Dave Airlie wrote: > Hi Thomas, > > Okay I've come across a problem in the kernel memory validaton that > I'm not sure how to solve, > > The sequence of events is something like.. > > a) allocate frontbuffer MEM_LOCAL. > b) setstatus into MEM_VRAM | MEM_TT > c) emit a relocation in a batchbuffer to its BO for only MEM_TT > (possibly a bug - need to setup better) > d) submit batchbuffer. > > Now although what I may be doing is slightly wrong, what the bo mem > layer does it really wierd.. > > as drm_bo_mem_compat fails as the VRAM bit is left over, it calls into > the drm_bo_mem_space function > which allocates a chunk of TTM memory space for the frontbuffer again, > and again, and again, until I run out of aperture. > That's really odd. It shouldn't do that. Do you have a small test app? > Setting the flags on setstatus to MEM_TT, makes it work but I just > thought I raise the issue. > We should be hitting basically the same code paths, but clearly something is wrong.
/Thomas > Dave. > ------------------------------------------------------------------------- This SF.net email is sponsored by: Microsoft Defy all challenges. Microsoft(R) Visual Studio 2008. http://clk.atdmt.com/MRT/go/vse0120000070mrt/direct/01/ -- _______________________________________________ Dri-devel mailing list [email protected] https://lists.sourceforge.net/lists/listinfo/dri-devel
