[Intel-gfx] [PATCH 23/25] drm/i915: Prioritise non-busywait semaphore workloads

[Chris Wilson]

We don't want to busywait on the GPU if we have other work to do. If we
give non-busywaiting workloads higher (initial) priority than workloads
that require a busywait, we will prioritise work that is ready to run
immediately. We then also have to be careful that we don't give earlier
semaphores an accidental boost because later work doesn't wait on other
rings, hence we keep a history of semaphore usage of the dependency chain.

Testcase: igt/gem_exec_schedule/semaphore
Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/i915_request.c   | 16 ++++++++++++++++
 drivers/gpu/drm/i915/i915_scheduler.c |  5 +++++
 drivers/gpu/drm/i915/i915_scheduler.h |  9 ++++++---
 drivers/gpu/drm/i915/intel_lrc.c      |  2 +-
 4 files changed, 28 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index 439816b48eb6..8279f7b04194 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -811,6 +811,7 @@ emit_semaphore_wait(struct i915_request *to,
 	*cs++ = 0;
 
 	intel_ring_advance(to, cs);
+	to->sched.semaphore |= I915_SCHED_HAS_SEMAPHORE;
 	return 0;
 }
 
@@ -1081,6 +1082,21 @@ void i915_request_add(struct i915_request *request)
 	if (engine->schedule) {
 		struct i915_sched_attr attr = request->gem_context->sched;
 
+		/*
+		 * Boost actual workloads past semaphores!
+		 *
+		 * With semaphores we spin on one engine waiting for another,
+		 * simply to reduce the latency of starting our work when
+		 * the signaler completes. However, if there is any other
+		 * work that we could be doing on this engine instead, that
+		 * is better utilisation and will reduce the overall duration
+		 * of the current work. To avoid PI boosting a semaphore
+		 * far in the distance past over useful work, we keep a history
+		 * of any semaphore use along our dependency chain.
+		 */
+		if (!request->sched.semaphore)
+			attr.priority |= I915_PRIORITY_NOSEMAPHORE;
+
 		/*
 		 * Boost priorities to new clients (new request flows).
 		 *
diff --git a/drivers/gpu/drm/i915/i915_scheduler.c b/drivers/gpu/drm/i915/i915_scheduler.c
index 50018ad30233..fd684b9ed108 100644
--- a/drivers/gpu/drm/i915/i915_scheduler.c
+++ b/drivers/gpu/drm/i915/i915_scheduler.c
@@ -39,6 +39,7 @@ void i915_sched_node_init(struct i915_sched_node *node)
 	INIT_LIST_HEAD(&node->waiters_list);
 	INIT_LIST_HEAD(&node->link);
 	node->attr.priority = I915_PRIORITY_INVALID;
+	node->semaphore = 0;
 }
 
 static struct i915_dependency *
@@ -69,6 +70,10 @@ bool __i915_sched_node_add_dependency(struct i915_sched_node *node,
 		dep->signaler = signal;
 		dep->flags = flags;
 
+		/* Keep track of whether anyone on this chain has a semaphore */
+		if (signal->semaphore && !node_started(signal))
+			node->semaphore |= signal->semaphore << 1;
+
 		ret = true;
 	}
 
diff --git a/drivers/gpu/drm/i915/i915_scheduler.h b/drivers/gpu/drm/i915/i915_scheduler.h
index 5196ce07b6c2..24c2c027fd2c 100644
--- a/drivers/gpu/drm/i915/i915_scheduler.h
+++ b/drivers/gpu/drm/i915/i915_scheduler.h
@@ -24,14 +24,15 @@ enum {
 	I915_PRIORITY_INVALID = INT_MIN
 };
 
-#define I915_USER_PRIORITY_SHIFT 2
+#define I915_USER_PRIORITY_SHIFT 3
 #define I915_USER_PRIORITY(x) ((x) << I915_USER_PRIORITY_SHIFT)
 
 #define I915_PRIORITY_COUNT BIT(I915_USER_PRIORITY_SHIFT)
 #define I915_PRIORITY_MASK (I915_PRIORITY_COUNT - 1)
 
-#define I915_PRIORITY_WAIT	((u8)BIT(0))
-#define I915_PRIORITY_NEWCLIENT	((u8)BIT(1))
+#define I915_PRIORITY_WAIT		((u8)BIT(0))
+#define I915_PRIORITY_NEWCLIENT		((u8)BIT(1))
+#define I915_PRIORITY_NOSEMAPHORE	((u8)BIT(2))
 
 #define __NO_PREEMPTION (I915_PRIORITY_WAIT)
 
@@ -74,6 +75,8 @@ struct i915_sched_node {
 	struct list_head waiters_list; /* those after us, they depend upon us */
 	struct list_head link;
 	struct i915_sched_attr attr;
+	unsigned long semaphore;
+#define I915_SCHED_HAS_SEMAPHORE	BIT(0)
 };
 
 struct i915_dependency {
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 75881162235d..5e9cff19a6b6 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -164,7 +164,7 @@
 #define WA_TAIL_DWORDS 2
 #define WA_TAIL_BYTES (sizeof(u32) * WA_TAIL_DWORDS)
 
-#define ACTIVE_PRIORITY (I915_PRIORITY_NEWCLIENT)
+#define ACTIVE_PRIORITY (I915_PRIORITY_NEWCLIENT | I915_PRIORITY_NOSEMAPHORE)
 
 static int execlists_context_deferred_alloc(struct i915_gem_context *ctx,
 					    struct intel_engine_cs *engine,
-- 
2.20.1