[Intel-gfx] [PATCH i-g-t 14/17] gem_wsim: Engine map load balance command

[Tvrtko Ursulin]

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

A new workload command for enabling a load balanced context map (aka
Virtual Engine). Example usage:

  1.B

This turns on load balancing for context one, assuming it has already been
configured with an engine map. Only DEFAULT engine specifier can be used
with load balanced engine maps.

Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin at intel.com>
---
 benchmarks/gem_wsim.c  | 62 +++++++++++++++++++++++++++++++++++++-----
 benchmarks/wsim/README | 18 ++++++++++++
 2 files changed, 73 insertions(+), 7 deletions(-)

diff --git a/benchmarks/gem_wsim.c b/benchmarks/gem_wsim.c
index b805ecd9a680..a772e2c588b5 100644
--- a/benchmarks/gem_wsim.c
+++ b/benchmarks/gem_wsim.c
@@ -82,7 +82,8 @@ enum w_type
 	SW_FENCE_SIGNAL,
 	CTX_PRIORITY,
 	PREEMPTION,
-	ENGINE_MAP
+	ENGINE_MAP,
+	LOAD_BALANCE,
 };
 
 struct deps
@@ -120,6 +121,7 @@ struct w_step
 			unsigned int engine_map_count;
 			enum intel_engine_id *engine_map;
 		};
+		bool load_balance;
 	};
 
 	/* Implementation details */
@@ -502,6 +504,25 @@ parse_workload(struct w_arg *arg, unsigned int flags, struct workload *app_w)
 
 				step.type = PREEMPTION;
 				goto add_step;
+			} else if (!strcmp(field, "B")) {
+				unsigned int nr = 0;
+				while ((field = strtok_r(fstart, ".", &fctx))) {
+					tmp = atoi(field);
+					check_arg(nr == 0 && tmp <= 0,
+						  "Invalid context at step %u!\n",
+						  nr_steps);
+					check_arg(nr > 0,
+						  "Invalid load balance format at step %u!\n",
+						  nr_steps);
+
+					step.context = tmp;
+					step.load_balance = true;
+
+					nr++;
+				}
+
+				step.type = LOAD_BALANCE;
+				goto add_step;
 			}
 
 			tmp = atoi(field);
@@ -828,7 +849,7 @@ find_engine_in_map(struct ctx *ctx, enum intel_engine_id engine)
 			return i + 1;
 	}
 
-	igt_assert(0);
+	igt_assert(ctx->wants_balance);
 	return 0;
 }
 
@@ -1039,12 +1060,19 @@ prepare_workload(unsigned int id, struct workload *wrk, unsigned int flags)
 				wrk->ctx_list[j].engine_map = w->engine_map;
 				wrk->ctx_list[j].engine_map_count =
 					w->engine_map_count;
+			} else if (w->type == LOAD_BALANCE) {
+				if (!wrk->ctx_list[j].engine_map) {
+					wsim_err("Load balancing needs an engine map!\n");
+					return 1;
+				}
+				wrk->ctx_list[j].wants_balance =
+					w->load_balance;
 			}
 		}
 
 		wrk->ctx_list[j].targets_instance = targets;
 		if (flags & I915)
-			wrk->ctx_list[j].wants_balance = balance;
+			wrk->ctx_list[j].wants_balance |= balance;
 	}
 
 	/*
@@ -1058,10 +1086,19 @@ prepare_workload(unsigned int id, struct workload *wrk, unsigned int flags)
 			if (w->type != BATCH)
 				continue;
 
-			if (wrk->ctx_list[j].engine_map && w->engine == VCS) {
+			if (wrk->ctx_list[j].engine_map &&
+			    !wrk->ctx_list[j].wants_balance &&
+			    (w->engine == VCS || w->engine == DEFAULT)) {
 				wsim_err("Batches targetting engine maps must use explicit engines!\n");
 				return -1;
 			}
+
+			if (wrk->ctx_list[j].engine_map &&
+			    wrk->ctx_list[j].wants_balance &&
+			    w->engine != DEFAULT) {
+				wsim_err("Batches targetting load balanced maps must not use explicit engines!\n");
+				return -1;
+			}
 		}
 	}
 
@@ -1090,7 +1127,8 @@ prepare_workload(unsigned int id, struct workload *wrk, unsigned int flags)
 				break;
 			}
 
-			if ((!ctx->engine_map && !ctx->targets_instance))
+			if ((!ctx->engine_map && !ctx->targets_instance) ||
+			    (ctx->engine_map && ctx->wants_balance))
 				args.flags |= I915_GEM_CONTEXT_SINGLE_TIMELINE;
 
 			drmIoctl(fd, DRM_IOCTL_I915_GEM_CONTEXT_CREATE, &args);
@@ -1154,8 +1192,17 @@ prepare_workload(unsigned int id, struct workload *wrk, unsigned int flags)
 				.size = sizeof(set_engines),
 				.value = to_user_pointer(&set_engines),
 			};
+			struct i915_context_engines_load_balance load_balance =
+				{ .base.name = I915_CONTEXT_ENGINES_EXT_LOAD_BALANCE,
+				  .engines_mask = -1,
+				};
 
-			set_engines.extensions = 0;
+			if (ctx->wants_balance) {
+				set_engines.extensions =
+					to_user_pointer(&load_balance);
+			} else {
+				set_engines.extensions = 0;
+			}
 
 			for (j = 0; j < ctx->engine_map_count; j++) {
 				set_engines.engines[j].class =
@@ -2134,7 +2181,8 @@ static void *run_workload(void *data)
 				}
 				continue;
 			} else if (w->type == PREEMPTION ||
-				   w->type == ENGINE_MAP) {
+				   w->type == ENGINE_MAP ||
+				   w->type == LOAD_BALANCE) {
 				continue;
 			}
 
diff --git a/benchmarks/wsim/README b/benchmarks/wsim/README
index 20e3e358cd2e..58dada675357 100644
--- a/benchmarks/wsim/README
+++ b/benchmarks/wsim/README
@@ -3,6 +3,7 @@ Workload descriptor format
 
 ctx.engine.duration_us.dependency.wait,...
 <uint>.<str>.<uint>[-<uint>].<int <= 0>[/<int <= 0>][...].<0|1>,...
+B.<uint>
 M.<uint>.<str>[|<str>]...
 P|X.<uint>.<int>
 d|p|s|t|q|a.<int>,...
@@ -24,6 +25,7 @@ Additional workload steps are also supported:
  'q' - Throttle to n max queue depth.
  'f' - Create a sync fence.
  'a' - Advance the previously created sync fence.
+ 'B' - Turn on context load balancing.
  'M' - Set up engine map.
  'P' - Context priority.
  'X' - Context preemption control.
@@ -176,3 +178,19 @@ Example:
 
 This sets up context 1 with an engine map containing VCS1 and VCS2 engine.
 Submission to this context can now only reference these two engines.
+
+Context load balancing
+----------------------
+
+Context load balancing (aka Virtual Engine) is an i915 feature where the driver
+will pick the best engine (most idle) to submit to given previously configured
+engine map.
+
+Example:
+
+  1.B
+
+This enables load balancing for context number one.
+
+Submissions to load balanced contexts are only allowed to use the DEFAULT engine
+specifier.
-- 
2.17.1