From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1756160Ab1AaQgn (ORCPT ); Mon, 31 Jan 2011 11:36:43 -0500 Received: from mga02.intel.com ([134.134.136.20]:55989 "EHLO mga02.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752626Ab1AaQgm (ORCPT ); Mon, 31 Jan 2011 11:36:42 -0500 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="4.60,404,1291622400"; d="scan'208";a="598096517" Date: Mon, 31 Jan 2011 08:36:39 -0800 From: Andi Kleen To: Chuck Ebbert Cc: linux-kernel@vger.kernel.org, David Woodhouse Subject: Re: b44 driver causes panic when using swiotlb Message-ID: <20110131163639.GA32095@tassilo.jf.intel.com> References: <20110131105412.7252a09c@katamari> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20110131105412.7252a09c@katamari> User-Agent: Mutt/1.5.21 (2010-09-15) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Mon, Jan 31, 2011 at 10:54:12AM -0500, Chuck Ebbert wrote: > The b44 driver is triggering this panic in swiotlb_map_page(): > > if (!dma_capable(dev, dev_addr, size)) > panic("map_single: bounce buffer is not DMA'ble"); > > The kernel log says the bounce buffers are at 0xdb400000, but b44 can > only do DMA to the first 1GB of memory: b44 needs to use GFP_DMA then and do its own custom bouncing. The standard pci_map_* bounce buffering is only designed for at least 32bit capable devices. BTW I'm pretty sure this worked at some point, must have regressed somehow. -Andi -- ak@linux.intel.com -- Speaking for myself only