Merge tag 'drm-next-2021-02-26' of git://anongit.freedesktop.org/drm/drm

Pull more drm updates from Dave Airlie:
 "This is mostly fixes but I missed msm-next pull last week. It's been
  in drm-next.

  Otherwise it's a selection of i915, amdgpu and misc fixes, one TTM
  memory leak, nothing really major stands out otherwise.

  core:
   - vblank fence timing improvements

  dma-buf:
   - improve error handling

  ttm:
   - memory leak fix

  msm:
   - a6xx speedbin support
   - a508, a509, a512 support
   - various a5xx fixes
   - various dpu fixes
   - qseed3lite support for sm8250
   - dsi fix for msm8994
   - mdp5 fix for framerate bug with cmd mode panels
   - a6xx GMU OOB race fixes that were showing up in CI
   - various addition and removal of semicolons
   - gem submit fix for legacy userspace relocs path

  amdgpu:
   - clang warning fix
   - S0ix platform shutdown/poweroff fix
   - misc display fixes

  i915:
   - color format fix
   - -Wuninitialised reenabled
   - GVT ww locking, cmd parser fixes

  atyfb:
   - fix build

  rockchip:
   - AFBC modifier fix"

* tag 'drm-next-2021-02-26' of git://anongit.freedesktop.org/drm/drm: (60 commits)
  drm/panel: kd35t133: allow using non-continuous dsi clock
  drm/rockchip: Require the YTR modifier for AFBC
  drm/ttm: Fix a memory leak
  drm/drm_vblank: set the dma-fence timestamp during send_vblank_event
  dma-fence: allow signaling drivers to set fence timestamp
  dma-buf: heaps: Rework heap allocation hooks to return struct dma_buf instead of fd
  dma-buf: system_heap: Make sure to return an error if we abort
  drm/amd/display: Fix system hang after multiple hotplugs (v3)
  drm/amdgpu: fix shutdown and poweroff process failed with s0ix
  drm/i915: Nuke INTEL_OUTPUT_FORMAT_INVALID
  drm/i915: Enable -Wuninitialized
  drm/amd/display: Remove Assert from dcn10_get_dig_frontend
  drm/amd/display: Add vupdate_no_lock interrupts for DCN2.1
  Revert "drm/amd/display: reuse current context instead of recreating one"
  drm/amd/pm/swsmu: Avoid using structure_size uninitialized in smu_cmn_init_soft_gpu_metrics
  fbdev: atyfb: add stubs for aty_{ld,st}_lcd()
  drm/i915/gvt: Introduce per object locking in GVT scheduler.
  drm/i915/gvt: Purge dev_priv->gt
  drm/i915/gvt: Parse default state to update reg whitelist
  dt-bindings: dp-connector: Drop maxItems from -supply
  ...

64 files changed, 1211 insertions, 416 deletions

diff --git a/drivers/dma-buf/dma-fence.c b/drivers/dma-buf/dma-fence.c
index 7475e09b0680..d64fc03929be 100644
--- a/drivers/dma-buf/dma-fence.c
+++ b/drivers/dma-buf/dma-fence.c
@@ -312,22 +312,25 @@ void __dma_fence_might_wait(void)
 
 
 /**
- * dma_fence_signal_locked - signal completion of a fence
+ * dma_fence_signal_timestamp_locked - signal completion of a fence
  * @fence: the fence to signal
+ * @timestamp: fence signal timestamp in kernel's CLOCK_MONOTONIC time domain
  *
  * Signal completion for software callbacks on a fence, this will unblock
  * dma_fence_wait() calls and run all the callbacks added with
  * dma_fence_add_callback(). Can be called multiple times, but since a fence
  * can only go from the unsignaled to the signaled state and not back, it will
- * only be effective the first time.
+ * only be effective the first time. Set the timestamp provided as the fence
+ * signal timestamp.
  *
- * Unlike dma_fence_signal(), this function must be called with &dma_fence.lock
- * held.
+ * Unlike dma_fence_signal_timestamp(), this function must be called with
+ * &dma_fence.lock held.
  *
  * Returns 0 on success and a negative error value when @fence has been
  * signalled already.
  */
-int dma_fence_signal_locked(struct dma_fence *fence)
+int dma_fence_signal_timestamp_locked(struct dma_fence *fence,
+				      ktime_t timestamp)
 {
 	struct dma_fence_cb *cur, *tmp;
 	struct list_head cb_list;
@@ -341,7 +344,7 @@ int dma_fence_signal_locked(struct dma_fence *fence)
 	/* Stash the cb_list before replacing it with the timestamp */
 	list_replace(&fence->cb_list, &cb_list);
 
-	fence->timestamp = ktime_get();
+	fence->timestamp = timestamp;
 	set_bit(DMA_FENCE_FLAG_TIMESTAMP_BIT, &fence->flags);
 	trace_dma_fence_signaled(fence);
 
@@ -352,6 +355,59 @@ int dma_fence_signal_locked(struct dma_fence *fence)
 
 	return 0;
 }
+EXPORT_SYMBOL(dma_fence_signal_timestamp_locked);
+
+/**
+ * dma_fence_signal_timestamp - signal completion of a fence
+ * @fence: the fence to signal
+ * @timestamp: fence signal timestamp in kernel's CLOCK_MONOTONIC time domain
+ *
+ * Signal completion for software callbacks on a fence, this will unblock
+ * dma_fence_wait() calls and run all the callbacks added with
+ * dma_fence_add_callback(). Can be called multiple times, but since a fence
+ * can only go from the unsignaled to the signaled state and not back, it will
+ * only be effective the first time. Set the timestamp provided as the fence
+ * signal timestamp.
+ *
+ * Returns 0 on success and a negative error value when @fence has been
+ * signalled already.
+ */
+int dma_fence_signal_timestamp(struct dma_fence *fence, ktime_t timestamp)
+{
+	unsigned long flags;
+	int ret;
+
+	if (!fence)
+		return -EINVAL;
+
+	spin_lock_irqsave(fence->lock, flags);
+	ret = dma_fence_signal_timestamp_locked(fence, timestamp);
+	spin_unlock_irqrestore(fence->lock, flags);
+
+	return ret;
+}
+EXPORT_SYMBOL(dma_fence_signal_timestamp);
+
+/**
+ * dma_fence_signal_locked - signal completion of a fence
+ * @fence: the fence to signal
+ *
+ * Signal completion for software callbacks on a fence, this will unblock
+ * dma_fence_wait() calls and run all the callbacks added with
+ * dma_fence_add_callback(). Can be called multiple times, but since a fence
+ * can only go from the unsignaled to the signaled state and not back, it will
+ * only be effective the first time.
+ *
+ * Unlike dma_fence_signal(), this function must be called with &dma_fence.lock
+ * held.
+ *
+ * Returns 0 on success and a negative error value when @fence has been
+ * signalled already.
+ */
+int dma_fence_signal_locked(struct dma_fence *fence)
+{
+	return dma_fence_signal_timestamp_locked(fence, ktime_get());
+}
 EXPORT_SYMBOL(dma_fence_signal_locked);
 
 /**
@@ -379,7 +435,7 @@ int dma_fence_signal(struct dma_fence *fence)
 	tmp = dma_fence_begin_signalling();
 
 	spin_lock_irqsave(fence->lock, flags);
-	ret = dma_fence_signal_locked(fence);
+	ret = dma_fence_signal_timestamp_locked(fence, ktime_get());
 	spin_unlock_irqrestore(fence->lock, flags);
 
 	dma_fence_end_signalling(tmp);
diff --git a/drivers/dma-buf/dma-heap.c b/drivers/dma-buf/dma-heap.c
index afd22c9dbdcf..6b5db954569f 100644
--- a/drivers/dma-buf/dma-heap.c
+++ b/drivers/dma-buf/dma-heap.c
@@ -52,6 +52,9 @@ static int dma_heap_buffer_alloc(struct dma_heap *heap, size_t len,
 				 unsigned int fd_flags,
 				 unsigned int heap_flags)
 {
+	struct dma_buf *dmabuf;
+	int fd;
+
 	/*
 	 * Allocations from all heaps have to begin
 	 * and end on page boundaries.
@@ -60,7 +63,16 @@ static int dma_heap_buffer_alloc(struct dma_heap *heap, size_t len,
 	if (!len)
 		return -EINVAL;
 
-	return heap->ops->allocate(heap, len, fd_flags, heap_flags);
+	dmabuf = heap->ops->allocate(heap, len, fd_flags, heap_flags);
+	if (IS_ERR(dmabuf))
+		return PTR_ERR(dmabuf);
+
+	fd = dma_buf_fd(dmabuf, fd_flags);
+	if (fd < 0) {
+		dma_buf_put(dmabuf);
+		/* just return, as put will call release and that will free */
+	}
+	return fd;
 }
 
 static int dma_heap_open(struct inode *inode, struct file *file)
diff --git a/drivers/dma-buf/heaps/cma_heap.c b/drivers/dma-buf/heaps/cma_heap.c
index 364fc2f3e499..5d64eccd21d6 100644
--- a/drivers/dma-buf/heaps/cma_heap.c
+++ b/drivers/dma-buf/heaps/cma_heap.c
@@ -271,10 +271,10 @@ static const struct dma_buf_ops cma_heap_buf_ops = {
 	.release = cma_heap_dma_buf_release,
 };
 
-static int cma_heap_allocate(struct dma_heap *heap,
-				  unsigned long len,
-				  unsigned long fd_flags,
-				  unsigned long heap_flags)
+static struct dma_buf *cma_heap_allocate(struct dma_heap *heap,
+					 unsigned long len,
+					 unsigned long fd_flags,
+					 unsigned long heap_flags)
 {
 	struct cma_heap *cma_heap = dma_heap_get_drvdata(heap);
 	struct cma_heap_buffer *buffer;
@@ -289,7 +289,7 @@ static int cma_heap_allocate(struct dma_heap *heap,
 
 	buffer = kzalloc(sizeof(*buffer), GFP_KERNEL);
 	if (!buffer)
-		return -ENOMEM;
+		return ERR_PTR(-ENOMEM);
 
 	INIT_LIST_HEAD(&buffer->attachments);
 	mutex_init(&buffer->lock);
@@ -348,15 +348,7 @@ static int cma_heap_allocate(struct dma_heap *heap,
 		ret = PTR_ERR(dmabuf);
 		goto free_pages;
 	}
-
-	ret = dma_buf_fd(dmabuf, fd_flags);
-	if (ret < 0) {
-		dma_buf_put(dmabuf);
-		/* just return, as put will call release and that will free */
-		return ret;
-	}
-
-	return ret;
+	return dmabuf;
 
 free_pages:
 	kfree(buffer->pages);
@@ -365,7 +357,7 @@ free_cma:
 free_buffer:
 	kfree(buffer);
 
-	return ret;
+	return ERR_PTR(ret);
 }
 
 static const struct dma_heap_ops cma_heap_ops = {
diff --git a/drivers/dma-buf/heaps/system_heap.c b/drivers/dma-buf/heaps/system_heap.c
index 17e0e9a68baf..29e49ac17251 100644
--- a/drivers/dma-buf/heaps/system_heap.c
+++ b/drivers/dma-buf/heaps/system_heap.c
@@ -331,10 +331,10 @@ static struct page *alloc_largest_available(unsigned long size,
 	return NULL;
 }
 
-static int system_heap_allocate(struct dma_heap *heap,
-				unsigned long len,
-				unsigned long fd_flags,
-				unsigned long heap_flags)
+static struct dma_buf *system_heap_allocate(struct dma_heap *heap,
+					    unsigned long len,
+					    unsigned long fd_flags,
+					    unsigned long heap_flags)
 {
 	struct system_heap_buffer *buffer;
 	DEFINE_DMA_BUF_EXPORT_INFO(exp_info);
@@ -349,7 +349,7 @@ static int system_heap_allocate(struct dma_heap *heap,
 
 	buffer = kzalloc(sizeof(*buffer), GFP_KERNEL);
 	if (!buffer)
-		return -ENOMEM;
+		return ERR_PTR(-ENOMEM);
 
 	INIT_LIST_HEAD(&buffer->attachments);
 	mutex_init(&buffer->lock);
@@ -363,8 +363,10 @@ static int system_heap_allocate(struct dma_heap *heap,
 		 * Avoid trying to allocate memory if the process
 		 * has been killed by SIGKILL
 		 */
-		if (fatal_signal_pending(current))
+		if (fatal_signal_pending(current)) {
+			ret = -EINTR;
 			goto free_buffer;
+		}
 
 		page = alloc_largest_available(size_remaining, max_order);
 		if (!page)
@@ -397,14 +399,7 @@ static int system_heap_allocate(struct dma_heap *heap,
 		ret = PTR_ERR(dmabuf);
 		goto free_pages;
 	}
-
-	ret = dma_buf_fd(dmabuf, fd_flags);
-	if (ret < 0) {
-		dma_buf_put(dmabuf);
-		/* just return, as put will call release and that will free */
-		return ret;
-	}
-	return ret;
+	return dmabuf;
 
 free_pages:
 	for_each_sgtable_sg(table, sg, i) {
@@ -418,7 +413,7 @@ free_buffer:
 		__free_pages(page, compound_order(page));
 	kfree(buffer);
 
-	return ret;
+	return ERR_PTR(ret);
 }
 
 static const struct dma_heap_ops system_heap_ops = {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 86452f4f3c82..b6879d97c9c9 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -1008,6 +1008,12 @@ struct amdgpu_device {
 	bool                            in_suspend;
 	bool				in_hibernate;
 
+	/*
+	 * The combination flag in_poweroff_reboot_com used to identify the poweroff
+	 * and reboot opt in the s0i3 system-wide suspend.
+	 */
+	bool 				in_poweroff_reboot_com;
+
 	atomic_t 			in_gpu_reset;
 	enum pp_mp1_state               mp1_state;
 	struct rw_semaphore reset_sem;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 7052dc35d278..6447cd6ca5a8 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -2678,7 +2678,8 @@ static int amdgpu_device_ip_suspend_phase1(struct amdgpu_device *adev)
 {
 	int i, r;
 
-	if (!amdgpu_acpi_is_s0ix_supported(adev) || amdgpu_in_reset(adev)) {
+	if (adev->in_poweroff_reboot_com ||
+	    !amdgpu_acpi_is_s0ix_supported(adev) || amdgpu_in_reset(adev)) {
 		amdgpu_device_set_pg_state(adev, AMD_PG_STATE_UNGATE);
 		amdgpu_device_set_cg_state(adev, AMD_CG_STATE_UNGATE);
 	}
@@ -3741,7 +3742,8 @@ int amdgpu_device_suspend(struct drm_device *dev, bool fbcon)
 
 	amdgpu_fence_driver_suspend(adev);
 
-	if (!amdgpu_acpi_is_s0ix_supported(adev) || amdgpu_in_reset(adev))
+	if (adev->in_poweroff_reboot_com ||
+	    !amdgpu_acpi_is_s0ix_supported(adev) || amdgpu_in_reset(adev))
 		r = amdgpu_device_ip_suspend_phase2(adev);
 	else
 		amdgpu_gfx_state_change_set(adev, sGpuChangeState_D3Entry);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 03c529630c21..4575192d9b08 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -1270,7 +1270,9 @@ amdgpu_pci_shutdown(struct pci_dev *pdev)
 	 */
 	if (!amdgpu_passthrough(adev))
 		adev->mp1_state = PP_MP1_STATE_UNLOAD;
+	adev->in_poweroff_reboot_com = true;
 	amdgpu_device_ip_suspend(adev);
+	adev->in_poweroff_reboot_com = false;
 	adev->mp1_state = PP_MP1_STATE_NONE;
 }
 
@@ -1312,8 +1314,13 @@ static int amdgpu_pmops_thaw(struct device *dev)
 static int amdgpu_pmops_poweroff(struct device *dev)
 {
 	struct drm_device *drm_dev = dev_get_drvdata(dev);
+	struct amdgpu_device *adev = drm_to_adev(drm_dev);
+	int r;
 
-	return amdgpu_device_suspend(drm_dev, true);
+	adev->in_poweroff_reboot_com = true;
+	r =  amdgpu_device_suspend(drm_dev, true);
+	adev->in_poweroff_reboot_com = false;
+	return r;
 }
 
 static int amdgpu_pmops_restore(struct device *dev)
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index 94cd5ddd67ef..3e1fd1e7d09f 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -937,7 +937,49 @@ static void mmhub_read_system_context(struct amdgpu_device *adev, struct dc_phy_
 
 }
 #endif
+#if defined(CONFIG_DRM_AMD_DC_DCN)
+static void event_mall_stutter(struct work_struct *work)
+{
+
+	struct vblank_workqueue *vblank_work = container_of(work, struct vblank_workqueue, mall_work);
+	struct amdgpu_display_manager *dm = vblank_work->dm;
+
+	mutex_lock(&dm->dc_lock);
+
+	if (vblank_work->enable)
+		dm->active_vblank_irq_count++;
+	else
+		dm->active_vblank_irq_count--;
+
+
+	dc_allow_idle_optimizations(
+		dm->dc, dm->active_vblank_irq_count == 0 ? true : false);
+
+	DRM_DEBUG_DRIVER("Allow idle optimizations (MALL): %d\n", dm->active_vblank_irq_count == 0);
 
+
+	mutex_unlock(&dm->dc_lock);
+}
+
+static struct vblank_workqueue *vblank_create_workqueue(struct amdgpu_device *adev, struct dc *dc)
+{
+
+	int max_caps = dc->caps.max_links;
+	struct vblank_workqueue *vblank_work;
+	int i = 0;
+
+	vblank_work = kcalloc(max_caps, sizeof(*vblank_work), GFP_KERNEL);
+	if (ZERO_OR_NULL_PTR(vblank_work)) {
+		kfree(vblank_work);
+		return NULL;
+	}
+
+	for (i = 0; i < max_caps; i++)
+		INIT_WORK(&vblank_work[i].mall_work, event_mall_stutter);
+
+	return vblank_work;
+}
+#endif
 static int amdgpu_dm_init(struct amdgpu_device *adev)
 {
 	struct dc_init_data init_data;
@@ -957,6 +999,9 @@ static int amdgpu_dm_init(struct amdgpu_device *adev)
 
 	mutex_init(&adev->dm.dc_lock);
 	mutex_init(&adev->dm.audio_lock);
+#if defined(CONFIG_DRM_AMD_DC_DCN)
+	spin_lock_init(&adev->dm.vblank_lock);
+#endif
 
 	if(amdgpu_dm_irq_init(adev)) {
 		DRM_ERROR("amdgpu: failed to initialize DM IRQ support.\n");
@@ -1071,6 +1116,17 @@ static int amdgpu_dm_init(struct amdgpu_device *adev)
 
 	amdgpu_dm_init_color_mod();
 
+#if defined(CONFIG_DRM_AMD_DC_DCN)
+	if (adev->dm.dc->caps.max_links > 0) {
+		adev->dm.vblank_workqueue = vblank_create_workqueue(adev, adev->dm.dc);
+
+		if (!adev->dm.vblank_workqueue)
+			DRM_ERROR("amdgpu: failed to initialize vblank_workqueue.\n");
+		else
+			DRM_DEBUG_DRIVER("amdgpu: vblank_workqueue init done %p.\n", adev->dm.vblank_workqueue);
+	}
+#endif
+
 #ifdef CONFIG_DRM_AMD_DC_HDCP
 	if (adev->dm.dc->caps.max_links > 0 && adev->asic_type >= CHIP_RAVEN) {
 		adev->dm.hdcp_workqueue = hdcp_create_workqueue(adev, &init_params.cp_psp, adev->dm.dc);
@@ -1936,7 +1992,7 @@ static void dm_gpureset_commit_state(struct dc_state *dc_state,
 		dc_commit_updates_for_stream(
 			dm->dc, bundle->surface_updates,
 			dc_state->stream_status->plane_count,
-			dc_state->streams[k], &bundle->stream_update);
+			dc_state->streams[k], &bundle->stream_update, dc_state);
 	}
 
 cleanup:
@@ -1967,7 +2023,8 @@ static void dm_set_dpms_off(struct dc_link *link)
 
 	stream_update.stream = stream_state;
 	dc_commit_updates_for_stream(stream_state->ctx->dc, NULL, 0,
-				     stream_state, &stream_update);
+				     stream_state, &stream_update,
+				     stream_state->ctx->dc->current_state);
 	mutex_unlock(&adev->dm.dc_lock);
 }
 
@@ -5374,7 +5431,10 @@ static inline int dm_set_vblank(struct drm_crtc *crtc, bool enable)
 	struct amdgpu_crtc *acrtc = to_amdgpu_crtc(crtc);
 	struct amdgpu_device *adev = drm_to_adev(crtc->dev);
 	struct dm_crtc_state *acrtc_state = to_dm_crtc_state(crtc->state);
+#if defined(CONFIG_DRM_AMD_DC_DCN)
 	struct amdgpu_display_manager *dm = &adev->dm;
+	unsigned long flags;
+#endif
 	int rc = 0;
 
 	if (enable) {
@@ -5397,22 +5457,15 @@ static inline int dm_set_vblank(struct drm_crtc *crtc, bool enable)
 	if (amdgpu_in_reset(adev))
 		return 0;
 
-	mutex_lock(&dm->dc_lock);
-
-	if (enable)
-		dm->active_vblank_irq_count++;
-	else
-		dm->active_vblank_irq_count--;
-
 #if defined(CONFIG_DRM_AMD_DC_DCN)
-	dc_allow_idle_optimizations(
-		adev->dm.dc, dm->active_vblank_irq_count == 0 ? true : false);
-
-	DRM_DEBUG_DRIVER("Allow idle optimizations (MALL): %d\n", dm->active_vblank_irq_count == 0);
+	spin_lock_irqsave(&dm->vblank_lock, flags);
+	dm->vblank_workqueue->dm = dm;
+	dm->vblank_workqueue->otg_inst = acrtc->otg_inst;
+	dm->vblank_workqueue->enable = enable;
+	spin_unlock_irqrestore(&dm->vblank_lock, flags);
+	schedule_work(&dm->vblank_workqueue->mall_work);
 #endif
 
-	mutex_unlock(&dm->dc_lock);
-
 	return 0;
 }
 
@@ -7663,7 +7716,7 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state,
 				    struct drm_crtc *pcrtc,
 				    bool wait_for_vblank)
 {
-	int i;
+	uint32_t i;
 	uint64_t timestamp_ns;
 	struct drm_plane *plane;
 	struct drm_plane_state *old_plane_state, *new_plane_state;
@@ -7704,7 +7757,7 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state,
 		amdgpu_dm_commit_cursors(state);
 
 	/* update planes when needed */
-	for_each_oldnew_plane_in_state_reverse(state, plane, old_plane_state, new_plane_state, i) {
+	for_each_oldnew_plane_in_state(state, plane, old_plane_state, new_plane_state, i) {
 		struct drm_crtc *crtc = new_plane_state->crtc;
 		struct drm_crtc_state *new_crtc_state;
 		struct drm_framebuffer *fb = new_plane_state->fb;
@@ -7927,7 +7980,8 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state,
 						     bundle->surface_updates,
 						     planes_count,
 						     acrtc_state->stream,
-						     &bundle->stream_update);
+						     &bundle->stream_update,
+						     dc_state);
 
 		/**
 		 * Enable or disable the interrupts on the backend.
@@ -8263,13 +8317,13 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state)
 		struct dm_connector_state *dm_new_con_state = to_dm_connector_state(new_con_state);
 		struct dm_connector_state *dm_old_con_state = to_dm_connector_state(old_con_state);
 		struct amdgpu_crtc *acrtc = to_amdgpu_crtc(dm_new_con_state->base.crtc);
-		struct dc_surface_update surface_updates[MAX_SURFACES];
+		struct dc_surface_update dummy_updates[MAX_SURFACES];
 		struct dc_stream_update stream_update;
 		struct dc_info_packet hdr_packet;
 		struct dc_stream_status *status = NULL;
 		bool abm_changed, hdr_changed, scaling_changed;
 
-		memset(&surface_updates, 0, sizeof(surface_updates));
+		memset(&dummy_updates, 0, sizeof(dummy_updates));
 		memset(&stream_update, 0, sizeof(stream_update));
 
 		if (acrtc) {
@@ -8326,15 +8380,16 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state)
 		 * To fix this, DC should permit updating only stream properties.
 		 */
 		for (j = 0; j < status->plane_count; j++)
-			surface_updates[j].surface = status->plane_states[j];
+			dummy_updates[j].surface = status->plane_states[0];
 
 
 		mutex_lock(&dm->dc_lock);
 		dc_commit_updates_for_stream(dm->dc,
-						surface_updates,
+						     dummy_updates,
 						     status->plane_count,
 						     dm_new_crtc_state->stream,
-						     &stream_update);
+						     &stream_update,
+						     dc_state);
 		mutex_unlock(&dm->dc_lock);
 	}
 
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
index f72930c36c22..8bfe901cf237 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
@@ -93,6 +93,20 @@ struct dm_compressor_info {
 };
 
 /**
+ * struct vblank_workqueue - Works to be executed in a separate thread during vblank
+ * @mall_work: work for mall stutter
+ * @dm: amdgpu display manager device
+ * @otg_inst: otg instance of which vblank is being set
+ * @enable: true if enable vblank
+ */
+struct vblank_workqueue {
+	struct work_struct mall_work;
+	struct amdgpu_display_manager *dm;
+	int otg_inst;
+	bool enable;
+};
+
+/**
  * struct amdgpu_dm_backlight_caps - Information about backlight
  *
  * Describe the backlight support for ACPI or eDP AUX.
@@ -244,6 +258,15 @@ struct amdgpu_display_manager {
 	struct mutex audio_lock;
 
 	/**
+	 * @vblank_work_lock:
+	 *
+	 * Guards access to deferred vblank work state.
+	 */
+#if defined(CONFIG_DRM_AMD_DC_DCN)
+	spinlock_t vblank_lock;
+#endif
+
+	/**
 	 * @audio_component:
 	 *
 	 * Used to notify ELD changes to sound driver.
@@ -321,6 +344,10 @@ struct amdgpu_display_manager {
 	struct hdcp_workqueue *hdcp_workqueue;
 #endif
 
+#if defined(CONFIG_DRM_AMD_DC_DCN)
+	struct vblank_workqueue *vblank_workqueue;
+#endif
+
 	struct drm_atomic_state *cached_state;
 	struct dc_state *cached_dc_state;
 
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c
index c9aede2f783d..8f8a13c7cf73 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc.c
@@ -2697,7 +2697,8 @@ void dc_commit_updates_for_stream(struct dc *dc,
 		struct dc_surface_update *srf_updates,
 		int surface_count,
 		struct dc_stream_state *stream,
-		struct dc_stream_update *stream_update)
+		struct dc_stream_update *stream_update,
+		struct dc_state *state)
 {
 	const struct dc_stream_status *stream_status;
 	enum surface_update_type update_type;
@@ -2716,12 +2717,6 @@ void dc_commit_updates_for_stream(struct dc *dc,
 
 
 	if (update_type >= UPDATE_TYPE_FULL) {
-		struct dc_plane_state *new_planes[MAX_SURFACES];
-
-		memset(new_planes, 0, sizeof(new_planes));
-
-		for (i = 0; i < surface_count; i++)
-			new_planes[i] = srf_updates[i].surface;
 
 		/* initialize scratch memory for building context */
 		context = dc_create_state(dc);
@@ -2730,21 +2725,15 @@ void dc_commit_updates_for_stream(struct dc *dc,
 			return;
 		}
 
-		dc_resource_state_copy_construct(
-				dc->current_state, context);
+		dc_resource_state_copy_construct(state, context);
 
-		/*remove old surfaces from context */
-		if (!dc_rem_all_planes_for_stream(dc, stream, context)) {
-			DC_ERROR("Failed to remove streams for new validate context!\n");
-			return;
-		}
+		for (i = 0; i < dc->res_pool->pipe_count; i++) {
+			struct pipe_ctx *new_pipe = &context->res_ctx.pipe_ctx[i];
+			struct pipe_ctx *old_pipe = &dc->current_state->res_ctx.pipe_ctx[i];
 
-		/* add surface to context */
-		if (!dc_add_all_planes_for_stream(dc, stream, new_planes, surface_count, context)) {
-			DC_ERROR("Failed to add streams for new validate context!\n");
-			return;
+			if (new_pipe->plane_state && new_pipe->plane_state != old_pipe->plane_state)
+				new_pipe->plane_state->force_full_update = true;
 		}
-
 	}
 
 
diff --git a/drivers/gpu/drm/amd/display/dc/dc_stream.h b/drivers/gpu/drm/amd/display/dc/dc_stream.h
index a4f7ec888c67..80b67b860091 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_stream.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_stream.h
@@ -294,7 +294,8 @@ void dc_commit_updates_for_stream(struct dc *dc,
 		struct dc_surface_update *srf_updates,
 		int surface_count,
 		struct dc_stream_state *stream,
-		struct dc_stream_update *stream_update);
+		struct dc_stream_update *stream_update,
+		struct dc_state *state);
 /*
  * Log the current stream state.
  */
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_link_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_link_encoder.c
index 59024653430c..e4701825b5a0 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_link_encoder.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_link_encoder.c
@@ -480,7 +480,6 @@ unsigned int dcn10_get_dig_frontend(struct link_encoder *enc)
 		break;
 	default:
 		// invalid source select DIG
-		ASSERT(false);
 		result = ENGINE_ID_UNKNOWN;
 	}
 
diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c
index 9620fb8a27dc..06dc1e2e8383 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c
@@ -539,6 +539,8 @@ void dcn30_init_hw(struct dc *dc)
 
 					fe = dc->links[i]->link_enc->funcs->get_dig_frontend(
 										dc->links[i]->link_enc);
+					if (fe == ENGINE_ID_UNKNOWN)
+						continue;
 
 					for (j = 0; j < dc->res_pool->stream_enc_count; j++) {
 						if (fe == dc->res_pool->stream_enc[j]->id) {
diff --git a/drivers/gpu/drm/amd/display/dc/irq/dcn21/irq_service_dcn21.c b/drivers/gpu/drm/amd/display/dc/irq/dcn21/irq_service_dcn21.c
index 1b971265418b..0e0f494fbb5e 100644
--- a/drivers/gpu/drm/amd/display/dc/irq/dcn21/irq_service_dcn21.c
+++ b/drivers/gpu/drm/amd/display/dc/irq/dcn21/irq_service_dcn21.c
@@ -168,6 +168,11 @@ static const struct irq_source_info_funcs vblank_irq_info_funcs = {
 	.ack = NULL
 };
 
+static const struct irq_source_info_funcs vupdate_no_lock_irq_info_funcs = {
+	.set = NULL,
+	.ack = NULL
+};
+
 #undef BASE_INNER
 #define BASE_INNER(seg) DMU_BASE__INST0_SEG ## seg
 
@@ -230,6 +235,17 @@ static const struct irq_source_info_funcs vblank_irq_info_funcs = {
 		.funcs = &vblank_irq_info_funcs\
 	}
 
+/* vupdate_no_lock_int_entry maps to DC_IRQ_SOURCE_VUPDATEx, to match semantic
+ * of DCE's DC_IRQ_SOURCE_VUPDATEx.
+ */
+#define vupdate_no_lock_int_entry(reg_num)\
+	[DC_IRQ_SOURCE_VUPDATE1 + reg_num] = {\
+		IRQ_REG_ENTRY(OTG, reg_num,\
+			OTG_GLOBAL_SYNC_STATUS, VUPDATE_NO_LOCK_INT_EN,\
+			OTG_GLOBAL_SYNC_STATUS, VUPDATE_NO_LOCK_EVENT_CLEAR),\
+		.funcs = &vupdate_no_lock_irq_info_funcs\
+	}
+
 #define vblank_int_entry(reg_num)\
 	[DC_IRQ_SOURCE_VBLANK1 + reg_num] = {\
 		IRQ_REG_ENTRY(OTG, reg_num,\
@@ -338,6 +354,12 @@ irq_source_info_dcn21[DAL_IRQ_SOURCES_NUMBER] = {
 	vupdate_int_entry(3),
 	vupdate_int_entry(4),
 	vupdate_int_entry(5),
+	vupdate_no_lock_int_entry(0),
+	vupdate_no_lock_int_entry(1),
+	vupdate_no_lock_int_entry(2),
+	vupdate_no_lock_int_entry(3),
+	vupdate_no_lock_int_entry(4),
+	vupdate_no_lock_int_entry(5),
 	vblank_int_entry(0),
 	vblank_int_entry(1),
 	vblank_int_entry(2),
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c
index bb620fdd4cd2..bcedd4d92e35 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c
@@ -762,7 +762,7 @@ void smu_cmn_init_soft_gpu_metrics(void *table, uint8_t frev, uint8_t crev)
 		structure_size = sizeof(struct gpu_metrics_v2_0);
 		break;
 	default:
-		break;
+		return;
 	}
 
 #undef METRICS_VERSION
diff --git a/drivers/gpu/drm/drm_file.c b/drivers/gpu/drm/drm_file.c
index 6b116bfd747c..7efbccffc2ea 100644
--- a/drivers/gpu/drm/drm_file.c
+++ b/drivers/gpu/drm/drm_file.c
@@ -775,20 +775,19 @@ void drm_event_cancel_free(struct drm_device *dev,
 EXPORT_SYMBOL(drm_event_cancel_free);
 
 /**
- * drm_send_event_locked - send DRM event to file descriptor
+ * drm_send_event_helper - send DRM event to file descriptor
  * @dev: DRM device
  * @e: DRM event to deliver
+ * @timestamp: timestamp to set for the fence event in kernel's CLOCK_MONOTONIC
+ * time domain
  *
- * This function sends the event @e, initialized with drm_event_reserve_init(),
- * to its associated userspace DRM file. Callers must already hold
- * &drm_device.event_lock, see drm_send_event() for the unlocked version.
- *
- * Note that the core will take care of unlinking and disarming events when the
- * corresponding DRM file is closed. Drivers need not worry about whether the
- * DRM file for this event still exists and can call this function upon
- * completion of the asynchronous work unconditionally.
+ * This helper function sends the event @e, initialized with
+ * drm_event_reserve_init(), to its associated userspace DRM file.
+ * The timestamp variant of dma_fence_signal is used when the caller
+ * sends a valid timestamp.
  */
-void drm_send_event_locked(struct drm_device *dev, struct drm_pending_event *e)
+void drm_send_event_helper(struct drm_device *dev,
+			   struct drm_pending_event *e, ktime_t timestamp)
 {
 	assert_spin_locked(&dev->event_lock);
 
@@ -799,7 +798,10 @@ void drm_send_event_locked(struct drm_device *dev, struct drm_pending_event *e)
 	}
 
 	if (e->fence) {
-		dma_fence_signal(e->fence);
+		if (timestamp)
+			dma_fence_signal_timestamp(e->fence, timestamp);
+		else
+			dma_fence_signal(e->fence);
 		dma_fence_put(e->fence);
 	}
 
@@ -814,6 +816,48 @@ void drm_send_event_locked(struct drm_device *dev, struct drm_pending_event *e)
 	wake_up_interruptible_poll(&e->file_priv->event_wait,
 		EPOLLIN | EPOLLRDNORM);
 }
+
+/**
+ * drm_send_event_timestamp_locked - send DRM event to file descriptor
+ * @dev: DRM device
+ * @e: DRM event to deliver
+ * @timestamp: timestamp to set for the fence event in kernel's CLOCK_MONOTONIC
+ * time domain
+ *
+ * This function sends the event @e, initialized with drm_event_reserve_init(),
+ * to its associated userspace DRM file. Callers must already hold
+ * &drm_device.event_lock.
+ *
+ * Note that the core will take care of unlinking and disarming events when the
+ * corresponding DRM file is closed. Drivers need not worry about whether the
+ * DRM file for this event still exists and can call this function upon
+ * completion of the asynchronous work unconditionally.
+ */
+void drm_send_event_timestamp_locked(struct drm_device *dev,
+				     struct drm_pending_event *e, ktime_t timestamp)
+{
+	drm_send_event_helper(dev, e, timestamp);
+}
+EXPORT_SYMBOL(drm_send_event_timestamp_locked);
+
+/**
+ * drm_send_event_locked - send DRM event to file descriptor
+ * @dev: DRM device
+ * @e: DRM event to deliver
+ *
+ * This function sends the event @e, initialized with drm_event_reserve_init(),
+ * to its associated userspace DRM file. Callers must already hold
+ * &drm_device.event_lock, see drm_send_event() for the unlocked version.
+ *
+ * Note that the core will take care of unlinking and disarming events when the
+ * corresponding DRM file is closed. Drivers need not worry about whether the
+ * DRM file for this event still exists and can call this function upon
+ * completion of the asynchronous work unconditionally.
+ */
+void drm_send_event_locked(struct drm_device *dev, struct drm_pending_event *e)
+{
+	drm_send_event_helper(dev, e, 0);
+}
 EXPORT_SYMBOL(drm_send_event_locked);
 
 /**
@@ -836,7 +880,7 @@ void drm_send_event(struct drm_device *dev, struct drm_pending_event *e)
 	unsigned long irqflags;
 
 	spin_lock_irqsave(&dev->event_lock, irqflags);
-	drm_send_event_locked(dev, e);
+	drm_send_event_helper(dev, e, 0);
 	spin_unlock_irqrestore(&dev->event_lock, irqflags);
 }
 EXPORT_SYMBOL(drm_send_event);
diff --git a/drivers/gpu/drm/drm_vblank.c b/drivers/gpu/drm/drm_vblank.c
index 30912d8f82a5..893165eeddf3 100644
--- a/drivers/gpu/drm/drm_vblank.c
+++ b/drivers/gpu/drm/drm_vblank.c
@@ -1006,7 +1006,14 @@ static void send_vblank_event(struct drm_device *dev,
 		break;
 	}
 	trace_drm_vblank_event_delivered(e->base.file_priv, e->pipe, seq);
-	drm_send_event_locked(dev, &e->base);
+	/*
+	 * Use the same timestamp for any associated fence signal to avoid
+	 * mismatch in timestamps for vsync & fence events triggered by the
+	 * same HW event. Frameworks like SurfaceFlinger in Android expects the
+	 * retire-fence timestamp to match exactly with HW vsync as it uses it
+	 * for its software vsync modeling.
+	 */
+	drm_send_event_timestamp_locked(dev, &e->base, now);
 }
 
 /**
diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile
index 2ae471518d9a..2385a7505f5d 100644
--- a/drivers/gpu/drm/i915/Makefile
+++ b/drivers/gpu/drm/i915/Makefile
@@ -21,7 +21,6 @@ subdir-ccflags-y += $(call cc-disable-warning, unused-but-set-variable)
 subdir-ccflags-y += $(call cc-disable-warning, sign-compare)
 subdir-ccflags-y += $(call cc-disable-warning, sometimes-uninitialized)
 subdir-ccflags-y += $(call cc-disable-warning, initializer-overrides)
-subdir-ccflags-y += $(call cc-disable-warning, uninitialized)
 subdir-ccflags-y += $(call cc-disable-warning, frame-address)
 subdir-ccflags-$(CONFIG_DRM_I915_WERROR) += -Werror
 
diff --git a/drivers/gpu/drm/i915/display/intel_crtc.c b/drivers/gpu/drm/i915/display/intel_crtc.c
index 57b0a3ebe908..8e77ca7ddf11 100644
--- a/drivers/gpu/drm/i915/display/intel_crtc.c
+++ b/drivers/gpu/drm/i915/display/intel_crtc.c
@@ -109,7 +109,6 @@ void intel_crtc_state_reset(struct intel_crtc_state *crtc_state,
 	crtc_state->cpu_transcoder = INVALID_TRANSCODER;
 	crtc_state->master_transcoder = INVALID_TRANSCODER;
 	crtc_state->hsw_workaround_pipe = INVALID_PIPE;
-	crtc_state->output_format = INTEL_OUTPUT_FORMAT_INVALID;
 	crtc_state->scaler_state.scaler_id = -1;
 	crtc_state->mst_master_transcoder = INVALID_TRANSCODER;
 }
diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index 7ea1e5b487b6..8d7aaa68c6f6 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -10211,7 +10211,6 @@ static void snprintf_output_types(char *buf, size_t len,
 }
 
 static const char * const output_format_str[] = {
-	[INTEL_OUTPUT_FORMAT_INVALID] = "Invalid",
 	[INTEL_OUTPUT_FORMAT_RGB] = "RGB",
 	[INTEL_OUTPUT_FORMAT_YCBCR420] = "YCBCR4:2:0",
 	[INTEL_OUTPUT_FORMAT_YCBCR444] = "YCBCR4:4:4",
@@ -10220,7 +10219,7 @@ static const char * const output_format_str[] = {
 static const char *output_formats(enum intel_output_format format)
 {
 	if (format >= ARRAY_SIZE(output_format_str))
-		format = INTEL_OUTPUT_FORMAT_INVALID;
+		return "invalid";
 	return output_format_str[format];
 }
 
diff --git a/drivers/gpu/drm/i915/display/intel_display_types.h b/drivers/gpu/drm/i915/display/intel_display_types.h
index 39397748b4b0..184ecbbcec99 100644
--- a/drivers/gpu/drm/i915/display/intel_display_types.h
+++ b/drivers/gpu/drm/i915/display/intel_display_types.h
@@ -830,7 +830,6 @@ struct intel_crtc_wm_state {
 };
 
 enum intel_output_format {
-	INTEL_OUTPUT_FORMAT_INVALID,
 	INTEL_OUTPUT_FORMAT_RGB,
 	INTEL_OUTPUT_FORMAT_YCBCR420,
 	INTEL_OUTPUT_FORMAT_YCBCR444,
diff --git a/drivers/gpu/drm/i915/gvt/cmd_parser.c b/drivers/gpu/drm/i915/gvt/cmd_parser.c
index d54ea0e4681d..fef1e857cefc 100644
--- a/drivers/gpu/drm/i915/gvt/cmd_parser.c
+++ b/drivers/gpu/drm/i915/gvt/cmd_parser.c
@@ -41,6 +41,7 @@
 #include "gt/intel_lrc.h"
 #include "gt/intel_ring.h"
 #include "gt/intel_gt_requests.h"
+#include "gt/shmem_utils.h"
 #include "gvt.h"
 #include "i915_pvinfo.h"
 #include "trace.h"
@@ -3094,71 +3095,28 @@ int intel_gvt_scan_and_shadow_wa_ctx(struct intel_shadow_wa_ctx *wa_ctx)
  */
 void intel_gvt_update_reg_whitelist(struct intel_vgpu *vgpu)
 {
+	const unsigned long start = LRC_STATE_PN * PAGE_SIZE;
 	struct intel_gvt *gvt = vgpu->gvt;
-	struct drm_i915_private *dev_priv = gvt->gt->i915;
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
-	const unsigned long start = LRC_STATE_PN * PAGE_SIZE;
-	struct i915_request *rq;
-	struct intel_vgpu_submission *s = &vgpu->submission;
-	struct i915_request *requests[I915_NUM_ENGINES] = {};
-	bool is_ctx_pinned[I915_NUM_ENGINES] = {};
-	int ret = 0;
 
 	if (gvt->is_reg_whitelist_updated)
 		return;
 
-	for_each_engine(engine, &dev_priv->gt, id) {
-		ret = intel_context_pin(s->shadow[id]);
-		if (ret) {
-			gvt_vgpu_err("fail to pin shadow ctx\n");
-			goto out;
-		}
-		is_ctx_pinned[id] = true;
-
-		rq = i915_request_create(s->shadow[id]);
-		if (IS_ERR(rq)) {
-			gvt_vgpu_err("fail to alloc default request\n");
-			ret = -EIO;
-			goto out;
-		}
-		requests[id] = i915_request_get(rq);
-		i915_request_add(rq);
-	}
-
-	if (intel_gt_wait_for_idle(&dev_priv->gt,
-				I915_GEM_IDLE_TIMEOUT) == -ETIME) {
-		ret = -EIO;
-		goto out;
-	}
-
 	/* scan init ctx to update cmd accessible list */
-	for_each_engine(engine, &dev_priv->gt, id) {
-		int size = engine->context_size - PAGE_SIZE;
-		void *vaddr;
+	for_each_engine(engine, gvt->gt, id) {
 		struct parser_exec_state s;
-		struct drm_i915_gem_object *obj;
-		struct i915_request *rq;
-
-		rq = requests[id];
-		GEM_BUG_ON(!i915_request_completed(rq));
-		GEM_BUG_ON(!intel_context_is_pinned(rq->context));
-		obj = rq->context->state->obj;
-
-		if (!obj) {
-			ret = -EIO;
-			goto out;
-		}
+		void *vaddr;
+		int ret;
 
-		i915_gem_object_set_cache_coherency(obj,
-						    I915_CACHE_LLC);
+		if (!engine->default_state)
+			continue;
 
-		vaddr = i915_gem_object_pin_map(obj, I915_MAP_WB);
+		vaddr = shmem_pin_map(engine->default_state);
 		if (IS_ERR(vaddr)) {
-			gvt_err("failed to pin init ctx obj, ring=%d, err=%lx\n",
-				id, PTR_ERR(vaddr));
-			ret = PTR_ERR(vaddr);
-			goto out;
+			gvt_err("failed to map %s->default state, err:%zd\n",
+				engine->name, PTR_ERR(vaddr));
+			return;
 		}
 
 		s.buf_type = RING_BUFFER_CTX;
@@ -3166,9 +3124,9 @@ void intel_gvt_update_reg_whitelist(struct intel_vgpu *vgpu)
 		s.vgpu = vgpu;
 		s.engine = engine;
 		s.ring_start = 0;
-		s.ring_size = size;
+		s.ring_size = engine->context_size - start;
 		s.ring_head = 0;
-		s.ring_tail = size;
+		s.ring_tail = s.ring_size;
 		s.rb_va = vaddr + start;
 		s.workload = NULL;
 		s.is_ctx_wa = false;
@@ -3176,29 +3134,18 @@ void intel_gvt_update_reg_whitelist(struct intel_vgpu *vgpu)
 
 		/* skipping the first RING_CTX_SIZE(0x50) dwords */
 		ret = ip_gma_set(&s, RING_CTX_SIZE);
-		if (ret) {
-			i915_gem_object_unpin_map(obj);
-			goto out;
+		if (ret == 0) {
+			ret = command_scan(&s, 0, s.ring_size, 0, s.ring_size);
+			if (ret)
+				gvt_err("Scan init ctx error\n");
 		}
 
-		ret = command_scan(&s, 0, size, 0, size);
+		shmem_unpin_map(engine->default_state, vaddr);
 		if (ret)
-			gvt_err("Scan init ctx error\n");
-
-		i915_gem_object_unpin_map(obj);
+			return;
 	}
 
-out:
-	if (!ret)
-		gvt->is_reg_whitelist_updated = true;
-
-	for (id = 0; id < I915_NUM_ENGINES ; id++) {
-		if (requests[id])
-			i915_request_put(requests[id]);
-
-		if (is_ctx_pinned[id])
-			intel_context_unpin(s->shadow[id]);
-	}
+	gvt->is_reg_whitelist_updated = true;
 }
 
 int intel_gvt_scan_engine_context(struct intel_vgpu_workload *workload)
diff --git a/drivers/gpu/drm/i915/gvt/execlist.c b/drivers/gpu/drm/i915/gvt/execlist.c
index 158873f269b1..c8dcda6d4f0d 100644
--- a/drivers/gpu/drm/i915/gvt/execlist.c
+++ b/drivers/gpu/drm/i915/gvt/execlist.c
@@ -522,12 +522,11 @@ static void init_vgpu_execlist(struct intel_vgpu *vgpu,
 static void clean_execlist(struct intel_vgpu *vgpu,
 			   intel_engine_mask_t engine_mask)
 {
-	struct drm_i915_private *dev_priv = vgpu->gvt->gt->i915;
-	struct intel_engine_cs *engine;
 	struct intel_vgpu_submission *s = &vgpu->submission;
+	struct intel_engine_cs *engine;
 	intel_engine_mask_t tmp;
 
-	for_each_engine_masked(engine, &dev_priv->gt, engine_mask, tmp) {
+	for_each_engine_masked(engine, vgpu->gvt->gt, engine_mask, tmp) {
 		kfree(s->ring_scan_buffer[engine->id]);
 		s->ring_scan_buffer[engine->id] = NULL;
 		s->ring_scan_buffer_size[engine->id] = 0;
@@ -537,11 +536,10 @@ static void clean_execlist(struct intel_vgpu *vgpu,
 static void reset_execlist(struct intel_vgpu *vgpu,
 			   intel_engine_mask_t engine_mask)
 {
-	struct drm_i915_private *dev_priv = vgpu->gvt->gt->i915;
 	struct intel_engine_cs *engine;
 	intel_engine_mask_t tmp;
 
-	for_each_engine_masked(engine, &dev_priv->gt, engine_mask, tmp)
+	for_each_engine_masked(engine, vgpu->gvt->gt, engine_mask, tmp)
 		init_vgpu_execlist(vgpu, engine);
 }
 
diff --git a/drivers/gpu/drm/i915/gvt/scheduler.c b/drivers/gpu/drm/i915/gvt/scheduler.c
index 43f31c2eab14..fc735692f21f 100644
--- a/drivers/gpu/drm/i915/gvt/scheduler.c
+++ b/drivers/gpu/drm/i915/gvt/scheduler.c
@@ -412,7 +412,9 @@ static void release_shadow_wa_ctx(struct intel_shadow_wa_ctx *wa_ctx)
 	if (!wa_ctx->indirect_ctx.obj)
 		return;
 
+	i915_gem_object_lock(wa_ctx->indirect_ctx.obj, NULL);
 	i915_gem_object_unpin_map(wa_ctx->indirect_ctx.obj);
+	i915_gem_object_unlock(wa_ctx->indirect_ctx.obj);
 	i915_gem_object_put(wa_ctx->indirect_ctx.obj);
 
 	wa_ctx->indirect_ctx.obj = NULL;
@@ -520,6 +522,7 @@ static int prepare_shadow_batch_buffer(struct intel_vgpu_workload *workload)
 	struct intel_gvt *gvt = workload->vgpu->gvt;
 	const int gmadr_bytes = gvt->device_info.gmadr_bytes_in_cmd;
 	struct intel_vgpu_shadow_bb *bb;
+	struct i915_gem_ww_ctx ww;
 	int ret;
 
 	list_for_each_entry(bb, &workload->shadow_bb, list) {
@@ -544,10 +547,19 @@ static int prepare_shadow_batch_buffer(struct intel_vgpu_workload *workload)
 		 * directly
 		 */
 		if (!bb->ppgtt) {
-			bb->vma = i915_gem_object_ggtt_pin(bb->obj,
-							   NULL, 0, 0, 0);
+			i915_gem_ww_ctx_init(&ww, false);
+retry:
+			i915_gem_object_lock(bb->obj, &ww);
+
+			bb->vma = i915_gem_object_ggtt_pin_ww(bb->obj, &ww,
+							      NULL, 0, 0, 0);
 			if (IS_ERR(bb->vma)) {
 				ret = PTR_ERR(bb->vma);
+				if (ret == -EDEADLK) {
+					ret = i915_gem_ww_ctx_backoff(&ww);
+					if (!ret)
+						goto retry;
+				}
 				goto err;
 			}
 
@@ -561,13 +573,15 @@ static int prepare_shadow_batch_buffer(struct intel_vgpu_workload *workload)
 						      0);
 			if (ret)
 				goto err;
-		}
 
-		/* No one is going to touch shadow bb from now on. */
-		i915_gem_object_flush_map(bb->obj);
+			/* No one is going to touch shadow bb from now on. */
+			i915_gem_object_flush_map(bb->obj);
+			i915_gem_object_unlock(bb->obj);
+		}
 	}
 	return 0;
 err:
+	i915_gem_ww_ctx_fini(&ww);
 	release_shadow_batch_buffer(workload);
 	return ret;
 }
@@ -594,14 +608,29 @@ static int prepare_shadow_wa_ctx(struct intel_shadow_wa_ctx *wa_ctx)
 	unsigned char *per_ctx_va =
 		(unsigned char *)wa_ctx->indirect_ctx.shadow_va +
 		wa_ctx->indirect_ctx.size;
+	struct i915_gem_ww_ctx ww;
+	int ret;
 
 	if (wa_ctx->indirect_ctx.size == 0)
 		return 0;
 
-	vma = i915_gem_object_ggtt_pin(wa_ctx->indirect_ctx.obj, NULL,
-				       0, CACHELINE_BYTES, 0);
-	if (IS_ERR(vma))
-		return PTR_ERR(vma);
+	i915_gem_ww_ctx_init(&ww, false);
+retry:
+	i915_gem_object_lock(wa_ctx->indirect_ctx.obj, &ww);
+
+	vma = i915_gem_object_ggtt_pin_ww(wa_ctx->indirect_ctx.obj, &ww, NULL,
+					  0, CACHELINE_BYTES, 0);
+	if (IS_ERR(vma)) {
+		ret = PTR_ERR(vma);
+		if (ret == -EDEADLK) {
+			ret = i915_gem_ww_ctx_backoff(&ww);
+			if (!ret)
+				goto retry;
+		}
+		return ret;
+	}
+
+	i915_gem_object_unlock(wa_ctx->indirect_ctx.obj);
 
 	/* FIXME: we are not tracking our pinned VMA leaving it
 	 * up to the core to fix up the stray pin_count upon
@@ -635,12 +664,14 @@ static void release_shadow_batch_buffer(struct intel_vgpu_workload *workload)
 
 	list_for_each_entry_safe(bb, pos, &workload->shadow_bb, list) {
 		if (bb->obj) {
+			i915_gem_object_lock(bb->obj, NULL);
 			if (bb->va && !IS_ERR(bb->va))
 				i915_gem_object_unpin_map(bb->obj);
 
 			if (bb->vma && !IS_ERR(bb->vma))
 				i915_vma_unpin(bb->vma);
 
+			i915_gem_object_unlock(bb->obj);
 			i915_gem_object_put(bb->obj);
 		}
 		list_del(&bb->list);
@@ -1015,13 +1046,12 @@ void intel_vgpu_clean_workloads(struct intel_vgpu *vgpu,
 				intel_engine_mask_t engine_mask)
 {
 	struct intel_vgpu_submission *s = &vgpu->submission;
-	struct drm_i915_private *dev_priv = vgpu->gvt->gt->i915;
 	struct intel_engine_cs *engine;
 	struct intel_vgpu_workload *pos, *n;
 	intel_engine_mask_t tmp;
 
 	/* free the unsubmited workloads in the queues. */
-	for_each_engine_masked(engine, &dev_priv->gt, engine_mask, tmp) {
+	for_each_engine_masked(engine, vgpu->gvt->gt, engine_mask, tmp) {
 		list_for_each_entry_safe(pos, n,
 			&s->workload_q_head[engine->id], list) {
 			list_del_init(&pos->list);
diff --git a/drivers/gpu/drm/msm/adreno/a5xx.xml.h b/drivers/gpu/drm/msm/adreno/a5xx.xml.h
index 346cc6ff3a36..7b9fcfe95c04 100644
--- a/drivers/gpu/drm/msm/adreno/a5xx.xml.h
+++ b/drivers/gpu/drm/msm/adreno/a5xx.xml.h
@@ -2367,6 +2367,8 @@ static inline uint32_t A5XX_VSC_RESOLVE_CNTL_Y(uint32_t val)
 
 #define REG_A5XX_UCHE_ADDR_MODE_CNTL				0x00000e80
 
+#define REG_A5XX_UCHE_MODE_CNTL					0x00000e81
+
 #define REG_A5XX_UCHE_SVM_CNTL					0x00000e82
 
 #define REG_A5XX_UCHE_WRITE_THRU_BASE_LO			0x00000e87
diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
index a5af223eaf50..7e553d3efeb2 100644
--- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
@@ -222,7 +222,7 @@ static void a5xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit)
 	a5xx_preempt_trigger(gpu);
 }
 
-static const struct {
+static const struct adreno_five_hwcg_regs {
 	u32 offset;
 	u32 value;
 } a5xx_hwcg[] = {
@@ -318,16 +318,124 @@ static const struct {
 	{REG_A5XX_RBBM_CLOCK_DELAY_TSE_RAS_RBBM, 0x00004000},
 	{REG_A5XX_RBBM_CLOCK_DELAY_GPC, 0x00000200},
 	{REG_A5XX_RBBM_CLOCK_DELAY_VFD, 0x00002222}
+}, a50x_hwcg[] = {
+	{REG_A5XX_RBBM_CLOCK_CNTL_SP0, 0x02222222},
+	{REG_A5XX_RBBM_CLOCK_CNTL2_SP0, 0x02222220},
+	{REG_A5XX_RBBM_CLOCK_HYST_SP0, 0x0000F3CF},
+	{REG_A5XX_RBBM_CLOCK_DELAY_SP0, 0x00000080},
+	{REG_A5XX_RBBM_CLOCK_CNTL_TP0, 0x22222222},
+	{REG_A5XX_RBBM_CLOCK_CNTL2_TP0, 0x22222222},
+	{REG_A5XX_RBBM_CLOCK_CNTL3_TP0, 0x00002222},
+	{REG_A5XX_RBBM_CLOCK_HYST_TP0, 0x77777777},
+	{REG_A5XX_RBBM_CLOCK_HYST2_TP0, 0x77777777},
+	{REG_A5XX_RBBM_CLOCK_HYST3_TP0, 0x00007777},
+	{REG_A5XX_RBBM_CLOCK_DELAY_TP0, 0x11111111},
+	{REG_A5XX_RBBM_CLOCK_DELAY2_TP0, 0x11111111},
+	{REG_A5XX_RBBM_CLOCK_DELAY3_TP0, 0x00001111},
+	{REG_A5XX_RBBM_CLOCK_CNTL2_UCHE, 0x22222222},
+	{REG_A5XX_RBBM_CLOCK_CNTL3_UCHE, 0x22222222},
+	{REG_A5XX_RBBM_CLOCK_CNTL4_UCHE, 0x00222222},
+	{REG_A5XX_RBBM_CLOCK_CNTL_UCHE, 0x22222222},
+	{REG_A5XX_RBBM_CLOCK_HYST_UCHE, 0x00FFFFF4},
+	{REG_A5XX_RBBM_CLOCK_DELAY_UCHE, 0x00000002},
+	{REG_A5XX_RBBM_CLOCK_CNTL_RB0, 0x22222222},
+	{REG_A5XX_RBBM_CLOCK_CNTL2_RB0, 0x00222222},
+	{REG_A5XX_RBBM_CLOCK_CNTL_CCU0, 0x00022220},
+	{REG_A5XX_RBBM_CLOCK_CNTL_RAC, 0x05522222},
+	{REG_A5XX_RBBM_CLOCK_CNTL2_RAC, 0x00505555},
+	{REG_A5XX_RBBM_CLOCK_HYST_RB_CCU0, 0x04040404},
+	{REG_A5XX_RBBM_CLOCK_HYST_RAC, 0x07444044},
+	{REG_A5XX_RBBM_CLOCK_DELAY_RB_CCU_L1_0, 0x00000002},
+	{REG_A5XX_RBBM_CLOCK_DELAY_RAC, 0x00010011},
+	{REG_A5XX_RBBM_CLOCK_CNTL_TSE_RAS_RBBM, 0x04222222},
+	{REG_A5XX_RBBM_CLOCK_MODE_GPC, 0x02222222},
+	{REG_A5XX_RBBM_CLOCK_MODE_VFD, 0x00002222},
+	{REG_A5XX_RBBM_CLOCK_HYST_TSE_RAS_RBBM, 0x00000000},
+	{REG_A5XX_RBBM_CLOCK_HYST_GPC, 0x04104004},
+	{REG_A5XX_RBBM_CLOCK_HYST_VFD, 0x00000000},
+	{REG_A5XX_RBBM_CLOCK_DELAY_HLSQ, 0x00000000},
+	{REG_A5XX_RBBM_CLOCK_DELAY_TSE_RAS_RBBM, 0x00004000},
+	{REG_A5XX_RBBM_CLOCK_DELAY_GPC, 0x00000200},
+	{REG_A5XX_RBBM_CLOCK_DELAY_VFD, 0x00002222},
+}, a512_hwcg[] = {
+	{REG_A5XX_RBBM_CLOCK_CNTL_SP0, 0x02222222},
+	{REG_A5XX_RBBM_CLOCK_CNTL_SP1, 0x02222222},
+	{REG_A5XX_RBBM_CLOCK_CNTL2_SP0, 0x02222220},
+	{REG_A5XX_RBBM_CLOCK_CNTL2_SP1, 0x02222220},
+	{REG_A5XX_RBBM_CLOCK_HYST_SP0, 0x0000F3CF},
+	{REG_A5XX_RBBM_CLOCK_HYST_SP1, 0x0000F3CF},
+	{REG_A5XX_RBBM_CLOCK_DELAY_SP0, 0x00000080},
+	{REG_A5XX_RBBM_CLOCK_DELAY_SP1, 0x00000080},
+	{REG_A5XX_RBBM_CLOCK_CNTL_TP0, 0x22222222},
+	{REG_A5XX_RBBM_CLOCK_CNTL_TP1, 0x22222222},
+	{REG_A5XX_RBBM_CLOCK_CNTL2_TP0, 0x22222222},
+	{REG_A5XX_RBBM_CLOCK_CNTL2_TP1, 0x22222222},
+	{REG_A5XX_RBBM_CLOCK_CNTL3_TP0, 0x00002222},
+	{REG_A5XX_RBBM_CLOCK_CNTL3_TP1, 0x00002222},
+	{REG_A5XX_RBBM_CLOCK_HYST_TP0, 0x77777777},
+	{REG_A5XX_RBBM_CLOCK_HYST_TP1, 0x77777777},
+	{REG_A5XX_RBBM_CLOCK_HYST2_TP0, 0x77777777},
+	{REG_A5XX_RBBM_CLOCK_HYST2_TP1, 0x77777777},
+	{REG_A5XX_RBBM_CLOCK_HYST3_TP0, 0x00007777},
+	{REG_A5XX_RBBM_CLOCK_HYST3_TP1, 0x00007777},
+	{REG_A5XX_RBBM_CLOCK_DELAY_TP0, 0x11111111},
+	{REG_A5XX_RBBM_CLOCK_DELAY_TP1, 0x11111111},
+	{REG_A5XX_RBBM_CLOCK_DELAY2_TP0, 0x11111111},
+	{REG_A5XX_RBBM_CLOCK_DELAY2_TP1, 0x11111111},
+	{REG_A5XX_RBBM_CLOCK_DELAY3_TP0, 0x00001111},
+	{REG_A5XX_RBBM_CLOCK_DELAY3_TP1, 0x00001111},
+	{REG_A5XX_RBBM_CLOCK_CNTL_UCHE, 0x22222222},
+	{REG_A5XX_RBBM_CLOCK_CNTL2_UCHE, 0x22222222},
+	{REG_A5XX_RBBM_CLOCK_CNTL3_UCHE, 0x22222222},
+	{REG_A5XX_RBBM_CLOCK_CNTL4_UCHE, 0x00222222},
+	{REG_A5XX_RBBM_CLOCK_HYST_UCHE, 0x00444444},
+	{REG_A5XX_RBBM_CLOCK_DELAY_UCHE, 0x00000002},
+	{REG_A5XX_RBBM_CLOCK_CNTL_RB0, 0x22222222},
+	{REG_A5XX_RBBM_CLOCK_CNTL_RB1, 0x22222222},
+	{REG_A5XX_RBBM_CLOCK_CNTL2_RB0, 0x00222222},
+	{REG_A5XX_RBBM_CLOCK_CNTL2_RB1, 0x00222222},
+	{REG_A5XX_RBBM_CLOCK_CNTL_CCU0, 0x00022220},
+	{REG_A5XX_RBBM_CLOCK_CNTL_CCU1, 0x00022220},
+	{REG_A5XX_RBBM_CLOCK_CNTL_RAC, 0x05522222},
+	{REG_A5XX_RBBM_CLOCK_CNTL2_RAC, 0x00505555},
+	{REG_A5XX_RBBM_CLOCK_HYST_RB_CCU0, 0x04040404},
+	{REG_A5XX_RBBM_CLOCK_HYST_RB_CCU1, 0x04040404},
+	{REG_A5XX_RBBM_CLOCK_HYST_RAC, 0x07444044},
+	{REG_A5XX_RBBM_CLOCK_DELAY_RB_CCU_L1_0, 0x00000002},
+	{REG_A5XX_RBBM_CLOCK_DELAY_RB_CCU_L1_1, 0x00000002},
+	{REG_A5XX_RBBM_CLOCK_DELAY_RAC, 0x00010011},
+	{REG_A5XX_RBBM_CLOCK_CNTL_TSE_RAS_RBBM, 0x04222222},
+	{REG_A5XX_RBBM_CLOCK_MODE_GPC, 0x02222222},
+	{REG_A5XX_RBBM_CLOCK_MODE_VFD, 0x00002222},
+	{REG_A5XX_RBBM_CLOCK_HYST_TSE_RAS_RBBM, 0x00000000},
+	{REG_A5XX_RBBM_CLOCK_HYST_GPC, 0x04104004},
+	{REG_A5XX_RBBM_CLOCK_HYST_VFD, 0x00000000},
+	{REG_A5XX_RBBM_CLOCK_DELAY_HLSQ, 0x00000000},
+	{REG_A5XX_RBBM_CLOCK_DELAY_TSE_RAS_RBBM, 0x00004000},
+	{REG_A5XX_RBBM_CLOCK_DELAY_GPC, 0x00000200},
+	{REG_A5XX_RBBM_CLOCK_DELAY_VFD, 0x00002222},
 };
 
 void a5xx_set_hwcg(struct msm_gpu *gpu, bool state)
 {
 	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
-	unsigned int i;
+	const struct adreno_five_hwcg_regs *regs;
+	unsigned int i, sz;
+
+	if (adreno_is_a508(adreno_gpu)) {
+		regs = a50x_hwcg;
+		sz = ARRAY_SIZE(a50x_hwcg);
+	} else if (adreno_is_a509(adreno_gpu) || adreno_is_a512(adreno_gpu)) {
+		regs = a512_hwcg;
+		sz = ARRAY_SIZE(a512_hwcg);
+	} else {
+		regs = a5xx_hwcg;
+		sz = ARRAY_SIZE(a5xx_hwcg);
+	}
 
-	for (i = 0; i < ARRAY_SIZE(a5xx_hwcg); i++)
-		gpu_write(gpu, a5xx_hwcg[i].offset,
-			state ? a5xx_hwcg[i].value : 0);
+	for (i = 0; i < sz; i++)
+		gpu_write(gpu, regs[i].offset,
+			  state ? regs[i].value : 0);
 
 	if (adreno_is_a540(adreno_gpu)) {
 		gpu_write(gpu, REG_A5XX_RBBM_CLOCK_DELAY_GPMU, state ? 0x00000770 : 0);
@@ -538,11 +646,13 @@ static int a5xx_hw_init(struct msm_gpu *gpu)
 {
 	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
 	struct a5xx_gpu *a5xx_gpu = to_a5xx_gpu(adreno_gpu);
+	u32 regbit;
 	int ret;
 
 	gpu_write(gpu, REG_A5XX_VBIF_ROUND_ROBIN_QOS_ARB, 0x00000003);
 
-	if (adreno_is_a540(adreno_gpu))
+	if (adreno_is_a509(adreno_gpu) || adreno_is_a512(adreno_gpu) ||
+	    adreno_is_a540(adreno_gpu))
 		gpu_write(gpu, REG_A5XX_VBIF_GATE_OFF_WRREQ_EN, 0x00000009);
 
 	/* Make all blocks contribute to the GPU BUSY perf counter */
@@ -604,29 +714,48 @@ static int a5xx_hw_init(struct msm_gpu *gpu)
 		0x00100000 + adreno_gpu->gmem - 1);
 	gpu_write(gpu, REG_A5XX_UCHE_GMEM_RANGE_MAX_HI, 0x00000000);
 
-	if (adreno_is_a510(adreno_gpu)) {
+	if (adreno_is_a508(adreno_gpu) || adreno_is_a510(adreno_gpu)) {
 		gpu_write(gpu, REG_A5XX_CP_MEQ_THRESHOLDS, 0x20);
-		gpu_write(gpu, REG_A5XX_CP_MERCIU_SIZE, 0x20);
+		if (adreno_is_a508(adreno_gpu))
+			gpu_write(gpu, REG_A5XX_CP_MERCIU_SIZE, 0x400);
+		else
+			gpu_write(gpu, REG_A5XX_CP_MERCIU_SIZE, 0x20);
 		gpu_write(gpu, REG_A5XX_CP_ROQ_THRESHOLDS_2, 0x40000030);
 		gpu_write(gpu, REG_A5XX_CP_ROQ_THRESHOLDS_1, 0x20100D0A);
-		gpu_write(gpu, REG_A5XX_PC_DBG_ECO_CNTL,
-			  (0x200 << 11 | 0x200 << 22));
 	} else {
 		gpu_write(gpu, REG_A5XX_CP_MEQ_THRESHOLDS, 0x40);
 		if (adreno_is_a530(adreno_gpu))
 			gpu_write(gpu, REG_A5XX_CP_MERCIU_SIZE, 0x40);
-		if (adreno_is_a540(adreno_gpu))
+		else
 			gpu_write(gpu, REG_A5XX_CP_MERCIU_SIZE, 0x400);
 		gpu_write(gpu, REG_A5XX_CP_ROQ_THRESHOLDS_2, 0x80000060);
 		gpu_write(gpu, REG_A5XX_CP_ROQ_THRESHOLDS_1, 0x40201B16);
+	}
+
+	if (adreno_is_a508(adreno_gpu))
+		gpu_write(gpu, REG_A5XX_PC_DBG_ECO_CNTL,
+			  (0x100 << 11 | 0x100 << 22));
+	else if (adreno_is_a509(adreno_gpu) || adreno_is_a510(adreno_gpu) ||
+		 adreno_is_a512(adreno_gpu))
+		gpu_write(gpu, REG_A5XX_PC_DBG_ECO_CNTL,
+			  (0x200 << 11 | 0x200 << 22));
+	else
 		gpu_write(gpu, REG_A5XX_PC_DBG_ECO_CNTL,
 			  (0x400 << 11 | 0x300 << 22));
-	}
 
 	if (adreno_gpu->info->quirks & ADRENO_QUIRK_TWO_PASS_USE_WFI)
 		gpu_rmw(gpu, REG_A5XX_PC_DBG_ECO_CNTL, 0, (1 << 8));
 
-	gpu_write(gpu, REG_A5XX_PC_DBG_ECO_CNTL, 0xc0200100);
+	/*
+	 * Disable the RB sampler datapath DP2 clock gating optimization
+	 * for 1-SP GPUs, as it is enabled by default.
+	 */
+	if (adreno_is_a508(adreno_gpu) || adreno_is_a509(adreno_gpu) ||
+	    adreno_is_a512(adreno_gpu))
+		gpu_rmw(gpu, REG_A5XX_RB_DBG_ECO_CNTL, 0, (1 << 9));
+
+	/* Disable UCHE global filter as SP can invalidate/flush independently */
+	gpu_write(gpu, REG_A5XX_UCHE_MODE_CNTL, BIT(29));
 
 	/* Enable USE_RETENTION_FLOPS */
 	gpu_write(gpu, REG_A5XX_CP_CHICKEN_DBG, 0x02000000);
@@ -653,10 +782,20 @@ static int a5xx_hw_init(struct msm_gpu *gpu)
 	gpu_write(gpu, REG_A5XX_RBBM_AHB_CNTL2, 0x0000003F);
 
 	/* Set the highest bank bit */
-	gpu_write(gpu, REG_A5XX_TPL1_MODE_CNTL, 2 << 7);
-	gpu_write(gpu, REG_A5XX_RB_MODE_CNTL, 2 << 1);
 	if (adreno_is_a540(adreno_gpu))
-		gpu_write(gpu, REG_A5XX_UCHE_DBG_ECO_CNTL_2, 2);
+		regbit = 2;
+	else
+		regbit = 1;
+
+	gpu_write(gpu, REG_A5XX_TPL1_MODE_CNTL, regbit << 7);
+	gpu_write(gpu, REG_A5XX_RB_MODE_CNTL, regbit << 1);
+
+	if (adreno_is_a509(adreno_gpu) || adreno_is_a512(adreno_gpu) ||
+	    adreno_is_a540(adreno_gpu))
+		gpu_write(gpu, REG_A5XX_UCHE_DBG_ECO_CNTL_2, regbit);
+
+	/* Disable All flat shading optimization (ALLFLATOPTDIS) */
+	gpu_rmw(gpu, REG_A5XX_VPC_DBG_ECO_CNTL, 0, (1 << 10));
 
 	/* Protect registers from the CP */
 	gpu_write(gpu, REG_A5XX_CP_PROTECT_CNTL, 0x00000007);
@@ -688,12 +827,14 @@ static int a5xx_hw_init(struct msm_gpu *gpu)
 
 	/* VPC */
 	gpu_write(gpu, REG_A5XX_CP_PROTECT(14), ADRENO_PROTECT_RW(0xE68, 8));
-	gpu_write(gpu, REG_A5XX_CP_PROTECT(15), ADRENO_PROTECT_RW(0xE70, 4));
+	gpu_write(gpu, REG_A5XX_CP_PROTECT(15), ADRENO_PROTECT_RW(0xE70, 16));
 
 	/* UCHE */
 	gpu_write(gpu, REG_A5XX_CP_PROTECT(16), ADRENO_PROTECT_RW(0xE80, 16));
 
-	if (adreno_is_a530(adreno_gpu) || adreno_is_a510(adreno_gpu))
+	if (adreno_is_a508(adreno_gpu) || adreno_is_a509(adreno_gpu) ||
+	    adreno_is_a510(adreno_gpu) || adreno_is_a512(adreno_gpu) ||
+	    adreno_is_a530(adreno_gpu))
 		gpu_write(gpu, REG_A5XX_CP_PROTECT(17),
 			ADRENO_PROTECT_RW(0x10000, 0x8000));
 
@@ -735,7 +876,8 @@ static int a5xx_hw_init(struct msm_gpu *gpu)
 	if (ret)
 		return ret;
 
-	if (!adreno_is_a510(adreno_gpu))
+	if (!(adreno_is_a508(adreno_gpu) || adreno_is_a509(adreno_gpu) ||
+	      adreno_is_a510(adreno_gpu) || adreno_is_a512(adreno_gpu)))
 		a5xx_gpmu_ucode_init(gpu);
 
 	ret = a5xx_ucode_init(gpu);
@@ -1168,7 +1310,8 @@ static int a5xx_pm_resume(struct msm_gpu *gpu)
 	if (ret)
 		return ret;
 
-	if (adreno_is_a510(adreno_gpu)) {
+	/* Adreno 508, 509, 510, 512 needs manual RBBM sus/res control */
+	if (!(adreno_is_a530(adreno_gpu) || adreno_is_a540(adreno_gpu))) {
 		/* Halt the sp_input_clk at HM level */
 		gpu_write(gpu, REG_A5XX_RBBM_CLOCK_CNTL, 0x00000055);
 		a5xx_set_hwcg(gpu, true);
@@ -1210,8 +1353,8 @@ static int a5xx_pm_suspend(struct msm_gpu *gpu)
 	u32 mask = 0xf;
 	int i, ret;
 
-	/* A510 has 3 XIN ports in VBIF */
-	if (adreno_is_a510(adreno_gpu))
+	/* A508, A510 have 3 XIN ports in VBIF */
+	if (adreno_is_a508(adreno_gpu) || adreno_is_a510(adreno_gpu))
 		mask = 0x7;
 
 	/* Clear the VBIF pipe before shutting down */
@@ -1223,10 +1366,12 @@ static int a5xx_pm_suspend(struct msm_gpu *gpu)
 
 	/*
 	 * Reset the VBIF before power collapse to avoid issue with FIFO
-	 * entries
+	 * entries on Adreno A510 and A530 (the others will tend to lock up)
 	 */
-	gpu_write(gpu, REG_A5XX_RBBM_BLOCK_SW_RESET_CMD, 0x003C0000);
-	gpu_write(gpu, REG_A5XX_RBBM_BLOCK_SW_RESET_CMD, 0x00000000);
+	if (adreno_is_a510(adreno_gpu) || adreno_is_a530(adreno_gpu)) {
+		gpu_write(gpu, REG_A5XX_RBBM_BLOCK_SW_RESET_CMD, 0x003C0000);
+		gpu_write(gpu, REG_A5XX_RBBM_BLOCK_SW_RESET_CMD, 0x00000000);
+	}
 
 	ret = msm_gpu_pm_suspend(gpu);
 	if (ret)
diff --git a/drivers/gpu/drm/msm/adreno/a5xx_power.c b/drivers/gpu/drm/msm/adreno/a5xx_power.c
index f176a6f3eff6..5ccc9da455a1 100644
--- a/drivers/gpu/drm/msm/adreno/a5xx_power.c
+++ b/drivers/gpu/drm/msm/adreno/a5xx_power.c
@@ -298,7 +298,7 @@ int a5xx_power_init(struct msm_gpu *gpu)
 	int ret;
 
 	/* Not all A5xx chips have a GPMU */
-	if (adreno_is_a510(adreno_gpu))
+	if (!(adreno_is_a530(adreno_gpu) || adreno_is_a540(adreno_gpu)))
 		return 0;
 
 	/* Set up the limits management */
@@ -330,7 +330,7 @@ void a5xx_gpmu_ucode_init(struct msm_gpu *gpu)
 	unsigned int *data, *ptr, *cmds;
 	unsigned int cmds_size;
 
-	if (adreno_is_a510(adreno_gpu))
+	if (!(adreno_is_a530(adreno_gpu) || adreno_is_a540(adreno_gpu)))
 		return;
 
 	if (a5xx_gpu->gpmu_bo)
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
index 05e0ef58fe32..71c917f909af 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
@@ -245,37 +245,66 @@ static int a6xx_gmu_hfi_start(struct a6xx_gmu *gmu)
 	return ret;
 }
 
+struct a6xx_gmu_oob_bits {
+	int set, ack, set_new, ack_new;
+	const char *name;
+};
+
+/* These are the interrupt / ack bits for each OOB request that are set
+ * in a6xx_gmu_set_oob and a6xx_clear_oob
+ */
+static const struct a6xx_gmu_oob_bits a6xx_gmu_oob_bits[] = {
+	[GMU_OOB_GPU_SET] = {
+		.name = "GPU_SET",
+		.set = 16,
+		.ack = 24,
+		.set_new = 30,
+		.ack_new = 31,
+	},
+
+	[GMU_OOB_PERFCOUNTER_SET] = {
+		.name = "PERFCOUNTER",
+		.set = 17,
+		.ack = 25,
+		.set_new = 28,
+		.ack_new = 30,
+	},
+
+	[GMU_OOB_BOOT_SLUMBER] = {
+		.name = "BOOT_SLUMBER",
+		.set = 22,
+		.ack = 30,
+	},
+
+	[GMU_OOB_DCVS_SET] = {
+		.name = "GPU_DCVS",
+		.set = 23,
+		.ack = 31,
+	},
+};
+
 /* Trigger a OOB (out of band) request to the GMU */
 int a6xx_gmu_set_oob(struct a6xx_gmu *gmu, enum a6xx_gmu_oob_state state)
 {
 	int ret;
 	u32 val;
 	int request, ack;
-	const char *name;
 
-	switch (state) {
-	case GMU_OOB_GPU_SET:
-		if (gmu->legacy) {
-			request = GMU_OOB_GPU_SET_REQUEST;
-			ack = GMU_OOB_GPU_SET_ACK;
-		} else {
-			request = GMU_OOB_GPU_SET_REQUEST_NEW;
-			ack = GMU_OOB_GPU_SET_ACK_NEW;
-		}
-		name = "GPU_SET";
-		break;
-	case GMU_OOB_BOOT_SLUMBER:
-		request = GMU_OOB_BOOT_SLUMBER_REQUEST;
-		ack = GMU_OOB_BOOT_SLUMBER_ACK;
-		name = "BOOT_SLUMBER";
-		break;
-	case GMU_OOB_DCVS_SET:
-		request = GMU_OOB_DCVS_REQUEST;
-		ack = GMU_OOB_DCVS_ACK;
-		name = "GPU_DCVS";
-		break;
-	default:
+	if (state >= ARRAY_SIZE(a6xx_gmu_oob_bits))
 		return -EINVAL;
+
+	if (gmu->legacy) {
+		request = a6xx_gmu_oob_bits[state].set;
+		ack = a6xx_gmu_oob_bits[state].ack;
+	} else {
+		request = a6xx_gmu_oob_bits[state].set_new;
+		ack = a6xx_gmu_oob_bits[state].ack_new;
+		if (!request || !ack) {
+			DRM_DEV_ERROR(gmu->dev,
+				      "Invalid non-legacy GMU request %s\n",
+				      a6xx_gmu_oob_bits[state].name);
+			return -EINVAL;
+		}
 	}
 
 	/* Trigger the equested OOB operation */
@@ -288,7 +317,7 @@ int a6xx_gmu_set_oob(struct a6xx_gmu *gmu, enum a6xx_gmu_oob_state state)
 	if (ret)
 		DRM_DEV_ERROR(gmu->dev,
 			"Timeout waiting for GMU OOB set %s: 0x%x\n",
-				name,
+				a6xx_gmu_oob_bits[state].name,
 				gmu_read(gmu, REG_A6XX_GMU_GMU2HOST_INTR_INFO));
 
 	/* Clear the acknowledge interrupt */
@@ -300,27 +329,17 @@ int a6xx_gmu_set_oob(struct a6xx_gmu *gmu, enum a6xx_gmu_oob_state state)
 /* Clear a pending OOB state in the GMU */
 void a6xx_gmu_clear_oob(struct a6xx_gmu *gmu, enum a6xx_gmu_oob_state state)
 {
-	if (!gmu->legacy) {
-		WARN_ON(state != GMU_OOB_GPU_SET);
-		gmu_write(gmu, REG_A6XX_GMU_HOST2GMU_INTR_SET,
-			1 << GMU_OOB_GPU_SET_CLEAR_NEW);
+	int bit;
+
+	if (state >= ARRAY_SIZE(a6xx_gmu_oob_bits))
 		return;
-	}
 
-	switch (state) {
-	case GMU_OOB_GPU_SET:
-		gmu_write(gmu, REG_A6XX_GMU_HOST2GMU_INTR_SET,
-			1 << GMU_OOB_GPU_SET_CLEAR);
-		break;
-	case GMU_OOB_BOOT_SLUMBER:
-		gmu_write(gmu, REG_A6XX_GMU_HOST2GMU_INTR_SET,
-			1 << GMU_OOB_BOOT_SLUMBER_CLEAR);
-		break;
-	case GMU_OOB_DCVS_SET:
-		gmu_write(gmu, REG_A6XX_GMU_HOST2GMU_INTR_SET,
-			1 << GMU_OOB_DCVS_CLEAR);
-		break;
-	}
+	if (gmu->legacy)
+		bit = a6xx_gmu_oob_bits[state].ack;
+	else
+		bit = a6xx_gmu_oob_bits[state].ack_new;
+
+	gmu_write(gmu, REG_A6XX_GMU_HOST2GMU_INTR_SET, bit);
 }
 
 /* Enable CPU control of SPTP power power collapse */
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.h b/drivers/gpu/drm/msm/adreno/a6xx_gmu.h
index c6d2bced8e5d..71dfa60070cc 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.h
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.h
@@ -153,44 +153,27 @@ static inline void gmu_write_rscc(struct a6xx_gmu *gmu, u32 offset, u32 value)
  */
 
 enum a6xx_gmu_oob_state {
+	/*
+	 * Let the GMU know that a boot or slumber operation has started. The value in
+	 * REG_A6XX_GMU_BOOT_SLUMBER_OPTION lets the GMU know which operation we are
+	 * doing
+	 */
 	GMU_OOB_BOOT_SLUMBER = 0,
+	/*
+	 * Let the GMU know to not turn off any GPU registers while the CPU is in a
+	 * critical section
+	 */
 	GMU_OOB_GPU_SET,
+	/*
+	 * Set a new power level for the GPU when the CPU is doing frequency scaling
+	 */
 	GMU_OOB_DCVS_SET,
+	/*
+	 * Used to keep the GPU on for CPU-side reads of performance counters.
+	 */
+	GMU_OOB_PERFCOUNTER_SET,
 };
 
-/* These are the interrupt / ack bits for each OOB request that are set
- * in a6xx_gmu_set_oob and a6xx_clear_oob
- */
-
-/*
- * Let the GMU know that a boot or slumber operation has started. The value in
- * REG_A6XX_GMU_BOOT_SLUMBER_OPTION lets the GMU know which operation we are
- * doing
- */
-#define GMU_OOB_BOOT_SLUMBER_REQUEST	22
-#define GMU_OOB_BOOT_SLUMBER_ACK	30
-#define GMU_OOB_BOOT_SLUMBER_CLEAR	30
-
-/*
- * Set a new power level for the GPU when the CPU is doing frequency scaling
- */
-#define GMU_OOB_DCVS_REQUEST	23
-#define GMU_OOB_DCVS_ACK	31
-#define GMU_OOB_DCVS_CLEAR	31
-
-/*
- * Let the GMU know to not turn off any GPU registers while the CPU is in a
- * critical section
- */
-#define GMU_OOB_GPU_SET_REQUEST	16
-#define GMU_OOB_GPU_SET_ACK	24
-#define GMU_OOB_GPU_SET_CLEAR	24
-
-#define GMU_OOB_GPU_SET_REQUEST_NEW	30
-#define GMU_OOB_GPU_SET_ACK_NEW		31
-#define GMU_OOB_GPU_SET_CLEAR_NEW	31
-
-
 void a6xx_hfi_init(struct a6xx_gmu *gmu);
 int a6xx_hfi_start(struct a6xx_gmu *gmu, int boot_state);
 void a6xx_hfi_stop(struct a6xx_gmu *gmu);
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
index 130661898546..ba8e9d3cf0fe 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
@@ -10,6 +10,7 @@
 
 #include <linux/bitfield.h>
 #include <linux/devfreq.h>
+#include <linux/nvmem-consumer.h>
 #include <linux/soc/qcom/llcc-qcom.h>
 
 #define GPU_PAS_ID 13
@@ -1117,7 +1118,7 @@ static void a6xx_llc_slices_init(struct platform_device *pdev,
 	a6xx_gpu->llc_slice = llcc_slice_getd(LLCC_GPU);
 	a6xx_gpu->htw_llc_slice = llcc_slice_getd(LLCC_GPUHTW);
 
-	if (IS_ERR(a6xx_gpu->llc_slice) && IS_ERR(a6xx_gpu->htw_llc_slice))
+	if (IS_ERR_OR_NULL(a6xx_gpu->llc_slice) && IS_ERR_OR_NULL(a6xx_gpu->htw_llc_slice))
 		a6xx_gpu->llc_mmio = ERR_PTR(-EINVAL);
 }
 
@@ -1169,14 +1170,18 @@ static int a6xx_get_timestamp(struct msm_gpu *gpu, uint64_t *value)
 {
 	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
 	struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu);
+	static DEFINE_MUTEX(perfcounter_oob);
+
+	mutex_lock(&perfcounter_oob);
 
 	/* Force the GPU power on so we can read this register */
-	a6xx_gmu_set_oob(&a6xx_gpu->gmu, GMU_OOB_GPU_SET);
+	a6xx_gmu_set_oob(&a6xx_gpu->gmu, GMU_OOB_PERFCOUNTER_SET);
 
 	*value = gpu_read64(gpu, REG_A6XX_RBBM_PERFCTR_CP_0_LO,
 		REG_A6XX_RBBM_PERFCTR_CP_0_HI);
 
-	a6xx_gmu_clear_oob(&a6xx_gpu->gmu, GMU_OOB_GPU_SET);
+	a6xx_gmu_clear_oob(&a6xx_gpu->gmu, GMU_OOB_PERFCOUNTER_SET);
+	mutex_unlock(&perfcounter_oob);
 	return 0;
 }
 
@@ -1208,6 +1213,10 @@ static void a6xx_destroy(struct msm_gpu *gpu)
 	a6xx_gmu_remove(a6xx_gpu);
 
 	adreno_gpu_cleanup(adreno_gpu);
+
+	if (a6xx_gpu->opp_table)
+		dev_pm_opp_put_supported_hw(a6xx_gpu->opp_table);
+
 	kfree(a6xx_gpu);
 }
 
@@ -1240,6 +1249,50 @@ static unsigned long a6xx_gpu_busy(struct msm_gpu *gpu)
 }
 
 static struct msm_gem_address_space *
+a6xx_create_address_space(struct msm_gpu *gpu, struct platform_device *pdev)
+{
+	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
+	struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu);
+	struct iommu_domain *iommu;
+	struct msm_mmu *mmu;
+	struct msm_gem_address_space *aspace;
+	u64 start, size;
+
+	iommu = iommu_domain_alloc(&platform_bus_type);
+	if (!iommu)
+		return NULL;
+
+	/*
+	 * This allows GPU to set the bus attributes required to use system
+	 * cache on behalf of the iommu page table walker.
+	 */
+	if (!IS_ERR_OR_NULL(a6xx_gpu->htw_llc_slice))
+		adreno_set_llc_attributes(iommu);
+
+	mmu = msm_iommu_new(&pdev->dev, iommu);
+	if (IS_ERR(mmu)) {
+		iommu_domain_free(iommu);
+		return ERR_CAST(mmu);
+	}
+
+	/*
+	 * Use the aperture start or SZ_16M, whichever is greater. This will
+	 * ensure that we align with the allocated pagetable range while still
+	 * allowing room in the lower 32 bits for GMEM and whatnot
+	 */
+	start = max_t(u64, SZ_16M, iommu->geometry.aperture_start);
+	size = iommu->geometry.aperture_end - start + 1;
+
+	aspace = msm_gem_address_space_create(mmu, "gpu",
+		start & GENMASK_ULL(48, 0), size);
+
+	if (IS_ERR(aspace) && !IS_ERR(mmu))
+		mmu->funcs->destroy(mmu);
+
+	return aspace;
+}
+
+static struct msm_gem_address_space *
 a6xx_create_private_address_space(struct msm_gpu *gpu)
 {
 	struct msm_mmu *mmu;
@@ -1264,6 +1317,78 @@ static uint32_t a6xx_get_rptr(struct msm_gpu *gpu, struct msm_ringbuffer *ring)
 	return ring->memptrs->rptr = gpu_read(gpu, REG_A6XX_CP_RB_RPTR);
 }
 
+static u32 a618_get_speed_bin(u32 fuse)
+{
+	if (fuse == 0)
+		return 0;
+	else if (fuse == 169)
+		return 1;
+	else if (fuse == 174)
+		return 2;
+
+	return UINT_MAX;
+}
+
+static u32 fuse_to_supp_hw(struct device *dev, u32 revn, u32 fuse)
+{
+	u32 val = UINT_MAX;
+
+	if (revn == 618)
+		val = a618_get_speed_bin(fuse);
+
+	if (val == UINT_MAX) {
+		DRM_DEV_ERROR(dev,
+			"missing support for speed-bin: %u. Some OPPs may not be supported by hardware",
+			fuse);
+		return UINT_MAX;
+	}
+
+	return (1 << val);
+}
+
+static int a6xx_set_supported_hw(struct device *dev, struct a6xx_gpu *a6xx_gpu,
+		u32 revn)
+{
+	struct opp_table *opp_table;
+	struct nvmem_cell *cell;
+	u32 supp_hw = UINT_MAX;
+	void *buf;
+
+	cell = nvmem_cell_get(dev, "speed_bin");
+	/*
+	 * -ENOENT means that the platform doesn't support speedbin which is
+	 * fine
+	 */
+	if (PTR_ERR(cell) == -ENOENT)
+		return 0;
+	else if (IS_ERR(cell)) {
+		DRM_DEV_ERROR(dev,
+				"failed to read speed-bin. Some OPPs may not be supported by hardware");
+		goto done;
+	}
+
+	buf = nvmem_cell_read(cell, NULL);
+	if (IS_ERR(buf)) {
+		nvmem_cell_put(cell);
+		DRM_DEV_ERROR(dev,
+				"failed to read speed-bin. Some OPPs may not be supported by hardware");
+		goto done;
+	}
+
+	supp_hw = fuse_to_supp_hw(dev, revn, *((u32 *) buf));
+
+	kfree(buf);
+	nvmem_cell_put(cell);
+
+done:
+	opp_table = dev_pm_opp_set_supported_hw(dev, &supp_hw, 1);
+	if (IS_ERR(opp_table))
+		return PTR_ERR(opp_table);
+
+	a6xx_gpu->opp_table = opp_table;
+	return 0;
+}
+
 static const struct adreno_gpu_funcs funcs = {
 	.base = {
 		.get_param = adreno_get_param,
@@ -1285,7 +1410,7 @@ static const struct adreno_gpu_funcs funcs = {
 		.gpu_state_get = a6xx_gpu_state_get,
 		.gpu_state_put = a6xx_gpu_state_put,
 #endif
-		.create_address_space = adreno_iommu_create_address_space,
+		.create_address_space = a6xx_create_address_space,
 		.create_private_address_space = a6xx_create_private_address_space,
 		.get_rptr = a6xx_get_rptr,
 	},
@@ -1325,6 +1450,12 @@ struct msm_gpu *a6xx_gpu_init(struct drm_device *dev)
 
 	a6xx_llc_slices_init(pdev, a6xx_gpu);
 
+	ret = a6xx_set_supported_hw(&pdev->dev, a6xx_gpu, info->revn);
+	if (ret) {
+		a6xx_destroy(&(a6xx_gpu->base.base));
+		return ERR_PTR(ret);
+	}
+
 	ret = adreno_gpu_init(dev, pdev, adreno_gpu, &funcs, 1);
 	if (ret) {
 		a6xx_destroy(&(a6xx_gpu->base.base));
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.h b/drivers/gpu/drm/msm/adreno/a6xx_gpu.h
index e793d329e77b..ce0610c5256f 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.h
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.h
@@ -33,6 +33,8 @@ struct a6xx_gpu {
 	void *llc_slice;
 	void *htw_llc_slice;
 	bool have_mmu500;
+
+	struct opp_table *opp_table;
 };
 
 #define to_a6xx_gpu(x) container_of(x, struct a6xx_gpu, base)
diff --git a/drivers/gpu/drm/msm/adreno/adreno_device.c b/drivers/gpu/drm/msm/adreno/adreno_device.c
index 12e75ba360f9..600d445fabe8 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_device.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_device.c
@@ -134,6 +134,41 @@ static const struct adreno_info gpulist[] = {
 		.inactive_period = DRM_MSM_INACTIVE_PERIOD,
 		.init  = a4xx_gpu_init,
 	}, {
+		.rev   = ADRENO_REV(5, 0, 8, ANY_ID),
+		.revn = 508,
+		.name = "A508",
+		.fw = {
+			[ADRENO_FW_PM4] = "a530_pm4.fw",
+			[ADRENO_FW_PFP] = "a530_pfp.fw",
+		},
+		.gmem = (SZ_128K + SZ_8K),
+		/*
+		 * Increase inactive period to 250 to avoid bouncing
+		 * the GDSC which appears to make it grumpy
+		 */
+		.inactive_period = 250,
+		.quirks = ADRENO_QUIRK_LMLOADKILL_DISABLE,
+		.init = a5xx_gpu_init,
+		.zapfw = "a508_zap.mdt",
+	}, {
+		.rev   = ADRENO_REV(5, 0, 9, ANY_ID),
+		.revn = 509,
+		.name = "A509",
+		.fw = {
+			[ADRENO_FW_PM4] = "a530_pm4.fw",
+			[ADRENO_FW_PFP] = "a530_pfp.fw",
+		},
+		.gmem = (SZ_256K + SZ_16K),
+		/*
+		 * Increase inactive period to 250 to avoid bouncing
+		 * the GDSC which appears to make it grumpy
+		 */
+		.inactive_period = 250,
+		.quirks = ADRENO_QUIRK_LMLOADKILL_DISABLE,
+		.init = a5xx_gpu_init,
+		/* Adreno 509 uses the same ZAP as 512 */
+		.zapfw = "a512_zap.mdt",
+	}, {
 		.rev   = ADRENO_REV(5, 1, 0, ANY_ID),
 		.revn = 510,
 		.name = "A510",
@@ -149,6 +184,23 @@ static const struct adreno_info gpulist[] = {
 		.inactive_period = 250,
 		.init = a5xx_gpu_init,
 	}, {
+		.rev   = ADRENO_REV(5, 1, 2, ANY_ID),
+		.revn = 512,
+		.name = "A512",
+		.fw = {
+			[ADRENO_FW_PM4] = "a530_pm4.fw",
+			[ADRENO_FW_PFP] = "a530_pfp.fw",
+		},
+		.gmem = (SZ_256K + SZ_16K),
+		/*
+		 * Increase inactive period to 250 to avoid bouncing
+		 * the GDSC which appears to make it grumpy
+		 */
+		.inactive_period = 250,
+		.quirks = ADRENO_QUIRK_LMLOADKILL_DISABLE,
+		.init = a5xx_gpu_init,
+		.zapfw = "a512_zap.mdt",
+	}, {
 		.rev = ADRENO_REV(5, 3, 0, 2),
 		.revn = 530,
 		.name = "A530",
@@ -168,7 +220,7 @@ static const struct adreno_info gpulist[] = {
 		.init = a5xx_gpu_init,
 		.zapfw = "a530_zap.mdt",
 	}, {
-		.rev = ADRENO_REV(5, 4, 0, 2),
+		.rev = ADRENO_REV(5, 4, 0, ANY_ID),
 		.revn = 540,
 		.name = "A540",
 		.fw = {
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
index f09175698827..0f184c3dd9d9 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
@@ -186,11 +186,18 @@ int adreno_zap_shader_load(struct msm_gpu *gpu, u32 pasid)
 	return zap_shader_load_mdt(gpu, adreno_gpu->info->zapfw, pasid);
 }
 
+void adreno_set_llc_attributes(struct iommu_domain *iommu)
+{
+	struct io_pgtable_domain_attr pgtbl_cfg;
+
+	pgtbl_cfg.quirks = IO_PGTABLE_QUIRK_ARM_OUTER_WBWA;
+	iommu_domain_set_attr(iommu, DOMAIN_ATTR_IO_PGTABLE_CFG, &pgtbl_cfg);
+}
+
 struct msm_gem_address_space *
 adreno_iommu_create_address_space(struct msm_gpu *gpu,
 		struct platform_device *pdev)
 {
-	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
 	struct iommu_domain *iommu;
 	struct msm_mmu *mmu;
 	struct msm_gem_address_space *aspace;
@@ -200,20 +207,6 @@ adreno_iommu_create_address_space(struct msm_gpu *gpu,
 	if (!iommu)
 		return NULL;
 
-
-	if (adreno_is_a6xx(adreno_gpu)) {
-		struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu);
-		struct io_pgtable_domain_attr pgtbl_cfg;
-		/*
-		* This allows GPU to set the bus attributes required to use system
-		* cache on behalf of the iommu page table walker.
-		*/
-		if (!IS_ERR(a6xx_gpu->htw_llc_slice)) {
-			pgtbl_cfg.quirks = IO_PGTABLE_QUIRK_ARM_OUTER_WBWA;
-			iommu_domain_set_attr(iommu, DOMAIN_ATTR_IO_PGTABLE_CFG, &pgtbl_cfg);
-		}
-	}
-
 	mmu = msm_iommu_new(&pdev->dev, iommu);
 	if (IS_ERR(mmu)) {
 		iommu_domain_free(iommu);
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.h b/drivers/gpu/drm/msm/adreno/adreno_gpu.h
index b3d9a333591b..ccac275aa7a2 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.h
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.h
@@ -197,11 +197,26 @@ static inline int adreno_is_a430(struct adreno_gpu *gpu)
        return gpu->revn == 430;
 }
 
+static inline int adreno_is_a508(struct adreno_gpu *gpu)
+{
+	return gpu->revn == 508;
+}
+
+static inline int adreno_is_a509(struct adreno_gpu *gpu)
+{
+	return gpu->revn == 509;
+}
+
 static inline int adreno_is_a510(struct adreno_gpu *gpu)
 {
 	return gpu->revn == 510;
 }
 
+static inline int adreno_is_a512(struct adreno_gpu *gpu)
+{
+	return gpu->revn == 512;
+}
+
 static inline int adreno_is_a530(struct adreno_gpu *gpu)
 {
 	return gpu->revn == 530;
@@ -212,11 +227,6 @@ static inline int adreno_is_a540(struct adreno_gpu *gpu)
 	return gpu->revn == 540;
 }
 
-static inline bool adreno_is_a6xx(struct adreno_gpu *gpu)
-{
-	return ((gpu->revn < 700 && gpu->revn > 599));
-}
-
 static inline int adreno_is_a618(struct adreno_gpu *gpu)
 {
        return gpu->revn == 618;
@@ -278,6 +288,8 @@ struct msm_gem_address_space *
 adreno_iommu_create_address_space(struct msm_gpu *gpu,
 		struct platform_device *pdev);
 
+void adreno_set_llc_attributes(struct iommu_domain *iommu);
+
 /*
  * For a5xx and a6xx targets load the zap shader that is used to pull the GPU
  * out of secure mode
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_cmd.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_cmd.c
index 5a056c1191df..b2be39b9144e 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_cmd.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_cmd.c
@@ -4,8 +4,10 @@
  */
 
 #define pr_fmt(fmt)	"[drm:%s:%d] " fmt, __func__, __LINE__
+#include <linux/delay.h>
 #include "dpu_encoder_phys.h"
 #include "dpu_hw_interrupts.h"
+#include "dpu_hw_pingpong.h"
 #include "dpu_core_irq.h"
 #include "dpu_formats.h"
 #include "dpu_trace.h"
@@ -35,6 +37,8 @@
 
 #define DPU_ENC_WR_PTR_START_TIMEOUT_US 20000
 
+#define DPU_ENC_MAX_POLL_TIMEOUT_US	2000
+
 static bool dpu_encoder_phys_cmd_is_master(struct dpu_encoder_phys *phys_enc)
 {
 	return (phys_enc->split_role != ENC_ROLE_SLAVE) ? true : false;
@@ -368,15 +372,12 @@ static void dpu_encoder_phys_cmd_tearcheck_config(
 	tc_cfg.vsync_count = vsync_hz /
 				(mode->vtotal * drm_mode_vrefresh(mode));
 
-	/* enable external TE after kickoff to avoid premature autorefresh */
-	tc_cfg.hw_vsync_mode = 0;
-
 	/*
-	 * By setting sync_cfg_height to near max register value, we essentially
-	 * disable dpu hw generated TE signal, since hw TE will arrive first.
-	 * Only caveat is if due to error, we hit wrap-around.
+	 * Set the sync_cfg_height to twice vtotal so that if we lose a
+	 * TE event coming from the display TE pin we won't stall immediately
 	 */
-	tc_cfg.sync_cfg_height = 0xFFF0;
+	tc_cfg.hw_vsync_mode = 1;
+	tc_cfg.sync_cfg_height = mode->vtotal * 2;
 	tc_cfg.vsync_init_val = mode->vdisplay;
 	tc_cfg.sync_threshold_start = DEFAULT_TEARCHECK_SYNC_THRESH_START;
 	tc_cfg.sync_threshold_continue = DEFAULT_TEARCHECK_SYNC_THRESH_CONTINUE;
@@ -580,6 +581,69 @@ static void dpu_encoder_phys_cmd_prepare_for_kickoff(
 			atomic_read(&phys_enc->pending_kickoff_cnt));
 }
 
+static bool dpu_encoder_phys_cmd_is_ongoing_pptx(
+		struct dpu_encoder_phys *phys_enc)
+{
+	struct dpu_hw_pp_vsync_info info;
+
+	if (!phys_enc)
+		return false;
+
+	phys_enc->hw_pp->ops.get_vsync_info(phys_enc->hw_pp, &info);
+	if (info.wr_ptr_line_count > 0 &&
+	    info.wr_ptr_line_count < phys_enc->cached_mode.vdisplay)
+		return true;
+
+	return false;
+}
+
+static void dpu_encoder_phys_cmd_prepare_commit(
+		struct dpu_encoder_phys *phys_enc)
+{
+	struct dpu_encoder_phys_cmd *cmd_enc =
+		to_dpu_encoder_phys_cmd(phys_enc);
+	int trial = 0;
+
+	if (!phys_enc)
+		return;
+	if (!phys_enc->hw_pp)
+		return;
+	if (!dpu_encoder_phys_cmd_is_master(phys_enc))
+		return;
+
+	/* If autorefresh is already disabled, we have nothing to do */
+	if (!phys_enc->hw_pp->ops.get_autorefresh(phys_enc->hw_pp, NULL))
+		return;
+
+	/*
+	 * If autorefresh is enabled, disable it and make sure it is safe to
+	 * proceed with current frame commit/push. Sequence fallowed is,
+	 * 1. Disable TE
+	 * 2. Disable autorefresh config
+	 * 4. Poll for frame transfer ongoing to be false
+	 * 5. Enable TE back
+	 */
+	_dpu_encoder_phys_cmd_connect_te(phys_enc, false);
+	phys_enc->hw_pp->ops.setup_autorefresh(phys_enc->hw_pp, 0, false);
+
+	do {
+		udelay(DPU_ENC_MAX_POLL_TIMEOUT_US);
+		if ((trial * DPU_ENC_MAX_POLL_TIMEOUT_US)
+				> (KICKOFF_TIMEOUT_MS * USEC_PER_MSEC)) {
+			DPU_ERROR_CMDENC(cmd_enc,
+					"disable autorefresh failed\n");
+			break;
+		}
+
+		trial++;
+	} while (dpu_encoder_phys_cmd_is_ongoing_pptx(phys_enc));
+
+	_dpu_encoder_phys_cmd_connect_te(phys_enc, true);
+
+	DPU_DEBUG_CMDENC(to_dpu_encoder_phys_cmd(phys_enc),
+			 "disabled autorefresh\n");
+}
+
 static int _dpu_encoder_phys_cmd_wait_for_ctl_start(
 		struct dpu_encoder_phys *phys_enc)
 {
@@ -621,20 +685,15 @@ static int dpu_encoder_phys_cmd_wait_for_tx_complete(
 static int dpu_encoder_phys_cmd_wait_for_commit_done(
 		struct dpu_encoder_phys *phys_enc)
 {
-	int rc = 0;
 	struct dpu_encoder_phys_cmd *cmd_enc;
 
 	cmd_enc = to_dpu_encoder_phys_cmd(phys_enc);
 
 	/* only required for master controller */
-	if (dpu_encoder_phys_cmd_is_master(phys_enc))
-		rc = _dpu_encoder_phys_cmd_wait_for_ctl_start(phys_enc);
-
-	/* required for both controllers */
-	if (!rc && cmd_enc->serialize_wait4pp)
-		dpu_encoder_phys_cmd_prepare_for_kickoff(phys_enc);
+	if (!dpu_encoder_phys_cmd_is_master(phys_enc))
+		return 0;
 
-	return rc;
+	return _dpu_encoder_phys_cmd_wait_for_ctl_start(phys_enc);
 }
 
 static int dpu_encoder_phys_cmd_wait_for_vblank(
@@ -681,6 +740,7 @@ static void dpu_encoder_phys_cmd_trigger_start(
 static void dpu_encoder_phys_cmd_init_ops(
 		struct dpu_encoder_phys_ops *ops)
 {
+	ops->prepare_commit = dpu_encoder_phys_cmd_prepare_commit;
 	ops->is_master = dpu_encoder_phys_cmd_is_master;
 	ops->mode_set = dpu_encoder_phys_cmd_mode_set;
 	ops->mode_fixup = dpu_encoder_phys_cmd_mode_fixup;
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c
index 90393fe9e59c..189f3533525c 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c
@@ -12,14 +12,17 @@
 
 #define VIG_MASK \
 	(BIT(DPU_SSPP_SRC) | BIT(DPU_SSPP_QOS) |\
-	BIT(DPU_SSPP_CSC_10BIT) | BIT(DPU_SSPP_CDP) | BIT(DPU_SSPP_QOS_8LVL) |\
+	BIT(DPU_SSPP_CSC_10BIT) | BIT(DPU_SSPP_CDP) |\
 	BIT(DPU_SSPP_TS_PREFILL) | BIT(DPU_SSPP_EXCL_RECT))
 
 #define VIG_SDM845_MASK \
-	(VIG_MASK | BIT(DPU_SSPP_SCALER_QSEED3))
+	(VIG_MASK | BIT(DPU_SSPP_QOS_8LVL) | BIT(DPU_SSPP_SCALER_QSEED3))
 
 #define VIG_SC7180_MASK \
-	(VIG_MASK | BIT(DPU_SSPP_SCALER_QSEED4))
+	(VIG_MASK | BIT(DPU_SSPP_QOS_8LVL) | BIT(DPU_SSPP_SCALER_QSEED4))
+
+#define VIG_SM8250_MASK \
+	(VIG_MASK | BIT(DPU_SSPP_SCALER_QSEED3LITE))
 
 #define DMA_SDM845_MASK \
 	(BIT(DPU_SSPP_SRC) | BIT(DPU_SSPP_QOS) | BIT(DPU_SSPP_QOS_8LVL) |\
@@ -185,7 +188,7 @@ static const struct dpu_caps sm8150_dpu_caps = {
 static const struct dpu_caps sm8250_dpu_caps = {
 	.max_mixer_width = DEFAULT_DPU_OUTPUT_LINE_WIDTH,
 	.max_mixer_blendstages = 0xb,
-	.qseed_type = DPU_SSPP_SCALER_QSEED3, /* TODO: qseed3 lite */
+	.qseed_type = DPU_SSPP_SCALER_QSEED3LITE,
 	.smart_dma_rev = DPU_SSPP_SMART_DMA_V2, /* TODO: v2.5 */
 	.ubwc_version = DPU_HW_UBWC_VER_40,
 	.has_src_split = true,
@@ -444,6 +447,34 @@ static const struct dpu_sspp_cfg sc7180_sspp[] = {
 		sdm845_dma_sblk_2, 9, SSPP_TYPE_DMA, DPU_CLK_CTRL_CURSOR1),
 };
 
+static const struct dpu_sspp_sub_blks sm8250_vig_sblk_0 =
+				_VIG_SBLK("0", 5, DPU_SSPP_SCALER_QSEED3LITE);
+static const struct dpu_sspp_sub_blks sm8250_vig_sblk_1 =
+				_VIG_SBLK("1", 6, DPU_SSPP_SCALER_QSEED3LITE);
+static const struct dpu_sspp_sub_blks sm8250_vig_sblk_2 =
+				_VIG_SBLK("2", 7, DPU_SSPP_SCALER_QSEED3LITE);
+static const struct dpu_sspp_sub_blks sm8250_vig_sblk_3 =
+				_VIG_SBLK("3", 8, DPU_SSPP_SCALER_QSEED3LITE);
+
+static const struct dpu_sspp_cfg sm8250_sspp[] = {
+	SSPP_BLK("sspp_0", SSPP_VIG0, 0x4000, VIG_SM8250_MASK,
+		sm8250_vig_sblk_0, 0,  SSPP_TYPE_VIG, DPU_CLK_CTRL_VIG0),
+	SSPP_BLK("sspp_1", SSPP_VIG1, 0x6000, VIG_SM8250_MASK,
+		sm8250_vig_sblk_1, 4,  SSPP_TYPE_VIG, DPU_CLK_CTRL_VIG1),
+	SSPP_BLK("sspp_2", SSPP_VIG2, 0x8000, VIG_SM8250_MASK,
+		sm8250_vig_sblk_2, 8, SSPP_TYPE_VIG, DPU_CLK_CTRL_VIG2),
+	SSPP_BLK("sspp_3", SSPP_VIG3, 0xa000, VIG_SM8250_MASK,
+		sm8250_vig_sblk_3, 12,  SSPP_TYPE_VIG, DPU_CLK_CTRL_VIG3),
+	SSPP_BLK("sspp_8", SSPP_DMA0, 0x24000,  DMA_SDM845_MASK,
+		sdm845_dma_sblk_0, 1, SSPP_TYPE_DMA, DPU_CLK_CTRL_DMA0),
+	SSPP_BLK("sspp_9", SSPP_DMA1, 0x26000,  DMA_SDM845_MASK,
+		sdm845_dma_sblk_1, 5, SSPP_TYPE_DMA, DPU_CLK_CTRL_DMA1),
+	SSPP_BLK("sspp_10", SSPP_DMA2, 0x28000,  DMA_CURSOR_SDM845_MASK,
+		sdm845_dma_sblk_2, 9, SSPP_TYPE_DMA, DPU_CLK_CTRL_CURSOR0),
+	SSPP_BLK("sspp_11", SSPP_DMA3, 0x2a000,  DMA_CURSOR_SDM845_MASK,
+		sdm845_dma_sblk_3, 13, SSPP_TYPE_DMA, DPU_CLK_CTRL_CURSOR1),
+};
+
 /*************************************************************
  * MIXER sub blocks config
  *************************************************************/
@@ -532,23 +563,28 @@ static const struct dpu_dspp_sub_blks sm8150_dspp_sblk = {
 		.len = 0x90, .version = 0x40000},
 };
 
-#define DSPP_BLK(_name, _id, _base, _sblk) \
+#define DSPP_BLK(_name, _id, _base, _mask, _sblk) \
 		{\
 		.name = _name, .id = _id, \
 		.base = _base, .len = 0x1800, \
-		.features = DSPP_SC7180_MASK, \
+		.features = _mask, \
 		.sblk = _sblk \
 		}
 
 static const struct dpu_dspp_cfg sc7180_dspp[] = {
-	DSPP_BLK("dspp_0", DSPP_0, 0x54000, &sc7180_dspp_sblk),
+	DSPP_BLK("dspp_0", DSPP_0, 0x54000, DSPP_SC7180_MASK,
+		 &sc7180_dspp_sblk),
 };
 
 static const struct dpu_dspp_cfg sm8150_dspp[] = {
-	DSPP_BLK("dspp_0", DSPP_0, 0x54000, &sm8150_dspp_sblk),
-	DSPP_BLK("dspp_1", DSPP_1, 0x56000, &sm8150_dspp_sblk),
-	DSPP_BLK("dspp_2", DSPP_2, 0x58000, &sm8150_dspp_sblk),
-	DSPP_BLK("dspp_3", DSPP_3, 0x5a000, &sm8150_dspp_sblk),
+	DSPP_BLK("dspp_0", DSPP_0, 0x54000, DSPP_SC7180_MASK,
+		 &sm8150_dspp_sblk),
+	DSPP_BLK("dspp_1", DSPP_1, 0x56000, DSPP_SC7180_MASK,
+		 &sm8150_dspp_sblk),
+	DSPP_BLK("dspp_2", DSPP_2, 0x58000, DSPP_SC7180_MASK,
+		 &sm8150_dspp_sblk),
+	DSPP_BLK("dspp_3", DSPP_3, 0x5a000, DSPP_SC7180_MASK,
+		 &sm8150_dspp_sblk),
 };
 
 /*************************************************************
@@ -624,33 +660,33 @@ static const struct dpu_merge_3d_cfg sm8150_merge_3d[] = {
 /*************************************************************
  * INTF sub blocks config
  *************************************************************/
-#define INTF_BLK(_name, _id, _base, _type, _ctrl_id, _features) \
+#define INTF_BLK(_name, _id, _base, _type, _ctrl_id, _progfetch, _features) \
 	{\
 	.name = _name, .id = _id, \
 	.base = _base, .len = 0x280, \
 	.features = _features, \
 	.type = _type, \
 	.controller_id = _ctrl_id, \
-	.prog_fetch_lines_worst_case = 24 \
+	.prog_fetch_lines_worst_case = _progfetch \
 	}
 
 static const struct dpu_intf_cfg sdm845_intf[] = {
-	INTF_BLK("intf_0", INTF_0, 0x6A000, INTF_DP, 0, INTF_SDM845_MASK),
-	INTF_BLK("intf_1", INTF_1, 0x6A800, INTF_DSI, 0, INTF_SDM845_MASK),
-	INTF_BLK("intf_2", INTF_2, 0x6B000, INTF_DSI, 1, INTF_SDM845_MASK),
-	INTF_BLK("intf_3", INTF_3, 0x6B800, INTF_DP, 1, INTF_SDM845_MASK),
+	INTF_BLK("intf_0", INTF_0, 0x6A000, INTF_DP, 0, 24, INTF_SDM845_MASK),
+	INTF_BLK("intf_1", INTF_1, 0x6A800, INTF_DSI, 0, 24, INTF_SDM845_MASK),
+	INTF_BLK("intf_2", INTF_2, 0x6B000, INTF_DSI, 1, 24, INTF_SDM845_MASK),
+	INTF_BLK("intf_3", INTF_3, 0x6B800, INTF_DP, 1, 24, INTF_SDM845_MASK),
 };
 
 static const struct dpu_intf_cfg sc7180_intf[] = {
-	INTF_BLK("intf_0", INTF_0, 0x6A000, INTF_DP, 0, INTF_SC7180_MASK),
-	INTF_BLK("intf_1", INTF_1, 0x6A800, INTF_DSI, 0, INTF_SC7180_MASK),
+	INTF_BLK("intf_0", INTF_0, 0x6A000, INTF_DP, 0, 24, INTF_SC7180_MASK),
+	INTF_BLK("intf_1", INTF_1, 0x6A800, INTF_DSI, 0, 24, INTF_SC7180_MASK),
 };
 
 static const struct dpu_intf_cfg sm8150_intf[] = {
-	INTF_BLK("intf_0", INTF_0, 0x6A000, INTF_DP, 0, INTF_SC7180_MASK),
-	INTF_BLK("intf_1", INTF_1, 0x6A800, INTF_DSI, 0, INTF_SC7180_MASK),
-	INTF_BLK("intf_2", INTF_2, 0x6B000, INTF_DSI, 1, INTF_SC7180_MASK),
-	INTF_BLK("intf_3", INTF_3, 0x6B800, INTF_DP, 1, INTF_SC7180_MASK),
+	INTF_BLK("intf_0", INTF_0, 0x6A000, INTF_DP, 0, 24, INTF_SC7180_MASK),
+	INTF_BLK("intf_1", INTF_1, 0x6A800, INTF_DSI, 0, 24, INTF_SC7180_MASK),
+	INTF_BLK("intf_2", INTF_2, 0x6B000, INTF_DSI, 1, 24, INTF_SC7180_MASK),
+	INTF_BLK("intf_3", INTF_3, 0x6B800, INTF_DP, 1, 24, INTF_SC7180_MASK),
 };
 
 /*************************************************************
@@ -969,9 +1005,8 @@ static void sm8250_cfg_init(struct dpu_mdss_cfg *dpu_cfg)
 		.mdp = sm8250_mdp,
 		.ctl_count = ARRAY_SIZE(sm8150_ctl),
 		.ctl = sm8150_ctl,
-		/* TODO: sspp qseed version differs from 845 */
-		.sspp_count = ARRAY_SIZE(sdm845_sspp),
-		.sspp = sdm845_sspp,
+		.sspp_count = ARRAY_SIZE(sm8250_sspp),
+		.sspp = sm8250_sspp,
 		.mixer_count = ARRAY_SIZE(sm8150_lm),
 		.mixer = sm8150_lm,
 		.dspp_count = ARRAY_SIZE(sm8150_dspp),
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.h
index eaef99db2d2f..ea4647d21a20 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.h
@@ -95,6 +95,7 @@ enum {
  * @DPU_SSPP_SRC             Src and fetch part of the pipes,
  * @DPU_SSPP_SCALER_QSEED2,  QSEED2 algorithm support
  * @DPU_SSPP_SCALER_QSEED3,  QSEED3 alogorithm support
+ * @DPU_SSPP_SCALER_QSEED3LITE,  QSEED3 Lite alogorithm support
  * @DPU_SSPP_SCALER_QSEED4,  QSEED4 algorithm support
  * @DPU_SSPP_SCALER_RGB,     RGB Scaler, supported by RGB pipes
  * @DPU_SSPP_CSC,            Support of Color space converion
@@ -114,6 +115,7 @@ enum {
 	DPU_SSPP_SRC = 0x1,
 	DPU_SSPP_SCALER_QSEED2,
 	DPU_SSPP_SCALER_QSEED3,
+	DPU_SSPP_SCALER_QSEED3LITE,
 	DPU_SSPP_SCALER_QSEED4,
 	DPU_SSPP_SCALER_RGB,
 	DPU_SSPP_CSC,
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_pingpong.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_pingpong.c
index bea4ab5c58c5..245a7a62b5c6 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_pingpong.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_pingpong.c
@@ -23,6 +23,7 @@
 #define PP_WR_PTR_IRQ                   0x024
 #define PP_OUT_LINE_COUNT               0x028
 #define PP_LINE_COUNT                   0x02C
+#define PP_AUTOREFRESH_CONFIG           0x030
 
 #define PP_FBC_MODE                     0x034
 #define PP_FBC_BUDGET_CTL               0x038
@@ -120,6 +121,29 @@ static int dpu_hw_pp_setup_te_config(struct dpu_hw_pingpong *pp,
 	return 0;
 }
 
+static void dpu_hw_pp_setup_autorefresh_config(struct dpu_hw_pingpong *pp,
+					       u32 frame_count, bool enable)
+{
+	DPU_REG_WRITE(&pp->hw, PP_AUTOREFRESH_CONFIG,
+		      enable ? (BIT(31) | frame_count) : 0);
+}
+
+/*
+ * dpu_hw_pp_get_autorefresh_config - Get autorefresh config from HW
+ * @pp:          DPU pingpong structure
+ * @frame_count: Used to return the current frame count from hw
+ *
+ * Returns: True if autorefresh enabled, false if disabled.
+ */
+static bool dpu_hw_pp_get_autorefresh_config(struct dpu_hw_pingpong *pp,
+					     u32 *frame_count)
+{
+	u32 val = DPU_REG_READ(&pp->hw, PP_AUTOREFRESH_CONFIG);
+	if (frame_count != NULL)
+		*frame_count = val & 0xffff;
+	return !!((val & BIT(31)) >> 31);
+}
+
 static int dpu_hw_pp_poll_timeout_wr_ptr(struct dpu_hw_pingpong *pp,
 		u32 timeout_us)
 {
@@ -228,6 +252,8 @@ static void _setup_pingpong_ops(struct dpu_hw_pingpong *c,
 	c->ops.enable_tearcheck = dpu_hw_pp_enable_te;
 	c->ops.connect_external_te = dpu_hw_pp_connect_external_te;
 	c->ops.get_vsync_info = dpu_hw_pp_get_vsync_info;
+	c->ops.setup_autorefresh = dpu_hw_pp_setup_autorefresh_config;
+	c->ops.get_autorefresh = dpu_hw_pp_get_autorefresh_config;
 	c->ops.poll_timeout_wr_ptr = dpu_hw_pp_poll_timeout_wr_ptr;
 	c->ops.get_line_count = dpu_hw_pp_get_line_count;
 
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_pingpong.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_pingpong.h
index 6902b9b95c8e..845b9ce80e31 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_pingpong.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_pingpong.h
@@ -63,6 +63,8 @@ struct dpu_hw_dither_cfg {
  *  @setup_tearcheck : program tear check values
  *  @enable_tearcheck : enables tear check
  *  @get_vsync_info : retries timing info of the panel
+ *  @setup_autorefresh : configure and enable the autorefresh config
+ *  @get_autorefresh : retrieve autorefresh config from hardware
  *  @setup_dither : function to program the dither hw block
  *  @get_line_count: obtain current vertical line counter
  */
@@ -95,6 +97,18 @@ struct dpu_hw_pingpong_ops {
 			struct dpu_hw_pp_vsync_info  *info);
 
 	/**
+	 * configure and enable the autorefresh config
+	 */
+	void (*setup_autorefresh)(struct dpu_hw_pingpong *pp,
+				  u32 frame_count, bool enable);
+
+	/**
+	 * retrieve autorefresh config from hardware
+	 */
+	bool (*get_autorefresh)(struct dpu_hw_pingpong *pp,
+				u32 *frame_count);
+
+	/**
 	 * poll until write pointer transmission starts
 	 * @Return: 0 on success, -ETIMEDOUT on timeout
 	 */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp.c
index 2c2ca5335aa8..34d81aa16041 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp.c
@@ -673,6 +673,7 @@ static void _setup_layer_ops(struct dpu_hw_pipe *c,
 		c->ops.setup_multirect = dpu_hw_sspp_setup_multirect;
 
 	if (test_bit(DPU_SSPP_SCALER_QSEED3, &features) ||
+			test_bit(DPU_SSPP_SCALER_QSEED3LITE, &features) ||
 			test_bit(DPU_SSPP_SCALER_QSEED4, &features)) {
 		c->ops.setup_scaler = _dpu_hw_sspp_setup_scaler3;
 		c->ops.get_scaler_ver = _dpu_hw_sspp_get_scaler3_ver;
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp.h
index 85b018a9b03c..fdfd4b46e2c6 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp.h
@@ -28,6 +28,7 @@ struct dpu_hw_pipe;
 #define DPU_SSPP_SCALER ((1UL << DPU_SSPP_SCALER_RGB) | \
 	(1UL << DPU_SSPP_SCALER_QSEED2) | \
 	 (1UL << DPU_SSPP_SCALER_QSEED3) | \
+	 (1UL << DPU_SSPP_SCALER_QSEED3LITE) | \
 	  (1UL << DPU_SSPP_SCALER_QSEED4))
 
 /**
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_util.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_util.c
index 84e9875994a8..f94584c982cd 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_util.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_util.c
@@ -59,6 +59,19 @@ static u32 dpu_hw_util_log_mask = DPU_DBG_MASK_NONE;
 #define QSEED3_SEP_LUT_SIZE \
 	(QSEED3_LUT_SIZE * QSEED3_SEPARABLE_LUTS * sizeof(u32))
 
+/* DPU_SCALER_QSEED3LITE */
+#define QSEED3LITE_COEF_LUT_Y_SEP_BIT         4
+#define QSEED3LITE_COEF_LUT_UV_SEP_BIT        5
+#define QSEED3LITE_COEF_LUT_CTRL              0x4C
+#define QSEED3LITE_COEF_LUT_SWAP_BIT          0
+#define QSEED3LITE_DIR_FILTER_WEIGHT          0x60
+#define QSEED3LITE_FILTERS                 2
+#define QSEED3LITE_SEPARABLE_LUTS             10
+#define QSEED3LITE_LUT_SIZE                   33
+#define QSEED3LITE_SEP_LUT_SIZE \
+	        (QSEED3LITE_LUT_SIZE * QSEED3LITE_SEPARABLE_LUTS * sizeof(u32))
+
+
 void dpu_reg_write(struct dpu_hw_blk_reg_map *c,
 		u32 reg_off,
 		u32 val,
@@ -156,6 +169,57 @@ static void _dpu_hw_setup_scaler3_lut(struct dpu_hw_blk_reg_map *c,
 
 }
 
+static void _dpu_hw_setup_scaler3lite_lut(struct dpu_hw_blk_reg_map *c,
+		struct dpu_hw_scaler3_cfg *scaler3_cfg, u32 offset)
+{
+	int j, filter;
+	int config_lut = 0x0;
+	unsigned long lut_flags;
+	u32 lut_addr, lut_offset;
+	u32 *lut[QSEED3LITE_FILTERS] = {NULL, NULL};
+	static const uint32_t off_tbl[QSEED3_FILTERS] = { 0x000, 0x200 };
+
+	DPU_REG_WRITE(c, QSEED3LITE_DIR_FILTER_WEIGHT + offset, scaler3_cfg->dir_weight);
+
+	if (!scaler3_cfg->sep_lut)
+		return;
+
+	lut_flags = (unsigned long) scaler3_cfg->lut_flag;
+	if (test_bit(QSEED3_COEF_LUT_Y_SEP_BIT, &lut_flags) &&
+		(scaler3_cfg->y_rgb_sep_lut_idx < QSEED3LITE_SEPARABLE_LUTS) &&
+		(scaler3_cfg->sep_len == QSEED3LITE_SEP_LUT_SIZE)) {
+		lut[0] = scaler3_cfg->sep_lut +
+			scaler3_cfg->y_rgb_sep_lut_idx * QSEED3LITE_LUT_SIZE;
+		config_lut = 1;
+	}
+	if (test_bit(QSEED3_COEF_LUT_UV_SEP_BIT, &lut_flags) &&
+		(scaler3_cfg->uv_sep_lut_idx < QSEED3LITE_SEPARABLE_LUTS) &&
+		(scaler3_cfg->sep_len == QSEED3LITE_SEP_LUT_SIZE)) {
+		lut[1] = scaler3_cfg->sep_lut +
+			scaler3_cfg->uv_sep_lut_idx * QSEED3LITE_LUT_SIZE;
+		config_lut = 1;
+	}
+
+	if (config_lut) {
+		for (filter = 0; filter < QSEED3LITE_FILTERS; filter++) {
+			if (!lut[filter])
+				continue;
+			lut_offset = 0;
+			lut_addr = QSEED3_COEF_LUT + offset + off_tbl[filter];
+			for (j = 0; j < QSEED3LITE_LUT_SIZE; j++) {
+				DPU_REG_WRITE(c,
+					lut_addr,
+					(lut[filter])[lut_offset++]);
+				lut_addr += 4;
+			}
+		}
+	}
+
+	if (test_bit(QSEED3_COEF_LUT_SWAP_BIT, &lut_flags))
+		DPU_REG_WRITE(c, QSEED3_COEF_LUT_CTRL + offset, BIT(0));
+
+}
+
 static void _dpu_hw_setup_scaler3_de(struct dpu_hw_blk_reg_map *c,
 		struct dpu_hw_scaler3_de_cfg *de_cfg, u32 offset)
 {
@@ -242,9 +306,12 @@ void dpu_hw_setup_scaler3(struct dpu_hw_blk_reg_map *c,
 		op_mode |= BIT(8);
 	}
 
-	if (scaler3_cfg->lut_flag)
-		_dpu_hw_setup_scaler3_lut(c, scaler3_cfg,
-								scaler_offset);
+	if (scaler3_cfg->lut_flag) {
+		if (scaler_version < 0x2004)
+			_dpu_hw_setup_scaler3_lut(c, scaler3_cfg, scaler_offset);
+		else
+			_dpu_hw_setup_scaler3lite_lut(c, scaler3_cfg, scaler_offset);
+	}
 
 	if (scaler_version == 0x1002) {
 		phase_init =
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_util.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_util.h
index 234eb7d65753..ff3cffde84cd 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_util.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_util.h
@@ -97,6 +97,7 @@ struct dpu_hw_scaler3_de_cfg {
  * @ cir_lut:      pointer to circular filter LUT
  * @ sep_lut:      pointer to separable filter LUT
  * @ de: detail enhancer configuration
+ * @ dir_weight:   Directional weight
  */
 struct dpu_hw_scaler3_cfg {
 	u32 enable;
@@ -137,6 +138,8 @@ struct dpu_hw_scaler3_cfg {
 	 * Detail enhancer settings
 	 */
 	struct dpu_hw_scaler3_de_cfg de;
+
+	u32 dir_weight;
 };
 
 /**
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_vbif.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_vbif.c
index cf867f3f7c36..b757054e1c23 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_vbif.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_vbif.c
@@ -30,7 +30,7 @@
 #define VBIF_XIN_HALT_CTRL0		0x0200
 #define VBIF_XIN_HALT_CTRL1		0x0204
 #define VBIF_XINL_QOS_RP_REMAP_000	0x0550
-#define VBIF_XINL_QOS_LVL_REMAP_000	0x0590
+#define VBIF_XINL_QOS_LVL_REMAP_000(v)	(v < DPU_HW_VER_400 ? 0x570 : 0x0590)
 
 static void dpu_hw_clear_errors(struct dpu_hw_vbif *vbif,
 		u32 *pnd_errors, u32 *src_errors)
@@ -156,18 +156,19 @@ static void dpu_hw_set_qos_remap(struct dpu_hw_vbif *vbif,
 		u32 xin_id, u32 level, u32 remap_level)
 {
 	struct dpu_hw_blk_reg_map *c;
-	u32 reg_val, reg_val_lvl, mask, reg_high, reg_shift;
+	u32 reg_lvl, reg_val, reg_val_lvl, mask, reg_high, reg_shift;
 
 	if (!vbif)
 		return;
 
 	c = &vbif->hw;
 
+	reg_lvl = VBIF_XINL_QOS_LVL_REMAP_000(c->hwversion);
 	reg_high = ((xin_id & 0x8) >> 3) * 4 + (level * 8);
 	reg_shift = (xin_id & 0x7) * 4;
 
 	reg_val = DPU_REG_READ(c, VBIF_XINL_QOS_RP_REMAP_000 + reg_high);
-	reg_val_lvl = DPU_REG_READ(c, VBIF_XINL_QOS_LVL_REMAP_000 + reg_high);
+	reg_val_lvl = DPU_REG_READ(c, reg_lvl + reg_high);
 
 	mask = 0x7 << reg_shift;
 
@@ -178,7 +179,7 @@ static void dpu_hw_set_qos_remap(struct dpu_hw_vbif *vbif,
 	reg_val_lvl |= (remap_level << reg_shift) & mask;
 
 	DPU_REG_WRITE(c, VBIF_XINL_QOS_RP_REMAP_000 + reg_high, reg_val);
-	DPU_REG_WRITE(c, VBIF_XINL_QOS_LVL_REMAP_000 + reg_high, reg_val_lvl);
+	DPU_REG_WRITE(c, reg_lvl + reg_high, reg_val_lvl);
 }
 
 static void dpu_hw_set_write_gather_en(struct dpu_hw_vbif *vbif, u32 xin_id)
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c
index 374b0e8471e6..5a8e3e1fc48c 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c
@@ -749,7 +749,7 @@ static void _dpu_kms_set_encoder_mode(struct msm_kms *kms,
 	case DRM_MODE_ENCODER_TMDS:
 		info.num_of_h_tiles = 1;
 		break;
-	};
+	}
 
 	rc = dpu_encoder_setup(encoder->dev, encoder, &info);
 	if (rc)
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c
index bc0231a50132..f898a8f67b7f 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c
@@ -1465,6 +1465,7 @@ static int _dpu_plane_init_debugfs(struct drm_plane *plane)
 			pdpu->debugfs_root, &pdpu->debugfs_src);
 
 	if (cfg->features & BIT(DPU_SSPP_SCALER_QSEED3) ||
+			cfg->features & BIT(DPU_SSPP_SCALER_QSEED3LITE) ||
 			cfg->features & BIT(DPU_SSPP_SCALER_QSEED2) ||
 			cfg->features & BIT(DPU_SSPP_SCALER_QSEED4)) {
 		dpu_debugfs_setup_regset32(&pdpu->debugfs_scaler,
diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_cfg.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_cfg.c
index df10c1ac7591..94ce62a26daf 100644
--- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_cfg.c
+++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_cfg.c
@@ -177,7 +177,7 @@ static const struct mdp5_cfg_hw msm8x74v2_config = {
 			[3] = INTF_HDMI,
 		},
 	},
-	.max_clk = 200000000,
+	.max_clk = 320000000,
 };
 
 static const struct mdp5_cfg_hw apq8084_config = {
diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c
index 0c8f9f88301f..f5d71b274079 100644
--- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c
+++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c
@@ -1180,7 +1180,7 @@ static void mdp5_crtc_pp_done_irq(struct mdp_irq *irq, uint32_t irqstatus)
 	struct mdp5_crtc *mdp5_crtc = container_of(irq, struct mdp5_crtc,
 								pp_done);
 
-	complete(&mdp5_crtc->pp_completion);
+	complete_all(&mdp5_crtc->pp_completion);
 }
 
 static void mdp5_crtc_wait_for_pp_done(struct drm_crtc *crtc)
diff --git a/drivers/gpu/drm/msm/dp/dp_aux.c b/drivers/gpu/drm/msm/dp/dp_aux.c
index 19b35ae3e927..1c6e1d2b947c 100644
--- a/drivers/gpu/drm/msm/dp/dp_aux.c
+++ b/drivers/gpu/drm/msm/dp/dp_aux.c
@@ -336,7 +336,6 @@ static ssize_t dp_aux_transfer(struct drm_dp_aux *dp_aux,
 	ssize_t ret;
 	int const aux_cmd_native_max = 16;
 	int const aux_cmd_i2c_max = 128;
-	int const retry_count = 5;
 	struct dp_aux_private *aux = container_of(dp_aux,
 		struct dp_aux_private, dp_aux);
 
@@ -378,12 +377,6 @@ static ssize_t dp_aux_transfer(struct drm_dp_aux *dp_aux,
 	ret = dp_aux_cmd_fifo_tx(aux, msg);
 
 	if (ret < 0) {
-		if (aux->native) {
-			aux->retry_cnt++;
-			if (!(aux->retry_cnt % retry_count))
-				dp_catalog_aux_update_cfg(aux->catalog);
-			dp_catalog_aux_reset(aux->catalog);
-		}
 		usleep_range(400, 500); /* at least 400us to next try */
 		goto unlock_exit;
 	}
diff --git a/drivers/gpu/drm/msm/dp/dp_catalog.c b/drivers/gpu/drm/msm/dp/dp_catalog.c
index 44f0c57798d0..b1a9b1b98f5f 100644
--- a/drivers/gpu/drm/msm/dp/dp_catalog.c
+++ b/drivers/gpu/drm/msm/dp/dp_catalog.c
@@ -190,6 +190,18 @@ int dp_catalog_aux_clear_hw_interrupts(struct dp_catalog *dp_catalog)
 	return 0;
 }
 
+/**
+ * dp_catalog_aux_reset() - reset AUX controller
+ *
+ * @aux: DP catalog structure
+ *
+ * return: void
+ *
+ * This function reset AUX controller
+ *
+ * NOTE: reset AUX controller will also clear any pending HPD related interrupts
+ * 
+ */
 void dp_catalog_aux_reset(struct dp_catalog *dp_catalog)
 {
 	u32 aux_ctrl;
@@ -483,6 +495,18 @@ int dp_catalog_ctrl_set_pattern(struct dp_catalog *dp_catalog,
 	return 0;
 }
 
+/**
+ * dp_catalog_ctrl_reset() - reset DP controller
+ *
+ * @dp_catalog: DP catalog structure
+ *
+ * return: void
+ *
+ * This function reset the DP controller
+ *
+ * NOTE: reset DP controller will also clear any pending HPD related interrupts
+ * 
+ */
 void dp_catalog_ctrl_reset(struct dp_catalog *dp_catalog)
 {
 	u32 sw_reset;
diff --git a/drivers/gpu/drm/msm/dp/dp_ctrl.c b/drivers/gpu/drm/msm/dp/dp_ctrl.c
index 36b39c381b3f..1390f3547fde 100644
--- a/drivers/gpu/drm/msm/dp/dp_ctrl.c
+++ b/drivers/gpu/drm/msm/dp/dp_ctrl.c
@@ -631,7 +631,7 @@ static void _dp_ctrl_calc_tu(struct dp_tu_calc_input *in,
 
 	tu = kzalloc(sizeof(*tu), GFP_KERNEL);
 	if (!tu)
-		return
+		return;
 
 	dp_panel_update_tu_timings(in, tu);
 
@@ -1158,7 +1158,7 @@ static int dp_ctrl_link_rate_down_shift(struct dp_ctrl_private *ctrl)
 	default:
 		ret = -EINVAL;
 		break;
-	};
+	}
 
 	if (!ret)
 		DRM_DEBUG_DP("new rate=0x%x\n", ctrl->link->link_params.rate);
@@ -1296,7 +1296,6 @@ static int dp_ctrl_setup_main_link(struct dp_ctrl_private *ctrl,
 	 * transitioned to PUSH_IDLE. In order to start transmitting
 	 * a link training pattern, we have to first do soft reset.
 	 */
-	dp_catalog_ctrl_reset(ctrl->catalog);
 
 	ret = dp_ctrl_link_train(ctrl, cr, training_step);
 
@@ -1365,7 +1364,7 @@ static int dp_ctrl_enable_stream_clocks(struct dp_ctrl_private *ctrl)
 	return ret;
 }
 
-int dp_ctrl_host_init(struct dp_ctrl *dp_ctrl, bool flip)
+int dp_ctrl_host_init(struct dp_ctrl *dp_ctrl, bool flip, bool reset)
 {
 	struct dp_ctrl_private *ctrl;
 	struct dp_io *dp_io;
@@ -1382,6 +1381,9 @@ int dp_ctrl_host_init(struct dp_ctrl *dp_ctrl, bool flip)
 
 	ctrl->dp_ctrl.orientation = flip;
 
+	if (reset)
+		dp_catalog_ctrl_reset(ctrl->catalog);
+
 	dp_catalog_ctrl_phy_reset(ctrl->catalog);
 	phy_init(phy);
 	dp_catalog_ctrl_enable_irq(ctrl->catalog, true);
@@ -1496,7 +1498,6 @@ static int dp_ctrl_link_maintenance(struct dp_ctrl_private *ctrl)
 	int training_step = DP_TRAINING_NONE;
 
 	dp_ctrl_push_idle(&ctrl->dp_ctrl);
-	dp_catalog_ctrl_reset(ctrl->catalog);
 
 	ctrl->dp_ctrl.pixel_rate = ctrl->panel->dp_mode.drm_mode.clock;
 
@@ -1785,14 +1786,14 @@ int dp_ctrl_on_stream(struct dp_ctrl *dp_ctrl)
 	 * Set up transfer unit values and set controller state to send
 	 * video.
 	 */
+	reinit_completion(&ctrl->video_comp);
+
 	dp_ctrl_configure_source_params(ctrl);
 
 	dp_catalog_ctrl_config_msa(ctrl->catalog,
 		ctrl->link->link_params.rate,
 		ctrl->dp_ctrl.pixel_rate, dp_ctrl_use_fixed_nvid(ctrl));
 
-	reinit_completion(&ctrl->video_comp);
-
 	dp_ctrl_setup_tr_unit(ctrl);
 
 	dp_catalog_ctrl_state_ctrl(ctrl->catalog, DP_STATE_CTRL_SEND_VIDEO);
diff --git a/drivers/gpu/drm/msm/dp/dp_ctrl.h b/drivers/gpu/drm/msm/dp/dp_ctrl.h
index f60ba93c8678..a836bd358447 100644
--- a/drivers/gpu/drm/msm/dp/dp_ctrl.h
+++ b/drivers/gpu/drm/msm/dp/dp_ctrl.h
@@ -19,7 +19,7 @@ struct dp_ctrl {
 	u32 pixel_rate;
 };
 
-int dp_ctrl_host_init(struct dp_ctrl *dp_ctrl, bool flip);
+int dp_ctrl_host_init(struct dp_ctrl *dp_ctrl, bool flip, bool reset);
 void dp_ctrl_host_deinit(struct dp_ctrl *dp_ctrl);
 int dp_ctrl_on_link(struct dp_ctrl *dp_ctrl);
 int dp_ctrl_on_stream(struct dp_ctrl *dp_ctrl);
diff --git a/drivers/gpu/drm/msm/dp/dp_display.c b/drivers/gpu/drm/msm/dp/dp_display.c
index 3bc7ed21de28..5a39da6e1eaf 100644
--- a/drivers/gpu/drm/msm/dp/dp_display.c
+++ b/drivers/gpu/drm/msm/dp/dp_display.c
@@ -350,7 +350,7 @@ end:
 	return rc;
 }
 
-static void dp_display_host_init(struct dp_display_private *dp)
+static void dp_display_host_init(struct dp_display_private *dp, int reset)
 {
 	bool flip = false;
 
@@ -365,7 +365,7 @@ static void dp_display_host_init(struct dp_display_private *dp)
 	dp_display_set_encoder_mode(dp);
 
 	dp_power_init(dp->power, flip);
-	dp_ctrl_host_init(dp->ctrl, flip);
+	dp_ctrl_host_init(dp->ctrl, flip, reset);
 	dp_aux_init(dp->aux);
 	dp->core_initialized = true;
 }
@@ -403,7 +403,7 @@ static int dp_display_usbpd_configure_cb(struct device *dev)
 		goto end;
 	}
 
-	dp_display_host_init(dp);
+	dp_display_host_init(dp, false);
 
 	/*
 	 * set sink to normal operation mode -- D0
@@ -651,8 +651,8 @@ static int dp_hpd_unplug_handle(struct dp_display_private *dp, u32 data)
 	dp_add_event(dp, EV_DISCONNECT_PENDING_TIMEOUT, 0, DP_TIMEOUT_5_SECOND);
 
 	/* signal the disconnect event early to ensure proper teardown */
-	dp_display_handle_plugged_change(g_dp_display, false);
 	reinit_completion(&dp->audio_comp);
+	dp_display_handle_plugged_change(g_dp_display, false);
 
 	dp_catalog_hpd_config_intr(dp->catalog, DP_DP_HPD_PLUG_INT_MASK |
 					DP_DP_IRQ_HPD_INT_MASK, true);
@@ -700,6 +700,13 @@ static int dp_irq_hpd_handle(struct dp_display_private *dp, u32 data)
 		return 0;
 	}
 
+	if (state == ST_CONNECT_PENDING || state == ST_DISCONNECT_PENDING) {
+		/* wait until ST_CONNECTED */
+		dp_add_event(dp, EV_IRQ_HPD_INT, 0, 1); /* delay = 1 */
+		mutex_unlock(&dp->event_mutex);
+		return 0;
+	}
+
 	ret = dp_display_usbpd_attention_cb(&dp->pdev->dev);
 	if (ret == -ECONNRESET) { /* cable unplugged */
 		dp->core_initialized = false;
@@ -890,6 +897,9 @@ static int dp_display_disable(struct dp_display_private *dp, u32 data)
 
 	/* wait only if audio was enabled */
 	if (dp_display->audio_enabled) {
+		/* signal the disconnect event */
+		reinit_completion(&dp->audio_comp);
+		dp_display_handle_plugged_change(dp_display, false);
 		if (!wait_for_completion_timeout(&dp->audio_comp,
 				HZ * 5))
 			DRM_ERROR("audio comp timeout\n");
@@ -1002,7 +1012,7 @@ int dp_display_get_test_bpp(struct msm_dp *dp)
 static void dp_display_config_hpd(struct dp_display_private *dp)
 {
 
-	dp_display_host_init(dp);
+	dp_display_host_init(dp, true);
 	dp_catalog_ctrl_hpd_config(dp->catalog);
 
 	/* Enable interrupt first time
@@ -1256,7 +1266,7 @@ static int dp_pm_resume(struct device *dev)
 	dp->hpd_state = ST_DISCONNECTED;
 
 	/* turn on dp ctrl/phy */
-	dp_display_host_init(dp);
+	dp_display_host_init(dp, true);
 
 	dp_catalog_ctrl_hpd_config(dp->catalog);
 
@@ -1439,7 +1449,7 @@ int msm_dp_display_enable(struct msm_dp *dp, struct drm_encoder *encoder)
 	state =  dp_display->hpd_state;
 
 	if (state == ST_DISPLAY_OFF)
-		dp_display_host_init(dp_display);
+		dp_display_host_init(dp_display, true);
 
 	dp_display_enable(dp_display, 0);
 
diff --git a/drivers/gpu/drm/msm/dp/dp_panel.c b/drivers/gpu/drm/msm/dp/dp_panel.c
index d1780bcac8cc..9cc816663668 100644
--- a/drivers/gpu/drm/msm/dp/dp_panel.c
+++ b/drivers/gpu/drm/msm/dp/dp_panel.c
@@ -409,7 +409,6 @@ int dp_panel_timing_cfg(struct dp_panel *dp_panel)
 
 int dp_panel_init_panel_info(struct dp_panel *dp_panel)
 {
-	int rc = 0;
 	struct drm_display_mode *drm_mode;
 
 	drm_mode = &dp_panel->dp_mode.drm_mode;
@@ -436,7 +435,7 @@ int dp_panel_init_panel_info(struct dp_panel *dp_panel)
 					min_t(u32, dp_panel->dp_mode.bpp, 30));
 	DRM_DEBUG_DP("updated bpp = %d\n", dp_panel->dp_mode.bpp);
 
-	return rc;
+	return 0;
 }
 
 struct dp_panel *dp_panel_get(struct dp_panel_in *in)
diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_20nm.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_20nm.c
index 1afb7c579dbb..eca86bf448f7 100644
--- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_20nm.c
+++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_20nm.c
@@ -139,7 +139,7 @@ const struct msm_dsi_phy_cfg dsi_phy_20nm_cfgs = {
 		.disable = dsi_20nm_phy_disable,
 		.init = msm_dsi_phy_init_common,
 	},
-	.io_start = { 0xfd998300, 0xfd9a0300 },
+	.io_start = { 0xfd998500, 0xfd9a0500 },
 	.num_dsi_phy = 2,
 };
 
diff --git a/drivers/gpu/drm/msm/dsi/pll/dsi_pll_10nm.c b/drivers/gpu/drm/msm/dsi/pll/dsi_pll_10nm.c
index e4e9bf04b736..de3b802ccd3d 100644
--- a/drivers/gpu/drm/msm/dsi/pll/dsi_pll_10nm.c
+++ b/drivers/gpu/drm/msm/dsi/pll/dsi_pll_10nm.c
@@ -172,9 +172,7 @@ static void dsi_pll_calc_dec_frac(struct dsi_pll_10nm *pll)
 
 	multiplier = 1 << config->frac_bits;
 	dec_multiple = div_u64(pll_freq * multiplier, divider);
-	div_u64_rem(dec_multiple, multiplier, &frac);
-
-	dec = div_u64(dec_multiple, multiplier);
+	dec = div_u64_rem(dec_multiple, multiplier, &frac);
 
 	if (pll_freq <= 1900000000UL)
 		regs->pll_prop_gain_rate = 8;
@@ -306,7 +304,8 @@ static void dsi_pll_commit(struct dsi_pll_10nm *pll)
 		  reg->frac_div_start_mid);
 	pll_write(base + REG_DSI_10nm_PHY_PLL_FRAC_DIV_START_HIGH_1,
 		  reg->frac_div_start_high);
-	pll_write(base + REG_DSI_10nm_PHY_PLL_PLL_LOCKDET_RATE_1, 0x40);
+	pll_write(base + REG_DSI_10nm_PHY_PLL_PLL_LOCKDET_RATE_1,
+		  reg->pll_lockdet_rate);
 	pll_write(base + REG_DSI_10nm_PHY_PLL_PLL_LOCK_DELAY, 0x06);
 	pll_write(base + REG_DSI_10nm_PHY_PLL_CMODE, 0x10);
 	pll_write(base + REG_DSI_10nm_PHY_PLL_CLOCK_INVERTERS,
@@ -345,6 +344,7 @@ static int dsi_pll_10nm_vco_set_rate(struct clk_hw *hw, unsigned long rate,
 
 static int dsi_pll_10nm_lock_status(struct dsi_pll_10nm *pll)
 {
+	struct device *dev = &pll->pdev->dev;
 	int rc;
 	u32 status = 0;
 	u32 const delay_us = 100;
@@ -357,8 +357,8 @@ static int dsi_pll_10nm_lock_status(struct dsi_pll_10nm *pll)
 				       delay_us,
 				       timeout_us);
 	if (rc)
-		pr_err("DSI PLL(%d) lock failed, status=0x%08x\n",
-		       pll->id, status);
+		DRM_DEV_ERROR(dev, "DSI PLL(%d) lock failed, status=0x%08x\n",
+			      pll->id, status);
 
 	return rc;
 }
@@ -405,6 +405,7 @@ static int dsi_pll_10nm_vco_prepare(struct clk_hw *hw)
 {
 	struct msm_dsi_pll *pll = hw_clk_to_pll(hw);
 	struct dsi_pll_10nm *pll_10nm = to_pll_10nm(pll);
+	struct device *dev = &pll_10nm->pdev->dev;
 	int rc;
 
 	dsi_pll_enable_pll_bias(pll_10nm);
@@ -413,7 +414,7 @@ static int dsi_pll_10nm_vco_prepare(struct clk_hw *hw)
 
 	rc = dsi_pll_10nm_vco_set_rate(hw,pll_10nm->vco_current_rate, 0);
 	if (rc) {
-		pr_err("vco_set_rate failed, rc=%d\n", rc);
+		DRM_DEV_ERROR(dev, "vco_set_rate failed, rc=%d\n", rc);
 		return rc;
 	}
 
@@ -430,7 +431,7 @@ static int dsi_pll_10nm_vco_prepare(struct clk_hw *hw)
 	/* Check for PLL lock */
 	rc = dsi_pll_10nm_lock_status(pll_10nm);
 	if (rc) {
-		pr_err("PLL(%d) lock failed\n", pll_10nm->id);
+		DRM_DEV_ERROR(dev, "PLL(%d) lock failed\n", pll_10nm->id);
 		goto error;
 	}
 
@@ -483,6 +484,7 @@ static unsigned long dsi_pll_10nm_vco_recalc_rate(struct clk_hw *hw,
 {
 	struct msm_dsi_pll *pll = hw_clk_to_pll(hw);
 	struct dsi_pll_10nm *pll_10nm = to_pll_10nm(pll);
+	struct dsi_pll_config *config = &pll_10nm->pll_configuration;
 	void __iomem *base = pll_10nm->mmio;
 	u64 ref_clk = pll_10nm->vco_ref_clk_rate;
 	u64 vco_rate = 0x0;
@@ -503,9 +505,8 @@ static unsigned long dsi_pll_10nm_vco_recalc_rate(struct clk_hw *hw,
 	/*
 	 * TODO:
 	 *	1. Assumes prescaler is disabled
-	 *	2. Multiplier is 2^18. it should be 2^(num_of_frac_bits)
 	 */
-	multiplier = 1 << 18;
+	multiplier = 1 << config->frac_bits;
 	pll_freq = dec * (ref_clk * 2);
 	tmp64 = (ref_clk * 2 * frac);
 	pll_freq += div_u64(tmp64, multiplier);
diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c
index 108c405e03dd..94525ac76d4e 100644
--- a/drivers/gpu/drm/msm/msm_drv.c
+++ b/drivers/gpu/drm/msm/msm_drv.c
@@ -788,9 +788,10 @@ static int msm_ioctl_gem_info_iova(struct drm_device *dev,
 		struct drm_file *file, struct drm_gem_object *obj,
 		uint64_t *iova)
 {
+	struct msm_drm_private *priv = dev->dev_private;
 	struct msm_file_private *ctx = file->driver_priv;
 
-	if (!ctx->aspace)
+	if (!priv->gpu)
 		return -EINVAL;
 
 	/*
diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c
index a588b0388d27..f091c1e164fa 100644
--- a/drivers/gpu/drm/msm/msm_gem.c
+++ b/drivers/gpu/drm/msm/msm_gem.c
@@ -987,8 +987,7 @@ void msm_gem_free_object(struct drm_gem_object *obj)
 		/* Don't drop the pages for imported dmabuf, as they are not
 		 * ours, just free the array we allocated:
 		 */
-		if (msm_obj->pages)
-			kvfree(msm_obj->pages);
+		kvfree(msm_obj->pages);
 
 		put_iova_vmas(obj);
 
diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c
index d04c349d8112..5480852bdeda 100644
--- a/drivers/gpu/drm/msm/msm_gem_submit.c
+++ b/drivers/gpu/drm/msm/msm_gem_submit.c
@@ -198,6 +198,8 @@ static int submit_lookup_cmds(struct msm_gem_submit *submit,
 		submit->cmd[i].idx  = submit_cmd.submit_idx;
 		submit->cmd[i].nr_relocs = submit_cmd.nr_relocs;
 
+		userptr = u64_to_user_ptr(submit_cmd.relocs);
+
 		sz = array_size(submit_cmd.nr_relocs,
 				sizeof(struct drm_msm_gem_submit_reloc));
 		/* check for overflow: */
diff --git a/drivers/gpu/drm/msm/msm_kms.h b/drivers/gpu/drm/msm/msm_kms.h
index d8151a89e163..4735251a394d 100644
--- a/drivers/gpu/drm/msm/msm_kms.h
+++ b/drivers/gpu/drm/msm/msm_kms.h
@@ -157,6 +157,7 @@ struct msm_kms {
 	 * from the crtc's pending_timer close to end of the frame:
 	 */
 	struct mutex commit_lock[MAX_CRTCS];
+	struct lock_class_key commit_lock_keys[MAX_CRTCS];
 	unsigned pending_crtc_mask;
 	struct msm_pending_timer pending_timers[MAX_CRTCS];
 };
@@ -166,8 +167,11 @@ static inline int msm_kms_init(struct msm_kms *kms,
 {
 	unsigned i, ret;
 
-	for (i = 0; i < ARRAY_SIZE(kms->commit_lock); i++)
-		mutex_init(&kms->commit_lock[i]);
+	for (i = 0; i < ARRAY_SIZE(kms->commit_lock); i++) {
+		lockdep_register_key(&kms->commit_lock_keys[i]);
+		__mutex_init(&kms->commit_lock[i], "&kms->commit_lock[i]",
+			     &kms->commit_lock_keys[i]);
+	}
 
 	kms->funcs = funcs;
 
diff --git a/drivers/gpu/drm/panel/panel-elida-kd35t133.c b/drivers/gpu/drm/panel/panel-elida-kd35t133.c
index bc36aa3c1123..fe5ac3ef9018 100644
--- a/drivers/gpu/drm/panel/panel-elida-kd35t133.c
+++ b/drivers/gpu/drm/panel/panel-elida-kd35t133.c
@@ -265,7 +265,8 @@ static int kd35t133_probe(struct mipi_dsi_device *dsi)
 	dsi->lanes = 1;
 	dsi->format = MIPI_DSI_FMT_RGB888;
 	dsi->mode_flags = MIPI_DSI_MODE_VIDEO | MIPI_DSI_MODE_VIDEO_BURST |
-			  MIPI_DSI_MODE_LPM | MIPI_DSI_MODE_EOT_PACKET;
+			  MIPI_DSI_MODE_LPM | MIPI_DSI_MODE_EOT_PACKET |
+			  MIPI_DSI_CLOCK_NON_CONTINUOUS;
 
 	drm_panel_init(&ctx->panel, &dsi->dev, &kd35t133_funcs,
 		       DRM_MODE_CONNECTOR_DSI);
diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop.h b/drivers/gpu/drm/rockchip/rockchip_drm_vop.h
index 4a2099cb582e..857d97cdc67c 100644
--- a/drivers/gpu/drm/rockchip/rockchip_drm_vop.h
+++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop.h
@@ -17,9 +17,20 @@
 
 #define NUM_YUV2YUV_COEFFICIENTS 12
 
+/* AFBC supports a number of configurable modes. Relevant to us is block size
+ * (16x16 or 32x8), storage modifiers (SPARSE, SPLIT), and the YUV-like
+ * colourspace transform (YTR). 16x16 SPARSE mode is always used. SPLIT mode
+ * could be enabled via the hreg_block_split register, but is not currently
+ * handled. The colourspace transform is implicitly always assumed by the
+ * decoder, so consumers must use this transform as well.
+ *
+ * Failure to match modifiers will cause errors displaying AFBC buffers
+ * produced by conformant AFBC producers, including Mesa.
+ */
 #define ROCKCHIP_AFBC_MOD \
 	DRM_FORMAT_MOD_ARM_AFBC( \
 		AFBC_FORMAT_MOD_BLOCK_SIZE_16x16 | AFBC_FORMAT_MOD_SPARSE \
+			| AFBC_FORMAT_MOD_YTR \
 	)
 
 enum vop_data_format {
diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index b65f4b12f986..20a25660b35b 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -959,8 +959,10 @@ static int ttm_bo_bounce_temp_buffer(struct ttm_buffer_object *bo,
 		return ret;
 	/* move to the bounce domain */
 	ret = ttm_bo_handle_move_mem(bo, &hop_mem, false, ctx, NULL);
-	if (ret)
+	if (ret) {
+		ttm_resource_free(bo, &hop_mem);
 		return ret;
+	}
 	return 0;
 }
 
@@ -991,18 +993,19 @@ static int ttm_bo_move_buffer(struct ttm_buffer_object *bo,
 	 * stop and the driver will be called to make
 	 * the second hop.
 	 */
-bounce:
 	ret = ttm_bo_mem_space(bo, placement, &mem, ctx);
 	if (ret)
 		return ret;
+bounce:
 	ret = ttm_bo_handle_move_mem(bo, &mem, false, ctx, &hop);
 	if (ret == -EMULTIHOP) {
 		ret = ttm_bo_bounce_temp_buffer(bo, &mem, ctx, &hop);
 		if (ret)
-			return ret;
+			goto out;
 		/* try and move to final place now. */
 		goto bounce;
 	}
+out:
 	if (ret)
 		ttm_resource_free(bo, &mem);
 	return ret;
diff --git a/drivers/video/fbdev/aty/atyfb_base.c b/drivers/video/fbdev/aty/atyfb_base.c
index 83c8e809955a..e946903a86c2 100644
--- a/drivers/video/fbdev/aty/atyfb_base.c
+++ b/drivers/video/fbdev/aty/atyfb_base.c
@@ -175,6 +175,15 @@ u32 aty_ld_lcd(int index, const struct atyfb_par *par)
 		return aty_ld_le32(LCD_DATA, par);
 	}
 }
+#else /* defined(CONFIG_PMAC_BACKLIGHT) || defined(CONFIG_FB_ATY_BACKLIGHT) \
+	 defined(CONFIG_FB_ATY_GENERIC_LCD) */
+void aty_st_lcd(int index, u32 val, const struct atyfb_par *par)
+{ }
+
+u32 aty_ld_lcd(int index, const struct atyfb_par *par)
+{
+	return 0;
+}
 #endif /* defined(CONFIG_PMAC_BACKLIGHT) || defined (CONFIG_FB_ATY_GENERIC_LCD) */
 
 #ifdef CONFIG_FB_ATY_GENERIC_LCD