[Intel-gfx] [PATCH 3/3] drm/i915: Move find_active_request() to the engine

[Tvrtko Ursulin]

On 05/03/2019 18:03, Chris Wilson wrote:
> To find the active request, we need only search along the individual
> engine for the right request. This does not require touching any global
> GEM state, so move it into the engine compartment.
> 
> Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
> ---
>   drivers/gpu/drm/i915/i915_drv.h         |  3 --
>   drivers/gpu/drm/i915/i915_gem.c         | 45 -----------------------
>   drivers/gpu/drm/i915/i915_gpu_error.c   |  2 +-
>   drivers/gpu/drm/i915/intel_engine_cs.c  | 47 ++++++++++++++++++++++++-
>   drivers/gpu/drm/i915/intel_ringbuffer.h |  3 ++
>   5 files changed, 50 insertions(+), 50 deletions(-)
> 
> diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
> index 08ead854ac2d..ff039750069d 100644
> --- a/drivers/gpu/drm/i915/i915_drv.h
> +++ b/drivers/gpu/drm/i915/i915_drv.h
> @@ -2996,9 +2996,6 @@ void i915_gem_track_fb(struct drm_i915_gem_object *old,
>   
>   int __must_check i915_gem_set_global_seqno(struct drm_device *dev, u32 seqno);
>   
> -struct i915_request *
> -i915_gem_find_active_request(struct intel_engine_cs *engine);
> -
>   static inline bool __i915_wedged(struct i915_gpu_error *error)
>   {
>   	return unlikely(test_bit(I915_WEDGED, &error->flags));
> diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
> index 69413f99ed04..c67369bd145b 100644
> --- a/drivers/gpu/drm/i915/i915_gem.c
> +++ b/drivers/gpu/drm/i915/i915_gem.c
> @@ -2803,51 +2803,6 @@ i915_gem_object_pwrite_gtt(struct drm_i915_gem_object *obj,
>   	return 0;
>   }
>   
> -static bool match_ring(struct i915_request *rq)
> -{
> -	struct drm_i915_private *dev_priv = rq->i915;
> -	u32 ring = I915_READ(RING_START(rq->engine->mmio_base));
> -
> -	return ring == i915_ggtt_offset(rq->ring->vma);
> -}
> -
> -struct i915_request *
> -i915_gem_find_active_request(struct intel_engine_cs *engine)
> -{
> -	struct i915_request *request, *active = NULL;
> -	unsigned long flags;
> -
> -	/*
> -	 * We are called by the error capture, reset and to dump engine
> -	 * state at random points in time. In particular, note that neither is
> -	 * crucially ordered with an interrupt. After a hang, the GPU is dead
> -	 * and we assume that no more writes can happen (we waited long enough
> -	 * for all writes that were in transaction to be flushed) - adding an
> -	 * extra delay for a recent interrupt is pointless. Hence, we do
> -	 * not need an engine->irq_seqno_barrier() before the seqno reads.
> -	 * At all other times, we must assume the GPU is still running, but
> -	 * we only care about the snapshot of this moment.
> -	 */
> -	spin_lock_irqsave(&engine->timeline.lock, flags);
> -	list_for_each_entry(request, &engine->timeline.requests, link) {
> -		if (i915_request_completed(request))
> -			continue;
> -
> -		if (!i915_request_started(request))
> -			break;
> -
> -		/* More than one preemptible request may match! */
> -		if (!match_ring(request))
> -			break;
> -
> -		active = request;
> -		break;
> -	}
> -	spin_unlock_irqrestore(&engine->timeline.lock, flags);
> -
> -	return active;
> -}
> -
>   static void
>   i915_gem_retire_work_handler(struct work_struct *work)
>   {
> diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
> index 5f1cdbc9eb5d..3d8020888604 100644
> --- a/drivers/gpu/drm/i915/i915_gpu_error.c
> +++ b/drivers/gpu/drm/i915/i915_gpu_error.c
> @@ -1411,7 +1411,7 @@ static void gem_record_rings(struct i915_gpu_state *error)
>   		error_record_engine_registers(error, engine, ee);
>   		error_record_engine_execlists(engine, ee);
>   
> -		request = i915_gem_find_active_request(engine);
> +		request = intel_engine_find_active_request(engine);
>   		if (request) {
>   			struct i915_gem_context *ctx = request->gem_context;
>   			struct intel_ring *ring;
> diff --git a/drivers/gpu/drm/i915/intel_engine_cs.c b/drivers/gpu/drm/i915/intel_engine_cs.c
> index 62a2bbbbcc64..555a4590fa23 100644
> --- a/drivers/gpu/drm/i915/intel_engine_cs.c
> +++ b/drivers/gpu/drm/i915/intel_engine_cs.c
> @@ -1545,7 +1545,7 @@ void intel_engine_dump(struct intel_engine_cs *engine,
>   	if (&rq->link != &engine->timeline.requests)
>   		print_request(m, rq, "\t\tlast   ");
>   
> -	rq = i915_gem_find_active_request(engine);
> +	rq = intel_engine_find_active_request(engine);
>   	if (rq) {
>   		print_request(m, rq, "\t\tactive ");
>   
> @@ -1712,6 +1712,51 @@ void intel_disable_engine_stats(struct intel_engine_cs *engine)
>   	write_sequnlock_irqrestore(&engine->stats.lock, flags);
>   }
>   
> +static bool match_ring(struct i915_request *rq)
> +{
> +	struct drm_i915_private *dev_priv = rq->i915;
> +	u32 ring = I915_READ(RING_START(rq->engine->mmio_base));
> +
> +	return ring == i915_ggtt_offset(rq->ring->vma);
> +}
> +
> +struct i915_request *
> +intel_engine_find_active_request(struct intel_engine_cs *engine)
> +{
> +	struct i915_request *request, *active = NULL;
> +	unsigned long flags;
> +
> +	/*
> +	 * We are called by the error capture, reset and to dump engine
> +	 * state at random points in time. In particular, note that neither is
> +	 * crucially ordered with an interrupt. After a hang, the GPU is dead
> +	 * and we assume that no more writes can happen (we waited long enough
> +	 * for all writes that were in transaction to be flushed) - adding an
> +	 * extra delay for a recent interrupt is pointless. Hence, we do
> +	 * not need an engine->irq_seqno_barrier() before the seqno reads.
> +	 * At all other times, we must assume the GPU is still running, but
> +	 * we only care about the snapshot of this moment.
> +	 */
> +	spin_lock_irqsave(&engine->timeline.lock, flags);
> +	list_for_each_entry(request, &engine->timeline.requests, link) {
> +		if (i915_request_completed(request))
> +			continue;
> +
> +		if (!i915_request_started(request))
> +			break;
> +
> +		/* More than one preemptible request may match! */
> +		if (!match_ring(request))
> +			break;
> +
> +		active = request;
> +		break;
> +	}
> +	spin_unlock_irqrestore(&engine->timeline.lock, flags);
> +
> +	return active;
> +}
> +
>   #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
>   #include "selftests/mock_engine.c"
>   #include "selftests/intel_engine_cs.c"
> diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
> index 18e865ff6637..84b7047e2df5 100644
> --- a/drivers/gpu/drm/i915/intel_ringbuffer.h
> +++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
> @@ -1014,6 +1014,9 @@ void intel_disable_engine_stats(struct intel_engine_cs *engine);
>   
>   ktime_t intel_engine_get_busy_time(struct intel_engine_cs *engine);
>   
> +struct i915_request *
> +intel_engine_find_active_request(struct intel_engine_cs *engine);
> +
>   #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
>   
>   static inline bool inject_preempt_hang(struct intel_engine_execlists *execlists)
> 

intel_engine.h in 3...2...1.. ;)

Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin at intel.com>

Regards,

Tvrtko