Re: [PATCH v3 20/21] KVM: arm64: Restrict EL2 stage-1 changes in protected mode

[Quentin Perret]

On Tuesday 03 Aug 2021 at 10:22:03 (+0200), Fuad Tabba wrote:
> Hi Quentin,
> 
> > diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
> > index 0ccea58df7e0..1b67f562b6fc 100644
> > --- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c
> > +++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
> > @@ -338,6 +338,95 @@ static int host_stage2_idmap(u64 addr)
> >         return ret;
> >  }
> >
> > +static inline bool check_prot(enum kvm_pgtable_prot prot,
> > +                             enum kvm_pgtable_prot required,
> > +                             enum kvm_pgtable_prot denied)
> > +{
> > +       return (prot & (required | denied)) == required;
> > +}
> > +
> > +int __pkvm_host_share_hyp(u64 pfn)
> > +{
> > +       phys_addr_t addr = hyp_pfn_to_phys(pfn);
> > +       enum kvm_pgtable_prot prot, cur;
> > +       void *virt = __hyp_va(addr);
> > +       enum pkvm_page_state state;
> > +       kvm_pte_t pte;
> > +       u32 level;
> > +       int ret;
> > +
> > +       if (!range_is_memory(addr, addr + PAGE_SIZE))
> > +               return -EINVAL;
> > +
> > +       hyp_spin_lock(&host_kvm.lock);
> > +       hyp_spin_lock(&pkvm_pgd_lock);
> > +
> > +       ret = kvm_pgtable_get_leaf(&host_kvm.pgt, addr, &pte, &level);
> > +       if (ret)
> > +               goto unlock;
> > +       if (!pte)
> > +               goto map_shared;
> 
> Should this check whether kvm_pte_valid as well, is that guaranteed to
> always be the case, or implicitly handled later?

Yep, this is implicitly handled by kvm_pgtable_stage2_pte_prot() which
is guaranteed not to return KVM_PGTABLE_PROT_RWX for an invalid mapping.

> > +
> > +       /*
> > +        * Check attributes in the host stage-2 PTE. We need the page to be:
> > +        *  - mapped RWX as we're sharing memory;
> > +        *  - not borrowed, as that implies absence of ownership.
> > +        * Otherwise, we can't let it got through
> > +        */
> > +       cur = kvm_pgtable_stage2_pte_prot(pte);
> > +       prot = pkvm_mkstate(0, PKVM_PAGE_SHARED_BORROWED);
> > +       if (!check_prot(cur, KVM_PGTABLE_PROT_RWX, prot)) {
> > +               ret = -EPERM;
> > +               goto unlock;
> > +       }
> > +
> > +       state = pkvm_getstate(cur);
> > +       if (state == PKVM_PAGE_OWNED)
> > +               goto map_shared;
> > +
> > +       /*
> > +        * Tolerate double-sharing the same page, but this requires
> > +        * cross-checking the hypervisor stage-1.
> > +        */
> > +       if (state != PKVM_PAGE_SHARED_OWNED) {
> > +               ret = -EPERM;
> > +               goto unlock;
> > +       }
> > +
> > +       ret = kvm_pgtable_get_leaf(&pkvm_pgtable, (u64)virt, &pte, &level);
> > +       if (ret)
> > +               goto unlock;
> > +
> > +       /*
> > +        * If the page has been shared with the hypervisor, it must be
> > +        * SHARED_BORROWED already.
> > +        */
> 
> This comment confused me at first, but then I realized it's referring
> to the page from the hyp's point of view. Could you add something to
> the comment to that effect?

Sure thing.

> It might also make it easier to follow if the variables could be
> annotated to specify whether cur, state, and prot are the host's or
> hyps (and not reuse the same one for both).
> 
> > +       cur = kvm_pgtable_hyp_pte_prot(pte);
> > +       prot = pkvm_mkstate(PAGE_HYP, PKVM_PAGE_SHARED_BORROWED);
> > +       if (!check_prot(cur, prot, ~prot))
> > +               ret = EPERM;
> > +       goto unlock;
> > +
> > +map_shared:
> > +       /*
> > +        * If the page is not yet shared, adjust mappings in both page-tables
> > +        * while both locks are held.
> > +        */
> > +       prot = pkvm_mkstate(PAGE_HYP, PKVM_PAGE_SHARED_BORROWED);
> > +       ret = pkvm_create_mappings_locked(virt, virt + PAGE_SIZE, prot);
> > +       BUG_ON(ret);
> > +
> > +       prot = pkvm_mkstate(KVM_PGTABLE_PROT_RWX, PKVM_PAGE_SHARED_OWNED);
> > +       ret = host_stage2_idmap_locked(addr, addr + PAGE_SIZE, prot);
> > +       BUG_ON(ret);
> > +
> > +unlock:
> > +       hyp_spin_unlock(&pkvm_pgd_lock);
> > +       hyp_spin_unlock(&host_kvm.lock);
> > +
> > +       return ret;
> > +}
> > +
> >  void handle_host_mem_abort(struct kvm_cpu_context *host_ctxt)
> >  {
> >         struct kvm_vcpu_fault_info fault;
> > diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
> > index 0625bf2353c2..cbab146cda6a 100644
> > --- a/arch/arm64/kvm/mmu.c
> > +++ b/arch/arm64/kvm/mmu.c
> > @@ -259,10 +259,8 @@ static int __create_hyp_mappings(unsigned long start, unsigned long size,
> >  {
> >         int err;
> >
> > -       if (!kvm_host_owns_hyp_mappings()) {
> > -               return kvm_call_hyp_nvhe(__pkvm_create_mappings,
> > -                                        start, size, phys, prot);
> > -       }
> > +       if (WARN_ON(!kvm_host_owns_hyp_mappings()))
> > +               return -EINVAL;
> >
> >         mutex_lock(&kvm_hyp_pgd_mutex);
> >         err = kvm_pgtable_hyp_map(hyp_pgtable, start, size, phys, prot);
> > @@ -282,6 +280,21 @@ static phys_addr_t kvm_kaddr_to_phys(void *kaddr)
> >         }
> >  }
> >
> > +static int pkvm_share_hyp(phys_addr_t start, phys_addr_t end)
> > +{
> > +       phys_addr_t addr;
> > +       int ret;
> > +
> > +       for (addr = ALIGN_DOWN(start, PAGE_SIZE); addr < end; addr += PAGE_SIZE) {
> > +               ret = kvm_call_hyp_nvhe(__pkvm_host_share_hyp,
> > +                                       __phys_to_pfn(addr));
> 
> I guess we don't expect this to happen often, but I wonder if it would
> be better to have the looping in the hyp call rather than here, to
> reduce the number of hyp calls when sharing.

Yes, I was wondering the same thing, but ended up doing the looping here
to avoid spending long periods of time in a non-preemptible state at
EL2. Probably doesn't make a big difference for now, but it might if we
ever need to share large memory regions.

Cheers,
Quentin

> 
> Thanks,
> /fuad
> 
> > +               if (ret)
> > +                       return ret;
> > +       }
> > +
> > +       return 0;
> > +}
> > +
> >  /**
> >   * create_hyp_mappings - duplicate a kernel virtual address range in Hyp mode
> >   * @from:      The virtual kernel start address of the range
> > @@ -302,6 +315,13 @@ int create_hyp_mappings(void *from, void *to, enum kvm_pgtable_prot prot)
> >         if (is_kernel_in_hyp_mode())
> >                 return 0;
> >
> > +       if (!kvm_host_owns_hyp_mappings()) {
> > +               if (WARN_ON(prot != PAGE_HYP))
> > +                       return -EPERM;
> > +               return pkvm_share_hyp(kvm_kaddr_to_phys(from),
> > +                                     kvm_kaddr_to_phys(to));
> > +       }
> > +
> >         start = start & PAGE_MASK;
> >         end = PAGE_ALIGN(end);
> >
> > --
> > 2.32.0.432.gabb21c7263-goog
> >