1 files changed, 169 insertions, 1 deletions

diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
index acc56c75ba99..ce13c4062647 100644
--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -391,7 +391,7 @@ static int mfill_atomic_pte_continue(pmd_t *dst_pmd,
 	struct page *page;
 	int ret;
 
-	ret = shmem_get_folio(inode, pgoff, &folio, SGP_NOALLOC);
+	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;
@@ -1763,3 +1763,171 @@ out:
 	VM_WARN_ON(!moved && !err);
 	return moved ? moved : err;
 }
+
+static void userfaultfd_set_vm_flags(struct vm_area_struct *vma,
+				     vm_flags_t flags)
+{
+	const bool uffd_wp_changed = (vma->vm_flags ^ flags) & VM_UFFD_WP;
+
+	vm_flags_reset(vma, flags);
+	/*
+	 * For shared mappings, we want to enable writenotify while
+	 * userfaultfd-wp is enabled (see vma_wants_writenotify()). We'll simply
+	 * recalculate vma->vm_page_prot whenever userfaultfd-wp changes.
+	 */
+	if ((vma->vm_flags & VM_SHARED) && uffd_wp_changed)
+		vma_set_page_prot(vma);
+}
+
+static void userfaultfd_set_ctx(struct vm_area_struct *vma,
+				struct userfaultfd_ctx *ctx,
+				unsigned long flags)
+{
+	vma_start_write(vma);
+	vma->vm_userfaultfd_ctx = (struct vm_userfaultfd_ctx){ctx};
+	userfaultfd_set_vm_flags(vma,
+				 (vma->vm_flags & ~__VM_UFFD_FLAGS) | flags);
+}
+
+void userfaultfd_reset_ctx(struct vm_area_struct *vma)
+{
+	userfaultfd_set_ctx(vma, NULL, 0);
+}
+
+struct vm_area_struct *userfaultfd_clear_vma(struct vma_iterator *vmi,
+					     struct vm_area_struct *prev,
+					     struct vm_area_struct *vma,
+					     unsigned long start,
+					     unsigned long end)
+{
+	struct vm_area_struct *ret;
+
+	/* Reset ptes for the whole vma range if wr-protected */
+	if (userfaultfd_wp(vma))
+		uffd_wp_range(vma, start, end - start, false);
+
+	ret = vma_modify_flags_uffd(vmi, prev, vma, start, end,
+				    vma->vm_flags & ~__VM_UFFD_FLAGS,
+				    NULL_VM_UFFD_CTX);
+
+	/*
+	 * In the vma_merge() successful mprotect-like case 8:
+	 * the next vma was merged into the current one and
+	 * the current one has not been updated yet.
+	 */
+	if (!IS_ERR(ret))
+		userfaultfd_reset_ctx(ret);
+
+	return ret;
+}
+
+/* Assumes mmap write lock taken, and mm_struct pinned. */
+int userfaultfd_register_range(struct userfaultfd_ctx *ctx,
+			       struct vm_area_struct *vma,
+			       unsigned long vm_flags,
+			       unsigned long start, unsigned long end,
+			       bool wp_async)
+{
+	VMA_ITERATOR(vmi, ctx->mm, start);
+	struct vm_area_struct *prev = vma_prev(&vmi);
+	unsigned long vma_end;
+	unsigned long new_flags;
+
+	if (vma->vm_start < start)
+		prev = vma;
+
+	for_each_vma_range(vmi, vma, end) {
+		cond_resched();
+
+		BUG_ON(!vma_can_userfault(vma, vm_flags, wp_async));
+		BUG_ON(vma->vm_userfaultfd_ctx.ctx &&
+		       vma->vm_userfaultfd_ctx.ctx != ctx);
+		WARN_ON(!(vma->vm_flags & VM_MAYWRITE));
+
+		/*
+		 * Nothing to do: this vma is already registered into this
+		 * userfaultfd and with the right tracking mode too.
+		 */
+		if (vma->vm_userfaultfd_ctx.ctx == ctx &&
+		    (vma->vm_flags & vm_flags) == vm_flags)
+			goto skip;
+
+		if (vma->vm_start > start)
+			start = vma->vm_start;
+		vma_end = min(end, vma->vm_end);
+
+		new_flags = (vma->vm_flags & ~__VM_UFFD_FLAGS) | vm_flags;
+		vma = vma_modify_flags_uffd(&vmi, prev, vma, start, vma_end,
+					    new_flags,
+					    (struct vm_userfaultfd_ctx){ctx});
+		if (IS_ERR(vma))
+			return PTR_ERR(vma);
+
+		/*
+		 * In the vma_merge() successful mprotect-like case 8:
+		 * the next vma was merged into the current one and
+		 * the current one has not been updated yet.
+		 */
+		userfaultfd_set_ctx(vma, ctx, vm_flags);
+
+		if (is_vm_hugetlb_page(vma) && uffd_disable_huge_pmd_share(vma))
+			hugetlb_unshare_all_pmds(vma);
+
+skip:
+		prev = vma;
+		start = vma->vm_end;
+	}
+
+	return 0;
+}
+
+void userfaultfd_release_new(struct userfaultfd_ctx *ctx)
+{
+	struct mm_struct *mm = ctx->mm;
+	struct vm_area_struct *vma;
+	VMA_ITERATOR(vmi, mm, 0);
+
+	/* the various vma->vm_userfaultfd_ctx still points to it */
+	mmap_write_lock(mm);
+	for_each_vma(vmi, vma) {
+		if (vma->vm_userfaultfd_ctx.ctx == ctx)
+			userfaultfd_reset_ctx(vma);
+	}
+	mmap_write_unlock(mm);
+}
+
+void userfaultfd_release_all(struct mm_struct *mm,
+			     struct userfaultfd_ctx *ctx)
+{
+	struct vm_area_struct *vma, *prev;
+	VMA_ITERATOR(vmi, mm, 0);
+
+	if (!mmget_not_zero(mm))
+		return;
+
+	/*
+	 * Flush page faults out of all CPUs. NOTE: all page faults
+	 * must be retried without returning VM_FAULT_SIGBUS if
+	 * userfaultfd_ctx_get() succeeds but vma->vma_userfault_ctx
+	 * changes while handle_userfault released the mmap_lock. So
+	 * it's critical that released is set to true (above), before
+	 * taking the mmap_lock for writing.
+	 */
+	mmap_write_lock(mm);
+	prev = NULL;
+	for_each_vma(vmi, vma) {
+		cond_resched();
+		BUG_ON(!!vma->vm_userfaultfd_ctx.ctx ^
+		       !!(vma->vm_flags & __VM_UFFD_FLAGS));
+		if (vma->vm_userfaultfd_ctx.ctx != ctx) {
+			prev = vma;
+			continue;
+		}
+
+		vma = userfaultfd_clear_vma(&vmi, prev, vma,
+					    vma->vm_start, vma->vm_end);
+		prev = vma;
+	}
+	mmap_write_unlock(mm);
+	mmput(mm);
+}