Merge tag 'drm-msm-fixes-2020-08-24' of https://gitlab.freedesktop.org/drm/msm into drm-fixes

Some fixes for v5.9 plus the one opp/bandwidth scaling patch ("drm:
msm: a6xx: use dev_pm_opp_set_bw to scale DDR") which was not included
in the initial pull due to dependency on patch landing thru OPP tree
Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Rob Clark <robdclark@gmail.com>
Link: https://patchwork.freedesktop.org/patch/msgid/ <CAF6AEGt45A4ObyhEdC5Ga4f4cAf-NBSVRECu7df3Gh6-X4G3tQ@mail.gmail.com

drivers/gpu/drm/msm/adreno/a6xx_gmu.c

@@ -133,7 +133,7 @@ void a6xx_gmu_set_freq(struct msm_gpu *gpu, struct dev_pm_opp *opp)
 
 	if (!gmu->legacy) {
 		a6xx_hfi_set_freq(gmu, perf_index);
-		icc_set_bw(gpu->icc_path, 0, MBps_to_icc(7216));
+		dev_pm_opp_set_bw(&gpu->pdev->dev, opp);
 		pm_runtime_put(gmu->dev);
 		return;
 	}
@@ -157,11 +157,7 @@ void a6xx_gmu_set_freq(struct msm_gpu *gpu, struct dev_pm_opp *opp)
 	if (ret)
 		dev_err(gmu->dev, "GMU set GPU frequency error: %d\n", ret);
 
-	/*
-	 * Eventually we will want to scale the path vote with the frequency but
-	 * for now leave it at max so that the performance is nominal.
-	 */
-	icc_set_bw(gpu->icc_path, 0, MBps_to_icc(7216));
+	dev_pm_opp_set_bw(&gpu->pdev->dev, opp);
 	pm_runtime_put(gmu->dev);
 }
 
@@ -204,6 +200,16 @@ static int a6xx_gmu_start(struct a6xx_gmu *gmu)
 {
 	int ret;
 	u32 val;
+	u32 mask, reset_val;
+
+	val = gmu_read(gmu, REG_A6XX_GMU_CM3_DTCM_START + 0xff8);
+	if (val <= 0x20010004) {
+		mask = 0xffffffff;
+		reset_val = 0xbabeface;
+	} else {
+		mask = 0x1ff;
+		reset_val = 0x100;
+	}
 
 	gmu_write(gmu, REG_A6XX_GMU_CM3_SYSRESET, 1);
 
@@ -215,7 +221,7 @@ static int a6xx_gmu_start(struct a6xx_gmu *gmu)
 	gmu_write(gmu, REG_A6XX_GMU_CM3_SYSRESET, 0);
 
 	ret = gmu_poll_timeout(gmu, REG_A6XX_GMU_CM3_FW_INIT_RESULT, val,
-		val == 0xbabeface, 100, 10000);
+		(val & mask) == reset_val, 100, 10000);
 
 	if (ret)
 		DRM_DEV_ERROR(gmu->dev, "GMU firmware initialization timed out\n");
@@ -845,10 +851,24 @@ static void a6xx_gmu_set_initial_freq(struct msm_gpu *gpu, struct a6xx_gmu *gmu)
 	if (IS_ERR_OR_NULL(gpu_opp))
 		return;
 
+	gmu->freq = 0; /* so a6xx_gmu_set_freq() doesn't exit early */
 	a6xx_gmu_set_freq(gpu, gpu_opp);
 	dev_pm_opp_put(gpu_opp);
 }
 
+static void a6xx_gmu_set_initial_bw(struct msm_gpu *gpu, struct a6xx_gmu *gmu)
+{
+	struct dev_pm_opp *gpu_opp;
+	unsigned long gpu_freq = gmu->gpu_freqs[gmu->current_perf_index];
+
+	gpu_opp = dev_pm_opp_find_freq_exact(&gpu->pdev->dev, gpu_freq, true);
+	if (IS_ERR_OR_NULL(gpu_opp))
+		return;
+
+	dev_pm_opp_set_bw(&gpu->pdev->dev, gpu_opp);
+	dev_pm_opp_put(gpu_opp);
+}
+
 int a6xx_gmu_resume(struct a6xx_gpu *a6xx_gpu)
 {
 	struct adreno_gpu *adreno_gpu = &a6xx_gpu->base;
@@ -882,7 +902,7 @@ int a6xx_gmu_resume(struct a6xx_gpu *a6xx_gpu)
 	}
 
 	/* Set the bus quota to a reasonable value for boot */
-	icc_set_bw(gpu->icc_path, 0, MBps_to_icc(3072));
+	a6xx_gmu_set_initial_bw(gpu, gmu);
 
 	/* Enable the GMU interrupt */
 	gmu_write(gmu, REG_A6XX_GMU_AO_HOST_INTERRUPT_CLR, ~0);
@@ -1051,7 +1071,7 @@ int a6xx_gmu_stop(struct a6xx_gpu *a6xx_gpu)
 		a6xx_gmu_shutdown(gmu);
 
 	/* Remove the bus vote */
-	icc_set_bw(gpu->icc_path, 0, 0);
+	dev_pm_opp_set_bw(&gpu->pdev->dev, NULL);
 
 	/*
 	 * Make sure the GX domain is off before turning off the GMU (CX)

drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c

@@ -938,6 +938,7 @@ struct msm_gpu_state *a6xx_gpu_state_get(struct msm_gpu *gpu)
 		msm_gem_kernel_put(dumper.bo, gpu->aspace, true);
 	}
 
+	if (snapshot_debugbus)
 		a6xx_get_debugbus(gpu, a6xx_state);
 
 	return  &a6xx_state->base;

drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h

@@ -372,7 +372,7 @@ static const struct a6xx_indexed_registers {
 	u32 data;
 	u32 count;
 } a6xx_indexed_reglist[] = {
-	{ "CP_SEQ_STAT", REG_A6XX_CP_SQE_STAT_ADDR,
+	{ "CP_SQE_STAT", REG_A6XX_CP_SQE_STAT_ADDR,
 		REG_A6XX_CP_SQE_STAT_DATA, 0x33 },
 	{ "CP_DRAW_STATE", REG_A6XX_CP_DRAW_STATE_ADDR,
 		REG_A6XX_CP_DRAW_STATE_DATA, 0x100 },

drivers/gpu/drm/msm/adreno/adreno_device.c

@@ -14,6 +14,10 @@ bool hang_debug = false;
 MODULE_PARM_DESC(hang_debug, "Dump registers when hang is detected (can be slow!)");
 module_param_named(hang_debug, hang_debug, bool, 0600);
 
+bool snapshot_debugbus = false;
+MODULE_PARM_DESC(snapshot_debugbus, "Include debugbus sections in GPU devcoredump (if not fused off)");
+module_param_named(snapshot_debugbus, snapshot_debugbus, bool, 0600);
+
 static const struct adreno_info gpulist[] = {
 	{
 		.rev   = ADRENO_REV(2, 0, 0, 0),

drivers/gpu/drm/msm/adreno/adreno_gpu.c

@@ -396,7 +396,7 @@ int adreno_hw_init(struct msm_gpu *gpu)
 		ring->next = ring->start;
 
 		/* reset completed fence seqno: */
-		ring->memptrs->fence = ring->seqno;
+		ring->memptrs->fence = ring->fctx->completed_fence;
 		ring->memptrs->rptr = 0;
 	}
 

drivers/gpu/drm/msm/adreno/adreno_gpu.h

@@ -21,6 +21,8 @@
 #define REG_SKIP ~0
 #define REG_ADRENO_SKIP(_offset) [_offset] = REG_SKIP
 
+extern bool snapshot_debugbus;
+
 /**
  * adreno_regs: List of registers that are used in across all
  * 3D devices. Each device type has different offset value for the same

drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c

@@ -827,7 +827,7 @@ static void dpu_crtc_enable(struct drm_crtc *crtc,
 {
 	struct dpu_crtc *dpu_crtc;
 	struct drm_encoder *encoder;
-	bool request_bandwidth;
+	bool request_bandwidth = false;
 
 	if (!crtc) {
 		DPU_ERROR("invalid crtc\n");

drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c

@@ -599,7 +599,10 @@ static int dpu_encoder_virt_atomic_check(
 	dpu_kms = to_dpu_kms(priv->kms);
 	mode = &crtc_state->mode;
 	adj_mode = &crtc_state->adjusted_mode;
-	global_state = dpu_kms_get_existing_global_state(dpu_kms);
+	global_state = dpu_kms_get_global_state(crtc_state->state);
+	if (IS_ERR(global_state))
+		return PTR_ERR(global_state);
+
 	trace_dpu_enc_atomic_check(DRMID(drm_enc));
 
 	/* perform atomic check on the first physical encoder (master) */
@@ -625,10 +628,13 @@ static int dpu_encoder_virt_atomic_check(
 	/* Reserve dynamic resources now. */
 	if (!ret) {
 		/*
-		 * Avoid reserving resources when mode set is pending. Topology
-		 * info may not be available to complete reservation.
+		 * Release and Allocate resources on every modeset
+		 * Dont allocate when active is false.
 		 */
 		if (drm_atomic_crtc_needs_modeset(crtc_state)) {
+			dpu_rm_release(global_state, drm_enc);
+
+			if (!crtc_state->active_changed || crtc_state->active)
 				ret = dpu_rm_reserve(&dpu_kms->rm, global_state,
 						drm_enc, crtc_state, topology);
 		}
@@ -1181,7 +1187,6 @@ static void dpu_encoder_virt_disable(struct drm_encoder *drm_enc)
 	struct dpu_encoder_virt *dpu_enc = NULL;
 	struct msm_drm_private *priv;
 	struct dpu_kms *dpu_kms;
-	struct dpu_global_state *global_state;
 	int i = 0;
 
 	if (!drm_enc) {
@@ -1200,7 +1205,6 @@ static void dpu_encoder_virt_disable(struct drm_encoder *drm_enc)
 
 	priv = drm_enc->dev->dev_private;
 	dpu_kms = to_dpu_kms(priv->kms);
-	global_state = dpu_kms_get_existing_global_state(dpu_kms);
 
 	trace_dpu_enc_disable(DRMID(drm_enc));
 
@@ -1230,8 +1234,6 @@ static void dpu_encoder_virt_disable(struct drm_encoder *drm_enc)
 
 	DPU_DEBUG_ENC(dpu_enc, "encoder disabled\n");
 
-	dpu_rm_release(global_state, drm_enc);
-
 	mutex_unlock(&dpu_enc->enc_lock);
 }
 

drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c

@@ -866,9 +866,9 @@ static int dpu_plane_atomic_check(struct drm_plane *plane,
 		crtc_state = drm_atomic_get_new_crtc_state(state->state,
 							   state->crtc);
 
-	min_scale = FRAC_16_16(1, pdpu->pipe_sblk->maxdwnscale);
+	min_scale = FRAC_16_16(1, pdpu->pipe_sblk->maxupscale);
 	ret = drm_atomic_helper_check_plane_state(state, crtc_state, min_scale,
-					  pdpu->pipe_sblk->maxupscale << 16,
+					  pdpu->pipe_sblk->maxdwnscale << 16,
 					  true, true);
 	if (ret) {
 		DPU_DEBUG_PLANE(pdpu, "Check plane state failed (%d)\n", ret);

drivers/gpu/drm/msm/msm_atomic.c

@@ -27,6 +27,34 @@ int msm_atomic_prepare_fb(struct drm_plane *plane,
 	return msm_framebuffer_prepare(new_state->fb, kms->aspace);
 }
 
+/*
+ * Helpers to control vblanks while we flush.. basically just to ensure
+ * that vblank accounting is switched on, so we get valid seqn/timestamp
+ * on pageflip events (if requested)
+ */
+
+static void vblank_get(struct msm_kms *kms, unsigned crtc_mask)
+{
+	struct drm_crtc *crtc;
+
+	for_each_crtc_mask(kms->dev, crtc, crtc_mask) {
+		if (!crtc->state->active)
+			continue;
+		drm_crtc_vblank_get(crtc);
+	}
+}
+
+static void vblank_put(struct msm_kms *kms, unsigned crtc_mask)
+{
+	struct drm_crtc *crtc;
+
+	for_each_crtc_mask(kms->dev, crtc, crtc_mask) {
+		if (!crtc->state->active)
+			continue;
+		drm_crtc_vblank_put(crtc);
+	}
+}
+
 static void msm_atomic_async_commit(struct msm_kms *kms, int crtc_idx)
 {
 	unsigned crtc_mask = BIT(crtc_idx);
@@ -44,6 +72,8 @@ static void msm_atomic_async_commit(struct msm_kms *kms, int crtc_idx)
 
 	kms->funcs->enable_commit(kms);
 
+	vblank_get(kms, crtc_mask);
+
 	/*
 	 * Flush hardware updates:
 	 */
@@ -58,6 +88,8 @@ static void msm_atomic_async_commit(struct msm_kms *kms, int crtc_idx)
 	kms->funcs->wait_flush(kms, crtc_mask);
 	trace_msm_atomic_wait_flush_finish(crtc_mask);
 
+	vblank_put(kms, crtc_mask);
+
 	mutex_lock(&kms->commit_lock);
 	kms->funcs->complete_commit(kms, crtc_mask);
 	mutex_unlock(&kms->commit_lock);
@@ -221,6 +253,8 @@ void msm_atomic_commit_tail(struct drm_atomic_state *state)
 	 */
 	kms->pending_crtc_mask &= ~crtc_mask;
 
+	vblank_get(kms, crtc_mask);
+
 	/*
 	 * Flush hardware updates:
 	 */
@@ -235,6 +269,8 @@ void msm_atomic_commit_tail(struct drm_atomic_state *state)
 	kms->funcs->wait_flush(kms, crtc_mask);
 	trace_msm_atomic_wait_flush_finish(crtc_mask);
 
+	vblank_put(kms, crtc_mask);
+
 	mutex_lock(&kms->commit_lock);
 	kms->funcs->complete_commit(kms, crtc_mask);
 	mutex_unlock(&kms->commit_lock);

drivers/gpu/drm/msm/msm_drv.c

@@ -1320,6 +1320,13 @@ static int msm_pdev_remove(struct platform_device *pdev)
 	return 0;
 }
 
+static void msm_pdev_shutdown(struct platform_device *pdev)
+{
+	struct drm_device *drm = platform_get_drvdata(pdev);
+
+	drm_atomic_helper_shutdown(drm);
+}
+
 static const struct of_device_id dt_match[] = {
 	{ .compatible = "qcom,mdp4", .data = (void *)KMS_MDP4 },
 	{ .compatible = "qcom,mdss", .data = (void *)KMS_MDP5 },
@@ -1332,6 +1339,7 @@ MODULE_DEVICE_TABLE(of, dt_match);
 static struct platform_driver msm_platform_driver = {
 	.probe      = msm_pdev_probe,
 	.remove     = msm_pdev_remove,
+	.shutdown   = msm_pdev_shutdown,
 	.driver     = {
 		.name   = "msm",
 		.of_match_table = dt_match,

drivers/gpu/drm/msm/msm_ringbuffer.c

@@ -27,7 +27,8 @@ struct msm_ringbuffer *msm_ringbuffer_new(struct msm_gpu *gpu, int id,
 	ring->id = id;
 
 	ring->start = msm_gem_kernel_new(gpu->dev, MSM_GPU_RINGBUFFER_SZ,
-		MSM_BO_WC, gpu->aspace, &ring->bo, &ring->iova);
+		MSM_BO_WC | MSM_BO_GPU_READONLY, gpu->aspace, &ring->bo,
+		&ring->iova);
 
 	if (IS_ERR(ring->start)) {
 		ret = PTR_ERR(ring->start);