From: Nikita Kalyazin <[email protected]> userfaultfd missing mode allows populating guest memory with the content supplied by userspace on demand.
Extend guest_memfd implementation of vm_uffd_ops to support MISSING mode. Signed-off-by: Nikita Kalyazin <[email protected]> Co-developed-by: Mike Rapoport (Microsoft) <[email protected]> Signed-off-by: Mike Rapoport (Microsoft) <[email protected]> --- virt/kvm/guest_memfd.c | 60 +++++++++++++++++++++++++++++++++++++++++- 1 file changed, 59 insertions(+), 1 deletion(-) diff --git a/virt/kvm/guest_memfd.c b/virt/kvm/guest_memfd.c index 087e7632bf70..14cca057fc0e 100644 --- a/virt/kvm/guest_memfd.c +++ b/virt/kvm/guest_memfd.c @@ -431,6 +431,14 @@ static vm_fault_t kvm_gmem_fault_user_mapping(struct vm_fault *vmf) ret = VM_FAULT_UFFD_MINOR; goto out_folio; } + + /* + * Check if userfaultfd is registered in missing mode. If so, + * check if a folio exists in the page cache. If not, return + * VM_FAULT_UFFD_MISSING to trigger the userfaultfd handler. + */ + if (userfaultfd_missing(vmf->vma) && IS_ERR_OR_NULL(folio)) + return VM_FAULT_UFFD_MISSING; } /* folio not in the pagecache, try to allocate */ @@ -507,9 +515,59 @@ static bool kvm_gmem_can_userfault(struct vm_area_struct *vma, vm_flags_t vm_fla 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 = folio_alloc_mpol(gfp, 0, mpol, pgoff, numa_node_id()); + 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); + 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, + .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 */ -- 2.51.0
