Hi all, I filed a bug on bugzilla[1], I wish we could discuss and find a solution on bugzilla. I'll try to build a patch if you think adding a quirk is do-able. Thanks,
1. https://bugzilla.kernel.org/show_bug.cgi?id=97661 Best regards, AceLan Kao. 2015-04-23 10:15 GMT+08:00 AceLan Kao <acelan....@canonical.com>: > Hi Joerg, > > We can confirm that the issue comes from the resources conflict, > adding this boot option can solve the issue. > ivrs_ioapic[5]=00:00.1 > We've tried to negotiate with the OEM BIOS team, but they refused to > modify the BIOS code, since there is no issue on MS Windows and it'll > require to re-start a full test if the BIOS code is changed, so they > don't want to do that. > > I'm wondering if we can add a quirk to list those machine and assign > them the correct ivrs_ioapic value in amd_iommu driver? > Thanks. > > Best regards, > AceLan Kao. > > 2015-03-31 8:30 GMT+08:00 AceLan Kao <acelan....@canonical.com>: >> Hi Joerg, >> >> Thank you so much, I'll try asking BIOS engineer to deliver us a new >> BIOS for testing. >> >> Best regards, >> AceLan Kao. >> >> 2015-03-31 0:09 GMT+08:00 Joerg Roedel <j...@8bytes.org>: >>> Hi AceLan, >>> >>> On Fri, Mar 27, 2015 at 08:48:22AM +0800, AceLan Kao wrote: >>>> Very thanks for your time. >>>> This is the log booting with kernel 4.0rc5 without fglrx loaded. >>> >>> Thanks, it scheds some light on the issue. See below. >>> >>>> [ 0.080177] AMD-Vi: device: 00:00.2 cap: 0040 seg: 0 flags: b8 info 0000 >>>> [ 0.080181] AMD-Vi: mmio-addr: 00000000feb80000 >>>> [ 0.080198] AMD-Vi: DEV_SELECT_RANGE_START devid: 00:01.0 >>>> flags: 00 >>>> [ 0.080200] AMD-Vi: DEV_RANGE_END devid: ff:1f.6 >>>> [ 0.081192] AMD-Vi: DEV_ALIAS_RANGE devid: 05:00.0 >>>> flags: 00 devid_to: 00:14.4 >>>> [ 0.081194] AMD-Vi: DEV_RANGE_END devid: 05:1f.7 >>>> [ 0.081204] AMD-Vi: DEV_SPECIAL(HPET[0]) devid: 00:14.0 >>>> [ 0.081207] AMD-Vi: DEV_SPECIAL(IOAPIC[4]) devid: >>>> 00:14.0 >>>> [ 0.081208] AMD-Vi: DEV_SPECIAL(IOAPIC[5]) devid: >>>> 00:00.0 >>> >>> This is dump of the IVRS table contents. It tells us that IOAPIC with ID >>> 5 uses PCI request-id 00:00.0. But this information is wrong, it uses >>> request-id 00:00.1, as seen below: >>> >>>> [ 23.515063] AMD-Vi: Event logged [INVALID_DEVICE_REQUEST device=00:00.1 >>>> address=0x000000fdf80c0020 flags=0x0a00] >>> >>> This message comes from an interrupt request sent by the IOAPIC, and it >>> uses a different request-id. Can you try to update the BIOS on that >>> machine and test if it fixes the issue? >>> >>> >>> Joerg >>> _______________________________________________ iommu mailing list iommu@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/iommu
