sched: Fix balance vs hotplug race
Since (e761b77
: cpu hotplug, sched: Introduce cpu_active_map and redo
sched domain managment) we have cpu_active_mask which is suppose to rule
scheduler migration and load-balancing, except it never (fully) did.
The particular problem being solved here is a crash in try_to_wake_up()
where select_task_rq() ends up selecting an offline cpu because
select_task_rq_fair() trusts the sched_domain tree to reflect the
current state of affairs, similarly select_task_rq_rt() trusts the
root_domain.
However, the sched_domains are updated from CPU_DEAD, which is after the
cpu is taken offline and after stop_machine is done. Therefore it can
race perfectly well with code assuming the domains are right.
Cure this by building the domains from cpu_active_mask on
CPU_DOWN_PREPARE.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
This commit is contained in:
committed by
Ingo Molnar
parent
e1b8090bdf
commit
6ad4c18884
@@ -84,6 +84,7 @@ extern const struct cpumask *const cpu_active_mask;
|
||||
#define num_online_cpus() cpumask_weight(cpu_online_mask)
|
||||
#define num_possible_cpus() cpumask_weight(cpu_possible_mask)
|
||||
#define num_present_cpus() cpumask_weight(cpu_present_mask)
|
||||
#define num_active_cpus() cpumask_weight(cpu_active_mask)
|
||||
#define cpu_online(cpu) cpumask_test_cpu((cpu), cpu_online_mask)
|
||||
#define cpu_possible(cpu) cpumask_test_cpu((cpu), cpu_possible_mask)
|
||||
#define cpu_present(cpu) cpumask_test_cpu((cpu), cpu_present_mask)
|
||||
@@ -92,6 +93,7 @@ extern const struct cpumask *const cpu_active_mask;
|
||||
#define num_online_cpus() 1
|
||||
#define num_possible_cpus() 1
|
||||
#define num_present_cpus() 1
|
||||
#define num_active_cpus() 1
|
||||
#define cpu_online(cpu) ((cpu) == 0)
|
||||
#define cpu_possible(cpu) ((cpu) == 0)
|
||||
#define cpu_present(cpu) ((cpu) == 0)
|
||||
|
Reference in New Issue
Block a user