[PATCH v4 08/15] shmem, userfaultfd: use a VMA callback to handle UFFDIO_CONTINUE

Mike Rapoport posted 15 patches 1 day, 21 hours ago
[PATCH v4 08/15] shmem, userfaultfd: use a VMA callback to handle UFFDIO_CONTINUE
Posted by Mike Rapoport 1 day, 21 hours ago
From: "Mike Rapoport (Microsoft)" <rppt@kernel.org>

When userspace resolves a page fault in a shmem VMA with UFFDIO_CONTINUE
it needs to get a folio that already exists in the pagecache backing that
VMA.

Instead of using shmem_get_folio() for that, add a get_folio_noalloc()
method to 'struct vm_uffd_ops' that will return a folio if it exists in
the VMA's pagecache at given pgoff.

Implement get_folio_noalloc() method for shmem and slightly refactor
userfaultfd's mfill_get_vma() and mfill_atomic_pte_continue() to support
this new API.

Signed-off-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
Reviewed-by: James Houghton <jthoughton@google.com>
---
 include/linux/userfaultfd_k.h |  7 +++++++
 mm/shmem.c                    | 15 ++++++++++++++-
 mm/userfaultfd.c              | 34 ++++++++++++++++++----------------
 3 files changed, 39 insertions(+), 17 deletions(-)

diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h
index 56e85ab166c7..66dfc3c164e6 100644
--- a/include/linux/userfaultfd_k.h
+++ b/include/linux/userfaultfd_k.h
@@ -84,6 +84,13 @@ extern vm_fault_t handle_userfault(struct vm_fault *vmf, unsigned long reason);
 struct vm_uffd_ops {
 	/* Checks if a VMA can support userfaultfd */
 	bool (*can_userfault)(struct vm_area_struct *vma, vm_flags_t vm_flags);
+	/*
+	 * Called to resolve UFFDIO_CONTINUE request.
+	 * Should return the folio found at pgoff in the VMA's pagecache if it
+	 * exists or ERR_PTR otherwise.
+	 * The returned folio is locked and with reference held.
+	 */
+	struct folio *(*get_folio_noalloc)(struct inode *inode, pgoff_t pgoff);
 };
 
 /* A combined operation mode + behavior flags. */
diff --git a/mm/shmem.c b/mm/shmem.c
index f2a25805b9bf..7bd887b64f62 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -3295,13 +3295,26 @@ int shmem_mfill_atomic_pte(pmd_t *dst_pmd,
 	return ret;
 }
 
+static struct folio *shmem_get_folio_noalloc(struct inode *inode, pgoff_t pgoff)
+{
+	struct folio *folio;
+	int err;
+
+	err = shmem_get_folio(inode, pgoff, 0, &folio, SGP_NOALLOC);
+	if (err)
+		return ERR_PTR(err);
+
+	return folio;
+}
+
 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,
+	.can_userfault		= shmem_can_userfault,
+	.get_folio_noalloc	= shmem_get_folio_noalloc,
 };
 #endif /* CONFIG_USERFAULTFD */
 
diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
index e3024a39c19d..832dbdde5868 100644
--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -191,6 +191,7 @@ static int mfill_get_vma(struct mfill_state *state)
 	struct userfaultfd_ctx *ctx = state->ctx;
 	uffd_flags_t flags = state->flags;
 	struct vm_area_struct *dst_vma;
+	const struct vm_uffd_ops *ops;
 	int err;
 
 	/*
@@ -232,10 +233,12 @@ static int mfill_get_vma(struct mfill_state *state)
 	if (is_vm_hugetlb_page(dst_vma))
 		return 0;
 
-	if (!vma_is_anonymous(dst_vma) && !vma_is_shmem(dst_vma))
+	ops = vma_uffd_ops(dst_vma);
+	if (!ops)
 		goto out_unlock;
-	if (!vma_is_shmem(dst_vma) &&
-	    uffd_flags_mode_is(flags, MFILL_ATOMIC_CONTINUE))
+
+	if (uffd_flags_mode_is(flags, MFILL_ATOMIC_CONTINUE) &&
+	    !ops->get_folio_noalloc)
 		goto out_unlock;
 
 	return 0;
@@ -575,6 +578,7 @@ static int mfill_atomic_pte_zeropage(struct mfill_state *state)
 static int mfill_atomic_pte_continue(struct mfill_state *state)
 {
 	struct vm_area_struct *dst_vma = state->vma;
+	const struct vm_uffd_ops *ops = vma_uffd_ops(dst_vma);
 	unsigned long dst_addr = state->dst_addr;
 	pgoff_t pgoff = linear_page_index(dst_vma, dst_addr);
 	struct inode *inode = file_inode(dst_vma->vm_file);
@@ -584,17 +588,16 @@ static int mfill_atomic_pte_continue(struct mfill_state *state)
 	struct page *page;
 	int ret;
 
-	ret = shmem_get_folio(inode, pgoff, 0, &folio, SGP_NOALLOC);
-	/* Our caller expects us to return -EFAULT if we failed to find folio */
-	if (ret == -ENOENT)
-		ret = -EFAULT;
-	if (ret)
-		goto out;
-	if (!folio) {
-		ret = -EFAULT;
-		goto out;
+	if (!ops) {
+		VM_WARN_ONCE(1, "UFFDIO_CONTINUE for unsupported VMA");
+		return -EOPNOTSUPP;
 	}
 
+	folio = ops->get_folio_noalloc(inode, pgoff);
+	/* Our caller expects us to return -EFAULT if we failed to find folio */
+	if (IS_ERR_OR_NULL(folio))
+		return -EFAULT;
+
 	page = folio_file_page(folio, pgoff);
 	if (PageHWPoison(page)) {
 		ret = -EIO;
@@ -607,13 +610,12 @@ static int mfill_atomic_pte_continue(struct mfill_state *state)
 		goto out_release;
 
 	folio_unlock(folio);
-	ret = 0;
-out:
-	return ret;
+	return 0;
+
 out_release:
 	folio_unlock(folio);
 	folio_put(folio);
-	goto out;
+	return ret;
 }
 
 /* Handles UFFDIO_POISON for all non-hugetlb VMAs. */
-- 
2.53.0