drm/i915/userptr: Hold mmref whilst calling get-user-pages

Holding a reference to the containing task_struct is not sufficient to
prevent the mm_struct from being reaped under memory pressure. If this
happens whilst we are calling get_user_pages(), explosions erupt -
sometimes an immediate GPF, sometimes page flag corruption. To prevent
the target mm from being reaped as we are reading from it, acquire a
reference before we begin.

Testcase: igt/gem_shrink/*userptr
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Michał Winiarski <michal.winiarski@intel.com>
Cc: stable@vger.kernel.org
Reviewed-by: Michał Winiarski <michal.winiarski@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1459864801-28606-2-git-send-email-chris@chris-wilson.co.uk

drivers/gpu/drm/i915/i915_gem_userptr.c

@@ -544,9 +544,12 @@ __i915_gem_userptr_get_pages_worker(struct work_struct *_work)
 	if (pvec != NULL) {
 		struct mm_struct *mm = obj->userptr.mm->mm;
 
+		ret = -EFAULT;
+		if (atomic_inc_not_zero(&mm->mm_users)) {
 			down_read(&mm->mmap_sem);
 			while (pinned < npages) {
-			ret = get_user_pages_remote(work->task, mm,
+				ret = get_user_pages_remote
+					(work->task, mm,
 					 obj->userptr.ptr + pinned * PAGE_SIZE,
 					 npages - pinned,
 					 !obj->userptr.read_only, 0,
@@ -557,6 +560,8 @@ __i915_gem_userptr_get_pages_worker(struct work_struct *_work)
 				pinned += ret;
 			}
 			up_read(&mm->mmap_sem);
+			mmput(mm);
+		}
 	}
 
 	mutex_lock(&dev->struct_mutex);