[PATCH v3 17/21] KVM: arm64: Mark host bss and rodata section as shared

[Fuad Tabba]

Hi Quentin,

On Thu, Jul 29, 2021 at 3:29 PM Quentin Perret <qperret at google.com> wrote:
>
> As the hypervisor maps the host's .bss and .rodata sections in its
> stage-1, make sure to tag them as shared in hyp and host page-tables.
>
> But since the hypervisor relies on the presence of these mappings, we
> cannot let the host in complete control of the memory regions -- it
> must not unshare or donate them to another entity for example. To
> prevent this, let's transfer the ownership of those ranges to the
> hypervisor itself, and share the pages back with the host.
>
> Signed-off-by: Quentin Perret <qperret at google.com>
> ---
>  arch/arm64/kvm/hyp/nvhe/setup.c | 82 +++++++++++++++++++++++++++++----
>  1 file changed, 74 insertions(+), 8 deletions(-)
>
> diff --git a/arch/arm64/kvm/hyp/nvhe/setup.c b/arch/arm64/kvm/hyp/nvhe/setup.c
> index 0b574d106519..7f557b264f62 100644
> --- a/arch/arm64/kvm/hyp/nvhe/setup.c
> +++ b/arch/arm64/kvm/hyp/nvhe/setup.c
> @@ -58,6 +58,7 @@ static int recreate_hyp_mappings(phys_addr_t phys, unsigned long size,
>  {
>         void *start, *end, *virt = hyp_phys_to_virt(phys);
>         unsigned long pgt_size = hyp_s1_pgtable_pages() << PAGE_SHIFT;
> +       enum kvm_pgtable_prot prot;
>         int ret, i;
>
>         /* Recreate the hyp page-table using the early page allocator */
> @@ -83,10 +84,6 @@ static int recreate_hyp_mappings(phys_addr_t phys, unsigned long size,
>         if (ret)
>                 return ret;
>
> -       ret = pkvm_create_mappings(__start_rodata, __end_rodata, PAGE_HYP_RO);
> -       if (ret)
> -               return ret;
> -
>         ret = pkvm_create_mappings(__hyp_rodata_start, __hyp_rodata_end, PAGE_HYP_RO);
>         if (ret)
>                 return ret;
> @@ -95,10 +92,6 @@ static int recreate_hyp_mappings(phys_addr_t phys, unsigned long size,
>         if (ret)
>                 return ret;
>
> -       ret = pkvm_create_mappings(__hyp_bss_end, __bss_stop, PAGE_HYP_RO);
> -       if (ret)
> -               return ret;
> -
>         ret = pkvm_create_mappings(virt, virt + size, PAGE_HYP);
>         if (ret)
>                 return ret;
> @@ -117,6 +110,24 @@ static int recreate_hyp_mappings(phys_addr_t phys, unsigned long size,
>                         return ret;
>         }
>
> +       /*
> +        * Map the host's .bss and .rodata sections RO in the hypervisor, but
> +        * transfer the ownerhsip from the host to the hypervisor itself to
> +        * make sure it can't be donated or shared with another entity.

nit: ownerhsip -> ownership

> +        *
> +        * The ownership transtion requires matching changes in the host

nit: transtion -> transition

> +        * stage-2. This will done later (see finalize_host_mappings()) once the

nit: will done -> will be done

> +        * hyp_vmemmap is addressable.
> +        */
> +       prot = pkvm_mkstate(PAGE_HYP_RO, PKVM_PAGE_SHARED_OWNED);
> +       ret = pkvm_create_mappings(__start_rodata, __end_rodata, prot);
> +       if (ret)
> +               return ret;
> +
> +       ret = pkvm_create_mappings(__hyp_bss_end, __bss_stop, prot);

nit: for clarity, I wonder if it might be good to create an alias of
__hyp_bss_end as __bss_start or something. When it's been moved here,
it sticks out a bit more and makes the reader wonder about the
significance of __hyp_bss_end.

> +       if (ret)
> +               return ret;
> +
>         return 0;
>  }
>
> @@ -148,6 +159,57 @@ static void hpool_put_page(void *addr)
>         hyp_put_page(&hpool, addr);
>  }
>
> +static int finalize_host_mappings_walker(u64 addr, u64 end, u32 level,
> +                                        kvm_pte_t *ptep,
> +                                        enum kvm_pgtable_walk_flags flag,
> +                                        void * const arg)
> +{
> +       enum kvm_pgtable_prot prot;
> +       enum pkvm_page_state state;
> +       kvm_pte_t pte = *ptep;
> +       phys_addr_t phys;
> +
> +       if (!kvm_pte_valid(pte))
> +               return 0;
> +
> +       if (level != (KVM_PGTABLE_MAX_LEVELS - 1))
> +               return -EINVAL;

I know that it's not in scope here, but I'm wondering whether we
should be checking for KVM_PTE_TYPE_PAGE instead of the level. Maybe
it would be good to have a helper somewhere for all these checks both
for clarity and to ensure that nothing has gone wrong with the pte.

> +
> +       phys = kvm_pte_to_phys(pte);
> +       if (!addr_is_memory(phys))
> +               return 0;
> +
> +       /*
> +        * Adjust the host stage-2 mappings to match the ownership attributes
> +        * configured in the hypervisor stage-1.
> +        */
> +       state = pkvm_getstate(kvm_pgtable_hyp_pte_prot(pte));
> +       switch (state) {
> +       case PKVM_PAGE_OWNED:
> +               return host_stage2_set_owner_locked(phys, phys + PAGE_SIZE, pkvm_hyp_id);
> +       case PKVM_PAGE_SHARED_OWNED:
> +               prot = pkvm_mkstate(KVM_PGTABLE_PROT_RWX, PKVM_PAGE_SHARED_BORROWED);
> +               break;
> +       case PKVM_PAGE_SHARED_BORROWED:
> +               prot = pkvm_mkstate(KVM_PGTABLE_PROT_RWX, PKVM_PAGE_SHARED_OWNED);
> +               break;
> +       default:
> +               return -EINVAL;
> +       }
> +
> +       return host_stage2_idmap_locked(phys, phys + PAGE_SIZE, prot);
> +}
> +
> +static int finalize_host_mappings(void)
> +{
> +       struct kvm_pgtable_walker walker = {
> +               .cb     = finalize_host_mappings_walker,
> +               .flags  = KVM_PGTABLE_WALK_LEAF,
> +       };
> +
> +       return kvm_pgtable_walk(&pkvm_pgtable, 0, BIT(pkvm_pgtable.ia_bits), &walker);
> +}
> +
>  void __noreturn __pkvm_init_finalise(void)
>  {
>         struct kvm_host_data *host_data = this_cpu_ptr(&kvm_host_data);
> @@ -167,6 +229,10 @@ void __noreturn __pkvm_init_finalise(void)
>         if (ret)
>                 goto out;
>
> +       ret = finalize_host_mappings();
> +       if (ret)
> +               goto out;
> +
>         pkvm_pgtable_mm_ops = (struct kvm_pgtable_mm_ops) {
>                 .zalloc_page = hyp_zalloc_hyp_page,
>                 .phys_to_virt = hyp_phys_to_virt,
> --
> 2.32.0.432.gabb21c7263-goog
>

Thanks,
/fuad