[Intel-gfx] [PATCH 6/9] drm/i915/tdr: Add engine reset count to error state

[Chris Wilson]

On Fri, Dec 16, 2016 at 12:20:07PM -0800, Michel Thierry wrote:
> From: Arun Siluvery <arun.siluvery at linux.intel.com>
> 
> Driver maintains count of how many times a given engine is reset, useful to
> capture this in error state also. It gives an idea of how engine is coping
> up with the workloads it is executing before this error state.

Also i915_engine_info().
 
> Cc: Chris Wilson <chris at chris-wilson.co.uk>
> Cc: Mika Kuoppala <mika.kuoppala at linux.intel.com>
> Signed-off-by: Arun Siluvery <arun.siluvery at linux.intel.com>
> Signed-off-by: Michel Thierry <michel.thierry at intel.com>
> ---
>  drivers/gpu/drm/i915/i915_drv.c       | 1 +
>  drivers/gpu/drm/i915/i915_drv.h       | 9 +++++++++
>  drivers/gpu/drm/i915/i915_gpu_error.c | 3 +++
>  3 files changed, 13 insertions(+)
> 
> diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
> index a034793bc246..1c706a082d60 100644
> --- a/drivers/gpu/drm/i915/i915_drv.c
> +++ b/drivers/gpu/drm/i915/i915_drv.c
> @@ -1877,6 +1877,7 @@ int i915_reset_engine(struct intel_engine_cs *engine)
>  	intel_engine_reset_cancel(engine);
>  	intel_execlists_restart_submission(engine);
>  
> +	dev_priv->gpu_error.engine_reset_count[engine->id]++;
>  	intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL);
>  	return 0;
>  
> diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
> index a97cc8f50ade..25183762ed94 100644
> --- a/drivers/gpu/drm/i915/i915_drv.h
> +++ b/drivers/gpu/drm/i915/i915_drv.h
> @@ -937,6 +937,7 @@ struct drm_i915_error_state {
>  		enum intel_engine_hangcheck_action hangcheck_action;
>  		struct i915_address_space *vm;
>  		int num_requests;
> +		u32 reset_count;
>  
>  		/* position of active request inside the ring */
>  		u32 rq_head, rq_post, rq_tail;
> @@ -1629,6 +1630,8 @@ struct i915_gpu_error {
>  #define I915_RESET_IN_PROGRESS	0
>  #define I915_WEDGED		(BITS_PER_LONG - 1)
>  
> +	unsigned long engine_reset_count[I915_NUM_ENGINES];
> +
>  	/**
>  	 * Waitqueue to signal when a hang is detected. Used to for waiters
>  	 * to release the struct_mutex for the reset to procede.
> @@ -3397,6 +3400,12 @@ static inline u32 i915_reset_count(struct i915_gpu_error *error)
>  	return READ_ONCE(error->reset_count);
>  }
>  
> +static inline u32 i915_engine_reset_count(struct i915_gpu_error *error,

That's a weird hodgepodge. We first think of intel_engine and are
confused, then we spot the reset. i915_reset_engine_count?

> +					  struct intel_engine_cs *engine)
> +{
> +	return READ_ONCE(error->engine_reset_count[engine->id]);
> +}
> +
>  void i915_gem_reset(struct drm_i915_private *dev_priv);
>  void i915_gem_set_wedged(struct drm_i915_private *dev_priv);
>  void i915_gem_reset_engine(struct intel_engine_cs *engine);
> diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
> index e16037d1b0ba..f168ad873521 100644
> --- a/drivers/gpu/drm/i915/i915_gpu_error.c
> +++ b/drivers/gpu/drm/i915/i915_gpu_error.c
> @@ -453,6 +453,7 @@ static void error_print_engine(struct drm_i915_error_state_buf *m,
>  	err_printf(m, "  hangcheck action timestamp: %lu, %u ms ago\n",
>  		   ee->hangcheck_timestamp,
>  		   jiffies_to_msecs(jiffies - ee->hangcheck_timestamp));
> +	err_printf(m, "  engine reset count: %u\n", ee->reset_count);
>  
>  	error_print_request(m, "  ELSP[0]: ", &ee->execlist[0]);
>  	error_print_request(m, "  ELSP[1]: ", &ee->execlist[1]);
> @@ -1170,6 +1171,8 @@ static void error_record_engine_registers(struct drm_i915_error_state *error,
>  	ee->hangcheck_timestamp = engine->hangcheck.action_timestamp;
>  	ee->hangcheck_action = engine->hangcheck.action;
>  	ee->hangcheck_stalled = engine->hangcheck.stalled;
> +	ee->reset_count = i915_engine_reset_count(&dev_priv->gpu_error,
> +						  engine);
>  
>  	if (USES_PPGTT(dev_priv)) {
>  		int i;
> -- 
> 2.11.0
> 

-- 
Chris Wilson, Intel Open Source Technology Centre