1 files changed, 103 insertions, 238 deletions

diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index 959551ff9a95..97c4d71115d8 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -31,11 +31,12 @@
 #include <linux/hugetlb.h>
 #include <linux/swapops.h>
 #include <linux/miscdevice.h>
+#include <linux/uio.h>
 
 static int sysctl_unprivileged_userfaultfd __read_mostly;
 
 #ifdef CONFIG_SYSCTL
-static struct ctl_table vm_userfaultfd_table[] = {
+static const struct ctl_table vm_userfaultfd_table[] = {
 	{
 		.procname	= "unprivileged_userfaultfd",
 		.data		= &sysctl_unprivileged_userfaultfd,
@@ -50,45 +51,6 @@ static struct ctl_table vm_userfaultfd_table[] = {
 
 static struct kmem_cache *userfaultfd_ctx_cachep __ro_after_init;
 
-/*
- * Start with fault_pending_wqh and fault_wqh so they're more likely
- * to be in the same cacheline.
- *
- * Locking order:
- *	fd_wqh.lock
- *		fault_pending_wqh.lock
- *			fault_wqh.lock
- *		event_wqh.lock
- *
- * To avoid deadlocks, IRQs must be disabled when taking any of the above locks,
- * since fd_wqh.lock is taken by aio_poll() while it's holding a lock that's
- * also taken in IRQ context.
- */
-struct userfaultfd_ctx {
-	/* waitqueue head for the pending (i.e. not read) userfaults */
-	wait_queue_head_t fault_pending_wqh;
-	/* waitqueue head for the userfaults */
-	wait_queue_head_t fault_wqh;
-	/* waitqueue head for the pseudo fd to wakeup poll/read */
-	wait_queue_head_t fd_wqh;
-	/* waitqueue head for events */
-	wait_queue_head_t event_wqh;
-	/* a refile sequence protected by fault_pending_wqh lock */
-	seqcount_spinlock_t refile_seq;
-	/* pseudo fd refcounting */
-	refcount_t refcount;
-	/* userfaultfd syscall flags */
-	unsigned int flags;
-	/* features requested from the userspace */
-	unsigned int features;
-	/* released */
-	bool released;
-	/* memory mappings are changing because of non-cooperative event */
-	atomic_t mmap_changing;
-	/* mm with one ore more vmas attached to this userfaultfd_ctx */
-	struct mm_struct *mm;
-};
-
 struct userfaultfd_fork_ctx {
 	struct userfaultfd_ctx *orig;
 	struct userfaultfd_ctx *new;
@@ -142,21 +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)
 {
@@ -295,7 +242,7 @@ static inline bool userfaultfd_huge_must_wait(struct userfaultfd_ctx *ctx,
 		goto out;
 
 	ret = false;
-	pte = huge_ptep_get(ptep);
+	pte = huge_ptep_get(vma->vm_mm, vmf->address, ptep);
 
 	/*
 	 * Lockless access: we're in a wait_event so it's ok if it
@@ -321,7 +268,7 @@ static inline bool userfaultfd_huge_must_wait(struct userfaultfd_ctx *ctx,
 /*
  * Verify the pagetables are still not ok after having reigstered into
  * the fault_pending_wqh to avoid userland having to UFFDIO_WAKE any
- * userfault that has already been resolved, if userfaultfd_read and
+ * userfault that has already been resolved, if userfaultfd_read_iter and
  * UFFDIO_COPY|ZEROPAGE are being run simultaneously on two different
  * threads.
  */
@@ -424,15 +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;
@@ -653,22 +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);
 	}
 
@@ -696,10 +621,11 @@ int dup_userfaultfd(struct vm_area_struct *vma, struct list_head *fcs)
 	struct userfaultfd_fork_ctx *fctx;
 
 	octx = vma->vm_userfaultfd_ctx.ctx;
-	if (!octx || !(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);
+	if (!octx)
+		return 0;
+
+	if (!(octx->features & UFFD_FEATURE_EVENT_FORK)) {
+		userfaultfd_reset_ctx(vma);
 		return 0;
 	}
 
@@ -724,12 +650,15 @@ int dup_userfaultfd(struct vm_area_struct *vma, struct list_head *fcs)
 		ctx->flags = octx->flags;
 		ctx->features = octx->features;
 		ctx->released = false;
+		init_rwsem(&ctx->map_changing_lock);
 		atomic_set(&ctx->mmap_changing, 0);
 		ctx->mm = vma->vm_mm;
 		mmgrab(ctx->mm);
 
 		userfaultfd_ctx_get(octx);
+		down_write(&octx->map_changing_lock);
 		atomic_inc(&octx->mmap_changing);
+		up_write(&octx->map_changing_lock);
 		fctx->orig = octx;
 		fctx->new = ctx;
 		list_add_tail(&fctx->list, fcs);
@@ -763,6 +692,34 @@ void dup_userfaultfd_complete(struct list_head *fcs)
 	}
 }
 
+void dup_userfaultfd_fail(struct list_head *fcs)
+{
+	struct userfaultfd_fork_ctx *fctx, *n;
+
+	/*
+	 * An error has occurred on fork, we will tear memory down, but have
+	 * allocated memory for fctx's and raised reference counts for both the
+	 * original and child contexts (and on the mm for each as a result).
+	 *
+	 * These would ordinarily be taken care of by a user handling the event,
+	 * but we are no longer doing so, so manually clean up here.
+	 *
+	 * mm tear down will take care of cleaning up VMA contexts.
+	 */
+	list_for_each_entry_safe(fctx, n, fcs, list) {
+		struct userfaultfd_ctx *octx = fctx->orig;
+		struct userfaultfd_ctx *ctx = fctx->new;
+
+		atomic_dec(&octx->mmap_changing);
+		VM_BUG_ON(atomic_read(&octx->mmap_changing) < 0);
+		userfaultfd_ctx_put(octx);
+		userfaultfd_ctx_put(ctx);
+
+		list_del(&fctx->list);
+		kfree(fctx);
+	}
+}
+
 void mremap_userfaultfd_prep(struct vm_area_struct *vma,
 			     struct vm_userfaultfd_ctx *vm_ctx)
 {
@@ -776,12 +733,12 @@ void mremap_userfaultfd_prep(struct vm_area_struct *vma,
 	if (ctx->features & UFFD_FEATURE_EVENT_REMAP) {
 		vm_ctx->ctx = ctx;
 		userfaultfd_ctx_get(ctx);
+		down_write(&ctx->map_changing_lock);
 		atomic_inc(&ctx->mmap_changing);
+		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);
 	}
 }
 
@@ -822,7 +779,9 @@ bool userfaultfd_remove(struct vm_area_struct *vma,
 		return true;
 
 	userfaultfd_ctx_get(ctx);
+	down_write(&ctx->map_changing_lock);
 	atomic_inc(&ctx->mmap_changing);
+	up_write(&ctx->map_changing_lock);
 	mmap_read_unlock(mm);
 
 	msg_init(&ewq.msg);
@@ -864,7 +823,9 @@ int userfaultfd_unmap_prep(struct vm_area_struct *vma, unsigned long start,
 		return -ENOMEM;
 
 	userfaultfd_ctx_get(ctx);
+	down_write(&ctx->map_changing_lock);
 	atomic_inc(&ctx->mmap_changing);
+	up_write(&ctx->map_changing_lock);
 	unmap_ctx->ctx = ctx;
 	unmap_ctx->start = start;
 	unmap_ctx->end = end;
@@ -896,49 +857,13 @@ 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;
-
-	/*
-	 * 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;
-		}
-		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;
+	userfaultfd_release_all(mm, 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
@@ -1207,34 +1132,34 @@ static ssize_t userfaultfd_ctx_read(struct userfaultfd_ctx *ctx, int no_wait,
 	return ret;
 }
 
-static ssize_t userfaultfd_read(struct file *file, char __user *buf,
-				size_t count, loff_t *ppos)
+static ssize_t userfaultfd_read_iter(struct kiocb *iocb, struct iov_iter *to)
 {
+	struct file *file = iocb->ki_filp;
 	struct userfaultfd_ctx *ctx = file->private_data;
 	ssize_t _ret, ret = 0;
 	struct uffd_msg msg;
-	int no_wait = file->f_flags & O_NONBLOCK;
 	struct inode *inode = file_inode(file);
+	bool no_wait;
 
 	if (!userfaultfd_is_initialized(ctx))
 		return -EINVAL;
 
+	no_wait = file->f_flags & O_NONBLOCK || iocb->ki_flags & IOCB_NOWAIT;
 	for (;;) {
-		if (count < sizeof(msg))
+		if (iov_iter_count(to) < sizeof(msg))
 			return ret ? ret : -EINVAL;
 		_ret = userfaultfd_ctx_read(ctx, no_wait, &msg, inode);
 		if (_ret < 0)
 			return ret ? ret : _ret;
-		if (copy_to_user((__u64 __user *) buf, &msg, sizeof(msg)))
+		_ret = !copy_to_iter_full(&msg, sizeof(msg), to);
+		if (_ret)
 			return ret ? ret : -EFAULT;
 		ret += sizeof(msg);
-		buf += sizeof(msg);
-		count -= sizeof(msg);
 		/*
 		 * Allow to read more than one fault at time but only
 		 * block if waiting for the very first one.
 		 */
-		no_wait = O_NONBLOCK;
+		no_wait = true;
 	}
 }
 
@@ -1315,14 +1240,14 @@ 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);
 
@@ -1450,57 +1375,8 @@ 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);
@@ -1541,7 +1417,6 @@ 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;
@@ -1644,27 +1519,13 @@ 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;
@@ -1748,9 +1609,8 @@ static int userfaultfd_copy(struct userfaultfd_ctx *ctx,
 	if (uffdio_copy.mode & UFFDIO_COPY_MODE_WP)
 		flags |= MFILL_ATOMIC_WP;
 	if (mmget_not_zero(ctx->mm)) {
-		ret = mfill_atomic_copy(ctx->mm, uffdio_copy.dst, uffdio_copy.src,
-					uffdio_copy.len, &ctx->mmap_changing,
-					flags);
+		ret = mfill_atomic_copy(ctx, uffdio_copy.dst, uffdio_copy.src,
+					uffdio_copy.len, flags);
 		mmput(ctx->mm);
 	} else {
 		return -ESRCH;
@@ -1800,9 +1660,8 @@ static int userfaultfd_zeropage(struct userfaultfd_ctx *ctx,
 		goto out;
 
 	if (mmget_not_zero(ctx->mm)) {
-		ret = mfill_atomic_zeropage(ctx->mm, uffdio_zeropage.range.start,
-					   uffdio_zeropage.range.len,
-					   &ctx->mmap_changing);
+		ret = mfill_atomic_zeropage(ctx, uffdio_zeropage.range.start,
+					   uffdio_zeropage.range.len);
 		mmput(ctx->mm);
 	} else {
 		return -ESRCH;
@@ -1857,9 +1716,8 @@ static int userfaultfd_writeprotect(struct userfaultfd_ctx *ctx,
 		return -EINVAL;
 
 	if (mmget_not_zero(ctx->mm)) {
-		ret = mwriteprotect_range(ctx->mm, uffdio_wp.range.start,
-					  uffdio_wp.range.len, mode_wp,
-					  &ctx->mmap_changing);
+		ret = mwriteprotect_range(ctx, uffdio_wp.range.start,
+					  uffdio_wp.range.len, mode_wp);
 		mmput(ctx->mm);
 	} else {
 		return -ESRCH;
@@ -1909,9 +1767,8 @@ static int userfaultfd_continue(struct userfaultfd_ctx *ctx, unsigned long arg)
 		flags |= MFILL_ATOMIC_WP;
 
 	if (mmget_not_zero(ctx->mm)) {
-		ret = mfill_atomic_continue(ctx->mm, uffdio_continue.range.start,
-					    uffdio_continue.range.len,
-					    &ctx->mmap_changing, flags);
+		ret = mfill_atomic_continue(ctx, uffdio_continue.range.start,
+					    uffdio_continue.range.len, flags);
 		mmput(ctx->mm);
 	} else {
 		return -ESRCH;
@@ -1964,9 +1821,8 @@ static inline int userfaultfd_poison(struct userfaultfd_ctx *ctx, unsigned long
 		goto out;
 
 	if (mmget_not_zero(ctx->mm)) {
-		ret = mfill_atomic_poison(ctx->mm, uffdio_poison.range.start,
-					  uffdio_poison.range.len,
-					  &ctx->mmap_changing, 0);
+		ret = mfill_atomic_poison(ctx, uffdio_poison.range.start,
+					  uffdio_poison.range.len, 0);
 		mmput(ctx->mm);
 	} else {
 		return -ESRCH;
@@ -2040,16 +1896,8 @@ static int userfaultfd_move(struct userfaultfd_ctx *ctx,
 		return -EINVAL;
 
 	if (mmget_not_zero(mm)) {
-		mmap_read_lock(mm);
-
-		/* Re-check after taking mmap_lock */
-		if (likely(!atomic_read(&ctx->mmap_changing)))
-			ret = move_pages(ctx, mm, uffdio_move.dst, uffdio_move.src,
-					 uffdio_move.len, uffdio_move.mode);
-		else
-			ret = -EINVAL;
-
-		mmap_read_unlock(mm);
+		ret = move_pages(ctx, uffdio_move.dst, uffdio_move.src,
+				 uffdio_move.len, uffdio_move.mode);
 		mmput(mm);
 	} else {
 		return -ESRCH;
@@ -2092,7 +1940,7 @@ static int userfaultfd_api(struct userfaultfd_ctx *ctx,
 		goto out;
 	features = uffdio_api.features;
 	ret = -EINVAL;
-	if (uffdio_api.api != UFFD_API || (features & ~UFFD_API_FEATURES))
+	if (uffdio_api.api != UFFD_API)
 		goto err_out;
 	ret = -EPERM;
 	if ((features & UFFD_FEATURE_EVENT_FORK) && !capable(CAP_SYS_PTRACE))
@@ -2116,6 +1964,11 @@ static int userfaultfd_api(struct userfaultfd_ctx *ctx,
 	uffdio_api.features &= ~UFFD_FEATURE_WP_UNPOPULATED;
 	uffdio_api.features &= ~UFFD_FEATURE_WP_ASYNC;
 #endif
+
+	ret = -EINVAL;
+	if (features & ~uffdio_api.features)
+		goto err_out;
+
 	uffdio_api.ioctls = UFFD_API_IOCTLS;
 	ret = -EFAULT;
 	if (copy_to_user(buf, &uffdio_api, sizeof(uffdio_api)))
@@ -2215,7 +2068,7 @@ static const struct file_operations userfaultfd_fops = {
 #endif
 	.release	= userfaultfd_release,
 	.poll		= userfaultfd_poll,
-	.read		= userfaultfd_read,
+	.read_iter	= userfaultfd_read_iter,
 	.unlocked_ioctl = userfaultfd_ioctl,
 	.compat_ioctl	= compat_ptr_ioctl,
 	.llseek		= noop_llseek,
@@ -2235,6 +2088,7 @@ static void init_once_userfaultfd_ctx(void *mem)
 static int new_userfaultfd(int flags)
 {
 	struct userfaultfd_ctx *ctx;
+	struct file *file;
 	int fd;
 
 	BUG_ON(!current->mm);
@@ -2255,18 +2109,29 @@ static int new_userfaultfd(int flags)
 	ctx->flags = flags;
 	ctx->features = 0;
 	ctx->released = false;
+	init_rwsem(&ctx->map_changing_lock);
 	atomic_set(&ctx->mmap_changing, 0);
 	ctx->mm = current->mm;
-	/* prevent the mm struct to be freed */
-	mmgrab(ctx->mm);
+
+	fd = get_unused_fd_flags(flags & UFFD_SHARED_FCNTL_FLAGS);
+	if (fd < 0)
+		goto err_out;
 
 	/* Create a new inode so that the LSM can block the creation.  */
-	fd = anon_inode_create_getfd("[userfaultfd]", &userfaultfd_fops, ctx,
+	file = anon_inode_create_getfile("[userfaultfd]", &userfaultfd_fops, ctx,
 			O_RDONLY | (flags & UFFD_SHARED_FCNTL_FLAGS), NULL);
-	if (fd < 0) {
-		mmdrop(ctx->mm);
-		kmem_cache_free(userfaultfd_ctx_cachep, ctx);
+	if (IS_ERR(file)) {
+		put_unused_fd(fd);
+		fd = PTR_ERR(file);
+		goto err_out;
 	}
+	/* prevent the mm struct to be freed */
+	mmgrab(ctx->mm);
+	file->f_mode |= FMODE_NOWAIT;
+	fd_install(fd, file);
+	return fd;
+err_out:
+	kmem_cache_free(userfaultfd_ctx_cachep, ctx);
 	return fd;
 }