libnvdimm, e820: make CONFIG_X86_PMEM_LEGACY a tristate option

We currently register a platform device for e820 type-12 memory and
register a nvdimm bus beneath it.  Registering the platform device
triggers the device-core machinery to probe for a driver, but that
search currently comes up empty.  Building the nvdimm-bus registration
into the e820_pmem platform device registration in this way forces
libnvdimm to be built-in.  Instead, convert the built-in portion of
CONFIG_X86_PMEM_LEGACY to simply register a platform device and move the
rest of the logic to the driver for e820_pmem, for the following
reasons:

1/ Letting e820_pmem support be a module allows building and testing
   libnvdimm.ko changes without rebooting

2/ All the normal policy around modules can be applied to e820_pmem
   (unbind to disable and/or blacklisting the module from loading by
   default)

3/ Moving the driver to a generic location and converting it to scan
   "iomem_resource" rather than "e820.map" means any other architecture can
   take advantage of this simple nvdimm resource discovery mechanism by
   registering a resource named "Persistent Memory (legacy)"

Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>

arch/x86/Kconfig

@@ -1426,10 +1426,14 @@ config ILLEGAL_POINTER_VALUE
 
 source "mm/Kconfig"
 
+config X86_PMEM_LEGACY_DEVICE
+	bool
+
 config X86_PMEM_LEGACY
-	bool "Support non-standard NVDIMMs and ADR protected memory"
+	tristate "Support non-standard NVDIMMs and ADR protected memory"
 	depends on PHYS_ADDR_T_64BIT
 	depends on BLK_DEV
+	select X86_PMEM_LEGACY_DEVICE
 	select LIBNVDIMM
 	help
 	  Treat memory marked using the non-standard e820 type of 12 as used

arch/x86/include/uapi/asm/e820.h

@@ -37,7 +37,7 @@
 /*
  * This is a non-standardized way to represent ADR or NVDIMM regions that
  * persist over a reboot.  The kernel will ignore their special capabilities
- * unless the CONFIG_X86_PMEM_LEGACY=y option is set.
+ * unless the CONFIG_X86_PMEM_LEGACY option is set.
  *
  * ( Note that older platforms also used 6 for the same type of memory,
  *   but newer versions switched to 12 as 6 was assigned differently.  Some

arch/x86/kernel/Makefile

@@ -92,7 +92,7 @@ obj-$(CONFIG_KVM_GUEST)		+= kvm.o kvmclock.o
 obj-$(CONFIG_PARAVIRT)		+= paravirt.o paravirt_patch_$(BITS).o
 obj-$(CONFIG_PARAVIRT_SPINLOCKS)+= paravirt-spinlocks.o
 obj-$(CONFIG_PARAVIRT_CLOCK)	+= pvclock.o
-obj-$(CONFIG_X86_PMEM_LEGACY)	+= pmem.o
+obj-$(CONFIG_X86_PMEM_LEGACY_DEVICE) += pmem.o
 
 obj-$(CONFIG_PCSPKR_PLATFORM)	+= pcspeaker.o
 

arch/x86/kernel/pmem.c

@@ -3,80 +3,17 @@
  * Copyright (c) 2015, Intel Corporation.
  */
 #include <linux/platform_device.h>
-#include <linux/libnvdimm.h>
 #include <linux/module.h>
-#include <asm/e820.h>
-
-static void e820_pmem_release(struct device *dev)
-{
-	struct nvdimm_bus *nvdimm_bus = dev->platform_data;
-
-	if (nvdimm_bus)
-		nvdimm_bus_unregister(nvdimm_bus);
-}
-
-static struct platform_device e820_pmem = {
-	.name = "e820_pmem",
-	.id = -1,
-	.dev = {
-		.release = e820_pmem_release,
-	},
-};
-
-static const struct attribute_group *e820_pmem_attribute_groups[] = {
-	&nvdimm_bus_attribute_group,
-	NULL,
-};
-
-static const struct attribute_group *e820_pmem_region_attribute_groups[] = {
-	&nd_region_attribute_group,
-	&nd_device_attribute_group,
-	NULL,
-};
 
 static __init int register_e820_pmem(void)
 {
-	static struct nvdimm_bus_descriptor nd_desc;
-	struct device *dev = &e820_pmem.dev;
-	struct nvdimm_bus *nvdimm_bus;
-	int rc, i;
-
-	rc = platform_device_register(&e820_pmem);
-	if (rc)
-		return rc;
-
-	nd_desc.attr_groups = e820_pmem_attribute_groups;
-	nd_desc.provider_name = "e820";
-	nvdimm_bus = nvdimm_bus_register(dev, &nd_desc);
-	if (!nvdimm_bus)
-		goto err;
-	dev->platform_data = nvdimm_bus;
-
-	for (i = 0; i < e820.nr_map; i++) {
-		struct e820entry *ei = &e820.map[i];
-		struct resource res = {
-			.flags	= IORESOURCE_MEM,
-			.start	= ei->addr,
-			.end	= ei->addr + ei->size - 1,
-		};
-		struct nd_region_desc ndr_desc;
-
-		if (ei->type != E820_PRAM)
-			continue;
-
-		memset(&ndr_desc, 0, sizeof(ndr_desc));
-		ndr_desc.res = &res;
-		ndr_desc.attr_groups = e820_pmem_region_attribute_groups;
-		ndr_desc.numa_node = NUMA_NO_NODE;
-		if (!nvdimm_pmem_region_create(nvdimm_bus, &ndr_desc))
-			goto err;
-	}
-
-	return 0;
-
- err:
-	dev_err(dev, "failed to register legacy persistent memory ranges\n");
-	platform_device_unregister(&e820_pmem);
-	return -ENXIO;
+	struct platform_device *pdev;
+
+	/*
+	 * See drivers/nvdimm/e820.c for the implementation, this is
+	 * simply here to trigger the module to load on demand.
+	 */
+	pdev = platform_device_alloc("e820_pmem", -1);
+	return platform_device_add(pdev);
 }
 device_initcall(register_e820_pmem);

drivers/nvdimm/Makefile

@@ -2,6 +2,7 @@ obj-$(CONFIG_LIBNVDIMM) += libnvdimm.o
 obj-$(CONFIG_BLK_DEV_PMEM) += nd_pmem.o
 obj-$(CONFIG_ND_BTT) += nd_btt.o
 obj-$(CONFIG_ND_BLK) += nd_blk.o
+obj-$(CONFIG_X86_PMEM_LEGACY) += nd_e820.o
 
 nd_pmem-y := pmem.o
 
@@ -9,6 +10,8 @@ nd_btt-y := btt.o
 
 nd_blk-y := blk.o
 
+nd_e820-y := e820.o
+
 libnvdimm-y := core.o
 libnvdimm-y += bus.o
 libnvdimm-y += dimm_devs.o

drivers/nvdimm/e820.c

@@ -0,0 +1,86 @@
+/*
+ * Copyright (c) 2015, Christoph Hellwig.
+ * Copyright (c) 2015, Intel Corporation.
+ */
+#include <linux/platform_device.h>
+#include <linux/libnvdimm.h>
+#include <linux/module.h>
+
+static const struct attribute_group *e820_pmem_attribute_groups[] = {
+	&nvdimm_bus_attribute_group,
+	NULL,
+};
+
+static const struct attribute_group *e820_pmem_region_attribute_groups[] = {
+	&nd_region_attribute_group,
+	&nd_device_attribute_group,
+	NULL,
+};
+
+static int e820_pmem_remove(struct platform_device *pdev)
+{
+	struct nvdimm_bus *nvdimm_bus = platform_get_drvdata(pdev);
+
+	nvdimm_bus_unregister(nvdimm_bus);
+	return 0;
+}
+
+static int e820_pmem_probe(struct platform_device *pdev)
+{
+	static struct nvdimm_bus_descriptor nd_desc;
+	struct device *dev = &pdev->dev;
+	struct nvdimm_bus *nvdimm_bus;
+	struct resource *p;
+
+	nd_desc.attr_groups = e820_pmem_attribute_groups;
+	nd_desc.provider_name = "e820";
+	nvdimm_bus = nvdimm_bus_register(dev, &nd_desc);
+	if (!nvdimm_bus)
+		goto err;
+	platform_set_drvdata(pdev, nvdimm_bus);
+
+	for (p = iomem_resource.child; p ; p = p->sibling) {
+		struct nd_region_desc ndr_desc;
+
+		if (strncmp(p->name, "Persistent Memory (legacy)", 26) != 0)
+			continue;
+
+		memset(&ndr_desc, 0, sizeof(ndr_desc));
+		ndr_desc.res = p;
+		ndr_desc.attr_groups = e820_pmem_region_attribute_groups;
+		ndr_desc.numa_node = NUMA_NO_NODE;
+		if (!nvdimm_pmem_region_create(nvdimm_bus, &ndr_desc))
+			goto err;
+	}
+
+	return 0;
+
+ err:
+	nvdimm_bus_unregister(nvdimm_bus);
+	dev_err(dev, "failed to register legacy persistent memory ranges\n");
+	return -ENXIO;
+}
+
+static struct platform_driver e820_pmem_driver = {
+	.probe = e820_pmem_probe,
+	.remove = e820_pmem_remove,
+	.driver = {
+		.name = "e820_pmem",
+	},
+};
+
+static __init int e820_pmem_init(void)
+{
+	return platform_driver_register(&e820_pmem_driver);
+}
+
+static __exit void e820_pmem_exit(void)
+{
+	platform_driver_unregister(&e820_pmem_driver);
+}
+
+MODULE_ALIAS("platform:e820_pmem*");
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Intel Corporation");
+module_init(e820_pmem_init);
+module_exit(e820_pmem_exit);

tools/testing/nvdimm/Kbuild

@@ -15,6 +15,7 @@ obj-$(CONFIG_LIBNVDIMM) += libnvdimm.o
 obj-$(CONFIG_BLK_DEV_PMEM) += nd_pmem.o
 obj-$(CONFIG_ND_BTT) += nd_btt.o
 obj-$(CONFIG_ND_BLK) += nd_blk.o
+obj-$(CONFIG_X86_PMEM_LEGACY) += nd_e820.o
 obj-$(CONFIG_ACPI_NFIT) += nfit.o
 
 nfit-y := $(ACPI_SRC)/nfit.o
@@ -29,6 +30,9 @@ nd_btt-y += config_check.o
 nd_blk-y := $(NVDIMM_SRC)/blk.o
 nd_blk-y += config_check.o
 
+nd_e820-y := $(NVDIMM_SRC)/e820.o
+nd_e820-y += config_check.o
+
 libnvdimm-y := $(NVDIMM_SRC)/core.o
 libnvdimm-y += $(NVDIMM_SRC)/bus.o
 libnvdimm-y += $(NVDIMM_SRC)/dimm_devs.o