drm/i915/gt: Drop atomic for engine->fw_active tracking

Since schedule-in/out is now entirely serialised by the tasklet bitlock,
we do not need to worry about concurrent in/out operations and so reduce
the atomic operations to plain instructions.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Andi Shyti <andi.shyti@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20210115142331.24458-1-chris@chris-wilson.co.uk

drivers/gpu/drm/i915/gt/intel_engine_cs.c

@@ -1676,7 +1676,7 @@ void intel_engine_dump(struct intel_engine_cs *engine,
 			   ktime_to_ms(intel_engine_get_busy_time(engine,
 								  &dummy)));
 	drm_printf(m, "\tForcewake: %x domains, %d active\n",
-		   engine->fw_domain, atomic_read(&engine->fw_active));
+		   engine->fw_domain, READ_ONCE(engine->fw_active));
 
 	rcu_read_lock();
 	rq = READ_ONCE(engine->heartbeat.systole);

drivers/gpu/drm/i915/gt/intel_engine_types.h

@@ -319,7 +319,7 @@ struct intel_engine_cs {
 	 * as possible.
 	 */
 	enum forcewake_domains fw_domain;
-	atomic_t fw_active;
+	unsigned int fw_active;
 
 	unsigned long context_tag;
 

drivers/gpu/drm/i915/gt/intel_execlists_submission.c

@@ -538,7 +538,7 @@ __execlists_schedule_in(struct i915_request *rq)
 	ce->lrc.ccid |= engine->execlists.ccid;
 
 	__intel_gt_pm_get(engine->gt);
-	if (engine->fw_domain && !atomic_fetch_inc(&engine->fw_active))
+	if (engine->fw_domain && !engine->fw_active++)
 		intel_uncore_forcewake_get(engine->uncore, engine->fw_domain);
 	execlists_context_status_change(rq, INTEL_CONTEXT_SCHEDULE_IN);
 	intel_engine_context_in(engine);
@@ -645,7 +645,7 @@ static void __execlists_schedule_out(struct i915_request * const rq,
 	lrc_update_runtime(ce);
 	intel_engine_context_out(engine);
 	execlists_context_status_change(rq, INTEL_CONTEXT_SCHEDULE_OUT);
-	if (engine->fw_domain && !atomic_dec_return(&engine->fw_active))
+	if (engine->fw_domain && !--engine->fw_active)
 		intel_uncore_forcewake_put(engine->uncore, engine->fw_domain);
 	intel_gt_pm_put_async(engine->gt);