + balanced = this_eff_load <= prev_eff_load; + }else + balanced = true;/* * If the currently running task will sleep within
@@ -2298,6 +2307,7 @@ static void update_cpu_power(struct sched_domain *sd, int cpu)if (!power) power =1 ; +cpu_rq (cpu)->cpu_power = power; sdg->cpu_power = power; }
kernel/stop_machine.c +1 -1
@@ -321,7 +321,7 @@ static int __cpuinit cpu_stop_cpu_callback(struct notifier_block *nfb,#ifdef CONFIG_HOTPLUG_CPU case CPU_UP_CANCELED : -case CPU_DEAD : +case CPU_POST_DEAD : {struct cpu_stop_work *work;