@@ -1946,8 +1946,15 @@ int intel_enable_engine_stats(struct intel_engine_cs *engine)
spin_lock_irqsave(&engine->stats.lock, flags);
if (engine->stats.enabled == ~0)
goto busy;
- if (engine->stats.enabled++ == 0)
+ if (engine->stats.enabled++ == 0) {
engine->stats.enabled_at = ktime_get();
+
+ /* XXX submission method oblivious */
+ engine->stats.active = port_count(&engine->execlists.port[1]);
+ engine->stats.active += port_count(&engine->execlists.port[0]);
+ if (engine->stats.active)
+ engine->stats.start = engine->stats.enabled_at;
+ }
spin_unlock_irqrestore(&engine->stats.lock, flags);
return 0;
We have a hole in our busy-stat accounting if the pmu is enabled during a long running batch, the pmu will not start accumulating busy-time until the next context switch. This then fails tests that are only sampling a single batch. Testcase: igt/perf_pmu/start-busy # To Be Written Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> --- We should also construct a queue of batches just to complicate things. spin1 = spin_batch; for (QLEN - 1) { rvsd1 = create_context; resubmit_spin1_batch; delete_context(rsvd1); } rsvd1 = create_context; spin2 = spin_batch() delete_context(rsvd1); start_pmu cancel_spin1 usleep(batch_duration) cancel_spin2 end_pmu assert(busy == batch_duration); --- drivers/gpu/drm/i915/intel_engine_cs.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-)