Re: [PATCH v2 13/15] KVM: guest_memfd: implement userfaultfd operations

[James Houghton <jthoughton@google.com>]

On Fri, Mar 6, 2026 at 9:19 AM Mike Rapoport <rppt@kernel.org> wrote:
>
> From: Nikita Kalyazin <kalyazin@amazon.com>
>
> userfaultfd notifications about page faults used for live migration
> and snapshotting of VMs.
>
> MISSING mode allows post-copy live migration and MINOR mode allows
> optimization for post-copy live migration for VMs backed with shared
> hugetlbfs or tmpfs mappings as described in detail in commit
> 7677f7fd8be7 ("userfaultfd: add minor fault registration mode").
>
> To use the same mechanisms for VMs that use guest_memfd to map their
> memory, guest_memfd should support userfaultfd operations.
>
> Add implementation of vm_uffd_ops to guest_memfd.
>
> Signed-off-by: Nikita Kalyazin <kalyazin@amazon.com>
> Co-developed-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
> Signed-off-by: Mike Rapoport (Microsoft) <rppt@kernel.org>

Overall looks fine to me, but I am slightly concerned about in-place
conversion[1], and I think you're going to want to implement a
kvm_gmem_folio_present() op or something (like I was saying on the
previous patch[2]).

[1]: https://lore.kernel.org/kvm/20260326-gmem-inplace-conversion-v4-0-e202fe950ffd@google.com/
[2]: https://lore.kernel.org/linux-mm/CADrL8HVUJ5FL97d9ytxp2WXos6HS+U+ycpsi5VxffsW9vacr9Q@mail.gmail.com/

Some in-line comments below.

> ---
>  mm/filemap.c           |  1 +
>  virt/kvm/guest_memfd.c | 84 +++++++++++++++++++++++++++++++++++++++++-
>  2 files changed, 83 insertions(+), 2 deletions(-)
>
> diff --git a/mm/filemap.c b/mm/filemap.c
> index 6cd7974d4ada..19dfcebcd23f 100644
> --- a/mm/filemap.c
> +++ b/mm/filemap.c
> @@ -262,6 +262,7 @@ void filemap_remove_folio(struct folio *folio)
>
>         filemap_free_folio(mapping, folio);
>  }
> +EXPORT_SYMBOL_FOR_MODULES(filemap_remove_folio, "kvm");
>
>  /*
>   * page_cache_delete_batch - delete several folios from page cache
> diff --git a/virt/kvm/guest_memfd.c b/virt/kvm/guest_memfd.c
> index 017d84a7adf3..46582feeed75 100644
> --- a/virt/kvm/guest_memfd.c
> +++ b/virt/kvm/guest_memfd.c
> @@ -7,6 +7,7 @@
>  #include <linux/mempolicy.h>
>  #include <linux/pseudo_fs.h>
>  #include <linux/pagemap.h>
> +#include <linux/userfaultfd_k.h>
>
>  #include "kvm_mm.h"
>
> @@ -107,6 +108,12 @@ static int kvm_gmem_prepare_folio(struct kvm *kvm, struct kvm_memory_slot *slot,
>         return __kvm_gmem_prepare_folio(kvm, slot, index, folio);
>  }
>
> +static struct folio *kvm_gmem_get_folio_noalloc(struct inode *inode, pgoff_t pgoff)
> +{
> +       return __filemap_get_folio(inode->i_mapping, pgoff,
> +                                  FGP_LOCK | FGP_ACCESSED, 0);
> +}

When in-place conversion is supported, I wonder what the semantics
should be for when we get userfaults.

Upon a userspace access to a file offset that is populated but
private, should we get a userfault or a SIGBUS?

I guess getting a userfault is strictly more useful for userspace, but
I'm not sure which choice is more correct.

> +
>  /*
>   * Returns a locked folio on success.  The caller is responsible for
>   * setting the up-to-date flag before the memory is mapped into the guest.
> @@ -126,8 +133,7 @@ static struct folio *kvm_gmem_get_folio(struct inode *inode, pgoff_t index)
>          * Fast-path: See if folio is already present in mapping to avoid
>          * policy_lookup.
>          */
> -       folio = __filemap_get_folio(inode->i_mapping, index,
> -                                   FGP_LOCK | FGP_ACCESSED, 0);
> +       folio = kvm_gmem_get_folio_noalloc(inode, index);
>         if (!IS_ERR(folio))
>                 return folio;
>
> @@ -457,12 +463,86 @@ static struct mempolicy *kvm_gmem_get_policy(struct vm_area_struct *vma,
>  }
>  #endif /* CONFIG_NUMA */
>
> +#ifdef CONFIG_USERFAULTFD
> +static bool kvm_gmem_can_userfault(struct vm_area_struct *vma, vm_flags_t vm_flags)
> +{
> +       struct inode *inode = file_inode(vma->vm_file);
> +
> +       /*
> +        * Only support userfaultfd for guest_memfd with INIT_SHARED flag.
> +        * This ensures the memory can be mapped to userspace.
> +        */
> +       if (!(GMEM_I(inode)->flags & GUEST_MEMFD_FLAG_INIT_SHARED))
> +               return false;
> +
> +       return true;
> +}
> +
> +static struct folio *kvm_gmem_folio_alloc(struct vm_area_struct *vma,
> +                                         unsigned long addr)
> +{
> +       struct inode *inode = file_inode(vma->vm_file);
> +       pgoff_t pgoff = linear_page_index(vma, addr);
> +       struct mempolicy *mpol;
> +       struct folio *folio;
> +       gfp_t gfp;
> +
> +       if (unlikely(pgoff >= (i_size_read(inode) >> PAGE_SHIFT)))
> +               return NULL;
> +
> +       gfp = mapping_gfp_mask(inode->i_mapping);
> +       mpol = mpol_shared_policy_lookup(&GMEM_I(inode)->policy, pgoff);
> +       mpol = mpol ?: get_task_policy(current);
> +       folio = filemap_alloc_folio(gfp, 0, mpol);
> +       mpol_cond_put(mpol);
> +
> +       return folio;
> +}
> +
> +static int kvm_gmem_filemap_add(struct folio *folio,
> +                               struct vm_area_struct *vma,
> +                               unsigned long addr)
> +{
> +       struct inode *inode = file_inode(vma->vm_file);
> +       struct address_space *mapping = inode->i_mapping;
> +       pgoff_t pgoff = linear_page_index(vma, addr);
> +       int err;
> +
> +       __folio_set_locked(folio);
> +       err = filemap_add_folio(mapping, folio, pgoff, GFP_KERNEL);

This is going to get more interesting with in-place conversion. I'm
not really sure how to synchronize with it, but we'll probably need to
take the invalidate lock for reading. And then we'll need a separate
uffd_op to drop it after we install the PTE... I think.

> +       if (err) {
> +               folio_unlock(folio);
> +               return err;
> +       }
> +
> +       return 0;
> +}
> +
> +static void kvm_gmem_filemap_remove(struct folio *folio,
> +                                   struct vm_area_struct *vma)
> +{
> +       filemap_remove_folio(folio);
> +       folio_unlock(folio);
> +}
> +
> +static const struct vm_uffd_ops kvm_gmem_uffd_ops = {
> +       .can_userfault     = kvm_gmem_can_userfault,
> +       .get_folio_noalloc = kvm_gmem_get_folio_noalloc,
> +       .alloc_folio       = kvm_gmem_folio_alloc,
> +       .filemap_add       = kvm_gmem_filemap_add,
> +       .filemap_remove    = kvm_gmem_filemap_remove,
> +};
> +#endif /* CONFIG_USERFAULTFD */
> +
>  static const struct vm_operations_struct kvm_gmem_vm_ops = {
>         .fault          = kvm_gmem_fault_user_mapping,
>  #ifdef CONFIG_NUMA
>         .get_policy     = kvm_gmem_get_policy,
>         .set_policy     = kvm_gmem_set_policy,
>  #endif
> +#ifdef CONFIG_USERFAULTFD
> +       .uffd_ops       = &kvm_gmem_uffd_ops,
> +#endif
>  };
>
>  static int kvm_gmem_mmap(struct file *file, struct vm_area_struct *vma)
> --
> 2.51.0
>