drm/i915: Update I915_GEM_BUSY IOCTL to understand composite fences

Parallel submission create composite fences (dma_fence_array) for excl /
shared slots in objects. The I915_GEM_BUSY IOCTL checks these slots to
determine the busyness of the object. Prior to patch it only check if
the fence in the slot was a i915_request. Update the check to understand
composite fences and correctly report the busyness.

v2:
 (Tvrtko)
  - Remove duplicate BUILD_BUG_ON

Reviewed-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20211014172005.27155-24-matthew.brost@intel.com

drivers/gpu/drm/i915/gem/i915_gem_busy.c

@@ -4,6 +4,8 @@
  * Copyright © 2014-2016 Intel Corporation
  */
 
+#include <linux/dma-fence-array.h>
+
 #include "gt/intel_engine.h"
 
 #include "i915_gem_ioctls.h"
@@ -36,7 +38,7 @@ static __always_inline u32 __busy_write_id(u16 id)
 }
 
 static __always_inline unsigned int
-__busy_set_if_active(const struct dma_fence *fence, u32 (*flag)(u16 id))
+__busy_set_if_active(struct dma_fence *fence, u32 (*flag)(u16 id))
 {
 	const struct i915_request *rq;
 
@@ -46,29 +48,60 @@ __busy_set_if_active(const struct dma_fence *fence, u32 (*flag)(u16 id))
 	 * to eventually flush us, but to minimise latency just ask the
 	 * hardware.
 	 *
-	 * Note we only report on the status of native fences.
+	 * Note we only report on the status of native fences and we currently
+	 * have two native fences:
+	 *
+	 * 1. A composite fence (dma_fence_array) constructed of i915 requests
+	 * created during a parallel submission. In this case we deconstruct the
+	 * composite fence into individual i915 requests and check the status of
+	 * each request.
+	 *
+	 * 2. A single i915 request.
 	 */
-	if (!dma_fence_is_i915(fence))
-		return 0;
+	if (dma_fence_is_array(fence)) {
+		struct dma_fence_array *array = to_dma_fence_array(fence);
+		struct dma_fence **child = array->fences;
+		unsigned int nchild = array->num_fences;
 
-	/* opencode to_request() in order to avoid const warnings */
-	rq = container_of(fence, const struct i915_request, fence);
-	if (i915_request_completed(rq))
-		return 0;
+		do {
+			struct dma_fence *current_fence = *child++;
 
-	/* Beware type-expansion follies! */
-	BUILD_BUG_ON(!typecheck(u16, rq->engine->uabi_class));
-	return flag(rq->engine->uabi_class);
+			/* Not an i915 fence, can't be busy per above */
+			if (!dma_fence_is_i915(current_fence) ||
+			    !test_bit(I915_FENCE_FLAG_COMPOSITE,
+				      &current_fence->flags)) {
+				return 0;
+			}
+
+			rq = to_request(current_fence);
+			if (!i915_request_completed(rq))
+				return flag(rq->engine->uabi_class);
+		} while (--nchild);
+
+		/* All requests in array complete, not busy */
+		return 0;
+	} else {
+		if (!dma_fence_is_i915(fence))
+			return 0;
+
+		rq = to_request(fence);
+		if (i915_request_completed(rq))
+			return 0;
+
+		/* Beware type-expansion follies! */
+		BUILD_BUG_ON(!typecheck(u16, rq->engine->uabi_class));
+		return flag(rq->engine->uabi_class);
+	}
 }
 
 static __always_inline unsigned int
-busy_check_reader(const struct dma_fence *fence)
+busy_check_reader(struct dma_fence *fence)
 {
 	return __busy_set_if_active(fence, __busy_read_flag);
 }
 
 static __always_inline unsigned int
-busy_check_writer(const struct dma_fence *fence)
+busy_check_writer(struct dma_fence *fence)
 {
 	if (!fence)
 		return 0;

drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c

@@ -2997,8 +2997,11 @@ eb_composite_fence_create(struct i915_execbuffer *eb, int out_fence_fd)
 	if (!fences)
 		return ERR_PTR(-ENOMEM);
 
-	for_each_batch_create_order(eb, i)
+	for_each_batch_create_order(eb, i) {
 		fences[i] = &eb->requests[i]->fence;
+		__set_bit(I915_FENCE_FLAG_COMPOSITE,
+			  &eb->requests[i]->fence.flags);
+	}
 
 	fence_array = dma_fence_array_create(eb->num_batches,
 					     fences,

drivers/gpu/drm/i915/i915_request.h

@@ -156,6 +156,12 @@ enum {
 	 * submission / relationship encoutered an error.
 	 */
 	I915_FENCE_FLAG_SKIP_PARALLEL,
+
+	/*
+	 * I915_FENCE_FLAG_COMPOSITE - Indicates fence is part of a composite
+	 * fence (dma_fence_array) and i915 generated for parallel submission.
+	 */
+	I915_FENCE_FLAG_COMPOSITE,
 };
 
 /**