[Intel-gfx] [PATCH 16/18] drm/i915: Extend execution fence to support a callback

[Chris Wilson]

In the next patch, we will want to configure the slave request
depending on which physical engine the master request is executed on.
For this, we introduce a callback from the execute fence to convey this
information.

Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin at intel.com>
---
 drivers/gpu/drm/i915/i915_request.c | 84 +++++++++++++++++++++++++++--
 drivers/gpu/drm/i915/i915_request.h |  4 ++
 2 files changed, 83 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index e9c2094ab8ea..3faf06d2a9b0 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -38,6 +38,8 @@ struct execute_cb {
 	struct list_head link;
 	struct irq_work work;
 	struct i915_sw_fence *fence;
+	void (*hook)(struct i915_request *rq, struct dma_fence *signal);
+	struct i915_request *signal;
 };
 
 static struct i915_global_request {
@@ -342,6 +344,17 @@ static void irq_execute_cb(struct irq_work *wrk)
 	kmem_cache_free(global.slab_execute_cbs, cb);
 }
 
+static void irq_execute_cb_hook(struct irq_work *wrk)
+{
+	struct execute_cb *cb = container_of(wrk, typeof(*cb), work);
+
+	cb->hook(container_of(cb->fence, struct i915_request, submit),
+		 &cb->signal->fence);
+	i915_request_put(cb->signal);
+
+	irq_execute_cb(wrk);
+}
+
 static void __notify_execute_cb(struct i915_request *rq)
 {
 	struct execute_cb *cb;
@@ -368,14 +381,19 @@ static void __notify_execute_cb(struct i915_request *rq)
 }
 
 static int
-i915_request_await_execution(struct i915_request *rq,
-			     struct i915_request *signal,
-			     gfp_t gfp)
+__i915_request_await_execution(struct i915_request *rq,
+			       struct i915_request *signal,
+			       void (*hook)(struct i915_request *rq,
+					    struct dma_fence *signal),
+			       gfp_t gfp)
 {
 	struct execute_cb *cb;
 
-	if (i915_request_is_active(signal))
+	if (i915_request_is_active(signal)) {
+		if (hook)
+			hook(rq, &signal->fence);
 		return 0;
+	}
 
 	cb = kmem_cache_alloc(global.slab_execute_cbs, gfp);
 	if (!cb)
@@ -385,8 +403,18 @@ i915_request_await_execution(struct i915_request *rq,
 	i915_sw_fence_await(cb->fence);
 	init_irq_work(&cb->work, irq_execute_cb);
 
+	if (hook) {
+		cb->hook = hook;
+		cb->signal = i915_request_get(signal);
+		cb->work.func = irq_execute_cb_hook;
+	}
+
 	spin_lock_irq(&signal->lock);
 	if (i915_request_is_active(signal)) {
+		if (hook) {
+			hook(rq, &signal->fence);
+			i915_request_put(signal);
+		}
 		i915_sw_fence_complete(cb->fence);
 		kmem_cache_free(global.slab_execute_cbs, cb);
 	} else {
@@ -789,7 +817,7 @@ emit_semaphore_wait(struct i915_request *to,
 		return err;
 
 	/* Only submit our spinner after the signaler is running! */
-	err = i915_request_await_execution(to, from, gfp);
+	err = __i915_request_await_execution(to, from, NULL, gfp);
 	if (err)
 		return err;
 
@@ -909,6 +937,52 @@ i915_request_await_dma_fence(struct i915_request *rq, struct dma_fence *fence)
 	return 0;
 }
 
+int
+i915_request_await_execution(struct i915_request *rq,
+			     struct dma_fence *fence,
+			     void (*hook)(struct i915_request *rq,
+					  struct dma_fence *signal))
+{
+	struct dma_fence **child = &fence;
+	unsigned int nchild = 1;
+	int ret;
+
+	if (dma_fence_is_array(fence)) {
+		struct dma_fence_array *array = to_dma_fence_array(fence);
+
+		/* XXX Error for signal-on-any fence arrays */
+
+		child = array->fences;
+		nchild = array->num_fences;
+		GEM_BUG_ON(!nchild);
+	}
+
+	do {
+		fence = *child++;
+		if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags))
+			continue;
+
+		/*
+		 * We don't squash repeated fence dependencies here as we
+		 * want to run our callback in all cases.
+		 */
+
+		if (dma_fence_is_i915(fence))
+			ret = __i915_request_await_execution(rq,
+							     to_request(fence),
+							     hook,
+							     I915_FENCE_GFP);
+		else
+			ret = i915_sw_fence_await_dma_fence(&rq->submit, fence,
+							    I915_FENCE_TIMEOUT,
+							    GFP_KERNEL);
+		if (ret < 0)
+			return ret;
+	} while (--nchild);
+
+	return 0;
+}
+
 /**
  * i915_request_await_object - set this request to (async) wait upon a bo
  * @to: request we are wishing to use
diff --git a/drivers/gpu/drm/i915/i915_request.h b/drivers/gpu/drm/i915/i915_request.h
index cd6c130964cd..d4f6b2940130 100644
--- a/drivers/gpu/drm/i915/i915_request.h
+++ b/drivers/gpu/drm/i915/i915_request.h
@@ -265,6 +265,10 @@ int i915_request_await_object(struct i915_request *to,
 			      bool write);
 int i915_request_await_dma_fence(struct i915_request *rq,
 				 struct dma_fence *fence);
+int i915_request_await_execution(struct i915_request *rq,
+				 struct dma_fence *fence,
+				 void (*hook)(struct i915_request *rq,
+					      struct dma_fence *signal));
 
 void i915_request_add(struct i915_request *rq);
 
-- 
2.20.1