| Message ID | 20210909162248.14969-4-david@redhat.com (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
| Series | s390: fixes, cleanups and optimizations for page table walkers | expand |
On Thu, 9 Sep 2021 18:22:42 +0200 David Hildenbrand <david@redhat.com> wrote: > We should not walk/touch page tables outside of VMA boundaries when > holding only the mmap sem in read mode. Evil user space can modify the > VMA layout just before this function runs and e.g., trigger races with > page table removal code since commit dd2283f2605e ("mm: mmap: zap pages > with read mmap_sem in munmap"). gfn_to_hva() will only translate using > KVM memory regions, but won't validate the VMA. > > Further, we should not allocate page tables outside of VMA boundaries: if > evil user space decides to map hugetlbfs to these ranges, bad things will > happen because we suddenly have PTE or PMD page tables where we > shouldn't have them. > > Similarly, we have to check if we suddenly find a hugetlbfs VMA, before > calling get_locked_pte(). > > Fixes: 2d42f9477320 ("s390/kvm: Add PGSTE manipulation functions") > Signed-off-by: David Hildenbrand <david@redhat.com> Reviewed-by: Claudio Imbrenda <imbrenda@linux.ibm.com> > --- > arch/s390/mm/pgtable.c | 13 +++++++++++++ > 1 file changed, 13 insertions(+) > > diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c > index eec3a9d7176e..54969e0f3a94 100644 > --- a/arch/s390/mm/pgtable.c > +++ b/arch/s390/mm/pgtable.c > @@ -988,6 +988,7 @@ EXPORT_SYMBOL(get_guest_storage_key); > int pgste_perform_essa(struct mm_struct *mm, unsigned long hva, int orc, > unsigned long *oldpte, unsigned long *oldpgste) > { > + struct vm_area_struct *vma; > unsigned long pgstev; > spinlock_t *ptl; > pgste_t pgste; > @@ -997,6 +998,10 @@ int pgste_perform_essa(struct mm_struct *mm, unsigned long hva, int orc, > WARN_ON_ONCE(orc > ESSA_MAX); > if (unlikely(orc > ESSA_MAX)) > return -EINVAL; > + > + vma = vma_lookup(mm, hva); > + if (!vma || is_vm_hugetlb_page(vma)) > + return -EFAULT; > ptep = get_locked_pte(mm, hva, &ptl); > if (unlikely(!ptep)) > return -EFAULT; > @@ -1089,10 +1094,14 @@ EXPORT_SYMBOL(pgste_perform_essa); > int set_pgste_bits(struct mm_struct *mm, unsigned long hva, > unsigned long bits, unsigned long value) > { > + struct vm_area_struct *vma; > spinlock_t *ptl; > pgste_t new; > pte_t *ptep; > > + vma = vma_lookup(mm, hva); > + if (!vma || is_vm_hugetlb_page(vma)) > + return -EFAULT; > ptep = get_locked_pte(mm, hva, &ptl); > if (unlikely(!ptep)) > return -EFAULT; > @@ -1117,9 +1126,13 @@ EXPORT_SYMBOL(set_pgste_bits); > */ > int get_pgste(struct mm_struct *mm, unsigned long hva, unsigned long *pgstep) > { > + struct vm_area_struct *vma; > spinlock_t *ptl; > pte_t *ptep; > > + vma = vma_lookup(mm, hva); > + if (!vma || is_vm_hugetlb_page(vma)) > + return -EFAULT; > ptep = get_locked_pte(mm, hva, &ptl); > if (unlikely(!ptep)) > return -EFAULT;
diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c index eec3a9d7176e..54969e0f3a94 100644 --- a/arch/s390/mm/pgtable.c +++ b/arch/s390/mm/pgtable.c @@ -988,6 +988,7 @@ EXPORT_SYMBOL(get_guest_storage_key); int pgste_perform_essa(struct mm_struct *mm, unsigned long hva, int orc, unsigned long *oldpte, unsigned long *oldpgste) { + struct vm_area_struct *vma; unsigned long pgstev; spinlock_t *ptl; pgste_t pgste; @@ -997,6 +998,10 @@ int pgste_perform_essa(struct mm_struct *mm, unsigned long hva, int orc, WARN_ON_ONCE(orc > ESSA_MAX); if (unlikely(orc > ESSA_MAX)) return -EINVAL; + + vma = vma_lookup(mm, hva); + if (!vma || is_vm_hugetlb_page(vma)) + return -EFAULT; ptep = get_locked_pte(mm, hva, &ptl); if (unlikely(!ptep)) return -EFAULT; @@ -1089,10 +1094,14 @@ EXPORT_SYMBOL(pgste_perform_essa); int set_pgste_bits(struct mm_struct *mm, unsigned long hva, unsigned long bits, unsigned long value) { + struct vm_area_struct *vma; spinlock_t *ptl; pgste_t new; pte_t *ptep; + vma = vma_lookup(mm, hva); + if (!vma || is_vm_hugetlb_page(vma)) + return -EFAULT; ptep = get_locked_pte(mm, hva, &ptl); if (unlikely(!ptep)) return -EFAULT; @@ -1117,9 +1126,13 @@ EXPORT_SYMBOL(set_pgste_bits); */ int get_pgste(struct mm_struct *mm, unsigned long hva, unsigned long *pgstep) { + struct vm_area_struct *vma; spinlock_t *ptl; pte_t *ptep; + vma = vma_lookup(mm, hva); + if (!vma || is_vm_hugetlb_page(vma)) + return -EFAULT; ptep = get_locked_pte(mm, hva, &ptl); if (unlikely(!ptep)) return -EFAULT;
We should not walk/touch page tables outside of VMA boundaries when holding only the mmap sem in read mode. Evil user space can modify the VMA layout just before this function runs and e.g., trigger races with page table removal code since commit dd2283f2605e ("mm: mmap: zap pages with read mmap_sem in munmap"). gfn_to_hva() will only translate using KVM memory regions, but won't validate the VMA. Further, we should not allocate page tables outside of VMA boundaries: if evil user space decides to map hugetlbfs to these ranges, bad things will happen because we suddenly have PTE or PMD page tables where we shouldn't have them. Similarly, we have to check if we suddenly find a hugetlbfs VMA, before calling get_locked_pte(). Fixes: 2d42f9477320 ("s390/kvm: Add PGSTE manipulation functions") Signed-off-by: David Hildenbrand <david@redhat.com> --- arch/s390/mm/pgtable.c | 13 +++++++++++++ 1 file changed, 13 insertions(+)