x86/mm: Add support for the non-standard protected e820 type

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 earlier work from:

   Dave Jiang <dave.jiang@intel.com>
   Dan Williams <dan.j.williams@intel.com>

Includes fixes for NUMA regions from Boaz Harrosh.

Tested-by: Ross Zwisler <ross.zwisler@linux.intel.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Dan Williams <dan.j.williams@intel.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Boaz Harrosh <boaz@plexistor.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Jens Axboe <axboe@fb.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Keith Busch <keith.busch@intel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Matthew Wilcox <willy@linux.intel.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-nvdimm@ml01.01.org
Link: http://lkml.kernel.org/r/1427872339-6688-2-git-send-email-hch@lst.de
[ Minor cleanups. ]
Signed-off-by: Ingo Molnar <mingo@kernel.org>

6 files changed, 100 insertions, 6 deletions

diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index bfcb1a6..c87122d 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -1965,6 +1965,12 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			         or
 			         memmap=0x10000$0x18690000
 
+	memmap=nn[KMG]!ss[KMG]
+			[KNL,X86] Mark specific memory as protected.
+			Region of memory to be used, from ss to ss+nn.
+			The memory region may be marked as e820 type 12 (0xc)
+			and is NVDIMM or ADR memory.
+
 	memory_corruption_check=0/1 [X86]
 			Some BIOSes seem to corrupt the first 64k of
 			memory when doing things like suspend/resume.
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index b7d31ca..9e3bcd6 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..960a8a9 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=y 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..11cc7d5 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;
@@ -343,7 +346,7 @@ int __init sanitize_e820_map(struct e820entry *biosmap, int max_nr_map,
 		 * continue building up new bios map based on this
 		 * information
 		 */
-		if (current_type != last_type)	{
+		if (current_type != last_type || current_type == E820_PRAM) {
 			if (last_type != 0)	 {
 				new_bios[new_bios_entry].size =
 					change_point[chgidx]->addr - last_addr;
@@ -688,6 +691,7 @@ 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)
 			register_nosave_region(PFN_UP(ei->addr), pfn);
 
@@ -748,7 +752,7 @@ 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 +763,11 @@ 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 +792,12 @@ 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)
@@ -866,6 +874,9 @@ static int __init parse_memmap_one(char *p)
 	} else if (*p == '$') {
 		start_at = memparse(p+1, &p);
 		e820_add_region(start_at, mem_size, E820_RESERVED);
+	} else if (*p == '!') {
+		start_at = memparse(p+1, &p);
+		e820_add_region(start_at, mem_size, E820_PRAM);
 	} else
 		e820_remove_range(mem_size, ULLONG_MAX - mem_size, E820_RAM, 1);
 
@@ -907,6 +918,7 @@ 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";
 	}
 }
@@ -940,7 +952,9 @@ void __init e820_reserve_resources(void)
 		 * pci device BAR resource and insert them later in
 		 * pcibios_resource_survey()
 		 */
-		if (e820.map[i].type != E820_RESERVED || res->start < (1ULL<<20)) {
+		if (((e820.map[i].type != E820_RESERVED) &&
+		     (e820.map[i].type != E820_PRAM)) ||
+		     res->start < (1ULL<<20)) {
 			res->flags |= IORESOURCE_BUSY;
 			insert_resource(&iomem_resource, res);
 		}
diff --git a/arch/x86/kernel/pmem.c b/arch/x86/kernel/pmem.c
new file mode 100644
index 0000000..3420c87
--- /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' (persistent memory) 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);