2013/3/26 Joerg Roedel <[email protected]>: > Hi Andreas, > > thanks for the information. > > On Tue, Mar 26, 2013 at 01:48:38PM +0100, Andreas Degert wrote: >> seems to be this (additionaly I have appended the full dump): >> >> device: 00:00.2 cap: 0040 seg: 0 flags: fe info 1300 >> mmio-addr: 00000000feb80000 >> DEV_SELECT_RANGE_START devid: 00:01.0 flags: 00 >> DEV_RANGE_END devid: ff:1f.6 >> DEV_ALIAS_RANGE devid: 03:00.0 flags: 00 devid_to: 00:14.4 >> DEV_RANGE_END devid: 04:1f.7 >> DEV_SPECIAL(HPET[0]) devid: 00:14.0 >> DEV_SPECIAL(IOAPIC[5]) devid: 00:14.0 > > That looks good so far. You have two sound devices: > > One in the GPU at 00:01.1 > One in the SB at 00:14.2 > > Both are covered by the above IVRS entries.
There is a third sound device: 04:00.0 Multimedia audio controller: Xilinx Corporation RME Hammerfall DSP (rev 35) (at the end of the lspci listing in my first mail). This is the one that doesn't work, it's connected via cardbus (yenta driver), so it appears a bit further down in the dmesg output. > Does a unpatched kernel (no > rt patch) work for you, so can you try > if it also happens with 3.8.4? Yes, I started seeing the problem in 3.2 (in Debian wheezy), then found the commit which made the difference in 3.0-rc3 by bisecting. Happens also in unpatched 3.8.4. > So you see IO_PAGE_FAULTS when trying to use the soundcard? No io page faults, just reading zeros when recording and silence on playback.. (I'll double check later today for any dmesg output while using the soundcard.) Thanks, Andreas _______________________________________________ iommu mailing list [email protected] https://lists.linuxfoundation.org/mailman/listinfo/iommu
