Linux-ACPI Archive on lore.kernel.org
 help / color / Atom feed
From: Dan Williams <dan.j.williams@intel.com>
To: mingo@redhat.com
Cc: Vishal Verma <vishal.l.verma@intel.com>,
	Keith Busch <kbusch@kernel.org>,
	Dave Jiang <dave.jiang@intel.com>,
	kbuild test robot <lkp@intel.com>,
	Dave Hansen <dave.hansen@linux.intel.com>,
	peterz@infradead.org, ard.biesheuvel@linaro.org, x86@kernel.org,
	linux-efi@vger.kernel.org, linux-kernel@vger.kernel.org,
	linux-acpi@vger.kernel.org
Subject: [PATCH v6 10/12] device-dax: Add a driver for "hmem" devices
Date: Wed, 09 Oct 2019 16:05:29 -0700
Message-ID: <157066232989.1059972.17944824166396672432.stgit@dwillia2-desk3.amr.corp.intel.com> (raw)
In-Reply-To: <157066227329.1059972.5659620631541203458.stgit@dwillia2-desk3.amr.corp.intel.com>

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 <kbusch@kernel.org>
Cc: Dave Jiang <dave.jiang@intel.com>
Reported-by: kbuild test robot <lkp@intel.com>
Reviewed-by: Dave Hansen <dave.hansen@linux.intel.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/dax/Kconfig       |   27 ++++++++++++++++++----
 drivers/dax/Makefile      |    2 ++
 drivers/dax/hmem.c        |   56 +++++++++++++++++++++++++++++++++++++++++++++
 include/linux/memregion.h |    4 +++
 4 files changed, 84 insertions(+), 5 deletions(-)
 create mode 100644 drivers/dax/hmem.c

diff --git a/drivers/dax/Kconfig b/drivers/dax/Kconfig
index f33c73e4af41..3b6c06f07326 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_SOFT_RESERVE
+	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..fe7214daf62e
--- /dev/null
+++ b/drivers/dax/hmem.c
@@ -0,0 +1,56 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/platform_device.h>
+#include <linux/memregion.h>
+#include <linux/module.h>
+#include <linux/pfn_t.h>
+#include "bus.h"
+
+static int dax_hmem_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct dev_pagemap pgmap = { };
+	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;
+	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 7de7c0a1444e..e11595256cac 100644
--- a/include/linux/memregion.h
+++ b/include/linux/memregion.h
@@ -4,6 +4,10 @@
 #include <linux/types.h>
 #include <linux/errno.h>
 
+struct memregion_info {
+	int target_node;
+};
+
 #ifdef CONFIG_MEMREGION
 int memregion_alloc(gfp_t gfp);
 void memregion_free(int id);


  parent reply index

Thread overview: 23+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-10-09 23:04 [PATCH v6 00/12] EFI Specific Purpose Memory Support Dan Williams
2019-10-09 23:04 ` [PATCH v6 01/12] acpi/numa: Establish a new drivers/acpi/numa/ directory Dan Williams
2019-10-09 23:04 ` [PATCH v6 02/12] efi: Enumerate EFI_MEMORY_SP Dan Williams
2019-10-09 23:04 ` [PATCH v6 03/12] x86/efi: Push EFI_MEMMAP check into leaf routines Dan Williams
2019-10-09 23:04 ` [PATCH v6 04/12] efi: Common enable/disable infrastructure for EFI soft reservation Dan Williams
2019-10-10  6:36   ` Ard Biesheuvel
2019-10-09 23:05 ` [PATCH v6 05/12] x86/efi: EFI soft reservation to E820 enumeration Dan Williams
2019-10-10  6:44   ` Ard Biesheuvel
2019-10-10 18:31     ` Dan Williams
2019-10-10 18:40       ` Ard Biesheuvel
2019-10-11  2:39         ` Dan Williams
2019-10-11  5:52           ` Ard Biesheuvel
2019-10-11 14:35             ` Dan Williams
2019-10-11 14:38               ` Ard Biesheuvel
2019-10-09 23:05 ` [PATCH v6 06/12] arm/efi: EFI soft reservation to memblock Dan Williams
2019-10-10  6:46   ` Ard Biesheuvel
2019-10-09 23:05 ` [PATCH v6 07/12] x86/efi: Add efi_fake_mem support for EFI_MEMORY_SP Dan Williams
2019-10-10  7:01   ` Ard Biesheuvel
2019-10-09 23:05 ` [PATCH v6 08/12] lib: Uplevel the pmem "region" ida to a global allocator Dan Williams
2019-10-09 23:05 ` [PATCH v6 09/12] dax: Fix alloc_dax_region() compile warning Dan Williams
2019-10-09 23:05 ` Dan Williams [this message]
2019-10-09 23:05 ` [PATCH v6 11/12] acpi/numa/hmat: Register HMAT at device_initcall level Dan Williams
2019-10-09 23:05 ` [PATCH v6 12/12] acpi/numa/hmat: Register "soft reserved" memory as an "hmem" device Dan Williams

Reply instructions:

You may reply publically to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=157066232989.1059972.17944824166396672432.stgit@dwillia2-desk3.amr.corp.intel.com \
    --to=dan.j.williams@intel.com \
    --cc=ard.biesheuvel@linaro.org \
    --cc=dave.hansen@linux.intel.com \
    --cc=dave.jiang@intel.com \
    --cc=kbusch@kernel.org \
    --cc=linux-acpi@vger.kernel.org \
    --cc=linux-efi@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=lkp@intel.com \
    --cc=mingo@redhat.com \
    --cc=peterz@infradead.org \
    --cc=vishal.l.verma@intel.com \
    --cc=x86@kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

Linux-ACPI Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/linux-acpi/0 linux-acpi/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 linux-acpi linux-acpi/ https://lore.kernel.org/linux-acpi \
		linux-acpi@vger.kernel.org
	public-inbox-index linux-acpi

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.linux-acpi


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git