acpi/nfit, device-dax: Identify differentiated memory with a unique numa-node

Persistent memory, as described by the ACPI NFIT (NVDIMM Firmware
Interface Table), is the first known instance of a memory range
described by a unique "target" proximity domain. Where "initiator" and
"target" proximity domains is an approach that the ACPI HMAT
(Heterogeneous Memory Attributes Table) uses to described the unique
performance properties of a memory range relative to a given initiator
(e.g. CPU or DMA device).

Currently the numa-node for a /dev/pmemX block-device or /dev/daxX.Y
char-device follows the traditional notion of 'numa-node' where the
attribute conveys the closest online numa-node. That numa-node attribute
is useful for cpu-binding and memory-binding processes *near* the
device. However, when the memory range backing a 'pmem', or 'dax' device
is onlined (memory hot-add) the memory-only-numa-node representing that
address needs to be differentiated from the set of online nodes. In
other words, the numa-node association of the device depends on whether
you can bind processes *near* the cpu-numa-node in the offline
device-case, or bind process *on* the memory-range directly after the
backing address range is onlined.

Allow for the case that platform firmware describes persistent memory
with a unique proximity domain, i.e. when it is distinct from the
proximity of DRAM and CPUs that are on the same socket. Plumb the Linux
numa-node translation of that proximity through the libnvdimm region
device to namespaces that are in device-dax mode. With this in place the
proposed kmem driver [1] can optionally discover a unique numa-node
number for the address range as it transitions the memory from an
offline state managed by a device-driver to an online memory range
managed by the core-mm.

[1]: https://lore.kernel.org/lkml/20181022201317.8558C1D8@viggo.jf.intel.com

Reported-by: Fan Du <fan.du@intel.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: "Oliver O'Halloran" <oohall@gmail.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Jérôme Glisse <jglisse@redhat.com>
Reviewed-by: Yang Shi <yang.shi@linux.alibaba.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>

4 files changed, 12 insertions, 3 deletions

diff --git a/drivers/dax/bus.c b/drivers/dax/bus.c
index 568168500217..c620ad52d7e5 100644
--- a/drivers/dax/bus.c
+++ b/drivers/dax/bus.c
@@ -214,7 +214,7 @@ static void dax_region_unregister(void *region)
 }
 
 struct dax_region *alloc_dax_region(struct device *parent, int region_id,
-		struct resource *res, unsigned int align,
+		struct resource *res, int target_node, unsigned int align,
 		unsigned long pfn_flags)
 {
 	struct dax_region *dax_region;
@@ -244,6 +244,7 @@ struct dax_region *alloc_dax_region(struct device *parent, int region_id,
 	dax_region->id = region_id;
 	dax_region->align = align;
 	dax_region->dev = parent;
+	dax_region->target_node = target_node;
 	if (sysfs_create_groups(&parent->kobj, dax_region_attribute_groups)) {
 		kfree(dax_region);
 		return NULL;
@@ -348,6 +349,7 @@ struct dev_dax *__devm_create_dev_dax(struct dax_region *dax_region, int id,
 
 	dev_dax->dax_dev = dax_dev;
 	dev_dax->region = dax_region;
+	dev_dax->target_node = dax_region->target_node;
 	kref_get(&dax_region->kref);
 
 	inode = dax_inode(dax_dev);
diff --git a/drivers/dax/bus.h b/drivers/dax/bus.h
index ce977552ffb5..8619e3299943 100644
--- a/drivers/dax/bus.h
+++ b/drivers/dax/bus.h
@@ -10,7 +10,8 @@ struct dax_device;
 struct dax_region;
 void dax_region_put(struct dax_region *dax_region);
 struct dax_region *alloc_dax_region(struct device *parent, int region_id,
-		struct resource *res, unsigned int align, unsigned long flags);
+		struct resource *res, int target_node, unsigned int align,
+		unsigned long flags);
 
 enum dev_dax_subsys {
 	DEV_DAX_BUS,
diff --git a/drivers/dax/dax-private.h b/drivers/dax/dax-private.h
index a82ce48f5884..a45612148ca0 100644
--- a/drivers/dax/dax-private.h
+++ b/drivers/dax/dax-private.h
@@ -26,6 +26,7 @@ void dax_bus_exit(void);
 /**
  * struct dax_region - mapping infrastructure for dax devices
  * @id: kernel-wide unique region for a memory range
+ * @target_node: effective numa node if this memory range is onlined
  * @kref: to pin while other agents have a need to do lookups
  * @dev: parent device backing this region
  * @align: allocation and mapping alignment for child dax devices
@@ -34,6 +35,7 @@ void dax_bus_exit(void);
  */
 struct dax_region {
 	int id;
+	int target_node;
 	struct kref kref;
 	struct device *dev;
 	unsigned int align;
@@ -46,6 +48,7 @@ struct dax_region {
  * data while the device is activated in the driver.
  * @region - parent region
  * @dax_dev - core dax functionality
+ * @target_node: effective numa node if dev_dax memory range is onlined
  * @dev - device core
  * @pgmap - pgmap for memmap setup / lifetime (driver owned)
  * @ref: pgmap reference count (driver owned)
@@ -54,6 +57,7 @@ struct dax_region {
 struct dev_dax {
 	struct dax_region *region;
 	struct dax_device *dax_dev;
+	int target_node;
 	struct device dev;
 	struct dev_pagemap pgmap;
 	struct percpu_ref ref;
diff --git a/drivers/dax/pmem/core.c b/drivers/dax/pmem/core.c
index bdcff1b14e95..f71019ce0647 100644
--- a/drivers/dax/pmem/core.c
+++ b/drivers/dax/pmem/core.c
@@ -20,6 +20,7 @@ struct dev_dax *__dax_pmem_probe(struct device *dev, enum dev_dax_subsys subsys)
 	struct nd_namespace_common *ndns;
 	struct nd_dax *nd_dax = to_nd_dax(dev);
 	struct nd_pfn *nd_pfn = &nd_dax->nd_pfn;
+	struct nd_region *nd_region = to_nd_region(dev->parent);
 
 	ndns = nvdimm_namespace_common_probe(dev);
 	if (IS_ERR(ndns))
@@ -52,7 +53,8 @@ struct dev_dax *__dax_pmem_probe(struct device *dev, enum dev_dax_subsys subsys)
 	memcpy(&res, &pgmap.res, sizeof(res));
 	res.start += offset;
 	dax_region = alloc_dax_region(dev, region_id, &res,
-			le32_to_cpu(pfn_sb->align), PFN_DEV|PFN_MAP);
+			nd_region->target_node, le32_to_cpu(pfn_sb->align),
+			PFN_DEV|PFN_MAP);
 	if (!dax_region)
 		return ERR_PTR(-ENOMEM);