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>
memset(&ndr_desc, 0, sizeof(ndr_desc));
ndr_desc.attr_groups = region_attr_groups;
ndr_desc.numa_node = dev_to_node(&p->pdev->dev);
+ ndr_desc.target_node = ndr_desc.numa_node;
ndr_desc.res = &p->res;
ndr_desc.of_node = p->dn;
ndr_desc.provider_data = p;
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)
+ if (spa->flags & ACPI_NFIT_PROXIMITY_VALID) {
ndr_desc->numa_node = acpi_map_pxm_to_online_node(
spa->proximity_domain);
- else
+ ndr_desc->target_node = acpi_map_pxm_to_node(
+ spa->proximity_domain);
+ } else {
ndr_desc->numa_node = NUMA_NO_NODE;
+ ndr_desc->target_node = NUMA_NO_NODE;
+ }
/*
* Persistence domain bits are hierarchical, if
return node;
}
+EXPORT_SYMBOL(acpi_map_pxm_to_node);
/**
* acpi_map_pxm_to_online_node - Map proximity ID to online node
}
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;
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;
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);
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,
/**
* 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
*/
struct dax_region {
int id;
+ int target_node;
struct kref kref;
struct device *dev;
unsigned int align;
* 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)
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;
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))
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);
ndr_desc.res = res;
ndr_desc.attr_groups = e820_pmem_region_attribute_groups;
ndr_desc.numa_node = e820_range_to_nid(res->start);
+ ndr_desc.target_node = ndr_desc.numa_node;
set_bit(ND_REGION_PAGEMAP, &ndr_desc.flags);
if (!nvdimm_pmem_region_create(nvdimm_bus, &ndr_desc))
return -ENXIO;
u16 ndr_mappings;
u64 ndr_size;
u64 ndr_start;
- int id, num_lanes, ro, numa_node;
+ int id, num_lanes, ro, numa_node, target_node;
void *provider_data;
struct kernfs_node *bb_state;
struct badblocks bb;
memset(&ndr_desc, 0, sizeof(ndr_desc));
ndr_desc.attr_groups = region_attr_groups;
ndr_desc.numa_node = dev_to_node(&pdev->dev);
+ ndr_desc.target_node = ndr_desc.numa_node;
ndr_desc.res = &pdev->resource[i];
ndr_desc.of_node = np;
set_bit(ND_REGION_PAGEMAP, &ndr_desc.flags);
nd_region->flags = ndr_desc->flags;
nd_region->ro = ro;
nd_region->numa_node = ndr_desc->numa_node;
+ nd_region->target_node = ndr_desc->target_node;
ida_init(&nd_region->ns_ida);
ida_init(&nd_region->btt_ida);
ida_init(&nd_region->pfn_ida);
#ifdef CONFIG_ACPI_NUMA
int acpi_map_pxm_to_online_node(int pxm);
+int acpi_map_pxm_to_node(int pxm);
int acpi_get_node(acpi_handle handle);
#else
static inline int acpi_map_pxm_to_online_node(int pxm)
{
return 0;
}
+static inline int acpi_map_pxm_to_node(int pxm)
+{
+ return 0;
+}
static inline int acpi_get_node(acpi_handle handle)
{
return 0;
void *provider_data;
int num_lanes;
int numa_node;
+ int target_node;
unsigned long flags;
struct device_node *of_node;
};