[PATCH RFC 09/17] userfaultfd: introduce vm_uffd_ops->alloc_folio()

[Mike Rapoport <rppt@kernel.org>]

From: "Mike Rapoport (Microsoft)" <rppt@kernel.org>

and use it to refactor mfill_atomic_pte_zeroed_folio() and
mfill_atomic_pte_copy().

mfill_atomic_pte_zeroed_folio() and mfill_atomic_pte_copy() perform
almost identical actions:
* allocate a folio
* update folio contents (either copy from userspace of fill with zeros)
* update page tables with the new folio

Split a __mfill_atomic_pte() helper that handles both cases and uses
newly introduced vm_uffd_ops->alloc_folio() to allocate the folio.

Pass the ops structure from the callers to __mfill_atomic_pte() to later
allow using anon_uffd_ops for MAP_PRIVATE mappings of file-backed VMAs.

Note, that the new ops method is called alloc_folio() rather than
folio_alloc() to avoid clash with alloc_tag macro folio_alloc().

Signed-off-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
---
 include/linux/userfaultfd_k.h |  6 +++
 mm/userfaultfd.c              | 92 ++++++++++++++++++-----------------
 2 files changed, 54 insertions(+), 44 deletions(-)

diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h
index 66dfc3c164e6..4d8b879eed91 100644
--- a/include/linux/userfaultfd_k.h
+++ b/include/linux/userfaultfd_k.h
@@ -91,6 +91,12 @@ struct vm_uffd_ops {
 	 * The returned folio is locked and with reference held.
 	 */
 	struct folio *(*get_folio_noalloc)(struct inode *inode, pgoff_t pgoff);
+	/*
+	 * Called during resolution of UFFDIO_COPY request.
+	 * Should return allocate a and return folio or NULL if allocation fails.
+	 */
+	struct folio *(*alloc_folio)(struct vm_area_struct *vma,
+				     unsigned long addr);
 };
 
 /* A combined operation mode + behavior flags. */
diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
index f0e6336015f1..b3c12630769c 100644
--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -42,8 +42,26 @@ static bool anon_can_userfault(struct vm_area_struct *vma, vm_flags_t vm_flags)
 	return true;
 }
 
+static struct folio *anon_alloc_folio(struct vm_area_struct *vma,
+				      unsigned long addr)
+{
+	struct folio *folio = vma_alloc_folio(GFP_HIGHUSER_MOVABLE, 0, vma,
+					      addr);
+
+	if (!folio)
+		return NULL;
+
+	if (mem_cgroup_charge(folio, vma->vm_mm, GFP_KERNEL)) {
+		folio_put(folio);
+		return NULL;
+	}
+
+	return folio;
+}
+
 static const struct vm_uffd_ops anon_uffd_ops = {
 	.can_userfault	= anon_can_userfault,
+	.alloc_folio	= anon_alloc_folio,
 };
 
 static const struct vm_uffd_ops *vma_uffd_ops(struct vm_area_struct *vma)
@@ -455,7 +473,8 @@ static int mfill_copy_folio_retry(struct mfill_state *state, struct folio *folio
 	return 0;
 }
 
-static int mfill_atomic_pte_copy(struct mfill_state *state)
+static int __mfill_atomic_pte(struct mfill_state *state,
+			      const struct vm_uffd_ops *ops)
 {
 	unsigned long dst_addr = state->dst_addr;
 	unsigned long src_addr = state->src_addr;
@@ -463,20 +482,22 @@ static int mfill_atomic_pte_copy(struct mfill_state *state)
 	struct folio *folio;
 	int ret;
 
-	folio = vma_alloc_folio(GFP_HIGHUSER_MOVABLE, 0, state->vma, dst_addr);
+	folio = ops->alloc_folio(state->vma, state->dst_addr);
 	if (!folio)
 		return -ENOMEM;
 
-	ret = -ENOMEM;
-	if (mem_cgroup_charge(folio, state->vma->vm_mm, GFP_KERNEL))
-		goto out_release;
-
-	ret = mfill_copy_folio_locked(folio, src_addr);
-	if (unlikely(ret)) {
+	if (uffd_flags_mode_is(flags, MFILL_ATOMIC_COPY)) {
+		ret = mfill_copy_folio_locked(folio, src_addr);
 		/* fallback to copy_from_user outside mmap_lock */
-		ret = mfill_copy_folio_retry(state, folio);
-		if (ret)
-			goto out_release;
+		if (unlikely(ret)) {
+			ret = mfill_copy_folio_retry(state, folio);
+			if (ret)
+				goto err_folio_put;
+		}
+	} else if (uffd_flags_mode_is(flags, MFILL_ATOMIC_ZEROPAGE)) {
+		clear_user_highpage(&folio->page, state->dst_addr);
+	} else {
+		VM_WARN_ONCE(1, "unknown UFFDIO operation");
 	}
 
 	/*
@@ -489,47 +510,30 @@ static int mfill_atomic_pte_copy(struct mfill_state *state)
 	ret = mfill_atomic_install_pte(state->pmd, state->vma, dst_addr,
 				       &folio->page, true, flags);
 	if (ret)
-		goto out_release;
-out:
-	return ret;
-out_release:
+		goto err_folio_put;
+
+	return 0;
+
+err_folio_put:
+	folio_put(folio);
 	/* Don't return -ENOENT so that our caller won't retry */
 	if (ret == -ENOENT)
 		ret = -EFAULT;
-	folio_put(folio);
-	goto out;
+	return ret;
 }
 
-static int mfill_atomic_pte_zeroed_folio(pmd_t *dst_pmd,
-					 struct vm_area_struct *dst_vma,
-					 unsigned long dst_addr)
+static int mfill_atomic_pte_copy(struct mfill_state *state)
 {
-	struct folio *folio;
-	int ret = -ENOMEM;
-
-	folio = vma_alloc_zeroed_movable_folio(dst_vma, dst_addr);
-	if (!folio)
-		return ret;
-
-	if (mem_cgroup_charge(folio, dst_vma->vm_mm, GFP_KERNEL))
-		goto out_put;
+	const struct vm_uffd_ops *ops = vma_uffd_ops(state->vma);
 
-	/*
-	 * The memory barrier inside __folio_mark_uptodate makes sure that
-	 * zeroing out the folio become visible before mapping the page
-	 * using set_pte_at(). See do_anonymous_page().
-	 */
-	__folio_mark_uptodate(folio);
+	return __mfill_atomic_pte(state, ops);
+}
 
-	ret = mfill_atomic_install_pte(dst_pmd, dst_vma, dst_addr,
-				       &folio->page, true, 0);
-	if (ret)
-		goto out_put;
+static int mfill_atomic_pte_zeroed_folio(struct mfill_state *state)
+{
+	const struct vm_uffd_ops *ops = vma_uffd_ops(state->vma);
 
-	return 0;
-out_put:
-	folio_put(folio);
-	return ret;
+	return __mfill_atomic_pte(state, ops);
 }
 
 static int mfill_atomic_pte_zeropage(struct mfill_state *state)
@@ -542,7 +546,7 @@ static int mfill_atomic_pte_zeropage(struct mfill_state *state)
 	int ret;
 
 	if (mm_forbids_zeropage(dst_vma->vm_mm))
-		return mfill_atomic_pte_zeroed_folio(dst_pmd, dst_vma, dst_addr);
+		return mfill_atomic_pte_zeroed_folio(state);
 
 	_dst_pte = pte_mkspecial(pfn_pte(my_zero_pfn(dst_addr),
 					 dst_vma->vm_page_prot));
-- 
2.51.0