[PATCH v2 12/15] mm: generalize handling of userfaults in __do_fault()

[Mike Rapoport <rppt@kernel.org>]

From: Peter Xu <peterx@redhat.com>

When a VMA is registered with userfaulfd, its ->fault()
method should check if a folio exists in the page cache and call
handle_userfault() with appropriate mode:

- VM_UFFD_MINOR if VMA is registered in minor mode and the folio exists
- VM_UFFD_MISSING if VMA is registered in missing mode and the folio
  does not exist

Instead of calling handle_userfault() directly from a specific ->fault()
handler, call __do_userfault() helper from the generic __do_fault().

For VMAs registered with userfaultfd the new __do_userfault() helper
will check if the folio is found in the page cache using
vm_uffd_ops->get_folio_noalloc() and call handle_userfault() with the
appropriate mode.

Make vm_uffd_ops->get_folio_noalloc() required method for non-anonymous
VMAs mapped at PTE level.

Signed-off-by: Peter Xu <peterx@redhat.com>
Co-developed-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
Signed-off-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
---
 mm/memory.c      | 43 +++++++++++++++++++++++++++++++++++++++++++
 mm/shmem.c       | 12 ------------
 mm/userfaultfd.c |  8 ++++++++
 3 files changed, 51 insertions(+), 12 deletions(-)

diff --git a/mm/memory.c b/mm/memory.c
index 07778814b4a8..e2183c44d70b 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -5328,6 +5328,41 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf)
 	return VM_FAULT_OOM;
 }
 
+#ifdef CONFIG_USERFAULTFD
+static vm_fault_t __do_userfault(struct vm_fault *vmf)
+{
+	struct vm_area_struct *vma = vmf->vma;
+	struct inode *inode;
+	struct folio *folio;
+
+	if (!(userfaultfd_missing(vma) || userfaultfd_minor(vma)))
+		return 0;
+
+	inode = file_inode(vma->vm_file);
+	folio = vma->vm_ops->uffd_ops->get_folio_noalloc(inode, vmf->pgoff);
+	if (!IS_ERR_OR_NULL(folio)) {
+		/*
+		 * TODO: provide a flag for get_folio_noalloc() to avoid
+		 * locking (or even the extra reference?)
+		 */
+		folio_unlock(folio);
+		folio_put(folio);
+		if (userfaultfd_minor(vma))
+			return handle_userfault(vmf, VM_UFFD_MINOR);
+	} else {
+		if (userfaultfd_missing(vma))
+			return handle_userfault(vmf, VM_UFFD_MISSING);
+	}
+
+	return 0;
+}
+#else
+static inline vm_fault_t __do_userfault(struct vm_fault *vmf)
+{
+	return 0;
+}
+#endif
+
 /*
  * The mmap_lock must have been held on entry, and may have been
  * released depending on flags and vma->vm_ops->fault() return value.
@@ -5360,6 +5395,14 @@ static vm_fault_t __do_fault(struct vm_fault *vmf)
 			return VM_FAULT_OOM;
 	}
 
+	/*
+	 * If this is an userfaultfd trap, process it in advance before
+	 * triggering the genuine fault handler.
+	 */
+	ret = __do_userfault(vmf);
+	if (ret)
+		return ret;
+
 	ret = vma->vm_ops->fault(vmf);
 	if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY |
 			    VM_FAULT_DONE_COW)))
diff --git a/mm/shmem.c b/mm/shmem.c
index 68620caaf75f..239545352cd2 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -2489,13 +2489,6 @@ static int shmem_get_folio_gfp(struct inode *inode, pgoff_t index,
 	fault_mm = vma ? vma->vm_mm : NULL;
 
 	folio = filemap_get_entry(inode->i_mapping, index);
-	if (folio && vma && userfaultfd_minor(vma)) {
-		if (!xa_is_value(folio))
-			folio_put(folio);
-		*fault_type = handle_userfault(vmf, VM_UFFD_MINOR);
-		return 0;
-	}
-
 	if (xa_is_value(folio)) {
 		error = shmem_swapin_folio(inode, index, &folio,
 					   sgp, gfp, vma, fault_type);
@@ -2540,11 +2533,6 @@ static int shmem_get_folio_gfp(struct inode *inode, pgoff_t index,
 	 * Fast cache lookup and swap lookup did not find it: allocate.
 	 */
 
-	if (vma && userfaultfd_missing(vma)) {
-		*fault_type = handle_userfault(vmf, VM_UFFD_MISSING);
-		return 0;
-	}
-
 	/* Find hugepage orders that are allowed for anonymous shmem and tmpfs. */
 	orders = shmem_allowable_huge_orders(inode, vma, index, write_end, false);
 	if (orders > 0) {
diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
index 7cd7c5d1ce84..2ac5fad0ed6c 100644
--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -2045,6 +2045,14 @@ bool vma_can_userfault(struct vm_area_struct *vma, vm_flags_t vm_flags,
 	    !vma_is_anonymous(vma))
 		return false;
 
+	/*
+	 * File backed memory with PTE level mappigns must implement
+	 * ops->get_folio_noalloc()
+	 */
+	if (!vma_is_anonymous(vma) && !is_vm_hugetlb_page(vma) &&
+	    !ops->get_folio_noalloc)
+		return false;
+
 	return ops->can_userfault(vma, vm_flags);
 }
 
-- 
2.51.0