On Thu, Aug 9, 2012 at 2:23 PM, Jacob Shin <jacob.s...@amd.com> wrote:
> Currently direct mappings are created for [ 0 to max_low_pfn<<PAGE_SHIFT )
> and [ 4GB to max_pfn<<PAGE_SHIFT ), which may include regions that are not
> backed by actual DRAM. This is fine for holes under 4GB which are covered
> by fixed and variable range MTRRs to be UC. However, we run into trouble
> on higher memory addresses which cannot be covered by MTRRs.
>
> This patch iterates through e820 and only direct maps ranges that are
> marked as E820_RAM, and keeps track of those pfn ranges.
>
> Signed-off-by: Jacob Shin <jacob.s...@amd.com>
> ---
> arch/x86/include/asm/page_types.h | 9 ++++
> arch/x86/kernel/setup.c | 87
> +++++++++++++++++++++++++++++++++----
> 2 files changed, 88 insertions(+), 8 deletions(-)
>
> diff --git a/arch/x86/include/asm/page_types.h
> b/arch/x86/include/asm/page_types.h
> index e21fdd1..0b8aa52 100644
> --- a/arch/x86/include/asm/page_types.h
> +++ b/arch/x86/include/asm/page_types.h
> @@ -3,6 +3,7 @@
>
> #include <linux/const.h>
> #include <linux/types.h>
> +#include <asm/e820.h>
>
> /* PAGE_SHIFT determines the page size */
> #define PAGE_SHIFT 12
> @@ -40,12 +41,20 @@
> #endif /* CONFIG_X86_64 */
>
> #ifndef __ASSEMBLY__
> +#include <linux/range.h>
>
> extern int devmem_is_allowed(unsigned long pagenr);
>
> extern unsigned long max_low_pfn_mapped;
> extern unsigned long max_pfn_mapped;
>
> +extern struct range pfn_mapped[E820_X_MAX];
> +extern int nr_pfn_mapped;
> +
> +extern void add_pfn_range_mapped(unsigned long start_pfn, unsigned long
> end_pfn);
> +extern int pfn_range_is_mapped(unsigned long start_pfn, unsigned long
> end_pfn);
> +extern int pfn_is_mapped(unsigned long pfn);
> +
> static inline phys_addr_t get_max_mapped(void)
> {
> return (phys_addr_t)max_pfn_mapped << PAGE_SHIFT;
> diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
> index f4b9b80..4f26944 100644
> --- a/arch/x86/kernel/setup.c
> +++ b/arch/x86/kernel/setup.c
> @@ -115,13 +115,55 @@
> #include <asm/prom.h>
>
> /*
> - * end_pfn only includes RAM, while max_pfn_mapped includes all e820 entries.
> - * The direct mapping extends to max_pfn_mapped, so that we can directly
> access
> - * apertures, ACPI and other tables without having to play with fixmaps.
> + * max_low_pfn_mapped: highest direct mapped pfn under 4GB
> + * max_pfn_mapped: highest direct mapped pfn over 4GB
> + *
> + * The direct mapping only covers E820_RAM regions, so the ranges and gaps
> are
> + * represented by pfn_mapped
> */
> unsigned long max_low_pfn_mapped;
> unsigned long max_pfn_mapped;
>
> +struct range pfn_mapped[E820_X_MAX];
> +int nr_pfn_mapped;
> +
> +void add_pfn_range_mapped(unsigned long start_pfn, unsigned long end_pfn)
> +{
> + nr_pfn_mapped = add_range_with_merge(pfn_mapped, E820_X_MAX,
> + nr_pfn_mapped, start_pfn,
> end_pfn);
> +
> + if (end_pfn > max_pfn_mapped)
> + max_pfn_mapped = end_pfn;
> +
> + if ((end_pfn <= (1UL << (32 - PAGE_SHIFT))) &&
> + (end_pfn > max_low_pfn_mapped))
> + max_low_pfn_mapped = end_pfn;
> +}
> +
> +int pfn_range_is_mapped(unsigned long start_pfn, unsigned long end_pfn)
> +{
> + int i;
> +
> + for (i = 0; i < nr_pfn_mapped; i++)
> + if ((start_pfn >= pfn_mapped[i].start) &&
> + (end_pfn <= pfn_mapped[i].end))
> + break;
> +
> + return i < nr_pfn_mapped;
> +}
> +
> +int pfn_is_mapped(unsigned long pfn)
> +{
> + int i;
> +
> + for (i = 0; i < nr_pfn_mapped; i++)
> + if ((pfn >= pfn_mapped[i].start) &&
> + (pfn < pfn_mapped[i].end))
> + break;
> +
> + return i < nr_pfn_mapped;
> +}
> +
> #ifdef CONFIG_DMI
> RESERVE_BRK(dmi_alloc, 65536);
> #endif
> @@ -673,6 +715,9 @@ early_param("reservelow", parse_reservelow);
>
> void __init setup_arch(char **cmdline_p)
> {
> + int i;
> + unsigned long init_pfn, pfn;
> +
> #ifdef CONFIG_X86_32
> memcpy(&boot_cpu_data, &new_cpu_data, sizeof(new_cpu_data));
> visws_early_detect();
> @@ -913,14 +958,40 @@ void __init setup_arch(char **cmdline_p)
>
> init_gbpages();
>
> - /* max_pfn_mapped is updated here */
> - max_low_pfn_mapped = init_memory_mapping(0, max_low_pfn<<PAGE_SHIFT);
> - max_pfn_mapped = max_low_pfn_mapped;
> + init_pfn = max_pfn_mapped;
> +
> + memset(pfn_mapped, 0, sizeof(pfn_mapped));
> + nr_pfn_mapped = 0;
> +
> + add_pfn_range_mapped(0, max_pfn_mapped);
> +
> + for (i = 0; i < e820.nr_map; i++) {
> + struct e820entry *ei = &e820.map[i];
> + u64 start = ei->addr;
> + u64 end = ei->addr + ei->size;
> +
> + if (ei->type != E820_RAM)
> + continue;
> +
> + if (end <= (init_pfn << PAGE_SHIFT))
> + continue;
> +
> + if (start < (init_pfn << PAGE_SHIFT))
> + start = init_pfn << PAGE_SHIFT;
> +
> +#ifdef CONFIG_X86_32
> + if ((start >> PAGE_SHIFT) >= max_low_pfn)
> + continue;
> +
> + if ((end >> PAGE_SHIFT) > max_low_pfn)
> + end = max_low_pfn << PAGE_SHIFT;
> +#endif
> + pfn = init_memory_mapping(start, end);
> + add_pfn_range_mapped(start >> PAGE_SHIFT, pfn);
> + }
can you put those line in another function?
setup_arch is way too big now.
Also put tj to CC list, because last time I separate page table for
every node upset him.
Thanks
Yinghai Lu
>
> #ifdef CONFIG_X86_64
> if (max_pfn > max_low_pfn) {
> - max_pfn_mapped = init_memory_mapping(1UL<<32,
> - max_pfn<<PAGE_SHIFT);
> /* can we preseve max_low_pfn ?*/
> max_low_pfn = max_pfn;
> }
> --
> 1.7.9.5
>
>
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
