[PATCH kvm-next V11 6/7] KVM: guest_memfd: Enforce NUMA mempolicy using shared policy

[Sean Christopherson]

On Wed, Aug 27, 2025, Shivank Garg wrote:
> @@ -26,6 +28,9 @@ static inline struct kvm_gmem_inode_info *KVM_GMEM_I(struct inode *inode)
>  	return container_of(inode, struct kvm_gmem_inode_info, vfs_inode);
>  }
>  
> +static struct mempolicy *kvm_gmem_get_pgoff_policy(struct kvm_gmem_inode_info *info,
> +						   pgoff_t index);
> +
>  /**
>   * folio_file_pfn - like folio_file_page, but return a pfn.
>   * @folio: The folio which contains this index.
> @@ -112,7 +117,25 @@ static int kvm_gmem_prepare_folio(struct kvm *kvm, struct kvm_memory_slot *slot,
>  static struct folio *kvm_gmem_get_folio(struct inode *inode, pgoff_t index)
>  {
>  	/* TODO: Support huge pages. */
> -	return filemap_grab_folio(inode->i_mapping, index);
> +	struct mempolicy *policy;
> +	struct folio *folio;
> +
> +	/*
> +	 * 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);
> +	if (!IS_ERR(folio))
> +		return folio;
> +
> +	policy = kvm_gmem_get_pgoff_policy(KVM_GMEM_I(inode), index);
> +	folio = __filemap_get_folio_mpol(inode->i_mapping, index,
> +					 FGP_LOCK | FGP_ACCESSED | FGP_CREAT,
> +					 mapping_gfp_mask(inode->i_mapping), policy);
> +	mpol_cond_put(policy);
> +
> +	return folio;
>  }
>  
>  static void kvm_gmem_invalidate_begin(struct kvm_gmem *gmem, pgoff_t start,
> @@ -372,8 +395,45 @@ static vm_fault_t kvm_gmem_fault_user_mapping(struct vm_fault *vmf)
>  	return ret;
>  }
>  
> +#ifdef CONFIG_NUMA
> +static int kvm_gmem_set_policy(struct vm_area_struct *vma, struct mempolicy *mpol)
> +{
> +	struct inode *inode = file_inode(vma->vm_file);
> +
> +	return mpol_set_shared_policy(&KVM_GMEM_I(inode)->policy, vma, mpol);
> +}
> +
> +static struct mempolicy *kvm_gmem_get_policy(struct vm_area_struct *vma,
> +					     unsigned long addr, pgoff_t *pgoff)
> +{
> +	struct inode *inode = file_inode(vma->vm_file);
> +
> +	*pgoff = vma->vm_pgoff + ((addr - vma->vm_start) >> PAGE_SHIFT);
> +	return mpol_shared_policy_lookup(&KVM_GMEM_I(inode)->policy, *pgoff);
> +}
> +
> +static struct mempolicy *kvm_gmem_get_pgoff_policy(struct kvm_gmem_inode_info *info,
> +						   pgoff_t index)

I keep reading this is "page offset policy", as opposed to "policy given a page
offset".  Another oddity that is confusing is that this helper explicitly does
get_task_policy(current), while kvm_gmem_get_policy() lets the caller do that.
The end result is the same, but I think it would be helpful for gmem to be
internally consistent.

If we have kvm_gmem_get_policy() use this helper, then we can kill two birds with
one stone:

static struct mempolicy *__kvm_gmem_get_policy(struct gmem_inode *gi,
					       pgoff_t index)
{
	struct mempolicy *mpol;

	mpol = mpol_shared_policy_lookup(&gi->policy, index);
	return mpol ? mpol : get_task_policy(current);
}

static struct mempolicy *kvm_gmem_get_policy(struct vm_area_struct *vma,
					     unsigned long addr, pgoff_t *pgoff)
{
	*pgoff = vma->vm_pgoff + ((addr - vma->vm_start) >> PAGE_SHIFT);

	return __kvm_gmem_get_policy(GMEM_I(file_inode(vma->vm_file)), *pgoff);
}