[PATCH 1/2] x86: add support for the non-standard protected e820 type

[Christoph Hellwig <hch@lst.de>]

Various recent BIOSes support NVDIMMs or ADR using a non-standard
e820 memory type, and Intel supplied reference Linux code using this
type to various vendors.

Wire this e820 table type up to export platform devices for the pmem
driver so that we can use it in Linux.

Based on arlier work from Dave Jiang <dave.jiang@intel.com> and
Dan Williams <dan.j.williams@intel.com>.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Tested-by: Ross Zwisler <ross.zwisler@linux.intel.com>
Acked-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Dan Williams <dan.j.williams@intel.com>
---
 arch/x86/Kconfig                 | 10 ++++++++
 arch/x86/include/uapi/asm/e820.h | 10 ++++++++
 arch/x86/kernel/Makefile         |  1 +
 arch/x86/kernel/e820.c           | 28 ++++++++++++++++-----
 arch/x86/kernel/pmem.c           | 53 ++++++++++++++++++++++++++++++++++++++++
 5 files changed, 96 insertions(+), 6 deletions(-)
 create mode 100644 arch/x86/kernel/pmem.c

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index b7d31ca..c0e8ee3 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1430,6 +1430,16 @@ config ILLEGAL_POINTER_VALUE
 
 source "mm/Kconfig"
 
+config X86_PMEM_LEGACY
+	bool "Support non-standard NVDIMMs and ADR protected memory"
+	help
+	  Treat memory marked using the non-standard e820 type of 12 as used
+	  by the Intel Sandy Bridge-EP reference BIOS as protected memory.
+	  The kernel will offer these regions to the pmem driver so
+	  they can be used for persistent storage.
+
+	  Say Y if unsure.
+
 config HIGHPTE
 	bool "Allocate 3rd-level pagetables from highmem"
 	depends on HIGHMEM
diff --git a/arch/x86/include/uapi/asm/e820.h b/arch/x86/include/uapi/asm/e820.h
index d993e33..ce0d0bf 100644
--- a/arch/x86/include/uapi/asm/e820.h
+++ b/arch/x86/include/uapi/asm/e820.h
@@ -33,6 +33,16 @@
 #define E820_NVS	4
 #define E820_UNUSABLE	5
 
+/*
+ * 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 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
+ * time they will learn..
+ */
+#define E820_PRAM	12
 
 /*
  * reserved RAM used by kernel itself
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index cdb1b70..971f18c 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -94,6 +94,7 @@ 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_PCSPKR_PLATFORM)	+= pcspeaker.o
 
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index 46201de..e26ca56 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -149,6 +149,9 @@ static void __init e820_print_type(u32 type)
 	case E820_UNUSABLE:
 		printk(KERN_CONT "unusable");
 		break;
+	case E820_PRAM:
+		printk(KERN_CONT "persistent (type %u)", type);
+		break;
 	default:
 		printk(KERN_CONT "type %u", type);
 		break;
@@ -688,8 +691,15 @@ void __init e820_mark_nosave_regions(unsigned long limit_pfn)
 			register_nosave_region(pfn, PFN_UP(ei->addr));
 
 		pfn = PFN_DOWN(ei->addr + ei->size);
-		if (ei->type != E820_RAM && ei->type != E820_RESERVED_KERN)
+
+		switch (ei->type) {
+		case E820_RAM:
+		case E820_PRAM:
+		case E820_RESERVED_KERN:
+			break;
+		default:
 			register_nosave_region(PFN_UP(ei->addr), pfn);
+		}
 
 		if (pfn >= limit_pfn)
 			break;
@@ -748,7 +758,7 @@ u64 __init early_reserve_e820(u64 size, u64 align)
 /*
  * Find the highest page frame number we have available
  */
-static unsigned long __init e820_end_pfn(unsigned long limit_pfn, unsigned type)
+static unsigned long __init e820_end_pfn(unsigned long limit_pfn)
 {
 	int i;
 	unsigned long last_pfn = 0;
@@ -759,7 +769,11 @@ static unsigned long __init e820_end_pfn(unsigned long limit_pfn, unsigned type)
 		unsigned long start_pfn;
 		unsigned long end_pfn;
 
-		if (ei->type != type)
+		/*
+		 * Persistent memory is accounted as ram for purposes of
+		 * establishing max_pfn and mem_map.
+		 */
+		if (ei->type != E820_RAM && ei->type != E820_PRAM)
 			continue;
 
 		start_pfn = ei->addr >> PAGE_SHIFT;
@@ -784,12 +798,12 @@ static unsigned long __init e820_end_pfn(unsigned long limit_pfn, unsigned type)
 }
 unsigned long __init e820_end_of_ram_pfn(void)
 {
-	return e820_end_pfn(MAX_ARCH_PFN, E820_RAM);
+	return e820_end_pfn(MAX_ARCH_PFN);
 }
 
 unsigned long __init e820_end_of_low_ram_pfn(void)
 {
-	return e820_end_pfn(1UL<<(32 - PAGE_SHIFT), E820_RAM);
+	return e820_end_pfn(1UL<<(32 - PAGE_SHIFT));
 }
 
 static void early_panic(char *msg)
@@ -907,6 +921,7 @@ static inline const char *e820_type_to_string(int e820_type)
 	case E820_ACPI:	return "ACPI Tables";
 	case E820_NVS:	return "ACPI Non-volatile Storage";
 	case E820_UNUSABLE:	return "Unusable memory";
+	case E820_PRAM: return "Persistent RAM";
 	default:	return "reserved";
 	}
 }
@@ -941,7 +956,8 @@ void __init e820_reserve_resources(void)
 		 * pcibios_resource_survey()
 		 */
 		if (e820.map[i].type != E820_RESERVED || res->start < (1ULL<<20)) {
-			res->flags |= IORESOURCE_BUSY;
+			if (e820.map[i].type != E820_PRAM)
+				res->flags |= IORESOURCE_BUSY;
 			insert_resource(&iomem_resource, res);
 		}
 		res++;
diff --git a/arch/x86/kernel/pmem.c b/arch/x86/kernel/pmem.c
new file mode 100644
index 0000000..89ab53c
--- /dev/null
+++ b/arch/x86/kernel/pmem.c
@@ -0,0 +1,53 @@
+/*
+ * Copyright (c) 2015, Christoph Hellwig.
+ */
+#include <linux/memblock.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+#include <asm/e820.h>
+#include <asm/page_types.h>
+#include <asm/setup.h>
+
+static __init void register_pmem_device(struct resource *res)
+{
+	struct platform_device *pdev;
+	int error;
+
+	pdev = platform_device_alloc("pmem", PLATFORM_DEVID_AUTO);
+	if (!pdev)
+		return;
+
+	error = platform_device_add_resources(pdev, res, 1);
+	if (error)
+		goto out_put_pdev;
+
+	error = platform_device_add(pdev);
+	if (error)
+		goto out_put_pdev;
+	return;
+
+out_put_pdev:
+	dev_warn(&pdev->dev, "failed to add pmem device!\n");
+	platform_device_put(pdev);
+}
+
+static __init int register_pmem_devices(void)
+{
+	int i;
+
+	for (i = 0; i < e820.nr_map; i++) {
+		struct e820entry *ei = &e820.map[i];
+
+		if (ei->type == E820_PRAM) {
+			struct resource res = {
+				.flags	= IORESOURCE_MEM,
+				.start	= ei->addr,
+				.end	= ei->addr + ei->size - 1,
+			};
+			register_pmem_device(&res);
+		}
+	}
+
+	return 0;
+}
+device_initcall(register_pmem_devices);
-- 
1.9.1