diff --git a/drivers/gpu/drm/msm/Kconfig b/drivers/gpu/drm/msm/Kconfig
index ae11061..39197b4 100644
--- a/drivers/gpu/drm/msm/Kconfig
+++ b/drivers/gpu/drm/msm/Kconfig
@@ -4,8 +4,8 @@
 	tristate "MSM DRM"
 	depends on DRM
 	depends on ARCH_QCOM || SOC_IMX5 || COMPILE_TEST
+	depends on COMMON_CLK
 	depends on IOMMU_SUPPORT
-	depends on (OF && COMMON_CLK) || COMPILE_TEST
 	depends on QCOM_OCMEM || QCOM_OCMEM=n
 	depends on QCOM_LLCC || QCOM_LLCC=n
 	depends on QCOM_COMMAND_DB || QCOM_COMMAND_DB=n
diff --git a/drivers/gpu/drm/msm/Makefile b/drivers/gpu/drm/msm/Makefile
index 40577f8..0934544 100644
--- a/drivers/gpu/drm/msm/Makefile
+++ b/drivers/gpu/drm/msm/Makefile
@@ -23,8 +23,10 @@
 	hdmi/hdmi_i2c.o \
 	hdmi/hdmi_phy.o \
 	hdmi/hdmi_phy_8960.o \
+	hdmi/hdmi_phy_8996.o \
 	hdmi/hdmi_phy_8x60.o \
 	hdmi/hdmi_phy_8x74.o \
+	hdmi/hdmi_pll_8960.o \
 	edp/edp.o \
 	edp/edp_aux.o \
 	edp/edp_bridge.o \
@@ -37,6 +39,7 @@
 	disp/mdp4/mdp4_dtv_encoder.o \
 	disp/mdp4/mdp4_lcdc_encoder.o \
 	disp/mdp4/mdp4_lvds_connector.o \
+	disp/mdp4/mdp4_lvds_pll.o \
 	disp/mdp4/mdp4_irq.o \
 	disp/mdp4/mdp4_kms.o \
 	disp/mdp4/mdp4_plane.o \
@@ -116,9 +119,6 @@
 	dp/dp_audio.o
 
 msm-$(CONFIG_DRM_FBDEV_EMULATION) += msm_fbdev.o
-msm-$(CONFIG_COMMON_CLK) += disp/mdp4/mdp4_lvds_pll.o
-msm-$(CONFIG_COMMON_CLK) += hdmi/hdmi_pll_8960.o
-msm-$(CONFIG_COMMON_CLK) += hdmi/hdmi_phy_8996.o
 
 msm-$(CONFIG_DRM_MSM_HDMI_HDCP) += hdmi/hdmi_hdcp.o
 
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
index 267a880..78aad52 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
@@ -1424,17 +1424,24 @@
 {
 	struct adreno_gpu *adreno_gpu = &a6xx_gpu->base;
 	struct msm_gpu *gpu = &adreno_gpu->base;
-	u32 gpu_scid, cntl1_regval = 0;
+	u32 cntl1_regval = 0;
 
 	if (IS_ERR(a6xx_gpu->llc_mmio))
 		return;
 
 	if (!llcc_slice_activate(a6xx_gpu->llc_slice)) {
-		gpu_scid = llcc_get_slice_id(a6xx_gpu->llc_slice);
+		u32 gpu_scid = llcc_get_slice_id(a6xx_gpu->llc_slice);
 
 		gpu_scid &= 0x1f;
 		cntl1_regval = (gpu_scid << 0) | (gpu_scid << 5) | (gpu_scid << 10) |
 			       (gpu_scid << 15) | (gpu_scid << 20);
+
+		/* On A660, the SCID programming for UCHE traffic is done in
+		 * A6XX_GBIF_SCACHE_CNTL0[14:10]
+		 */
+		if (adreno_is_a660_family(adreno_gpu))
+			gpu_rmw(gpu, REG_A6XX_GBIF_SCACHE_CNTL0, (0x1f << 10) |
+				(1 << 8), (gpu_scid << 10) | (1 << 8));
 	}
 
 	/*
@@ -1471,13 +1478,6 @@
 	}
 
 	gpu_rmw(gpu, REG_A6XX_GBIF_SCACHE_CNTL1, GENMASK(24, 0), cntl1_regval);
-
-	/* On A660, the SCID programming for UCHE traffic is done in
-	 * A6XX_GBIF_SCACHE_CNTL0[14:10]
-	 */
-	if (adreno_is_a660_family(adreno_gpu))
-		gpu_rmw(gpu, REG_A6XX_GBIF_SCACHE_CNTL0, (0x1f << 10) |
-			(1 << 8), (gpu_scid << 10) | (1 << 8));
 }
 
 static void a6xx_llc_slices_destroy(struct a6xx_gpu *a6xx_gpu)
@@ -1640,7 +1640,7 @@
 	return (unsigned long)busy_time;
 }
 
-void a6xx_gpu_set_freq(struct msm_gpu *gpu, struct dev_pm_opp *opp)
+static void a6xx_gpu_set_freq(struct msm_gpu *gpu, struct dev_pm_opp *opp)
 {
 	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
 	struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu);
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c
index 7501849..6e90209 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c
@@ -777,12 +777,12 @@
 	struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu);
 
 	a6xx_state->gmu_registers = state_kcalloc(a6xx_state,
-		2, sizeof(*a6xx_state->gmu_registers));
+		3, sizeof(*a6xx_state->gmu_registers));
 
 	if (!a6xx_state->gmu_registers)
 		return;
 
-	a6xx_state->nr_gmu_registers = 2;
+	a6xx_state->nr_gmu_registers = 3;
 
 	/* Get the CX GMU registers from AHB */
 	_a6xx_get_gmu_registers(gpu, a6xx_state, &a6xx_gmu_reglist[0],
diff --git a/drivers/gpu/drm/msm/dp/dp_aux.c b/drivers/gpu/drm/msm/dp/dp_aux.c
index eb40d84..6d36f63 100644
--- a/drivers/gpu/drm/msm/dp/dp_aux.c
+++ b/drivers/gpu/drm/msm/dp/dp_aux.c
@@ -33,6 +33,7 @@
 	bool read;
 	bool no_send_addr;
 	bool no_send_stop;
+	bool initted;
 	u32 offset;
 	u32 segment;
 
@@ -331,6 +332,10 @@
 	}
 
 	mutex_lock(&aux->mutex);
+	if (!aux->initted) {
+		ret = -EIO;
+		goto exit;
+	}
 
 	dp_aux_update_offset_and_segment(aux, msg);
 	dp_aux_transfer_helper(aux, msg, true);
@@ -380,6 +385,8 @@
 	}
 
 	aux->cmd_busy = false;
+
+exit:
 	mutex_unlock(&aux->mutex);
 
 	return ret;
@@ -431,8 +438,13 @@
 
 	aux = container_of(dp_aux, struct dp_aux_private, dp_aux);
 
+	mutex_lock(&aux->mutex);
+
 	dp_catalog_aux_enable(aux->catalog, true);
 	aux->retry_cnt = 0;
+	aux->initted = true;
+
+	mutex_unlock(&aux->mutex);
 }
 
 void dp_aux_deinit(struct drm_dp_aux *dp_aux)
@@ -441,7 +453,12 @@
 
 	aux = container_of(dp_aux, struct dp_aux_private, dp_aux);
 
+	mutex_lock(&aux->mutex);
+
+	aux->initted = false;
 	dp_catalog_aux_enable(aux->catalog, false);
+
+	mutex_unlock(&aux->mutex);
 }
 
 int dp_aux_register(struct drm_dp_aux *dp_aux)
diff --git a/drivers/gpu/drm/msm/dsi/dsi_host.c b/drivers/gpu/drm/msm/dsi/dsi_host.c
index f69a125f..0afc3b7 100644
--- a/drivers/gpu/drm/msm/dsi/dsi_host.c
+++ b/drivers/gpu/drm/msm/dsi/dsi_host.c
@@ -1658,6 +1658,8 @@
 	if (!prop) {
 		DRM_DEV_DEBUG(dev,
 			"failed to find data lane mapping, using default\n");
+		/* Set the number of date lanes to 4 by default. */
+		msm_host->num_data_lanes = 4;
 		return 0;
 	}
 
diff --git a/drivers/gpu/drm/msm/msm_debugfs.c b/drivers/gpu/drm/msm/msm_debugfs.c
index 09d2d27..dee13fe 100644
--- a/drivers/gpu/drm/msm/msm_debugfs.c
+++ b/drivers/gpu/drm/msm/msm_debugfs.c
@@ -77,6 +77,7 @@
 		goto free_priv;
 
 	pm_runtime_get_sync(&gpu->pdev->dev);
+	msm_gpu_hw_init(gpu);
 	show_priv->state = gpu->funcs->gpu_state_get(gpu);
 	pm_runtime_put_sync(&gpu->pdev->dev);
 
diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c
index 7936e8d..892c043 100644
--- a/drivers/gpu/drm/msm/msm_drv.c
+++ b/drivers/gpu/drm/msm/msm_drv.c
@@ -967,29 +967,18 @@
 	return ret;
 }
 
-static int msm_ioctl_wait_fence(struct drm_device *dev, void *data,
-		struct drm_file *file)
+static int wait_fence(struct msm_gpu_submitqueue *queue, uint32_t fence_id,
+		      ktime_t timeout)
 {
-	struct msm_drm_private *priv = dev->dev_private;
-	struct drm_msm_wait_fence *args = data;
-	ktime_t timeout = to_ktime(args->timeout);
-	struct msm_gpu_submitqueue *queue;
-	struct msm_gpu *gpu = priv->gpu;
 	struct dma_fence *fence;
 	int ret;
 
-	if (args->pad) {
-		DRM_ERROR("invalid pad: %08x\n", args->pad);
+	if (fence_id > queue->last_fence) {
+		DRM_ERROR_RATELIMITED("waiting on invalid fence: %u (of %u)\n",
+				      fence_id, queue->last_fence);
 		return -EINVAL;
 	}
 
-	if (!gpu)
-		return 0;
-
-	queue = msm_submitqueue_get(file->driver_priv, args->queueid);
-	if (!queue)
-		return -ENOENT;
-
 	/*
 	 * Map submitqueue scoped "seqno" (which is actually an idr key)
 	 * back to underlying dma-fence
@@ -1001,7 +990,7 @@
 	ret = mutex_lock_interruptible(&queue->lock);
 	if (ret)
 		return ret;
-	fence = idr_find(&queue->fence_idr, args->fence);
+	fence = idr_find(&queue->fence_idr, fence_id);
 	if (fence)
 		fence = dma_fence_get_rcu(fence);
 	mutex_unlock(&queue->lock);
@@ -1017,6 +1006,32 @@
 	}
 
 	dma_fence_put(fence);
+
+	return ret;
+}
+
+static int msm_ioctl_wait_fence(struct drm_device *dev, void *data,
+		struct drm_file *file)
+{
+	struct msm_drm_private *priv = dev->dev_private;
+	struct drm_msm_wait_fence *args = data;
+	struct msm_gpu_submitqueue *queue;
+	int ret;
+
+	if (args->pad) {
+		DRM_ERROR("invalid pad: %08x\n", args->pad);
+		return -EINVAL;
+	}
+
+	if (!priv->gpu)
+		return 0;
+
+	queue = msm_submitqueue_get(file->driver_priv, args->queueid);
+	if (!queue)
+		return -ENOENT;
+
+	ret = wait_fence(queue, args->fence, to_ktime(args->timeout));
+
 	msm_submitqueue_put(queue);
 
 	return ret;
diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c
index 104fdfc..512d55e 100644
--- a/drivers/gpu/drm/msm/msm_gem.c
+++ b/drivers/gpu/drm/msm/msm_gem.c
@@ -1056,8 +1056,7 @@
 {
 	struct msm_gem_object *msm_obj = to_msm_bo(obj);
 
-	vma->vm_flags &= ~VM_PFNMAP;
-	vma->vm_flags |= VM_MIXEDMAP | VM_DONTEXPAND;
+	vma->vm_flags |= VM_IO | VM_MIXEDMAP | VM_DONTEXPAND | VM_DONTDUMP;
 	vma->vm_page_prot = msm_gem_pgprot(msm_obj, vm_get_page_prot(vma->vm_flags));
 
 	return 0;
@@ -1121,7 +1120,7 @@
 			break;
 		fallthrough;
 	default:
-		DRM_DEV_ERROR(dev->dev, "invalid cache flag: %x\n",
+		DRM_DEV_DEBUG(dev->dev, "invalid cache flag: %x\n",
 				(flags & MSM_BO_CACHE_MASK));
 		return -EINVAL;
 	}
diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c
index 3cb029f..282628d 100644
--- a/drivers/gpu/drm/msm/msm_gem_submit.c
+++ b/drivers/gpu/drm/msm/msm_gem_submit.c
@@ -772,6 +772,7 @@
 		args->nr_cmds);
 	if (IS_ERR(submit)) {
 		ret = PTR_ERR(submit);
+		submit = NULL;
 		goto out_unlock;
 	}
 
@@ -904,6 +905,7 @@
 	drm_sched_entity_push_job(&submit->base);
 
 	args->fence = submit->fence_id;
+	queue->last_fence = submit->fence_id;
 
 	msm_reset_syncobjs(syncobjs_to_reset, args->nr_in_syncobjs);
 	msm_process_post_deps(post_deps, args->nr_out_syncobjs,
diff --git a/drivers/gpu/drm/msm/msm_gpu.h b/drivers/gpu/drm/msm/msm_gpu.h
index 59cdd00..48ea2de 100644
--- a/drivers/gpu/drm/msm/msm_gpu.h
+++ b/drivers/gpu/drm/msm/msm_gpu.h
@@ -359,6 +359,8 @@
  * @ring_nr:   the ringbuffer used by this submitqueue, which is determined
  *             by the submitqueue's priority
  * @faults:    the number of GPU hangs associated with this submitqueue
+ * @last_fence: the sequence number of the last allocated fence (for error
+ *             checking)
  * @ctx:       the per-drm_file context associated with the submitqueue (ie.
  *             which set of pgtables do submits jobs associated with the
  *             submitqueue use)
@@ -374,6 +376,7 @@
 	u32 flags;
 	u32 ring_nr;
 	int faults;
+	uint32_t last_fence;
 	struct msm_file_private *ctx;
 	struct list_head node;
 	struct idr fence_idr;
diff --git a/drivers/gpu/drm/msm/msm_gpu_devfreq.c b/drivers/gpu/drm/msm/msm_gpu_devfreq.c
index 8b7473f..384e90c 100644
--- a/drivers/gpu/drm/msm/msm_gpu_devfreq.c
+++ b/drivers/gpu/drm/msm/msm_gpu_devfreq.c
@@ -20,6 +20,10 @@
 	struct msm_gpu *gpu = dev_to_gpu(dev);
 	struct dev_pm_opp *opp;
 
+	/*
+	 * Note that devfreq_recommended_opp() can modify the freq
+	 * to something that actually is in the opp table:
+	 */
 	opp = devfreq_recommended_opp(dev, freq, flags);
 
 	/*
@@ -28,6 +32,7 @@
 	 */
 	if (gpu->devfreq.idle_freq) {
 		gpu->devfreq.idle_freq = *freq;
+		dev_pm_opp_put(opp);
 		return 0;
 	}
 
@@ -203,9 +208,6 @@
 	struct msm_gpu *gpu = container_of(df, struct msm_gpu, devfreq);
 	unsigned long idle_freq, target_freq = 0;
 
-	if (!df->devfreq)
-		return;
-
 	/*
 	 * Hold devfreq lock to synchronize with get_dev_status()/
 	 * target() callbacks
@@ -227,6 +229,9 @@
 {
 	struct msm_gpu_devfreq *df = &gpu->devfreq;
 
+	if (!df->devfreq)
+		return;
+
 	msm_hrtimer_queue_work(&df->idle_work, ms_to_ktime(1),
-			       HRTIMER_MODE_ABS);
+			       HRTIMER_MODE_REL);
 }