@@ -899,6 +899,7 @@ struct sched_domain {
unsigned int wake_idx;
unsigned int forkexec_idx;
unsigned int smt_gain;
+ unsigned long nohz_flags; /* NOHZ_IDLE flag status */
int flags; /* See SD_* */
int level;
@@ -5394,14 +5394,21 @@ static inline void set_cpu_sd_state_busy(void)
{
struct sched_domain *sd;
int cpu = smp_processor_id();
-
- if (!test_bit(NOHZ_IDLE, nohz_flags(cpu)))
- return;
- clear_bit(NOHZ_IDLE, nohz_flags(cpu));
+ int first_nohz_idle = 1;
rcu_read_lock();
- for_each_domain(cpu, sd)
+ for_each_domain(cpu, sd) {
+ if (first_nohz_idle) {
+ if (!test_bit(NOHZ_IDLE, &sd->nohz_flags))
+ goto unlock;
+
+ clear_bit(NOHZ_IDLE, &sd->nohz_flags);
+ first_nohz_idle = 0;
+ }
+
atomic_inc(&sd->groups->sgp->nr_busy_cpus);
+ }
+unlock:
rcu_read_unlock();
}
@@ -5409,14 +5416,21 @@ void set_cpu_sd_state_idle(void)
{
struct sched_domain *sd;
int cpu = smp_processor_id();
-
- if (test_bit(NOHZ_IDLE, nohz_flags(cpu)))
- return;
- set_bit(NOHZ_IDLE, nohz_flags(cpu));
+ int first_nohz_idle = 1;
rcu_read_lock();
- for_each_domain(cpu, sd)
+ for_each_domain(cpu, sd) {
+ if (first_nohz_idle) {
+ if (test_bit(NOHZ_IDLE, &sd->nohz_flags))
+ goto unlock;
+
+ set_bit(NOHZ_IDLE, &sd->nohz_flags);
+ first_nohz_idle = 0;
+ }
+
atomic_dec(&sd->groups->sgp->nr_busy_cpus);
+ }
+unlock:
rcu_read_unlock();
}
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. 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_flags has been added to sched_domain so both flags and sched_domain will share the same RCU lifecycle and will be always synchronized. This solution is prefered to the creation of a new struct with an extra pointer indirection. The synchronization is done at the cost of : - An additional indirection and a rcu_dereference for accessing the NOHZ_IDLE flag. - We use only the nohz_flags field of the top sched_domain. Change since v6: - Add the flags in struct sched_domain instead of creating a sched_domain_rq. Change since v5: - minor variable and function name change. - remove a useless null check before kfree - fix a compilation error when NO_HZ is not set. Change since v4: - link both sched_domain and NOHZ_IDLE flag in one RCU object so their states are always synchronized. Change since V3; - NOHZ flag is not cleared if a NULL domain is attached to the CPU - Remove patch 2/2 which becomes useless with latest modifications Change since V2: - change the initialization to idle state instead of busy state so a CPU that enters idle during the build of the sched_domain will not corrupt the initialization state Change since V1: - remove the patch for SCHED softirq on an idle core use case as it was a side effect of the other use cases. Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org> --- include/linux/sched.h | 1 + kernel/sched/fair.c | 34 ++++++++++++++++++++++++---------- 2 files changed, 25 insertions(+), 10 deletions(-)