From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753370AbZCJBeM (ORCPT ); Mon, 9 Mar 2009 21:34:12 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1752203AbZCJBd4 (ORCPT ); Mon, 9 Mar 2009 21:33:56 -0400 Received: from 69-30-77-85.dq1sn.easystreet.com ([69.30.77.85]:34288 "EHLO kingsolver.anholt.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751426AbZCJBdz (ORCPT ); Mon, 9 Mar 2009 21:33:55 -0400 From: Eric Anholt To: linux-kernel@vger.kernel.org Subject: Fixing the i915 lock ordering Date: Mon, 9 Mar 2009 18:33:49 -0700 Message-Id: <1236648831-18230-1-git-send-email-eric@anholt.net> X-Mailer: git-send-email 1.5.6.5 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Here's a new patch series with a proposed fix for two of the paths with lock ordering problems in i915. If these look OK (in particular GTT pwrite, which is the most important performance path), I'll work on resolving the non-GEM issue and figuring out what we want to do about execbuffers (either this plan, or krh's patch, or something with get_user_pages and kmap).