summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorDmitry Adamushko <dmitry.adamushko@gmail.com>2008-07-13 04:10:29 +0400
committerIngo Molnar <mingo@elte.hu>2008-07-13 13:37:02 +0400
commit3e84050c81ffb4961ef43d20e1fb1d7607167d83 (patch)
tree62ae82ba6cc923222ab0053efcb8b2dec9b91ca0
parentb1e387348a2a70954312b102d0589c3e2ca3dba1 (diff)
downloadlinux-3e84050c81ffb4961ef43d20e1fb1d7607167d83.tar.xz
cpusets, hotplug, scheduler: fix scheduler domain breakage
Commit f18f982ab ("sched: CPU hotplug events must not destroy scheduler domains created by the cpusets") introduced a hotplug-related problem as described below: Upon CPU_DOWN_PREPARE, update_sched_domains() -> detach_destroy_domains(&cpu_online_map) does the following: /* * Force a reinitialization of the sched domains hierarchy. The domains * and groups cannot be updated in place without racing with the balancing * code, so we temporarily attach all running cpus to the NULL domain * which will prevent rebalancing while the sched domains are recalculated. */ The sched-domains should be rebuilt when a CPU_DOWN ops. has been completed, effectively either upon CPU_DEAD{_FROZEN} (upon success) or CPU_DOWN_FAILED{_FROZEN} (upon failure -- restore the things to their initial state). That's what update_sched_domains() also does but only for !CPUSETS case. With f18f982ab, sched-domains' reinitialization is delegated to CPUSETS code: cpuset_handle_cpuhp() -> common_cpu_mem_hotplug_unplug() -> rebuild_sched_domains() Being called for CPU_UP_PREPARE and if its callback is called after update_sched_domains()), it just negates all the work done by update_sched_domains() -- i.e. a soon-to-be-offline cpu is included in the sched-domains and that makes it visible for the load-balancer while the CPU_DOWN ops. is in progress. __migrate_live_tasks() moves the tasks off a 'dead' cpu (it's already "offline" when this function is called). try_to_wake_up() is called for one of these tasks from another CPU -> the load-balancer (wake_idle()) picks up a "dead" CPU and places the task on it. Then e.g. BUG_ON(rq->nr_running) detects this a bit later -> oops. Signed-off-by: Dmitry Adamushko <dmitry.adamushko@gmail.com> Tested-by: Vegard Nossum <vegard.nossum@gmail.com> Cc: Paul Menage <menage@google.com> Cc: Max Krasnyansky <maxk@qualcomm.com> Cc: Paul Jackson <pj@sgi.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: miaox@cn.fujitsu.com Cc: rostedt@goodmis.org Cc: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
-rw-r--r--kernel/cpuset.c24
1 files changed, 18 insertions, 6 deletions
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 9fceb97e989c..798b3ab054eb 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -1882,7 +1882,7 @@ static void scan_for_empty_cpusets(const struct cpuset *root)
* in order to minimize text size.
*/
-static void common_cpu_mem_hotplug_unplug(void)
+static void common_cpu_mem_hotplug_unplug(int rebuild_sd)
{
cgroup_lock();
@@ -1894,7 +1894,8 @@ static void common_cpu_mem_hotplug_unplug(void)
* Scheduler destroys domains on hotplug events.
* Rebuild them based on the current settings.
*/
- rebuild_sched_domains();
+ if (rebuild_sd)
+ rebuild_sched_domains();
cgroup_unlock();
}
@@ -1912,11 +1913,22 @@ static void common_cpu_mem_hotplug_unplug(void)
static int cpuset_handle_cpuhp(struct notifier_block *unused_nb,
unsigned long phase, void *unused_cpu)
{
- if (phase == CPU_DYING || phase == CPU_DYING_FROZEN)
+ switch (phase) {
+ case CPU_UP_CANCELED:
+ case CPU_UP_CANCELED_FROZEN:
+ case CPU_DOWN_FAILED:
+ case CPU_DOWN_FAILED_FROZEN:
+ case CPU_ONLINE:
+ case CPU_ONLINE_FROZEN:
+ case CPU_DEAD:
+ case CPU_DEAD_FROZEN:
+ common_cpu_mem_hotplug_unplug(1);
+ break;
+ default:
return NOTIFY_DONE;
+ }
- common_cpu_mem_hotplug_unplug();
- return 0;
+ return NOTIFY_OK;
}
#ifdef CONFIG_MEMORY_HOTPLUG
@@ -1929,7 +1941,7 @@ static int cpuset_handle_cpuhp(struct notifier_block *unused_nb,
void cpuset_track_online_nodes(void)
{
- common_cpu_mem_hotplug_unplug();
+ common_cpu_mem_hotplug_unplug(0);
}
#endif