Re: [RFC PATCH v2 03/11] KVM: guest_memfd: Allow host to map guest_memfd() pages

[David Hildenbrand <david@redhat.com>]

On 29.01.25 18:23, Fuad Tabba wrote:
> Add support for mmap() and fault() for guest_memfd backed memory
> in the host for VMs that support in-place conversion between
> shared and private (shared memory). To that end, this patch adds
> the ability to check whether the VM type has that support, and
> only allows mapping its memory if that's the case.
> 
> Additionally, this behavior is gated with a new configuration
> option, CONFIG_KVM_GMEM_SHARED_MEM.
> 
> Signed-off-by: Fuad Tabba <tabba@google.com>
> 
> ---
> 
> This patch series will allow shared memory support for software
> VMs in x86. It will also introduce a similar VM type for arm64
> and allow shared memory support for that. In the future, pKVM
> will also support shared memory.
> ---
>   include/linux/kvm_host.h | 11 ++++++
>   virt/kvm/Kconfig         |  4 +++
>   virt/kvm/guest_memfd.c   | 77 ++++++++++++++++++++++++++++++++++++++++
>   3 files changed, 92 insertions(+)
> 
> diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
> index 401439bb21e3..408429f13bf4 100644
> --- a/include/linux/kvm_host.h
> +++ b/include/linux/kvm_host.h
> @@ -717,6 +717,17 @@ static inline bool kvm_arch_has_private_mem(struct kvm *kvm)
>   }
>   #endif
>   
> +/*
> + * Arch code must define kvm_arch_gmem_supports_shared_mem if support for
> + * private memory is enabled and it supports in-place shared/private conversion.
> + */
> +#if !defined(kvm_arch_gmem_supports_shared_mem) && !IS_ENABLED(CONFIG_KVM_PRIVATE_MEM)
> +static inline bool kvm_arch_gmem_supports_shared_mem(struct kvm *kvm)
> +{
> +	return false;
> +}
> +#endif
> +
>   #ifndef kvm_arch_has_readonly_mem
>   static inline bool kvm_arch_has_readonly_mem(struct kvm *kvm)
>   {
> diff --git a/virt/kvm/Kconfig b/virt/kvm/Kconfig
> index 54e959e7d68f..4e759e8020c5 100644
> --- a/virt/kvm/Kconfig
> +++ b/virt/kvm/Kconfig
> @@ -124,3 +124,7 @@ config HAVE_KVM_ARCH_GMEM_PREPARE
>   config HAVE_KVM_ARCH_GMEM_INVALIDATE
>          bool
>          depends on KVM_PRIVATE_MEM
> +
> +config KVM_GMEM_SHARED_MEM
> +       select KVM_PRIVATE_MEM
> +       bool
> diff --git a/virt/kvm/guest_memfd.c b/virt/kvm/guest_memfd.c
> index 47a9f68f7b24..86441581c9ae 100644
> --- a/virt/kvm/guest_memfd.c
> +++ b/virt/kvm/guest_memfd.c
> @@ -307,7 +307,84 @@ static pgoff_t kvm_gmem_get_index(struct kvm_memory_slot *slot, gfn_t gfn)
>   	return gfn - slot->base_gfn + slot->gmem.pgoff;
>   }
>   
> +#ifdef CONFIG_KVM_GMEM_SHARED_MEM
> +static vm_fault_t kvm_gmem_fault(struct vm_fault *vmf)
> +{
> +	struct inode *inode = file_inode(vmf->vma->vm_file);
> +	struct folio *folio;
> +	vm_fault_t ret = VM_FAULT_LOCKED;
> +
> +	filemap_invalidate_lock_shared(inode->i_mapping);
> +
> +	folio = kvm_gmem_get_folio(inode, vmf->pgoff);
> +	if (IS_ERR(folio)) {
> +		ret = VM_FAULT_SIGBUS;
> +		goto out_filemap;
> +	}
> +
> +	if (folio_test_hwpoison(folio)) {
> +		ret = VM_FAULT_HWPOISON;
> +		goto out_folio;
> +	}
> +

Worth adding a comment, something like

/*
  * Only private folios are marked as "guestmem" so far, and we never
  * expect private folios at this point.
  */
> +	if (WARN_ON_ONCE(folio_test_guestmem(folio)))  {
> +		ret = VM_FAULT_SIGBUS;
> +		goto out_folio;
> +	}
> +
> +	/* No support for huge pages. */
> +	if (WARN_ON_ONCE(folio_nr_pages(folio) > 1)) {
> +		ret = VM_FAULT_SIGBUS;
> +		goto out_folio;
> +	}
> +

/* We only support mmap of small folios. */
VM_WARN_ON_ONCE(folio_test_large(folio));

> +	if (!folio_test_uptodate(folio)) {
> +		clear_highpage(folio_page(folio, 0));
> +		folio_mark_uptodate(folio);
> +	}
> +
> +	vmf->page = folio_file_page(folio, vmf->pgoff);
> +

Apart from that LGTM.

-- 
Cheers,

David / dhildenb