From mboxrd@z Thu Jan 1 00:00:00 1970 From: Ben Greear Date: Fri, 27 Jan 2012 13:37:38 -0800 Subject: [ath9k-devel] Failed to stop TX DMA In-Reply-To: References: <6b8a2b68eccbe5b3c9762c6f052a6878@www.thefabfarrows.com> <91fa72618754b69f9bf13a733e981523@www.thefabfarrows.com> <2ef536609cbee9c771dc3ebdf7e79bb1@www.thefabfarrows.com> <4F18FBE9.8000500@candelatech.com> <88fc9df2a2ff8d4dff6a56da7754a20f@www.thefabfarrows.com> <4F199E6B.2010302@candelatech.com> <394a9f3888c25d0d12e30c7018741598@www.thefabfarrows.com> <4F1DB019.3040206@candelatech.com> <4F228ED6.2070102@molgaard.org> <4F22D932.2060502@candelatech.com> <4F22ED46.1000207@molgaard.org> <4F22F8E7.5010704@candelatech.com> Message-ID: <4F231922.9030903@candelatech.com> List-Id: MIME-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit To: ath9k-devel@lists.ath9k.org On 01/27/2012 12:05 PM, Adrian Chadd wrote: > "pissed off bus glue." > > You'll get that error whenever the PCI/PCIe interface glue errors out. > > " > > host1_fatal signal from PCI core during a DMA transfer > > " > > > As for what this means, I'll have to go and tickle someone in the MAC group to give us some ideas. > > > Ben, would you please work with the OP to take everything above and dump it into a comphrensive bugzilla.kernel.org report? > > I'll then assign it to the ath9k team here and follow it up with the MAC group. Maybe they'll have some ideas on what we can do. The bug is here: https://bugzilla.kernel.org/show_bug.cgi?id=42673 If I can figure out exactly what NIC it is I'll try to get one and see if I can reproduce the problem on my machines. It's always possible it's a bad interaction with some specific motherboard(s). I don't have a bus analyzer, but if I can reproduce it, likely others can as well. Thanks, Ben -- Ben Greear Candela Technologies Inc http://www.candelatech.com