diff mbox series

[v3,08/10] device-dax: Add a driver for "hmem" devices

Message ID 155993567538.3036719.16306480832003017141.stgit@dwillia2-desk3.amr.corp.intel.com (mailing list archive)
State Superseded
Headers show
Series EFI Specific Purpose Memory Support | expand

Commit Message

Dan Williams June 7, 2019, 7:27 p.m. UTC
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.

This consumes "hmem" devices the producer of "hmem" devices is saved for
a follow-on patch so that it can reference the new CONFIG_DEV_DAX_HMEM
symbol to gate performing the enumeration work.

Cc: Vishal Verma <vishal.l.verma@intel.com>
Cc: Keith Busch <keith.busch@intel.com>
Cc: Dave Jiang <dave.jiang@intel.com>
Reported-by: kbuild test robot <lkp@intel.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/dax/Kconfig       |   27 +++++++++++++++++----
 drivers/dax/Makefile      |    2 ++
 drivers/dax/hmem.c        |   58 +++++++++++++++++++++++++++++++++++++++++++++
 include/linux/memregion.h |    3 ++
 4 files changed, 85 insertions(+), 5 deletions(-)
 create mode 100644 drivers/dax/hmem.c

Comments

Dave Hansen June 7, 2019, 7:54 p.m. UTC | #1
On 6/7/19 12:27 PM, Dan Williams wrote:
> This consumes "hmem" devices the producer of "hmem" devices is saved for
> a follow-on patch so that it can reference the new CONFIG_DEV_DAX_HMEM
> symbol to gate performing the enumeration work.

Do these literally show up as /dev/hmemX?
Dan Williams June 7, 2019, 8:07 p.m. UTC | #2
On Fri, Jun 7, 2019 at 12:54 PM Dave Hansen <dave.hansen@intel.com> wrote:
>
> On 6/7/19 12:27 PM, Dan Williams wrote:
> > This consumes "hmem" devices the producer of "hmem" devices is saved for
> > a follow-on patch so that it can reference the new CONFIG_DEV_DAX_HMEM
> > symbol to gate performing the enumeration work.
>
> Do these literally show up as /dev/hmemX?

No, everything shows as daxX.Y character devices across hmem and pmem
producers. For example:

# daxctl list -RDu
[
  {
    "path":"/platform/hmem.1",
    "id":1,
    "size":"4.00 GiB (4.29 GB)",
    "align":2097152,
    "devices":[
      {
        "chardev":"dax1.0",
        "size":"4.00 GiB (4.29 GB)"
      }
    ]
  },
  {
    "path":"/LNXSYSTM:00/LNXSYBUS:00/ACPI0012:00/ndbus0/region2/dax2.1",
    "id":2,
    "size":"125.01 GiB (134.23 GB)",
    "align":2097152,
    "devices":[
      {
        "chardev":"dax2.0",
        "size":"125.01 GiB (134.23 GB)"
      }
    ]
  },
  {
    "path":"/platform/hmem.0",
    "id":0,
    "size":"4.00 GiB (4.29 GB)",
    "align":2097152,
    "devices":[
      {
        "chardev":"dax0.0",
        "size":"4.00 GiB (4.29 GB)"
      }
    ]
  }
]
diff mbox series

Patch

diff --git a/drivers/dax/Kconfig b/drivers/dax/Kconfig
index f33c73e4af41..1a59ef86f148 100644
--- a/drivers/dax/Kconfig
+++ b/drivers/dax/Kconfig
@@ -32,19 +32,36 @@  config DEV_DAX_PMEM
 
 	  Say M if unsure
 
+config DEV_DAX_HMEM
+	tristate "HMEM DAX: direct access to 'specific purpose' memory"
+	depends on EFI_APPLICATION_RESERVED
+	default DEV_DAX
+	help
+	  EFI 2.8 platforms, and others, may advertise 'specific 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 M if unsure.
+
 config DEV_DAX_KMEM
 	tristate "KMEM DAX: volatile-use of persistent memory"
 	default DEV_DAX
 	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.
 
diff --git a/drivers/dax/Makefile b/drivers/dax/Makefile
index 81f7d54dadfb..80065b38b3c4 100644
--- a/drivers/dax/Makefile
+++ b/drivers/dax/Makefile
@@ -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/
diff --git a/drivers/dax/hmem.c b/drivers/dax/hmem.c
new file mode 100644
index 000000000000..741f2c222271
--- /dev/null
+++ b/drivers/dax/hmem.c
@@ -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 = { NULL };
+	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");
diff --git a/include/linux/memregion.h b/include/linux/memregion.h
index ba03c70f98d2..920fb300a98b 100644
--- a/include/linux/memregion.h
+++ b/include/linux/memregion.h
@@ -3,6 +3,9 @@ 
 #define _MEMREGION_H_
 #include <linux/types.h>
 
+struct memregion_info {
+	int target_node;
+};
 int memregion_alloc(gfp_t gfp);
 void memregion_free(int id);
 #endif /* _MEMREGION_H_ */