[Intel-gfx] [PATCH 13/14] drm/i915/guc: Workaround the missing user interrupt after preemption

[Michał Winiarski]

With GuC, we're scheduling tasklet on USER_INTERRUPT - since some work
has completed, perhaps we're able to submit some more work. We're doing
similar thing for preemption - after preemption has completed, it's time
to schedule the tasklet and submit more work (since the engine is now
idle). Unfortunately, we can hit the scenarios where the preemption is
done, but the interrupt is nowhere to be seen. To work around the
problem, let's use a delayed work that's kicking the tasklet if
preemption is done, and queueing itself otherwise.

Testcase: igt/gem_exec_whisper/*-priority
Signed-off-by: Michał Winiarski <michal.winiarski at intel.com>
Cc: Chris Wilson <chris at chris-wilson.co.uk>
Cc: Jeff McGee <jeff.mcgee at intel.com>
Cc: John Harrison <john.c.harrison at intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen at linux.intel.com>
---
 drivers/gpu/drm/i915/i915_guc_submission.c | 36 +++++++++++++++++++++++++++++-
 drivers/gpu/drm/i915/intel_guc.h           |  1 +
 2 files changed, 36 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/i915_guc_submission.c b/drivers/gpu/drm/i915/i915_guc_submission.c
index a11ed4deff4b..dbb03b5481d2 100644
--- a/drivers/gpu/drm/i915/i915_guc_submission.c
+++ b/drivers/gpu/drm/i915/i915_guc_submission.c
@@ -574,6 +574,26 @@ static void flush_ggtt_writes(struct i915_vma *vma)
 		POSTING_READ_FW(GUC_STATUS);
 }
 
+#define GUC_LOST_IRQ_WORK_DELAY_MS 100
+static void guc_lost_user_interrupt(struct work_struct *work)
+{
+	struct guc_preempt_work *preempt_work =
+		container_of(to_delayed_work(work), typeof(*preempt_work),
+			     lost_irq_work);
+	struct intel_engine_cs *engine = preempt_work->engine;
+	struct intel_guc *guc = &engine->i915->guc;
+	struct guc_shared_ctx_data *data = guc->shared_data_vaddr;
+	struct guc_ctx_report *report = &data->preempt_ctx_report[engine->guc_id];
+
+	if (report->report_return_status == INTEL_GUC_REPORT_STATUS_COMPLETE)
+		tasklet_schedule(&engine->execlists.irq_tasklet);
+	else
+		queue_delayed_work(guc->preempt_wq,
+				   &preempt_work->lost_irq_work,
+				   msecs_to_jiffies(GUC_LOST_IRQ_WORK_DELAY_MS));
+
+}
+
 #define GUC_PREEMPT_FINISHED 0x1
 #define GUC_PREEMPT_BREADCRUMB_DWORDS 0x8
 static void inject_preempt_context(struct work_struct *work)
@@ -629,7 +649,13 @@ static void inject_preempt_context(struct work_struct *work)
 	if (WARN_ON(intel_guc_send(guc, data, ARRAY_SIZE(data)))) {
 		WRITE_ONCE(engine->execlists.preempt, false);
 		tasklet_schedule(&engine->execlists.irq_tasklet);
+
+		return;
 	}
+
+	queue_delayed_work(engine->i915->guc.preempt_wq,
+			   &preempt_work->lost_irq_work,
+			   msecs_to_jiffies(GUC_LOST_IRQ_WORK_DELAY_MS));
 }
 
 /*
@@ -647,6 +673,10 @@ static void wait_for_guc_preempt_report(struct intel_engine_cs *engine)
 	struct guc_shared_ctx_data *data = guc->shared_data_vaddr;
 	struct guc_ctx_report *report = &data->preempt_ctx_report[engine->guc_id];
 
+	/* If we landed here, it means that we didn't lose an interrupt, and
+	 * we can safely cancel the worker */
+	cancel_delayed_work(&guc->preempt_work[engine->id].lost_irq_work);
+
 	WARN_ON(wait_for_atomic(report->report_return_status ==
 				INTEL_GUC_REPORT_STATUS_COMPLETE,
 				GUC_PREEMPT_POSTPROCESS_DELAY_MS));
@@ -1229,6 +1259,8 @@ static int guc_preempt_work_create(struct intel_guc *guc)
 	for_each_engine(engine, dev_priv, id) {
 		guc->preempt_work[id].engine = engine;
 		INIT_WORK(&guc->preempt_work[id].work, inject_preempt_context);
+		INIT_DELAYED_WORK(&guc->preempt_work[id].lost_irq_work,
+				  guc_lost_user_interrupt);
 	}
 
 	return 0;
@@ -1240,8 +1272,10 @@ static void guc_preempt_work_destroy(struct intel_guc *guc)
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
 
-	for_each_engine(engine, dev_priv, id)
+	for_each_engine(engine, dev_priv, id) {
+		cancel_delayed_work_sync(&guc->preempt_work[id].lost_irq_work);
 		cancel_work_sync(&guc->preempt_work[id].work);
+	}
 
 	destroy_workqueue(guc->preempt_wq);
 }
diff --git a/drivers/gpu/drm/i915/intel_guc.h b/drivers/gpu/drm/i915/intel_guc.h
index 7273a6be7dc1..0c9338b5c4b8 100644
--- a/drivers/gpu/drm/i915/intel_guc.h
+++ b/drivers/gpu/drm/i915/intel_guc.h
@@ -49,6 +49,7 @@ enum i915_guc_client_id {
 struct guc_preempt_work {
 	struct intel_engine_cs *engine;
 	struct work_struct work;
+	struct delayed_work lost_irq_work;
 };
 
 struct intel_guc {
-- 
2.13.6