Op 22-02-16 om 15:33 schreef John Harrison: > On 18/02/2016 14:49, Chris Wilson wrote: >> On Thu, Feb 18, 2016 at 02:24:06PM +0000, John.C.Harrison@xxxxxxxxx wrote: >>> From: John Harrison <John.C.Harrison@xxxxxxxxx> >>> >>> The fence object used inside the request structure requires a sequence >>> number. Although this is not used by the i915 driver itself, it could >>> potentially be used by non-i915 code if the fence is passed outside of >>> the driver. This is the intention as it allows external kernel drivers >>> and user applications to wait on batch buffer completion >>> asynchronously via the dma-buff fence API. >>> >>> To ensure that such external users are not confused by strange things >>> happening with the seqno, this patch adds in a per context timeline >>> that can provide a guaranteed in-order seqno value for the fence. This >>> is safe because the scheduler will not re-order batch buffers within a >>> context - they are considered to be mutually dependent. >> This is still nonsense. Just implement per-context seqno. > If you already have a set of patches to implement per-context seqno then let's get them merged. Otherwise, that is follow up work to be done once the scheduler has landed. There has already been too much churn and delay. So the decision is to get the scheduler in as soon as possible and any 'could do better' issues should be logged for follow up work. Seems to me that per context seqno would be cleaner than this hack.. ~Maarten _______________________________________________ Intel-gfx mailing list Intel-gfx@xxxxxxxxxxxxxxxxxxxxx https://lists.freedesktop.org/mailman/listinfo/intel-gfx
