[PATCH v3 12/16] drm/msm/a8xx: Add perfcntr flush sequence

[Rob Clark <robin.clark@oss.qualcomm.com>]

With the slice architecture, we need to flush the slice and unslice
counters to perf RAM before reading counters.

Signed-off-by: Rob Clark <robin.clark@oss.qualcomm.com>
---
 drivers/gpu/drm/msm/adreno/a6xx_gpu.c |  1 +
 drivers/gpu/drm/msm/adreno/a6xx_gpu.h |  1 +
 drivers/gpu/drm/msm/adreno/a8xx_gpu.c | 20 ++++++++++++++++++++
 3 files changed, 22 insertions(+)

diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
index 30df9bfa9ef8..a329d20033d7 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
@@ -2921,6 +2921,7 @@ const struct adreno_gpu_funcs a8xx_gpu_funcs = {
 		.progress = a8xx_progress,
 		.sysprof_setup = a6xx_gmu_sysprof_setup,
 		.perfcntr_configure = a6xx_perfcntr_configure,
+		.perfcntr_flush = a8xx_perfcntr_flush,
 	},
 	.init = a6xx_gpu_init,
 	.get_timestamp = a8xx_gmu_get_timestamp,
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.h b/drivers/gpu/drm/msm/adreno/a6xx_gpu.h
index 99c3e55f5ca8..3491a24a9320 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.h
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.h
@@ -334,5 +334,6 @@ void a8xx_preempt_hw_init(struct msm_gpu *gpu);
 void a8xx_preempt_trigger(struct msm_gpu *gpu);
 void a8xx_preempt_irq(struct msm_gpu *gpu);
 bool a8xx_progress(struct msm_gpu *gpu, struct msm_ringbuffer *ring);
+void a8xx_perfcntr_flush(struct msm_gpu *gpu);
 void a8xx_recover(struct msm_gpu *gpu);
 #endif /* __A6XX_GPU_H__ */
diff --git a/drivers/gpu/drm/msm/adreno/a8xx_gpu.c b/drivers/gpu/drm/msm/adreno/a8xx_gpu.c
index 124d315b2469..6c040f718176 100644
--- a/drivers/gpu/drm/msm/adreno/a8xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a8xx_gpu.c
@@ -1345,3 +1345,23 @@ bool a8xx_progress(struct msm_gpu *gpu, struct msm_ringbuffer *ring)
 {
 	return true;
 }
+
+void a8xx_perfcntr_flush(struct msm_gpu *gpu)
+{
+	u32 val;
+
+	/*
+	 * Flush delta counters (both perf counters and pipe stats) present in
+	 * RBBM_S and RBBM_US to perf RAM logic to get the latest data.
+	 */
+	gpu_write(gpu, REG_A8XX_RBBM_PERFCTR_FLUSH_HOST_CMD, BIT(0));
+	gpu_write(gpu, REG_A8XX_RBBM_SLICE_PERFCTR_FLUSH_HOST_CMD, BIT(0));
+
+	/* Ensure all writes are posted before polling status register */
+	wmb();
+
+	if (gpu_poll_timeout(gpu, REG_A8XX_RBBM_PERFCTR_FLUSH_HOST_STATUS, val,
+			     val & BIT(0), 100, 100 * 1000)) {
+		dev_err(&gpu->pdev->dev, "Perfcounter flush timed out: status=0x%08x\n", val);
+	}
+}
-- 
2.54.0