powerpc: Add debug checks to catch invalid cpu-to-node mappings

There have been some weird bugs in the past where the kernel tried to associate
threads of the same core to different NUMA nodes, and things went haywire after
that point (as expected).

But unfortunately, root-causing such issues have been quite challenging, due to
the lack of appropriate debug checks in the kernel. These bugs usually lead to
some odd soft-lockups in the scheduler's build-sched-domain code in the CPU
hotplug path, which makes it very hard to trace it back to the incorrect
cpu-to-node mappings.

So add appropriate debug checks to catch such invalid cpu-to-node mappings
as early as possible.

Signed-off-by: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>

1 files changed, 24 insertions, 2 deletions

diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index b7293bba00622f..7f7c0db2cc560e 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -567,17 +567,39 @@ out:
 	return nid;
 }
 
+static void verify_cpu_node_mapping(int cpu, int node)
+{
+	int base, sibling, i;
+
+	/* Verify that all the threads in the core belong to the same node */
+	base = cpu_first_thread_sibling(cpu);
+
+	for (i = 0; i < threads_per_core; i++) {
+		sibling = base + i;
+
+		if (sibling == cpu || cpu_is_offline(sibling))
+			continue;
+
+		if (cpu_to_node(sibling) != node) {
+			WARN(1, "CPU thread siblings %d and %d don't belong"
+				" to the same node!\n", cpu, sibling);
+			break;
+		}
+	}
+}
+
 static int __cpuinit cpu_numa_callback(struct notifier_block *nfb,
 			     unsigned long action,
 			     void *hcpu)
 {
 	unsigned long lcpu = (unsigned long)hcpu;
-	int ret = NOTIFY_DONE;
+	int ret = NOTIFY_DONE, nid;
 
 	switch (action) {
 	case CPU_UP_PREPARE:
 	case CPU_UP_PREPARE_FROZEN:
-		numa_setup_cpu(lcpu);
+		nid = numa_setup_cpu(lcpu);
+		verify_cpu_node_mapping((int)lcpu, nid);
 		ret = NOTIFY_OK;
 		break;
 #ifdef CONFIG_HOTPLUG_CPU