linux/drivers/nvdimm/of_pmem.c

109 lines
2.6 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0+
#define pr_fmt(fmt) "of_pmem: " fmt
#include <linux/of_platform.h>
#include <linux/of_address.h>
#include <linux/libnvdimm.h>
#include <linux/module.h>
#include <linux/ioport.h>
#include <linux/slab.h>
struct of_pmem_private {
struct nvdimm_bus_descriptor bus_desc;
struct nvdimm_bus *bus;
};
static int of_pmem_region_probe(struct platform_device *pdev)
{
struct of_pmem_private *priv;
struct device_node *np;
struct nvdimm_bus *bus;
bool is_volatile;
int i;
np = dev_of_node(&pdev->dev);
if (!np)
return -ENXIO;
priv = kzalloc(sizeof(*priv), GFP_KERNEL);
if (!priv)
return -ENOMEM;
priv->bus_desc.provider_name = kstrdup(pdev->name, GFP_KERNEL);
priv->bus_desc.module = THIS_MODULE;
priv->bus_desc.of_node = np;
priv->bus = bus = nvdimm_bus_register(&pdev->dev, &priv->bus_desc);
if (!bus) {
kfree(priv);
return -ENODEV;
}
platform_set_drvdata(pdev, priv);
is_volatile = !!of_find_property(np, "volatile", NULL);
dev_dbg(&pdev->dev, "Registering %s regions from %pOF\n",
is_volatile ? "volatile" : "non-volatile", np);
for (i = 0; i < pdev->num_resources; i++) {
struct nd_region_desc ndr_desc;
struct nd_region *region;
/*
* NB: libnvdimm copies the data from ndr_desc into it's own
* structures so passing a stack pointer is fine.
*/
memset(&ndr_desc, 0, sizeof(ndr_desc));
ndr_desc.numa_node = dev_to_node(&pdev->dev);
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>
2018-11-10 04:43:07 +08:00
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);
if (is_volatile)
region = nvdimm_volatile_region_create(bus, &ndr_desc);
else {
set_bit(ND_REGION_PERSIST_MEMCTRL, &ndr_desc.flags);
region = nvdimm_pmem_region_create(bus, &ndr_desc);
}
if (!region)
dev_warn(&pdev->dev, "Unable to register region %pR from %pOF\n",
ndr_desc.res, np);
else
dev_dbg(&pdev->dev, "Registered region %pR from %pOF\n",
ndr_desc.res, np);
}
return 0;
}
static int of_pmem_region_remove(struct platform_device *pdev)
{
struct of_pmem_private *priv = platform_get_drvdata(pdev);
nvdimm_bus_unregister(priv->bus);
kfree(priv);
return 0;
}
static const struct of_device_id of_pmem_region_match[] = {
{ .compatible = "pmem-region" },
{ },
};
static struct platform_driver of_pmem_region_driver = {
.probe = of_pmem_region_probe,
.remove = of_pmem_region_remove,
.driver = {
.name = "of_pmem",
.of_match_table = of_pmem_region_match,
},
};
module_platform_driver(of_pmem_region_driver);
MODULE_DEVICE_TABLE(of, of_pmem_region_match);
MODULE_LICENSE("GPL");
MODULE_AUTHOR("IBM Corporation");