Many eons ago, we add ppgtt support. Among the rejoicing, was a bitter pill, it was slow, much slower due to driver overhead in looking up the vma. In part this was due to obj_to_vma being a linear walk, but there was also the effect in execbuf of going from handle to obj to vma, and we have had talked for a long time of finding a faster method, so why not use a ht to go from handle to vma. That's the headline, the majority of the code deals with little fixes to avoid relocations and to reduce the cost in processing them (and reduce the cost in avoiding them). -Chris _______________________________________________ Intel-gfx mailing list Intel-gfx@xxxxxxxxxxxxxxxxxxxxx https://lists.freedesktop.org/mailman/listinfo/intel-gfx
