Re: [Xen-devel] [PATCH 4/7] xen/mmu: Recycle the Xen provided L4,L3, and L2 pages

[Stefano Stabellini]

On Thu, 26 Jul 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.
> 
> Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@xxxxxxxxxx>
> ---
>  arch/x86/xen/mmu.c |   38 ++++++++++++++++++++++++++++++++------
>  1 files changed, 32 insertions(+), 6 deletions(-)
> 
> diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
> index 48bdc9f..7f54b75 100644
> --- a/arch/x86/xen/mmu.c
> +++ b/arch/x86/xen/mmu.c
> @@ -1724,6 +1724,9 @@ 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 +1734,9 @@ 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)));
> +
>  	/* Zap identity mapping */
>  	init_level4_pgt[0] = __pgd(0);
>  
> @@ -1749,6 +1755,9 @@ 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)l2;
> +	addr[2] = (unsigned long)l3;
>  	/* 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
> @@ -1791,12 +1800,29 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn)
>  	__xen_write_cr3(true, __pa(init_level4_pgt));
>  	xen_mc_issue(PARAVIRT_LAZY_CPU);
>  
> -	/* Offset by one page since the original pgd is going bye bye */
> -	memblock_reserve(__pa(xen_start_info->pt_base + PAGE_SIZE),
> -			 (xen_start_info->nr_pt_frames * PAGE_SIZE) - PAGE_SIZE);
> -	/* and also RW it so it can actually be used. */
> -	set_page_prot(pgd, PAGE_KERNEL);
> -	clear_page(pgd);
> +	/* 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++) {
> +		unsigned j;
> +		/* No idea about the order the addr are in, so just do them twice. */
> +		for (j = 0; j < ARRAY_SIZE(addr); j++) {

I don't think I understand this double loop.
Shouldn't we be looping on pt_base or pt_end?


> +			if (pt_base == PFN_DOWN(__pa(addr[j]))) {
> +				set_page_prot((void *)addr[j], PAGE_KERNEL);
> +				clear_page((void *)addr[j]);
> +				pt_base++;
> +
> +			}
> +			if (pt_end == PFN_DOWN(__pa(addr[j]))) {
> +				set_page_prot((void *)addr[j], PAGE_KERNEL);
> +				clear_page((void *)addr[j]);
> +				pt_end--;
> +			}
> +		}
> +	}
> +	/* Our (by three pages) smaller Xen pagetable that we are using */
> +	memblock_reserve(PFN_PHYS(pt_base), (pt_end - pt_base) * PAGE_SIZE);


--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/