Re: [PATCH 1/2] drm/i915: Be paranoid and post the writes to stop the rings

[Mika Kuoppala <mika.kuoppala@linux.intel.com>]

Chris Wilson <chris@chris-wilson.co.uk> writes:

> Although the mmio are uncached and so should be flushed on every write,
> be paranoid and do a mmio read after setting the ring head/tail to be
> sure they have taken effect before moving on.
>
> Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
> Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
> ---
>  drivers/gpu/drm/i915/intel_uncore.c | 2 ++
>  1 file changed, 2 insertions(+)
>
> diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c
> index 164dbb8cfa36..612aad205b59 100644
> --- a/drivers/gpu/drm/i915/intel_uncore.c
> +++ b/drivers/gpu/drm/i915/intel_uncore.c
> @@ -1522,9 +1522,11 @@ static void gen3_stop_engine(struct intel_engine_cs *engine)
>  				 engine->name);
>  
>  	I915_WRITE_FW(RING_HEAD(base), I915_READ_FW(RING_TAIL(base)));
> +	POSTING_READ_FW(RING_HEAD(base)); /* paranoia */
>  
>  	I915_WRITE_FW(RING_HEAD(base), 0);
>  	I915_WRITE_FW(RING_TAIL(base), 0);
> +	POSTING_READ_FW(RING_HEAD(base));

Is there a benefit on doing it on head? Both
should be flushed but tail would be more eye pleasing.
-Mika

>  
>  	/* The ring must be empty before it is disabled */
>  	I915_WRITE_FW(RING_CTL(base), 0);
> -- 
> 2.16.1
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx