aboutsummaryrefslogtreecommitdiffstats
path: root/kernel/sched
diff options
context:
space:
mode:
authorVincent Guittot <vincent.guittot@linaro.org>2013-04-23 10:59:02 -0400
committerIngo Molnar <mingo@kernel.org>2013-04-26 06:13:44 -0400
commit25f55d9d01ad7a7ad248fd5af1d22675ffd202c5 (patch)
treedc6ba0d1f4dc8119c7dd4d0844fa31a8ed60bf6f /kernel/sched
parente02e60c109ca70935bad1131976bdbf5160cf576 (diff)
sched: Fix init NOHZ_IDLE flag
On my SMP platform which is made of 5 cores in 2 clusters, I have the nr_busy_cpu field of sched_group_power struct that is not null when the platform is fully idle - which makes the scheduler unhappy. The root cause is: During the boot sequence, some CPUs reach the idle loop and set their NOHZ_IDLE flag while waiting for others CPUs to boot. But the nr_busy_cpus field is initialized later with the assumption that all CPUs are in the busy state whereas some CPUs have already set their NOHZ_IDLE flag. More generally, the NOHZ_IDLE flag must be initialized when new sched_domains are created in order to ensure that NOHZ_IDLE and nr_busy_cpus are aligned. This condition can be ensured by adding a synchronize_rcu() between the destruction of old sched_domains and the creation of new ones so the NOHZ_IDLE flag will not be updated with old sched_domain once it has been initialized. But this solution introduces a additionnal latency in the rebuild sequence that is called during cpu hotplug. As suggested by Frederic Weisbecker, another solution is to have the same rcu lifecycle for both NOHZ_IDLE and sched_domain struct. A new nohz_idle field is added to sched_domain so both status and sched_domain will share the same RCU lifecycle and will be always synchronized. In addition, there is no more need to protect nohz_idle against concurrent access as it is only modified by 2 exclusive functions called by local cpu. This solution has been prefered to the creation of a new struct with an extra pointer indirection for sched_domain. The synchronization is done at the cost of : - An additional indirection and a rcu_dereference for accessing nohz_idle. - We use only the nohz_idle field of the top sched_domain. Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: linaro-kernel@lists.linaro.org Cc: peterz@infradead.org Cc: fweisbec@gmail.com Cc: pjt@google.com Cc: rostedt@goodmis.org Cc: efault@gmx.de Link: http://lkml.kernel.org/r/1366729142-14662-1-git-send-email-vincent.guittot@linaro.org [ Fixed !NO_HZ build bug. ] Signed-off-by: Ingo Molnar <mingo@kernel.org>
Diffstat (limited to 'kernel/sched')
-rw-r--r--kernel/sched/fair.c26
-rw-r--r--kernel/sched/sched.h1
2 files changed, 16 insertions, 11 deletions
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index acaf567a03d2..8bf7081b1ec5 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -5420,13 +5420,16 @@ static inline void set_cpu_sd_state_busy(void)
5420 struct sched_domain *sd; 5420 struct sched_domain *sd;
5421 int cpu = smp_processor_id(); 5421 int cpu = smp_processor_id();
5422 5422
5423 if (!test_bit(NOHZ_IDLE, nohz_flags(cpu)))
5424 return;
5425 clear_bit(NOHZ_IDLE, nohz_flags(cpu));
5426
5427 rcu_read_lock(); 5423 rcu_read_lock();
5428 for_each_domain(cpu, sd) 5424 sd = rcu_dereference_check_sched_domain(cpu_rq(cpu)->sd);
5425
5426 if (!sd || !sd->nohz_idle)
5427 goto unlock;
5428 sd->nohz_idle = 0;
5429
5430 for (; sd; sd = sd->parent)
5429 atomic_inc(&sd->groups->sgp->nr_busy_cpus); 5431 atomic_inc(&sd->groups->sgp->nr_busy_cpus);
5432unlock:
5430 rcu_read_unlock(); 5433 rcu_read_unlock();
5431} 5434}
5432 5435
@@ -5435,13 +5438,16 @@ void set_cpu_sd_state_idle(void)
5435 struct sched_domain *sd; 5438 struct sched_domain *sd;
5436 int cpu = smp_processor_id(); 5439 int cpu = smp_processor_id();
5437 5440
5438 if (test_bit(NOHZ_IDLE, nohz_flags(cpu)))
5439 return;
5440 set_bit(NOHZ_IDLE, nohz_flags(cpu));
5441
5442 rcu_read_lock(); 5441 rcu_read_lock();
5443 for_each_domain(cpu, sd) 5442 sd = rcu_dereference_check_sched_domain(cpu_rq(cpu)->sd);
5443
5444 if (!sd || sd->nohz_idle)
5445 goto unlock;
5446 sd->nohz_idle = 1;
5447
5448 for (; sd; sd = sd->parent)
5444 atomic_dec(&sd->groups->sgp->nr_busy_cpus); 5449 atomic_dec(&sd->groups->sgp->nr_busy_cpus);
5450unlock:
5445 rcu_read_unlock(); 5451 rcu_read_unlock();
5446} 5452}
5447 5453
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 605426a63588..4c225c4c7111 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1303,7 +1303,6 @@ extern void account_cfs_bandwidth_used(int enabled, int was_enabled);
1303enum rq_nohz_flag_bits { 1303enum rq_nohz_flag_bits {
1304 NOHZ_TICK_STOPPED, 1304 NOHZ_TICK_STOPPED,
1305 NOHZ_BALANCE_KICK, 1305 NOHZ_BALANCE_KICK,
1306 NOHZ_IDLE,
1307}; 1306};
1308 1307
1309#define nohz_flags(cpu) (&cpu_rq(cpu)->nohz_flags) 1308#define nohz_flags(cpu) (&cpu_rq(cpu)->nohz_flags)