core_ctl: Synchronize access to cluster cpu list
Cluster cpu list traversal is not properly protected against removal of
element by a separate thread. Add proper locking to ensure an element
cannot be removed while accessing the list.
In addition ensure we don't end up in a livelock never exiting the loop
due to hotplug continuously moving elements to the end of the list.
Change-Id: Ie98fe48c2f4fdd0244573229b77ee9823df9e214
Signed-off-by: Olav Haugan <ohaugan@codeaurora.org>
diff --git a/kernel/sched/core_ctl.c b/kernel/sched/core_ctl.c
index 0db85a4..ecf6c56 100644
--- a/kernel/sched/core_ctl.c
+++ b/kernel/sched/core_ctl.c
@@ -719,8 +719,18 @@
static void try_to_isolate(struct cluster_data *cluster, unsigned int need)
{
struct cpu_data *c, *tmp;
+ unsigned long flags;
+ unsigned int num_cpus = cluster->num_cpus;
+ /*
+ * Protect against entry being removed (and added at tail) by other
+ * thread (hotplug).
+ */
+ spin_lock_irqsave(&state_lock, flags);
list_for_each_entry_safe(c, tmp, &cluster->lru, sib) {
+ if (!num_cpus--)
+ break;
+
if (!is_active(c))
continue;
if (cluster->active_cpus == need)
@@ -729,6 +739,8 @@
if (c->is_busy)
continue;
+ spin_unlock_irqrestore(&state_lock, flags);
+
pr_debug("Trying to isolate CPU%u\n", c->cpu);
if (!sched_isolate_cpu(c->cpu)) {
c->isolated_by_us = true;
@@ -738,7 +750,9 @@
pr_debug("Unable to isolate CPU%u\n", c->cpu);
}
cluster->active_cpus = get_active_cpu_count(cluster);
+ spin_lock_irqsave(&state_lock, flags);
}
+ spin_unlock_irqrestore(&state_lock, flags);
/*
* If the number of active CPUs is within the limits, then
@@ -747,12 +761,19 @@
if (cluster->active_cpus <= cluster->max_cpus)
return;
+ num_cpus = cluster->num_cpus;
+ spin_lock_irqsave(&state_lock, flags);
list_for_each_entry_safe(c, tmp, &cluster->lru, sib) {
+ if (!num_cpus--)
+ break;
+
if (!is_active(c))
continue;
if (cluster->active_cpus <= cluster->max_cpus)
break;
+ spin_unlock_irqrestore(&state_lock, flags);
+
pr_debug("Trying to isolate CPU%u\n", c->cpu);
if (!sched_isolate_cpu(c->cpu)) {
c->isolated_by_us = true;
@@ -762,15 +783,28 @@
pr_debug("Unable to isolate CPU%u\n", c->cpu);
}
cluster->active_cpus = get_active_cpu_count(cluster);
+ spin_lock_irqsave(&state_lock, flags);
}
+ spin_unlock_irqrestore(&state_lock, flags);
+
}
static void __try_to_unisolate(struct cluster_data *cluster,
unsigned int need, bool force)
{
struct cpu_data *c, *tmp;
+ unsigned long flags;
+ unsigned int num_cpus = cluster->num_cpus;
+ /*
+ * Protect against entry being removed (and added at tail) by other
+ * thread (hotplug).
+ */
+ spin_lock_irqsave(&state_lock, flags);
list_for_each_entry_safe(c, tmp, &cluster->lru, sib) {
+ if (!num_cpus--)
+ break;
+
if (!c->isolated_by_us)
continue;
if ((c->online && !cpu_isolated(c->cpu)) ||
@@ -779,6 +813,8 @@
if (cluster->active_cpus == need)
break;
+ spin_unlock_irqrestore(&state_lock, flags);
+
pr_debug("Trying to unisolate CPU%u\n", c->cpu);
if (!sched_unisolate_cpu(c->cpu)) {
c->isolated_by_us = false;
@@ -787,7 +823,9 @@
pr_debug("Unable to unisolate CPU%u\n", c->cpu);
}
cluster->active_cpus = get_active_cpu_count(cluster);
+ spin_lock_irqsave(&state_lock, flags);
}
+ spin_unlock_irqrestore(&state_lock, flags);
}
static void try_to_unisolate(struct cluster_data *cluster, unsigned int need)