summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorMax Krasnyansky <maxk@qualcomm.com>2008-05-29 11:17:01 -0700
committerIngo Molnar <mingo@elte.hu>2008-06-19 09:14:51 +0200
commitf18f982abf183e91f435990d337164c7a43d1e6d (patch)
treed80f6b09825db1c5103d7b8518189613c9b57fbe
parent15a8641eadb492ef7c5489faa25256967bdfd303 (diff)
downloadlinux-3.10-f18f982abf183e91f435990d337164c7a43d1e6d.tar.gz
linux-3.10-f18f982abf183e91f435990d337164c7a43d1e6d.tar.bz2
linux-3.10-f18f982abf183e91f435990d337164c7a43d1e6d.zip
sched: CPU hotplug events must not destroy scheduler domains created by the cpusets
First issue is not related to the cpusets. We're simply leaking doms_cur. It's allocated in arch_init_sched_domains() which is called for every hotplug event. So we just keep reallocation doms_cur without freeing it. I introduced free_sched_domains() function that cleans things up. Second issue is that sched domains created by the cpusets are completely destroyed by the CPU hotplug events. For all CPU hotplug events scheduler attaches all CPUs to the NULL domain and then puts them all into the single domain thereby destroying domains created by the cpusets (partition_sched_domains). The solution is simple, when cpusets are enabled scheduler should not create default domain and instead let cpusets do that. Which is exactly what the patch does. Signed-off-by: Max Krasnyansky <maxk@qualcomm.com> Cc: pj@sgi.com Cc: menage@google.com Cc: rostedt@goodmis.org Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
-rw-r--r--kernel/cpuset.c6
-rw-r--r--kernel/sched.c22
2 files changed, 28 insertions, 0 deletions
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 039baa4cd90..bceb8955797 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -1890,6 +1890,12 @@ static void common_cpu_mem_hotplug_unplug(void)
top_cpuset.mems_allowed = node_states[N_HIGH_MEMORY];
scan_for_empty_cpusets(&top_cpuset);
+ /*
+ * Scheduler destroys domains on hotplug events.
+ * Rebuild them based on the current settings.
+ */
+ rebuild_sched_domains();
+
cgroup_unlock();
}
diff --git a/kernel/sched.c b/kernel/sched.c
index ce375cb551e..4a3cb061415 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -7238,6 +7238,18 @@ void __attribute__((weak)) arch_update_cpu_topology(void)
}
/*
+ * Free current domain masks.
+ * Called after all cpus are attached to NULL domain.
+ */
+static void free_sched_domains(void)
+{
+ ndoms_cur = 0;
+ if (doms_cur != &fallback_doms)
+ kfree(doms_cur);
+ doms_cur = &fallback_doms;
+}
+
+/*
* Set up scheduler domains and groups. Callers must hold the hotplug lock.
* For now this just excludes isolated cpus, but could be used to
* exclude other special cases in the future.
@@ -7384,6 +7396,7 @@ int arch_reinit_sched_domains(void)
get_online_cpus();
mutex_lock(&sched_domains_mutex);
detach_destroy_domains(&cpu_online_map);
+ free_sched_domains();
err = arch_init_sched_domains(&cpu_online_map);
mutex_unlock(&sched_domains_mutex);
put_online_cpus();
@@ -7469,6 +7482,7 @@ static int update_sched_domains(struct notifier_block *nfb,
case CPU_DOWN_PREPARE:
case CPU_DOWN_PREPARE_FROZEN:
detach_destroy_domains(&cpu_online_map);
+ free_sched_domains();
return NOTIFY_OK;
case CPU_UP_CANCELED:
@@ -7487,8 +7501,16 @@ static int update_sched_domains(struct notifier_block *nfb,
return NOTIFY_DONE;
}
+#ifndef CONFIG_CPUSETS
+ /*
+ * Create default domain partitioning if cpusets are disabled.
+ * Otherwise we let cpusets rebuild the domains based on the
+ * current setup.
+ */
+
/* The hotplug lock is already held by cpu_up/cpu_down */
arch_init_sched_domains(&cpu_online_map);
+#endif
return NOTIFY_OK;
}