libnvdimm: Schedule device registration on node local to the device

Force the device registration for nvdimm devices to be closer to the actual
device. This is achieved by using either the NUMA node ID of the region, or
of the parent. By doing this we can have everything above the region based
on the region, and everything below the region based on the nvdimm bus.

By guaranteeing NUMA locality I see an improvement of as high as 25% for
per-node init of a system with 12TB of persistent memory.

Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Alexander Duyck <alexander.h.duyck@linux.intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

diff --git a/drivers/nvdimm/bus.c b/drivers/nvdimm/bus.c
index dca5f7a805cb225fd384650b2e54a1c8e936b7cd..7bbff0af29b2305fb1360949f680ebcdc11cbd40 100644 (file)
--- a/drivers/nvdimm/bus.c
+++ b/drivers/nvdimm/bus.c
@@ -23,6 +23,7 @@
 #include <linux/ndctl.h>
 #include <linux/sched.h>
 #include <linux/slab.h>
+#include <linux/cpu.h>
 #include <linux/fs.h>
 #include <linux/io.h>
 #include <linux/mm.h>
@@ -534,11 +535,15 @@ void __nd_device_register(struct device *dev)
                set_dev_node(dev, to_nd_region(dev)->numa_node);
 
        dev->bus = &nvdimm_bus_type;
-       if (dev->parent)
+       if (dev->parent) {
                get_device(dev->parent);
+               if (dev_to_node(dev) == NUMA_NO_NODE)
+                       set_dev_node(dev, dev_to_node(dev->parent));
+       }
        get_device(dev);
-       async_schedule_domain(nd_async_device_register, dev,
-                       &nd_async_domain);
+
+       async_schedule_dev_domain(nd_async_device_register, dev,
+                                 &nd_async_domain);
 }
 
 void nd_device_register(struct device *dev)