Re: [RFC v2] drm/i915: Emit to ringbuffer directly

[Chris Wilson <chris@chris-wilson.co.uk>]

On Fri, Sep 09, 2016 at 04:52:28PM +0100, Tvrtko Ursulin wrote:
> From: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
> 
> This removes the usage of intel_ring_emit in favour of
> directly writing to the ring buffer.
> 
> intel_ring_emit was preventing the compiler for optimising
> fetch and increment of the current ring buffer pointer and
> therefore generating very verbose code for every write.
> 
> It had no useful purpose since all ringbuffer operations
> are started and ended with intel_ring_begin and
> intel_ring_advance respectively, with no bail out in the
> middle possible, so it is fine to increment the tail in
> intel_ring_begin and let the code manage the pointer
> itself.
> 
> Useless instruction removal amounts to approximately
> two and half kilobytes of saved text on my build.
> 
> Not sure if this has any measurable performance
> implications but executing a ton of useless instructions
> on fast paths cannot be good.
> 
> Patch is not fully polished, but it compiles and runs
> on Gen9 at least.
> 
> v2:
>  * Change return from intel_ring_begin to error pointer by
>    popular demand.
>  * Move tail increment to intel_ring_advance to enable some
>    error checking.

The increment can stay in begin (it's not intel_ring_begin() anymore
since it operates on the request!) as that will be smaller at no
usability cost.

Just check that rbuf == ring->vaddr + ring->tail at end.
-Chris

-- 
Chris Wilson, Intel Open Source Technology Centre
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx