On Thu, Mar 26, 2015 at 10:02:15AM +0100, Ingo Molnar wrote:
> This is_e820_ram() factoring out becomes really messy in patch #3.
>
> So you left out a bunch of places making comparisons with E820_RAM,
> notably e820_reserve_resources_late() and memblock_x86_fill() - and of
> course those have to be left out, otherwise NVRAM might be registered
> and used as real kernel RAM!
>
> And this shows the weakness and confusion caused by the factoring out
> of is_e820_ram() and then adding E820_PMEM to its definition...
>
> I'd rather you add explicit checks to E820_PMEM (why not E820_PRAM, to
> keep in line with the E820_RAM name?), and not lie about
> is_e820_ram(). It should result in the exact same end result, with
> less confusion.
>
> I have no fundamental objections to the driver otherwise.
Does this patch (replaces patches 2 and 3) look better to you?
---
>From 4a6fdc8433559d649d7bf707f72aafa4488f2d23 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@xxxxxx>
Date: Wed, 25 Mar 2015 12:24:11 +0100
Subject: x86: 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, and also provide a memmap=
argument to manually tag memory as protected, which can be used
if the BIOSs doesn't use the standard nonstandard interface, or
we just want to test the pmem driver with regular memory.
Based on an earlier patch from Dave Jiang <dave.jiang@xxxxxxxxx>
Signed-off-by: Christoph Hellwig <hch@xxxxxx>
Tested-by: Ross Zwisler <ross.zwisler@xxxxxxxxxxxxxxx>
---
Documentation/kernel-parameters.txt | 6 ++++
arch/x86/Kconfig | 10 ++++++
arch/x86/include/asm/setup.h | 6 ++++
arch/x86/include/uapi/asm/e820.h | 10 ++++++
arch/x86/kernel/Makefile | 1 +
arch/x86/kernel/e820.c | 31 ++++++++++++----
arch/x86/kernel/pmem.c | 70 +++++++++++++++++++++++++++++++++++++
arch/x86/kernel/setup.c | 2 ++
8 files changed, 130 insertions(+), 6 deletions(-)
create mode 100644 arch/x86/kernel/pmem.c
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..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/asm/setup.h b/arch/x86/include/asm/setup.h
index ff4e7b2..2352fde 100644
--- a/arch/x86/include/asm/setup.h
+++ b/arch/x86/include/asm/setup.h
@@ -57,6 +57,12 @@ extern void x86_ce4100_early_setup(void);
static inline void x86_ce4100_early_setup(void) { }
#endif
+#ifdef CONFIG_X86_PMEM_LEGACY
+void reserve_pmem(void);
+#else
+static inline void reserve_pmem(void) { }
+#endif
+
#ifndef _SETUP
#include <asm/espfix.h>
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..4bd525a 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)
@@ -866,6 +880,9 @@ 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 +924,7 @@ 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 +959,8 @@ 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..f970048
--- /dev/null
+++ b/arch/x86/kernel/pmem.c
@@ -0,0 +1,70 @@
+/*
+ * Copyright (c) 2009, Intel Corporation.
+ * 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>
+
+void __init reserve_pmem(void)
+{
+ int i;
+
+ for (i = 0; i < e820.nr_map; i++) {
+ struct e820entry *ei = &e820.map[i];
+
+ if (ei->type != E820_PRAM)
+ continue;
+
+ memblock_reserve(ei->addr, ei->addr + ei->size);
+ max_pfn_mapped = init_memory_mapping(
+ ei->addr < 1UL << 32 ? 1UL << 32 : ei->addr,
+ ei->addr + ei->size);
+ }
+}
+
+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);
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 0a2421c..f2bed2b 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -1158,6 +1158,8 @@ void __init setup_arch(char **cmdline_p)
early_acpi_boot_init();
+ reserve_pmem();
+
initmem_init();
dma_contiguous_reserve(max_pfn_mapped << PAGE_SHIFT);
--
1.9.1
--
To unsubscribe from this list: send the line "unsubscribe linux-fsdevel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
