[Intel-gfx] [PATCH i-g-t 6/7] gem_wsim: Per context preemption point control

[Tvrtko Ursulin]

From: Tvrtko Ursulin <tvrtko.ursulin at intel.com>

Allow workloads to specify frequency of preemption points per context.

New workload command ('X') is added to allow this.

Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin at intel.com>
---
 benchmarks/gem_wsim.c  | 84 ++++++++++++++++++++++++++++++++++++++++--
 benchmarks/wsim/README | 18 ++++++++-
 2 files changed, 98 insertions(+), 4 deletions(-)

diff --git a/benchmarks/gem_wsim.c b/benchmarks/gem_wsim.c
index f60c086a3f1e..fd268b3ab456 100644
--- a/benchmarks/gem_wsim.c
+++ b/benchmarks/gem_wsim.c
@@ -83,7 +83,8 @@ enum w_type
 	QD_THROTTLE,
 	SW_FENCE,
 	SW_FENCE_SIGNAL,
-	CTX_PRIORITY
+	CTX_PRIORITY,
+	PREEMPTION
 };
 
 struct deps
@@ -122,6 +123,7 @@ struct w_step
 	unsigned int idx;
 	struct igt_list rq_link;
 	unsigned int request;
+	unsigned int preempt_us;
 
 	struct drm_i915_gem_execbuffer2 eb;
 	struct drm_i915_gem_exec_object2 *obj;
@@ -441,6 +443,42 @@ parse_workload(struct w_arg *arg, unsigned int flags, struct workload *app_w)
 			} else if (!strcmp(field, "f")) {
 				step.type = SW_FENCE;
 				goto add_step;
+			} else if (!strcmp(field, "X")) {
+				unsigned int nr = 0;
+				while ((field = strtok_r(fstart, ".", &fctx)) !=
+				    NULL) {
+					tmp = atoi(field);
+					if (tmp <= 0 && nr == 0) {
+						if (verbose)
+							fprintf(stderr,
+								"Invalid context at step %u!\n",
+								nr_steps);
+						return NULL;
+					} else if (tmp < 0 && nr == 1) {
+						if (verbose)
+							fprintf(stderr,
+								"Invalid preemption period at step %u!\n",
+								nr_steps);
+						return NULL;
+					}
+
+					if (nr == 0) {
+						step.context = tmp;
+					} else if (nr == 1) {
+						step.period = tmp;
+					} else {
+						if (verbose)
+							fprintf(stderr,
+								"Invalid preemption format at step %u!\n",
+								nr_steps);
+						return NULL;
+					}
+
+					nr++;
+				}
+
+				step.type = PREEMPTION;
+				goto add_step;
 			}
 
 			tmp = atoi(field);
@@ -686,11 +724,14 @@ static unsigned long get_bb_sz(unsigned int duration)
 static void
 init_bb(struct w_step *w, unsigned int flags)
 {
-	/* Preemption point every 100us. */
-	const unsigned int arb_period = get_bb_sz(100) / sizeof(uint32_t);
+	const unsigned int arb_period =
+			get_bb_sz(w->preempt_us) / sizeof(uint32_t);
 	unsigned int i;
 	uint32_t *ptr;
 
+	if (!arb_period)
+		return;
+
 	gem_set_domain(fd, w->bb_handle,
 		       I915_GEM_DOMAIN_WC, I915_GEM_DOMAIN_WC);
 
@@ -965,6 +1006,41 @@ prepare_workload(unsigned int id, struct workload *wrk, unsigned int flags)
 		}
 	}
 
+	/* Record default preemption. */
+	for (i = 0, w = wrk->steps; i < wrk->nr_steps; i++, w++) {
+		if (w->type == BATCH)
+			w->preempt_us = 100;
+	}
+
+	/*
+	 * Scan for contexts with modified preemption config and record their
+	 * preemption period for the following steps belonging to the same
+	 * context.
+	 */
+	for (i = 0, w = wrk->steps; i < wrk->nr_steps; i++, w++) {
+		struct w_step *w2;
+		int j;
+
+		if (w->type != PREEMPTION)
+			continue;
+
+		for (j = i + 1; j < wrk->nr_steps; j++) {
+			w2 = &wrk->steps[j];
+
+			if (w2->context != w->context)
+				continue;
+			else if (w2->type == PREEMPTION)
+				break;
+			else if (w2->type != BATCH)
+				continue;
+
+			w2->preempt_us = w->period;
+		}
+	}
+
+	/*
+	 * Allocate batch buffers.
+	 */
 	for (i = 0, w = wrk->steps; i < wrk->nr_steps; i++, w++) {
 		unsigned int _flags = flags;
 		enum intel_engine_id engine = w->engine;
@@ -1869,6 +1945,8 @@ static void *run_workload(void *data)
 								    w->priority;
 				}
 				continue;
+			} else if (w->type == PREEMPTION) {
+				continue;
 			}
 
 			if (do_sleep || w->type == PERIOD) {
diff --git a/benchmarks/wsim/README b/benchmarks/wsim/README
index fd9bff3401af..205cd6c93afb 100644
--- a/benchmarks/wsim/README
+++ b/benchmarks/wsim/README
@@ -3,7 +3,7 @@ Workload descriptor format
 
 ctx.engine.duration_us.dependency.wait,...
 <uint>.<str>.<uint>[-<uint>].<int <= 0>[/<int <= 0>][...].<0|1>,...
-P.<uint>.<int>
+P|X.<uint>.<int>
 d|p|s|t|q|a.<int>,...
 f
 
@@ -24,6 +24,7 @@ Additional workload steps are also supported:
  'f' - Create a sync fence.
  'a' - Advance the previously created sync fence.
  'P' - Context priority.
+ 'X' - Context preemption control.
 
 Engine ids: RCS, BCS, VCS, VCS1, VCS2, VECS
 
@@ -128,3 +129,18 @@ is submitted against it which depends on the batch from context 1.
 Context priority command is executed at workload runtime and is valid until
 overriden by another (optional) same context priority change. Actual driver
 ioctls are executed only if the priority level has changed for the context.
+
+Context preemption control
+--------------------------
+
+  X.1.0
+  1.RCS.1000.0.0
+  X.1.500
+  1.RCS.1000.0.0
+
+Context 1 is marked as non-preemptable batches and a batch is sent against 1.
+The same context is then marked to have batches which can be preempted every
+500us and another batch is submitted.
+
+Same as with context priority, context preemption commands are valid until
+optionally overriden by another preemption control change on the same context.
-- 
2.17.1