libnvdimm: Set numa_node to NVDIMM devices

ACPI NFIT table has System Physical Address Range Structure entries that
describe a proximity ID of each range when ACPI_NFIT_PROXIMITY_VALID is
set in the flags.

Change acpi_nfit_register_region() to map a proximity ID to its node ID,
and set it to a new numa_node field of nd_region_desc, which is then
conveyed to the nd_region device.

The device core arranges for btt and namespace devices to inherit their
node from their parent region.

Signed-off-by: Toshi Kani <toshi.kani@hp.com>
[djbw: move set_dev_node() from region.c to bus.c]
Signed-off-by: Dan Williams <dan.j.williams@intel.com>

6 files changed, 16 insertions, 1 deletions

diff --git a/arch/x86/kernel/pmem.c b/arch/x86/kernel/pmem.c
index 0f4ef472ab9e..64f90f53bb85 100644
--- a/arch/x86/kernel/pmem.c
+++ b/arch/x86/kernel/pmem.c
@@ -67,6 +67,7 @@ static __init int register_e820_pmem(void)
 		memset(&ndr_desc, 0, sizeof(ndr_desc));
 		ndr_desc.res = &res;
 		ndr_desc.attr_groups = e820_pmem_region_attribute_groups;
+		ndr_desc.numa_node = NUMA_NO_NODE;
 		if (!nvdimm_pmem_region_create(nvdimm_bus, &ndr_desc))
 			goto err;
 	}
diff --git a/drivers/acpi/nfit.c b/drivers/acpi/nfit.c
index 1f6f1b1a54f4..d96c8fe974dd 100644
--- a/drivers/acpi/nfit.c
+++ b/drivers/acpi/nfit.c
@@ -1392,6 +1392,12 @@ static int acpi_nfit_register_region(struct acpi_nfit_desc *acpi_desc,
 	ndr_desc->res = &res;
 	ndr_desc->provider_data = nfit_spa;
 	ndr_desc->attr_groups = acpi_nfit_region_attribute_groups;
+	if (spa->flags & ACPI_NFIT_PROXIMITY_VALID)
+		ndr_desc->numa_node = acpi_map_pxm_to_online_node(
+						spa->proximity_domain);
+	else
+		ndr_desc->numa_node = NUMA_NO_NODE;
+
 	list_for_each_entry(nfit_memdev, &acpi_desc->memdevs, list) {
 		struct acpi_nfit_memory_map *memdev = nfit_memdev->memdev;
 		struct nd_mapping *nd_mapping;
diff --git a/drivers/nvdimm/bus.c b/drivers/nvdimm/bus.c
index ec59f1f26d95..205344643852 100644
--- a/drivers/nvdimm/bus.c
+++ b/drivers/nvdimm/bus.c
@@ -48,6 +48,12 @@ static int to_nd_device_type(struct device *dev)
 
 static int nvdimm_bus_uevent(struct device *dev, struct kobj_uevent_env *env)
 {
+	/*
+	 * Ensure that region devices always have their numa node set as
+	 * early as possible.
+	 */
+	if (is_nd_pmem(dev) || is_nd_blk(dev))
+		set_dev_node(dev, to_nd_region(dev)->numa_node);
 	return add_uevent_var(env, "MODALIAS=" ND_DEVICE_MODALIAS_FMT,
 			to_nd_device_type(dev));
 }
diff --git a/drivers/nvdimm/nd.h b/drivers/nvdimm/nd.h
index 48b09a210689..c41f53e74277 100644
--- a/drivers/nvdimm/nd.h
+++ b/drivers/nvdimm/nd.h
@@ -97,7 +97,7 @@ struct nd_region {
 	u16 ndr_mappings;
 	u64 ndr_size;
 	u64 ndr_start;
-	int id, num_lanes, ro;
+	int id, num_lanes, ro, numa_node;
 	void *provider_data;
 	struct nd_interleave_set *nd_set;
 	struct nd_percpu_lane __percpu *lane;
diff --git a/drivers/nvdimm/region_devs.c b/drivers/nvdimm/region_devs.c
index 482ee3e4e04a..a5233422f9dc 100644
--- a/drivers/nvdimm/region_devs.c
+++ b/drivers/nvdimm/region_devs.c
@@ -736,6 +736,7 @@ static struct nd_region *nd_region_create(struct nvdimm_bus *nvdimm_bus,
 	nd_region->nd_set = ndr_desc->nd_set;
 	nd_region->num_lanes = ndr_desc->num_lanes;
 	nd_region->ro = ro;
+	nd_region->numa_node = ndr_desc->numa_node;
 	ida_init(&nd_region->ns_ida);
 	ida_init(&nd_region->btt_ida);
 	dev = &nd_region->dev;
diff --git a/include/linux/libnvdimm.h b/include/linux/libnvdimm.h
index dc799a29ed1a..30b3deaafd51 100644
--- a/include/linux/libnvdimm.h
+++ b/include/linux/libnvdimm.h
@@ -89,6 +89,7 @@ struct nd_region_desc {
 	struct nd_interleave_set *nd_set;
 	void *provider_data;
 	int num_lanes;
+	int numa_node;
 };
 
 struct nvdimm_bus;