Re: [Intel-gfx] [PATCH v2 7/9] drm/i915: Properly write lock bw_state when it changes

["Lisovskiy, Stanislav" <stanislav.lisovskiy@intel.com>]

On Thu, Mar 03, 2022 at 09:12:05PM +0200, Ville Syrjala wrote:
> From: Ville Syrjälä <ville.syrjala@linux.intel.com>
> 
> The current code also forgets to call intel_atomic_lock_global_state()
> when other stuff besides the final min_cdlck changes in the state.
> That means we may throw away data which actually has changed, and
> thus we can't be at all sure what the code ends up doing during
> subsequent commits. Do the write lock properly.
> 
> Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>

Reviewed-by: Stanislav Lisovskiy <stanislav.lisovskiy@intel.com>

> ---
>  drivers/gpu/drm/i915/display/intel_bw.c | 24 +++++++++++++++++++++++-
>  1 file changed, 23 insertions(+), 1 deletion(-)
> 
> diff --git a/drivers/gpu/drm/i915/display/intel_bw.c b/drivers/gpu/drm/i915/display/intel_bw.c
> index 0759bb95ea4b..56eebccd16e2 100644
> --- a/drivers/gpu/drm/i915/display/intel_bw.c
> +++ b/drivers/gpu/drm/i915/display/intel_bw.c
> @@ -678,6 +678,28 @@ intel_atomic_get_bw_state(struct intel_atomic_state *state)
>  	return to_intel_bw_state(bw_state);
>  }
>  
> +static bool intel_bw_state_changed(struct drm_i915_private *i915,
> +				   const struct intel_bw_state *old_bw_state,
> +				   const struct intel_bw_state *new_bw_state)
> +{
> +	enum pipe pipe;
> +
> +	for_each_pipe(i915, pipe) {
> +		const struct intel_dbuf_bw *old_crtc_bw =
> +			&old_bw_state->dbuf_bw[pipe];
> +		const struct intel_dbuf_bw *new_crtc_bw =
> +			&new_bw_state->dbuf_bw[pipe];
> +		enum dbuf_slice slice;
> +
> +		for_each_dbuf_slice(i915, slice) {
> +			if (old_crtc_bw->used_bw[slice] != new_crtc_bw->used_bw[slice])
> +				return true;
> +		}
> +	}
> +
> +	return old_bw_state->min_cdclk != new_bw_state->min_cdclk;
> +}
> +
>  static void skl_crtc_calc_dbuf_bw(struct intel_bw_state *bw_state,
>  				  const struct intel_crtc_state *crtc_state)
>  {
> @@ -765,7 +787,7 @@ int intel_bw_calc_min_cdclk(struct intel_atomic_state *state)
>  
>  	new_bw_state->min_cdclk = DIV_ROUND_UP(max_bw, 64);
>  
> -	if (new_bw_state->min_cdclk != old_bw_state->min_cdclk) {
> +	if (intel_bw_state_changed(dev_priv, old_bw_state, new_bw_state)) {
>  		int ret = intel_atomic_lock_global_state(&new_bw_state->base);
>  
>  		if (ret)
> -- 
> 2.34.1
>