[Intel-gfx] [PATCH 2/2] drm/i915: add hangcheck action and score to error state

[Chris Wilson]

On Fri, Aug 30, 2013 at 04:19:29PM +0300, Mika Kuoppala wrote:
> Score and action reveal what the rings were doing
> when hang was declared.
> 
> Signed-off-by: Mika Kuoppala <mika.kuoppala at intel.com>
> ---
>  drivers/gpu/drm/i915/i915_drv.h       |    2 ++
>  drivers/gpu/drm/i915/i915_gpu_error.c |   22 ++++++++++++++++++++++
>  2 files changed, 24 insertions(+)
> 
> diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
> index 2c5f3bc..16629cc 100644
> --- a/drivers/gpu/drm/i915/i915_drv.h
> +++ b/drivers/gpu/drm/i915/i915_drv.h
> @@ -326,6 +326,8 @@ struct drm_i915_error_state {
>  	u32 *active_bo_count, *pinned_bo_count;
>  	struct intel_overlay_error_state *overlay;
>  	struct intel_display_error_state *display;
> +	int hangcheck_score[I915_NUM_RINGS];
> +	enum intel_ring_hangcheck_action hangcheck_action[I915_NUM_RINGS];
>  };
>  
>  struct intel_crtc_config;
> diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
> index aba9d74..7e92ba8 100644
> --- a/drivers/gpu/drm/i915/i915_gpu_error.c
> +++ b/drivers/gpu/drm/i915/i915_gpu_error.c
> @@ -213,6 +213,22 @@ static void print_error_buffers(struct drm_i915_error_state_buf *m,
>  	}
>  }
>  
> +static const char *hangcheck_action_to_str(enum intel_ring_hangcheck_action a)
> +{
> +	switch (a) {
> +	case HANGCHECK_WAIT:
> +		return "wait";
> +	case HANGCHECK_ACTIVE:
> +		return "active";
> +	case HANGCHECK_KICK:
> +		return "kick";
> +	case HANGCHECK_HUNG:
> +		return "hung";
> +	}
> +
> +	return "unknown";

Should be "none" or perhaps "idle".

> +}
> +
>  static void i915_ring_error_state(struct drm_i915_error_state_buf *m,
>  				  struct drm_device *dev,
>  				  struct drm_i915_error_state *error,
> @@ -253,6 +269,9 @@ static void i915_ring_error_state(struct drm_i915_error_state_buf *m,
>  	err_printf(m, "  waiting: %s\n", yesno(error->waiting[ring]));
>  	err_printf(m, "  ring->head: 0x%08x\n", error->cpu_ring_head[ring]);
>  	err_printf(m, "  ring->tail: 0x%08x\n", error->cpu_ring_tail[ring]);
> +	err_printf(m, "  hangcheck_action: %s\n",
> +		   hangcheck_action_to_str(error->hangcheck_action[ring]));
> +	err_printf(m, "  hangcheck_score: %d\n", error->hangcheck_score[ring]);
>  }

I would condense this to a single line
  hangcheck: wait [5]

So err_printf(m, "  hangcheck: %s [%d]\n", 
	      hangcheck_action_to_str(error->hangcheck_action[ring]),
	      error->hangcheck_score[ring]));
-Chris

-- 
Chris Wilson, Intel Open Source Technology Centre