Re: [RFC PATCH v2 02/51] KVM: guest_memfd: Introduce and use shareability to guard faulting

[Ackerley Tng <ackerleytng@google.com>]

Fuad Tabba <tabba@google.com> writes:

> Hi,
>
> .. snip..
>
>> I noticed that in [1], the kvm_gmem_mmap() does not check the range.
>> So, the WARN() here can be hit when userspace mmap() an area larger than the
>> inode size and accesses the out of band HVA.
>>
>> Maybe limit the mmap() range?
>>
>> @@ -1609,6 +1620,10 @@ static int kvm_gmem_mmap(struct file *file, struct vm_area_struct *vma)
>>         if (!kvm_gmem_supports_shared(file_inode(file)))
>>                 return -ENODEV;
>>
>> +       if (vma->vm_end - vma->vm_start + (vma->vm_pgoff << PAGE_SHIFT) > i_size_read(file_inode(file)))
>> +               return -EINVAL;
>> +
>>         if ((vma->vm_flags & (VM_SHARED | VM_MAYSHARE)) !=
>>             (VM_SHARED | VM_MAYSHARE)) {
>>                 return -EINVAL;
>>
>> [1] https://lore.kernel.org/all/20250513163438.3942405-8-tabba@google.com/
>
> I don't think we want to do that for a couple of reasons. We catch
> such invalid accesses on faulting, and, by analogy, afaikt, neither
> secretmem nor memfd perform a similar check on mmap (nor do
> memory-mapped files in general).
>
> There are also valid reasons why a user would want to deliberately
> mmap more memory than the backing store, knowing that it's only going
> to fault what it's going to use, e.g., alignment.
>

This is a good point.

I think there's no check against the inode size on faulting now though?
v10's [1] kvm_gmem_fault_shared() calls kvm_gmem_get_folio()
straightaway.

We should add a check like [2] to kvm_gmem_fault_shared().

[1] https://lore.kernel.org/all/20250513163438.3942405-8-tabba@google.com/
[2] https://github.com/torvalds/linux/blob/8477ab143069c6b05d6da4a8184ded8b969240f5/mm/filemap.c#L3373

> Cheers,
> /fuad
>
>
>> > +     return xa_to_value(entry);
>> > +}
>> > +
>> > +static struct folio *kvm_gmem_get_shared_folio(struct inode *inode, pgoff_t index)
>> > +{
>> > +     if (kvm_gmem_shareability_get(inode, index) != SHAREABILITY_ALL)
>> > +             return ERR_PTR(-EACCES);
>> > +
>> > +     return kvm_gmem_get_folio(inode, index);
>> > +}
>> > +
>> > +#else
>> > +
>> > +static int kvm_gmem_shareability_setup(struct maple_tree *mt, loff_t size, u64 flags)
>> > +{
>> > +     return 0;
>> > +}
>> > +
>> > +static inline struct folio *kvm_gmem_get_shared_folio(struct inode *inode, pgoff_t index)
>> > +{
>> > +     WARN_ONCE("Unexpected call to get shared folio.")
>> > +     return NULL;
>> > +}
>> > +
>> > +#endif /* CONFIG_KVM_GMEM_SHARED_MEM */
>> > +
>> >  static int __kvm_gmem_prepare_folio(struct kvm *kvm, struct kvm_memory_slot *slot,
>> >                                   pgoff_t index, struct folio *folio)
>> >  {
>> > @@ -333,7 +404,7 @@ static vm_fault_t kvm_gmem_fault_shared(struct vm_fault *vmf)
>> >
>> >       filemap_invalidate_lock_shared(inode->i_mapping);
>> >
>> > -     folio = kvm_gmem_get_folio(inode, vmf->pgoff);
>> > +     folio = kvm_gmem_get_shared_folio(inode, vmf->pgoff);
>> >       if (IS_ERR(folio)) {
>> >               int err = PTR_ERR(folio);
>> >
>> > @@ -420,8 +491,33 @@ static struct file_operations kvm_gmem_fops = {
>> >       .fallocate      = kvm_gmem_fallocate,
>> >  };
>> >
>> > +static void kvm_gmem_free_inode(struct inode *inode)
>> > +{
>> > +     struct kvm_gmem_inode_private *private = kvm_gmem_private(inode);
>> > +
>> > +     kfree(private);
>> > +
>> > +     free_inode_nonrcu(inode);
>> > +}
>> > +
>> > +static void kvm_gmem_destroy_inode(struct inode *inode)
>> > +{
>> > +     struct kvm_gmem_inode_private *private = kvm_gmem_private(inode);
>> > +
>> > +#ifdef CONFIG_KVM_GMEM_SHARED_MEM
>> > +     /*
>> > +      * mtree_destroy() can't be used within rcu callback, hence can't be
>> > +      * done in ->free_inode().
>> > +      */
>> > +     if (private)
>> > +             mtree_destroy(&private->shareability);
>> > +#endif
>> > +}
>> > +
>> >  static const struct super_operations kvm_gmem_super_operations = {
>> >       .statfs         = simple_statfs,
>> > +     .destroy_inode  = kvm_gmem_destroy_inode,
>> > +     .free_inode     = kvm_gmem_free_inode,
>> >  };
>> >
>> >  static int kvm_gmem_init_fs_context(struct fs_context *fc)
>> > @@ -549,12 +645,26 @@ static const struct inode_operations kvm_gmem_iops = {
>> >  static struct inode *kvm_gmem_inode_make_secure_inode(const char *name,
>> >                                                     loff_t size, u64 flags)
>> >  {
>> > +     struct kvm_gmem_inode_private *private;
>> >       struct inode *inode;
>> > +     int err;
>> >
>> >       inode = alloc_anon_secure_inode(kvm_gmem_mnt->mnt_sb, name);
>> >       if (IS_ERR(inode))
>> >               return inode;
>> >
>> > +     err = -ENOMEM;
>> > +     private = kzalloc(sizeof(*private), GFP_KERNEL);
>> > +     if (!private)
>> > +             goto out;
>> > +
>> > +     mt_init(&private->shareability);
>> Wrap the mt_init() inside "#ifdef CONFIG_KVM_GMEM_SHARED_MEM" ?
>>
>> > +     inode->i_mapping->i_private_data = private;
>> > +
>> > +     err = kvm_gmem_shareability_setup(private, size, flags);
>> > +     if (err)
>> > +             goto out;
>> > +
>> >       inode->i_private = (void *)(unsigned long)flags;
>> >       inode->i_op = &kvm_gmem_iops;
>> >       inode->i_mapping->a_ops = &kvm_gmem_aops;
>> > @@ -566,6 +676,11 @@ static struct inode *kvm_gmem_inode_make_secure_inode(const char *name,
>> >       WARN_ON_ONCE(!mapping_unevictable(inode->i_mapping));
>> >
>> >       return inode;
>> > +
>> > +out:
>> > +     iput(inode);
>> > +
>> > +     return ERR_PTR(err);
>> >  }
>> >
>> >  static struct file *kvm_gmem_inode_create_getfile(void *priv, loff_t size,
>> > @@ -654,6 +769,9 @@ int kvm_gmem_create(struct kvm *kvm, struct kvm_create_guest_memfd *args)
>> >       if (kvm_arch_vm_supports_gmem_shared_mem(kvm))
>> >               valid_flags |= GUEST_MEMFD_FLAG_SUPPORT_SHARED;
>> >
>> > +     if (flags & GUEST_MEMFD_FLAG_SUPPORT_SHARED)
>> > +             valid_flags |= GUEST_MEMFD_FLAG_INIT_PRIVATE;
>> > +
>> >       if (flags & ~valid_flags)
>> >               return -EINVAL;
>> >
>> > @@ -842,6 +960,8 @@ int kvm_gmem_get_pfn(struct kvm *kvm, struct kvm_memory_slot *slot,
>> >       if (!file)
>> >               return -EFAULT;
>> >
>> > +     filemap_invalidate_lock_shared(file_inode(file)->i_mapping);
>> > +
>> >       folio = __kvm_gmem_get_pfn(file, slot, index, pfn, &is_prepared, max_order);
>> >       if (IS_ERR(folio)) {
>> >               r = PTR_ERR(folio);
>> > @@ -857,8 +977,8 @@ int kvm_gmem_get_pfn(struct kvm *kvm, struct kvm_memory_slot *slot,
>> >               *page = folio_file_page(folio, index);
>> >       else
>> >               folio_put(folio);
>> > -
>> >  out:
>> > +     filemap_invalidate_unlock_shared(file_inode(file)->i_mapping);
>> >       fput(file);
>> >       return r;
>> >  }
>> > --
>> > 2.49.0.1045.g170613ef41-goog
>> >
>> >