[PATCH v4 20/40] drm/msm: Drop queued submits on lastclose()

[Rob Clark <robdclark@gmail.com>]

From: Rob Clark <robdclark@chromium.org>

If we haven't written the submit into the ringbuffer yet, then drop it.
The submit still retires through the normal path, to preserve fence
signalling order, but we can skip the IB's to userspace cmdstream.

Signed-off-by: Rob Clark <robdclark@chromium.org>
---
 drivers/gpu/drm/msm/msm_drv.c        | 1 +
 drivers/gpu/drm/msm/msm_gpu.h        | 8 ++++++++
 drivers/gpu/drm/msm/msm_ringbuffer.c | 6 ++++++
 3 files changed, 15 insertions(+)

diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c
index 6ef29bc48bb0..5909720be48d 100644
--- a/drivers/gpu/drm/msm/msm_drv.c
+++ b/drivers/gpu/drm/msm/msm_drv.c
@@ -250,6 +250,7 @@ static int msm_open(struct drm_device *dev, struct drm_file *file)
 
 static void context_close(struct msm_context *ctx)
 {
+	ctx->closed = true;
 	msm_submitqueue_close(ctx);
 	msm_context_put(ctx);
 }
diff --git a/drivers/gpu/drm/msm/msm_gpu.h b/drivers/gpu/drm/msm/msm_gpu.h
index d8425e6d7f5a..bfaec80e5f2d 100644
--- a/drivers/gpu/drm/msm/msm_gpu.h
+++ b/drivers/gpu/drm/msm/msm_gpu.h
@@ -362,6 +362,14 @@ struct msm_context {
 	 */
 	int queueid;
 
+	/**
+	 * @closed: The device file associated with this context has been closed.
+	 *
+	 * Once the device is closed, any submits that have not been written
+	 * to the ring buffer are no-op'd.
+	 */
+	bool closed;
+
 	/** @vm: the per-process GPU address-space */
 	struct drm_gpuvm *vm;
 
diff --git a/drivers/gpu/drm/msm/msm_ringbuffer.c b/drivers/gpu/drm/msm/msm_ringbuffer.c
index bbf8503f6bb5..b8bcd5d9690d 100644
--- a/drivers/gpu/drm/msm/msm_ringbuffer.c
+++ b/drivers/gpu/drm/msm/msm_ringbuffer.c
@@ -17,6 +17,7 @@ static struct dma_fence *msm_job_run(struct drm_sched_job *job)
 	struct msm_fence_context *fctx = submit->ring->fctx;
 	struct msm_gpu *gpu = submit->gpu;
 	struct msm_drm_private *priv = gpu->dev->dev_private;
+	unsigned nr_cmds = submit->nr_cmds;
 	int i;
 
 	msm_fence_init(submit->hw_fence, fctx);
@@ -36,8 +37,13 @@ static struct dma_fence *msm_job_run(struct drm_sched_job *job)
 	/* TODO move submit path over to using a per-ring lock.. */
 	mutex_lock(&gpu->lock);
 
+	if (submit->queue->ctx->closed)
+		submit->nr_cmds = 0;
+
 	msm_gpu_submit(gpu, submit);
 
+	submit->nr_cmds = nr_cmds;
+
 	mutex_unlock(&gpu->lock);
 
 	return dma_fence_get(submit->hw_fence);
-- 
2.49.0