1 files changed, 13 insertions, 158 deletions

diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index 27a3e9285fbf..68cdd89c97a3 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -104,21 +104,6 @@ bool userfaultfd_wp_unpopulated(struct vm_area_struct *vma)
 	return ctx->features & UFFD_FEATURE_WP_UNPOPULATED;
 }
 
-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 int userfaultfd_wake_function(wait_queue_entry_t *wq, unsigned mode,
 				     int wake_flags, void *key)
 {
@@ -386,15 +371,8 @@ vm_fault_t handle_userfault(struct vm_fault *vmf, unsigned long reason)
 	unsigned int blocking_state;
 
 	/*
-	 * We don't do userfault handling for the final child pid update.
-	 *
-	 * We also don't do userfault handling during
-	 * coredumping. hugetlbfs has the special
-	 * hugetlb_follow_page_mask() to skip missing pages in the
-	 * FOLL_DUMP case, anon memory also checks for FOLL_DUMP with
-	 * the no_page_table() helper in follow_page_mask(), but the
-	 * shmem_vm_ops->fault method is invoked even during
-	 * coredumping and it ends up here.
+	 * We don't do userfault handling for the final child pid update
+	 * and when coredumping (faults triggered by get_dump_page()).
 	 */
 	if (current->flags & (PF_EXITING|PF_DUMPCORE))
 		goto out;
@@ -615,22 +593,7 @@ static void userfaultfd_event_wait_completion(struct userfaultfd_ctx *ctx,
 	spin_unlock_irq(&ctx->event_wqh.lock);
 
 	if (release_new_ctx) {
-		struct vm_area_struct *vma;
-		struct mm_struct *mm = release_new_ctx->mm;
-		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 == release_new_ctx) {
-				vma_start_write(vma);
-				vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
-				userfaultfd_set_vm_flags(vma,
-							 vma->vm_flags & ~__VM_UFFD_FLAGS);
-			}
-		}
-		mmap_write_unlock(mm);
-
+		userfaultfd_release_new(release_new_ctx);
 		userfaultfd_ctx_put(release_new_ctx);
 	}
 
@@ -662,9 +625,7 @@ int dup_userfaultfd(struct vm_area_struct *vma, struct list_head *fcs)
 		return 0;
 
 	if (!(octx->features & UFFD_FEATURE_EVENT_FORK)) {
-		vma_start_write(vma);
-		vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
-		userfaultfd_set_vm_flags(vma, vma->vm_flags & ~__VM_UFFD_FLAGS);
+		userfaultfd_reset_ctx(vma);
 		return 0;
 	}
 
@@ -749,9 +710,7 @@ void mremap_userfaultfd_prep(struct vm_area_struct *vma,
 		up_write(&ctx->map_changing_lock);
 	} else {
 		/* Drop uffd context if remap feature not enabled */
-		vma_start_write(vma);
-		vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
-		userfaultfd_set_vm_flags(vma, vma->vm_flags & ~__VM_UFFD_FLAGS);
+		userfaultfd_reset_ctx(vma);
 	}
 }
 
@@ -870,54 +829,14 @@ static int userfaultfd_release(struct inode *inode, struct file *file)
 {
 	struct userfaultfd_ctx *ctx = file->private_data;
 	struct mm_struct *mm = ctx->mm;
-	struct vm_area_struct *vma, *prev;
 	/* len == 0 means wake all */
 	struct userfaultfd_wake_range range = { .len = 0, };
-	unsigned long new_flags;
-	VMA_ITERATOR(vmi, mm, 0);
 
 	WRITE_ONCE(ctx->released, true);
 
-	if (!mmget_not_zero(mm))
-		goto wakeup;
+	userfaultfd_release_all(mm, ctx);
 
 	/*
-	 * 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;
-		}
-		/* Reset ptes for the whole vma range if wr-protected */
-		if (userfaultfd_wp(vma))
-			uffd_wp_range(vma, vma->vm_start,
-				      vma->vm_end - vma->vm_start, false);
-		new_flags = vma->vm_flags & ~__VM_UFFD_FLAGS;
-		vma = vma_modify_flags_uffd(&vmi, prev, vma, vma->vm_start,
-					    vma->vm_end, new_flags,
-					    NULL_VM_UFFD_CTX);
-
-		vma_start_write(vma);
-		userfaultfd_set_vm_flags(vma, new_flags);
-		vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
-
-		prev = vma;
-	}
-	mmap_write_unlock(mm);
-	mmput(mm);
-wakeup:
-	/*
 	 * After no new page faults can wait on this fault_*wqh, flush
 	 * the last page faults that may have been already waiting on
 	 * the fault_*wqh.
@@ -1293,14 +1212,14 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
 				unsigned long arg)
 {
 	struct mm_struct *mm = ctx->mm;
-	struct vm_area_struct *vma, *prev, *cur;
+	struct vm_area_struct *vma, *cur;
 	int ret;
 	struct uffdio_register uffdio_register;
 	struct uffdio_register __user *user_uffdio_register;
-	unsigned long vm_flags, new_flags;
+	unsigned long vm_flags;
 	bool found;
 	bool basic_ioctls;
-	unsigned long start, end, vma_end;
+	unsigned long start, end;
 	struct vma_iterator vmi;
 	bool wp_async = userfaultfd_wp_async_ctx(ctx);
 
@@ -1428,57 +1347,8 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
 	} for_each_vma_range(vmi, cur, end);
 	BUG_ON(!found);
 
-	vma_iter_set(&vmi, start);
-	prev = vma_prev(&vmi);
-	if (vma->vm_start < start)
-		prev = vma;
-
-	ret = 0;
-	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)) {
-			ret = PTR_ERR(vma);
-			break;
-		}
-
-		/*
-		 * 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.
-		 */
-		vma_start_write(vma);
-		userfaultfd_set_vm_flags(vma, new_flags);
-		vma->vm_userfaultfd_ctx.ctx = ctx;
-
-		if (is_vm_hugetlb_page(vma) && uffd_disable_huge_pmd_share(vma))
-			hugetlb_unshare_all_pmds(vma);
-
-	skip:
-		prev = vma;
-		start = vma->vm_end;
-	}
+	ret = userfaultfd_register_range(ctx, vma, vm_flags, start, end,
+					 wp_async);
 
 out_unlock:
 	mmap_write_unlock(mm);
@@ -1519,7 +1389,6 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx,
 	struct vm_area_struct *vma, *prev, *cur;
 	int ret;
 	struct uffdio_range uffdio_unregister;
-	unsigned long new_flags;
 	bool found;
 	unsigned long start, end, vma_end;
 	const void __user *buf = (void __user *)arg;
@@ -1622,27 +1491,13 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx,
 			wake_userfault(vma->vm_userfaultfd_ctx.ctx, &range);
 		}
 
-		/* Reset ptes for the whole vma range if wr-protected */
-		if (userfaultfd_wp(vma))
-			uffd_wp_range(vma, start, vma_end - start, false);
-
-		new_flags = vma->vm_flags & ~__VM_UFFD_FLAGS;
-		vma = vma_modify_flags_uffd(&vmi, prev, vma, start, vma_end,
-					    new_flags, NULL_VM_UFFD_CTX);
+		vma = userfaultfd_clear_vma(&vmi, prev, vma,
+					    start, vma_end);
 		if (IS_ERR(vma)) {
 			ret = PTR_ERR(vma);
 			break;
 		}
 
-		/*
-		 * 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.
-		 */
-		vma_start_write(vma);
-		userfaultfd_set_vm_flags(vma, new_flags);
-		vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
-
 	skip:
 		prev = vma;
 		start = vma->vm_end;