drm/msm/gpu: Wait for idle before suspending

System suspend uses pm_runtime_force_suspend(), which cheekily bypasses
the runpm reference counts.  This doesn't actually work so well when the
GPU is active.  So add a reasonable delay waiting for the GPU to become
idle.

Alternatively we could just return -EBUSY in this case, but that has the
disadvantage of causing system suspend to fail.

v2: s/ret/remaining [sboyd], and switch to using active_submits count
    to ensure we aren't racing with submit cleanup (and devfreq idle
    work getting scheduled, etc)
v3: fix inverted logic

Signed-off-by: Rob Clark <robdclark@chromium.org>
Reviewed-by: Bjorn Andersson <bjorn.andersson@linaro.org>
Reviewed-by: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
Link: https://lore.kernel.org/r/20220108180913.814448-2-robdclark@gmail.com
Signed-off-by: Rob Clark <robdclark@chromium.org>

3 files changed, 24 insertions, 0 deletions

diff --git a/drivers/gpu/drm/msm/adreno/adreno_device.c b/drivers/gpu/drm/msm/adreno/adreno_device.c
index 93005839b5da..fb261930ad1c 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_device.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_device.c
@@ -608,9 +608,27 @@ static int adreno_resume(struct device *dev)
 	return gpu->funcs->pm_resume(gpu);
 }
 
+static int active_submits(struct msm_gpu *gpu)
+{
+	int active_submits;
+	mutex_lock(&gpu->active_lock);
+	active_submits = gpu->active_submits;
+	mutex_unlock(&gpu->active_lock);
+	return active_submits;
+}
+
 static int adreno_suspend(struct device *dev)
 {
 	struct msm_gpu *gpu = dev_to_gpu(dev);
+	int remaining;
+
+	remaining = wait_event_timeout(gpu->retire_event,
+				       active_submits(gpu) == 0,
+				       msecs_to_jiffies(1000));
+	if (remaining == 0) {
+		dev_err(dev, "Timeout waiting for GPU to suspend\n");
+		return -EBUSY;
+	}
 
 	return gpu->funcs->pm_suspend(gpu);
 }
diff --git a/drivers/gpu/drm/msm/msm_gpu.c b/drivers/gpu/drm/msm/msm_gpu.c
index 0f78c2615272..2c1049c0ea14 100644
--- a/drivers/gpu/drm/msm/msm_gpu.c
+++ b/drivers/gpu/drm/msm/msm_gpu.c
@@ -703,6 +703,8 @@ static void retire_submits(struct msm_gpu *gpu)
 			}
 		}
 	}
+
+	wake_up_all(&gpu->retire_event);
 }
 
 static void retire_worker(struct kthread_work *work)
@@ -848,6 +850,7 @@ int msm_gpu_init(struct drm_device *drm, struct platform_device *pdev,
 	INIT_LIST_HEAD(&gpu->active_list);
 	mutex_init(&gpu->active_lock);
 	mutex_init(&gpu->lock);
+	init_waitqueue_head(&gpu->retire_event);
 	kthread_init_work(&gpu->retire_work, retire_worker);
 	kthread_init_work(&gpu->recover_work, recover_worker);
 	kthread_init_work(&gpu->fault_work, fault_worker);
diff --git a/drivers/gpu/drm/msm/msm_gpu.h b/drivers/gpu/drm/msm/msm_gpu.h
index 445c6bfd4b6b..92aa1e9196c6 100644
--- a/drivers/gpu/drm/msm/msm_gpu.h
+++ b/drivers/gpu/drm/msm/msm_gpu.h
@@ -230,6 +230,9 @@ struct msm_gpu {
 	/* work for handling GPU recovery: */
 	struct kthread_work recover_work;
 
+	/** retire_event: notified when submits are retired: */
+	wait_queue_head_t retire_event;
+
 	/* work for handling active-list retiring: */
 	struct kthread_work retire_work;