Merge v7.1-rc5 into drm-next

Boris Brezillion needs the gem lru fixes 379e8f1ca5e9 ("drm/gem: Make
the GEM LRU lock part of drm_device") backmerged for drm-misc-next.
That also means we need to sort out the rename conflict in panthor with
the fixup patch from Boris from drm-tip.

Signed-off-by: Simona Vetter <simona.vetter@ffwll.ch>

61 files changed, 390 insertions, 275 deletions

diff --git a/drivers/gpu/drm/bridge/chipone-icn6211.c b/drivers/gpu/drm/bridge/chipone-icn6211.c
index e5957917ad88..d8344e011818 100644
--- a/drivers/gpu/drm/bridge/chipone-icn6211.c
+++ b/drivers/gpu/drm/bridge/chipone-icn6211.c
@@ -756,7 +756,9 @@ static int chipone_i2c_probe(struct i2c_client *client)
 	dev_set_drvdata(dev, icn);
 	i2c_set_clientdata(client, icn);
 
-	drm_bridge_add(&icn->bridge);
+	ret = devm_drm_bridge_add(dev, &icn->bridge);
+	if (ret)
+		return ret;
 
 	return chipone_dsi_host_attach(icn);
 }
diff --git a/drivers/gpu/drm/bridge/imx/imx8qxp-pxl2dpi.c b/drivers/gpu/drm/bridge/imx/imx8qxp-pxl2dpi.c
index 2e59f53f0eb6..87305d3e0c39 100644
--- a/drivers/gpu/drm/bridge/imx/imx8qxp-pxl2dpi.c
+++ b/drivers/gpu/drm/bridge/imx/imx8qxp-pxl2dpi.c
@@ -222,52 +222,58 @@ static const struct drm_bridge_funcs imx8qxp_pxl2dpi_bridge_funcs = {
 			imx8qxp_pxl2dpi_bridge_atomic_get_output_bus_fmts,
 };
 
-static struct device_node *
+static int
 imx8qxp_pxl2dpi_get_available_ep_from_port(struct imx8qxp_pxl2dpi *p2d,
-					   u32 port_id)
+					   u32 port_id,
+					   struct device_node **ep)
 {
-	struct device_node *port, *ep;
+	struct device_node *port;
+	int ret = 0;
 	int ep_cnt;
 
+	*ep = NULL;
+
 	port = of_graph_get_port_by_id(p2d->dev->of_node, port_id);
 	if (!port) {
 		DRM_DEV_ERROR(p2d->dev, "failed to get port@%u\n", port_id);
-		return ERR_PTR(-ENODEV);
+		return -ENODEV;
 	}
 
 	ep_cnt = of_get_available_child_count(port);
 	if (ep_cnt == 0) {
 		DRM_DEV_ERROR(p2d->dev, "no available endpoints of port@%u\n",
 			      port_id);
-		ep = ERR_PTR(-ENODEV);
+		ret = -ENODEV;
 		goto out;
 	} else if (ep_cnt > 1) {
 		DRM_DEV_ERROR(p2d->dev,
 			      "invalid available endpoints of port@%u\n",
 			      port_id);
-		ep = ERR_PTR(-EINVAL);
+		ret = -EINVAL;
 		goto out;
 	}
 
-	ep = of_get_next_available_child(port, NULL);
-	if (!ep) {
+	*ep = of_get_next_available_child(port, NULL);
+	if (!*ep) {
 		DRM_DEV_ERROR(p2d->dev,
 			      "failed to get available endpoint of port@%u\n",
 			      port_id);
-		ep = ERR_PTR(-ENODEV);
+		ret = -ENODEV;
 		goto out;
 	}
 out:
 	of_node_put(port);
-	return ep;
+	return ret;
 }
 
 static int imx8qxp_pxl2dpi_find_next_bridge(struct imx8qxp_pxl2dpi *p2d)
 {
-	struct device_node *ep __free(device_node) =
-		imx8qxp_pxl2dpi_get_available_ep_from_port(p2d, 1);
-	if (IS_ERR(ep))
-		return PTR_ERR(ep);
+	struct device_node *ep __free(device_node) = NULL;
+	int ret;
+
+	ret = imx8qxp_pxl2dpi_get_available_ep_from_port(p2d, 1, &ep);
+	if (ret)
+		return ret;
 
 	struct device_node *remote __free(device_node) = of_graph_get_remote_port_parent(ep);
 	if (!remote || !of_device_is_available(remote)) {
@@ -291,9 +297,9 @@ static int imx8qxp_pxl2dpi_set_pixel_link_sel(struct imx8qxp_pxl2dpi *p2d)
 	struct of_endpoint endpoint;
 	int ret;
 
-	ep = imx8qxp_pxl2dpi_get_available_ep_from_port(p2d, 0);
-	if (IS_ERR(ep))
-		return PTR_ERR(ep);
+	ret = imx8qxp_pxl2dpi_get_available_ep_from_port(p2d, 0, &ep);
+	if (ret)
+		return ret;
 
 	ret = of_graph_parse_endpoint(ep, &endpoint);
 	if (ret) {
diff --git a/drivers/gpu/drm/bridge/ite-it66121.c b/drivers/gpu/drm/bridge/ite-it66121.c
index 19e188fe6e3b..fd14639c0f9a 100644
--- a/drivers/gpu/drm/bridge/ite-it66121.c
+++ b/drivers/gpu/drm/bridge/ite-it66121.c
@@ -1509,6 +1509,11 @@ static int it66121_probe(struct i2c_client *client)
 		return ret;
 	}
 
+	ctx->gpio_reset = devm_gpiod_get(dev, "reset", GPIOD_OUT_LOW);
+	if (IS_ERR(ctx->gpio_reset))
+		return dev_err_probe(dev, PTR_ERR(ctx->gpio_reset),
+				     "Failed to get reset GPIO\n");
+
 	it66121_hw_reset(ctx);
 
 	ctx->regmap = devm_regmap_init_i2c(client, &it66121_regmap_config);
diff --git a/drivers/gpu/drm/bridge/megachips-stdpxxxx-ge-b850v3-fw.c b/drivers/gpu/drm/bridge/megachips-stdpxxxx-ge-b850v3-fw.c
index c9e6505cbd88..2d02cc69f237 100644
--- a/drivers/gpu/drm/bridge/megachips-stdpxxxx-ge-b850v3-fw.c
+++ b/drivers/gpu/drm/bridge/megachips-stdpxxxx-ge-b850v3-fw.c
@@ -251,7 +251,6 @@ static void ge_b850v3_lvds_remove(void)
 		goto out;
 
 	drm_bridge_remove(&ge_b850v3_lvds_ptr->bridge);
-
 	ge_b850v3_lvds_ptr = NULL;
 out:
 	mutex_unlock(&ge_b850v3_lvds_dev_mutex);
@@ -261,6 +260,7 @@ static int ge_b850v3_register(void)
 {
 	struct i2c_client *stdp4028_i2c = ge_b850v3_lvds_ptr->stdp4028_i2c;
 	struct device *dev = &stdp4028_i2c->dev;
+	int ret;
 
 	/* drm bridge initialization */
 	ge_b850v3_lvds_ptr->bridge.ops = DRM_BRIDGE_OP_DETECT |
@@ -277,11 +277,15 @@ static int ge_b850v3_register(void)
 	if (!stdp4028_i2c->irq)
 		return 0;
 
-	return devm_request_threaded_irq(&stdp4028_i2c->dev,
-			stdp4028_i2c->irq, NULL,
-			ge_b850v3_lvds_irq_handler,
-			IRQF_TRIGGER_HIGH | IRQF_ONESHOT,
-			"ge-b850v3-lvds-dp", ge_b850v3_lvds_ptr);
+	ret = devm_request_threaded_irq(&stdp4028_i2c->dev,
+					stdp4028_i2c->irq, NULL,
+					ge_b850v3_lvds_irq_handler,
+					IRQF_TRIGGER_HIGH | IRQF_ONESHOT,
+					"ge-b850v3-lvds-dp", ge_b850v3_lvds_ptr);
+	if (ret)
+		drm_bridge_remove(&ge_b850v3_lvds_ptr->bridge);
+
+	return ret;
 }
 
 static int stdp4028_ge_b850v3_fw_probe(struct i2c_client *stdp4028_i2c)
diff --git a/drivers/gpu/drm/bridge/tda998x_drv.c b/drivers/gpu/drm/bridge/tda998x_drv.c
index d9b388165de1..6c427bc75896 100644
--- a/drivers/gpu/drm/bridge/tda998x_drv.c
+++ b/drivers/gpu/drm/bridge/tda998x_drv.c
@@ -1293,7 +1293,7 @@ static const struct drm_edid *tda998x_edid_read(struct tda998x_priv *priv,
 	 * can't handle signals gracefully.
 	 */
 	if (tda998x_edid_delay_wait(priv))
-		return 0;
+		return NULL;
 
 	if (priv->rev == TDA19988)
 		reg_clear(priv, REG_TX4, TX4_PD_RAM);
@@ -1762,7 +1762,7 @@ static const struct drm_bridge_funcs tda998x_bridge_funcs = {
 static int tda998x_get_audio_ports(struct tda998x_priv *priv,
 				   struct device_node *np)
 {
-	const u32 *port_data;
+	const __be32 *port_data;
 	u32 size;
 	int i;
 
diff --git a/drivers/gpu/drm/drm_drv.c b/drivers/gpu/drm/drm_drv.c
index 985c283cf59f..675675480da4 100644
--- a/drivers/gpu/drm/drm_drv.c
+++ b/drivers/gpu/drm/drm_drv.c
@@ -697,6 +697,7 @@ static void drm_dev_init_release(struct drm_device *dev, void *res)
 	mutex_destroy(&dev->master_mutex);
 	mutex_destroy(&dev->clientlist_mutex);
 	mutex_destroy(&dev->filelist_mutex);
+	mutex_destroy(&dev->gem_lru_mutex);
 }
 
 static int drm_dev_init(struct drm_device *dev,
@@ -738,6 +739,7 @@ static int drm_dev_init(struct drm_device *dev,
 	INIT_LIST_HEAD(&dev->vblank_event_list);
 
 	spin_lock_init(&dev->event_lock);
+	mutex_init(&dev->gem_lru_mutex);
 	mutex_init(&dev->filelist_mutex);
 	mutex_init(&dev->clientlist_mutex);
 	mutex_init(&dev->master_mutex);
diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c
index 38d25dce7f33..7b11a582f8ec 100644
--- a/drivers/gpu/drm/drm_fb_helper.c
+++ b/drivers/gpu/drm/drm_fb_helper.c
@@ -490,7 +490,7 @@ static void drm_fb_helper_memory_range_to_clip(struct fb_info *info, off_t off,
 		 * the number of horizontal pixels that need an update.
 		 */
 		off_t bit_off = (off % line_length) * 8;
-		off_t bit_end = (end % line_length) * 8;
+		off_t bit_end = bit_off + len * 8;
 
 		x1 = bit_off / info->var.bits_per_pixel;
 		x2 = DIV_ROUND_UP(bit_end, info->var.bits_per_pixel);
diff --git a/drivers/gpu/drm/drm_gem.c b/drivers/gpu/drm/drm_gem.c
index fca42949eb2b..4c781c431642 100644
--- a/drivers/gpu/drm/drm_gem.c
+++ b/drivers/gpu/drm/drm_gem.c
@@ -1019,7 +1019,7 @@ int drm_gem_change_handle_ioctl(struct drm_device *dev, void *data,
 				struct drm_file *file_priv)
 {
 	struct drm_gem_change_handle *args = data;
-	struct drm_gem_object *obj;
+	struct drm_gem_object *obj, *idrobj;
 	int handle, ret;
 
 	if (!drm_core_check_feature(dev, DRIVER_GEM))
@@ -1042,12 +1042,30 @@ int drm_gem_change_handle_ioctl(struct drm_device *dev, void *data,
 	mutex_lock(&file_priv->prime.lock);
 
 	spin_lock(&file_priv->table_lock);
+
+       /* When create_tail allocs an obj idr, it needs to first alloc as NULL,
+	* then later replace with the correct object. This is not necessary
+	* here, because the only operations that could race are drm_prime
+	* bookkeeping, and we hold the prime lock.
+	*/
 	ret = idr_alloc(&file_priv->object_idr, obj, handle, handle + 1,
 			GFP_NOWAIT);
-	spin_unlock(&file_priv->table_lock);
 
-	if (ret < 0)
-		goto out_unlock;
+       if (ret < 0) {
+	       spin_unlock(&file_priv->table_lock);
+	       goto out_unlock;
+       }
+
+       idrobj = idr_replace(&file_priv->object_idr, NULL, handle);
+       if (idrobj != obj) {
+	       idr_replace(&file_priv->object_idr, idrobj, handle);
+	       idr_remove(&file_priv->object_idr, args->new_handle);
+	       spin_unlock(&file_priv->table_lock);
+	       ret = -ENOENT;
+	       goto out_unlock;
+       }
+
+	spin_unlock(&file_priv->table_lock);
 
 	if (obj->dma_buf) {
 		ret = drm_prime_add_buf_handle(&file_priv->prime, obj->dma_buf,
@@ -1066,7 +1084,9 @@ int drm_gem_change_handle_ioctl(struct drm_device *dev, void *data,
 
 	spin_lock(&file_priv->table_lock);
 	idr_remove(&file_priv->object_idr, args->handle);
+	idrobj = idr_replace(&file_priv->object_idr, obj, handle);
 	spin_unlock(&file_priv->table_lock);
+	WARN_ON(idrobj != NULL);
 
 out_unlock:
 	mutex_unlock(&file_priv->prime.lock);
@@ -1541,12 +1561,10 @@ EXPORT_SYMBOL(drm_gem_unlock_reservations);
  * drm_gem_lru_init - initialize a LRU
  *
  * @lru: The LRU to initialize
- * @lock: The lock protecting the LRU
  */
 void
-drm_gem_lru_init(struct drm_gem_lru *lru, struct mutex *lock)
+drm_gem_lru_init(struct drm_gem_lru *lru)
 {
-	lru->lock = lock;
 	lru->count = 0;
 	INIT_LIST_HEAD(&lru->list);
 }
@@ -1571,14 +1589,10 @@ drm_gem_lru_remove_locked(struct drm_gem_object *obj)
 void
 drm_gem_lru_remove(struct drm_gem_object *obj)
 {
-	struct drm_gem_lru *lru = obj->lru;
-
-	if (!lru)
-		return;
-
-	mutex_lock(lru->lock);
-	drm_gem_lru_remove_locked(obj);
-	mutex_unlock(lru->lock);
+	mutex_lock(&obj->dev->gem_lru_mutex);
+	if (obj->lru)
+		drm_gem_lru_remove_locked(obj);
+	mutex_unlock(&obj->dev->gem_lru_mutex);
 }
 EXPORT_SYMBOL(drm_gem_lru_remove);
 
@@ -1593,7 +1607,7 @@ EXPORT_SYMBOL(drm_gem_lru_remove);
 void
 drm_gem_lru_move_tail_locked(struct drm_gem_lru *lru, struct drm_gem_object *obj)
 {
-	lockdep_assert_held_once(lru->lock);
+	lockdep_assert_held_once(&obj->dev->gem_lru_mutex);
 
 	if (obj->lru)
 		drm_gem_lru_remove_locked(obj);
@@ -1617,9 +1631,9 @@ EXPORT_SYMBOL(drm_gem_lru_move_tail_locked);
 void
 drm_gem_lru_move_tail(struct drm_gem_lru *lru, struct drm_gem_object *obj)
 {
-	mutex_lock(lru->lock);
+	mutex_lock(&obj->dev->gem_lru_mutex);
 	drm_gem_lru_move_tail_locked(lru, obj);
-	mutex_unlock(lru->lock);
+	mutex_unlock(&obj->dev->gem_lru_mutex);
 }
 EXPORT_SYMBOL(drm_gem_lru_move_tail);
 
@@ -1633,6 +1647,7 @@ EXPORT_SYMBOL(drm_gem_lru_move_tail);
  * of the shrink callback to check for this (ie. dma_resv_test_signaled())
  * or if necessary block until the buffer becomes idle.
  *
+ * @dev: DRM device the LRU belongs to
  * @lru: The LRU to scan
  * @nr_to_scan: The number of pages to try to reclaim
  * @remaining: The number of pages left to reclaim, should be initialized by caller
@@ -1640,7 +1655,8 @@ EXPORT_SYMBOL(drm_gem_lru_move_tail);
  * @ticket: Optional ww_acquire_ctx context to use for locking
  */
 unsigned long
-drm_gem_lru_scan(struct drm_gem_lru *lru,
+drm_gem_lru_scan(struct drm_device *dev,
+		 struct drm_gem_lru *lru,
 		 unsigned int nr_to_scan,
 		 unsigned long *remaining,
 		 bool (*shrink)(struct drm_gem_object *obj, struct ww_acquire_ctx *ticket),
@@ -1650,9 +1666,9 @@ drm_gem_lru_scan(struct drm_gem_lru *lru,
 	struct drm_gem_object *obj;
 	unsigned freed = 0;
 
-	drm_gem_lru_init(&still_in_lru, lru->lock);
+	drm_gem_lru_init(&still_in_lru);
 
-	mutex_lock(lru->lock);
+	mutex_lock(&dev->gem_lru_mutex);
 
 	while (freed < nr_to_scan) {
 		obj = list_first_entry_or_null(&lru->list, typeof(*obj), lru_node);
@@ -1675,7 +1691,7 @@ drm_gem_lru_scan(struct drm_gem_lru *lru,
 		 * rest of the loop body, to reduce contention with other
 		 * code paths that need the LRU lock
 		 */
-		mutex_unlock(lru->lock);
+		mutex_unlock(&dev->gem_lru_mutex);
 
 		if (ticket)
 			ww_acquire_init(ticket, &reservation_ww_class);
@@ -1719,7 +1735,7 @@ drm_gem_lru_scan(struct drm_gem_lru *lru,
 
 tail:
 		drm_gem_object_put(obj);
-		mutex_lock(lru->lock);
+		mutex_lock(&dev->gem_lru_mutex);
 	}
 
 	/*
@@ -1731,7 +1747,7 @@ tail:
 	list_splice_tail(&still_in_lru.list, &lru->list);
 	lru->count += still_in_lru.count;
 
-	mutex_unlock(lru->lock);
+	mutex_unlock(&dev->gem_lru_mutex);
 
 	return freed;
 }
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_sched.c b/drivers/gpu/drm/etnaviv/etnaviv_sched.c
index 63f672536516..139e6e38784b 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_sched.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_sched.c
@@ -116,16 +116,18 @@ int etnaviv_sched_push_job(struct etnaviv_gem_submit *submit)
 	 */
 	mutex_lock(&gpu->sched_lock);
 
+	ret = xa_alloc_cyclic(&gpu->user_fences, &submit->out_fence_id,
+			      NULL, xa_limit_32b, &gpu->next_user_fence,
+			      GFP_KERNEL);
+	if (ret < 0)
+		goto out_unlock;
+
 	drm_sched_job_arm(&submit->sched_job);
 
 	submit->out_fence = dma_fence_get(&submit->sched_job.s_fence->finished);
-	ret = xa_alloc_cyclic(&gpu->user_fences, &submit->out_fence_id,
-			      submit->out_fence, xa_limit_32b,
-			      &gpu->next_user_fence, GFP_KERNEL);
-	if (ret < 0) {
-		drm_sched_job_cleanup(&submit->sched_job);
-		goto out_unlock;
-	}
+
+	xa_store(&gpu->user_fences, submit->out_fence_id,
+		 submit->out_fence, GFP_KERNEL);
 
 	/* the scheduler holds on to the job now */
 	kref_get(&submit->refcount);
diff --git a/drivers/gpu/drm/exynos/exynos_drm_mic.c b/drivers/gpu/drm/exynos/exynos_drm_mic.c
index 29a8366513fa..e68c954ec3e6 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_mic.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_mic.c
@@ -423,7 +423,9 @@ static int exynos_mic_probe(struct platform_device *pdev)
 
 	mic->bridge.of_node = dev->of_node;
 
-	drm_bridge_add(&mic->bridge);
+	ret = devm_drm_bridge_add(dev, &mic->bridge);
+	if (ret)
+		goto err;
 
 	pm_runtime_enable(dev);
 
@@ -443,12 +445,8 @@ err:
 
 static void exynos_mic_remove(struct platform_device *pdev)
 {
-	struct exynos_mic *mic = platform_get_drvdata(pdev);
-
 	component_del(&pdev->dev, &exynos_mic_component_ops);
 	pm_runtime_disable(&pdev->dev);
-
-	drm_bridge_remove(&mic->bridge);
 }
 
 static const struct of_device_id exynos_mic_of_match[] = {
diff --git a/drivers/gpu/drm/gma500/oaktrail_hdmi.c b/drivers/gpu/drm/gma500/oaktrail_hdmi.c
index 58d7e191fd56..403d21cbb3a2 100644
--- a/drivers/gpu/drm/gma500/oaktrail_hdmi.c
+++ b/drivers/gpu/drm/gma500/oaktrail_hdmi.c
@@ -580,6 +580,7 @@ static int oaktrail_hdmi_get_modes(struct drm_connector *connector)
 	} else {
 		edid = (struct edid *)raw_edid;
 		/* FIXME ? edid = drm_get_edid(connector, i2c_adap); */
+		i2c_put_adapter(i2c_adap);
 	}
 
 	if (edid) {
diff --git a/drivers/gpu/drm/gma500/oaktrail_lvds.c b/drivers/gpu/drm/gma500/oaktrail_lvds.c
index 884d324f0044..e194d0cce067 100644
--- a/drivers/gpu/drm/gma500/oaktrail_lvds.c
+++ b/drivers/gpu/drm/gma500/oaktrail_lvds.c
@@ -293,7 +293,7 @@ void oaktrail_lvds_init(struct drm_device *dev,
 {
 	struct gma_encoder *gma_encoder;
 	struct gma_connector *gma_connector;
-	struct gma_i2c_chan *ddc_bus;
+	struct gma_i2c_chan *ddc_bus = NULL;
 	struct drm_connector *connector;
 	struct drm_encoder *encoder;
 	struct drm_psb_private *dev_priv = to_drm_psb_private(dev);
@@ -367,6 +367,8 @@ void oaktrail_lvds_init(struct drm_device *dev,
 	if (edid == NULL && dev_priv->lpc_gpio_base) {
 		ddc_bus = oaktrail_lvds_i2c_init(dev);
 		if (!IS_ERR(ddc_bus)) {
+			if (i2c_adap)
+				i2c_put_adapter(i2c_adap);
 			i2c_adap = &ddc_bus->base;
 			edid = drm_get_edid(connector, i2c_adap);
 		}
@@ -421,7 +423,10 @@ out:
 
 err_unlock:
 	mutex_unlock(&dev->mode_config.mutex);
-	gma_i2c_destroy(to_gma_i2c_chan(connector->ddc));
+	if (!IS_ERR_OR_NULL(ddc_bus))
+		gma_i2c_destroy(ddc_bus);
+	else if (i2c_adap)
+		i2c_put_adapter(i2c_adap);
 	drm_encoder_cleanup(encoder);
 err_connector_cleanup:
 	drm_connector_cleanup(connector);
diff --git a/drivers/gpu/drm/i915/display/intel_display_types.h b/drivers/gpu/drm/i915/display/intel_display_types.h
index b7bcf8fefa3e..f44be5c689ae 100644
--- a/drivers/gpu/drm/i915/display/intel_display_types.h
+++ b/drivers/gpu/drm/i915/display/intel_display_types.h
@@ -584,6 +584,7 @@ struct intel_connector {
 
 		struct {
 			u8 dpcd[EDP_PSR_RECEIVER_CAP_SIZE];
+			u8 intel_wa_dpcd;
 
 			bool support;
 			bool su_support;
diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c
index 61ccaf0a46b6..f01a6eed3839 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.c
+++ b/drivers/gpu/drm/i915/display/intel_dp.c
@@ -5376,7 +5376,7 @@ int intel_dp_as_sdp_unpack(struct drm_dp_as_sdp *as_sdp,
 	as_sdp->length = sdp->sdp_header.HB3 & DP_AS_SDP_LENGTH_MASK;
 	as_sdp->mode = sdp->db[0] & DP_AS_SDP_OPERATION_MODE_MASK;
 	as_sdp->vtotal = (sdp->db[2] << 8) | sdp->db[1];
-	as_sdp->target_rr = (u64)sdp->db[3] | ((u64)sdp->db[4] & 0x3);
+	as_sdp->target_rr = ((sdp->db[4] & 0x3) << 8) | sdp->db[3];
 	as_sdp->target_rr_divider = sdp->db[4] & 0x20 ? true : false;
 
 	return 0;
diff --git a/drivers/gpu/drm/i915/display/intel_dpcd.h b/drivers/gpu/drm/i915/display/intel_dpcd.h
new file mode 100644
index 000000000000..4aea5326f2ed
--- /dev/null
+++ b/drivers/gpu/drm/i915/display/intel_dpcd.h
@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2026 Intel Corporation
+ */
+
+#ifndef __INTEL_DPCD_H__
+#define __INTEL_DPCD_H__
+
+#define INTEL_DPCD_INTEL_WA_REGISTER_CAPS					0x3f0
+# define INTEL_DPCD_INTEL_WA_REGISTER_CAPS_PSR2_EARLYSCANLINE_SDP_SUPPORT_MASK	REG_GENMASK(1, 0)
+# define INTEL_DPCD_INTEL_WA_REGISTER_CAPS_FALL_BACK_TO_PSR1			0
+# define INTEL_DPCD_INTEL_WA_REGISTER_CAPS_PSR2_WITH_EARLY_SCANLINE		1
+# define INTEL_DPCD_INTEL_WA_REGISTER_CAPS_PSR2_WITHOUT_EARLY_SCANLINE		2
+
+#endif /* __INTEL_DPCD_H__ */
diff --git a/drivers/gpu/drm/i915/display/intel_psr.c b/drivers/gpu/drm/i915/display/intel_psr.c
index 892d209dce1b..bb1c0252837e 100644
--- a/drivers/gpu/drm/i915/display/intel_psr.c
+++ b/drivers/gpu/drm/i915/display/intel_psr.c
@@ -44,6 +44,7 @@
 #include "intel_display_wa.h"
 #include "intel_dmc.h"
 #include "intel_dp.h"
+#include "intel_dpcd.h"
 #include "intel_dp_aux.h"
 #include "intel_dp_tunnel.h"
 #include "intel_dsb.h"
@@ -720,8 +721,14 @@ static void _psr_init_dpcd(struct intel_dp *intel_dp, struct intel_connector *co
 			    connector->dp.psr_caps.su_support ? "" : "not ");
 	}
 
-	if (connector->dp.psr_caps.su_support)
+	if (connector->dp.psr_caps.su_support) {
+		ret = drm_dp_dpcd_read_byte(&intel_dp->aux,
+					    INTEL_DPCD_INTEL_WA_REGISTER_CAPS,
+					    &connector->dp.psr_caps.intel_wa_dpcd);
+		if (ret < 0)
+			return;
 		_psr_compute_su_granularity(intel_dp, connector);
+	}
 }
 
 void intel_psr_init_dpcd(struct intel_dp *intel_dp, struct intel_connector *connector)
@@ -1382,9 +1389,35 @@ static bool psr2_granularity_check(struct intel_crtc_state *crtc_state,
 	return true;
 }
 
-static bool _compute_psr2_sdp_prior_scanline_indication(struct intel_dp *intel_dp,
-							struct intel_crtc_state *crtc_state)
+static bool apply_scanline_indication_wa(struct intel_crtc_state *crtc_state,
+					 struct intel_connector *connector)
+{
+	struct intel_dp *intel_dp = intel_attached_dp(connector);
+	u8 early_scanline_support = connector->dp.psr_caps.intel_wa_dpcd &
+		INTEL_DPCD_INTEL_WA_REGISTER_CAPS_PSR2_EARLYSCANLINE_SDP_SUPPORT_MASK;
+
+	if (intel_dp->edp_dpcd[0] >= DP_EDP_15)
+		return true;
+
+	switch (early_scanline_support)	{
+	case INTEL_DPCD_INTEL_WA_REGISTER_CAPS_FALL_BACK_TO_PSR1:
+		crtc_state->req_psr2_sdp_prior_scanline = false;
+		return false;
+	case INTEL_DPCD_INTEL_WA_REGISTER_CAPS_PSR2_WITH_EARLY_SCANLINE:
+		return true;
+	case INTEL_DPCD_INTEL_WA_REGISTER_CAPS_PSR2_WITHOUT_EARLY_SCANLINE:
+		crtc_state->req_psr2_sdp_prior_scanline = false;
+		return true;
+	default:
+		MISSING_CASE(early_scanline_support);
+		return false;
+	}
+}
+
+static bool _compute_psr2_sdp_prior_scanline_indication(struct intel_crtc_state *crtc_state,
+							struct intel_connector *connector)
 {
+	struct intel_dp *intel_dp = intel_attached_dp(connector);
 	struct intel_display *display = to_intel_display(intel_dp);
 	const struct drm_display_mode *adjusted_mode = &crtc_state->uapi.adjusted_mode;
 	u32 hblank_total, hblank_ns, req_ns;
@@ -1403,7 +1436,8 @@ static bool _compute_psr2_sdp_prior_scanline_indication(struct intel_dp *intel_d
 		return false;
 
 	crtc_state->req_psr2_sdp_prior_scanline = true;
-	return true;
+
+	return apply_scanline_indication_wa(crtc_state, connector);
 }
 
 static int intel_psr_entry_setup_frames(struct intel_dp *intel_dp,
@@ -1684,7 +1718,7 @@ static bool intel_sel_update_config_valid(struct intel_crtc_state *crtc_state,
 								      conn_state))
 		goto unsupported;
 
-	if (!_compute_psr2_sdp_prior_scanline_indication(intel_dp, crtc_state)) {
+	if (!_compute_psr2_sdp_prior_scanline_indication(crtc_state, connector)) {
 		drm_dbg_kms(display->drm,
 			    "Selective update not enabled, SDP indication do not fit in hblank\n");
 		goto unsupported;
diff --git a/drivers/gpu/drm/i915/gt/intel_reset.c b/drivers/gpu/drm/i915/gt/intel_reset.c
index 0b5f3fc58009..b2cf672564dd 100644
--- a/drivers/gpu/drm/i915/gt/intel_reset.c
+++ b/drivers/gpu/drm/i915/gt/intel_reset.c
@@ -133,7 +133,8 @@ void __i915_request_reset(struct i915_request *rq, bool guilty)
 	rcu_read_lock(); /* protect the GEM context */
 	if (guilty) {
 		i915_request_set_error_once(rq, -EIO);
-		__i915_request_skip(rq);
+		if (!i915_request_signaled(rq))
+			__i915_request_skip(rq);
 		banned = mark_guilty(rq);
 	} else {
 		i915_request_set_error_once(rq, -EAGAIN);
diff --git a/drivers/gpu/drm/loongson/lsdc_drv.c b/drivers/gpu/drm/loongson/lsdc_drv.c
index 1ece1ea42f78..34405073c4d4 100644
--- a/drivers/gpu/drm/loongson/lsdc_drv.c
+++ b/drivers/gpu/drm/loongson/lsdc_drv.c
@@ -293,7 +293,7 @@ static int lsdc_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	vga_client_register(pdev, lsdc_vga_set_decode);
 
-	drm_kms_helper_poll_init(ddev);
+	drmm_kms_helper_poll_init(ddev);
 
 	if (loongson_vblank) {
 		ret = drm_vblank_init(ddev, descp->num_of_crtc);
diff --git a/drivers/gpu/drm/mediatek/mtk_cec.c b/drivers/gpu/drm/mediatek/mtk_cec.c
index c7be530ca041..b8ccd6e55bed 100644
--- a/drivers/gpu/drm/mediatek/mtk_cec.c
+++ b/drivers/gpu/drm/mediatek/mtk_cec.c
@@ -240,7 +240,7 @@ static const struct of_device_id mtk_cec_of_ids[] = {
 };
 MODULE_DEVICE_TABLE(of, mtk_cec_of_ids);
 
-struct platform_driver mtk_cec_driver = {
+static struct platform_driver mtk_cec_driver = {
 	.probe = mtk_cec_probe,
 	.remove = mtk_cec_remove,
 	.driver = {
diff --git a/drivers/gpu/drm/mediatek/mtk_hdmi_ddc.c b/drivers/gpu/drm/mediatek/mtk_hdmi_ddc.c
index 6358e1af69b4..2acbdb025d89 100644
--- a/drivers/gpu/drm/mediatek/mtk_hdmi_ddc.c
+++ b/drivers/gpu/drm/mediatek/mtk_hdmi_ddc.c
@@ -328,7 +328,7 @@ static const struct of_device_id mtk_hdmi_ddc_match[] = {
 };
 MODULE_DEVICE_TABLE(of, mtk_hdmi_ddc_match);
 
-struct platform_driver mtk_hdmi_ddc_driver = {
+static struct platform_driver mtk_hdmi_ddc_driver = {
 	.probe = mtk_hdmi_ddc_probe,
 	.remove = mtk_hdmi_ddc_remove,
 	.driver = {
diff --git a/drivers/gpu/drm/mediatek/mtk_hdmi_ddc_v2.c b/drivers/gpu/drm/mediatek/mtk_hdmi_ddc_v2.c
index d937219fdb7e..31e81a6de6d8 100644
--- a/drivers/gpu/drm/mediatek/mtk_hdmi_ddc_v2.c
+++ b/drivers/gpu/drm/mediatek/mtk_hdmi_ddc_v2.c
@@ -389,7 +389,7 @@ static const struct of_device_id mtk_hdmi_ddc_v2_match[] = {
 };
 MODULE_DEVICE_TABLE(of, mtk_hdmi_ddc_v2_match);
 
-struct platform_driver mtk_hdmi_ddc_v2_driver = {
+static struct platform_driver mtk_hdmi_ddc_v2_driver = {
 	.probe = mtk_hdmi_ddc_v2_probe,
 	.driver = {
 		.name = "mediatek-hdmi-ddc-v2",
diff --git a/drivers/gpu/drm/mediatek/mtk_hdmi_v2.c b/drivers/gpu/drm/mediatek/mtk_hdmi_v2.c
index 81787cc95d2a..7bbf463056c9 100644
--- a/drivers/gpu/drm/mediatek/mtk_hdmi_v2.c
+++ b/drivers/gpu/drm/mediatek/mtk_hdmi_v2.c
@@ -50,7 +50,7 @@ enum mtk_hdmi_v2_clk_id {
 	MTK_HDMI_V2_CLK_COUNT,
 };
 
-const char *const mtk_hdmi_v2_clk_names[MTK_HDMI_V2_CLK_COUNT] = {
+static const char *const mtk_hdmi_v2_clk_names[MTK_HDMI_V2_CLK_COUNT] = {
 	[MTK_HDMI_V2_CLK_HDMI_APB_SEL] = "bus",
 	[MTK_HDMI_V2_CLK_HDCP_SEL] = "hdcp",
 	[MTK_HDMI_V2_CLK_HDCP_24M_SEL] = "hdcp24m",
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
index d5aba072f44c..7a3e3c2f5cf3 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
@@ -2621,7 +2621,6 @@ static struct msm_gpu *a6xx_gpu_init(struct drm_device *dev)
 	struct platform_device *pdev = priv->gpu_pdev;
 	struct adreno_platform_config *config = pdev->dev.platform_data;
 	const struct adreno_info *info = config->info;
-	struct device_node *node;
 	struct a6xx_gpu *a6xx_gpu;
 	struct adreno_gpu *adreno_gpu;
 	struct msm_gpu *gpu;
@@ -2643,7 +2642,8 @@ static struct msm_gpu *a6xx_gpu_init(struct drm_device *dev)
 	adreno_gpu->registers = NULL;
 
 	/* Check if there is a GMU phandle and set it up */
-	node = of_parse_phandle(pdev->dev.of_node, "qcom,gmu", 0);
+	struct device_node *node __free(device_node) =
+		of_parse_phandle(pdev->dev.of_node, "qcom,gmu", 0);
 	/* FIXME: How do we gracefully handle this? */
 	BUG_ON(!node);
 
@@ -2690,7 +2690,6 @@ static struct msm_gpu *a6xx_gpu_init(struct drm_device *dev)
 		ret = a6xx_gmu_wrapper_init(a6xx_gpu, node);
 	else
 		ret = a6xx_gmu_init(a6xx_gpu, node);
-	of_node_put(node);
 	if (ret) {
 		a6xx_destroy(&(a6xx_gpu->base.base));
 		return ERR_PTR(ret);
@@ -2740,6 +2739,7 @@ const struct adreno_gpu_funcs a6xx_gpu_funcs = {
 		.create_private_vm = a6xx_create_private_vm,
 		.get_rptr = a6xx_get_rptr,
 		.progress = a6xx_progress,
+		.sysprof_setup = a6xx_gmu_sysprof_setup,
 	},
 	.init = a6xx_gpu_init,
 	.get_timestamp = a6xx_gmu_get_timestamp,
@@ -2808,6 +2808,7 @@ const struct adreno_gpu_funcs a7xx_gpu_funcs = {
 		.create_private_vm = a6xx_create_private_vm,
 		.get_rptr = a6xx_get_rptr,
 		.progress = a6xx_progress,
+		.sysprof_setup = a6xx_gmu_sysprof_setup,
 	},
 	.init = a6xx_gpu_init,
 	.get_timestamp = a6xx_gmu_get_timestamp,
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_hfi.c b/drivers/gpu/drm/msm/adreno/a6xx_hfi.c
index 487c2736f2b3..186a73c0b99c 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_hfi.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_hfi.c
@@ -289,6 +289,8 @@ static int a8xx_hfi_send_perf_table(struct a6xx_gmu *gmu)
 		(gmu->nr_gpu_freqs * num_gx_votes * sizeof(gmu->gx_arc_votes[0])) +
 		(gmu->nr_gmu_freqs * num_cx_votes * sizeof(gmu->cx_arc_votes[0]));
 	tbl = kzalloc(size, GFP_KERNEL);
+	if (!tbl)
+		return -ENOMEM;
 	tbl->type = HFI_TABLE_GPU_PERF;
 
 	/* First fill GX votes */
diff --git a/drivers/gpu/drm/msm/adreno/adreno_device.c b/drivers/gpu/drm/msm/adreno/adreno_device.c
index 4edfe80c5be7..fc38331ce640 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_device.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_device.c
@@ -17,7 +17,7 @@ MODULE_PARM_DESC(snapshot_debugbus, "Include debugbus sections in GPU devcoredum
 module_param_named(snapshot_debugbus, snapshot_debugbus, bool, 0600);
 
 int enable_preemption = -1;
-MODULE_PARM_DESC(enable_preemption, "Enable preemption (A7xx only) (1=on , 0=disable, -1=auto (default))");
+MODULE_PARM_DESC(enable_preemption, "Enable preemption (A7xx+ only) (1=on , 0=disable, -1=auto (default))");
 module_param(enable_preemption, int, 0600);
 
 bool disable_acd;
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
index 66f80f2d12f9..03f96a1154e1 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
@@ -376,7 +376,7 @@ int adreno_get_param(struct msm_gpu *gpu, struct msm_context *ctx,
 		*value = adreno_gpu->info->gmem;
 		return 0;
 	case MSM_PARAM_GMEM_BASE:
-		if (adreno_gpu->info->family >= ADRENO_6XX_GEN4)
+		if (adreno_gpu->info->family >= ADRENO_6XX_GEN3)
 			*value = 0;
 		else
 			*value = 0x100000;
@@ -424,15 +424,21 @@ int adreno_get_param(struct msm_gpu *gpu, struct msm_context *ctx,
 		*value = vm->mm_range;
 		return 0;
 	case MSM_PARAM_HIGHEST_BANK_BIT:
+		if (!adreno_gpu->ubwc_config)
+			return UERR(ENOENT, drm, "no UBWC on this platform");
 		*value = adreno_gpu->ubwc_config->highest_bank_bit;
 		return 0;
 	case MSM_PARAM_RAYTRACING:
 		*value = adreno_gpu->has_ray_tracing;
 		return 0;
 	case MSM_PARAM_UBWC_SWIZZLE:
+		if (!adreno_gpu->ubwc_config)
+			return UERR(ENOENT, drm, "no UBWC on this platform");
 		*value = adreno_gpu->ubwc_config->ubwc_swizzle;
 		return 0;
 	case MSM_PARAM_MACROTILE_MODE:
+		if (!adreno_gpu->ubwc_config)
+			return UERR(ENOENT, drm, "no UBWC on this platform");
 		*value = adreno_gpu->ubwc_config->macrotile_mode;
 		return 0;
 	case MSM_PARAM_UCHE_TRAP_BASE:
diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_13_0_kaanapali.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_13_0_kaanapali.h
index b7b06e45b529..06da1583fb1e 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_13_0_kaanapali.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_13_0_kaanapali.h
@@ -480,7 +480,7 @@ const struct dpu_mdss_cfg dpu_kaanapali_cfg = {
 	.wb_count = ARRAY_SIZE(kaanapali_wb),
 	.wb = kaanapali_wb,
 	.cwb_count = ARRAY_SIZE(kaanapali_cwb),
-	.cwb = sm8650_cwb,
+	.cwb = kaanapali_cwb,
 	.intf_count = ARRAY_SIZE(kaanapali_intf),
 	.intf = kaanapali_intf,
 	.vbif = &sm8650_vbif,
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_formats.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_formats.c
index 6e8883dbfad4..590922c4f69b 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_formats.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_formats.c
@@ -61,7 +61,7 @@ static int _dpu_format_populate_plane_sizes_ubwc(
 	bool meta = MSM_FORMAT_IS_UBWC(fmt);
 
 	if (MSM_FORMAT_IS_YUV(fmt)) {
-		unsigned int stride, sclines;
+		unsigned int stride, y_sclines, uv_sclines;
 		unsigned int y_tile_width, y_tile_height;
 		unsigned int y_meta_stride, y_meta_scanlines;
 		unsigned int uv_meta_stride, uv_meta_scanlines;
@@ -77,23 +77,25 @@ static int _dpu_format_populate_plane_sizes_ubwc(
 				y_tile_width = 32;
 			}
 
-			sclines = round_up(fb->height, 16);
+			y_sclines = round_up(fb->height, 16);
+			uv_sclines = round_up((fb->height+1)>>1, 16);
 			y_tile_height = 4;
 		} else {
 			stride = round_up(fb->width, 128);
 			y_tile_width = 32;
 
-			sclines = round_up(fb->height, 32);
+			y_sclines = round_up(fb->height, 32);
+			uv_sclines = round_up((fb->height+1)>>1, 32);
 			y_tile_height = 8;
 		}
 
 		layout->plane_pitch[0] = stride;
 		layout->plane_size[0] = round_up(layout->plane_pitch[0] *
-			sclines, DPU_UBWC_PLANE_SIZE_ALIGNMENT);
+			y_sclines, DPU_UBWC_PLANE_SIZE_ALIGNMENT);
 
 		layout->plane_pitch[1] = stride;
 		layout->plane_size[1] = round_up(layout->plane_pitch[1] *
-			sclines, DPU_UBWC_PLANE_SIZE_ALIGNMENT);
+			uv_sclines, DPU_UBWC_PLANE_SIZE_ALIGNMENT);
 
 		if (!meta)
 			return 0;
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_writeback.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_writeback.c
index 54bd7c354b63..e7b09013ae4c 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_writeback.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_writeback.c
@@ -5,6 +5,7 @@
 
 #include <drm/drm_edid.h>
 #include <drm/drm_framebuffer.h>
+#include <drm/drm_managed.h>
 
 #include "dpu_writeback.h"
 
@@ -125,7 +126,7 @@ int dpu_writeback_init(struct drm_device *dev, struct drm_encoder *enc,
 	struct dpu_wb_connector *dpu_wb_conn;
 	int rc = 0;
 
-	dpu_wb_conn = devm_kzalloc(dev->dev, sizeof(*dpu_wb_conn), GFP_KERNEL);
+	dpu_wb_conn = drmm_kzalloc(dev, sizeof(*dpu_wb_conn), GFP_KERNEL);
 	if (!dpu_wb_conn)
 		return -ENOMEM;
 
diff --git a/drivers/gpu/drm/msm/disp/msm_disp_snapshot_util.c b/drivers/gpu/drm/msm/disp/msm_disp_snapshot_util.c
index 5e151952dea8..850246fc89e1 100644
--- a/drivers/gpu/drm/msm/disp/msm_disp_snapshot_util.c
+++ b/drivers/gpu/drm/msm/disp/msm_disp_snapshot_util.c
@@ -5,11 +5,11 @@
 
 #define pr_fmt(fmt)	"[drm:%s:%d] " fmt, __func__, __LINE__
 
-#include <generated/utsrelease.h>
+#include <linux/utsname.h>
 
 #include "msm_disp_snapshot.h"
 
-static void msm_disp_state_dump_regs(u32 **reg, u32 aligned_len, void __iomem *base_addr)
+static void msm_disp_state_dump_regs(u32 **reg, u32 len, void __iomem *base_addr)
 {
 	u32 len_padded;
 	u32 num_rows;
@@ -19,11 +19,11 @@ static void msm_disp_state_dump_regs(u32 **reg, u32 aligned_len, void __iomem *b
 	void __iomem *end_addr;
 	int i;
 
-	len_padded = aligned_len * REG_DUMP_ALIGN;
-	num_rows = aligned_len / REG_DUMP_ALIGN;
+	len_padded = round_up(len, REG_DUMP_ALIGN);
+	num_rows = DIV_ROUND_UP(len, REG_DUMP_ALIGN);
 
 	addr = base_addr;
-	end_addr = base_addr + aligned_len;
+	end_addr = base_addr + len;
 
 	*reg = kvzalloc(len_padded, GFP_KERNEL);
 	if (!*reg)
@@ -48,8 +48,8 @@ static void msm_disp_state_dump_regs(u32 **reg, u32 aligned_len, void __iomem *b
 static void msm_disp_state_print_regs(const u32 *dump_addr, u32 len,
 		void __iomem *base_addr, struct drm_printer *p)
 {
+	void __iomem *addr, *end_addr;
 	int i;
-	void __iomem *addr;
 	u32 num_rows;
 
 	if (!dump_addr) {
@@ -58,6 +58,7 @@ static void msm_disp_state_print_regs(const u32 *dump_addr, u32 len,
 	}
 
 	addr = base_addr;
+	end_addr = base_addr + len;
 	num_rows = len / REG_DUMP_ALIGN;
 
 	for (i = 0; i < num_rows; i++) {
@@ -67,6 +68,17 @@ static void msm_disp_state_print_regs(const u32 *dump_addr, u32 len,
 				dump_addr[i * 4 + 2], dump_addr[i * 4 + 3]);
 		addr += REG_DUMP_ALIGN;
 	}
+
+	if (addr != end_addr) {
+		drm_printf(p, "0x%lx : %08x",
+			   (unsigned long)(addr - base_addr),
+			   dump_addr[i * 4]);
+		if (addr + 0x4 < end_addr)
+			drm_printf(p, " %08x", dump_addr[i * 4 + 1]);
+		if (addr + 0x8 < end_addr)
+			drm_printf(p, " %08x", dump_addr[i * 4 + 2]);
+		drm_printf(p, "\n");
+	}
 }
 
 void msm_disp_state_print(struct msm_disp_state *state, struct drm_printer *p)
@@ -79,7 +91,7 @@ void msm_disp_state_print(struct msm_disp_state *state, struct drm_printer *p)
 	}
 
 	drm_printf(p, "---\n");
-	drm_printf(p, "kernel: " UTS_RELEASE "\n");
+	drm_printf(p, "kernel: %s\n", init_utsname()->release);
 	drm_printf(p, "module: " KBUILD_MODNAME "\n");
 	drm_printf(p, "dpu devcoredump\n");
 	drm_printf(p, "time: %ptSp\n", &state->time);
@@ -185,7 +197,7 @@ void msm_disp_snapshot_add_block(struct msm_disp_state *disp_state, u32 len,
 	va_end(va);
 
 	INIT_LIST_HEAD(&new_blk->node);
-	new_blk->size = ALIGN(len, REG_DUMP_ALIGN);
+	new_blk->size = len;
 	new_blk->base_addr = base_addr;
 
 	msm_disp_state_dump_regs(&new_blk->state, new_blk->size, base_addr);
diff --git a/drivers/gpu/drm/msm/dsi/dsi_host.c b/drivers/gpu/drm/msm/dsi/dsi_host.c
index 565d425f88b8..982abaaac00d 100644
--- a/drivers/gpu/drm/msm/dsi/dsi_host.c
+++ b/drivers/gpu/drm/msm/dsi/dsi_host.c
@@ -2033,6 +2033,7 @@ int msm_dsi_host_init(struct msm_dsi *msm_dsi)
 
 	/* fixup base address by io offset */
 	msm_host->ctrl_base += cfg->io_offset;
+	msm_host->ctrl_size -= cfg->io_offset;
 
 	ret = devm_regulator_bulk_get_const(&pdev->dev, cfg->num_regulators,
 					    cfg->regulator_data,
diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c
index 195f40e331e5..cc2bcd14b1c2 100644
--- a/drivers/gpu/drm/msm/msm_drv.c
+++ b/drivers/gpu/drm/msm/msm_drv.c
@@ -128,11 +128,10 @@ static int msm_drm_init(struct device *dev, const struct drm_driver *drv,
 	/*
 	 * Initialize the LRUs:
 	 */
-	mutex_init(&priv->lru.lock);
-	drm_gem_lru_init(&priv->lru.unbacked, &priv->lru.lock);
-	drm_gem_lru_init(&priv->lru.pinned,   &priv->lru.lock);
-	drm_gem_lru_init(&priv->lru.willneed, &priv->lru.lock);
-	drm_gem_lru_init(&priv->lru.dontneed, &priv->lru.lock);
+	drm_gem_lru_init(&priv->lru.unbacked);
+	drm_gem_lru_init(&priv->lru.pinned);
+	drm_gem_lru_init(&priv->lru.willneed);
+	drm_gem_lru_init(&priv->lru.dontneed);
 
 	/* Initialize stall-on-fault */
 	spin_lock_init(&priv->fault_stall_lock);
@@ -140,7 +139,7 @@ static int msm_drm_init(struct device *dev, const struct drm_driver *drv,
 
 	/* Teach lockdep about lock ordering wrt. shrinker: */
 	fs_reclaim_acquire(GFP_KERNEL);
-	might_lock(&priv->lru.lock);
+	might_lock(&ddev->gem_lru_mutex);
 	fs_reclaim_release(GFP_KERNEL);
 
 	if (priv->kms_init) {
diff --git a/drivers/gpu/drm/msm/msm_drv.h b/drivers/gpu/drm/msm/msm_drv.h
index 76ac61df0b35..c3fb3205f683 100644
--- a/drivers/gpu/drm/msm/msm_drv.h
+++ b/drivers/gpu/drm/msm/msm_drv.h
@@ -150,13 +150,6 @@ struct msm_drm_private {
 		 * DONTNEED state (ie. can be purged)
 		 */
 		struct drm_gem_lru dontneed;
-
-		/**
-		 * lock:
-		 *
-		 * Protects manipulation of all of the LRUs.
-		 */
-		struct mutex lock;
 	} lru;
 
 	struct notifier_block vmap_notifier;
diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c
index 2cb3ab04f125..efd3d3c9a449 100644
--- a/drivers/gpu/drm/msm/msm_gem.c
+++ b/drivers/gpu/drm/msm/msm_gem.c
@@ -177,11 +177,11 @@ static void update_lru_locked(struct drm_gem_object *obj)
 
 static void update_lru(struct drm_gem_object *obj)
 {
-	struct msm_drm_private *priv = obj->dev->dev_private;
+	struct drm_device *dev = obj->dev;
 
-	mutex_lock(&priv->lru.lock);
+	mutex_lock(&dev->gem_lru_mutex);
 	update_lru_locked(obj);
-	mutex_unlock(&priv->lru.lock);
+	mutex_unlock(&dev->gem_lru_mutex);
 }
 
 static struct page **get_pages(struct drm_gem_object *obj)
@@ -292,11 +292,11 @@ void msm_gem_pin_obj_locked(struct drm_gem_object *obj)
 
 static void pin_obj_locked(struct drm_gem_object *obj)
 {
-	struct msm_drm_private *priv = obj->dev->dev_private;
+	struct drm_device *dev = obj->dev;
 
-	mutex_lock(&priv->lru.lock);
+	mutex_lock(&dev->gem_lru_mutex);
 	msm_gem_pin_obj_locked(obj);
-	mutex_unlock(&priv->lru.lock);
+	mutex_unlock(&dev->gem_lru_mutex);
 }
 
 struct page **msm_gem_pin_pages_locked(struct drm_gem_object *obj)
@@ -487,16 +487,16 @@ int msm_gem_pin_vma_locked(struct drm_gem_object *obj, struct drm_gpuva *vma)
 
 void msm_gem_unpin_locked(struct drm_gem_object *obj)
 {
-	struct msm_drm_private *priv = obj->dev->dev_private;
+	struct drm_device *dev = obj->dev;
 	struct msm_gem_object *msm_obj = to_msm_bo(obj);
 
 	msm_gem_assert_locked(obj);
 
-	mutex_lock(&priv->lru.lock);
+	mutex_lock(&dev->gem_lru_mutex);
 	msm_obj->pin_count--;
 	GEM_WARN_ON(msm_obj->pin_count < 0);
 	update_lru_locked(obj);
-	mutex_unlock(&priv->lru.lock);
+	mutex_unlock(&dev->gem_lru_mutex);
 }
 
 /* Special unpin path for use in fence-signaling path, avoiding the need
@@ -507,10 +507,10 @@ void msm_gem_unpin_locked(struct drm_gem_object *obj)
  */
 void msm_gem_unpin_active(struct drm_gem_object *obj)
 {
-	struct msm_drm_private *priv = obj->dev->dev_private;
+	struct drm_device *dev = obj->dev;
 	struct msm_gem_object *msm_obj = to_msm_bo(obj);
 
-	GEM_WARN_ON(!mutex_is_locked(&priv->lru.lock));
+	GEM_WARN_ON(!mutex_is_locked(&dev->gem_lru_mutex));
 
 	msm_obj->pin_count--;
 	GEM_WARN_ON(msm_obj->pin_count < 0);
@@ -797,12 +797,12 @@ void msm_gem_put_vaddr(struct drm_gem_object *obj)
  */
 int msm_gem_madvise(struct drm_gem_object *obj, unsigned madv)
 {
-	struct msm_drm_private *priv = obj->dev->dev_private;
+	struct drm_device *dev = obj->dev;
 	struct msm_gem_object *msm_obj = to_msm_bo(obj);
 
 	msm_gem_lock(obj);
 
-	mutex_lock(&priv->lru.lock);
+	mutex_lock(&dev->gem_lru_mutex);
 
 	if (msm_obj->madv != __MSM_MADV_PURGED)
 		msm_obj->madv = madv;
@@ -814,7 +814,7 @@ int msm_gem_madvise(struct drm_gem_object *obj, unsigned madv)
 	 */
 	update_lru_locked(obj);
 
-	mutex_unlock(&priv->lru.lock);
+	mutex_unlock(&dev->gem_lru_mutex);
 
 	msm_gem_unlock(obj);
 
@@ -824,7 +824,6 @@ int msm_gem_madvise(struct drm_gem_object *obj, unsigned madv)
 void msm_gem_purge(struct drm_gem_object *obj)
 {
 	struct drm_device *dev = obj->dev;
-	struct msm_drm_private *priv = obj->dev->dev_private;
 	struct msm_gem_object *msm_obj = to_msm_bo(obj);
 
 	msm_gem_assert_locked(obj);
@@ -839,10 +838,10 @@ void msm_gem_purge(struct drm_gem_object *obj)
 
 	put_pages(obj);
 
-	mutex_lock(&priv->lru.lock);
+	mutex_lock(&dev->gem_lru_mutex);
 	/* A one-way transition: */
 	msm_obj->madv = __MSM_MADV_PURGED;
-	mutex_unlock(&priv->lru.lock);
+	mutex_unlock(&dev->gem_lru_mutex);
 
 	drm_gem_free_mmap_offset(obj);
 
diff --git a/drivers/gpu/drm/msm/msm_gem_shrinker.c b/drivers/gpu/drm/msm/msm_gem_shrinker.c
index 31fa51a44f86..9d2788f79ace 100644
--- a/drivers/gpu/drm/msm/msm_gem_shrinker.c
+++ b/drivers/gpu/drm/msm/msm_gem_shrinker.c
@@ -43,8 +43,7 @@ msm_gem_shrinker_count(struct shrinker *shrinker, struct shrink_control *sc)
 }
 
 static bool
-with_vm_locks(struct ww_acquire_ctx *ticket,
-	      void (*fn)(struct drm_gem_object *obj),
+with_vm_locks(void (*fn)(struct drm_gem_object *obj),
 	      struct drm_gem_object *obj)
 {
 	/*
@@ -52,7 +51,7 @@ with_vm_locks(struct ww_acquire_ctx *ticket,
 	 * success paths
 	 */
 	struct drm_gpuvm_bo *vm_bo, *last_locked = NULL;
-	int ret = 0;
+	bool locked = true;
 
 	drm_gem_for_each_gpuvm_bo (vm_bo, obj) {
 		struct dma_resv *resv = drm_gpuvm_resv(vm_bo->vm);
@@ -60,23 +59,14 @@ with_vm_locks(struct ww_acquire_ctx *ticket,
 		if (resv == obj->resv)
 			continue;
 
-		ret = dma_resv_lock(resv, ticket);
-
-		/*
-		 * Since we already skip the case when the VM and obj
-		 * share a resv (ie. _NO_SHARE objs), we don't expect
-		 * to hit a double-locking scenario... which the lock
-		 * unwinding cannot really cope with.
-		 */
-		WARN_ON(ret == -EALREADY);
-
 		/*
-		 * Don't bother with slow-lock / backoff / retry sequence,
-		 * if we can't get the lock just give up and move on to
-		 * the next object.
+		 * dma_resv_lock can't be used due to acquiring 'ticket' before the
+		 * fs_reclaim lock, which is held in shrinker context
 		 */
-		if (ret)
+		if (!dma_resv_trylock(resv)) {
+			locked = false;
 			goto out_unlock;
+		}
 
 		/*
 		 * Hold a ref to prevent the vm_bo from being freed
@@ -108,11 +98,11 @@ out_unlock:
 		}
 	}
 
-	return ret == 0;
+	return locked;
 }
 
 static bool
-purge(struct drm_gem_object *obj, struct ww_acquire_ctx *ticket)
+purge(struct drm_gem_object *obj, struct ww_acquire_ctx *unused)
 {
 	if (!is_purgeable(to_msm_bo(obj)))
 		return false;
@@ -120,11 +110,11 @@ purge(struct drm_gem_object *obj, struct ww_acquire_ctx *ticket)
 	if (msm_gem_active(obj))
 		return false;
 
-	return with_vm_locks(ticket, msm_gem_purge, obj);
+	return with_vm_locks(msm_gem_purge, obj);
 }
 
 static bool
-evict(struct drm_gem_object *obj, struct ww_acquire_ctx *ticket)
+evict(struct drm_gem_object *obj, struct ww_acquire_ctx *unused)
 {
 	if (is_unevictable(to_msm_bo(obj)))
 		return false;
@@ -132,7 +122,7 @@ evict(struct drm_gem_object *obj, struct ww_acquire_ctx *ticket)
 	if (msm_gem_active(obj))
 		return false;
 
-	return with_vm_locks(ticket, msm_gem_evict, obj);
+	return with_vm_locks(msm_gem_evict, obj);
 }
 
 static bool
@@ -164,7 +154,6 @@ static unsigned long
 msm_gem_shrinker_scan(struct shrinker *shrinker, struct shrink_control *sc)
 {
 	struct msm_drm_private *priv = shrinker->private_data;
-	struct ww_acquire_ctx ticket;
 	struct {
 		struct drm_gem_lru *lru;
 		bool (*shrink)(struct drm_gem_object *obj, struct ww_acquire_ctx *ticket);
@@ -185,11 +174,14 @@ msm_gem_shrinker_scan(struct shrinker *shrinker, struct shrink_control *sc)
 	for (unsigned i = 0; (nr > 0) && (i < ARRAY_SIZE(stages)); i++) {
 		if (!stages[i].cond)
 			continue;
+		/*
+		 * 'ticket' not needed on trylock paths
+		 */
 		stages[i].freed =
-			drm_gem_lru_scan(stages[i].lru, nr,
+			drm_gem_lru_scan(priv->dev, stages[i].lru, nr,
 					 &stages[i].remaining,
 					 stages[i].shrink,
-					 &ticket);
+					 NULL);
 		nr -= stages[i].freed;
 		freed += stages[i].freed;
 		remaining += stages[i].remaining;
@@ -255,7 +247,7 @@ msm_gem_shrinker_vmap(struct notifier_block *nb, unsigned long event, void *ptr)
 	unsigned long remaining = 0;
 
 	for (idx = 0; lrus[idx] && unmapped < vmap_shrink_limit; idx++) {
-		unmapped += drm_gem_lru_scan(lrus[idx],
+		unmapped += drm_gem_lru_scan(priv->dev, lrus[idx],
 					     vmap_shrink_limit - unmapped,
 					     &remaining,
 					     vmap_shrink,
diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c
index 26ea8a28be47..3c6bc90c3d48 100644
--- a/drivers/gpu/drm/msm/msm_gem_submit.c
+++ b/drivers/gpu/drm/msm/msm_gem_submit.c
@@ -352,7 +352,7 @@ static int submit_fence_sync(struct msm_gem_submit *submit)
 
 static int submit_pin_objects(struct msm_gem_submit *submit)
 {
-	struct msm_drm_private *priv = submit->dev->dev_private;
+	struct drm_device *dev = submit->dev;
 	int i, ret = 0;
 
 	for (i = 0; i < submit->nr_bos; i++) {
@@ -381,11 +381,11 @@ static int submit_pin_objects(struct msm_gem_submit *submit)
 	 * get_pages() which could trigger reclaim.. and if we held the LRU lock
 	 * could trigger deadlock with the shrinker).
 	 */
-	mutex_lock(&priv->lru.lock);
+	mutex_lock(&dev->gem_lru_mutex);
 	for (i = 0; i < submit->nr_bos; i++) {
 		msm_gem_pin_obj_locked(submit->bos[i].obj);
 	}
-	mutex_unlock(&priv->lru.lock);
+	mutex_unlock(&dev->gem_lru_mutex);
 
 	submit->bos_pinned = true;
 
diff --git a/drivers/gpu/drm/msm/msm_gem_vma.c b/drivers/gpu/drm/msm/msm_gem_vma.c
index 271691ae32c3..3ed05ab0eeef 100644
--- a/drivers/gpu/drm/msm/msm_gem_vma.c
+++ b/drivers/gpu/drm/msm/msm_gem_vma.c
@@ -702,7 +702,7 @@ static struct dma_fence *
 msm_vma_job_run(struct drm_sched_job *_job)
 {
 	struct msm_vm_bind_job *job = to_msm_vm_bind_job(_job);
-	struct msm_drm_private *priv = job->vm->drm->dev_private;
+	struct drm_device *dev = job->vm->drm;
 	struct msm_gem_vm *vm = to_msm_vm(job->vm);
 	struct drm_gem_object *obj;
 	int ret = vm->unusable ? -EINVAL : 0;
@@ -745,13 +745,13 @@ msm_vma_job_run(struct drm_sched_job *_job)
 	if (ret)
 		msm_gem_vm_unusable(job->vm);
 
-	mutex_lock(&priv->lru.lock);
+	mutex_lock(&dev->gem_lru_mutex);
 
 	job_foreach_bo (obj, job) {
 		msm_gem_unpin_active(obj);
 	}
 
-	mutex_unlock(&priv->lru.lock);
+	mutex_unlock(&dev->gem_lru_mutex);
 
 	/* VM_BIND ops are synchronous, so no fence to wait on: */
 	return NULL;
@@ -1304,7 +1304,7 @@ vm_bind_job_pin_objects(struct msm_vm_bind_job *job)
 			return PTR_ERR(pages);
 	}
 
-	struct msm_drm_private *priv = job->vm->drm->dev_private;
+	struct drm_device *dev = job->vm->drm;
 
 	/*
 	 * A second loop while holding the LRU lock (a) avoids acquiring/dropping
@@ -1313,10 +1313,10 @@ vm_bind_job_pin_objects(struct msm_vm_bind_job *job)
 	 * get_pages() which could trigger reclaim.. and if we held the LRU lock
 	 * could trigger deadlock with the shrinker).
 	 */
-	mutex_lock(&priv->lru.lock);
+	mutex_lock(&dev->gem_lru_mutex);
 	job_foreach_bo (obj, job)
 		msm_gem_pin_obj_locked(obj);
-	mutex_unlock(&priv->lru.lock);
+	mutex_unlock(&dev->gem_lru_mutex);
 
 	job->bos_pinned = true;
 
diff --git a/drivers/gpu/drm/msm/msm_gpu.c b/drivers/gpu/drm/msm/msm_gpu.c
index 930e54d1b0a7..3f3925b11eea 100644
--- a/drivers/gpu/drm/msm/msm_gpu.c
+++ b/drivers/gpu/drm/msm/msm_gpu.c
@@ -13,11 +13,11 @@
 #include "msm_gpu_trace.h"
 //#include "adreno/adreno_gpu.h"
 
-#include <generated/utsrelease.h>
 #include <linux/string_helpers.h>
 #include <linux/devcoredump.h>
 #include <linux/sched/task.h>
 #include <linux/sched/mm.h>
+#include <linux/utsname.h>
 
 /*
  * Power Management:
@@ -196,7 +196,7 @@ static ssize_t msm_gpu_devcoredump_read(char *buffer, loff_t offset,
 	p = drm_coredump_printer(&iter);
 
 	drm_printf(&p, "---\n");
-	drm_printf(&p, "kernel: " UTS_RELEASE "\n");
+	drm_printf(&p, "kernel: %s\n", init_utsname()->release);
 	drm_printf(&p, "module: " KBUILD_MODNAME "\n");
 	drm_printf(&p, "time: %ptSp\n", &state->time);
 	if (state->comm)
diff --git a/drivers/gpu/drm/msm/msm_iommu.c b/drivers/gpu/drm/msm/msm_iommu.c
index 7d449e5202c5..058c71c82cf5 100644
--- a/drivers/gpu/drm/msm/msm_iommu.c
+++ b/drivers/gpu/drm/msm/msm_iommu.c
@@ -677,7 +677,7 @@ static int msm_iommu_map(struct msm_mmu *mmu, uint64_t iova,
 			 int prot)
 {
 	struct msm_iommu *iommu = to_msm_iommu(mmu);
-	size_t ret;
+	ssize_t ret;
 
 	WARN_ON(off != 0);
 
@@ -686,7 +686,8 @@ static int msm_iommu_map(struct msm_mmu *mmu, uint64_t iova,
 		iova |= GENMASK_ULL(63, 49);
 
 	ret = iommu_map_sgtable(iommu->domain, iova, sgt, prot);
-	WARN_ON(!ret);
+	if (ret < 0)
+		return ret;
 
 	return (ret == len) ? 0 : -EINVAL;
 }
diff --git a/drivers/gpu/drm/msm/msm_ringbuffer.c b/drivers/gpu/drm/msm/msm_ringbuffer.c
index a7dafa7ab4b1..0d14c31bd4e4 100644
--- a/drivers/gpu/drm/msm/msm_ringbuffer.c
+++ b/drivers/gpu/drm/msm/msm_ringbuffer.c
@@ -16,13 +16,13 @@ static struct dma_fence *msm_job_run(struct drm_sched_job *job)
 	struct msm_gem_submit *submit = to_msm_submit(job);
 	struct msm_fence_context *fctx = submit->ring->fctx;
 	struct msm_gpu *gpu = submit->gpu;
-	struct msm_drm_private *priv = gpu->dev->dev_private;
+	struct drm_device *dev = gpu->dev;
 	unsigned nr_cmds = submit->nr_cmds;
 	int i;
 
 	msm_fence_init(submit->hw_fence, fctx);
 
-	mutex_lock(&priv->lru.lock);
+	mutex_lock(&dev->gem_lru_mutex);
 
 	for (i = 0; i < submit->nr_bos; i++) {
 		struct drm_gem_object *obj = submit->bos[i].obj;
@@ -32,7 +32,7 @@ static struct dma_fence *msm_job_run(struct drm_sched_job *job)
 
 	submit->bos_pinned = false;
 
-	mutex_unlock(&priv->lru.lock);
+	mutex_unlock(&dev->gem_lru_mutex);
 
 	/* TODO move submit path over to using a per-ring lock.. */
 	mutex_lock(&gpu->lock);
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c b/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c
index 72848ed80df7..b101e14f841e 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c
@@ -2513,6 +2513,7 @@ static const struct nvkm_device_chip
 nv170_chipset = {
 	.name = "GA100",
 	.bar      = { 0x00000001, tu102_bar_new },
+	.bios     = { 0x00000001, nvkm_bios_new },
 	.devinit  = { 0x00000001, ga100_devinit_new },
 	.fault    = { 0x00000001, tu102_fault_new },
 	.fb       = { 0x00000001, ga100_fb_new },
@@ -2529,7 +2530,6 @@ nv170_chipset = {
 	.vfn      = { 0x00000001, ga100_vfn_new },
 	.ce       = { 0x000003ff, ga100_ce_new },
 	.fifo     = { 0x00000001, ga100_fifo_new },
-	.sec2     = { 0x00000001, tu102_sec2_new },
 };
 
 static const struct nvkm_device_chip
@@ -3341,7 +3341,6 @@ nvkm_device_ctor(const struct nvkm_device_func *func,
 	case 0x166: device->chip = &nv166_chipset; break;
 	case 0x167: device->chip = &nv167_chipset; break;
 	case 0x168: device->chip = &nv168_chipset; break;
-	case 0x170: device->chip = &nv170_chipset; break;
 	case 0x172: device->chip = &nv172_chipset; break;
 	case 0x173: device->chip = &nv173_chipset; break;
 	case 0x174: device->chip = &nv174_chipset; break;
@@ -3361,6 +3360,14 @@ nvkm_device_ctor(const struct nvkm_device_func *func,
 	case 0x1b6: device->chip = &nv1b6_chipset; break;
 	case 0x1b7: device->chip = &nv1b7_chipset; break;
 	default:
+		if (nvkm_boolopt(device->cfgopt, "NvEnableUnsupportedChipsets", false)) {
+			switch (device->chipset) {
+			case 0x170: device->chip = &nv170_chipset; break;
+			default:
+				break;
+			}
+		}
+
 		if (!device->chip) {
 			nvdev_error(device, "unknown chipset (%08x)\n", boot0);
 			ret = -ENODEV;
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/ga100.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/ga100.c
index fdd820eeef81..27a13aeccd3c 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/ga100.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/ga100.c
@@ -41,11 +41,15 @@ ga100_gsp_flcn = {
 static const struct nvkm_gsp_func
 ga100_gsp = {
 	.flcn = &ga100_gsp_flcn,
+	.fwsec = &tu102_gsp_fwsec,
 
 	.sig_section = ".fwsignature_ga100",
 
 	.booter.ctor = tu102_gsp_booter_ctor,
 
+	.fwsec_sb.ctor = tu102_gsp_fwsec_sb_ctor,
+	.fwsec_sb.dtor = tu102_gsp_fwsec_sb_dtor,
+
 	.dtor = r535_gsp_dtor,
 	.oneinit = tu102_gsp_oneinit,
 	.init = tu102_gsp_init,
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/tu102.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/tu102.c
index dd82c76b8b9a..19cb269e7a26 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/tu102.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/tu102.c
@@ -318,13 +318,8 @@ tu102_gsp_oneinit(struct nvkm_gsp *gsp)
 	if (ret)
 		return ret;
 
-	/*
-	 * Calculate FB layout. FRTS is a memory region created by the FWSEC-FRTS firmware.
-	 * FWSEC comes from VBIOS.  So on systems with no VBIOS (e.g. GA100), the FRTS does
-	 * not exist.  Therefore, use the existence of VBIOS to determine whether to reserve
-	 * an FRTS region.
-	 */
-	gsp->fb.wpr2.frts.size = device->bios ? 0x100000 : 0;
+	/* Calculate FB layout. */
+	gsp->fb.wpr2.frts.size = 0x100000;
 	gsp->fb.wpr2.frts.addr = ALIGN_DOWN(gsp->fb.bios.addr, 0x20000) - gsp->fb.wpr2.frts.size;
 
 	gsp->fb.wpr2.boot.size = gsp->boot.fw.size;
@@ -348,12 +343,9 @@ tu102_gsp_oneinit(struct nvkm_gsp *gsp)
 	if (ret)
 		return ret;
 
-	/* Only boot FWSEC-FRTS if it actually exists */
-	if (gsp->fb.wpr2.frts.size) {
-		ret = nvkm_gsp_fwsec_frts(gsp);
-		if (WARN_ON(ret))
-			return ret;
-	}
+	ret = nvkm_gsp_fwsec_frts(gsp);
+	if (WARN_ON(ret))
+		return ret;
 
 	/* Reset GSP into RISC-V mode. */
 	ret = gsp->func->reset(gsp);
diff --git a/drivers/gpu/drm/panel/Kconfig b/drivers/gpu/drm/panel/Kconfig
index b0e9b92e2c84..7450b27622a2 100644
--- a/drivers/gpu/drm/panel/Kconfig
+++ b/drivers/gpu/drm/panel/Kconfig
@@ -232,6 +232,7 @@ config DRM_PANEL_HIMAX_HX83121A
 	depends on OF
 	depends on DRM_MIPI_DSI
 	depends on BACKLIGHT_CLASS_DEVICE
+	select DRM_DISPLAY_DSC_HELPER
 	select DRM_KMS_HELPER
 	help
 	  Say Y here if you want to enable support for Himax HX83121A-based
diff --git a/drivers/gpu/drm/panel/panel-boe-tv101wum-nl6.c b/drivers/gpu/drm/panel/panel-boe-tv101wum-nl6.c
index d5fe105bdbdd..658ce64c71eb 100644
--- a/drivers/gpu/drm/panel/panel-boe-tv101wum-nl6.c
+++ b/drivers/gpu/drm/panel/panel-boe-tv101wum-nl6.c
@@ -1324,6 +1324,8 @@ static int boe_panel_disable(struct drm_panel *panel)
 	mipi_dsi_dcs_set_display_off_multi(&ctx);
 	mipi_dsi_dcs_enter_sleep_mode_multi(&ctx);
 
+	boe->dsi->mode_flags |= MIPI_DSI_MODE_LPM;
+
 	mipi_dsi_msleep(&ctx, 150);
 
 	return ctx.accum_err;
diff --git a/drivers/gpu/drm/panel/panel-feiyang-fy07024di26a30d.c b/drivers/gpu/drm/panel/panel-feiyang-fy07024di26a30d.c
index 4f8d6d8c07e4..dbdb7e3cb7b6 100644
--- a/drivers/gpu/drm/panel/panel-feiyang-fy07024di26a30d.c
+++ b/drivers/gpu/drm/panel/panel-feiyang-fy07024di26a30d.c
@@ -98,9 +98,7 @@ static int feiyang_enable(struct drm_panel *panel)
 	/* T12 (video & logic signal rise + backlight rise) T12 >= 200ms */
 	msleep(200);
 
-	mipi_dsi_dcs_set_display_on(ctx->dsi);
-
-	return 0;
+	return mipi_dsi_dcs_set_display_on(ctx->dsi);
 }
 
 static int feiyang_disable(struct drm_panel *panel)
diff --git a/drivers/gpu/drm/panel/panel-himax-hx83102.c b/drivers/gpu/drm/panel/panel-himax-hx83102.c
index eab67893da86..d7e5664a5838 100644
--- a/drivers/gpu/drm/panel/panel-himax-hx83102.c
+++ b/drivers/gpu/drm/panel/panel-himax-hx83102.c
@@ -1070,6 +1070,8 @@ static int hx83102_disable(struct drm_panel *panel)
 	mipi_dsi_dcs_set_display_off_multi(&dsi_ctx);
 	mipi_dsi_dcs_enter_sleep_mode_multi(&dsi_ctx);
 
+	dsi->mode_flags |= MIPI_DSI_MODE_LPM;
+
 	mipi_dsi_msleep(&dsi_ctx, 150);
 
 	return dsi_ctx.accum_err;
diff --git a/drivers/gpu/drm/panel/panel-himax-hx83121a.c b/drivers/gpu/drm/panel/panel-himax-hx83121a.c
index ebe643ba4184..bed79aa06f46 100644
--- a/drivers/gpu/drm/panel/panel-himax-hx83121a.c
+++ b/drivers/gpu/drm/panel/panel-himax-hx83121a.c
@@ -596,8 +596,8 @@ static int himax_probe(struct mipi_dsi_device *dsi)
 
 	ctx = devm_drm_panel_alloc(dev, struct himax, panel, &himax_panel_funcs,
 				   DRM_MODE_CONNECTOR_DSI);
-	if (!ctx)
-		return -ENOMEM;
+	if (IS_ERR(ctx))
+		return PTR_ERR(ctx);
 
 	ret = devm_regulator_bulk_get_const(&dsi->dev,
 					    ARRAY_SIZE(himax_supplies),
diff --git a/drivers/gpu/drm/panfrost/panfrost_drv.c b/drivers/gpu/drm/panfrost/panfrost_drv.c
index 3d0bdba2a474..784e36d72c2b 100644
--- a/drivers/gpu/drm/panfrost/panfrost_drv.c
+++ b/drivers/gpu/drm/panfrost/panfrost_drv.c
@@ -390,6 +390,8 @@ panfrost_ioctl_wait_bo(struct drm_device *dev, void *data,
 				    true, timeout);
 	if (!ret)
 		ret = timeout ? -ETIMEDOUT : -EBUSY;
+	else if (ret > 0)
+		ret = 0;
 
 	drm_gem_object_put(gem_obj);
 
diff --git a/drivers/gpu/drm/panthor/panthor_device.h b/drivers/gpu/drm/panthor/panthor_device.h
index 4e4607bca7cc..a412a50eec76 100644
--- a/drivers/gpu/drm/panthor/panthor_device.h
+++ b/drivers/gpu/drm/panthor/panthor_device.h
@@ -187,9 +187,6 @@ struct panthor_device {
 		/** @reclaim.shrinker: Shrinker instance */
 		struct shrinker *shrinker;
 
-		/** @reclaim.lock: Lock protecting all LRUs */
-		struct mutex lock;
-
 		/**
 		 * @reclaim.unused: BOs with unused pages
 		 *
diff --git a/drivers/gpu/drm/panthor/panthor_gem.c b/drivers/gpu/drm/panthor/panthor_gem.c
index 13295d7a593d..abe0c5bb1bca 100644
--- a/drivers/gpu/drm/panthor/panthor_gem.c
+++ b/drivers/gpu/drm/panthor/panthor_gem.c
@@ -1495,13 +1495,13 @@ panthor_gem_shrinker_scan(struct shrinker *shrinker, struct shrink_control *sc)
 	if (!can_swap())
 		goto out;
 
-	freed += drm_gem_lru_scan(&ptdev->reclaim.unused,
+	freed += drm_gem_lru_scan(&ptdev->base, &ptdev->reclaim.unused,
 				  sc->nr_to_scan - freed, &remaining,
 				  panthor_gem_try_evict_no_resv_wait, NULL);
 	if (freed >= sc->nr_to_scan)
 		goto out;
 
-	freed += drm_gem_lru_scan(&ptdev->reclaim.mmapped,
+	freed += drm_gem_lru_scan(&ptdev->base, &ptdev->reclaim.mmapped,
 				  sc->nr_to_scan - freed, &remaining,
 				  panthor_gem_try_evict_no_resv_wait, NULL);
 	if (freed >= sc->nr_to_scan)
@@ -1515,7 +1515,7 @@ panthor_gem_shrinker_scan(struct shrinker *shrinker, struct shrink_control *sc)
 	if (freed >= sc->nr_to_scan)
 		goto out;
 
-	freed += drm_gem_lru_scan(&ptdev->reclaim.gpu_mapped_shared,
+	freed += drm_gem_lru_scan(&ptdev->base, &ptdev->reclaim.gpu_mapped_shared,
 				  sc->nr_to_scan - freed, &remaining,
 				  panthor_gem_try_evict, NULL);
 
@@ -1544,21 +1544,16 @@ out:
 int panthor_gem_shrinker_init(struct panthor_device *ptdev)
 {
 	struct shrinker *shrinker;
-	int ret;
-
-	ret = drmm_mutex_init(&ptdev->base, &ptdev->reclaim.lock);
-	if (ret)
-		return ret;
 
 	INIT_LIST_HEAD(&ptdev->reclaim.vms);
-	drm_gem_lru_init(&ptdev->reclaim.unused, &ptdev->reclaim.lock);
-	drm_gem_lru_init(&ptdev->reclaim.mmapped, &ptdev->reclaim.lock);
-	drm_gem_lru_init(&ptdev->reclaim.gpu_mapped_shared, &ptdev->reclaim.lock);
+	drm_gem_lru_init(&ptdev->reclaim.unused);
+	drm_gem_lru_init(&ptdev->reclaim.mmapped);
+	drm_gem_lru_init(&ptdev->reclaim.gpu_mapped_shared);
 	ptdev->reclaim.gpu_mapped_count = 0;
 
 	/* Teach lockdep about lock ordering wrt. shrinker: */
 	fs_reclaim_acquire(GFP_KERNEL);
-	might_lock(&ptdev->reclaim.lock);
+	might_lock(&ptdev->base.gem_lru_mutex);
 	fs_reclaim_release(GFP_KERNEL);
 
 	shrinker = shrinker_alloc(0, "drm-panthor-gem");
diff --git a/drivers/gpu/drm/panthor/panthor_mmu.c b/drivers/gpu/drm/panthor/panthor_mmu.c
index 452d0b6d4668..9d4500850561 100644
--- a/drivers/gpu/drm/panthor/panthor_mmu.c
+++ b/drivers/gpu/drm/panthor/panthor_mmu.c
@@ -715,10 +715,10 @@ int panthor_vm_active(struct panthor_vm *vm)
 	 * never became active in the first place will be reclaimed last, but
 	 * that's an acceptable trade-off.
 	 */
-	mutex_lock(&ptdev->reclaim.lock);
+	mutex_lock(&ptdev->base.gem_lru_mutex);
 	if (vm->reclaim.lru.count)
 		list_move_tail(&vm->reclaim.lru_node, &ptdev->reclaim.vms);
-	mutex_unlock(&ptdev->reclaim.lock);
+	mutex_unlock(&ptdev->base.gem_lru_mutex);
 
 	/* Make sure we don't race with lock/unlock_region() calls
 	 * happening around VM bind operations.
@@ -1962,9 +1962,9 @@ static void panthor_vm_free(struct drm_gpuvm *gpuvm)
 	struct panthor_vm *vm = container_of(gpuvm, struct panthor_vm, base);
 	struct panthor_device *ptdev = vm->ptdev;
 
-	mutex_lock(&ptdev->reclaim.lock);
+	mutex_lock(&ptdev->base.gem_lru_mutex);
 	list_del_init(&vm->reclaim.lru_node);
-	mutex_unlock(&ptdev->reclaim.lock);
+	mutex_unlock(&ptdev->base.gem_lru_mutex);
 
 	mutex_lock(&vm->heaps.lock);
 	if (drm_WARN_ON(&ptdev->base, vm->heaps.pool))
@@ -2360,11 +2360,11 @@ void panthor_vm_update_bo_reclaim_lru_locked(struct panthor_gem_object *bo)
 		drm_WARN_ON(&ptdev->base, vm);
 		vm = container_of(vm_bo->vm, struct panthor_vm, base);
 
-		mutex_lock(&ptdev->reclaim.lock);
+		mutex_lock(&ptdev->base.gem_lru_mutex);
 		drm_gem_lru_move_tail_locked(&vm->reclaim.lru, &bo->base);
 		if (list_empty(&vm->reclaim.lru_node))
 			list_move(&vm->reclaim.lru_node, &ptdev->reclaim.vms);
-		mutex_unlock(&ptdev->reclaim.lock);
+		mutex_unlock(&ptdev->base.gem_lru_mutex);
 	}
 }
 
@@ -2774,7 +2774,7 @@ panthor_vm_create(struct panthor_device *ptdev, bool for_mcu,
 	vm->kernel_auto_va.start = auto_kernel_va_start;
 	vm->kernel_auto_va.end = vm->kernel_auto_va.start + auto_kernel_va_size - 1;
 
-	drm_gem_lru_init(&vm->reclaim.lru, &ptdev->reclaim.lock);
+	drm_gem_lru_init(&vm->reclaim.lru);
 	INIT_LIST_HEAD(&vm->reclaim.lru_node);
 	INIT_LIST_HEAD(&vm->node);
 	INIT_LIST_HEAD(&vm->as.lru_node);
@@ -3140,7 +3140,7 @@ panthor_mmu_reclaim_priv_bos(struct panthor_device *ptdev,
 	LIST_HEAD(remaining_vms);
 	LIST_HEAD(vms);
 
-	mutex_lock(&ptdev->reclaim.lock);
+	mutex_lock(&ptdev->base.gem_lru_mutex);
 	list_splice_init(&ptdev->reclaim.vms, &vms);
 
 	while (freed < nr_to_scan) {
@@ -3156,12 +3156,13 @@ panthor_mmu_reclaim_priv_bos(struct panthor_device *ptdev,
 			continue;
 		}
 
-		mutex_unlock(&ptdev->reclaim.lock);
+		mutex_unlock(&ptdev->base.gem_lru_mutex);
 
-		freed += drm_gem_lru_scan(&vm->reclaim.lru, nr_to_scan - freed,
+		freed += drm_gem_lru_scan(&ptdev->base, &vm->reclaim.lru,
+					  nr_to_scan - freed,
 					  remaining, shrink, NULL);
 
-		mutex_lock(&ptdev->reclaim.lock);
+		mutex_lock(&ptdev->base.gem_lru_mutex);
 
 		/* If the VM is still in the temporary list, remove it so we
 		 * can proceed with the next VM.
@@ -3177,11 +3178,11 @@ panthor_mmu_reclaim_priv_bos(struct panthor_device *ptdev,
 				list_add_tail(&vm->reclaim.lru_node, &remaining_vms);
 		}
 
-		mutex_unlock(&ptdev->reclaim.lock);
+		mutex_unlock(&ptdev->base.gem_lru_mutex);
 
 		panthor_vm_put(vm);
 
-		mutex_lock(&ptdev->reclaim.lock);
+		mutex_lock(&ptdev->base.gem_lru_mutex);
 	}
 
 	/* Re-insert VMs with remaining data to reclaim at the beginning of
@@ -3192,7 +3193,7 @@ panthor_mmu_reclaim_priv_bos(struct panthor_device *ptdev,
 	 */
 	list_splice_tail(&vms, &remaining_vms);
 	list_splice(&remaining_vms, &ptdev->reclaim.vms);
-	mutex_unlock(&ptdev->reclaim.lock);
+	mutex_unlock(&ptdev->base.gem_lru_mutex);
 
 	return freed;
 }
diff --git a/drivers/gpu/drm/qxl/qxl_drv.c b/drivers/gpu/drm/qxl/qxl_drv.c
index 2bbb1168a3ff..1e6a2392d7c6 100644
--- a/drivers/gpu/drm/qxl/qxl_drv.c
+++ b/drivers/gpu/drm/qxl/qxl_drv.c
@@ -118,12 +118,13 @@ qxl_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	/* Complete initialization. */
 	ret = drm_dev_register(&qdev->ddev, ent->driver_data);
 	if (ret)
-		goto modeset_cleanup;
+		goto poll_fini;
 
 	drm_client_setup(&qdev->ddev, NULL);
 	return 0;
 
-modeset_cleanup:
+poll_fini:
+	drm_kms_helper_poll_fini(&qdev->ddev);
 	qxl_modeset_fini(qdev);
 unload:
 	qxl_device_fini(qdev);
@@ -154,6 +155,7 @@ qxl_pci_remove(struct pci_dev *pdev)
 {
 	struct drm_device *dev = pci_get_drvdata(pdev);
 
+	drm_kms_helper_poll_fini(dev);
 	drm_dev_unregister(dev);
 	drm_atomic_helper_shutdown(dev);
 	if (pci_is_vga(pdev) && pdev->revision < 5)
diff --git a/drivers/gpu/drm/sti/sti_hda.c b/drivers/gpu/drm/sti/sti_hda.c
index b7397827889c..360a88ca8f0c 100644
--- a/drivers/gpu/drm/sti/sti_hda.c
+++ b/drivers/gpu/drm/sti/sti_hda.c
@@ -741,6 +741,7 @@ static int sti_hda_probe(struct platform_device *pdev)
 	struct device *dev = &pdev->dev;
 	struct sti_hda *hda;
 	struct resource *res;
+	int ret;
 
 	DRM_INFO("%s\n", __func__);
 
@@ -779,7 +780,9 @@ static int sti_hda_probe(struct platform_device *pdev)
 		return PTR_ERR(hda->clk_hddac);
 	}
 
-	drm_bridge_add(&hda->bridge);
+	ret = devm_drm_bridge_add(dev, &hda->bridge);
+	if (ret)
+		return ret;
 
 	platform_set_drvdata(pdev, hda);
 
@@ -788,10 +791,7 @@ static int sti_hda_probe(struct platform_device *pdev)
 
 static void sti_hda_remove(struct platform_device *pdev)
 {
-	struct sti_hda *hda = platform_get_drvdata(pdev);
-
 	component_del(&pdev->dev, &sti_hda_ops);
-	drm_bridge_remove(&hda->bridge);
 }
 
 static const struct of_device_id hda_of_match[] = {
diff --git a/drivers/gpu/drm/tiny/bochs.c b/drivers/gpu/drm/tiny/bochs.c
index 376465b79b06..e2d957e51505 100644
--- a/drivers/gpu/drm/tiny/bochs.c
+++ b/drivers/gpu/drm/tiny/bochs.c
@@ -761,25 +761,21 @@ static int bochs_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent
 
 	ret = pcim_enable_device(pdev);
 	if (ret)
-		goto err_free_dev;
+		return ret;
 
 	pci_set_drvdata(pdev, dev);
 
 	ret = bochs_load(bochs);
 	if (ret)
-		goto err_free_dev;
+		return ret;
 
 	ret = drm_dev_register(dev, 0);
 	if (ret)
-		goto err_free_dev;
+		return ret;
 
 	drm_client_setup(dev, NULL);
 
 	return ret;
-
-err_free_dev:
-	drm_dev_put(dev);
-	return ret;
 }
 
 static void bochs_pci_remove(struct pci_dev *pdev)
diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index d85f0a37ac35..bcd76f6bb7f0 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -739,7 +739,7 @@ static int ttm_bo_alloc_resource(struct ttm_buffer_object *bo,
 		may_evict = (force_space && place->mem_type != TTM_PL_SYSTEM);
 		ret = ttm_resource_alloc(bo, place, res, force_space ? &limit_pool : NULL);
 		if (ret) {
-			if (ret != -ENOSPC && ret != -EAGAIN) {
+			if (ret != -ENOSPC) {
 				dmem_cgroup_pool_state_put(limit_pool);
 				return ret;
 			}
@@ -1177,17 +1177,13 @@ ttm_bo_swapout_cb(struct ttm_lru_walk *walk, struct ttm_buffer_object *bo)
 		bdev->funcs->swap_notify(bo);
 
 	if (ttm_tt_is_populated(tt)) {
-		spin_lock(&bdev->lru_lock);
-		ttm_resource_del_bulk_move(bo->resource, bo);
-		spin_unlock(&bdev->lru_lock);
-
 		ret = ttm_tt_swapout(bdev, tt, swapout_walk->gfp_flags);
-
-		spin_lock(&bdev->lru_lock);
-		if (ret)
-			ttm_resource_add_bulk_move(bo->resource, bo);
-		ttm_resource_move_to_lru_tail(bo->resource);
-		spin_unlock(&bdev->lru_lock);
+		if (!ret) {
+			spin_lock(&bdev->lru_lock);
+			ttm_resource_del_bulk_move_unevictable(bo->resource, bo);
+			ttm_resource_move_to_lru_tail(bo->resource);
+			spin_unlock(&bdev->lru_lock);
+		}
 	}
 
 out:
diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c
index f83b7d5ec6c6..3e3c201a0222 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_util.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_util.c
@@ -1112,19 +1112,14 @@ long ttm_bo_shrink(struct ttm_operation_ctx *ctx, struct ttm_buffer_object *bo,
 	if (lret < 0)
 		return lret;
 
-	if (bo->bulk_move) {
-		spin_lock(&bdev->lru_lock);
-		ttm_resource_del_bulk_move(bo->resource, bo);
-		spin_unlock(&bdev->lru_lock);
-	}
-
 	lret = ttm_tt_backup(bdev, bo->ttm, (struct ttm_backup_flags)
 			     {.purge = flags.purge,
 			      .writeback = flags.writeback});
 
-	if (lret <= 0 && bo->bulk_move) {
+	if (lret > 0) {
 		spin_lock(&bdev->lru_lock);
-		ttm_resource_add_bulk_move(bo->resource, bo);
+		ttm_resource_del_bulk_move_unevictable(bo->resource, bo);
+		ttm_resource_move_to_lru_tail(bo->resource);
 		spin_unlock(&bdev->lru_lock);
 	}
 
diff --git a/drivers/gpu/drm/ttm/ttm_pool.c b/drivers/gpu/drm/ttm/ttm_pool.c
index 26a3689e5fd9..278bbe7a11ad 100644
--- a/drivers/gpu/drm/ttm/ttm_pool.c
+++ b/drivers/gpu/drm/ttm/ttm_pool.c
@@ -206,6 +206,14 @@ error_free:
 	return NULL;
 }
 
+static void __free_pages_gpu_account(struct page *p, unsigned int order,
+				     bool reclaim)
+{
+	mod_lruvec_page_state(p, reclaim ? NR_GPU_RECLAIM : NR_GPU_ACTIVE,
+			      -(1 << order));
+	__free_pages(p, order);
+}
+
 /* Reset the caching and pages of size 1 << order */
 static void ttm_pool_free_page(struct ttm_pool *pool, enum ttm_caching caching,
 			       unsigned int order, struct page *p, bool reclaim)
@@ -223,9 +231,7 @@ static void ttm_pool_free_page(struct ttm_pool *pool, enum ttm_caching caching,
 #endif
 
 	if (!pool || !ttm_pool_uses_dma_alloc(pool)) {
-		mod_lruvec_page_state(p, reclaim ? NR_GPU_RECLAIM : NR_GPU_ACTIVE,
-				      -(1 << order));
-		__free_pages(p, order);
+		__free_pages_gpu_account(p, order, reclaim);
 		return;
 	}
 
@@ -606,7 +612,7 @@ static int ttm_pool_restore_commit(struct ttm_pool_tt_restore *restore,
 			 */
 			ttm_pool_split_for_swap(restore->pool, p);
 			copy_highpage(restore->alloced_page + i, p);
-			__free_pages(p, 0);
+			__free_pages_gpu_account(p, 0, false);
 		}
 
 		restore->restored_pages++;
@@ -1068,7 +1074,7 @@ long ttm_pool_backup(struct ttm_pool *pool, struct ttm_tt *tt,
 			if (flags->purge) {
 				shrunken += num_pages;
 				page->private = 0;
-				__free_pages(page, order);
+				__free_pages_gpu_account(page, order, false);
 				memset(tt->pages + i, 0,
 				       num_pages * sizeof(*tt->pages));
 			}
@@ -1109,7 +1115,7 @@ long ttm_pool_backup(struct ttm_pool *pool, struct ttm_tt *tt,
 		}
 		handle = shandle;
 		tt->pages[i] = ttm_backup_handle_to_page_ptr(handle);
-		put_page(page);
+		__free_pages_gpu_account(page, 0, false);
 		shrunken++;
 	}
 
diff --git a/drivers/gpu/drm/ttm/ttm_resource.c b/drivers/gpu/drm/ttm/ttm_resource.c
index 9f36631d48b6..154d6739256f 100644
--- a/drivers/gpu/drm/ttm/ttm_resource.c
+++ b/drivers/gpu/drm/ttm/ttm_resource.c
@@ -292,6 +292,19 @@ void ttm_resource_del_bulk_move(struct ttm_resource *res,
 		ttm_lru_bulk_move_del(bo->bulk_move, res);
 }
 
+/*
+ * Remove a resource from its bulk_move, bypassing the unevictable check.
+ * Use only when the resource is known to still be tracked in the range despite
+ * the BO having just become unevictable; asserts that this is the case.
+ */
+void ttm_resource_del_bulk_move_unevictable(struct ttm_resource *res,
+					    struct ttm_buffer_object *bo)
+{
+	WARN_ON_ONCE(!ttm_resource_unevictable(res, bo));
+	if (bo->bulk_move)
+		ttm_lru_bulk_move_del(bo->bulk_move, res);
+}
+
 /* Move a resource to the LRU or bulk tail */
 void ttm_resource_move_to_lru_tail(struct ttm_resource *res)
 {
@@ -385,8 +398,11 @@ int ttm_resource_alloc(struct ttm_buffer_object *bo,
 
 	if (man->cg) {
 		ret = dmem_cgroup_try_charge(man->cg, bo->base.size, &pool, ret_limit_pool);
-		if (ret)
+		if (ret) {
+			if (ret == -EAGAIN)
+				ret = -ENOSPC;
 			return ret;
+		}
 	}
 
 	ret = man->func->alloc(man, bo, place, res_ptr);
diff --git a/drivers/gpu/drm/v3d/v3d_sched.c b/drivers/gpu/drm/v3d/v3d_sched.c
index c01fa90def4c..0e266b29317f 100644
--- a/drivers/gpu/drm/v3d/v3d_sched.c
+++ b/drivers/gpu/drm/v3d/v3d_sched.c
@@ -126,20 +126,6 @@ v3d_performance_query_info_free(struct v3d_performance_query_info *query_info,
 }
 
 static void
-v3d_cpu_job_free(struct drm_sched_job *sched_job)
-{
-	struct v3d_cpu_job *job = to_cpu_job(sched_job);
-
-	v3d_timestamp_query_info_free(&job->timestamp_query,
-				      job->timestamp_query.count);
-
-	v3d_performance_query_info_free(&job->performance_query,
-					job->performance_query.count);
-
-	v3d_job_cleanup(&job->base);
-}
-
-static void
 v3d_switch_perfmon(struct v3d_dev *v3d, struct v3d_job *job)
 {
 	struct v3d_perfmon *perfmon = v3d->global_perfmon;
@@ -830,7 +816,7 @@ static const struct drm_sched_backend_ops v3d_cache_clean_sched_ops = {
 
 static const struct drm_sched_backend_ops v3d_cpu_sched_ops = {
 	.run_job = v3d_cpu_job_run,
-	.free_job = v3d_cpu_job_free
+	.free_job = v3d_sched_job_free
 };
 
 static int
diff --git a/drivers/gpu/drm/v3d/v3d_submit.c b/drivers/gpu/drm/v3d/v3d_submit.c
index d0f949a49dd2..1db43c6a078d 100644
--- a/drivers/gpu/drm/v3d/v3d_submit.c
+++ b/drivers/gpu/drm/v3d/v3d_submit.c
@@ -126,6 +126,24 @@ v3d_render_job_free(struct kref *ref)
 	v3d_job_free(ref);
 }
 
+static void
+v3d_cpu_job_free(struct kref *ref)
+{
+	struct v3d_cpu_job *job = container_of(ref, struct v3d_cpu_job,
+					       base.refcount);
+
+	v3d_timestamp_query_info_free(&job->timestamp_query,
+				      job->timestamp_query.count);
+
+	v3d_performance_query_info_free(&job->performance_query,
+					job->performance_query.count);
+
+	if (job->indirect_csd.indirect)
+		drm_gem_object_put(job->indirect_csd.indirect);
+
+	v3d_job_free(ref);
+}
+
 void v3d_job_cleanup(struct v3d_job *job)
 {
 	if (!job)
@@ -1313,7 +1331,7 @@ v3d_submit_cpu_ioctl(struct drm_device *dev, void *data,
 	trace_v3d_submit_cpu_ioctl(&v3d->drm, cpu_job->job_type);
 
 	ret = v3d_job_init(v3d, file_priv, &cpu_job->base,
-			   v3d_job_free, 0, &se, V3D_CPU);
+			   v3d_cpu_job_free, 0, &se, V3D_CPU);
 	if (ret) {
 		v3d_job_deallocate((void *)&cpu_job);
 		goto fail;
@@ -1396,8 +1414,6 @@ fail:
 	v3d_job_cleanup((void *)csd_job);
 	v3d_job_cleanup(clean_job);
 	v3d_put_multisync_post_deps(&se);
-	kvfree(cpu_job->timestamp_query.queries);
-	kvfree(cpu_job->performance_query.queries);
 
 	return ret;
 }