Re: [PATCH v12 08/18] KVM: guest_memfd: Allow host to map guest_memfd pages

[Sean Christopherson <seanjc@google.com>]

On Wed, Jun 11, 2025, Fuad Tabba wrote:
> This patch enables support for shared memory in guest_memfd, including

Please don't lead with with "This patch", simply state what changes are being
made as a command.

> mapping that memory from host userspace.

> This functionality is gated by the KVM_GMEM_SHARED_MEM Kconfig option,
> and enabled for a given instance by the GUEST_MEMFD_FLAG_SUPPORT_SHARED
> flag at creation time.

Why?  I can see that from the patch.

This changelog is way, way, waaay too light on details.  Sorry for jumping in at
the 11th hour, but we've spent what, 2 years working on this? 

> Reviewed-by: Gavin Shan <gshan@redhat.com>
> Acked-by: David Hildenbrand <david@redhat.com>
> Co-developed-by: Ackerley Tng <ackerleytng@google.com>
> Signed-off-by: Ackerley Tng <ackerleytng@google.com>
> Signed-off-by: Fuad Tabba <tabba@google.com>
> ---
> diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
> index d00b85cb168c..cb19150fd595 100644
> --- a/include/uapi/linux/kvm.h
> +++ b/include/uapi/linux/kvm.h
> @@ -1570,6 +1570,7 @@ struct kvm_memory_attributes {
>  #define KVM_MEMORY_ATTRIBUTE_PRIVATE           (1ULL << 3)
>  
>  #define KVM_CREATE_GUEST_MEMFD	_IOWR(KVMIO,  0xd4, struct kvm_create_guest_memfd)
> +#define GUEST_MEMFD_FLAG_SUPPORT_SHARED	(1ULL << 0)

I find the SUPPORT_SHARED terminology to be super confusing.  I had to dig quite
deep to undesrtand that "support shared" actually mean "userspace explicitly
enable sharing on _this_ guest_memfd instance".  E.g. I was surprised to see

IMO, GUEST_MEMFD_FLAG_SHAREABLE would be more appropriate.  But even that is
weird to me.  For non-CoCo VMs, there is no concept of shared vs. private.  What's
novel and notable is that the memory is _mappable_.  Yeah, yeah, pKVM's use case
is to share memory, but that's a _use case_, not the property of guest_memfd that
is being controlled by userspace.

And kvm_gmem_memslot_supports_shared() is even worse.  It's simply that the
memslot is bound to a mappable guest_memfd instance, it's that the guest_memfd
instance is the _only_ entry point to the memslot.

So my vote would be "GUEST_MEMFD_FLAG_MAPPABLE", and then something like
KVM_MEMSLOT_GUEST_MEMFD_ONLY.  That will make code like this:

	if (kvm_slot_has_gmem(slot) &&
	    (kvm_gmem_memslot_supports_shared(slot) ||
	     kvm_get_memory_attributes(kvm, gfn) & KVM_MEMORY_ATTRIBUTE_PRIVATE)) {
		return kvm_gmem_max_mapping_level(slot, gfn, max_level);
	}

much more intutive:

	if (kvm_is_memslot_gmem_only(slot) ||
	    kvm_get_memory_attributes(kvm, gfn) & KVM_MEMORY_ATTRIBUTE_PRIVATE))
		return kvm_gmem_max_mapping_level(slot, gfn, max_level);

And then have kvm_gmem_mapping_order() do:

	WARN_ON_ONCE(!kvm_slot_has_gmem(slot));
	return 0;

>  struct kvm_create_guest_memfd {
>  	__u64 size;
> diff --git a/virt/kvm/Kconfig b/virt/kvm/Kconfig
> index 559c93ad90be..e90884f74404 100644
> --- a/virt/kvm/Kconfig
> +++ b/virt/kvm/Kconfig
> @@ -128,3 +128,7 @@ config HAVE_KVM_ARCH_GMEM_PREPARE
>  config HAVE_KVM_ARCH_GMEM_INVALIDATE
>         bool
>         depends on KVM_GMEM
> +
> +config KVM_GMEM_SHARED_MEM
> +       select KVM_GMEM
> +       bool
> diff --git a/virt/kvm/guest_memfd.c b/virt/kvm/guest_memfd.c
> index 6db515833f61..06616b6b493b 100644
> --- a/virt/kvm/guest_memfd.c
> +++ b/virt/kvm/guest_memfd.c
> @@ -312,7 +312,77 @@ static pgoff_t kvm_gmem_get_index(struct kvm_memory_slot *slot, gfn_t gfn)
>  	return gfn - slot->base_gfn + slot->gmem.pgoff;
>  }
>  
> +static bool kvm_gmem_supports_shared(struct inode *inode)
> +{
> +	const u64 flags = (u64)inode->i_private;
> +
> +	if (!IS_ENABLED(CONFIG_KVM_GMEM_SHARED_MEM))
> +		return false;
> +
> +	return flags & GUEST_MEMFD_FLAG_SUPPORT_SHARED;
> +}
> +
> +static vm_fault_t kvm_gmem_fault_shared(struct vm_fault *vmf)

And to my point about "shared", this is also very confusing, because there are
zero checks in here about shared vs. private.

> +{
> +	struct inode *inode = file_inode(vmf->vma->vm_file);
> +	struct folio *folio;
> +	vm_fault_t ret = VM_FAULT_LOCKED;
> +
> +	if (((loff_t)vmf->pgoff << PAGE_SHIFT) >= i_size_read(inode))
> +		return VM_FAULT_SIGBUS;
> +
> +	folio = kvm_gmem_get_folio(inode, vmf->pgoff);
> +	if (IS_ERR(folio)) {
> +		int err = PTR_ERR(folio);
> +
> +		if (err == -EAGAIN)
> +			return VM_FAULT_RETRY;
> +
> +		return vmf_error(err);
> +	}
> +
> +	if (WARN_ON_ONCE(folio_test_large(folio))) {
> +		ret = VM_FAULT_SIGBUS;
> +		goto out_folio;
> +	}
> +
> +	if (!folio_test_uptodate(folio)) {
> +		clear_highpage(folio_page(folio, 0));
> +		kvm_gmem_mark_prepared(folio);
> +	}
> +
> +	vmf->page = folio_file_page(folio, vmf->pgoff);
> +
> +out_folio:
> +	if (ret != VM_FAULT_LOCKED) {
> +		folio_unlock(folio);
> +		folio_put(folio);
> +	}
> +
> +	return ret;
> +}
> +
> +static const struct vm_operations_struct kvm_gmem_vm_ops = {
> +	.fault = kvm_gmem_fault_shared,
> +};
> +
> +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_flags & (VM_SHARED | VM_MAYSHARE)) !=
> +	    (VM_SHARED | VM_MAYSHARE)) {

And the SHARED terminology gets really confusing here, due to colliding with the
existing notion of SHARED file mappings.

> +		return -EINVAL;
> +	}
> +
> +	vma->vm_ops = &kvm_gmem_vm_ops;
> +
> +	return 0;
> +}
> +
>  static struct file_operations kvm_gmem_fops = {
> +	.mmap		= kvm_gmem_mmap,
>  	.open		= generic_file_open,
>  	.release	= kvm_gmem_release,
>  	.fallocate	= kvm_gmem_fallocate,
> @@ -463,6 +533,9 @@ int kvm_gmem_create(struct kvm *kvm, struct kvm_create_guest_memfd *args)
>  	u64 flags = args->flags;
>  	u64 valid_flags = 0;
>  
> +	if (kvm_arch_supports_gmem_shared_mem(kvm))
> +		valid_flags |= GUEST_MEMFD_FLAG_SUPPORT_SHARED;
> +
>  	if (flags & ~valid_flags)
>  		return -EINVAL;
>  
> -- 
> 2.50.0.rc0.642.g800a2b2222-goog
>