From mboxrd@z Thu Jan 1 00:00:00 1970 From: Andi Kleen Subject: Re: Mystery packet killing tg3 Date: Wed, 04 May 2005 20:30:00 +0200 Message-ID: References: <20050502162405.65dfb4a9@localhost.localdomain> <20050502200251.38271b61.davem@davemloft.net> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: jgarzik@pobox.com, netdev@oss.sgi.com Return-path: To: "David S. Miller" In-Reply-To: <20050502200251.38271b61.davem@davemloft.net> (David S. Miller's message of "Mon, 2 May 2005 20:02:51 -0700") Sender: netdev-bounce@oss.sgi.com Errors-to: netdev-bounce@oss.sgi.com List-Id: netdev.vger.kernel.org "David S. Miller" writes: > > This usually means that there is some DMA corruption. > For example, some bug in the x86_64 IOMMU code or similar > causes a bogus DMA address to be fed to the tg3 or even > worse a DMA mapping is unmapped before tg3 is actually > done with it. IOMMU code on x86-64 should be never active unless Stephen used IOMMU_DEBUG or iommu=force. THat is because the tg3 is a 64bit capable device and should always use bypass. > Since AMD promised me an Opteron system last year, but never > made good on that promise, I've never been able to work on > fixing this bug myself. :-/ You could just buy one ,-) Lowend A64s boards+cpus are *really* cheap these days. And it will likely be much quieter than a noisy original AMD box. And the IOMMU works on that too if you force it (normally it is never active because they dont have enough memory to need remapping) -Andi