[PATCH v2 13/16] drm/msm/adreno: Disable IFPC when sysprof is active

[Akhil P Oommen <akhilpo@oss.qualcomm.com>]

Moving to IFPC state clears the 'Perfcounter Select' register setup
by the userspace. So, lets block the IFPC when sysprof is active by
using the perfcounter oob signal to the GMU.

Signed-off-by: Akhil P Oommen <akhilpo@oss.qualcomm.com>
---
 drivers/gpu/drm/msm/adreno/a6xx_gmu.c | 37 +++++++++++++++++++++++++++++++++++
 drivers/gpu/drm/msm/adreno/a6xx_gmu.h |  2 ++
 drivers/gpu/drm/msm/adreno/a6xx_gpu.c |  2 ++
 drivers/gpu/drm/msm/adreno/a6xx_gpu.h |  1 +
 drivers/gpu/drm/msm/msm_gpu.h         |  1 +
 drivers/gpu/drm/msm/msm_submitqueue.c |  4 ++++
 6 files changed, 47 insertions(+)

diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
index d6297cc7fe664a74224c441e877050612714a3e4..d76b6b766d4a644d342f62435892d54ebd7192e5 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
@@ -1157,6 +1157,11 @@ int a6xx_gmu_resume(struct a6xx_gpu *a6xx_gpu)
 	/* Set the GPU to the current freq */
 	a6xx_gmu_set_initial_freq(gpu, gmu);
 
+	if (refcount_read(&gpu->sysprof_active) > 1) {
+		ret = a6xx_gmu_set_oob(gmu, GMU_OOB_PERFCOUNTER_SET);
+		if (!ret)
+			set_bit(GMU_STATUS_OOB_PERF_SET, &gmu->status);
+	}
 out:
 	/* On failure, shut down the GMU to leave it in a good state */
 	if (ret) {
@@ -1204,6 +1209,9 @@ static void a6xx_gmu_shutdown(struct a6xx_gmu *gmu)
 		a6xx_gmu_clear_oob(&a6xx_gpu->gmu, GMU_OOB_GPU_SET);
 	}
 
+	if (test_and_clear_bit(GMU_STATUS_OOB_PERF_SET, &gmu->status))
+		a6xx_gmu_clear_oob(gmu, GMU_OOB_PERFCOUNTER_SET);
+
 	ret = a6xx_gmu_wait_for_idle(gmu);
 
 	/* If the GMU isn't responding assume it is hung */
@@ -1819,6 +1827,35 @@ static int a6xx_gmu_get_irq(struct a6xx_gmu *gmu, struct platform_device *pdev,
 	return irq;
 }
 
+void a6xx_gmu_sysprof_setup(struct msm_gpu *gpu)
+{
+	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
+	struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu);
+	struct a6xx_gmu *gmu = &a6xx_gpu->gmu;
+	unsigned int sysprof_active;
+
+	/* Nothing to do if GPU is suspended. We will handle this during GMU resume */
+	if (!pm_runtime_get_if_active(&gpu->pdev->dev))
+		return;
+
+	mutex_lock(&gmu->lock);
+
+	sysprof_active = refcount_read(&gpu->sysprof_active);
+
+	/*
+	 * 'Perfcounter select' register values are lost during IFPC collapse. To avoid that,
+	 * use the currently unused perfcounter oob vote to block IFPC when sysprof is active
+	 */
+	if ((sysprof_active > 1) && !test_and_set_bit(GMU_STATUS_OOB_PERF_SET, &gmu->status))
+		a6xx_gmu_set_oob(gmu, GMU_OOB_PERFCOUNTER_SET);
+	else if ((sysprof_active == 1) && test_and_clear_bit(GMU_STATUS_OOB_PERF_SET, &gmu->status))
+		a6xx_gmu_clear_oob(gmu, GMU_OOB_PERFCOUNTER_SET);
+
+	mutex_unlock(&gmu->lock);
+
+	pm_runtime_put(&gpu->pdev->dev);
+}
+
 void a6xx_gmu_remove(struct a6xx_gpu *a6xx_gpu)
 {
 	struct adreno_gpu *adreno_gpu = &a6xx_gpu->base;
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.h b/drivers/gpu/drm/msm/adreno/a6xx_gmu.h
index 40c4c0445b8e4349c9111850df9c0b1d355f0b73..06cfc294016f513a33eb4004c7892996ac9e0435 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.h
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.h
@@ -125,6 +125,8 @@ struct a6xx_gmu {
 #define GMU_STATUS_FW_START	0
 /* To track if PDC sleep seq was done */
 #define GMU_STATUS_PDC_SLEEP	1
+/* To track Perfcounter OOB set status */
+#define GMU_STATUS_OOB_PERF_SET 2
 	unsigned long status;
 };
 
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
index 61538b6912883a0e7ec7802cf5f5cfc8649ece2b..b54c88fb27d57f81306163e699961803ff765bdb 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
@@ -2533,6 +2533,7 @@ static const struct adreno_gpu_funcs funcs = {
 		.create_private_vm = a6xx_create_private_vm,
 		.get_rptr = a6xx_get_rptr,
 		.progress = a6xx_progress,
+		.sysprof_setup = a6xx_gmu_sysprof_setup,
 	},
 	.get_timestamp = a6xx_gmu_get_timestamp,
 };
@@ -2593,6 +2594,7 @@ static const struct adreno_gpu_funcs funcs_a7xx = {
 		.create_private_vm = a6xx_create_private_vm,
 		.get_rptr = a6xx_get_rptr,
 		.progress = a6xx_progress,
+		.sysprof_setup = a6xx_gmu_sysprof_setup,
 	},
 	.get_timestamp = a6xx_gmu_get_timestamp,
 };
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.h b/drivers/gpu/drm/msm/adreno/a6xx_gpu.h
index e736c59d566b3fcf8c62a212494e3b110c09caa9..124c63c4615930b00c64e488a498163ae35afccd 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.h
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.h
@@ -254,6 +254,7 @@ void a6xx_gmu_clear_oob(struct a6xx_gmu *gmu, enum a6xx_gmu_oob_state state);
 int a6xx_gmu_init(struct a6xx_gpu *a6xx_gpu, struct device_node *node);
 int a6xx_gmu_wrapper_init(struct a6xx_gpu *a6xx_gpu, struct device_node *node);
 void a6xx_gmu_remove(struct a6xx_gpu *a6xx_gpu);
+void a6xx_gmu_sysprof_setup(struct msm_gpu *gpu);
 
 void a6xx_preempt_init(struct msm_gpu *gpu);
 void a6xx_preempt_hw_init(struct msm_gpu *gpu);
diff --git a/drivers/gpu/drm/msm/msm_gpu.h b/drivers/gpu/drm/msm/msm_gpu.h
index 866bb090af064666586cea7125254bd375b7a35c..a597f2bee30b6370ecc3639bfe1072c85993e789 100644
--- a/drivers/gpu/drm/msm/msm_gpu.h
+++ b/drivers/gpu/drm/msm/msm_gpu.h
@@ -92,6 +92,7 @@ struct msm_gpu_funcs {
 	 * for cmdstream that is buffered in this FIFO upstream of the CP fw.
 	 */
 	bool (*progress)(struct msm_gpu *gpu, struct msm_ringbuffer *ring);
+	void (*sysprof_setup)(struct msm_gpu *gpu);
 };
 
 /* Additional state for iommu faults: */
diff --git a/drivers/gpu/drm/msm/msm_submitqueue.c b/drivers/gpu/drm/msm/msm_submitqueue.c
index 8617a82cd6b38a74d996ae6965a253a29a231fa4..d53dfad16bde7d5ae7b1e48f221696d525a10965 100644
--- a/drivers/gpu/drm/msm/msm_submitqueue.c
+++ b/drivers/gpu/drm/msm/msm_submitqueue.c
@@ -40,6 +40,10 @@ int msm_context_set_sysprof(struct msm_context *ctx, struct msm_gpu *gpu, int sy
 		break;
 	}
 
+	/* Some gpu families require additional setup for sysprof */
+	if (gpu->funcs->sysprof_setup)
+		gpu->funcs->sysprof_setup(gpu);
+
 	ctx->sysprof = sysprof;
 
 	return 0;

-- 
2.50.1