Re: [PATCH 0/4] mm/userfaultfd: modulize memory types

[Nikita Kalyazin <kalyazin@amazon.com>]

On 25/06/2025 21:17, Peter Xu wrote:
> On Wed, Jun 25, 2025 at 05:56:23PM +0100, Nikita Kalyazin wrote:
>>
>>
>> On 20/06/2025 20:03, Peter Xu wrote:
>>> [based on akpm/mm-new]
>>>
>>> This series is an alternative proposal of what Nikita proposed here on the
>>> initial three patches:
>>>
>>>     https://lore.kernel.org/r/20250404154352.23078-1-kalyazin@amazon.com
>>>
>>> This is not yet relevant to any guest-memfd support, but paving way for it.
>>
>> Hi Peter,
> 
> Hi, Nikita,
> 
>>
>> Thanks for posting this.  I confirmed that minor fault handling was working
>> for guest_memfd based on this series and looked simple (a draft based on
>> mmap support in guest_memfd v7 [1]):
> 
> Thanks for the quick spin, glad to know it works. Some trivial things to
> mention below..

Following up, I drafted UFFDIO_COPY support for guest_memfd to confirm 
it works as well:

diff --git a/virt/kvm/guest_memfd.c b/virt/kvm/guest_memfd.c
index 8c44e4b9f5f8..b5458a22fff4 100644
--- a/virt/kvm/guest_memfd.c
+++ b/virt/kvm/guest_memfd.c
@@ -349,12 +349,19 @@ static bool kvm_gmem_offset_is_shared(struct file 
*file, pgoff_t index)

  static vm_fault_t kvm_gmem_fault(struct vm_fault *vmf)
  {
+	struct vm_area_struct *vma = vmf ? vmf->vma : NULL;
  	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 = filemap_get_entry(inode->i_mapping, vmf->pgoff);
+	if (!folio && vma && userfaultfd_missing(vma)) {
+		filemap_invalidate_unlock_shared(inode->i_mapping);
+		return handle_userfault(vmf, VM_UFFD_MISSING);
+	}
+
  	folio = kvm_gmem_get_folio(inode, vmf->pgoff);
  	if (IS_ERR(folio)) {
  		int err = PTR_ERR(folio);
@@ -438,10 +445,57 @@ static int kvm_gmem_uffd_get_folio(struct inode 
*inode, pgoff_t pgoff,
  	return 0;
  }

+static int kvm_gmem_mfill_atomic_pte(pmd_t *dst_pmd,
+			   struct vm_area_struct *dst_vma,
+			   unsigned long dst_addr,
+			   unsigned long src_addr,
+			   uffd_flags_t flags,
+			   struct folio **foliop)
+{
+	struct inode *inode = file_inode(dst_vma->vm_file);
+	pgoff_t pgoff = linear_page_index(dst_vma, dst_addr);
+	struct folio *folio;
+	int ret;
+
+	folio = kvm_gmem_get_folio(inode, pgoff);
+	if (IS_ERR(folio)) {
+		ret = PTR_ERR(folio);
+		goto out;
+	}
+
+	folio_unlock(folio);
+
+	if (uffd_flags_mode_is(flags, MFILL_ATOMIC_COPY)) {
+		void *vaddr = kmap_local_folio(folio, 0);
+		ret = copy_from_user(vaddr, (const void __user *)src_addr, PAGE_SIZE);
+		kunmap_local(vaddr);
+		if (unlikely(ret)) {
+			*foliop = folio;
+			ret = -ENOENT;
+			goto out;
+		}
+	} else {		/* ZEROPAGE */
+		clear_user_highpage(&folio->page, dst_addr);
+	}
+
+	kvm_gmem_mark_prepared(folio);
+
+	ret = mfill_atomic_install_pte(dst_pmd, dst_vma, dst_addr,
+				       &folio->page, true, flags);
+
+	if (ret)
+		folio_put(folio);
+out:
+	return ret;
+}
+
  static const vm_uffd_ops kvm_gmem_uffd_ops = {
-	.uffd_features	= 	VM_UFFD_MINOR,
-	.uffd_ioctls	= 	BIT(_UFFDIO_CONTINUE),
+	.uffd_features	= 	VM_UFFD_MISSING | VM_UFFD_MINOR,
+	.uffd_ioctls	= 	BIT(_UFFDIO_COPY) |
+				BIT(_UFFDIO_ZEROPAGE) |
+				BIT(_UFFDIO_CONTINUE),
  	.uffd_get_folio	=	kvm_gmem_uffd_get_folio,
+	.uffd_copy	=	kvm_gmem_mfill_atomic_pte,
  };
  #endif

> 
>>
>> diff --git a/virt/kvm/guest_memfd.c b/virt/kvm/guest_memfd.c
>> index 5abb6d52a375..6ddc73419724 100644
>> --- a/virt/kvm/guest_memfd.c
>> +++ b/virt/kvm/guest_memfd.c
>> @@ -5,6 +5,9 @@
>>   #include <linux/pagemap.h>
>>   #include <linux/anon_inodes.h>
>>   #include <linux/set_memory.h>
>> +#ifdef CONFIG_USERFAULTFD
> 
> This ifdef not needed, userfaultfd_k.h has taken care of all cases.

Good to know, thanks.

>> +#include <linux/userfaultfd_k.h>
>> +#endif
>>
>>   #include "kvm_mm.h"
>>
>> @@ -396,6 +399,14 @@ static vm_fault_t kvm_gmem_fault(struct vm_fault *vmf)
>>                kvm_gmem_mark_prepared(folio);
>>        }
>>
>> +#ifdef CONFIG_USERFAULTFD
> 
> Same here.  userfaultfd_minor() is always defined.

Thank you.

> I'll wait for a few more days for reviewers, and likely send v2 before next
> week.
> 
> Thanks,
> 
> --
> Peter Xu
>