On 8 February 2013 19:05, Vincent Guittot vincent.guittot@linaro.org wrote:
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 seems to be: 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. We set the NOHZ_IDLE flag when nr_busy_cpus is initialized to 0 in order to have a coherent configuration.
The patch 2/2 protects this init against an update of NOHZ_IDLE flag because a NULL sched_domain is attached to the CPU during the build of the new sched_domain so nohz_kick_needed and set_cpu_sd_state_busy are not called and can't clear the NOHZ_IDLE flag
Hi Frederic,
With this v3, the initialization of NOHZ_IDLE and nr_busy_cpus is be protected against any race condition because the initial state is the idle state so if a cpu enters idle, it keeps the same state and we can't set a busy state until the initialization is complete thanks to the NULL domain.
Regards, Vincent
Signed-off-by: Vincent Guittot vincent.guittot@linaro.org
kernel/sched/core.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 26058d0..c730a4e 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -5884,7 +5884,9 @@ static void init_sched_groups_power(int cpu, struct sched_domain *sd) return;
update_group_power(sd, cpu);
atomic_set(&sg->sgp->nr_busy_cpus, sg->group_weight);
atomic_set(&sg->sgp->nr_busy_cpus, 0);set_bit(NOHZ_IDLE, nohz_flags(cpu));}
int __weak arch_sd_sibling_asym_packing(void)
1.7.9.5