Re: [Xen-devel] [PATCH 07/11] xen/mmu: Recycle the Xen provided L4, L3, and L2 pages

[Stefano Stabellini <stefano.stabellini@xxxxxxxxxxxxx>]

On Thu, 16 Aug 2012, Konrad Rzeszutek Wilk wrote:
> As we are not using them. We end up only using the L1 pagetables
> and grafting those to our page-tables.
> 
> [v1: Per Stefano's suggestion squashed two commits]
> [v2: Per Stefano's suggestion simplified loop]
> [v3: Fix smatch warnings]
> Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@xxxxxxxxxx>
> ---
>  arch/x86/xen/mmu.c |   40 +++++++++++++++++++++++++++++++++-------
>  1 files changed, 33 insertions(+), 7 deletions(-)
> 
> diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
> index a59070b..bd92c82 100644
> --- a/arch/x86/xen/mmu.c
> +++ b/arch/x86/xen/mmu.c
> @@ -1708,7 +1708,20 @@ static void convert_pfn_mfn(void *v)
>       for (i = 0; i < PTRS_PER_PTE; i++)
>               pte[i] = xen_make_pte(pte[i].pte);
>  }
> -
> +static void __init check_pt_base(unsigned long *pt_base, unsigned long 
> *pt_end,
> +                              unsigned long addr)
> +{
> +     if (*pt_base == PFN_DOWN(__pa(addr))) {
> +             set_page_prot((void *)addr, PAGE_KERNEL);
> +             clear_page((void *)addr);
> +             (*pt_base)++;
> +     }
> +     if (*pt_end == PFN_DOWN(__pa(addr))) {
> +             set_page_prot((void *)addr, PAGE_KERNEL);
> +             clear_page((void *)addr);
> +             (*pt_end)--;
> +     }
> +}
>  /*
>   * Set up the initial kernel pagetable.
>   *
> @@ -1724,6 +1737,9 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, 
> unsigned long max_pfn)
>  {
>       pud_t *l3;
>       pmd_t *l2;
> +     unsigned long addr[3];
> +     unsigned long pt_base, pt_end;
> +     unsigned i;
>  
>       /* max_pfn_mapped is the last pfn mapped in the initial memory
>        * mappings. Considering that on Xen after the kernel mappings we
> @@ -1731,6 +1747,9 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, 
> unsigned long max_pfn)
>        * set max_pfn_mapped to the last real pfn mapped. */
>       max_pfn_mapped = PFN_DOWN(__pa(xen_start_info->mfn_list));
>  
> +     pt_base = PFN_DOWN(__pa(xen_start_info->pt_base));
> +     pt_end = PFN_DOWN(__pa(xen_start_info->pt_base + 
> (xen_start_info->nr_pt_frames * PAGE_SIZE)));

code style

>       /* Zap identity mapping */
>       init_level4_pgt[0] = __pgd(0);
>  
> @@ -1749,6 +1768,9 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, 
> unsigned long max_pfn)
>       l3 = m2v(pgd[pgd_index(__START_KERNEL_map)].pgd);
>       l2 = m2v(l3[pud_index(__START_KERNEL_map)].pud);
>  
> +     addr[0] = (unsigned long)pgd;
> +     addr[1] = (unsigned long)l3;
> +     addr[2] = (unsigned long)l2;
>       /* Graft it onto L4[272][0]. Note that we creating an aliasing problem:
>        * Both L4[272][0] and L4[511][511] have entries that point to the same
>        * L2 (PMD) tables. Meaning that if you modify it in __va space
> @@ -1782,20 +1804,24 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, 
> unsigned long max_pfn)
>       /* Unpin Xen-provided one */
>       pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, PFN_DOWN(__pa(pgd)));
>  
> -     /* Switch over */
> -     pgd = init_level4_pgt;
> -
>       /*
>        * At this stage there can be no user pgd, and no page
>        * structure to attach it to, so make sure we just set kernel
>        * pgd.
>        */
>       xen_mc_batch();
> -     __xen_write_cr3(true, __pa(pgd));
> +     __xen_write_cr3(true, __pa(init_level4_pgt));
>       xen_mc_issue(PARAVIRT_LAZY_CPU);
>  
> -     memblock_reserve(__pa(xen_start_info->pt_base),
> -                      xen_start_info->nr_pt_frames * PAGE_SIZE);
> +     /* We can't that easily rip out L3 and L2, as the Xen pagetables are
> +      * set out this way: [L4], [L1], [L2], [L3], [L1], [L1] ...  for
> +      * the initial domain. For guests using the toolstack, they are in:
> +      * [L4], [L3], [L2], [L1], [L1], order .. */
> +     for (i = 0; i < ARRAY_SIZE(addr); i++)
> +             check_pt_base(&pt_base, &pt_end, addr[i]);

It is much clearer now, but if the comment is correct, doesn't it mean
that we are going to be able to free pgd, l3 and l2 only in the non-dom0
case?
If so it might be worth saying it explicitly.

Other than that, it is fine by me.


> +     /* Our (by three pages) smaller Xen pagetable that we are using */
> +     memblock_reserve(PFN_PHYS(pt_base), (pt_end - pt_base) * PAGE_SIZE);
>  }
>  #else        /* !CONFIG_X86_64 */
>  static RESERVE_BRK_ARRAY(pmd_t, initial_kernel_pmd, PTRS_PER_PMD);
> -- 
> 1.7.7.6
> 
> 
> _______________________________________________
> Xen-devel mailing list
> Xen-devel@xxxxxxxxxxxxx
> http://lists.xen.org/xen-devel
> 

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