@@ -38,16 +38,32 @@ config DEV_DAX_KMEM
depends on DEV_DAX
depends on MEMORY_HOTPLUG # for add_memory() and friends
help
- Support access to persistent memory as if it were RAM. This
- allows easier use of persistent memory by unmodified
- applications.
+ Support access to persistent, or other performance
+ differentiated memory as if it were System RAM. This allows
+ easier use of persistent memory by unmodified applications, or
+ adds core kernel memory services to heterogeneous memory types
+ (HMEM) marked "reserved" by platform firmware.
To use this feature, a DAX device must be unbound from the
- device_dax driver (PMEM DAX) and bound to this kmem driver
- on each boot.
+ device_dax driver and bound to this kmem driver on each boot.
Say N if unsure.
+config DEV_DAX_HMEM
+ tristate "HMEM DAX: generic support for 'special purpose' memory"
+ default DEV_DAX
+ help
+ EFI 2.8 platforms, and others, may advertise 'special purpose'
+ memory. For example, a high bandwidth memory pool. The
+ indication from platform firmware is meant to reserve the
+ memory from typical usage by default. This driver creates
+ device-dax instances for these memory ranges, and that also
+ enables the possibility to assign them to the DEV_DAX_KMEM
+ driver to override the reservation and add them to kernel
+ "System RAM" pool.
+
+ Say Y if unsure.
+
config DEV_DAX_PMEM_COMPAT
tristate "PMEM DAX: support the deprecated /sys/class/dax interface"
depends on DEV_DAX_PMEM
@@ -2,9 +2,11 @@
obj-$(CONFIG_DAX) += dax.o
obj-$(CONFIG_DEV_DAX) += device_dax.o
obj-$(CONFIG_DEV_DAX_KMEM) += kmem.o
+obj-$(CONFIG_DEV_DAX_HMEM) += dax_hmem.o
dax-y := super.o
dax-y += bus.o
device_dax-y := device.o
+dax_hmem-y := hmem.o
obj-y += pmem/
new file mode 100644
@@ -0,0 +1,58 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/platform_device.h>
+#include <linux/memregion.h>
+#include <linux/memremap.h>
+#include <linux/module.h>
+#include <linux/pfn_t.h>
+#include "bus.h"
+
+static int dax_hmem_probe(struct platform_device *pdev)
+{
+ struct dev_pagemap pgmap = { 0 };
+ struct device *dev = &pdev->dev;
+ struct dax_region *dax_region;
+ struct memregion_info *mri;
+ struct dev_dax *dev_dax;
+ struct resource *res;
+
+ res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+ if (!res)
+ return -ENOMEM;
+
+ mri = dev->platform_data;
+ pgmap.dev = dev;
+ memcpy(&pgmap.res, res, sizeof(*res));
+
+ dax_region = alloc_dax_region(dev, pdev->id, res, mri->target_node,
+ PMD_SIZE, PFN_DEV|PFN_MAP);
+ if (!dax_region)
+ return -ENOMEM;
+
+ dev_dax = devm_create_dev_dax(dax_region, 0, &pgmap);
+ if (IS_ERR(dev_dax))
+ return PTR_ERR(dev_dax);
+
+ /* child dev_dax instances now own the lifetime of the dax_region */
+ dax_region_put(dax_region);
+ return 0;
+}
+
+static int dax_hmem_remove(struct platform_device *pdev)
+{
+ /* devm handles teardown */
+ return 0;
+}
+
+static struct platform_driver dax_hmem_driver = {
+ .probe = dax_hmem_probe,
+ .remove = dax_hmem_remove,
+ .driver = {
+ .name = "hmem",
+ },
+};
+
+module_platform_driver(dax_hmem_driver);
+
+MODULE_ALIAS("platform:hmem*");
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Intel Corporation");
Platform firmware like EFI/ACPI may publish "hmem" platform devices. Such a device is a performance differentiated memory range likely reserved for an application specific use case. The driver gives access to 100% of the capacity via a device-dax mmap instance by default. However, if over-subscription and other kernel memory management is desired the resulting dax device can be assigned to the core-mm via the kmem driver. Cc: Vishal Verma <vishal.l.verma@intel.com> Cc: Keith Busch <keith.busch@intel.com> Cc: Dave Jiang <dave.jiang@intel.com> Signed-off-by: Dan Williams <dan.j.williams@intel.com> --- drivers/dax/Kconfig | 26 ++++++++++++++++++---- drivers/dax/Makefile | 2 ++ drivers/dax/hmem.c | 58 ++++++++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 81 insertions(+), 5 deletions(-) create mode 100644 drivers/dax/hmem.c