[PATCH] cpuset: hotunplug cpus and mems in all cpusets

The cpuset code handling hot unplug of CPUs or Memory Nodes was incorrect -
it could remove a CPU or Node from the top cpuset, while leaving it still
in some child cpusets.

One basic rule of cpusets is that each cpusets cpus and mems are subsets of
its parents.  The cpuset hot unplug code violated this rule.

So the cpuset hotunplug handler must walk down the tree, removing any
removed CPU or Node from all cpusets.

However, it is not allowed to make a cpusets cpus or mems become empty.
They can only transition from empty to non-empty, not back.

So if the last CPU or Node would be removed from a cpuset by the above
walk, we scan back up the cpuset hierarchy, finding the nearest ancestor
that still has something online, and copy its CPU or Memory placement.

Signed-off-by: Paul Jackson <pj@sgi.com>
Cc: Nathan Lynch <ntl@pobox.com>
Cc: Anton Blanchard <anton@samba.org>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

1 files changed, 70 insertions, 17 deletions

diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 794af50..cc0395d 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -2040,6 +2040,73 @@ out:
 	return err;
 }
 
+#if defined(CONFIG_HOTPLUG_CPU) || defined(CONFIG_MEMORY_HOTPLUG)
+/*
+ * If common_cpu_mem_hotplug_unplug(), below, unplugs any CPUs
+ * or memory nodes, we need to walk over the cpuset hierarchy,
+ * removing that CPU or node from all cpusets.  If this removes the
+ * last CPU or node from a cpuset, then the guarantee_online_cpus()
+ * or guarantee_online_mems() code will use that emptied cpusets
+ * parent online CPUs or nodes.  Cpusets that were already empty of
+ * CPUs or nodes are left empty.
+ *
+ * This routine is intentionally inefficient in a couple of regards.
+ * It will check all cpusets in a subtree even if the top cpuset of
+ * the subtree has no offline CPUs or nodes.  It checks both CPUs and
+ * nodes, even though the caller could have been coded to know that
+ * only one of CPUs or nodes needed to be checked on a given call.
+ * This was done to minimize text size rather than cpu cycles.
+ *
+ * Call with both manage_mutex and callback_mutex held.
+ *
+ * Recursive, on depth of cpuset subtree.
+ */
+
+static void guarantee_online_cpus_mems_in_subtree(const struct cpuset *cur)
+{
+	struct cpuset *c;
+
+	/* Each of our child cpusets mems must be online */
+	list_for_each_entry(c, &cur->children, sibling) {
+		guarantee_online_cpus_mems_in_subtree(c);
+		if (!cpus_empty(c->cpus_allowed))
+			guarantee_online_cpus(c, &c->cpus_allowed);
+		if (!nodes_empty(c->mems_allowed))
+			guarantee_online_mems(c, &c->mems_allowed);
+	}
+}
+
+/*
+ * The cpus_allowed and mems_allowed nodemasks in the top_cpuset track
+ * cpu_online_map and node_online_map.  Force the top cpuset to track
+ * whats online after any CPU or memory node hotplug or unplug event.
+ *
+ * To ensure that we don't remove a CPU or node from the top cpuset
+ * that is currently in use by a child cpuset (which would violate
+ * the rule that cpusets must be subsets of their parent), we first
+ * call the recursive routine guarantee_online_cpus_mems_in_subtree().
+ *
+ * Since there are two callers of this routine, one for CPU hotplug
+ * events and one for memory node hotplug events, we could have coded
+ * two separate routines here.  We code it as a single common routine
+ * in order to minimize text size.
+ */
+
+static void common_cpu_mem_hotplug_unplug(void)
+{
+	mutex_lock(&manage_mutex);
+	mutex_lock(&callback_mutex);
+
+	guarantee_online_cpus_mems_in_subtree(&top_cpuset);
+	top_cpuset.cpus_allowed = cpu_online_map;
+	top_cpuset.mems_allowed = node_online_map;
+
+	mutex_unlock(&callback_mutex);
+	mutex_unlock(&manage_mutex);
+}
+#endif
+
+#ifdef CONFIG_HOTPLUG_CPU
 /*
  * The top_cpuset tracks what CPUs and Memory Nodes are online,
  * period.  This is necessary in order to make cpusets transparent
@@ -2050,38 +2117,24 @@ out:
  * cpu_online_map on each CPU hotplug (cpuhp) event.
  */
 
-#ifdef CONFIG_HOTPLUG_CPU
 static int cpuset_handle_cpuhp(struct notifier_block *nb,
 				unsigned long phase, void *cpu)
 {
-	mutex_lock(&manage_mutex);
-	mutex_lock(&callback_mutex);
-
-	top_cpuset.cpus_allowed = cpu_online_map;
-
-	mutex_unlock(&callback_mutex);
-	mutex_unlock(&manage_mutex);
-
+	common_cpu_mem_hotplug_unplug();
 	return 0;
 }
 #endif
 
+#ifdef CONFIG_MEMORY_HOTPLUG
 /*
  * Keep top_cpuset.mems_allowed tracking node_online_map.
  * Call this routine anytime after you change node_online_map.
  * See also the previous routine cpuset_handle_cpuhp().
  */
 
-#ifdef CONFIG_MEMORY_HOTPLUG
 void cpuset_track_online_nodes()
 {
-	mutex_lock(&manage_mutex);
-	mutex_lock(&callback_mutex);
-
-	top_cpuset.mems_allowed = node_online_map;
-
-	mutex_unlock(&callback_mutex);
-	mutex_unlock(&manage_mutex);
+	common_cpu_mem_hotplug_unplug();
 }
 #endif