path: root/kernel/cpu.c
diff options
authorPeter Zijlstra <a.p.zijlstra@chello.nl>2009-11-25 13:31:39 +0100
committerIngo Molnar <mingo@elte.hu>2009-12-06 21:10:56 +0100
commit6ad4c18884e864cf4c77f9074d3d1816063f99cd (patch)
treef09643f6148b576fa2d23bf7d4b37d082d94e267 /kernel/cpu.c
parente1b8090bdf125f8b2e192149547fead7f302a89c (diff)
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>
Diffstat (limited to 'kernel/cpu.c')
1 files changed, 13 insertions, 5 deletions
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 6ba0f1ecb21..b2168864037 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -212,6 +212,8 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen)
err = __raw_notifier_call_chain(&cpu_chain, CPU_DOWN_PREPARE | mod,
hcpu, -1, &nr_calls);
if (err == NOTIFY_BAD) {
+ set_cpu_active(cpu, true);
__raw_notifier_call_chain(&cpu_chain, CPU_DOWN_FAILED | mod,
hcpu, nr_calls, NULL);
@@ -223,11 +225,11 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen)
/* Ensure that we are not runnable on dying cpu */
cpumask_copy(old_allowed, &current->cpus_allowed);
- set_cpus_allowed_ptr(current,
- cpumask_of(cpumask_any_but(cpu_online_mask, cpu)));
+ set_cpus_allowed_ptr(current, cpu_active_mask);
err = __stop_machine(take_cpu_down, &tcd_param, cpumask_of(cpu));
if (err) {
+ set_cpu_active(cpu, true);
/* CPU didn't die: tell everyone. Can't complain. */
if (raw_notifier_call_chain(&cpu_chain, CPU_DOWN_FAILED | mod,
hcpu) == NOTIFY_BAD)
@@ -292,9 +294,6 @@ int __ref cpu_down(unsigned int cpu)
err = _cpu_down(cpu, 0);
- if (cpu_online(cpu))
- set_cpu_active(cpu, true);
@@ -387,6 +386,15 @@ int disable_nonboot_cpus(void)
* with the userspace trying to use the CPU hotplug at the same time
+ for_each_online_cpu(cpu) {
+ if (cpu == first_cpu)
+ continue;
+ set_cpu_active(cpu, false);
+ }
+ synchronize_sched();
printk("Disabling non-boot CPUs ...\n");
for_each_online_cpu(cpu) {
if (cpu == first_cpu)