drm/msm/gpu: Move BO allocation out of hw_init

These allocations are only done the first (successful) time through
hw_init() so they won't actually happen in the job_run() path.  But
lockdep doesn't know this.  So dis-entangle them from the hw_init()
path.

Signed-off-by: Rob Clark <robdclark@chromium.org>
Patchwork: https://patchwork.freedesktop.org/patch/527852/
Link: https://lore.kernel.org/r/20230320144356.803762-14-robdclark@gmail.com

3 files changed, 51 insertions, 49 deletions

diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
index 0372f8908202..d6c1c3ab19a3 100644
--- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
@@ -567,7 +567,7 @@ static void a5xx_ucode_check_version(struct a5xx_gpu *a5xx_gpu,
 	msm_gem_put_vaddr(obj);
 }
 
-static int a5xx_ucode_init(struct msm_gpu *gpu)
+static int a5xx_ucode_load(struct msm_gpu *gpu)
 {
 	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
 	struct a5xx_gpu *a5xx_gpu = to_a5xx_gpu(adreno_gpu);
@@ -605,9 +605,24 @@ static int a5xx_ucode_init(struct msm_gpu *gpu)
 		a5xx_ucode_check_version(a5xx_gpu, a5xx_gpu->pfp_bo);
 	}
 
-	gpu_write64(gpu, REG_A5XX_CP_ME_INSTR_BASE_LO, a5xx_gpu->pm4_iova);
+	if (a5xx_gpu->has_whereami) {
+		if (!a5xx_gpu->shadow_bo) {
+			a5xx_gpu->shadow = msm_gem_kernel_new(gpu->dev,
+				sizeof(u32) * gpu->nr_rings,
+				MSM_BO_WC | MSM_BO_MAP_PRIV,
+				gpu->aspace, &a5xx_gpu->shadow_bo,
+				&a5xx_gpu->shadow_iova);
 
-	gpu_write64(gpu, REG_A5XX_CP_PFP_INSTR_BASE_LO, a5xx_gpu->pfp_iova);
+			if (IS_ERR(a5xx_gpu->shadow))
+				return PTR_ERR(a5xx_gpu->shadow);
+
+			msm_gem_object_set_name(a5xx_gpu->shadow_bo, "shadow");
+		}
+	} else if (gpu->nr_rings > 1) {
+		/* Disable preemption if WHERE_AM_I isn't available */
+		a5xx_preempt_fini(gpu);
+		gpu->nr_rings = 1;
+	}
 
 	return 0;
 }
@@ -900,9 +915,8 @@ static int a5xx_hw_init(struct msm_gpu *gpu)
 	if (adreno_is_a530(adreno_gpu) || adreno_is_a540(adreno_gpu))
 		a5xx_gpmu_ucode_init(gpu);
 
-	ret = a5xx_ucode_init(gpu);
-	if (ret)
-		return ret;
+	gpu_write64(gpu, REG_A5XX_CP_ME_INSTR_BASE_LO, a5xx_gpu->pm4_iova);
+	gpu_write64(gpu, REG_A5XX_CP_PFP_INSTR_BASE_LO, a5xx_gpu->pfp_iova);
 
 	/* Set the ringbuffer address */
 	gpu_write64(gpu, REG_A5XX_CP_RB_BASE, gpu->rb[0]->iova);
@@ -916,27 +930,10 @@ static int a5xx_hw_init(struct msm_gpu *gpu)
 	gpu_write(gpu, REG_A5XX_CP_RB_CNTL,
 		MSM_GPU_RB_CNTL_DEFAULT | AXXX_CP_RB_CNTL_NO_UPDATE);
 
-	/* Create a privileged buffer for the RPTR shadow */
-	if (a5xx_gpu->has_whereami) {
-		if (!a5xx_gpu->shadow_bo) {
-			a5xx_gpu->shadow = msm_gem_kernel_new(gpu->dev,
-				sizeof(u32) * gpu->nr_rings,
-				MSM_BO_WC | MSM_BO_MAP_PRIV,
-				gpu->aspace, &a5xx_gpu->shadow_bo,
-				&a5xx_gpu->shadow_iova);
-
-			if (IS_ERR(a5xx_gpu->shadow))
-				return PTR_ERR(a5xx_gpu->shadow);
-
-			msm_gem_object_set_name(a5xx_gpu->shadow_bo, "shadow");
-		}
-
+	/* Configure the RPTR shadow if needed: */
+	if (a5xx_gpu->shadow_bo) {
 		gpu_write64(gpu, REG_A5XX_CP_RB_RPTR_ADDR,
 			    shadowptr(a5xx_gpu, gpu->rb[0]));
-	} else if (gpu->nr_rings > 1) {
-		/* Disable preemption if WHERE_AM_I isn't available */
-		a5xx_preempt_fini(gpu);
-		gpu->nr_rings = 1;
 	}
 
 	a5xx_preempt_hw_init(gpu);
@@ -1682,6 +1679,7 @@ static const struct adreno_gpu_funcs funcs = {
 		.get_param = adreno_get_param,
 		.set_param = adreno_set_param,
 		.hw_init = a5xx_hw_init,
+		.ucode_load = a5xx_ucode_load,
 		.pm_suspend = a5xx_pm_suspend,
 		.pm_resume = a5xx_pm_resume,
 		.recover = a5xx_recover,
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
index 1e09777cce3f..0f6ed7a3f712 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
@@ -917,7 +917,7 @@ out:
 	return ret;
 }
 
-static int a6xx_ucode_init(struct msm_gpu *gpu)
+static int a6xx_ucode_load(struct msm_gpu *gpu)
 {
 	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
 	struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu);
@@ -946,7 +946,23 @@ static int a6xx_ucode_init(struct msm_gpu *gpu)
 		}
 	}
 
-	gpu_write64(gpu, REG_A6XX_CP_SQE_INSTR_BASE, a6xx_gpu->sqe_iova);
+	/*
+	 * Expanded APRIV and targets that support WHERE_AM_I both need a
+	 * privileged buffer to store the RPTR shadow
+	 */
+	if ((adreno_gpu->base.hw_apriv || a6xx_gpu->has_whereami) &&
+	    !a6xx_gpu->shadow_bo) {
+		a6xx_gpu->shadow = msm_gem_kernel_new(gpu->dev,
+						      sizeof(u32) * gpu->nr_rings,
+						      MSM_BO_WC | MSM_BO_MAP_PRIV,
+						      gpu->aspace, &a6xx_gpu->shadow_bo,
+						      &a6xx_gpu->shadow_iova);
+
+		if (IS_ERR(a6xx_gpu->shadow))
+			return PTR_ERR(a6xx_gpu->shadow);
+
+		msm_gem_object_set_name(a6xx_gpu->shadow_bo, "shadow");
+	}
 
 	return 0;
 }
@@ -1132,9 +1148,7 @@ static int hw_init(struct msm_gpu *gpu)
 	if (ret)
 		goto out;
 
-	ret = a6xx_ucode_init(gpu);
-	if (ret)
-		goto out;
+	gpu_write64(gpu, REG_A6XX_CP_SQE_INSTR_BASE, a6xx_gpu->sqe_iova);
 
 	/* Set the ringbuffer address */
 	gpu_write64(gpu, REG_A6XX_CP_RB_BASE, gpu->rb[0]->iova);
@@ -1149,25 +1163,8 @@ static int hw_init(struct msm_gpu *gpu)
 		gpu_write(gpu, REG_A6XX_CP_RB_CNTL,
 			MSM_GPU_RB_CNTL_DEFAULT | AXXX_CP_RB_CNTL_NO_UPDATE);
 
-	/*
-	 * Expanded APRIV and targets that support WHERE_AM_I both need a
-	 * privileged buffer to store the RPTR shadow
-	 */
-
-	if (adreno_gpu->base.hw_apriv || a6xx_gpu->has_whereami) {
-		if (!a6xx_gpu->shadow_bo) {
-			a6xx_gpu->shadow = msm_gem_kernel_new(gpu->dev,
-				sizeof(u32) * gpu->nr_rings,
-				MSM_BO_WC | MSM_BO_MAP_PRIV,
-				gpu->aspace, &a6xx_gpu->shadow_bo,
-				&a6xx_gpu->shadow_iova);
-
-			if (IS_ERR(a6xx_gpu->shadow))
-				return PTR_ERR(a6xx_gpu->shadow);
-
-			msm_gem_object_set_name(a6xx_gpu->shadow_bo, "shadow");
-		}
-
+	/* Configure the RPTR shadow if needed: */
+	if (a6xx_gpu->shadow_bo) {
 		gpu_write64(gpu, REG_A6XX_CP_RB_RPTR_ADDR,
 			shadowptr(a6xx_gpu, gpu->rb[0]));
 	}
@@ -1958,6 +1955,7 @@ static const struct adreno_gpu_funcs funcs = {
 		.get_param = adreno_get_param,
 		.set_param = adreno_set_param,
 		.hw_init = a6xx_hw_init,
+		.ucode_load = a6xx_ucode_load,
 		.pm_suspend = a6xx_pm_suspend,
 		.pm_resume = a6xx_pm_resume,
 		.recover = a6xx_recover,
diff --git a/drivers/gpu/drm/msm/adreno/adreno_device.c b/drivers/gpu/drm/msm/adreno/adreno_device.c
index 745f59682737..4d1448714285 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_device.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_device.c
@@ -432,6 +432,12 @@ struct msm_gpu *adreno_load_gpu(struct drm_device *dev)
 	if (ret)
 		return NULL;
 
+	if (gpu->funcs->ucode_load) {
+		ret = gpu->funcs->ucode_load(gpu);
+		if (ret)
+			return NULL;
+	}
+
 	/*
 	 * Now that we have firmware loaded, and are ready to begin
 	 * booting the gpu, go ahead and enable runpm: