The smpboot threads rely on the park/unpark mechanism which binds per cpu threads on a particular core. Though the functionality is racy: CPU0 CPU1 CPU2 unpark(T) wake_up_process(T) clear(SHOULD_PARK) T runs leave parkme() due to !SHOULD_PARK bind_to(CPU2) BUG_ON(wrong CPU) We cannot let the tasks move themself to the target CPU as one of those tasks is actually the migration thread itself, which requires that it starts running on the target cpu right away. The solution to this problem is to prevent wakeups in park mode which are not from unpark(). That way we can guarantee that the association of the task to the target cpu is working correctly. Add a new task state (TASK_PARKED) which prevents other wakeups and use this state explicitly for the unpark wakeup. Peter noticed: Also, since the task state is visible to userspace and all the parked tasks are still in the PID space, its a good hint in ps and friends that these tasks aren't really there for the moment. The migration thread has another related issue. CPU0 CPU1 Bring up CPU2 create_thread(T) park(T) wait_for_completion() parkme() complete() sched_set_stop_task() schedule(TASK_PARKED) The sched_set_stop_task() call is issued while the task is on the runqueue of CPU1 and that confuses the hell out of the stop_task class on that cpu. So we need the same synchronizaion before sched_set_stop_task().
Showing the changes to kernel/smpboot.c (1 of 5 files). Show all
Unified · Split
| @@ -185,8 +185,18 @@ __smpboot_create_thread(struct smp_hotplug_thread *ht, unsigned int cpu) · 184 unmodified lines | |||
| 185 | } | 185 | } |
| 186 | get_task_struct(tsk); | 186 | get_task_struct(tsk); |
| 187 | *per_cpu_ptr(ht->store, cpu) = tsk; | 187 | *per_cpu_ptr(ht->store, cpu) = tsk; |
| 188 | if (ht->create) | 188 | if (ht->create) { |
| 189 | ht->create(cpu); | 189 | /* |
| 190 | * Make sure that the task has actually scheduled out | ||
| 191 | * into park position, before calling the create | ||
| 192 | * callback. At least the migration thread callback | ||
| 193 | * requires that the task is off the runqueue. | ||
| 194 | */ | ||
| 195 | if (!wait_task_inactive(tsk, TASK_PARKED)) | ||
| 196 | WARN_ON(1); | ||
| 197 | else | ||
| 198 | ht->create(cpu); | ||
| 199 | } | ||
| 190 | return 0; | 200 | return 0; |
| 191 | } | 201 | } |
| 192 | 202 | ||