/srv/irclogs.ubuntu.com/2012/07/09/#ubuntu-x.txt

mlankhorst"Hello, world!\n"07:36
mlankhorstdoes pre-sandy bridge even allow snooped access?11:25
mlankhorstwoops wrong channel :)11:36
mlankhorst.. running kernel with kmemcheck is scary13:16
mlankhorstRAOF: great success :D22:11
mlankhorstdmabufmgr seems to work22:11
mlankhorsti adapted the code for nouveau to use the hardware for waiting22:12
mlankhorstwhich turned into a 800 line patch :s22:21
RAOFHuge success!22:54
mlankhorstRAOF: yeah was just tracking 2 bugs today, first one was in my test program with how I marked intel relocations. I needed a noop for testing, but it ended up executing the address as command, second one was probably due to some stuff not firing in idle stait, and workaround was adding some busyloops22:57
mlankhorsteg schedtool ... 'while true; do true; done' on all cpus22:58
RAOF:)22:59
mlankhorsthttp://people.canonical.com/~mlankhorst/prime-sync/ full patchset, probably best to use drm-intel-next-queue git tree23:01
mlankhorsti wanted to grab the delayed fput git tree too, but it hangs early on in boot23:02
jwia hacky max_cstate=0? ;)23:04
RAOFI may have to get you to give me some pointers for what needs to be done on the radeon side. That might be a fun project at 2am when Zoƫ's crying :)23:05
mlankhorstRAOF: oh I could do it easily myself23:07
mlankhorstRAOF: anyhow you need to create a read-only mapping and add a wait-ge op for a dma-buf23:08
mlankhorstwell, either read-only or userspace inaccessible..23:09
mlankhorstive glanced through the documentation so I know r600 supports the operations at least23:10
mlankhorstbut the easiest case is adapting i91523:12
mlankhorstoh btw, DON'T create a gem object for your sync bo, it will deadlock23:13
mlankhorstbesides that radeon uses ttm so there's no real  need for involving gem23:14
mlankhorstRAOF: night 23:28
RAOFGood night :)(23:28

Generated by irclog2html.py 2.7 by Marius Gedminas - find it at mg.pov.lt!