Re: [PATCH v3 08/11] KVM: arm64: Handle guest_memfd()-backed guest page faults

[Fuad Tabba <tabba@google.com>]

Hi Quentin,

On Tue, 11 Feb 2025 at 15:57, Quentin Perret <qperret@google.com> wrote:
>
> Hey Fuad,
>
> On Tuesday 11 Feb 2025 at 12:11:24 (+0000), Fuad Tabba wrote:
> > Add arm64 support for handling guest page faults on guest_memfd
> > backed memslots.
> >
> > For now, the fault granule is restricted to PAGE_SIZE.
> >
> > Signed-off-by: Fuad Tabba <tabba@google.com>
> > ---
> >  arch/arm64/kvm/mmu.c     | 84 ++++++++++++++++++++++++++--------------
> >  include/linux/kvm_host.h |  5 +++
> >  virt/kvm/kvm_main.c      |  5 ---
> >  3 files changed, 61 insertions(+), 33 deletions(-)
> >
> > diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
> > index b6c0acb2311c..305060518766 100644
> > --- a/arch/arm64/kvm/mmu.c
> > +++ b/arch/arm64/kvm/mmu.c
> > @@ -1454,6 +1454,33 @@ static bool kvm_vma_mte_allowed(struct vm_area_struct *vma)
> >       return vma->vm_flags & VM_MTE_ALLOWED;
> >  }
> >
> > +static kvm_pfn_t faultin_pfn(struct kvm *kvm, struct kvm_memory_slot *slot,
> > +                          gfn_t gfn, bool write_fault, bool *writable,
> > +                          struct page **page, bool is_private)
> > +{
> > +     kvm_pfn_t pfn;
> > +     int ret;
> > +
> > +     if (!is_private)
> > +             return __kvm_faultin_pfn(slot, gfn, write_fault ? FOLL_WRITE : 0, writable, page);
> > +
> > +     *writable = false;
> > +
> > +     if (WARN_ON_ONCE(write_fault && memslot_is_readonly(slot)))
> > +             return KVM_PFN_ERR_NOSLOT_MASK;
>
> I believe this check is superfluous, we should decide to report an MMIO
> exit to userspace for write faults to RO memslots and not get anywhere
> near user_mem_abort(). And nit but the error code should probably be
> KVM_PFN_ERR_RO_FAULT or something instead?

I tried to replicate the behavior of __kvm_faultin_pfn() here (but got
the wrong error!). I think you're right though that in the arm64 case,
this check isn't needed. Should I fix the return error and keep the
warning though?

> > +
> > +     ret = kvm_gmem_get_pfn(kvm, slot, gfn, &pfn, page, NULL);
> > +     if (!ret) {
> > +             *writable = write_fault;
>
> In normal KVM, if we're not dirty logging we'll actively map the page as
> writable if both the memslot and the userspace mappings are writable.
> With gmem, the latter doesn't make much sense, but essentially the
> underlying page should really be writable (e.g. no CoW getting in the
> way and such?). If so, then perhaps make this
>
>                 *writable = !memslot_is_readonly(slot);
>
> Wdyt?

Ack.

> > +             return pfn;
> > +     }
> > +
> > +     if (ret == -EHWPOISON)
> > +             return KVM_PFN_ERR_HWPOISON;
> > +
> > +     return KVM_PFN_ERR_NOSLOT_MASK;
> > +}
> > +
> >  static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
> >                         struct kvm_s2_trans *nested,
> >                         struct kvm_memory_slot *memslot, unsigned long hva,
> > @@ -1461,25 +1488,26 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
> >  {
> >       int ret = 0;
> >       bool write_fault, writable;
> > -     bool exec_fault, mte_allowed;
> > +     bool exec_fault, mte_allowed = false;
> >       bool device = false, vfio_allow_any_uc = false;
> >       unsigned long mmu_seq;
> >       phys_addr_t ipa = fault_ipa;
> >       struct kvm *kvm = vcpu->kvm;
> > -     struct vm_area_struct *vma;
> > +     struct vm_area_struct *vma = NULL;
> >       short vma_shift;
> >       void *memcache;
> > -     gfn_t gfn;
> > +     gfn_t gfn = ipa >> PAGE_SHIFT;
> >       kvm_pfn_t pfn;
> >       bool logging_active = memslot_is_logging(memslot);
> > -     bool force_pte = logging_active || is_protected_kvm_enabled();
> > -     long vma_pagesize, fault_granule;
> > +     bool is_private = kvm_mem_is_private(kvm, gfn);
>
> Just trying to understand the locking rule for the xarray behind this.
> Is it kvm->srcu that protects it for reads here? Something else?

I'm not sure I follow. Which xarray are you referring to?

>
> > +     bool force_pte = logging_active || is_private || is_protected_kvm_enabled();
> > +     long vma_pagesize, fault_granule = PAGE_SIZE;
> >       enum kvm_pgtable_prot prot = KVM_PGTABLE_PROT_R;
> >       struct kvm_pgtable *pgt;
> >       struct page *page;
> >       enum kvm_pgtable_walk_flags flags = KVM_PGTABLE_WALK_HANDLE_FAULT | KVM_PGTABLE_WALK_SHARED;
> >
> > -     if (fault_is_perm)
> > +     if (fault_is_perm && !is_private)
>
> Nit: not strictly necessary I think.

You're right.

Thanks,
/fuad

> >               fault_granule = kvm_vcpu_trap_get_perm_fault_granule(vcpu);
> >       write_fault = kvm_is_write_fault(vcpu);
> >       exec_fault = kvm_vcpu_trap_is_exec_fault(vcpu);
> > @@ -1510,24 +1538,30 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
> >                       return ret;
> >       }
> >
> > +     mmap_read_lock(current->mm);
> > +
> >       /*
> >        * Let's check if we will get back a huge page backed by hugetlbfs, or
> >        * get block mapping for device MMIO region.
> >        */
> > -     mmap_read_lock(current->mm);
> > -     vma = vma_lookup(current->mm, hva);
> > -     if (unlikely(!vma)) {
> > -             kvm_err("Failed to find VMA for hva 0x%lx\n", hva);
> > -             mmap_read_unlock(current->mm);
> > -             return -EFAULT;
> > -     }
> > +     if (!is_private) {
> > +             vma = vma_lookup(current->mm, hva);
> > +             if (unlikely(!vma)) {
> > +                     kvm_err("Failed to find VMA for hva 0x%lx\n", hva);
> > +                     mmap_read_unlock(current->mm);
> > +                     return -EFAULT;
> > +             }
> >
> > -     /*
> > -      * logging_active is guaranteed to never be true for VM_PFNMAP
> > -      * memslots.
> > -      */
> > -     if (WARN_ON_ONCE(logging_active && (vma->vm_flags & VM_PFNMAP)))
> > -             return -EFAULT;
> > +             /*
> > +              * logging_active is guaranteed to never be true for VM_PFNMAP
> > +              * memslots.
> > +              */
> > +             if (WARN_ON_ONCE(logging_active && (vma->vm_flags & VM_PFNMAP)))
> > +                     return -EFAULT;
> > +
> > +             vfio_allow_any_uc = vma->vm_flags & VM_ALLOW_ANY_UNCACHED;
> > +             mte_allowed = kvm_vma_mte_allowed(vma);
> > +     }
> >
> >       if (force_pte)
> >               vma_shift = PAGE_SHIFT;
> > @@ -1597,18 +1631,13 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
> >               ipa &= ~(vma_pagesize - 1);
> >       }
> >
> > -     gfn = ipa >> PAGE_SHIFT;
> > -     mte_allowed = kvm_vma_mte_allowed(vma);
> > -
> > -     vfio_allow_any_uc = vma->vm_flags & VM_ALLOW_ANY_UNCACHED;
> > -
> >       /* Don't use the VMA after the unlock -- it may have vanished */
> >       vma = NULL;
> >
> >       /*
> >        * Read mmu_invalidate_seq so that KVM can detect if the results of
> > -      * vma_lookup() or __kvm_faultin_pfn() become stale prior to
> > -      * acquiring kvm->mmu_lock.
> > +      * vma_lookup() or faultin_pfn() become stale prior to acquiring
> > +      * kvm->mmu_lock.
> >        *
> >        * Rely on mmap_read_unlock() for an implicit smp_rmb(), which pairs
> >        * with the smp_wmb() in kvm_mmu_invalidate_end().
> > @@ -1616,8 +1645,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
> >       mmu_seq = vcpu->kvm->mmu_invalidate_seq;
> >       mmap_read_unlock(current->mm);
> >
> > -     pfn = __kvm_faultin_pfn(memslot, gfn, write_fault ? FOLL_WRITE : 0,
> > -                             &writable, &page);
> > +     pfn = faultin_pfn(kvm, memslot, gfn, write_fault, &writable, &page, is_private);
> >       if (pfn == KVM_PFN_ERR_HWPOISON) {
> >               kvm_send_hwpoison_signal(hva, vma_shift);
> >               return 0;
> > diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
> > index 39fd6e35c723..415c6274aede 100644
> > --- a/include/linux/kvm_host.h
> > +++ b/include/linux/kvm_host.h
> > @@ -1882,6 +1882,11 @@ static inline int memslot_id(struct kvm *kvm, gfn_t gfn)
> >       return gfn_to_memslot(kvm, gfn)->id;
> >  }
> >
> > +static inline bool memslot_is_readonly(const struct kvm_memory_slot *slot)
> > +{
> > +     return slot->flags & KVM_MEM_READONLY;
> > +}
> > +
> >  static inline gfn_t
> >  hva_to_gfn_memslot(unsigned long hva, struct kvm_memory_slot *slot)
> >  {
> > diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
> > index 38f0f402ea46..3e40acb9f5c0 100644
> > --- a/virt/kvm/kvm_main.c
> > +++ b/virt/kvm/kvm_main.c
> > @@ -2624,11 +2624,6 @@ unsigned long kvm_host_page_size(struct kvm_vcpu *vcpu, gfn_t gfn)
> >       return size;
> >  }
> >
> > -static bool memslot_is_readonly(const struct kvm_memory_slot *slot)
> > -{
> > -     return slot->flags & KVM_MEM_READONLY;
> > -}
> > -
> >  static unsigned long __gfn_to_hva_many(const struct kvm_memory_slot *slot, gfn_t gfn,
> >                                      gfn_t *nr_pages, bool write)
> >  {
> > --
> > 2.48.1.502.g6dc24dfdaf-goog
> >