[PATCH v4 07/15] userfaultfd: introduce vm_uffd_ops

Mike Rapoport posted 15 patches 1 day, 21 hours ago
[PATCH v4 07/15] userfaultfd: introduce vm_uffd_ops
Posted by Mike Rapoport 1 day, 21 hours ago
From: "Mike Rapoport (Microsoft)" <rppt@kernel.org>

Current userfaultfd implementation works only with memory managed by core
MM: anonymous, shmem and hugetlb.

First, there is no fundamental reason to limit userfaultfd support only to
the core memory types and userfaults can be handled similarly to regular
page faults provided a VMA owner implements appropriate callbacks.

Second, historically various code paths were conditioned on
vma_is_anonymous(), vma_is_shmem() and is_vm_hugetlb_page() and some of
these conditions can be expressed as operations implemented by a
particular memory type.

Introduce vm_uffd_ops extension to vm_operations_struct that will delegate
memory type specific operations to a VMA owner.

Operations for anonymous memory are handled internally in userfaultfd
using anon_uffd_ops that implicitly assigned to anonymous VMAs.

Start with a single operation, ->can_userfault() that will verify that a
VMA meets requirements for userfaultfd support at registration time.

Implement that method for anonymous, shmem and hugetlb and move relevant
parts of vma_can_userfault() into the new callbacks.

Signed-off-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
---
 include/linux/mm.h            |  5 ++++
 include/linux/userfaultfd_k.h |  6 +++++
 mm/hugetlb.c                  | 15 ++++++++++++
 mm/shmem.c                    | 15 ++++++++++++
 mm/userfaultfd.c              | 44 ++++++++++++++++++++++++-----------
 5 files changed, 72 insertions(+), 13 deletions(-)

diff --git a/include/linux/mm.h b/include/linux/mm.h
index abb4963c1f06..0fbeb8012983 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -741,6 +741,8 @@ struct vm_fault {
 					 */
 };
 
+struct vm_uffd_ops;
+
 /*
  * These are the virtual MM functions - opening of an area, closing and
  * unmapping it (needed to keep files on disk up-to-date etc), pointer
@@ -826,6 +828,9 @@ struct vm_operations_struct {
 	struct page *(*find_normal_page)(struct vm_area_struct *vma,
 					 unsigned long addr);
 #endif /* CONFIG_FIND_NORMAL_PAGE */
+#ifdef CONFIG_USERFAULTFD
+	const struct vm_uffd_ops *uffd_ops;
+#endif
 };
 
 #ifdef CONFIG_NUMA_BALANCING
diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h
index a49cf750e803..56e85ab166c7 100644
--- a/include/linux/userfaultfd_k.h
+++ b/include/linux/userfaultfd_k.h
@@ -80,6 +80,12 @@ struct userfaultfd_ctx {
 
 extern vm_fault_t handle_userfault(struct vm_fault *vmf, unsigned long reason);
 
+/* VMA userfaultfd operations */
+struct vm_uffd_ops {
+	/* Checks if a VMA can support userfaultfd */
+	bool (*can_userfault)(struct vm_area_struct *vma, vm_flags_t vm_flags);
+};
+
 /* A combined operation mode + behavior flags. */
 typedef unsigned int __bitwise uffd_flags_t;
 
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 327eaa4074d3..530bc4337be6 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -4818,6 +4818,18 @@ static vm_fault_t hugetlb_vm_op_fault(struct vm_fault *vmf)
 	return 0;
 }
 
+#ifdef CONFIG_USERFAULTFD
+static bool hugetlb_can_userfault(struct vm_area_struct *vma,
+				  vm_flags_t vm_flags)
+{
+	return true;
+}
+
+static const struct vm_uffd_ops hugetlb_uffd_ops = {
+	.can_userfault = hugetlb_can_userfault,
+};
+#endif
+
 /*
  * When a new function is introduced to vm_operations_struct and added
  * to hugetlb_vm_ops, please consider adding the function to shm_vm_ops.
@@ -4831,6 +4843,9 @@ const struct vm_operations_struct hugetlb_vm_ops = {
 	.close = hugetlb_vm_op_close,
 	.may_split = hugetlb_vm_op_split,
 	.pagesize = hugetlb_vm_op_pagesize,
+#ifdef CONFIG_USERFAULTFD
+	.uffd_ops = &hugetlb_uffd_ops,
+#endif
 };
 
 static pte_t make_huge_pte(struct vm_area_struct *vma, struct folio *folio,
diff --git a/mm/shmem.c b/mm/shmem.c
index b40f3cd48961..f2a25805b9bf 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -3294,6 +3294,15 @@ int shmem_mfill_atomic_pte(pmd_t *dst_pmd,
 	shmem_inode_unacct_blocks(inode, 1);
 	return ret;
 }
+
+static bool shmem_can_userfault(struct vm_area_struct *vma, vm_flags_t vm_flags)
+{
+	return true;
+}
+
+static const struct vm_uffd_ops shmem_uffd_ops = {
+	.can_userfault	= shmem_can_userfault,
+};
 #endif /* CONFIG_USERFAULTFD */
 
 #ifdef CONFIG_TMPFS
@@ -5313,6 +5322,9 @@ static const struct vm_operations_struct shmem_vm_ops = {
 	.set_policy     = shmem_set_policy,
 	.get_policy     = shmem_get_policy,
 #endif
+#ifdef CONFIG_USERFAULTFD
+	.uffd_ops	= &shmem_uffd_ops,
+#endif
 };
 
 static const struct vm_operations_struct shmem_anon_vm_ops = {
@@ -5322,6 +5334,9 @@ static const struct vm_operations_struct shmem_anon_vm_ops = {
 	.set_policy     = shmem_set_policy,
 	.get_policy     = shmem_get_policy,
 #endif
+#ifdef CONFIG_USERFAULTFD
+	.uffd_ops	= &shmem_uffd_ops,
+#endif
 };
 
 int shmem_init_fs_context(struct fs_context *fc)
diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
index d51e080e9216..e3024a39c19d 100644
--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -34,6 +34,25 @@ struct mfill_state {
 	pmd_t *pmd;
 };
 
+static bool anon_can_userfault(struct vm_area_struct *vma, vm_flags_t vm_flags)
+{
+	/* anonymous memory does not support MINOR mode */
+	if (vm_flags & VM_UFFD_MINOR)
+		return false;
+	return true;
+}
+
+static const struct vm_uffd_ops anon_uffd_ops = {
+	.can_userfault	= anon_can_userfault,
+};
+
+static const struct vm_uffd_ops *vma_uffd_ops(struct vm_area_struct *vma)
+{
+	if (vma_is_anonymous(vma))
+		return &anon_uffd_ops;
+	return vma->vm_ops ? vma->vm_ops->uffd_ops : NULL;
+}
+
 static __always_inline
 bool validate_dst_vma(struct vm_area_struct *dst_vma, unsigned long dst_end)
 {
@@ -2021,34 +2040,33 @@ ssize_t move_pages(struct userfaultfd_ctx *ctx, unsigned long dst_start,
 bool vma_can_userfault(struct vm_area_struct *vma, vm_flags_t vm_flags,
 		       bool wp_async)
 {
-	vm_flags &= __VM_UFFD_FLAGS;
+	const struct vm_uffd_ops *ops = vma_uffd_ops(vma);
 
-	if (vma->vm_flags & VM_DROPPABLE)
-		return false;
-
-	if ((vm_flags & VM_UFFD_MINOR) &&
-	    (!is_vm_hugetlb_page(vma) && !vma_is_shmem(vma)))
-		return false;
+	vm_flags &= __VM_UFFD_FLAGS;
 
 	/*
-	 * If wp async enabled, and WP is the only mode enabled, allow any
+	 * If WP is the only mode enabled and context is wp async, allow any
 	 * memory type.
 	 */
 	if (wp_async && (vm_flags == VM_UFFD_WP))
 		return true;
 
+	/* For any other mode reject VMAs that don't implement vm_uffd_ops */
+	if (!ops)
+		return false;
+
+	if (vma->vm_flags & VM_DROPPABLE)
+		return false;
+
 	/*
 	 * If user requested uffd-wp but not enabled pte markers for
-	 * uffd-wp, then shmem & hugetlbfs are not supported but only
-	 * anonymous.
+	 * uffd-wp, then only anonymous memory is supported
 	 */
 	if (!uffd_supports_wp_marker() && (vm_flags & VM_UFFD_WP) &&
 	    !vma_is_anonymous(vma))
 		return false;
 
-	/* By default, allow any of anon|shmem|hugetlb */
-	return vma_is_anonymous(vma) || is_vm_hugetlb_page(vma) ||
-	    vma_is_shmem(vma);
+	return ops->can_userfault(vma, vm_flags);
 }
 
 static void userfaultfd_set_vm_flags(struct vm_area_struct *vma,
-- 
2.53.0
Re: [PATCH v4 07/15] userfaultfd: introduce vm_uffd_ops
Posted by Tal Zussman 1 day, 6 hours ago
Hi Mike,

On 4/2/26 12:11 AM, Mike Rapoport wrote:
> @@ -2021,34 +2040,33 @@ ssize_t move_pages(struct userfaultfd_ctx *ctx, unsigned long dst_start,
>  bool vma_can_userfault(struct vm_area_struct *vma, vm_flags_t vm_flags,
>  		       bool wp_async)
>  {
> -	vm_flags &= __VM_UFFD_FLAGS;
> +	const struct vm_uffd_ops *ops = vma_uffd_ops(vma);
>  
> -	if (vma->vm_flags & VM_DROPPABLE)
> -		return false;
> -
> -	if ((vm_flags & VM_UFFD_MINOR) &&
> -	    (!is_vm_hugetlb_page(vma) && !vma_is_shmem(vma)))
> -		return false;
> +	vm_flags &= __VM_UFFD_FLAGS;
>  
>  	/*
> -	 * If wp async enabled, and WP is the only mode enabled, allow any
> +	 * If WP is the only mode enabled and context is wp async, allow any
>  	 * memory type.
>  	 */
>  	if (wp_async && (vm_flags == VM_UFFD_WP))
>  		return true;
>  
> +	/* For any other mode reject VMAs that don't implement vm_uffd_ops */
> +	if (!ops)
> +		return false;
> +
> +	if (vma->vm_flags & VM_DROPPABLE)
> +		return false;
> +

Doesn't moving the VM_DROPPABLE check after the wp_async early return make
the issue David raised in [1] possible again (i.e. moving swapbacked pages
into a droppable region using UFFDIO_MOVE)? With this change, VM_DROPPABLE
pages can now be registered with uffd under wp_async, which allows
UFFDIO_MOVE.

I think the VM_DROPPABLE check should go right before the wp_async check.
And it would probably benefit from a comment...

[1] https://lore.kernel.org/linux-mm/5a875a3a-2243-4eab-856f-bc53ccfec3ea@redhat.com/

Thanks,
Tal