On Fri, Sep 14, 2012 at 09:39:00AM -0500, Josh Hunt wrote: > On 09/14/2012 07:55 AM, Josh Hunt wrote: > > > >Thanks to your help I was able to test your branch, but it still does > >not resolve the problem. Removal of the "factor=1" workaround fixes the > >memory size reporting on boot, but the sysfs values are still incorrect. > > > > Please disregard what I said earlier about the shift still being > wrong. Looking at the dmesg more I see now that the # of pages are > correctly reported (262144), however sysfs is still wrong. > > [ 25.837588] EDAC DEBUG: init_csrows: MC node: 0, csrow: 0 > [ 25.837589] EDAC DEBUG: amd64_csrow_nr_pages: csrow: 0, channel: > 0, DBAM idx: 2 > [ 25.837591] EDAC DEBUG: amd64_csrow_nr_pages: nr_pages/channel: 262144 > [ 25.837592] EDAC amd64: CS0: Unbuffered DDR2 RAM > [ 25.837724] EDAC DEBUG: init_csrows: Total csrow0 pages: 262144 > [ 25.837725] DBG: init_csrows: channel_count:2 > [ 25.837856] DBG: init_csrows: channel_count:2 > [ 25.837988] EDAC DEBUG: init_csrows: MC node: 0, csrow: 1 > [ 25.837989] EDAC DEBUG: amd64_csrow_nr_pages: csrow: 1, channel: > 0, DBAM idx: 2 > [ 25.837991] EDAC DEBUG: amd64_csrow_nr_pages: nr_pages/channel: 262144 > [ 25.837992] EDAC amd64: CS1: Unbuffered DDR2 RAM > [ 25.838157] EDAC DEBUG: init_csrows: Total csrow1 pages: 262144 > [ 25.838158] DBG: init_csrows: channel_count:2 > [ 25.838289] DBG: init_csrows: channel_count:2 > [ 25.838421] EDAC DEBUG: init_csrows: MC node: 0, csrow: 2 > [ 25.838422] EDAC DEBUG: amd64_csrow_nr_pages: csrow: 2, channel: > 0, DBAM idx: 2 > [ 25.838424] EDAC DEBUG: amd64_csrow_nr_pages: nr_pages/channel: 262144 > [ 25.838425] EDAC amd64: CS2: Unbuffered DDR2 RAM > [ 25.838556] EDAC DEBUG: init_csrows: Total csrow2 pages: 262144 > [ 25.838558] DBG: init_csrows: channel_count:2 > [ 25.838689] DBG: init_csrows: channel_count:2 > [ 25.838820] EDAC DEBUG: init_csrows: MC node: 0, csrow: 3 > [ 25.838822] EDAC DEBUG: amd64_csrow_nr_pages: csrow: 3, channel: > 0, DBAM idx: 2 > [ 25.838823] EDAC DEBUG: amd64_csrow_nr_pages: nr_pages/channel: 262144 > [ 25.838824] EDAC amd64: CS3: Unbuffered DDR2 RAM > [ 25.838957] EDAC DEBUG: init_csrows: Total csrow3 pages: 262144 > > I looked into this and see that sysfs is doing the double counting > b/c it loops over the # of channels: > > [ 131.423949] DBG: csrow_size_show: i:0 nr_pages:262144 nr_channels:2 > [ 131.424112] DBG: csrow_size_show: i:1 nr_pages:524288 nr_channels:2 > > I verified this in init_csrows: > [ 25.838958] DBG: init_csrows: channel_count:2 > > Since I don't know the details of the hardware here it's hard for me > to suggest a fix, but it would seem that k8_early_channel_count() > needs to be modified to only return 1 in this case?
Yeah, there are still some issues after the whole change to per-dimm accounting came in. I'm looking into it. Thanks for testing and reporting. If you see anything else out of the ordinary, let me know too so that I can fix it. Thanks. -- Regards/Gruss, Boris. Advanced Micro Devices GmbH Einsteinring 24, 85609 Dornach GM: Alberto Bozzo Reg: Dornach, Landkreis Muenchen HRB Nr. 43632 WEEE Registernr: 129 19551 -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
