Re: [Xen-devel] [PATCH V2 3/3] xen: eliminate scalability issues from initial mapping setup

[David Vrabel <david.vrabel@xxxxxxxxxx>]

On 17/09/14 05:12, Juergen Gross wrote:
> Direct Xen to place the initial P->M table outside of the initial
> mapping, as otherwise the 1G (implementation) / 2G (theoretical)
> restriction on the size of the initial mapping limits the amount
> of memory a domain can be handed initially.
> 
> As the initial P->M table is copied rather early during boot to
> domain private memory and it's initial virtual mapping is dropped,
> the easiest way to avoid virtual address conflicts with other
> addresses in the kernel is to use a user address area for the
> virtual address of the initial P->M table. This allows us to just
> throw away the page tables of the initial mapping after the copy
> without having to care about address invalidation.

This needs an additional paragraph like:

  "This does not increase the amount of memory the guest can use.  This
is still limited to 512 GiB by the 3-level p2m."

> --- a/arch/x86/xen/mmu.c
> +++ b/arch/x86/xen/mmu.c
> @@ -1198,6 +1198,76 @@ static void __init xen_cleanhighmap(unsigned long 
> vaddr,
[...]
> +/*
> + * Since it is well isolated we can (and since it is perhaps large we should)
> + * also free the page tables mapping the initial P->M table.
> + */
> +static void __init xen_cleanmfnmap(unsigned long vaddr)
> +{
> +     unsigned long va = vaddr & PMD_MASK;
> +     unsigned long pa;
> +     pgd_t *pgd = pgd_offset_k(va);
> +     pud_t *pud_page = pud_offset(pgd, 0);
> +     pud_t *pud;
> +     pmd_t *pmd;
> +     pte_t *pte;
> +     unsigned int i;
> +
> +     set_pgd(pgd, __pgd(0));
> +     do {
> +             pud = pud_page + pud_index(va);
> +             if (pud_none(*pud)) {
> +                     va += PUD_SIZE;
> +             } else if (pud_large(*pud)) {
> +                     pa = pud_val(*pud) & PHYSICAL_PAGE_MASK;
> +                     xen_free_ro_pages(pa, PUD_SIZE);
> +                     va += PUD_SIZE;

Are you missing a ClearPagePinned(..) here?

> +             } else {
> +                     pmd = pmd_offset(pud, va);
> +                     if (pmd_large(*pmd)) {
> +                             pa = pmd_val(*pmd) & PHYSICAL_PAGE_MASK;
> +                             xen_free_ro_pages(pa, PMD_SIZE);
> +                     } else if (!pmd_none(*pmd)) {
> +                             pte = pte_offset_kernel(pmd, va);
> +                             for (i = 0; i < PTRS_PER_PTE; ++i) {
> +                                     if (pte_none(pte[i]))
> +                                             break;
> +                                     pa = pte_pfn(pte[i]) << PAGE_SHIFT;
> +                                     xen_free_ro_pages(pa, PAGE_SIZE);
> +                             }

> +                             pa = __pa(pte) & PHYSICAL_PAGE_MASK;
> +                             ClearPagePinned(virt_to_page(__va(pa)));
> +                             xen_free_ro_pages(pa, PAGE_SIZE);

Put this into a helper function?  It's used here...

> +                     }
> +                     va += PMD_SIZE;
> +                     if (pmd_index(va))
> +                             continue;
> +                     pa = __pa(pmd) & PHYSICAL_PAGE_MASK;
> +                     ClearPagePinned(virt_to_page(__va(pa)));
> +                     xen_free_ro_pages(pa, PAGE_SIZE);

...and here...

> +             }
> +
> +     } while (pud_index(va) || pmd_index(va));
> +     pa = __pa(pud_page) & PHYSICAL_PAGE_MASK;
> +     ClearPagePinned(virt_to_page(__va(pa)));
> +     xen_free_ro_pages(pa, PAGE_SIZE);

... and here.

> @@ -1529,6 +1604,22 @@ static pte_t __init mask_rw_pte(pte_t *ptep, pte_t pte)
>  #else /* CONFIG_X86_64 */
>  static pte_t __init mask_rw_pte(pte_t *ptep, pte_t pte)
>  {
> +     unsigned long pfn;
> +
> +     if (xen_feature(XENFEAT_writable_page_tables) ||
> +         xen_feature(XENFEAT_auto_translated_physmap) ||
> +         xen_start_info->mfn_list >= __START_KERNEL_map)
> +             return pte;
> +
> +     /*
> +      * Pages belonging to the initial p2m list mapped outside the default
> +      * address range must be mapped read-only.

Why?  I didn't think was anything special about these MFNs.

David

_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxx
http://lists.xen.org/xen-devel