zhongjiang <zhongjiang at huawei.com> writes:
> From: zhong jiang <zhongjiang at huawei.com>
>
> when image is loaded into kernel, we need set up page table for it. and
> all valid pfn also set up new mapping. it will tend to establish a pmd
> page table in the form of a large page if pud_present is true. relocate_kernel
> points to code segment can locate in the pmd huge entry in init_transtion_pgtable.
> therefore, we need to take the situation into account.
I can see how in theory this might be necessary but when is a kernel virtual
address on x86_64 that is above 0x8000000000000000 in conflict with an
identity mapped physicall address that are all below 0x8000000000000000?
If anything the code could be simplified to always assume those mappings
are unoccupied.
Did you run into an actual failure somewhere?
Eric
> Signed-off-by: zhong jiang <zhongjiang at huawei.com>
> ---
> arch/x86/kernel/machine_kexec_64.c | 20 ++++++++++++++++++--
> 1 file changed, 18 insertions(+), 2 deletions(-)
>
> diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c
> index 5a294e4..c33e344 100644
> --- a/arch/x86/kernel/machine_kexec_64.c
> +++ b/arch/x86/kernel/machine_kexec_64.c
> @@ -14,6 +14,7 @@
> #include <linux/gfp.h>
> #include <linux/reboot.h>
> #include <linux/numa.h>
> +#include <linux/hugetlb.h>
> #include <linux/ftrace.h>
> #include <linux/io.h>
> #include <linux/suspend.h>
> @@ -34,6 +35,17 @@ static struct kexec_file_ops *kexec_file_loaders[] = {
> };
> #endif
>
> +static void split_pmd(pmd_t *pmd, pte_t *pte)
> +{
> + unsigned long pfn = pmd_pfn(*pmd);
> + int i = 0;
> +
> + do {
> + set_pte(pte, pfn_pte(pfn, PAGE_KERNEL_EXEC));
> + pfn++;
> + } while (pte++, i++, i < PTRS_PER_PTE);
> +}
> +
> static void free_transition_pgtable(struct kimage *image)
> {
> free_page((unsigned long)image->arch.pud);
> @@ -68,15 +80,19 @@ static int init_transition_pgtable(struct kimage *image, pgd_t *pgd)
> set_pud(pud, __pud(__pa(pmd) | _KERNPG_TABLE));
> }
> pmd = pmd_offset(pud, vaddr);
> - if (!pmd_present(*pmd)) {
> + if (!pmd_present(*pmd) || pmd_huge(*pmd)) {
> pte = (pte_t *)get_zeroed_page(GFP_KERNEL);
> if (!pte)
> goto err;
> image->arch.pte = pte;
> - set_pmd(pmd, __pmd(__pa(pte) | _KERNPG_TABLE));
> + if (pmd_huge(*pmd))
> + split_pmd(pmd, pte);
> + else
> + set_pmd(pmd, __pmd(__pa(pte) | _KERNPG_TABLE));
> }
> pte = pte_offset_kernel(pmd, vaddr);
> set_pte(pte, pfn_pte(paddr >> PAGE_SHIFT, PAGE_KERNEL_EXEC));
> +
> return 0;
> err:
> free_transition_pgtable(image);
