From mboxrd@z Thu Jan 1 00:00:00 1970 From: David Vrabel Subject: Re: [linux-linus test] 25478: regressions - FAIL Date: Tue, 18 Mar 2014 11:25:25 +0000 Message-ID: <53282D25.10203@citrix.com> References: <1394816855.6442.168.camel@kazak.uk.xensource.com> <20140314182355.GA1051@phenom.dumpdata.com> <1395054505.4122.65.camel@kazak.uk.xensource.com> <20140317193613.GA15772@phenom.dumpdata.com> <1395134987.18221.58.camel@kazak.uk.xensource.com> <5328262D.7040005@citrix.com> <1395140645.12847.38.camel@kazak.uk.xensource.com> <1395141039.12847.42.camel@kazak.uk.xensource.com> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Return-path: In-Reply-To: <1395141039.12847.42.camel@kazak.uk.xensource.com> List-Unsubscribe: , List-Post: List-Help: List-Subscribe: , Sender: xen-devel-bounces@lists.xen.org Errors-To: xen-devel-bounces@lists.xen.org To: Ian Campbell Cc: Boris.Ostrovsky@oracle.com, xen-devel@lists.xensource.com, "xen.org" List-Id: xen-devel@lists.xenproject.org On 18/03/14 11:10, Ian Campbell wrote: > > There are 64-bit bars but they don't have addresses >4G so I think they > don't count. If a device only has 32-bit BARs it's generally not capable of handling 64-bit DMA addresses and we can point and laugh at the card. mptsas is a driver that uses dma_get_required_mask() to determine a "suitable" DMA mask -- but under Xen dma_get_required_mask() may return the wrong mask since it only gets the physical RAM range and not machine addresses. David