powerpc: Only obtain cpu_hotplug_lock if called by rtasd

Calling arch_update_cpu_topology from a CPU hotplug state machine callback
hits a deadlock because the function tries to get a read lock on
cpu_hotplug_lock while the state machine still holds a write lock on it.

Since all callers of arch_update_cpu_topology except rtasd already hold
cpu_hotplug_lock, this patch changes the function to use
stop_machine_cpuslocked and creates a separate function for rtasd which
still tries to obtain the lock.

Michael Bringmann investigated the bug and provided a detailed analysis
of the deadlock on this previous RFC for an alternate solution:

Signed-off-by: Thiago Jung Bauermann <bauerman@linux.vnet.ibm.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Michael Ellerman <mpe@ellerman.id.au>
Cc: John Allen <jallen@linux.vnet.ibm.com>
Cc: Michael Bringmann <mwb@linux.vnet.ibm.com>
Cc: Nathan Fontenot <nfont@linux.vnet.ibm.com>
Cc: linuxppc-dev@lists.ozlabs.org
Link: http://lkml.kernel.org/r/1497996510-4032-1-git-send-email-bauerman@linux.vnet.ibm.com
Link: https://patchwork.ozlabs.org/patch/771293/

3 files changed, 26 insertions, 4 deletions

diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h
index 8b3b46b7b0f2..a2d36b7703ae 100644
--- a/arch/powerpc/include/asm/topology.h
+++ b/arch/powerpc/include/asm/topology.h
@@ -43,6 +43,7 @@ extern void __init dump_numa_cpu_topology(void);
 
 extern int sysfs_add_device_to_node(struct device *dev, int nid);
 extern void sysfs_remove_device_from_node(struct device *dev, int nid);
+extern int numa_update_cpu_topology(bool cpus_locked);
 
 #else
 
@@ -57,6 +58,11 @@ static inline void sysfs_remove_device_from_node(struct device *dev,
 						int nid)
 {
 }
+
+static inline int numa_update_cpu_topology(bool cpus_locked)
+{
+	return 0;
+}
 #endif /* CONFIG_NUMA */
 
 #if defined(CONFIG_NUMA) && defined(CONFIG_PPC_SPLPAR)
diff --git a/arch/powerpc/kernel/rtasd.c b/arch/powerpc/kernel/rtasd.c
index 3650732639ed..0f0b1b2f3b60 100644
--- a/arch/powerpc/kernel/rtasd.c
+++ b/arch/powerpc/kernel/rtasd.c
@@ -283,7 +283,7 @@ static void prrn_work_fn(struct work_struct *work)
 	 * the RTAS event.
 	 */
 	pseries_devicetree_update(-prrn_update_scope);
-	arch_update_cpu_topology();
+	numa_update_cpu_topology(false);
 }
 
 static DECLARE_WORK(prrn_work, prrn_work_fn);
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index 371792e4418f..b95c584ce19d 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -1311,8 +1311,10 @@ static int update_lookup_table(void *data)
 /*
  * Update the node maps and sysfs entries for each cpu whose home node
  * has changed. Returns 1 when the topology has changed, and 0 otherwise.
+ *
+ * cpus_locked says whether we already hold cpu_hotplug_lock.
  */
-int arch_update_cpu_topology(void)
+int numa_update_cpu_topology(bool cpus_locked)
 {
 	unsigned int cpu, sibling, changed = 0;
 	struct topology_update_data *updates, *ud;
@@ -1400,15 +1402,23 @@ int arch_update_cpu_topology(void)
 	if (!cpumask_weight(&updated_cpus))
 		goto out;
 
-	stop_machine(update_cpu_topology, &updates[0], &updated_cpus);
+	if (cpus_locked)
+		stop_machine_cpuslocked(update_cpu_topology, &updates[0],
+					&updated_cpus);
+	else
+		stop_machine(update_cpu_topology, &updates[0], &updated_cpus);
 
 	/*
 	 * Update the numa-cpu lookup table with the new mappings, even for
 	 * offline CPUs. It is best to perform this update from the stop-
 	 * machine context.
 	 */
-	stop_machine(update_lookup_table, &updates[0],
+	if (cpus_locked)
+		stop_machine_cpuslocked(update_lookup_table, &updates[0],
 					cpumask_of(raw_smp_processor_id()));
+	else
+		stop_machine(update_lookup_table, &updates[0],
+			     cpumask_of(raw_smp_processor_id()));
 
 	for (ud = &updates[0]; ud; ud = ud->next) {
 		unregister_cpu_under_node(ud->cpu, ud->old_nid);
@@ -1426,6 +1436,12 @@ out:
 	return changed;
 }
 
+int arch_update_cpu_topology(void)
+{
+	lockdep_assert_cpus_held();
+	return numa_update_cpu_topology(true);
+}
+
 static void topology_work_fn(struct work_struct *work)
 {
 	rebuild_sched_domains();