From: Don Dutile Subject: Re: RFC: IOMMU/AMD: Error Handling Date: Tue, 30 Apr 2013 11:09:08 -0400 Message-ID: <517FDE94.7080700@redhat.com> References: <517ECDDA.3000606@amd.com> <517ED3A9.2050508@redhat.com> <517EE940.8010005@redhat.com> <517FDB96.7060602@amd.com> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii"; Format="flowed" Content-Transfer-Encoding: 7bit Return-path: In-Reply-To: <517FDB96.7060602-5C7GfCeVMHo@public.gmane.org> List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Sender: iommu-bounces-cunTk1MwBs9QetFLy7KEm3xJsTq8ys+cHZ5vskTnxNA@public.gmane.org Errors-To: iommu-bounces-cunTk1MwBs9QetFLy7KEm3xJsTq8ys+cHZ5vskTnxNA@public.gmane.org To: Suravee Suthikulanit Cc: "iommu-cunTk1MwBs9QetFLy7KEm3xJsTq8ys+cHZ5vskTnxNA@public.gmane.org" , "linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org" List-Id: iommu@lists.linux-foundation.org On 04/30/2013 10:56 AM, Suravee Suthikulanit wrote: > On 4/29/2013 4:42 PM, Don Dutile wrote: >> On 04/29/2013 04:34 PM, Duran, Leo wrote: >>> I'm wondering if resetting the IOMMU at init-time (once) would clear any BIOS induced noise. >>> Leo >>> >> Well, depends what you mean by 'reset'.... >> (a) setting it up for OS use is effectively a reset, but doesn't quiesce a device >> doing dma reads of a (bios-setup) queue. then the noisy messages begin >> (b) disable the iommu, and then the dma just occurs... and bad for writes, potentially. >> >> Similar issue is being reported & worked for kdump, where device are still >> doing DMA while the system is trying to 'reset' to the kexec'd kernel, and >> take a crash dump. >> >> Solution: stop devices from doing dma... but some you _want_ enabled throughout... >> like keyboard & mouse via usb controller, so you get to pick os from >> grub... not so for kexec... >> >> so, again, for isolation faults.... let the hw do its job -- isolate >> and throttle/silence the fault messages on a per-device, time-duration heuristic >> so the system can get through boot-up where enough OS is init'd (drivers started) >> to stop the temporary noise. > This sounds more like issue with the order of how things are initialized in the system. > If so, could we separate the code which enabling of IOMMU error logging/handling and > delay it until we are certain that systems are stable? > So, you are proposing we not enable fault events when IOMMU is initially configured; use the IOMMU through boot/driver-config, hoping all is well, and if not, continue blindly, and then enable IOMMU faults post/late-init ? > Suravee >