userfaultfd: clear the vma->vm_userfaultfd_ctx if UFFD_EVENT_FORK fails

The previous fix in commit 384632e67e08 ("userfaultfd: non-cooperative:
fix fork use after free") corrected the refcounting in case of
UFFD_EVENT_FORK failure for the fork userfault paths.

That still didn't clear the vma->vm_userfaultfd_ctx of the vmas that
were set to point to the aborted new uffd ctx earlier in
dup_userfaultfd.

Link: http://lkml.kernel.org/r/20171223002505.593-2-aarcange@redhat.com
Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Reviewed-by: Mike Rapoport <rppt@linux.vnet.ibm.com>
Cc: Eric Biggers <ebiggers3@gmail.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index ac9a4e65ca497ad3b673dc50893d13b44150c70f..41a75f9f23fdbfc2d30ae80b979a331484f0dcf9 100644 (file)
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -570,11 +570,14 @@ out:
 static void userfaultfd_event_wait_completion(struct userfaultfd_ctx *ctx,
                                              struct userfaultfd_wait_queue *ewq)
 {
+       struct userfaultfd_ctx *release_new_ctx;
+
        if (WARN_ON_ONCE(current->flags & PF_EXITING))
                goto out;
 
        ewq->ctx = ctx;
        init_waitqueue_entry(&ewq->wq, current);
+       release_new_ctx = NULL;
 
        spin_lock(&ctx->event_wqh.lock);
        /*
@@ -601,8 +604,7 @@ static void userfaultfd_event_wait_completion(struct userfaultfd_ctx *ctx,
                                new = (struct userfaultfd_ctx *)
                                        (unsigned long)
                                        ewq->msg.arg.reserved.reserved1;
-
-                               userfaultfd_ctx_put(new);
+                               release_new_ctx = new;
                        }
                        break;
                }
@@ -617,6 +619,20 @@ static void userfaultfd_event_wait_completion(struct userfaultfd_ctx *ctx,
        __set_current_state(TASK_RUNNING);
        spin_unlock(&ctx->event_wqh.lock);
 
+       if (release_new_ctx) {
+               struct vm_area_struct *vma;
+               struct mm_struct *mm = release_new_ctx->mm;
+
+               /* the various vma->vm_userfaultfd_ctx still points to it */
+               down_write(&mm->mmap_sem);
+               for (vma = mm->mmap; vma; vma = vma->vm_next)
+                       if (vma->vm_userfaultfd_ctx.ctx == release_new_ctx)
+                               vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
+               up_write(&mm->mmap_sem);
+
+               userfaultfd_ctx_put(release_new_ctx);
+       }
+
        /*
         * ctx may go away after this if the userfault pseudo fd is
         * already released.