Yinghai Lu wrote:
> Ingo Molnar wrote:
>> * Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx> wrote:
>>
>>> On Sat, 18 Apr 2009, Ingo Molnar wrote:
>>>> Am i missing something?
>>> We also try to avoid random motherboard resources etc that aren't
>>> reserved or documented by the BIOS. It's better to go into big
>>> holes. It's also better to try to keep as close to the old
>>> (tested) behavior.
>> Yeah - i'm not suggesting any change in behavior, nor am i
>> suggesting any risky behavior. The current code seems to work quite
>> well.
>>
>> I'm just suggesting (maybe foolishly) that instead of having any
>> gap-rounding logic at all, add artificial entries to the e820 map to
>> 'extend' and round up any odd ending entries.
>>
>> I.e. explicitly manage all the 'hole' space to be nicely rounded and
>> to be far away from any T-Seg or other sekrit motherboard resource
>> danger area.
>>
>> We'd do this after PCI static allocations (so we dont ever stomp on
>> real, known resources) but before PCI dynamic allocations.
>>
>> The e820 printout would look literally like this:
>>
>> BIOS-provided physical RAM map:
>> BIOS-e820: 0000000000000000 - 000000000009fc00 (usable) 0.639 MB RAM
>> BIOS-e820: 000000000009fc00 - 00000000000a0000 (reserved) 0.001 MB
>> [ hole ] 0.250 MB
>> BIOS-e820: 00000000000e0000 - 0000000000100000 (reserved) 0.125 MB
>> BIOS-e820: 0000000000100000 - 000000003ed94000 (usable) 1004.5 MB RAM
>> BIOS-e820: 000000003ed94000 - 000000003ee4e000 (ACPI NVS) 0.7 MB
>> BIOS-e820: 000000003ee4e000 - 000000003fea2000 (usable) 16.3 MB RAM
>> BIOS-e820: 000000003fea2000 - 000000003fee9000 (ACPI NVS) 0.3 MB
>> BIOS-e820: 000000003fee9000 - 000000003feed000 (usable) 0.15 MB RAM
>> BIOS-e820: 000000003feed000 - 000000003feff000 (ACPI data 0.07 MB
>> BIOS-e820: 000000003feff000 - 000000003ff00000 (usable) 0.004 MB RAM
>> BIOS-e820: 000000003ff00000 - 0000000040000000 (guard) 1.0 MB
>> [ hole ] 3072.0 MB
>>
>> The '(guard)' entry at the end i added above.
>>
>> This way we intentionally create a 'free physical address space'
>> hole space that is the same as the rounding logic. No rounding
>> needed anywhere - as all the remaining address space is well-rounded
>> already. Plus we'd also _see_ all our rounding logic by looking at
>> the '(guard)' entries.
>>
>> Or maybe there's some aspect of gap-rounding that cannot be
>> expressed in such a static way?
>>
>
> please check following patch.
>
> From: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
>
> [PATCH] x86: reserve range near the ram -v2
>
> some BIOS use ram near end, but don't state it, just try to reserve them
> as RAM buffer
>
> v2: make it in e820 table early instead of resource tree.
>
> [Impact: protect stolen RAM]
>
> Signed-off-by: Yinghai Lu <yinghai@xxxxxxxxxx>
>
> ---
> arch/x86/include/asm/e820.h | 2 +
> arch/x86/kernel/e820.c | 52 ++++++++++++++++++++++++++++++++++++++++++++
> arch/x86/kernel/setup.c | 6 +++++
> 3 files changed, 60 insertions(+)
>
> Index: linux-2.6/arch/x86/kernel/e820.c
> ===================================================================
> --- linux-2.6.orig/arch/x86/kernel/e820.c
> +++ linux-2.6/arch/x86/kernel/e820.c
> @@ -150,6 +150,9 @@ static void __init e820_print_type(u32 t
> case E820_UNUSABLE:
> printk(KERN_CONT "(unusable)");
> break;
> + case E820_RAM_BUFFER:
> + printk(KERN_CONT "(RAM buffer)");
> + break;
> default:
> printk(KERN_CONT "type %u", type);
> break;
> @@ -1314,6 +1317,54 @@ void __init finish_e820_parsing(void)
> }
> }
>
> +/* How much should we pad RAM ending depending on where it is? */
> +static unsigned long __init ram_alignment(resource_size_t pos)
> +{
> + unsigned long mb = pos >> 20;
> +
> + /* To 64kB in the first megabyte */
> + if (!mb)
> + return 64*1024;
> +
> + /* To 1MB in the first 16MB */
> + if (mb < 16)
> + return 1024*1024;
> +
> + /* To 32MB for anything above that */
> + return 32*1024*1024;
> +}
> +
> +void __init e820_reserve_stolen_ram(void)
> +{
> + int i;
> + int changed = 0;
> +
> + /*
> + * Try to bump up RAM regions to reasonable boundaries to
> + * avoid stolen RAM
> + */
> + for (i = 0; i < e820.nr_map; i++) {
> + struct e820entry *entry = &e820_saved.map[i];
> + resource_size_t start, end;
> +
> + if (entry->type != E820_RAM)
> + continue;
> + start = entry->addr + entry->size;
> + end = round_up(start, ram_alignment(start));
> + if (start == end)
> + continue;
> + e820_add_region(start, end - start, E820_RAM_BUFFER);
> + changed = 1;
> + }
> +
> + if (!changed)
> + return;
> +
> + sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map);
> + printk(KERN_INFO "fixed physical RAM map:\n");
> + e820_print_map("reserve_stolen_range");
> +}
> +
> static inline const char *e820_type_to_string(int e820_type)
> {
> switch (e820_type) {
> @@ -1322,6 +1373,7 @@ static inline const char *e820_type_to_s
> case E820_ACPI: return "ACPI Tables";
> case E820_NVS: return "ACPI Non-volatile Storage";
> case E820_UNUSABLE: return "Unusable memory";
> + case E820_RAM_BUFFER: return "RAM Buffer";
> default: return "reserved";
> }
> }
> Index: linux-2.6/arch/x86/include/asm/e820.h
> ===================================================================
> --- linux-2.6.orig/arch/x86/include/asm/e820.h
> +++ linux-2.6/arch/x86/include/asm/e820.h
> @@ -44,6 +44,7 @@
> #define E820_ACPI 3
> #define E820_NVS 4
> #define E820_UNUSABLE 5
> +#define E820_RAM_BUFFER 6
>
> /* reserved RAM used by kernel itself */
> #define E820_RESERVED_KERN 128
> @@ -78,6 +79,7 @@ extern u64 e820_update_range(u64 start,
> extern u64 e820_remove_range(u64 start, u64 size, unsigned old_type,
> int checktype);
> extern void update_e820(void);
> +extern void e820_reserve_stolen_ram(void);
> extern void e820_setup_gap(void);
> extern int e820_search_gap(unsigned long *gapstart, unsigned long *gapsize,
> unsigned long start_addr, unsigned long long end_addr);
> Index: linux-2.6/arch/x86/kernel/setup.c
> ===================================================================
> --- linux-2.6.orig/arch/x86/kernel/setup.c
> +++ linux-2.6/arch/x86/kernel/setup.c
> @@ -812,6 +812,12 @@ void __init setup_arch(char **cmdline_p)
> insert_resource(&iomem_resource, &data_resource);
> insert_resource(&iomem_resource, &bss_resource);
>
> + /*
> + * some systems use end of ram to for acpi or video ram
> + * but doesn't state that in reserved in e820
> + * try to round of ram etc and reserve them
> + */
> + e820_reserve_stolen_ram();
>
> #ifdef CONFIG_X86_32
> if (ppro_with_ram_bug()) {
>
it seems ram_alignment is too aggressive, it eat some RAM really
[ 0.000000] BIOS-provided physical RAM map:
[ 0.000000] BIOS-e820: 0000000000000000 - 0000000000097400 (usable)
[ 0.000000] BIOS-e820: 0000000000097400 - 00000000000a0000 (reserved)
[ 0.000000] BIOS-e820: 00000000000e0000 - 0000000000100000 (reserved)
[ 0.000000] BIOS-e820: 0000000000100000 - 00000000b7fa0000 (usable)
[ 0.000000] BIOS-e820: 00000000b7fae000 - 00000000b7fb0000 (usable)
[ 0.000000] BIOS-e820: 00000000b7fb0000 - 00000000b7fbe000 (ACPI data)
[ 0.000000] BIOS-e820: 00000000b7fbe000 - 00000000b7ff0000 (ACPI NVS)
[ 0.000000] BIOS-e820: 00000000b7ff0000 - 00000000b8000000 (reserved)
[ 0.000000] BIOS-e820: 00000000e0000000 - 00000000f0000000 (reserved)
[ 0.000000] BIOS-e820: 00000000fec00000 - 00000000fec01000 (reserved)
[ 0.000000] BIOS-e820: 00000000fee00000 - 00000000fef00000 (reserved)
[ 0.000000] BIOS-e820: 00000000ff700000 - 0000000100000000 (reserved)
[ 0.000000] BIOS-e820: 0000000100000000 - 0000002048000000 (usable)
[ 0.000000] Early serial console at I/O port 0x3f8 (options '115200n8')
[ 0.000000] console [uart0] enabled
[ 0.000000] DMI present.
[ 0.000000] fixed physical RAM map:
[ 0.000000] reserve_stolen_range: 0000000000000000 - 0000000000097400 (usable)
[ 0.000000] reserve_stolen_range: 0000000000097400 - 00000000000a0000 (RAM buffer)
[ 0.000000] reserve_stolen_range: 00000000000e0000 - 0000000000100000 (reserved)
[ 0.000000] reserve_stolen_range: 0000000000100000 - 00000000b7fa0000 (usable)
[ 0.000000] reserve_stolen_range: 00000000b7fa0000 - 00000000b8000000 (RAM buffer)
[ 0.000000] reserve_stolen_range: 00000000e0000000 - 00000000f0000000 (reserved)
[ 0.000000] reserve_stolen_range: 00000000fec00000 - 00000000fec01000 (reserved)
[ 0.000000] reserve_stolen_range: 00000000fee00000 - 00000000fef00000 (reserved)
[ 0.000000] reserve_stolen_range: 00000000ff700000 - 0000000100000000 (reserved)
[ 0.000000] reserve_stolen_range: 0000000100000000 - 0000002048000000 (usable)
--
To unsubscribe from this list: send the line "unsubscribe linux-pci" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
