[Intel-gfx] [PATCH v2] drm/i915: Limit C-states when waiting for the active request

[Chris Wilson]

If we are waiting for the currently executing request, we have a good
idea that it will be completed in the very near future and so want to
cap the CPU_DMA_LATENCY to ensure that we wake up the client quickly.

v2: Not allowed to block in kmalloc after setting TASK_INTERRUPTIBLE.

Testcase: igt/gem_sync/store-default
Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin at linux.intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen at linux.intel.com>
Cc: Eero Tamminen <eero.t.tamminen at intel.com>
Cc: Francisco Jerez <currojerez at riseup.net>
---
 drivers/gpu/drm/i915/i915_request.c | 29 +++++++++++++++++++++++++++++
 1 file changed, 29 insertions(+)

diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index 5c2c93cbab12..de907150664e 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -1258,6 +1258,19 @@ static bool __i915_wait_request_check_and_reset(struct i915_request *request)
 	return true;
 }
 
+struct pm_qos {
+	struct pm_qos_request req;
+	struct work_struct work;
+};
+
+static void pm_qos_del(struct work_struct *work)
+{
+	struct pm_qos *pm_qos = container_of(work, typeof(*pm_qos), work);
+
+	pm_qos_remove_request(&pm_qos->req);
+	kfree(pm_qos);
+}
+
 /**
  * i915_request_wait - wait until execution of request has finished
  * @rq: the request to wait upon
@@ -1286,6 +1299,7 @@ long i915_request_wait(struct i915_request *rq,
 	wait_queue_head_t *errq = &rq->i915->gpu_error.wait_queue;
 	DEFINE_WAIT_FUNC(reset, default_wake_function);
 	DEFINE_WAIT_FUNC(exec, default_wake_function);
+	struct pm_qos *pm_qos = NULL;
 	struct intel_wait wait;
 
 	might_sleep();
@@ -1363,6 +1377,19 @@ long i915_request_wait(struct i915_request *rq,
 			break;
 		}
 
+		if (!pm_qos &&
+		    i915_seqno_passed(intel_engine_get_seqno(rq->engine),
+				      wait.seqno - 1)) {
+			pm_qos = kzalloc(sizeof(*pm_qos),
+					 GFP_NOWAIT | __GFP_NOWARN);
+			if (pm_qos) {
+				pm_qos_add_request(&pm_qos->req,
+						   PM_QOS_CPU_DMA_LATENCY,
+						   50);
+				INIT_WORK(&pm_qos->work, pm_qos_del);
+			}
+		}
+
 		timeout = io_schedule_timeout(timeout);
 
 		if (intel_wait_complete(&wait) &&
@@ -1412,6 +1439,8 @@ long i915_request_wait(struct i915_request *rq,
 	if (flags & I915_WAIT_LOCKED)
 		remove_wait_queue(errq, &reset);
 	remove_wait_queue(&rq->execute, &exec);
+	if (pm_qos)
+		schedule_work(&pm_qos->work);
 	trace_i915_request_wait_end(rq);
 
 	return timeout;
-- 
2.18.0