Merge branch 'master' into mm-stable

63 files changed, 807 insertions, 380 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
index 801f6fa692e9..6de63ea6687e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
@@ -642,7 +642,6 @@ int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
 			    atomic64_read(&adev->visible_pin_size),
 			    vram_gtt.vram_size);
 		vram_gtt.gtt_size = ttm_manager_type(&adev->mman.bdev, TTM_PL_TT)->size;
-		vram_gtt.gtt_size *= PAGE_SIZE;
 		vram_gtt.gtt_size -= atomic64_read(&adev->gart_pin_size);
 		return copy_to_user(out, &vram_gtt,
 				    min((size_t)size, sizeof(vram_gtt))) ? -EFAULT : 0;
@@ -675,7 +674,6 @@ int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
 			mem.cpu_accessible_vram.usable_heap_size * 3 / 4;
 
 		mem.gtt.total_heap_size = gtt_man->size;
-		mem.gtt.total_heap_size *= PAGE_SIZE;
 		mem.gtt.usable_heap_size = mem.gtt.total_heap_size -
 			atomic64_read(&adev->gart_pin_size);
 		mem.gtt.heap_usage = ttm_resource_manager_usage(gtt_man);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index be6f76a30ac6..3b4c19412625 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -1798,18 +1798,26 @@ int amdgpu_ttm_init(struct amdgpu_device *adev)
 	DRM_INFO("amdgpu: %uM of VRAM memory ready\n",
 		 (unsigned) (adev->gmc.real_vram_size / (1024 * 1024)));
 
-	/* Compute GTT size, either bsaed on 3/4th the size of RAM size
+	/* Compute GTT size, either based on 1/2 the size of RAM size
 	 * or whatever the user passed on module init */
 	if (amdgpu_gtt_size == -1) {
 		struct sysinfo si;
 
 		si_meminfo(&si);
-		gtt_size = min(max((AMDGPU_DEFAULT_GTT_SIZE_MB << 20),
-			       adev->gmc.mc_vram_size),
-			       ((uint64_t)si.totalram * si.mem_unit * 3/4));
-	}
-	else
+		/* Certain GL unit tests for large textures can cause problems
+		 * with the OOM killer since there is no way to link this memory
+		 * to a process.  This was originally mitigated (but not necessarily
+		 * eliminated) by limiting the GTT size.  The problem is this limit
+		 * is often too low for many modern games so just make the limit 1/2
+		 * of system memory which aligns with TTM. The OOM accounting needs
+		 * to be addressed, but we shouldn't prevent common 3D applications
+		 * from being usable just to potentially mitigate that corner case.
+		 */
+		gtt_size = max((AMDGPU_DEFAULT_GTT_SIZE_MB << 20),
+			       (u64)si.totalram * si.mem_unit / 2);
+	} else {
 		gtt_size = (uint64_t)amdgpu_gtt_size << 20;
+	}
 
 	/* Initialize GTT memory pool */
 	r = amdgpu_gtt_mgr_init(adev, gtt_size);
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 70be67a56673..39b425d83bb1 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -2812,7 +2812,7 @@ static struct drm_mode_config_helper_funcs amdgpu_dm_mode_config_helperfuncs = {
 
 static void update_connector_ext_caps(struct amdgpu_dm_connector *aconnector)
 {
-	u32 max_cll, min_cll, max, min, q, r;
+	u32 max_avg, min_cll, max, min, q, r;
 	struct amdgpu_dm_backlight_caps *caps;
 	struct amdgpu_display_manager *dm;
 	struct drm_connector *conn_base;
@@ -2842,7 +2842,7 @@ static void update_connector_ext_caps(struct amdgpu_dm_connector *aconnector)
 	caps = &dm->backlight_caps[i];
 	caps->ext_caps = &aconnector->dc_link->dpcd_sink_ext_caps;
 	caps->aux_support = false;
-	max_cll = conn_base->hdr_sink_metadata.hdmi_type1.max_cll;
+	max_avg = conn_base->hdr_sink_metadata.hdmi_type1.max_fall;
 	min_cll = conn_base->hdr_sink_metadata.hdmi_type1.min_cll;
 
 	if (caps->ext_caps->bits.oled == 1 /*||
@@ -2870,8 +2870,8 @@ static void update_connector_ext_caps(struct amdgpu_dm_connector *aconnector)
 	 * The results of the above expressions can be verified at
 	 * pre_computed_values.
 	 */
-	q = max_cll >> 5;
-	r = max_cll % 32;
+	q = max_avg >> 5;
+	r = max_avg % 32;
 	max = (1 << q) * pre_computed_values[r];
 
 	// min luminance: maxLum * (CV/255)^2 / 100
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_clk_mgr.c
index fb4ae800e919..f4381725b210 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_clk_mgr.c
@@ -550,7 +550,7 @@ static void dcn315_clk_mgr_helper_populate_bw_params(
 		if (!bw_params->clk_table.entries[i].dtbclk_mhz)
 			bw_params->clk_table.entries[i].dtbclk_mhz = def_max.dtbclk_mhz;
 	}
-	ASSERT(bw_params->clk_table.entries[i].dcfclk_mhz);
+	ASSERT(bw_params->clk_table.entries[i-1].dcfclk_mhz);
 	bw_params->vram_type = bios_info->memory_type;
 	bw_params->num_channels = bios_info->ma_channel_number;
 	if (!bw_params->num_channels)
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
index cbc47aecd00f..d8eee89e63ce 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
@@ -944,7 +944,7 @@ static void override_lane_settings(const struct link_training_settings *lt_setti
 
 		return;
 
-	for (lane = 1; lane < LANE_COUNT_DP_MAX; lane++) {
+	for (lane = 0; lane < LANE_COUNT_DP_MAX; lane++) {
 		if (lt_settings->voltage_swing)
 			lane_settings[lane].VOLTAGE_SWING = *lt_settings->voltage_swing;
 		if (lt_settings->pre_emphasis)
diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
index 7eff7811769d..5f2afa5b4814 100644
--- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
@@ -1766,29 +1766,9 @@ void dce110_enable_accelerated_mode(struct dc *dc, struct dc_state *context)
 				break;
 			}
 		}
-
-		/*
-		 * TO-DO: So far the code logic below only addresses single eDP case.
-		 * For dual eDP case, there are a few things that need to be
-		 * implemented first:
-		 *
-		 * 1. Change the fastboot logic above, so eDP link[0 or 1]'s
-		 * stream[0 or 1] will all be checked.
-		 *
-		 * 2. Change keep_edp_vdd_on to an array, and maintain keep_edp_vdd_on
-		 * for each eDP.
-		 *
-		 * Once above 2 things are completed, we can then change the logic below
-		 * correspondingly, so dual eDP case will be fully covered.
-		 */
-
-		// We are trying to enable eDP, don't power down VDD if eDP stream is existing
-		if ((edp_stream_num == 1 && edp_streams[0] != NULL) || can_apply_edp_fast_boot) {
+		// We are trying to enable eDP, don't power down VDD
+		if (can_apply_edp_fast_boot)
 			keep_edp_vdd_on = true;
-			DC_LOG_EVENT_LINK_TRAINING("Keep eDP Vdd on\n");
-		} else {
-			DC_LOG_EVENT_LINK_TRAINING("No eDP stream enabled, turn eDP Vdd off\n");
-		}
 	}
 
 	// Check seamless boot support
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dpp.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dpp.c
index 970b65efeac1..eaa7032f0f1a 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dpp.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dpp.c
@@ -212,6 +212,9 @@ static void dpp2_cnv_setup (
 		break;
 	}
 
+	/* Set default color space based on format if none is given. */
+	color_space = input_color_space ? input_color_space : color_space;
+
 	if (is_2bit == 1 && alpha_2bit_lut != NULL) {
 		REG_UPDATE(ALPHA_2BIT_LUT, ALPHA_2BIT_LUT0, alpha_2bit_lut->lut0);
 		REG_UPDATE(ALPHA_2BIT_LUT, ALPHA_2BIT_LUT1, alpha_2bit_lut->lut1);
diff --git a/drivers/gpu/drm/amd/display/dc/dcn201/dcn201_dpp.c b/drivers/gpu/drm/amd/display/dc/dcn201/dcn201_dpp.c
index 8b6505b7dca8..f50ab961bc17 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn201/dcn201_dpp.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn201/dcn201_dpp.c
@@ -153,6 +153,9 @@ static void dpp201_cnv_setup(
 		break;
 	}
 
+	/* Set default color space based on format if none is given. */
+	color_space = input_color_space ? input_color_space : color_space;
+
 	if (is_2bit == 1 && alpha_2bit_lut != NULL) {
 		REG_UPDATE(ALPHA_2BIT_LUT, ALPHA_2BIT_LUT0, alpha_2bit_lut->lut0);
 		REG_UPDATE(ALPHA_2BIT_LUT, ALPHA_2BIT_LUT1, alpha_2bit_lut->lut1);
diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp.c
index ab3918c0a15b..0dcc07531643 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp.c
@@ -294,6 +294,9 @@ static void dpp3_cnv_setup (
 		break;
 	}
 
+	/* Set default color space based on format if none is given. */
+	color_space = input_color_space ? input_color_space : color_space;
+
 	if (is_2bit == 1 && alpha_2bit_lut != NULL) {
 		REG_UPDATE(ALPHA_2BIT_LUT, ALPHA_2BIT_LUT0, alpha_2bit_lut->lut0);
 		REG_UPDATE(ALPHA_2BIT_LUT, ALPHA_2BIT_LUT1, alpha_2bit_lut->lut1);
diff --git a/drivers/gpu/drm/drm_panel_orientation_quirks.c b/drivers/gpu/drm/drm_panel_orientation_quirks.c
index 4e853acfd1e8..df87ba99a87c 100644
--- a/drivers/gpu/drm/drm_panel_orientation_quirks.c
+++ b/drivers/gpu/drm/drm_panel_orientation_quirks.c
@@ -152,6 +152,12 @@ static const struct dmi_system_id orientation_data[] = {
 		  DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "AYA NEO 2021"),
 		},
 		.driver_data = (void *)&lcd800x1280_rightside_up,
+	}, {	/* AYA NEO NEXT */
+		.matches = {
+		  DMI_EXACT_MATCH(DMI_BOARD_VENDOR, "AYANEO"),
+		  DMI_MATCH(DMI_BOARD_NAME, "NEXT"),
+		},
+		.driver_data = (void *)&lcd800x1280_rightside_up,
 	}, {	/* Chuwi HiBook (CWI514) */
 		.matches = {
 			DMI_MATCH(DMI_BOARD_VENDOR, "Hampoo"),
diff --git a/drivers/gpu/drm/exynos/exynos_drm_drv.c b/drivers/gpu/drm/exynos/exynos_drm_drv.c
index 424ea23eec32..16c539657f73 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_drv.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_drv.c
@@ -177,15 +177,15 @@ static struct exynos_drm_driver_info exynos_drm_drivers[] = {
 		DRV_PTR(mixer_driver, CONFIG_DRM_EXYNOS_MIXER),
 		DRM_COMPONENT_DRIVER
 	}, {
-		DRV_PTR(mic_driver, CONFIG_DRM_EXYNOS_MIC),
-		DRM_COMPONENT_DRIVER
-	}, {
 		DRV_PTR(dp_driver, CONFIG_DRM_EXYNOS_DP),
 		DRM_COMPONENT_DRIVER
 	}, {
 		DRV_PTR(dsi_driver, CONFIG_DRM_EXYNOS_DSI),
 		DRM_COMPONENT_DRIVER
 	}, {
+		DRV_PTR(mic_driver, CONFIG_DRM_EXYNOS_MIC),
+		DRM_COMPONENT_DRIVER
+	}, {
 		DRV_PTR(hdmi_driver, CONFIG_DRM_EXYNOS_HDMI),
 		DRM_COMPONENT_DRIVER
 	}, {
diff --git a/drivers/gpu/drm/exynos/exynos_drm_mic.c b/drivers/gpu/drm/exynos/exynos_drm_mic.c
index 9e06f8e2a863..09ce28ee08d9 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_mic.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_mic.c
@@ -26,6 +26,7 @@
 #include <drm/drm_print.h>
 
 #include "exynos_drm_drv.h"
+#include "exynos_drm_crtc.h"
 
 /* Sysreg registers for MIC */
 #define DSD_CFG_MUX	0x1004
@@ -100,9 +101,7 @@ struct exynos_mic {
 
 	bool i80_mode;
 	struct videomode vm;
-	struct drm_encoder *encoder;
 	struct drm_bridge bridge;
-	struct drm_bridge *next_bridge;
 
 	bool enabled;
 };
@@ -229,8 +228,6 @@ static void mic_set_reg_on(struct exynos_mic *mic, bool enable)
 	writel(reg, mic->reg + MIC_OP);
 }
 
-static void mic_disable(struct drm_bridge *bridge) { }
-
 static void mic_post_disable(struct drm_bridge *bridge)
 {
 	struct exynos_mic *mic = bridge->driver_private;
@@ -297,34 +294,30 @@ unlock:
 	mutex_unlock(&mic_mutex);
 }
 
-static void mic_enable(struct drm_bridge *bridge) { }
-
-static int mic_attach(struct drm_bridge *bridge,
-		      enum drm_bridge_attach_flags flags)
-{
-	struct exynos_mic *mic = bridge->driver_private;
-
-	return drm_bridge_attach(bridge->encoder, mic->next_bridge,
-				 &mic->bridge, flags);
-}
-
 static const struct drm_bridge_funcs mic_bridge_funcs = {
-	.disable = mic_disable,
 	.post_disable = mic_post_disable,
 	.mode_set = mic_mode_set,
 	.pre_enable = mic_pre_enable,
-	.enable = mic_enable,
-	.attach = mic_attach,
 };
 
 static int exynos_mic_bind(struct device *dev, struct device *master,
 			   void *data)
 {
 	struct exynos_mic *mic = dev_get_drvdata(dev);
+	struct drm_device *drm_dev = data;
+	struct exynos_drm_crtc *crtc = exynos_drm_crtc_get_by_type(drm_dev,
+						       EXYNOS_DISPLAY_TYPE_LCD);
+	struct drm_encoder *e, *encoder = NULL;
+
+	drm_for_each_encoder(e, drm_dev)
+		if (e->possible_crtcs == drm_crtc_mask(&crtc->base))
+			encoder = e;
+	if (!encoder)
+		return -ENODEV;
 
 	mic->bridge.driver_private = mic;
 
-	return 0;
+	return drm_bridge_attach(encoder, &mic->bridge, NULL, 0);
 }
 
 static void exynos_mic_unbind(struct device *dev, struct device *master,
@@ -388,7 +381,6 @@ static int exynos_mic_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
 	struct exynos_mic *mic;
-	struct device_node *remote;
 	struct resource res;
 	int ret, i;
 
@@ -432,16 +424,6 @@ static int exynos_mic_probe(struct platform_device *pdev)
 		}
 	}
 
-	remote = of_graph_get_remote_node(dev->of_node, 1, 0);
-	mic->next_bridge = of_drm_find_bridge(remote);
-	if (IS_ERR(mic->next_bridge)) {
-		DRM_DEV_ERROR(dev, "mic: Failed to find next bridge\n");
-		ret = PTR_ERR(mic->next_bridge);
-		goto err;
-	}
-
-	of_node_put(remote);
-
 	platform_set_drvdata(pdev, mic);
 
 	mic->bridge.funcs = &mic_bridge_funcs;
diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c
index e4a79c11fd25..ff67899522cf 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.c
+++ b/drivers/gpu/drm/i915/display/intel_dp.c
@@ -388,13 +388,23 @@ static int dg2_max_source_rate(struct intel_dp *intel_dp)
 	return intel_dp_is_edp(intel_dp) ? 810000 : 1350000;
 }
 
+static bool is_low_voltage_sku(struct drm_i915_private *i915, enum phy phy)
+{
+	u32 voltage;
+
+	voltage = intel_de_read(i915, ICL_PORT_COMP_DW3(phy)) & VOLTAGE_INFO_MASK;
+
+	return voltage == VOLTAGE_INFO_0_85V;
+}
+
 static int icl_max_source_rate(struct intel_dp *intel_dp)
 {
 	struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp);
 	struct drm_i915_private *dev_priv = to_i915(dig_port->base.base.dev);
 	enum phy phy = intel_port_to_phy(dev_priv, dig_port->base.port);
 
-	if (intel_phy_is_combo(dev_priv, phy) && !intel_dp_is_edp(intel_dp))
+	if (intel_phy_is_combo(dev_priv, phy) &&
+	    (is_low_voltage_sku(dev_priv, phy) || !intel_dp_is_edp(intel_dp)))
 		return 540000;
 
 	return 810000;
@@ -402,7 +412,23 @@ static int icl_max_source_rate(struct intel_dp *intel_dp)
 
 static int ehl_max_source_rate(struct intel_dp *intel_dp)
 {
-	if (intel_dp_is_edp(intel_dp))
+	struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp);
+	struct drm_i915_private *dev_priv = to_i915(dig_port->base.base.dev);
+	enum phy phy = intel_port_to_phy(dev_priv, dig_port->base.port);
+
+	if (intel_dp_is_edp(intel_dp) || is_low_voltage_sku(dev_priv, phy))
+		return 540000;
+
+	return 810000;
+}
+
+static int dg1_max_source_rate(struct intel_dp *intel_dp)
+{
+	struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp);
+	struct drm_i915_private *i915 = to_i915(dig_port->base.base.dev);
+	enum phy phy = intel_port_to_phy(i915, dig_port->base.port);
+
+	if (intel_phy_is_combo(i915, phy) && is_low_voltage_sku(i915, phy))
 		return 540000;
 
 	return 810000;
@@ -445,7 +471,7 @@ intel_dp_set_source_rates(struct intel_dp *intel_dp)
 			max_rate = dg2_max_source_rate(intel_dp);
 		else if (IS_ALDERLAKE_P(dev_priv) || IS_ALDERLAKE_S(dev_priv) ||
 			 IS_DG1(dev_priv) || IS_ROCKETLAKE(dev_priv))
-			max_rate = 810000;
+			max_rate = dg1_max_source_rate(intel_dp);
 		else if (IS_JSL_EHL(dev_priv))
 			max_rate = ehl_max_source_rate(intel_dp);
 		else
diff --git a/drivers/gpu/drm/i915/display/intel_dpll_mgr.c b/drivers/gpu/drm/i915/display/intel_dpll_mgr.c
index 22f55574a35c..88c2f38aa870 100644
--- a/drivers/gpu/drm/i915/display/intel_dpll_mgr.c
+++ b/drivers/gpu/drm/i915/display/intel_dpll_mgr.c
@@ -2396,7 +2396,7 @@ static void icl_wrpll_params_populate(struct skl_wrpll_params *params,
 }
 
 /*
- * Display WA #22010492432: ehl, tgl, adl-p
+ * Display WA #22010492432: ehl, tgl, adl-s, adl-p
  * Program half of the nominal DCO divider fraction value.
  */
 static bool
@@ -2404,7 +2404,7 @@ ehl_combo_pll_div_frac_wa_needed(struct drm_i915_private *i915)
 {
 	return ((IS_PLATFORM(i915, INTEL_ELKHARTLAKE) &&
 		 IS_JSL_EHL_DISPLAY_STEP(i915, STEP_B0, STEP_FOREVER)) ||
-		 IS_TIGERLAKE(i915) || IS_ALDERLAKE_P(i915)) &&
+		 IS_TIGERLAKE(i915) || IS_ALDERLAKE_S(i915) || IS_ALDERLAKE_P(i915)) &&
 		 i915->dpll.ref_clks.nssc == 38400;
 }
 
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
index c326bd2b444f..30fe847c6664 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
@@ -999,7 +999,8 @@ static int eb_validate_vmas(struct i915_execbuffer *eb)
 			}
 		}
 
-		err = dma_resv_reserve_fences(vma->obj->base.resv, 1);
+		/* Reserve enough slots to accommodate composite fences */
+		err = dma_resv_reserve_fences(vma->obj->base.resv, eb->num_batches);
 		if (err)
 			return err;
 
diff --git a/drivers/gpu/drm/i915/gt/intel_gt.c b/drivers/gpu/drm/i915/gt/intel_gt.c
index 53307ca0eed0..51a0fe60c050 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt.c
@@ -785,6 +785,7 @@ void intel_gt_driver_unregister(struct intel_gt *gt)
 {
 	intel_wakeref_t wakeref;
 
+	intel_gt_sysfs_unregister(gt);
 	intel_rps_driver_unregister(&gt->rps);
 	intel_gsc_fini(&gt->gsc);
 
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_sysfs.c b/drivers/gpu/drm/i915/gt/intel_gt_sysfs.c
index 8ec8bc660c8c..9e4ebf53379b 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_sysfs.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt_sysfs.c
@@ -24,7 +24,7 @@ bool is_object_gt(struct kobject *kobj)
 
 static struct intel_gt *kobj_to_gt(struct kobject *kobj)
 {
-	return container_of(kobj, struct kobj_gt, base)->gt;
+	return container_of(kobj, struct intel_gt, sysfs_gt);
 }
 
 struct intel_gt *intel_gt_sysfs_get_drvdata(struct device *dev,
@@ -72,9 +72,9 @@ static struct attribute *id_attrs[] = {
 };
 ATTRIBUTE_GROUPS(id);
 
+/* A kobject needs a release() method even if it does nothing */
 static void kobj_gt_release(struct kobject *kobj)
 {
-	kfree(kobj);
 }
 
 static struct kobj_type kobj_gt_type = {
@@ -85,8 +85,6 @@ static struct kobj_type kobj_gt_type = {
 
 void intel_gt_sysfs_register(struct intel_gt *gt)
 {
-	struct kobj_gt *kg;
-
 	/*
 	 * We need to make things right with the
 	 * ABI compatibility. The files were originally
@@ -98,25 +96,22 @@ void intel_gt_sysfs_register(struct intel_gt *gt)
 	if (gt_is_root(gt))
 		intel_gt_sysfs_pm_init(gt, gt_get_parent_obj(gt));
 
-	kg = kzalloc(sizeof(*kg), GFP_KERNEL);
-	if (!kg)
+	/* init and xfer ownership to sysfs tree */
+	if (kobject_init_and_add(&gt->sysfs_gt, &kobj_gt_type,
+				 gt->i915->sysfs_gt, "gt%d", gt->info.id))
 		goto exit_fail;
 
-	kobject_init(&kg->base, &kobj_gt_type);
-	kg->gt = gt;
-
-	/* xfer ownership to sysfs tree */
-	if (kobject_add(&kg->base, gt->i915->sysfs_gt, "gt%d", gt->info.id))
-		goto exit_kobj_put;
-
-	intel_gt_sysfs_pm_init(gt, &kg->base);
+	intel_gt_sysfs_pm_init(gt, &gt->sysfs_gt);
 
 	return;
 
-exit_kobj_put:
-	kobject_put(&kg->base);
-
 exit_fail:
+	kobject_put(&gt->sysfs_gt);
 	drm_warn(&gt->i915->drm,
 		 "failed to initialize gt%d sysfs root\n", gt->info.id);
 }
+
+void intel_gt_sysfs_unregister(struct intel_gt *gt)
+{
+	kobject_put(&gt->sysfs_gt);
+}
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_sysfs.h b/drivers/gpu/drm/i915/gt/intel_gt_sysfs.h
index 9471b26752cf..a99aa7e8b01a 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_sysfs.h
+++ b/drivers/gpu/drm/i915/gt/intel_gt_sysfs.h
@@ -13,11 +13,6 @@
 
 struct intel_gt;
 
-struct kobj_gt {
-	struct kobject base;
-	struct intel_gt *gt;
-};
-
 bool is_object_gt(struct kobject *kobj);
 
 struct drm_i915_private *kobj_to_i915(struct kobject *kobj);
@@ -28,6 +23,7 @@ intel_gt_create_kobj(struct intel_gt *gt,
 		     const char *name);
 
 void intel_gt_sysfs_register(struct intel_gt *gt);
+void intel_gt_sysfs_unregister(struct intel_gt *gt);
 struct intel_gt *intel_gt_sysfs_get_drvdata(struct device *dev,
 					    const char *name);
 
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_types.h b/drivers/gpu/drm/i915/gt/intel_gt_types.h
index b06611c1d4ad..edd7a3cf5f5f 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_gt_types.h
@@ -224,6 +224,9 @@ struct intel_gt {
 	} mocs;
 
 	struct intel_pxp pxp;
+
+	/* gt/gtN sysfs */
+	struct kobject sysfs_gt;
 };
 
 enum intel_gt_scratch_field {
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c
index d078f884b5e3..f0d7b57b741e 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c
@@ -156,7 +156,7 @@ __uc_fw_auto_select(struct drm_i915_private *i915, struct intel_uc_fw *uc_fw)
 		[INTEL_UC_FW_TYPE_GUC] = { blobs_guc, ARRAY_SIZE(blobs_guc) },
 		[INTEL_UC_FW_TYPE_HUC] = { blobs_huc, ARRAY_SIZE(blobs_huc) },
 	};
-	static const struct uc_fw_platform_requirement *fw_blobs;
+	const struct uc_fw_platform_requirement *fw_blobs;
 	enum intel_platform p = INTEL_INFO(i915)->platform;
 	u32 fw_count;
 	u8 rev = INTEL_REVID(i915);
diff --git a/drivers/gpu/drm/i915/i915_drm_client.c b/drivers/gpu/drm/i915/i915_drm_client.c
index 18d38cb59923..b09d1d386574 100644
--- a/drivers/gpu/drm/i915/i915_drm_client.c
+++ b/drivers/gpu/drm/i915/i915_drm_client.c
@@ -116,8 +116,9 @@ show_client_class(struct seq_file *m,
 		total += busy_add(ctx, class);
 	rcu_read_unlock();
 
-	seq_printf(m, "drm-engine-%s:\t%llu ns\n",
-		   uabi_class_names[class], total);
+	if (capacity)
+		seq_printf(m, "drm-engine-%s:\t%llu ns\n",
+			   uabi_class_names[class], total);
 
 	if (capacity > 1)
 		seq_printf(m, "drm-engine-capacity-%s:\t%u\n",
diff --git a/drivers/gpu/drm/i915/i915_sysfs.c b/drivers/gpu/drm/i915/i915_sysfs.c
index 8521daba212a..1e2750210831 100644
--- a/drivers/gpu/drm/i915/i915_sysfs.c
+++ b/drivers/gpu/drm/i915/i915_sysfs.c
@@ -166,7 +166,14 @@ static ssize_t error_state_read(struct file *filp, struct kobject *kobj,
 	struct device *kdev = kobj_to_dev(kobj);
 	struct drm_i915_private *i915 = kdev_minor_to_i915(kdev);
 	struct i915_gpu_coredump *gpu;
-	ssize_t ret;
+	ssize_t ret = 0;
+
+	/*
+	 * FIXME: Concurrent clients triggering resets and reading + clearing
+	 * dumps can cause inconsistent sysfs reads when a user calls in with a
+	 * non-zero offset to complete a prior partial read but the
+	 * gpu_coredump has been cleared or replaced.
+	 */
 
 	gpu = i915_first_error_state(i915);
 	if (IS_ERR(gpu)) {
@@ -178,8 +185,10 @@ static ssize_t error_state_read(struct file *filp, struct kobject *kobj,
 		const char *str = "No error state collected\n";
 		size_t len = strlen(str);
 
-		ret = min_t(size_t, count, len - off);
-		memcpy(buf, str + off, ret);
+		if (off < len) {
+			ret = min_t(size_t, count, len - off);
+			memcpy(buf, str + off, ret);
+		}
 	}
 
 	return ret;
@@ -259,4 +268,6 @@ void i915_teardown_sysfs(struct drm_i915_private *dev_priv)
 
 	device_remove_bin_file(kdev,  &dpf_attrs_1);
 	device_remove_bin_file(kdev,  &dpf_attrs);
+
+	kobject_put(dev_priv->sysfs_gt);
 }
diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c
index 4f6db539571a..0bffb70b3c5f 100644
--- a/drivers/gpu/drm/i915/i915_vma.c
+++ b/drivers/gpu/drm/i915/i915_vma.c
@@ -23,6 +23,7 @@
  */
 
 #include <linux/sched/mm.h>
+#include <linux/dma-fence-array.h>
 #include <drm/drm_gem.h>
 
 #include "display/intel_frontbuffer.h"
@@ -1823,6 +1824,21 @@ int _i915_vma_move_to_active(struct i915_vma *vma,
 	if (unlikely(err))
 		return err;
 
+	/*
+	 * Reserve fences slot early to prevent an allocation after preparing
+	 * the workload and associating fences with dma_resv.
+	 */
+	if (fence && !(flags & __EXEC_OBJECT_NO_RESERVE)) {
+		struct dma_fence *curr;
+		int idx;
+
+		dma_fence_array_for_each(curr, idx, fence)
+			;
+		err = dma_resv_reserve_fences(vma->obj->base.resv, idx);
+		if (unlikely(err))
+			return err;
+	}
+
 	if (flags & EXEC_OBJECT_WRITE) {
 		struct intel_frontbuffer *front;
 
@@ -1832,31 +1848,23 @@ int _i915_vma_move_to_active(struct i915_vma *vma,
 				i915_active_add_request(&front->write, rq);
 			intel_frontbuffer_put(front);
 		}
+	}
 
-		if (!(flags & __EXEC_OBJECT_NO_RESERVE)) {
-			err = dma_resv_reserve_fences(vma->obj->base.resv, 1);
-			if (unlikely(err))
-				return err;
-		}
+	if (fence) {
+		struct dma_fence *curr;
+		enum dma_resv_usage usage;
+		int idx;
 
-		if (fence) {
-			dma_resv_add_fence(vma->obj->base.resv, fence,
-					   DMA_RESV_USAGE_WRITE);
+		obj->read_domains = 0;
+		if (flags & EXEC_OBJECT_WRITE) {
+			usage = DMA_RESV_USAGE_WRITE;
 			obj->write_domain = I915_GEM_DOMAIN_RENDER;
-			obj->read_domains = 0;
-		}
-	} else {
-		if (!(flags & __EXEC_OBJECT_NO_RESERVE)) {
-			err = dma_resv_reserve_fences(vma->obj->base.resv, 1);
-			if (unlikely(err))
-				return err;
+		} else {
+			usage = DMA_RESV_USAGE_READ;
 		}
 
-		if (fence) {
-			dma_resv_add_fence(vma->obj->base.resv, fence,
-					   DMA_RESV_USAGE_READ);
-			obj->write_domain = 0;
-		}
+		dma_fence_array_for_each(curr, idx, fence)
+			dma_resv_add_fence(vma->obj->base.resv, curr, usage);
 	}
 
 	if (flags & EXEC_OBJECT_NEEDS_FENCE && vma->fence)
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
index 4e665c806a14..efe9840e28fa 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
@@ -498,10 +498,15 @@ int adreno_hw_init(struct msm_gpu *gpu)
 
 		ring->cur = ring->start;
 		ring->next = ring->start;
-
-		/* reset completed fence seqno: */
-		ring->memptrs->fence = ring->fctx->completed_fence;
 		ring->memptrs->rptr = 0;
+
+		/* Detect and clean up an impossible fence, ie. if GPU managed
+		 * to scribble something invalid, we don't want that to confuse
+		 * us into mistakingly believing that submits have completed.
+		 */
+		if (fence_before(ring->fctx->last_fence, ring->memptrs->fence)) {
+			ring->memptrs->fence = ring->fctx->last_fence;
+		}
 	}
 
 	return 0;
@@ -1057,7 +1062,8 @@ void adreno_gpu_cleanup(struct adreno_gpu *adreno_gpu)
 	for (i = 0; i < ARRAY_SIZE(adreno_gpu->info->fw); i++)
 		release_firmware(adreno_gpu->fw[i]);
 
-	pm_runtime_disable(&priv->gpu_pdev->dev);
+	if (pm_runtime_enabled(&priv->gpu_pdev->dev))
+		pm_runtime_disable(&priv->gpu_pdev->dev);
 
 	msm_gpu_cleanup(&adreno_gpu->base);
 }
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_writeback.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_writeback.c
index 399115e4e217..2fd787079f9b 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_writeback.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_writeback.c
@@ -11,7 +11,14 @@ static int dpu_wb_conn_get_modes(struct drm_connector *connector)
 	struct msm_drm_private *priv = dev->dev_private;
 	struct dpu_kms *dpu_kms = to_dpu_kms(priv->kms);
 
-	return drm_add_modes_noedid(connector, dpu_kms->catalog->caps->max_linewidth,
+	/*
+	 * We should ideally be limiting the modes only to the maxlinewidth but
+	 * on some chipsets this will allow even 4k modes to be added which will
+	 * fail the per SSPP bandwidth checks. So, till we have dual-SSPP support
+	 * and source split support added lets limit the modes based on max_mixer_width
+	 * as 4K modes can then be supported.
+	 */
+	return drm_add_modes_noedid(connector, dpu_kms->catalog->caps->max_mixer_width,
 			dev->mode_config.max_height);
 }
 
diff --git a/drivers/gpu/drm/msm/disp/mdp4/mdp4_kms.c b/drivers/gpu/drm/msm/disp/mdp4/mdp4_kms.c
index fb48c8c19ec3..17cb1fc78379 100644
--- a/drivers/gpu/drm/msm/disp/mdp4/mdp4_kms.c
+++ b/drivers/gpu/drm/msm/disp/mdp4/mdp4_kms.c
@@ -216,6 +216,7 @@ static int mdp4_modeset_init_intf(struct mdp4_kms *mdp4_kms,
 		encoder = mdp4_lcdc_encoder_init(dev, panel_node);
 		if (IS_ERR(encoder)) {
 			DRM_DEV_ERROR(dev->dev, "failed to construct LCDC encoder\n");
+			of_node_put(panel_node);
 			return PTR_ERR(encoder);
 		}
 
@@ -225,6 +226,7 @@ static int mdp4_modeset_init_intf(struct mdp4_kms *mdp4_kms,
 		connector = mdp4_lvds_connector_init(dev, panel_node, encoder);
 		if (IS_ERR(connector)) {
 			DRM_DEV_ERROR(dev->dev, "failed to initialize LVDS connector\n");
+			of_node_put(panel_node);
 			return PTR_ERR(connector);
 		}
 
diff --git a/drivers/gpu/drm/msm/dp/dp_ctrl.c b/drivers/gpu/drm/msm/dp/dp_ctrl.c
index b7f5b8d3bbd6..703249384e7c 100644
--- a/drivers/gpu/drm/msm/dp/dp_ctrl.c
+++ b/drivers/gpu/drm/msm/dp/dp_ctrl.c
@@ -1534,6 +1534,8 @@ end:
 	return ret;
 }
 
+static int dp_ctrl_on_stream_phy_test_report(struct dp_ctrl *dp_ctrl);
+
 static int dp_ctrl_process_phy_test_request(struct dp_ctrl_private *ctrl)
 {
 	int ret = 0;
@@ -1557,7 +1559,7 @@ static int dp_ctrl_process_phy_test_request(struct dp_ctrl_private *ctrl)
 
 	ret = dp_ctrl_on_link(&ctrl->dp_ctrl);
 	if (!ret)
-		ret = dp_ctrl_on_stream(&ctrl->dp_ctrl);
+		ret = dp_ctrl_on_stream_phy_test_report(&ctrl->dp_ctrl);
 	else
 		DRM_ERROR("failed to enable DP link controller\n");
 
@@ -1813,7 +1815,27 @@ static int dp_ctrl_link_retrain(struct dp_ctrl_private *ctrl)
 	return dp_ctrl_setup_main_link(ctrl, &training_step);
 }
 
-int dp_ctrl_on_stream(struct dp_ctrl *dp_ctrl)
+static int dp_ctrl_on_stream_phy_test_report(struct dp_ctrl *dp_ctrl)
+{
+	int ret;
+	struct dp_ctrl_private *ctrl;
+
+	ctrl = container_of(dp_ctrl, struct dp_ctrl_private, dp_ctrl);
+
+	ctrl->dp_ctrl.pixel_rate = ctrl->panel->dp_mode.drm_mode.clock;
+
+	ret = dp_ctrl_enable_stream_clocks(ctrl);
+	if (ret) {
+		DRM_ERROR("Failed to start pixel clocks. ret=%d\n", ret);
+		return ret;
+	}
+
+	dp_ctrl_send_phy_test_pattern(ctrl);
+
+	return 0;
+}
+
+int dp_ctrl_on_stream(struct dp_ctrl *dp_ctrl, bool force_link_train)
 {
 	int ret = 0;
 	bool mainlink_ready = false;
@@ -1849,12 +1871,7 @@ int dp_ctrl_on_stream(struct dp_ctrl *dp_ctrl)
 		goto end;
 	}
 
-	if (ctrl->link->sink_request & DP_TEST_LINK_PHY_TEST_PATTERN) {
-		dp_ctrl_send_phy_test_pattern(ctrl);
-		return 0;
-	}
-
-	if (!dp_ctrl_channel_eq_ok(ctrl))
+	if (force_link_train || !dp_ctrl_channel_eq_ok(ctrl))
 		dp_ctrl_link_retrain(ctrl);
 
 	/* stop txing train pattern to end link training */
diff --git a/drivers/gpu/drm/msm/dp/dp_ctrl.h b/drivers/gpu/drm/msm/dp/dp_ctrl.h
index 0745fde01b45..b563e2e3bfe5 100644
--- a/drivers/gpu/drm/msm/dp/dp_ctrl.h
+++ b/drivers/gpu/drm/msm/dp/dp_ctrl.h
@@ -21,7 +21,7 @@ struct dp_ctrl {
 };
 
 int dp_ctrl_on_link(struct dp_ctrl *dp_ctrl);
-int dp_ctrl_on_stream(struct dp_ctrl *dp_ctrl);
+int dp_ctrl_on_stream(struct dp_ctrl *dp_ctrl, bool force_link_train);
 int dp_ctrl_off_link_stream(struct dp_ctrl *dp_ctrl);
 int dp_ctrl_off_link(struct dp_ctrl *dp_ctrl);
 int dp_ctrl_off(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 bce77935394f..ec26855079c1 100644
--- a/drivers/gpu/drm/msm/dp/dp_display.c
+++ b/drivers/gpu/drm/msm/dp/dp_display.c
@@ -309,7 +309,8 @@ static void dp_display_unbind(struct device *dev, struct device *master,
 	struct msm_drm_private *priv = dev_get_drvdata(master);
 
 	/* disable all HPD interrupts */
-	dp_catalog_hpd_config_intr(dp->catalog, DP_DP_HPD_INT_MASK, false);
+	if (dp->core_initialized)
+		dp_catalog_hpd_config_intr(dp->catalog, DP_DP_HPD_INT_MASK, false);
 
 	kthread_stop(dp->ev_tsk);
 
@@ -872,7 +873,7 @@ static int dp_display_enable(struct dp_display_private *dp, u32 data)
 		return 0;
 	}
 
-	rc = dp_ctrl_on_stream(dp->ctrl);
+	rc = dp_ctrl_on_stream(dp->ctrl, data);
 	if (!rc)
 		dp_display->power_on = true;
 
@@ -1659,6 +1660,7 @@ void dp_bridge_enable(struct drm_bridge *drm_bridge)
 	int rc = 0;
 	struct dp_display_private *dp_display;
 	u32 state;
+	bool force_link_train = false;
 
 	dp_display = container_of(dp, struct dp_display_private, dp_display);
 	if (!dp_display->dp_mode.drm_mode.clock) {
@@ -1693,10 +1695,12 @@ void dp_bridge_enable(struct drm_bridge *drm_bridge)
 
 	state =  dp_display->hpd_state;
 
-	if (state == ST_DISPLAY_OFF)
+	if (state == ST_DISPLAY_OFF) {
 		dp_display_host_phy_init(dp_display);
+		force_link_train = true;
+	}
 
-	dp_display_enable(dp_display, 0);
+	dp_display_enable(dp_display, force_link_train);
 
 	rc = dp_display_post_enable(dp);
 	if (rc) {
@@ -1705,10 +1709,6 @@ void dp_bridge_enable(struct drm_bridge *drm_bridge)
 		dp_display_unprepare(dp);
 	}
 
-	/* manual kick off plug event to train link */
-	if (state == ST_DISPLAY_OFF)
-		dp_add_event(dp_display, EV_IRQ_HPD_INT, 0, 0);
-
 	/* completed connection */
 	dp_display->hpd_state = ST_CONNECTED;
 
diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c
index 44485363f37a..14ab9a627d8b 100644
--- a/drivers/gpu/drm/msm/msm_drv.c
+++ b/drivers/gpu/drm/msm/msm_drv.c
@@ -964,7 +964,7 @@ static const struct drm_driver msm_driver = {
 	.prime_handle_to_fd = drm_gem_prime_handle_to_fd,
 	.prime_fd_to_handle = drm_gem_prime_fd_to_handle,
 	.gem_prime_import_sg_table = msm_gem_prime_import_sg_table,
-	.gem_prime_mmap     = drm_gem_prime_mmap,
+	.gem_prime_mmap     = msm_gem_prime_mmap,
 #ifdef CONFIG_DEBUG_FS
 	.debugfs_init       = msm_debugfs_init,
 #endif
diff --git a/drivers/gpu/drm/msm/msm_drv.h b/drivers/gpu/drm/msm/msm_drv.h
index 08388d742d65..099a67d10c3a 100644
--- a/drivers/gpu/drm/msm/msm_drv.h
+++ b/drivers/gpu/drm/msm/msm_drv.h
@@ -246,6 +246,7 @@ unsigned long msm_gem_shrinker_shrink(struct drm_device *dev, unsigned long nr_t
 void msm_gem_shrinker_init(struct drm_device *dev);
 void msm_gem_shrinker_cleanup(struct drm_device *dev);
 
+int msm_gem_prime_mmap(struct drm_gem_object *obj, struct vm_area_struct *vma);
 struct sg_table *msm_gem_prime_get_sg_table(struct drm_gem_object *obj);
 int msm_gem_prime_vmap(struct drm_gem_object *obj, struct iosys_map *map);
 void msm_gem_prime_vunmap(struct drm_gem_object *obj, struct iosys_map *map);
diff --git a/drivers/gpu/drm/msm/msm_fence.c b/drivers/gpu/drm/msm/msm_fence.c
index 3df255402a33..38e3323bc232 100644
--- a/drivers/gpu/drm/msm/msm_fence.c
+++ b/drivers/gpu/drm/msm/msm_fence.c
@@ -46,12 +46,14 @@ bool msm_fence_completed(struct msm_fence_context *fctx, uint32_t fence)
 		(int32_t)(*fctx->fenceptr - fence) >= 0;
 }
 
-/* called from workqueue */
+/* called from irq handler and workqueue (in recover path) */
 void msm_update_fence(struct msm_fence_context *fctx, uint32_t fence)
 {
-	spin_lock(&fctx->spinlock);
+	unsigned long flags;
+
+	spin_lock_irqsave(&fctx->spinlock, flags);
 	fctx->completed_fence = max(fence, fctx->completed_fence);
-	spin_unlock(&fctx->spinlock);
+	spin_unlock_irqrestore(&fctx->spinlock, flags);
 }
 
 struct msm_fence {
diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c
index 97d5b4d8b9b0..7f92231785a0 100644
--- a/drivers/gpu/drm/msm/msm_gem.c
+++ b/drivers/gpu/drm/msm/msm_gem.c
@@ -439,14 +439,12 @@ int msm_gem_pin_vma_locked(struct drm_gem_object *obj, struct msm_gem_vma *vma)
 	return ret;
 }
 
-void msm_gem_unpin_vma_locked(struct drm_gem_object *obj, struct msm_gem_vma *vma)
+void msm_gem_unpin_locked(struct drm_gem_object *obj)
 {
 	struct msm_gem_object *msm_obj = to_msm_bo(obj);
 
 	GEM_WARN_ON(!msm_gem_is_locked(obj));
 
-	msm_gem_unpin_vma(vma);
-
 	msm_obj->pin_count--;
 	GEM_WARN_ON(msm_obj->pin_count < 0);
 
@@ -586,7 +584,8 @@ void msm_gem_unpin_iova(struct drm_gem_object *obj,
 	msm_gem_lock(obj);
 	vma = lookup_vma(obj, aspace);
 	if (!GEM_WARN_ON(!vma)) {
-		msm_gem_unpin_vma_locked(obj, vma);
+		msm_gem_unpin_vma(vma);
+		msm_gem_unpin_locked(obj);
 	}
 	msm_gem_unlock(obj);
 }
diff --git a/drivers/gpu/drm/msm/msm_gem.h b/drivers/gpu/drm/msm/msm_gem.h
index c75d3b879a53..6b7d5bb3b575 100644
--- a/drivers/gpu/drm/msm/msm_gem.h
+++ b/drivers/gpu/drm/msm/msm_gem.h
@@ -145,7 +145,7 @@ struct msm_gem_object {
 
 uint64_t msm_gem_mmap_offset(struct drm_gem_object *obj);
 int msm_gem_pin_vma_locked(struct drm_gem_object *obj, struct msm_gem_vma *vma);
-void msm_gem_unpin_vma_locked(struct drm_gem_object *obj, struct msm_gem_vma *vma);
+void msm_gem_unpin_locked(struct drm_gem_object *obj);
 struct msm_gem_vma *msm_gem_get_vma_locked(struct drm_gem_object *obj,
 					   struct msm_gem_address_space *aspace);
 int msm_gem_get_iova(struct drm_gem_object *obj,
@@ -377,10 +377,11 @@ struct msm_gem_submit {
 	} *cmd;  /* array of size nr_cmds */
 	struct {
 /* make sure these don't conflict w/ MSM_SUBMIT_BO_x */
-#define BO_VALID    0x8000   /* is current addr in cmdstream correct/valid? */
-#define BO_LOCKED   0x4000   /* obj lock is held */
-#define BO_ACTIVE   0x2000   /* active refcnt is held */
-#define BO_PINNED   0x1000   /* obj is pinned and on active list */
+#define BO_VALID	0x8000	/* is current addr in cmdstream correct/valid? */
+#define BO_LOCKED	0x4000	/* obj lock is held */
+#define BO_ACTIVE	0x2000	/* active refcnt is held */
+#define BO_OBJ_PINNED	0x1000	/* obj (pages) is pinned and on active list */
+#define BO_VMA_PINNED	0x0800	/* vma (virtual address) is pinned */
 		uint32_t flags;
 		union {
 			struct msm_gem_object *obj;
diff --git a/drivers/gpu/drm/msm/msm_gem_prime.c b/drivers/gpu/drm/msm/msm_gem_prime.c
index 94ab705e9b8a..dcc8a573bc76 100644
--- a/drivers/gpu/drm/msm/msm_gem_prime.c
+++ b/drivers/gpu/drm/msm/msm_gem_prime.c
@@ -11,6 +11,21 @@
 #include "msm_drv.h"
 #include "msm_gem.h"
 
+int msm_gem_prime_mmap(struct drm_gem_object *obj, struct vm_area_struct *vma)
+{
+	int ret;
+
+	/* Ensure the mmap offset is initialized.  We lazily initialize it,
+	 * so if it has not been first mmap'd directly as a GEM object, the
+	 * mmap offset will not be already initialized.
+	 */
+	ret = drm_gem_create_mmap_offset(obj);
+	if (ret)
+		return ret;
+
+	return drm_gem_prime_mmap(obj, vma);
+}
+
 struct sg_table *msm_gem_prime_get_sg_table(struct drm_gem_object *obj)
 {
 	struct msm_gem_object *msm_obj = to_msm_bo(obj);
diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c
index 80975229b4de..3c3a0cfade36 100644
--- a/drivers/gpu/drm/msm/msm_gem_submit.c
+++ b/drivers/gpu/drm/msm/msm_gem_submit.c
@@ -232,8 +232,11 @@ static void submit_cleanup_bo(struct msm_gem_submit *submit, int i,
 	 */
 	submit->bos[i].flags &= ~cleanup_flags;
 
-	if (flags & BO_PINNED)
-		msm_gem_unpin_vma_locked(obj, submit->bos[i].vma);
+	if (flags & BO_VMA_PINNED)
+		msm_gem_unpin_vma(submit->bos[i].vma);
+
+	if (flags & BO_OBJ_PINNED)
+		msm_gem_unpin_locked(obj);
 
 	if (flags & BO_ACTIVE)
 		msm_gem_active_put(obj);
@@ -244,7 +247,9 @@ static void submit_cleanup_bo(struct msm_gem_submit *submit, int i,
 
 static void submit_unlock_unpin_bo(struct msm_gem_submit *submit, int i)
 {
-	submit_cleanup_bo(submit, i, BO_PINNED | BO_ACTIVE | BO_LOCKED);
+	unsigned cleanup_flags = BO_VMA_PINNED | BO_OBJ_PINNED |
+				 BO_ACTIVE | BO_LOCKED;
+	submit_cleanup_bo(submit, i, cleanup_flags);
 
 	if (!(submit->bos[i].flags & BO_VALID))
 		submit->bos[i].iova = 0;
@@ -375,7 +380,7 @@ static int submit_pin_objects(struct msm_gem_submit *submit)
 		if (ret)
 			break;
 
-		submit->bos[i].flags |= BO_PINNED;
+		submit->bos[i].flags |= BO_OBJ_PINNED | BO_VMA_PINNED;
 		submit->bos[i].vma = vma;
 
 		if (vma->iova == submit->bos[i].iova) {
@@ -511,7 +516,7 @@ static void submit_cleanup(struct msm_gem_submit *submit, bool error)
 	unsigned i;
 
 	if (error)
-		cleanup_flags |= BO_PINNED | BO_ACTIVE;
+		cleanup_flags |= BO_VMA_PINNED | BO_OBJ_PINNED | BO_ACTIVE;
 
 	for (i = 0; i < submit->nr_bos; i++) {
 		struct msm_gem_object *msm_obj = submit->bos[i].obj;
@@ -529,7 +534,8 @@ void msm_submit_retire(struct msm_gem_submit *submit)
 		struct drm_gem_object *obj = &submit->bos[i].obj->base;
 
 		msm_gem_lock(obj);
-		submit_cleanup_bo(submit, i, BO_PINNED | BO_ACTIVE);
+		/* Note, VMA already fence-unpinned before submit: */
+		submit_cleanup_bo(submit, i, BO_OBJ_PINNED | BO_ACTIVE);
 		msm_gem_unlock(obj);
 		drm_gem_object_put(obj);
 	}
diff --git a/drivers/gpu/drm/msm/msm_gem_vma.c b/drivers/gpu/drm/msm/msm_gem_vma.c
index 3c1dc9241831..c471aebcdbab 100644
--- a/drivers/gpu/drm/msm/msm_gem_vma.c
+++ b/drivers/gpu/drm/msm/msm_gem_vma.c
@@ -62,8 +62,7 @@ void msm_gem_purge_vma(struct msm_gem_address_space *aspace,
 	unsigned size = vma->node.size;
 
 	/* Print a message if we try to purge a vma in use */
-	if (GEM_WARN_ON(msm_gem_vma_inuse(vma)))
-		return;
+	GEM_WARN_ON(msm_gem_vma_inuse(vma));
 
 	/* Don't do anything if the memory isn't mapped */
 	if (!vma->mapped)
@@ -128,8 +127,7 @@ msm_gem_map_vma(struct msm_gem_address_space *aspace,
 void msm_gem_close_vma(struct msm_gem_address_space *aspace,
 		struct msm_gem_vma *vma)
 {
-	if (GEM_WARN_ON(msm_gem_vma_inuse(vma) || vma->mapped))
-		return;
+	GEM_WARN_ON(msm_gem_vma_inuse(vma) || vma->mapped);
 
 	spin_lock(&aspace->lock);
 	if (vma->iova)
diff --git a/drivers/gpu/drm/msm/msm_gpu.c b/drivers/gpu/drm/msm/msm_gpu.c
index eb8a6663f309..c8cd9bfa3eeb 100644
--- a/drivers/gpu/drm/msm/msm_gpu.c
+++ b/drivers/gpu/drm/msm/msm_gpu.c
@@ -164,24 +164,6 @@ int msm_gpu_hw_init(struct msm_gpu *gpu)
 	return ret;
 }
 
-static void update_fences(struct msm_gpu *gpu, struct msm_ringbuffer *ring,
-		uint32_t fence)
-{
-	struct msm_gem_submit *submit;
-	unsigned long flags;
-
-	spin_lock_irqsave(&ring->submit_lock, flags);
-	list_for_each_entry(submit, &ring->submits, node) {
-		if (fence_after(submit->seqno, fence))
-			break;
-
-		msm_update_fence(submit->ring->fctx,
-			submit->hw_fence->seqno);
-		dma_fence_signal(submit->hw_fence);
-	}
-	spin_unlock_irqrestore(&ring->submit_lock, flags);
-}
-
 #ifdef CONFIG_DEV_COREDUMP
 static ssize_t msm_gpu_devcoredump_read(char *buffer, loff_t offset,
 		size_t count, void *data, size_t datalen)
@@ -436,9 +418,9 @@ static void recover_worker(struct kthread_work *work)
 		 * one more to clear the faulting submit
 		 */
 		if (ring == cur_ring)
-			fence++;
+			ring->memptrs->fence = ++fence;
 
-		update_fences(gpu, ring, fence);
+		msm_update_fence(ring->fctx, fence);
 	}
 
 	if (msm_gpu_active(gpu)) {
@@ -672,7 +654,6 @@ static void retire_submit(struct msm_gpu *gpu, struct msm_ringbuffer *ring,
 	msm_submit_retire(submit);
 
 	pm_runtime_mark_last_busy(&gpu->pdev->dev);
-	pm_runtime_put_autosuspend(&gpu->pdev->dev);
 
 	spin_lock_irqsave(&ring->submit_lock, flags);
 	list_del(&submit->node);
@@ -686,6 +667,8 @@ static void retire_submit(struct msm_gpu *gpu, struct msm_ringbuffer *ring,
 		msm_devfreq_idle(gpu);
 	mutex_unlock(&gpu->active_lock);
 
+	pm_runtime_put_autosuspend(&gpu->pdev->dev);
+
 	msm_gem_submit_put(submit);
 }
 
@@ -735,7 +718,7 @@ void msm_gpu_retire(struct msm_gpu *gpu)
 	int i;
 
 	for (i = 0; i < gpu->nr_rings; i++)
-		update_fences(gpu, gpu->rb[i], gpu->rb[i]->memptrs->fence);
+		msm_update_fence(gpu->rb[i]->fctx, gpu->rb[i]->memptrs->fence);
 
 	kthread_queue_work(gpu->worker, &gpu->retire_work);
 	update_sw_cntrs(gpu);
diff --git a/drivers/gpu/drm/msm/msm_iommu.c b/drivers/gpu/drm/msm/msm_iommu.c
index bcaddbba564d..a54ed354578b 100644
--- a/drivers/gpu/drm/msm/msm_iommu.c
+++ b/drivers/gpu/drm/msm/msm_iommu.c
@@ -58,7 +58,7 @@ static int msm_iommu_pagetable_map(struct msm_mmu *mmu, u64 iova,
 	u64 addr = iova;
 	unsigned int i;
 
-	for_each_sg(sgt->sgl, sg, sgt->nents, i) {
+	for_each_sgtable_sg(sgt, sg, i) {
 		size_t size = sg->length;
 		phys_addr_t phys = sg_phys(sg);
 
diff --git a/drivers/gpu/drm/msm/msm_ringbuffer.c b/drivers/gpu/drm/msm/msm_ringbuffer.c
index 43066320ff8c..56eecb4a72dc 100644
--- a/drivers/gpu/drm/msm/msm_ringbuffer.c
+++ b/drivers/gpu/drm/msm/msm_ringbuffer.c
@@ -25,7 +25,7 @@ static struct dma_fence *msm_job_run(struct drm_sched_job *job)
 
 		msm_gem_lock(obj);
 		msm_gem_unpin_vma_fenced(submit->bos[i].vma, fctx);
-		submit->bos[i].flags &= ~BO_PINNED;
+		submit->bos[i].flags &= ~BO_VMA_PINNED;
 		msm_gem_unlock(obj);
 	}
 
diff --git a/drivers/gpu/drm/sun4i/sun4i_drv.c b/drivers/gpu/drm/sun4i/sun4i_drv.c
index 275f7e4a03ae..6eb1aabdb161 100644
--- a/drivers/gpu/drm/sun4i/sun4i_drv.c
+++ b/drivers/gpu/drm/sun4i/sun4i_drv.c
@@ -7,6 +7,7 @@
  */
 
 #include <linux/component.h>
+#include <linux/dma-mapping.h>
 #include <linux/kfifo.h>
 #include <linux/module.h>
 #include <linux/of_graph.h>
@@ -73,7 +74,6 @@ static int sun4i_drv_bind(struct device *dev)
 		goto free_drm;
 	}
 
-	dev_set_drvdata(dev, drm);
 	drm->dev_private = drv;
 	INIT_LIST_HEAD(&drv->frontend_list);
 	INIT_LIST_HEAD(&drv->engine_list);
@@ -114,6 +114,8 @@ static int sun4i_drv_bind(struct device *dev)
 
 	drm_fbdev_generic_setup(drm, 32);
 
+	dev_set_drvdata(dev, drm);
+
 	return 0;
 
 finish_poll:
@@ -130,6 +132,7 @@ static void sun4i_drv_unbind(struct device *dev)
 {
 	struct drm_device *drm = dev_get_drvdata(dev);
 
+	dev_set_drvdata(dev, NULL);
 	drm_dev_unregister(drm);
 	drm_kms_helper_poll_fini(drm);
 	drm_atomic_helper_shutdown(drm);
@@ -367,6 +370,13 @@ static int sun4i_drv_probe(struct platform_device *pdev)
 
 	INIT_KFIFO(list.fifo);
 
+	/*
+	 * DE2 and DE3 cores actually supports 40-bit addresses, but
+	 * driver does not.
+	 */
+	dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32));
+	dma_set_max_seg_size(&pdev->dev, UINT_MAX);
+
 	for (i = 0;; i++) {
 		struct device_node *pipeline = of_parse_phandle(np,
 								"allwinner,pipelines",
diff --git a/drivers/gpu/drm/sun4i/sun4i_layer.c b/drivers/gpu/drm/sun4i/sun4i_layer.c
index 6d43080791a0..85fb9e800ddf 100644
--- a/drivers/gpu/drm/sun4i/sun4i_layer.c
+++ b/drivers/gpu/drm/sun4i/sun4i_layer.c
@@ -117,7 +117,7 @@ static bool sun4i_layer_format_mod_supported(struct drm_plane *plane,
 	struct sun4i_layer *layer = plane_to_sun4i_layer(plane);
 
 	if (IS_ERR_OR_NULL(layer->backend->frontend))
-		sun4i_backend_format_is_supported(format, modifier);
+		return sun4i_backend_format_is_supported(format, modifier);
 
 	return sun4i_backend_format_is_supported(format, modifier) ||
 	       sun4i_frontend_format_is_supported(format, modifier);
diff --git a/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.c b/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.c
index a8d75fd7e9f4..477cb6985b4d 100644
--- a/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.c
+++ b/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.c
@@ -93,34 +93,10 @@ crtcs_exit:
 	return crtcs;
 }
 
-static int sun8i_dw_hdmi_find_connector_pdev(struct device *dev,
-					     struct platform_device **pdev_out)
-{
-	struct platform_device *pdev;
-	struct device_node *remote;
-
-	remote = of_graph_get_remote_node(dev->of_node, 1, -1);
-	if (!remote)
-		return -ENODEV;
-
-	if (!of_device_is_compatible(remote, "hdmi-connector")) {
-		of_node_put(remote);
-		return -ENODEV;
-	}
-
-	pdev = of_find_device_by_node(remote);
-	of_node_put(remote);
-	if (!pdev)
-		return -ENODEV;
-
-	*pdev_out = pdev;
-	return 0;
-}
-
 static int sun8i_dw_hdmi_bind(struct device *dev, struct device *master,
 			      void *data)
 {
-	struct platform_device *pdev = to_platform_device(dev), *connector_pdev;
+	struct platform_device *pdev = to_platform_device(dev);
 	struct dw_hdmi_plat_data *plat_data;
 	struct drm_device *drm = data;
 	struct device_node *phy_node;
@@ -167,30 +143,16 @@ static int sun8i_dw_hdmi_bind(struct device *dev, struct device *master,
 		return dev_err_probe(dev, PTR_ERR(hdmi->regulator),
 				     "Couldn't get regulator\n");
 
-	ret = sun8i_dw_hdmi_find_connector_pdev(dev, &connector_pdev);
-	if (!ret) {
-		hdmi->ddc_en = gpiod_get_optional(&connector_pdev->dev,
-						  "ddc-en", GPIOD_OUT_HIGH);
-		platform_device_put(connector_pdev);
-
-		if (IS_ERR(hdmi->ddc_en)) {
-			dev_err(dev, "Couldn't get ddc-en gpio\n");
-			return PTR_ERR(hdmi->ddc_en);
-		}
-	}
-
 	ret = regulator_enable(hdmi->regulator);
 	if (ret) {
 		dev_err(dev, "Failed to enable regulator\n");
-		goto err_unref_ddc_en;
+		return ret;
 	}
 
-	gpiod_set_value(hdmi->ddc_en, 1);
-
 	ret = reset_control_deassert(hdmi->rst_ctrl);
 	if (ret) {
 		dev_err(dev, "Could not deassert ctrl reset control\n");
-		goto err_disable_ddc_en;
+		goto err_disable_regulator;
 	}
 
 	ret = clk_prepare_enable(hdmi->clk_tmds);
@@ -245,12 +207,8 @@ err_disable_clk_tmds:
 	clk_disable_unprepare(hdmi->clk_tmds);
 err_assert_ctrl_reset:
 	reset_control_assert(hdmi->rst_ctrl);
-err_disable_ddc_en:
-	gpiod_set_value(hdmi->ddc_en, 0);
+err_disable_regulator:
 	regulator_disable(hdmi->regulator);
-err_unref_ddc_en:
-	if (hdmi->ddc_en)
-		gpiod_put(hdmi->ddc_en);
 
 	return ret;
 }
@@ -264,11 +222,7 @@ static void sun8i_dw_hdmi_unbind(struct device *dev, struct device *master,
 	sun8i_hdmi_phy_deinit(hdmi->phy);
 	clk_disable_unprepare(hdmi->clk_tmds);
 	reset_control_assert(hdmi->rst_ctrl);
-	gpiod_set_value(hdmi->ddc_en, 0);
 	regulator_disable(hdmi->regulator);
-
-	if (hdmi->ddc_en)
-		gpiod_put(hdmi->ddc_en);
 }
 
 static const struct component_ops sun8i_dw_hdmi_ops = {
diff --git a/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.h b/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.h
index bffe1b9cd3dc..9ad09522947a 100644
--- a/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.h
+++ b/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.h
@@ -9,7 +9,6 @@
 #include <drm/bridge/dw_hdmi.h>
 #include <drm/drm_encoder.h>
 #include <linux/clk.h>
-#include <linux/gpio/consumer.h>
 #include <linux/regmap.h>
 #include <linux/regulator/consumer.h>
 #include <linux/reset.h>
@@ -193,7 +192,6 @@ struct sun8i_dw_hdmi {
 	struct regulator		*regulator;
 	const struct sun8i_dw_hdmi_quirks *quirks;
 	struct reset_control		*rst_ctrl;
-	struct gpio_desc		*ddc_en;
 };
 
 extern struct platform_driver sun8i_hdmi_phy_driver;
diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index 75d308ec173d..406e9c324e76 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -109,11 +109,11 @@ void ttm_bo_set_bulk_move(struct ttm_buffer_object *bo,
 		return;
 
 	spin_lock(&bo->bdev->lru_lock);
-	if (bo->bulk_move && bo->resource)
-		ttm_lru_bulk_move_del(bo->bulk_move, bo->resource);
+	if (bo->resource)
+		ttm_resource_del_bulk_move(bo->resource, bo);
 	bo->bulk_move = bulk;
-	if (bo->bulk_move && bo->resource)
-		ttm_lru_bulk_move_add(bo->bulk_move, bo->resource);
+	if (bo->resource)
+		ttm_resource_add_bulk_move(bo->resource, bo);
 	spin_unlock(&bo->bdev->lru_lock);
 }
 EXPORT_SYMBOL(ttm_bo_set_bulk_move);
@@ -689,8 +689,11 @@ void ttm_bo_pin(struct ttm_buffer_object *bo)
 {
 	dma_resv_assert_held(bo->base.resv);
 	WARN_ON_ONCE(!kref_read(&bo->kref));
-	if (!(bo->pin_count++) && bo->bulk_move && bo->resource)
-		ttm_lru_bulk_move_del(bo->bulk_move, bo->resource);
+	spin_lock(&bo->bdev->lru_lock);
+	if (bo->resource)
+		ttm_resource_del_bulk_move(bo->resource, bo);
+	++bo->pin_count;
+	spin_unlock(&bo->bdev->lru_lock);
 }
 EXPORT_SYMBOL(ttm_bo_pin);
 
@@ -707,8 +710,11 @@ void ttm_bo_unpin(struct ttm_buffer_object *bo)
 	if (WARN_ON_ONCE(!bo->pin_count))
 		return;
 
-	if (!(--bo->pin_count) && bo->bulk_move && bo->resource)
-		ttm_lru_bulk_move_add(bo->bulk_move, bo->resource);
+	spin_lock(&bo->bdev->lru_lock);
+	--bo->pin_count;
+	if (bo->resource)
+		ttm_resource_add_bulk_move(bo->resource, bo);
+	spin_unlock(&bo->bdev->lru_lock);
 }
 EXPORT_SYMBOL(ttm_bo_unpin);
 
diff --git a/drivers/gpu/drm/ttm/ttm_device.c b/drivers/gpu/drm/ttm/ttm_device.c
index a0562ab386f5..e7147e304637 100644
--- a/drivers/gpu/drm/ttm/ttm_device.c
+++ b/drivers/gpu/drm/ttm/ttm_device.c
@@ -156,8 +156,12 @@ int ttm_device_swapout(struct ttm_device *bdev, struct ttm_operation_ctx *ctx,
 
 		ttm_resource_manager_for_each_res(man, &cursor, res) {
 			struct ttm_buffer_object *bo = res->bo;
-			uint32_t num_pages = PFN_UP(bo->base.size);
+			uint32_t num_pages;
 
+			if (!bo)
+				continue;
+
+			num_pages = PFN_UP(bo->base.size);
 			ret = ttm_bo_swapout(bo, ctx, gfp_flags);
 			/* ttm_bo_swapout has dropped the lru_lock */
 			if (!ret)
diff --git a/drivers/gpu/drm/ttm/ttm_resource.c b/drivers/gpu/drm/ttm/ttm_resource.c
index 65889b3caf50..20f9adcc3235 100644
--- a/drivers/gpu/drm/ttm/ttm_resource.c
+++ b/drivers/gpu/drm/ttm/ttm_resource.c
@@ -91,8 +91,8 @@ static void ttm_lru_bulk_move_pos_tail(struct ttm_lru_bulk_move_pos *pos,
 }
 
 /* Add the resource to a bulk_move cursor */
-void ttm_lru_bulk_move_add(struct ttm_lru_bulk_move *bulk,
-			   struct ttm_resource *res)
+static void ttm_lru_bulk_move_add(struct ttm_lru_bulk_move *bulk,
+				  struct ttm_resource *res)
 {
 	struct ttm_lru_bulk_move_pos *pos = ttm_lru_bulk_move_pos(bulk, res);
 
@@ -105,8 +105,8 @@ void ttm_lru_bulk_move_add(struct ttm_lru_bulk_move *bulk,
 }
 
 /* Remove the resource from a bulk_move range */
-void ttm_lru_bulk_move_del(struct ttm_lru_bulk_move *bulk,
-			   struct ttm_resource *res)
+static void ttm_lru_bulk_move_del(struct ttm_lru_bulk_move *bulk,
+				  struct ttm_resource *res)
 {
 	struct ttm_lru_bulk_move_pos *pos = ttm_lru_bulk_move_pos(bulk, res);
 
@@ -122,6 +122,22 @@ void ttm_lru_bulk_move_del(struct ttm_lru_bulk_move *bulk,
 	}
 }
 
+/* Add the resource to a bulk move if the BO is configured for it */
+void ttm_resource_add_bulk_move(struct ttm_resource *res,
+				struct ttm_buffer_object *bo)
+{
+	if (bo->bulk_move && !bo->pin_count)
+		ttm_lru_bulk_move_add(bo->bulk_move, res);
+}
+
+/* Remove the resource from a bulk move if the BO is configured for it */
+void ttm_resource_del_bulk_move(struct ttm_resource *res,
+				struct ttm_buffer_object *bo)
+{
+	if (bo->bulk_move && !bo->pin_count)
+		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)
 {
@@ -169,15 +185,14 @@ void ttm_resource_init(struct ttm_buffer_object *bo,
 	res->bus.is_iomem = false;
 	res->bus.caching = ttm_cached;
 	res->bo = bo;
-	INIT_LIST_HEAD(&res->lru);
 
 	man = ttm_manager_type(bo->bdev, place->mem_type);
 	spin_lock(&bo->bdev->lru_lock);
-	man->usage += res->num_pages << PAGE_SHIFT;
-	if (bo->bulk_move)
-		ttm_lru_bulk_move_add(bo->bulk_move, res);
+	if (bo->pin_count)
+		list_add_tail(&res->lru, &bo->bdev->pinned);
 	else
-		ttm_resource_move_to_lru_tail(res);
+		list_add_tail(&res->lru, &man->lru[bo->priority]);
+	man->usage += res->num_pages << PAGE_SHIFT;
 	spin_unlock(&bo->bdev->lru_lock);
 }
 EXPORT_SYMBOL(ttm_resource_init);
@@ -210,8 +225,16 @@ int ttm_resource_alloc(struct ttm_buffer_object *bo,
 {
 	struct ttm_resource_manager *man =
 		ttm_manager_type(bo->bdev, place->mem_type);
+	int ret;
+
+	ret = man->func->alloc(man, bo, place, res_ptr);
+	if (ret)
+		return ret;
 
-	return man->func->alloc(man, bo, place, res_ptr);
+	spin_lock(&bo->bdev->lru_lock);
+	ttm_resource_add_bulk_move(*res_ptr, bo);
+	spin_unlock(&bo->bdev->lru_lock);
+	return 0;
 }
 
 void ttm_resource_free(struct ttm_buffer_object *bo, struct ttm_resource **res)
@@ -221,12 +244,9 @@ void ttm_resource_free(struct ttm_buffer_object *bo, struct ttm_resource **res)
 	if (!*res)
 		return;
 
-	if (bo->bulk_move) {
-		spin_lock(&bo->bdev->lru_lock);
-		ttm_lru_bulk_move_del(bo->bulk_move, *res);
-		spin_unlock(&bo->bdev->lru_lock);
-	}
-
+	spin_lock(&bo->bdev->lru_lock);
+	ttm_resource_del_bulk_move(*res, bo);
+	spin_unlock(&bo->bdev->lru_lock);
 	man = ttm_manager_type(bo->bdev, (*res)->mem_type);
 	man->func->free(man, *res);
 	*res = NULL;
diff --git a/drivers/gpu/drm/vc4/vc4_bo.c b/drivers/gpu/drm/vc4/vc4_bo.c
index 49c0f2ac868b..b8d856312846 100644
--- a/drivers/gpu/drm/vc4/vc4_bo.c
+++ b/drivers/gpu/drm/vc4/vc4_bo.c
@@ -248,6 +248,9 @@ void vc4_bo_add_to_purgeable_pool(struct vc4_bo *bo)
 {
 	struct vc4_dev *vc4 = to_vc4_dev(bo->base.base.dev);
 
+	if (WARN_ON_ONCE(vc4->is_vc5))
+		return;
+
 	mutex_lock(&vc4->purgeable.lock);
 	list_add_tail(&bo->size_head, &vc4->purgeable.list);
 	vc4->purgeable.num++;
@@ -259,6 +262,9 @@ static void vc4_bo_remove_from_purgeable_pool_locked(struct vc4_bo *bo)
 {
 	struct vc4_dev *vc4 = to_vc4_dev(bo->base.base.dev);
 
+	if (WARN_ON_ONCE(vc4->is_vc5))
+		return;
+
 	/* list_del_init() is used here because the caller might release
 	 * the purgeable lock in order to acquire the madv one and update the
 	 * madv status.
@@ -387,6 +393,9 @@ struct drm_gem_object *vc4_create_object(struct drm_device *dev, size_t size)
 	struct vc4_dev *vc4 = to_vc4_dev(dev);
 	struct vc4_bo *bo;
 
+	if (WARN_ON_ONCE(vc4->is_vc5))
+		return ERR_PTR(-ENODEV);
+
 	bo = kzalloc(sizeof(*bo), GFP_KERNEL);
 	if (!bo)
 		return ERR_PTR(-ENOMEM);
@@ -413,6 +422,9 @@ struct vc4_bo *vc4_bo_create(struct drm_device *dev, size_t unaligned_size,
 	struct drm_gem_cma_object *cma_obj;
 	struct vc4_bo *bo;
 
+	if (WARN_ON_ONCE(vc4->is_vc5))
+		return ERR_PTR(-ENODEV);
+
 	if (size == 0)
 		return ERR_PTR(-EINVAL);
 
@@ -471,19 +483,20 @@ struct vc4_bo *vc4_bo_create(struct drm_device *dev, size_t unaligned_size,
 	return bo;
 }
 
-int vc4_dumb_create(struct drm_file *file_priv,
-		    struct drm_device *dev,
-		    struct drm_mode_create_dumb *args)
+int vc4_bo_dumb_create(struct drm_file *file_priv,
+		       struct drm_device *dev,
+		       struct drm_mode_create_dumb *args)
 {
-	int min_pitch = DIV_ROUND_UP(args->width * args->bpp, 8);
+	struct vc4_dev *vc4 = to_vc4_dev(dev);
 	struct vc4_bo *bo = NULL;
 	int ret;
 
-	if (args->pitch < min_pitch)
-		args->pitch = min_pitch;
+	if (WARN_ON_ONCE(vc4->is_vc5))
+		return -ENODEV;
 
-	if (args->size < args->pitch * args->height)
-		args->size = args->pitch * args->height;
+	ret = vc4_dumb_fixup_args(args);
+	if (ret)
+		return ret;
 
 	bo = vc4_bo_create(dev, args->size, false, VC4_BO_TYPE_DUMB);
 	if (IS_ERR(bo))
@@ -601,8 +614,12 @@ static void vc4_bo_cache_time_work(struct work_struct *work)
 
 int vc4_bo_inc_usecnt(struct vc4_bo *bo)
 {
+	struct vc4_dev *vc4 = to_vc4_dev(bo->base.base.dev);
 	int ret;
 
+	if (WARN_ON_ONCE(vc4->is_vc5))
+		return -ENODEV;
+
 	/* Fast path: if the BO is already retained by someone, no need to
 	 * check the madv status.
 	 */
@@ -637,6 +654,11 @@ int vc4_bo_inc_usecnt(struct vc4_bo *bo)
 
 void vc4_bo_dec_usecnt(struct vc4_bo *bo)
 {
+	struct vc4_dev *vc4 = to_vc4_dev(bo->base.base.dev);
+
+	if (WARN_ON_ONCE(vc4->is_vc5))
+		return;
+
 	/* Fast path: if the BO is still retained by someone, no need to test
 	 * the madv value.
 	 */
@@ -756,6 +778,9 @@ int vc4_create_bo_ioctl(struct drm_device *dev, void *data,
 	struct vc4_bo *bo = NULL;
 	int ret;
 
+	if (WARN_ON_ONCE(vc4->is_vc5))
+		return -ENODEV;
+
 	ret = vc4_grab_bin_bo(vc4, vc4file);
 	if (ret)
 		return ret;
@@ -779,9 +804,13 @@ int vc4_create_bo_ioctl(struct drm_device *dev, void *data,
 int vc4_mmap_bo_ioctl(struct drm_device *dev, void *data,
 		      struct drm_file *file_priv)
 {
+	struct vc4_dev *vc4 = to_vc4_dev(dev);
 	struct drm_vc4_mmap_bo *args = data;
 	struct drm_gem_object *gem_obj;
 
+	if (WARN_ON_ONCE(vc4->is_vc5))
+		return -ENODEV;
+
 	gem_obj = drm_gem_object_lookup(file_priv, args->handle);
 	if (!gem_obj) {
 		DRM_DEBUG("Failed to look up GEM BO %d\n", args->handle);
@@ -805,6 +834,9 @@ vc4_create_shader_bo_ioctl(struct drm_device *dev, void *data,
 	struct vc4_bo *bo = NULL;
 	int ret;
 
+	if (WARN_ON_ONCE(vc4->is_vc5))
+		return -ENODEV;
+
 	if (args->size == 0)
 		return -EINVAL;
 
@@ -875,11 +907,15 @@ fail:
 int vc4_set_tiling_ioctl(struct drm_device *dev, void *data,
 			 struct drm_file *file_priv)
 {
+	struct vc4_dev *vc4 = to_vc4_dev(dev);
 	struct drm_vc4_set_tiling *args = data;
 	struct drm_gem_object *gem_obj;
 	struct vc4_bo *bo;
 	bool t_format;
 
+	if (WARN_ON_ONCE(vc4->is_vc5))
+		return -ENODEV;
+
 	if (args->flags != 0)
 		return -EINVAL;
 
@@ -918,10 +954,14 @@ int vc4_set_tiling_ioctl(struct drm_device *dev, void *data,
 int vc4_get_tiling_ioctl(struct drm_device *dev, void *data,
 			 struct drm_file *file_priv)
 {
+	struct vc4_dev *vc4 = to_vc4_dev(dev);
 	struct drm_vc4_get_tiling *args = data;
 	struct drm_gem_object *gem_obj;
 	struct vc4_bo *bo;
 
+	if (WARN_ON_ONCE(vc4->is_vc5))
+		return -ENODEV;
+
 	if (args->flags != 0 || args->modifier != 0)
 		return -EINVAL;
 
@@ -948,6 +988,9 @@ int vc4_bo_cache_init(struct drm_device *dev)
 	struct vc4_dev *vc4 = to_vc4_dev(dev);
 	int i;
 
+	if (WARN_ON_ONCE(vc4->is_vc5))
+		return -ENODEV;
+
 	/* Create the initial set of BO labels that the kernel will
 	 * use.  This lets us avoid a bunch of string reallocation in
 	 * the kernel's draw and BO allocation paths.
@@ -1007,6 +1050,9 @@ int vc4_label_bo_ioctl(struct drm_device *dev, void *data,
 	struct drm_gem_object *gem_obj;
 	int ret = 0, label;
 
+	if (WARN_ON_ONCE(vc4->is_vc5))
+		return -ENODEV;
+
 	if (!args->len)
 		return -EINVAL;
 
diff --git a/drivers/gpu/drm/vc4/vc4_crtc.c b/drivers/gpu/drm/vc4/vc4_crtc.c
index 59b20c8f132b..9355213dc883 100644
--- a/drivers/gpu/drm/vc4/vc4_crtc.c
+++ b/drivers/gpu/drm/vc4/vc4_crtc.c
@@ -256,7 +256,7 @@ static u32 vc4_get_fifo_full_level(struct vc4_crtc *vc4_crtc, u32 format)
 		 * Removing 1 from the FIFO full level however
 		 * seems to completely remove that issue.
 		 */
-		if (!vc4->hvs->hvs5)
+		if (!vc4->is_vc5)
 			return fifo_len_bytes - 3 * HVS_FIFO_LATENCY_PIX - 1;
 
 		return fifo_len_bytes - 3 * HVS_FIFO_LATENCY_PIX;
@@ -389,7 +389,7 @@ static void vc4_crtc_config_pv(struct drm_crtc *crtc, struct drm_encoder *encode
 	if (is_dsi)
 		CRTC_WRITE(PV_HACT_ACT, mode->hdisplay * pixel_rep);
 
-	if (vc4->hvs->hvs5)
+	if (vc4->is_vc5)
 		CRTC_WRITE(PV_MUX_CFG,
 			   VC4_SET_FIELD(PV_MUX_CFG_RGB_PIXEL_MUX_MODE_NO_SWAP,
 					 PV_MUX_CFG_RGB_PIXEL_MUX_MODE));
@@ -775,17 +775,18 @@ struct vc4_async_flip_state {
 	struct drm_framebuffer *old_fb;
 	struct drm_pending_vblank_event *event;
 
-	struct vc4_seqno_cb cb;
+	union {
+		struct dma_fence_cb fence;
+		struct vc4_seqno_cb seqno;
+	} cb;
 };
 
 /* Called when the V3D execution for the BO being flipped to is done, so that
  * we can actually update the plane's address to point to it.
  */
 static void
-vc4_async_page_flip_complete(struct vc4_seqno_cb *cb)
+vc4_async_page_flip_complete(struct vc4_async_flip_state *flip_state)
 {
-	struct vc4_async_flip_state *flip_state =
-		container_of(cb, struct vc4_async_flip_state, cb);
 	struct drm_crtc *crtc = flip_state->crtc;
 	struct drm_device *dev = crtc->dev;
 	struct drm_plane *plane = crtc->primary;
@@ -802,59 +803,96 @@ vc4_async_page_flip_complete(struct vc4_seqno_cb *cb)
 	drm_crtc_vblank_put(crtc);
 	drm_framebuffer_put(flip_state->fb);
 
-	/* Decrement the BO usecnt in order to keep the inc/dec calls balanced
-	 * when the planes are updated through the async update path.
-	 * FIXME: we should move to generic async-page-flip when it's
-	 * available, so that we can get rid of this hand-made cleanup_fb()
-	 * logic.
-	 */
-	if (flip_state->old_fb) {
-		struct drm_gem_cma_object *cma_bo;
-		struct vc4_bo *bo;
+	if (flip_state->old_fb)
+		drm_framebuffer_put(flip_state->old_fb);
+
+	kfree(flip_state);
+}
+
+static void vc4_async_page_flip_seqno_complete(struct vc4_seqno_cb *cb)
+{
+	struct vc4_async_flip_state *flip_state =
+		container_of(cb, struct vc4_async_flip_state, cb.seqno);
+	struct vc4_bo *bo = NULL;
 
-		cma_bo = drm_fb_cma_get_gem_obj(flip_state->old_fb, 0);
+	if (flip_state->old_fb) {
+		struct drm_gem_cma_object *cma_bo =
+			drm_fb_cma_get_gem_obj(flip_state->old_fb, 0);
 		bo = to_vc4_bo(&cma_bo->base);
-		vc4_bo_dec_usecnt(bo);
-		drm_framebuffer_put(flip_state->old_fb);
 	}
 
-	kfree(flip_state);
+	vc4_async_page_flip_complete(flip_state);
+
+	/*
+	 * Decrement the BO usecnt in order to keep the inc/dec
+	 * calls balanced when the planes are updated through
+	 * the async update path.
+	 *
+	 * FIXME: we should move to generic async-page-flip when
+	 * it's available, so that we can get rid of this
+	 * hand-made cleanup_fb() logic.
+	 */
+	if (bo)
+		vc4_bo_dec_usecnt(bo);
 }
 
-/* Implements async (non-vblank-synced) page flips.
- *
- * The page flip ioctl needs to return immediately, so we grab the
- * modeset semaphore on the pipe, and queue the address update for
- * when V3D is done with the BO being flipped to.
- */
-static int vc4_async_page_flip(struct drm_crtc *crtc,
-			       struct drm_framebuffer *fb,
-			       struct drm_pending_vblank_event *event,
-			       uint32_t flags)
+static void vc4_async_page_flip_fence_complete(struct dma_fence *fence,
+					       struct dma_fence_cb *cb)
 {
-	struct drm_device *dev = crtc->dev;
-	struct drm_plane *plane = crtc->primary;
-	int ret = 0;
-	struct vc4_async_flip_state *flip_state;
+	struct vc4_async_flip_state *flip_state =
+		container_of(cb, struct vc4_async_flip_state, cb.fence);
+
+	vc4_async_page_flip_complete(flip_state);
+	dma_fence_put(fence);
+}
+
+static int vc4_async_set_fence_cb(struct drm_device *dev,
+				  struct vc4_async_flip_state *flip_state)
+{
+	struct drm_framebuffer *fb = flip_state->fb;
 	struct drm_gem_cma_object *cma_bo = drm_fb_cma_get_gem_obj(fb, 0);
-	struct vc4_bo *bo = to_vc4_bo(&cma_bo->base);
+	struct vc4_dev *vc4 = to_vc4_dev(dev);
+	struct dma_fence *fence;
+	int ret;
 
-	/* Increment the BO usecnt here, so that we never end up with an
-	 * unbalanced number of vc4_bo_{dec,inc}_usecnt() calls when the
-	 * plane is later updated through the non-async path.
-	 * FIXME: we should move to generic async-page-flip when it's
-	 * available, so that we can get rid of this hand-made prepare_fb()
-	 * logic.
-	 */
-	ret = vc4_bo_inc_usecnt(bo);
+	if (!vc4->is_vc5) {
+		struct vc4_bo *bo = to_vc4_bo(&cma_bo->base);
+
+		return vc4_queue_seqno_cb(dev, &flip_state->cb.seqno, bo->seqno,
+					  vc4_async_page_flip_seqno_complete);
+	}
+
+	ret = dma_resv_get_singleton(cma_bo->base.resv, DMA_RESV_USAGE_READ, &fence);
 	if (ret)
 		return ret;
 
+	/* If there's no fence, complete the page flip immediately */
+	if (!fence) {
+		vc4_async_page_flip_fence_complete(fence, &flip_state->cb.fence);
+		return 0;
+	}
+
+	/* If the fence has already been completed, complete the page flip */
+	if (dma_fence_add_callback(fence, &flip_state->cb.fence,
+				   vc4_async_page_flip_fence_complete))
+		vc4_async_page_flip_fence_complete(fence, &flip_state->cb.fence);
+
+	return 0;
+}
+
+static int
+vc4_async_page_flip_common(struct drm_crtc *crtc,
+			   struct drm_framebuffer *fb,
+			   struct drm_pending_vblank_event *event,
+			   uint32_t flags)
+{
+	struct drm_device *dev = crtc->dev;
+	struct drm_plane *plane = crtc->primary;
+	struct vc4_async_flip_state *flip_state;
+
 	flip_state = kzalloc(sizeof(*flip_state), GFP_KERNEL);
-	if (!flip_state) {
-		vc4_bo_dec_usecnt(bo);
+	if (!flip_state)
 		return -ENOMEM;
-	}
 
 	drm_framebuffer_get(fb);
 	flip_state->fb = fb;
@@ -881,23 +919,79 @@ static int vc4_async_page_flip(struct drm_crtc *crtc,
 	 */
 	drm_atomic_set_fb_for_plane(plane->state, fb);
 
-	vc4_queue_seqno_cb(dev, &flip_state->cb, bo->seqno,
-			   vc4_async_page_flip_complete);
+	vc4_async_set_fence_cb(dev, flip_state);
 
 	/* Driver takes ownership of state on successful async commit. */
 	return 0;
 }
 
+/* Implements async (non-vblank-synced) page flips.
+ *
+ * The page flip ioctl needs to return immediately, so we grab the
+ * modeset semaphore on the pipe, and queue the address update for
+ * when V3D is done with the BO being flipped to.
+ */
+static int vc4_async_page_flip(struct drm_crtc *crtc,
+			       struct drm_framebuffer *fb,
+			       struct drm_pending_vblank_event *event,
+			       uint32_t flags)
+{
+	struct drm_device *dev = crtc->dev;
+	struct vc4_dev *vc4 = to_vc4_dev(dev);
+	struct drm_gem_cma_object *cma_bo = drm_fb_cma_get_gem_obj(fb, 0);
+	struct vc4_bo *bo = to_vc4_bo(&cma_bo->base);
+	int ret;
+
+	if (WARN_ON_ONCE(vc4->is_vc5))
+		return -ENODEV;
+
+	/*
+	 * Increment the BO usecnt here, so that we never end up with an
+	 * unbalanced number of vc4_bo_{dec,inc}_usecnt() calls when the
+	 * plane is later updated through the non-async path.
+	 *
+	 * FIXME: we should move to generic async-page-flip when
+	 * it's available, so that we can get rid of this
+	 * hand-made prepare_fb() logic.
+	 */
+	ret = vc4_bo_inc_usecnt(bo);
+	if (ret)
+		return ret;
+
+	ret = vc4_async_page_flip_common(crtc, fb, event, flags);
+	if (ret) {
+		vc4_bo_dec_usecnt(bo);
+		return ret;
+	}
+
+	return 0;
+}
+
+static int vc5_async_page_flip(struct drm_crtc *crtc,
+			       struct drm_framebuffer *fb,
+			       struct drm_pending_vblank_event *event,
+			       uint32_t flags)
+{
+	return vc4_async_page_flip_common(crtc, fb, event, flags);
+}
+
 int vc4_page_flip(struct drm_crtc *crtc,
 		  struct drm_framebuffer *fb,
 		  struct drm_pending_vblank_event *event,
 		  uint32_t flags,
 		  struct drm_modeset_acquire_ctx *ctx)
 {
-	if (flags & DRM_MODE_PAGE_FLIP_ASYNC)
-		return vc4_async_page_flip(crtc, fb, event, flags);
-	else
+	if (flags & DRM_MODE_PAGE_FLIP_ASYNC) {
+		struct drm_device *dev = crtc->dev;
+		struct vc4_dev *vc4 = to_vc4_dev(dev);
+
+		if (vc4->is_vc5)
+			return vc5_async_page_flip(crtc, fb, event, flags);
+		else
+			return vc4_async_page_flip(crtc, fb, event, flags);
+	} else {
 		return drm_atomic_helper_page_flip(crtc, fb, event, flags, ctx);
+	}
 }
 
 struct drm_crtc_state *vc4_crtc_duplicate_state(struct drm_crtc *crtc)
@@ -1149,7 +1243,7 @@ int vc4_crtc_init(struct drm_device *drm, struct vc4_crtc *vc4_crtc,
 				  crtc_funcs, NULL);
 	drm_crtc_helper_add(crtc, crtc_helper_funcs);
 
-	if (!vc4->hvs->hvs5) {
+	if (!vc4->is_vc5) {
 		drm_mode_crtc_set_gamma_size(crtc, ARRAY_SIZE(vc4_crtc->lut_r));
 
 		drm_crtc_enable_color_mgmt(crtc, 0, false, crtc->gamma_size);
diff --git a/drivers/gpu/drm/vc4/vc4_drv.c b/drivers/gpu/drm/vc4/vc4_drv.c
index 162bc18e7497..0f0f0263e744 100644
--- a/drivers/gpu/drm/vc4/vc4_drv.c
+++ b/drivers/gpu/drm/vc4/vc4_drv.c
@@ -63,6 +63,32 @@ void __iomem *vc4_ioremap_regs(struct platform_device *pdev, int index)
 	return map;
 }
 
+int vc4_dumb_fixup_args(struct drm_mode_create_dumb *args)
+{
+	int min_pitch = DIV_ROUND_UP(args->width * args->bpp, 8);
+
+	if (args->pitch < min_pitch)
+		args->pitch = min_pitch;
+
+	if (args->size < args->pitch * args->height)
+		args->size = args->pitch * args->height;
+
+	return 0;
+}
+
+static int vc5_dumb_create(struct drm_file *file_priv,
+			   struct drm_device *dev,
+			   struct drm_mode_create_dumb *args)
+{
+	int ret;
+
+	ret = vc4_dumb_fixup_args(args);
+	if (ret)
+		return ret;
+
+	return drm_gem_cma_dumb_create_internal(file_priv, dev, args);
+}
+
 static int vc4_get_param_ioctl(struct drm_device *dev, void *data,
 			       struct drm_file *file_priv)
 {
@@ -73,6 +99,9 @@ static int vc4_get_param_ioctl(struct drm_device *dev, void *data,
 	if (args->pad != 0)
 		return -EINVAL;
 
+	if (WARN_ON_ONCE(vc4->is_vc5))
+		return -ENODEV;
+
 	if (!vc4->v3d)
 		return -ENODEV;
 
@@ -116,11 +145,16 @@ static int vc4_get_param_ioctl(struct drm_device *dev, void *data,
 
 static int vc4_open(struct drm_device *dev, struct drm_file *file)
 {
+	struct vc4_dev *vc4 = to_vc4_dev(dev);
 	struct vc4_file *vc4file;
 
+	if (WARN_ON_ONCE(vc4->is_vc5))
+		return -ENODEV;
+
 	vc4file = kzalloc(sizeof(*vc4file), GFP_KERNEL);
 	if (!vc4file)
 		return -ENOMEM;
+	vc4file->dev = vc4;
 
 	vc4_perfmon_open_file(vc4file);
 	file->driver_priv = vc4file;
@@ -132,6 +166,9 @@ static void vc4_close(struct drm_device *dev, struct drm_file *file)
 	struct vc4_dev *vc4 = to_vc4_dev(dev);
 	struct vc4_file *vc4file = file->driver_priv;
 
+	if (WARN_ON_ONCE(vc4->is_vc5))
+		return;
+
 	if (vc4file->bin_bo_used)
 		vc4_v3d_bin_bo_put(vc4);
 
@@ -160,7 +197,7 @@ static const struct drm_ioctl_desc vc4_drm_ioctls[] = {
 	DRM_IOCTL_DEF_DRV(VC4_PERFMON_GET_VALUES, vc4_perfmon_get_values_ioctl, DRM_RENDER_ALLOW),
 };
 
-static struct drm_driver vc4_drm_driver = {
+static const struct drm_driver vc4_drm_driver = {
 	.driver_features = (DRIVER_MODESET |
 			    DRIVER_ATOMIC |
 			    DRIVER_GEM |
@@ -175,7 +212,7 @@ static struct drm_driver vc4_drm_driver = {
 
 	.gem_create_object = vc4_create_object,
 
-	DRM_GEM_CMA_DRIVER_OPS_WITH_DUMB_CREATE(vc4_dumb_create),
+	DRM_GEM_CMA_DRIVER_OPS_WITH_DUMB_CREATE(vc4_bo_dumb_create),
 
 	.ioctls = vc4_drm_ioctls,
 	.num_ioctls = ARRAY_SIZE(vc4_drm_ioctls),
@@ -189,6 +226,27 @@ static struct drm_driver vc4_drm_driver = {
 	.patchlevel = DRIVER_PATCHLEVEL,
 };
 
+static const struct drm_driver vc5_drm_driver = {
+	.driver_features = (DRIVER_MODESET |
+			    DRIVER_ATOMIC |
+			    DRIVER_GEM),
+
+#if defined(CONFIG_DEBUG_FS)
+	.debugfs_init = vc4_debugfs_init,
+#endif
+
+	DRM_GEM_CMA_DRIVER_OPS_WITH_DUMB_CREATE(vc5_dumb_create),
+
+	.fops = &vc4_drm_fops,
+
+	.name = DRIVER_NAME,
+	.desc = DRIVER_DESC,
+	.date = DRIVER_DATE,
+	.major = DRIVER_MAJOR,
+	.minor = DRIVER_MINOR,
+	.patchlevel = DRIVER_PATCHLEVEL,
+};
+
 static void vc4_match_add_drivers(struct device *dev,
 				  struct component_match **match,
 				  struct platform_driver *const *drivers,
@@ -212,42 +270,49 @@ static void vc4_match_add_drivers(struct device *dev,
 static int vc4_drm_bind(struct device *dev)
 {
 	struct platform_device *pdev = to_platform_device(dev);
+	const struct drm_driver *driver;
 	struct rpi_firmware *firmware = NULL;
 	struct drm_device *drm;
 	struct vc4_dev *vc4;
 	struct device_node *node;
 	struct drm_crtc *crtc;
+	bool is_vc5;
 	int ret = 0;
 
 	dev->coherent_dma_mask = DMA_BIT_MASK(32);
 
-	/* If VC4 V3D is missing, don't advertise render nodes. */
-	node = of_find_matching_node_and_match(NULL, vc4_v3d_dt_match, NULL);
-	if (!node || !of_device_is_available(node))
-		vc4_drm_driver.driver_features &= ~DRIVER_RENDER;
-	of_node_put(node);
+	is_vc5 = of_device_is_compatible(dev->of_node, "brcm,bcm2711-vc5");
+	if (is_vc5)
+		driver = &vc5_drm_driver;
+	else
+		driver = &vc4_drm_driver;
 
-	vc4 = devm_drm_dev_alloc(dev, &vc4_drm_driver, struct vc4_dev, base);
+	vc4 = devm_drm_dev_alloc(dev, driver, struct vc4_dev, base);
 	if (IS_ERR(vc4))
 		return PTR_ERR(vc4);
+	vc4->is_vc5 = is_vc5;
 
 	drm = &vc4->base;
 	platform_set_drvdata(pdev, drm);
 	INIT_LIST_HEAD(&vc4->debugfs_list);
 
-	mutex_init(&vc4->bin_bo_lock);
+	if (!is_vc5) {
+		mutex_init(&vc4->bin_bo_lock);
 
-	ret = vc4_bo_cache_init(drm);
-	if (ret)
-		return ret;
+		ret = vc4_bo_cache_init(drm);
+		if (ret)
+			return ret;
+	}
 
 	ret = drmm_mode_config_init(drm);
 	if (ret)
 		return ret;
 
-	ret = vc4_gem_init(drm);
-	if (ret)
-		return ret;
+	if (!is_vc5) {
+		ret = vc4_gem_init(drm);
+		if (ret)
+			return ret;
+	}
 
 	node = of_find_compatible_node(NULL, NULL, "raspberrypi,bcm2835-firmware");
 	if (node) {
@@ -258,7 +323,7 @@ static int vc4_drm_bind(struct device *dev)
 			return -EPROBE_DEFER;
 	}
 
-	ret = drm_aperture_remove_framebuffers(false, &vc4_drm_driver);
+	ret = drm_aperture_remove_framebuffers(false, driver);
 	if (ret)
 		return ret;
 
diff --git a/drivers/gpu/drm/vc4/vc4_drv.h b/drivers/gpu/drm/vc4/vc4_drv.h
index 15e0c2ac3940..93fd55b9e99e 100644
--- a/drivers/gpu/drm/vc4/vc4_drv.h
+++ b/drivers/gpu/drm/vc4/vc4_drv.h
@@ -48,6 +48,8 @@ enum vc4_kernel_bo_type {
  * done. This way, only events related to a specific job will be counted.
  */
 struct vc4_perfmon {
+	struct vc4_dev *dev;
+
 	/* Tracks the number of users of the perfmon, when this counter reaches
 	 * zero the perfmon is destroyed.
 	 */
@@ -74,6 +76,8 @@ struct vc4_perfmon {
 struct vc4_dev {
 	struct drm_device base;
 
+	bool is_vc5;
+
 	unsigned int irq;
 
 	struct vc4_hvs *hvs;
@@ -316,6 +320,7 @@ struct vc4_v3d {
 };
 
 struct vc4_hvs {
+	struct vc4_dev *vc4;
 	struct platform_device *pdev;
 	void __iomem *regs;
 	u32 __iomem *dlist;
@@ -333,9 +338,6 @@ struct vc4_hvs {
 	struct drm_mm_node mitchell_netravali_filter;
 
 	struct debugfs_regset32 regset;
-
-	/* HVS version 5 flag, therefore requires updated dlist structures */
-	bool hvs5;
 };
 
 struct vc4_plane {
@@ -580,6 +582,8 @@ to_vc4_crtc_state(struct drm_crtc_state *crtc_state)
 #define VC4_REG32(reg) { .name = #reg, .offset = reg }
 
 struct vc4_exec_info {
+	struct vc4_dev *dev;
+
 	/* Sequence number for this bin/render job. */
 	uint64_t seqno;
 
@@ -701,6 +705,8 @@ struct vc4_exec_info {
  * released when the DRM file is closed should be placed here.
  */
 struct vc4_file {
+	struct vc4_dev *dev;
+
 	struct {
 		struct idr idr;
 		struct mutex lock;
@@ -814,9 +820,9 @@ struct vc4_validated_shader_info {
 struct drm_gem_object *vc4_create_object(struct drm_device *dev, size_t size);
 struct vc4_bo *vc4_bo_create(struct drm_device *dev, size_t size,
 			     bool from_cache, enum vc4_kernel_bo_type type);
-int vc4_dumb_create(struct drm_file *file_priv,
-		    struct drm_device *dev,
-		    struct drm_mode_create_dumb *args);
+int vc4_bo_dumb_create(struct drm_file *file_priv,
+		       struct drm_device *dev,
+		       struct drm_mode_create_dumb *args);
 int vc4_create_bo_ioctl(struct drm_device *dev, void *data,
 			struct drm_file *file_priv);
 int vc4_create_shader_bo_ioctl(struct drm_device *dev, void *data,
@@ -885,6 +891,7 @@ static inline void vc4_debugfs_add_regset32(struct drm_device *drm,
 
 /* vc4_drv.c */
 void __iomem *vc4_ioremap_regs(struct platform_device *dev, int index);
+int vc4_dumb_fixup_args(struct drm_mode_create_dumb *args);
 
 /* vc4_dpi.c */
 extern struct platform_driver vc4_dpi_driver;
diff --git a/drivers/gpu/drm/vc4/vc4_gem.c b/drivers/gpu/drm/vc4/vc4_gem.c
index 9eaf304fc20d..fe10d9c3fff8 100644
--- a/drivers/gpu/drm/vc4/vc4_gem.c
+++ b/drivers/gpu/drm/vc4/vc4_gem.c
@@ -76,6 +76,9 @@ vc4_get_hang_state_ioctl(struct drm_device *dev, void *data,
 	u32 i;
 	int ret = 0;
 
+	if (WARN_ON_ONCE(vc4->is_vc5))
+		return -ENODEV;
+
 	if (!vc4->v3d) {
 		DRM_DEBUG("VC4_GET_HANG_STATE with no VC4 V3D probed\n");
 		return -ENODEV;
@@ -386,6 +389,9 @@ vc4_wait_for_seqno(struct drm_device *dev, uint64_t seqno, uint64_t timeout_ns,
 	unsigned long timeout_expire;
 	DEFINE_WAIT(wait);
 
+	if (WARN_ON_ONCE(vc4->is_vc5))
+		return -ENODEV;
+
 	if (vc4->finished_seqno >= seqno)
 		return 0;
 
@@ -468,6 +474,9 @@ vc4_submit_next_bin_job(struct drm_device *dev)
 	struct vc4_dev *vc4 = to_vc4_dev(dev);
 	struct vc4_exec_info *exec;
 
+	if (WARN_ON_ONCE(vc4->is_vc5))
+		return;
+
 again:
 	exec = vc4_first_bin_job(vc4);
 	if (!exec)
@@ -513,6 +522,9 @@ vc4_submit_next_render_job(struct drm_device *dev)
 	if (!exec)
 		return;
 
+	if (WARN_ON_ONCE(vc4->is_vc5))
+		return;
+
 	/* A previous RCL may have written to one of our textures, and
 	 * our full cache flush at bin time may have occurred before
 	 * that RCL completed.  Flush the texture cache now, but not
@@ -531,6 +543,9 @@ vc4_move_job_to_render(struct drm_device *dev, struct vc4_exec_info *exec)
 	struct vc4_dev *vc4 = to_vc4_dev(dev);
 	bool was_empty = list_empty(&vc4->render_job_list);
 
+	if (WARN_ON_ONCE(vc4->is_vc5))
+		return;
+
 	list_move_tail(&exec->head, &vc4->render_job_list);
 	if (was_empty)
 		vc4_submit_next_render_job(dev);
@@ -997,6 +1012,9 @@ vc4_job_handle_completed(struct vc4_dev *vc4)
 	unsigned long irqflags;
 	struct vc4_seqno_cb *cb, *cb_temp;
 
+	if (WARN_ON_ONCE(vc4->is_vc5))
+		return;
+
 	spin_lock_irqsave(&vc4->job_lock, irqflags);
 	while (!list_empty(&vc4->job_done_list)) {
 		struct vc4_exec_info *exec =
@@ -1033,6 +1051,9 @@ int vc4_queue_seqno_cb(struct drm_device *dev,
 	struct vc4_dev *vc4 = to_vc4_dev(dev);
 	unsigned long irqflags;
 
+	if (WARN_ON_ONCE(vc4->is_vc5))
+		return -ENODEV;
+
 	cb->func = func;
 	INIT_WORK(&cb->work, vc4_seqno_cb_work);
 
@@ -1083,8 +1104,12 @@ int
 vc4_wait_seqno_ioctl(struct drm_device *dev, void *data,
 		     struct drm_file *file_priv)
 {
+	struct vc4_dev *vc4 = to_vc4_dev(dev);
 	struct drm_vc4_wait_seqno *args = data;
 
+	if (WARN_ON_ONCE(vc4->is_vc5))
+		return -ENODEV;
+
 	return vc4_wait_for_seqno_ioctl_helper(dev, args->seqno,
 					       &args->timeout_ns);
 }
@@ -1093,11 +1118,15 @@ int
 vc4_wait_bo_ioctl(struct drm_device *dev, void *data,
 		  struct drm_file *file_priv)
 {
+	struct vc4_dev *vc4 = to_vc4_dev(dev);
 	int ret;
 	struct drm_vc4_wait_bo *args = data;
 	struct drm_gem_object *gem_obj;
 	struct vc4_bo *bo;
 
+	if (WARN_ON_ONCE(vc4->is_vc5))
+		return -ENODEV;
+
 	if (args->pad != 0)
 		return -EINVAL;
 
@@ -1144,6 +1173,9 @@ vc4_submit_cl_ioctl(struct drm_device *dev, void *data,
 				  args->shader_rec_size,
 				  args->bo_handle_count);
 
+	if (WARN_ON_ONCE(vc4->is_vc5))
+		return -ENODEV;
+
 	if (!vc4->v3d) {
 		DRM_DEBUG("VC4_SUBMIT_CL with no VC4 V3D probed\n");
 		return -ENODEV;
@@ -1167,6 +1199,7 @@ vc4_submit_cl_ioctl(struct drm_device *dev, void *data,
 		DRM_ERROR("malloc failure on exec struct\n");
 		return -ENOMEM;
 	}
+	exec->dev = vc4;
 
 	ret = vc4_v3d_pm_get(vc4);
 	if (ret) {
@@ -1276,6 +1309,9 @@ int vc4_gem_init(struct drm_device *dev)
 {
 	struct vc4_dev *vc4 = to_vc4_dev(dev);
 
+	if (WARN_ON_ONCE(vc4->is_vc5))
+		return -ENODEV;
+
 	vc4->dma_fence_context = dma_fence_context_alloc(1);
 
 	INIT_LIST_HEAD(&vc4->bin_job_list);
@@ -1321,11 +1357,15 @@ static void vc4_gem_destroy(struct drm_device *dev, void *unused)
 int vc4_gem_madvise_ioctl(struct drm_device *dev, void *data,
 			  struct drm_file *file_priv)
 {
+	struct vc4_dev *vc4 = to_vc4_dev(dev);
 	struct drm_vc4_gem_madvise *args = data;
 	struct drm_gem_object *gem_obj;
 	struct vc4_bo *bo;
 	int ret;
 
+	if (WARN_ON_ONCE(vc4->is_vc5))
+		return -ENODEV;
+
 	switch (args->madv) {
 	case VC4_MADV_DONTNEED:
 	case VC4_MADV_WILLNEED:
diff --git a/drivers/gpu/drm/vc4/vc4_hdmi.c b/drivers/gpu/drm/vc4/vc4_hdmi.c
index 823d812f4982..ce9d16666d91 100644
--- a/drivers/gpu/drm/vc4/vc4_hdmi.c
+++ b/drivers/gpu/drm/vc4/vc4_hdmi.c
@@ -1481,7 +1481,7 @@ vc4_hdmi_encoder_compute_mode_clock(const struct drm_display_mode *mode,
 				    unsigned int bpc,
 				    enum vc4_hdmi_output_format fmt)
 {
-	unsigned long long clock = mode->clock * 1000;
+	unsigned long long clock = mode->clock * 1000ULL;
 
 	if (mode->flags & DRM_MODE_FLAG_DBLCLK)
 		clock = clock * 2;
diff --git a/drivers/gpu/drm/vc4/vc4_hvs.c b/drivers/gpu/drm/vc4/vc4_hvs.c
index 2a58fc421cf6..ba2c8e5a9b64 100644
--- a/drivers/gpu/drm/vc4/vc4_hvs.c
+++ b/drivers/gpu/drm/vc4/vc4_hvs.c
@@ -220,10 +220,11 @@ u8 vc4_hvs_get_fifo_frame_count(struct vc4_hvs *hvs, unsigned int fifo)
 
 int vc4_hvs_get_fifo_from_output(struct vc4_hvs *hvs, unsigned int output)
 {
+	struct vc4_dev *vc4 = hvs->vc4;
 	u32 reg;
 	int ret;
 
-	if (!hvs->hvs5)
+	if (!vc4->is_vc5)
 		return output;
 
 	switch (output) {
@@ -273,6 +274,7 @@ int vc4_hvs_get_fifo_from_output(struct vc4_hvs *hvs, unsigned int output)
 static int vc4_hvs_init_channel(struct vc4_hvs *hvs, struct drm_crtc *crtc,
 				struct drm_display_mode *mode, bool oneshot)
 {
+	struct vc4_dev *vc4 = hvs->vc4;
 	struct vc4_crtc *vc4_crtc = to_vc4_crtc(crtc);
 	struct vc4_crtc_state *vc4_crtc_state = to_vc4_crtc_state(crtc->state);
 	unsigned int chan = vc4_crtc_state->assigned_channel;
@@ -291,7 +293,7 @@ static int vc4_hvs_init_channel(struct vc4_hvs *hvs, struct drm_crtc *crtc,
 	 */
 	dispctrl = SCALER_DISPCTRLX_ENABLE;
 
-	if (!hvs->hvs5)
+	if (!vc4->is_vc5)
 		dispctrl |= VC4_SET_FIELD(mode->hdisplay,
 					  SCALER_DISPCTRLX_WIDTH) |
 			    VC4_SET_FIELD(mode->vdisplay,
@@ -312,7 +314,7 @@ static int vc4_hvs_init_channel(struct vc4_hvs *hvs, struct drm_crtc *crtc,
 
 	HVS_WRITE(SCALER_DISPBKGNDX(chan), dispbkgndx |
 		  SCALER_DISPBKGND_AUTOHS |
-		  ((!hvs->hvs5) ? SCALER_DISPBKGND_GAMMA : 0) |
+		  ((!vc4->is_vc5) ? SCALER_DISPBKGND_GAMMA : 0) |
 		  (interlace ? SCALER_DISPBKGND_INTERLACE : 0));
 
 	/* Reload the LUT, since the SRAMs would have been disabled if
@@ -617,11 +619,9 @@ static int vc4_hvs_bind(struct device *dev, struct device *master, void *data)
 	if (!hvs)
 		return -ENOMEM;
 
+	hvs->vc4 = vc4;
 	hvs->pdev = pdev;
 
-	if (of_device_is_compatible(pdev->dev.of_node, "brcm,bcm2711-hvs"))
-		hvs->hvs5 = true;
-
 	hvs->regs = vc4_ioremap_regs(pdev, 0);
 	if (IS_ERR(hvs->regs))
 		return PTR_ERR(hvs->regs);
@@ -630,7 +630,7 @@ static int vc4_hvs_bind(struct device *dev, struct device *master, void *data)
 	hvs->regset.regs = hvs_regs;
 	hvs->regset.nregs = ARRAY_SIZE(hvs_regs);
 
-	if (hvs->hvs5) {
+	if (vc4->is_vc5) {
 		hvs->core_clk = devm_clk_get(&pdev->dev, NULL);
 		if (IS_ERR(hvs->core_clk)) {
 			dev_err(&pdev->dev, "Couldn't get core clock\n");
@@ -644,7 +644,7 @@ static int vc4_hvs_bind(struct device *dev, struct device *master, void *data)
 		}
 	}
 
-	if (!hvs->hvs5)
+	if (!vc4->is_vc5)
 		hvs->dlist = hvs->regs + SCALER_DLIST_START;
 	else
 		hvs->dlist = hvs->regs + SCALER5_DLIST_START;
@@ -665,7 +665,7 @@ static int vc4_hvs_bind(struct device *dev, struct device *master, void *data)
 	 * between planes when they don't overlap on the screen, but
 	 * for now we just allocate globally.
 	 */
-	if (!hvs->hvs5)
+	if (!vc4->is_vc5)
 		/* 48k words of 2x12-bit pixels */
 		drm_mm_init(&hvs->lbm_mm, 0, 48 * 1024);
 	else
diff --git a/drivers/gpu/drm/vc4/vc4_irq.c b/drivers/gpu/drm/vc4/vc4_irq.c
index 4342fb43e8c1..2eacfb6773d2 100644
--- a/drivers/gpu/drm/vc4/vc4_irq.c
+++ b/drivers/gpu/drm/vc4/vc4_irq.c
@@ -265,6 +265,9 @@ vc4_irq_enable(struct drm_device *dev)
 {
 	struct vc4_dev *vc4 = to_vc4_dev(dev);
 
+	if (WARN_ON_ONCE(vc4->is_vc5))
+		return;
+
 	if (!vc4->v3d)
 		return;
 
@@ -279,6 +282,9 @@ vc4_irq_disable(struct drm_device *dev)
 {
 	struct vc4_dev *vc4 = to_vc4_dev(dev);
 
+	if (WARN_ON_ONCE(vc4->is_vc5))
+		return;
+
 	if (!vc4->v3d)
 		return;
 
@@ -296,8 +302,12 @@ vc4_irq_disable(struct drm_device *dev)
 
 int vc4_irq_install(struct drm_device *dev, int irq)
 {
+	struct vc4_dev *vc4 = to_vc4_dev(dev);
 	int ret;
 
+	if (WARN_ON_ONCE(vc4->is_vc5))
+		return -ENODEV;
+
 	if (irq == IRQ_NOTCONNECTED)
 		return -ENOTCONN;
 
@@ -316,6 +326,9 @@ void vc4_irq_uninstall(struct drm_device *dev)
 {
 	struct vc4_dev *vc4 = to_vc4_dev(dev);
 
+	if (WARN_ON_ONCE(vc4->is_vc5))
+		return;
+
 	vc4_irq_disable(dev);
 	free_irq(vc4->irq, dev);
 }
@@ -326,6 +339,9 @@ void vc4_irq_reset(struct drm_device *dev)
 	struct vc4_dev *vc4 = to_vc4_dev(dev);
 	unsigned long irqflags;
 
+	if (WARN_ON_ONCE(vc4->is_vc5))
+		return;
+
 	/* Acknowledge any stale IRQs. */
 	V3D_WRITE(V3D_INTCTL, V3D_DRIVER_IRQS);
 
diff --git a/drivers/gpu/drm/vc4/vc4_kms.c b/drivers/gpu/drm/vc4/vc4_kms.c
index c169bd72e53b..893d831b24aa 100644
--- a/drivers/gpu/drm/vc4/vc4_kms.c
+++ b/drivers/gpu/drm/vc4/vc4_kms.c
@@ -393,7 +393,7 @@ static void vc4_atomic_commit_tail(struct drm_atomic_state *state)
 		old_hvs_state->fifo_state[channel].pending_commit = NULL;
 	}
 
-	if (vc4->hvs->hvs5) {
+	if (vc4->is_vc5) {
 		unsigned long state_rate = max(old_hvs_state->core_clock_rate,
 					       new_hvs_state->core_clock_rate);
 		unsigned long core_rate = max_t(unsigned long,
@@ -412,7 +412,7 @@ static void vc4_atomic_commit_tail(struct drm_atomic_state *state)
 
 	vc4_ctm_commit(vc4, state);
 
-	if (vc4->hvs->hvs5)
+	if (vc4->is_vc5)
 		vc5_hvs_pv_muxing_commit(vc4, state);
 	else
 		vc4_hvs_pv_muxing_commit(vc4, state);
@@ -430,7 +430,7 @@ static void vc4_atomic_commit_tail(struct drm_atomic_state *state)
 
 	drm_atomic_helper_cleanup_planes(dev, state);
 
-	if (vc4->hvs->hvs5) {
+	if (vc4->is_vc5) {
 		drm_dbg(dev, "Running the core clock at %lu Hz\n",
 			new_hvs_state->core_clock_rate);
 
@@ -479,8 +479,12 @@ static struct drm_framebuffer *vc4_fb_create(struct drm_device *dev,
 					     struct drm_file *file_priv,
 					     const struct drm_mode_fb_cmd2 *mode_cmd)
 {
+	struct vc4_dev *vc4 = to_vc4_dev(dev);
 	struct drm_mode_fb_cmd2 mode_cmd_local;
 
+	if (WARN_ON_ONCE(vc4->is_vc5))
+		return ERR_PTR(-ENODEV);
+
 	/* If the user didn't specify a modifier, use the
 	 * vc4_set_tiling_ioctl() state for the BO.
 	 */
@@ -997,11 +1001,15 @@ static const struct drm_mode_config_funcs vc4_mode_funcs = {
 	.fb_create = vc4_fb_create,
 };
 
+static const struct drm_mode_config_funcs vc5_mode_funcs = {
+	.atomic_check = vc4_atomic_check,
+	.atomic_commit = drm_atomic_helper_commit,
+	.fb_create = drm_gem_fb_create,
+};
+
 int vc4_kms_load(struct drm_device *dev)
 {
 	struct vc4_dev *vc4 = to_vc4_dev(dev);
-	bool is_vc5 = of_device_is_compatible(dev->dev->of_node,
-					      "brcm,bcm2711-vc5");
 	int ret;
 
 	/*
@@ -1009,7 +1017,7 @@ int vc4_kms_load(struct drm_device *dev)
 	 * the BCM2711, but the load tracker computations are used for
 	 * the core clock rate calculation.
 	 */
-	if (!is_vc5) {
+	if (!vc4->is_vc5) {
 		/* Start with the load tracker enabled. Can be
 		 * disabled through the debugfs load_tracker file.
 		 */
@@ -1025,7 +1033,7 @@ int vc4_kms_load(struct drm_device *dev)
 		return ret;
 	}
 
-	if (is_vc5) {
+	if (vc4->is_vc5) {
 		dev->mode_config.max_width = 7680;
 		dev->mode_config.max_height = 7680;
 	} else {
@@ -1033,7 +1041,7 @@ int vc4_kms_load(struct drm_device *dev)
 		dev->mode_config.max_height = 2048;
 	}
 
-	dev->mode_config.funcs = &vc4_mode_funcs;
+	dev->mode_config.funcs = vc4->is_vc5 ? &vc5_mode_funcs : &vc4_mode_funcs;
 	dev->mode_config.helper_private = &vc4_mode_config_helpers;
 	dev->mode_config.preferred_depth = 24;
 	dev->mode_config.async_page_flip = true;
diff --git a/drivers/gpu/drm/vc4/vc4_perfmon.c b/drivers/gpu/drm/vc4/vc4_perfmon.c
index 18abc06335c1..c7f5adb6bcf8 100644
--- a/drivers/gpu/drm/vc4/vc4_perfmon.c
+++ b/drivers/gpu/drm/vc4/vc4_perfmon.c
@@ -17,13 +17,27 @@
 
 void vc4_perfmon_get(struct vc4_perfmon *perfmon)
 {
+	struct vc4_dev *vc4 = perfmon->dev;
+
+	if (WARN_ON_ONCE(vc4->is_vc5))
+		return;
+
 	if (perfmon)
 		refcount_inc(&perfmon->refcnt);
 }
 
 void vc4_perfmon_put(struct vc4_perfmon *perfmon)
 {
-	if (perfmon && refcount_dec_and_test(&perfmon->refcnt))
+	struct vc4_dev *vc4;
+
+	if (!perfmon)
+		return;
+
+	vc4 = perfmon->dev;
+	if (WARN_ON_ONCE(vc4->is_vc5))
+		return;
+
+	if (refcount_dec_and_test(&perfmon->refcnt))
 		kfree(perfmon);
 }
 
@@ -32,6 +46,9 @@ void vc4_perfmon_start(struct vc4_dev *vc4, struct vc4_perfmon *perfmon)
 	unsigned int i;
 	u32 mask;
 
+	if (WARN_ON_ONCE(vc4->is_vc5))
+		return;
+
 	if (WARN_ON_ONCE(!perfmon || vc4->active_perfmon))
 		return;
 
@@ -49,6 +66,9 @@ void vc4_perfmon_stop(struct vc4_dev *vc4, struct vc4_perfmon *perfmon,
 {
 	unsigned int i;
 
+	if (WARN_ON_ONCE(vc4->is_vc5))
+		return;
+
 	if (WARN_ON_ONCE(!vc4->active_perfmon ||
 			 perfmon != vc4->active_perfmon))
 		return;
@@ -64,8 +84,12 @@ void vc4_perfmon_stop(struct vc4_dev *vc4, struct vc4_perfmon *perfmon,
 
 struct vc4_perfmon *vc4_perfmon_find(struct vc4_file *vc4file, int id)
 {
+	struct vc4_dev *vc4 = vc4file->dev;
 	struct vc4_perfmon *perfmon;
 
+	if (WARN_ON_ONCE(vc4->is_vc5))
+		return NULL;
+
 	mutex_lock(&vc4file->perfmon.lock);
 	perfmon = idr_find(&vc4file->perfmon.idr, id);
 	vc4_perfmon_get(perfmon);
@@ -76,8 +100,14 @@ struct vc4_perfmon *vc4_perfmon_find(struct vc4_file *vc4file, int id)
 
 void vc4_perfmon_open_file(struct vc4_file *vc4file)
 {
+	struct vc4_dev *vc4 = vc4file->dev;
+
+	if (WARN_ON_ONCE(vc4->is_vc5))
+		return;
+
 	mutex_init(&vc4file->perfmon.lock);
 	idr_init_base(&vc4file->perfmon.idr, VC4_PERFMONID_MIN);
+	vc4file->dev = vc4;
 }
 
 static int vc4_perfmon_idr_del(int id, void *elem, void *data)
@@ -91,6 +121,11 @@ static int vc4_perfmon_idr_del(int id, void *elem, void *data)
 
 void vc4_perfmon_close_file(struct vc4_file *vc4file)
 {
+	struct vc4_dev *vc4 = vc4file->dev;
+
+	if (WARN_ON_ONCE(vc4->is_vc5))
+		return;
+
 	mutex_lock(&vc4file->perfmon.lock);
 	idr_for_each(&vc4file->perfmon.idr, vc4_perfmon_idr_del, NULL);
 	idr_destroy(&vc4file->perfmon.idr);
@@ -107,6 +142,9 @@ int vc4_perfmon_create_ioctl(struct drm_device *dev, void *data,
 	unsigned int i;
 	int ret;
 
+	if (WARN_ON_ONCE(vc4->is_vc5))
+		return -ENODEV;
+
 	if (!vc4->v3d) {
 		DRM_DEBUG("Creating perfmon no VC4 V3D probed\n");
 		return -ENODEV;
@@ -127,6 +165,7 @@ int vc4_perfmon_create_ioctl(struct drm_device *dev, void *data,
 			  GFP_KERNEL);
 	if (!perfmon)
 		return -ENOMEM;
+	perfmon->dev = vc4;
 
 	for (i = 0; i < req->ncounters; i++)
 		perfmon->events[i] = req->events[i];
@@ -157,6 +196,9 @@ int vc4_perfmon_destroy_ioctl(struct drm_device *dev, void *data,
 	struct drm_vc4_perfmon_destroy *req = data;
 	struct vc4_perfmon *perfmon;
 
+	if (WARN_ON_ONCE(vc4->is_vc5))
+		return -ENODEV;
+
 	if (!vc4->v3d) {
 		DRM_DEBUG("Destroying perfmon no VC4 V3D probed\n");
 		return -ENODEV;
@@ -182,6 +224,9 @@ int vc4_perfmon_get_values_ioctl(struct drm_device *dev, void *data,
 	struct vc4_perfmon *perfmon;
 	int ret;
 
+	if (WARN_ON_ONCE(vc4->is_vc5))
+		return -ENODEV;
+
 	if (!vc4->v3d) {
 		DRM_DEBUG("Getting perfmon no VC4 V3D probed\n");
 		return -ENODEV;
diff --git a/drivers/gpu/drm/vc4/vc4_plane.c b/drivers/gpu/drm/vc4/vc4_plane.c
index b3438f4a81ce..1e866dc00ac3 100644
--- a/drivers/gpu/drm/vc4/vc4_plane.c
+++ b/drivers/gpu/drm/vc4/vc4_plane.c
@@ -489,10 +489,10 @@ static u32 vc4_lbm_size(struct drm_plane_state *state)
 	}
 
 	/* Align it to 64 or 128 (hvs5) bytes */
-	lbm = roundup(lbm, vc4->hvs->hvs5 ? 128 : 64);
+	lbm = roundup(lbm, vc4->is_vc5 ? 128 : 64);
 
 	/* Each "word" of the LBM memory contains 2 or 4 (hvs5) pixels */
-	lbm /= vc4->hvs->hvs5 ? 4 : 2;
+	lbm /= vc4->is_vc5 ? 4 : 2;
 
 	return lbm;
 }
@@ -608,7 +608,7 @@ static int vc4_plane_allocate_lbm(struct drm_plane_state *state)
 		ret = drm_mm_insert_node_generic(&vc4->hvs->lbm_mm,
 						 &vc4_state->lbm,
 						 lbm_size,
-						 vc4->hvs->hvs5 ? 64 : 32,
+						 vc4->is_vc5 ? 64 : 32,
 						 0, 0);
 		spin_unlock_irqrestore(&vc4->hvs->mm_lock, irqflags);
 
@@ -917,7 +917,7 @@ static int vc4_plane_mode_set(struct drm_plane *plane,
 	mix_plane_alpha = state->alpha != DRM_BLEND_ALPHA_OPAQUE &&
 			  fb->format->has_alpha;
 
-	if (!vc4->hvs->hvs5) {
+	if (!vc4->is_vc5) {
 	/* Control word */
 		vc4_dlist_write(vc4_state,
 				SCALER_CTL0_VALID |
@@ -1321,6 +1321,10 @@ static int vc4_plane_atomic_async_check(struct drm_plane *plane,
 
 	old_vc4_state = to_vc4_plane_state(plane->state);
 	new_vc4_state = to_vc4_plane_state(new_plane_state);
+
+	if (!new_vc4_state->hw_dlist)
+		return -EINVAL;
+
 	if (old_vc4_state->dlist_count != new_vc4_state->dlist_count ||
 	    old_vc4_state->pos0_offset != new_vc4_state->pos0_offset ||
 	    old_vc4_state->pos2_offset != new_vc4_state->pos2_offset ||
@@ -1385,6 +1389,13 @@ static const struct drm_plane_helper_funcs vc4_plane_helper_funcs = {
 	.atomic_async_update = vc4_plane_atomic_async_update,
 };
 
+static const struct drm_plane_helper_funcs vc5_plane_helper_funcs = {
+	.atomic_check = vc4_plane_atomic_check,
+	.atomic_update = vc4_plane_atomic_update,
+	.atomic_async_check = vc4_plane_atomic_async_check,
+	.atomic_async_update = vc4_plane_atomic_async_update,
+};
+
 static bool vc4_format_mod_supported(struct drm_plane *plane,
 				     uint32_t format,
 				     uint64_t modifier)
@@ -1453,14 +1464,13 @@ static const struct drm_plane_funcs vc4_plane_funcs = {
 struct drm_plane *vc4_plane_init(struct drm_device *dev,
 				 enum drm_plane_type type)
 {
+	struct vc4_dev *vc4 = to_vc4_dev(dev);
 	struct drm_plane *plane = NULL;
 	struct vc4_plane *vc4_plane;
 	u32 formats[ARRAY_SIZE(hvs_formats)];
 	int num_formats = 0;
 	int ret = 0;
 	unsigned i;
-	bool hvs5 = of_device_is_compatible(dev->dev->of_node,
-					    "brcm,bcm2711-vc5");
 	static const uint64_t modifiers[] = {
 		DRM_FORMAT_MOD_BROADCOM_VC4_T_TILED,
 		DRM_FORMAT_MOD_BROADCOM_SAND128,
@@ -1476,7 +1486,7 @@ struct drm_plane *vc4_plane_init(struct drm_device *dev,
 		return ERR_PTR(-ENOMEM);
 
 	for (i = 0; i < ARRAY_SIZE(hvs_formats); i++) {
-		if (!hvs_formats[i].hvs5_only || hvs5) {
+		if (!hvs_formats[i].hvs5_only || vc4->is_vc5) {
 			formats[num_formats] = hvs_formats[i].drm;
 			num_formats++;
 		}
@@ -1490,7 +1500,10 @@ struct drm_plane *vc4_plane_init(struct drm_device *dev,
 	if (ret)
 		return ERR_PTR(ret);
 
-	drm_plane_helper_add(plane, &vc4_plane_helper_funcs);
+	if (vc4->is_vc5)
+		drm_plane_helper_add(plane, &vc5_plane_helper_funcs);
+	else
+		drm_plane_helper_add(plane, &vc4_plane_helper_funcs);
 
 	drm_plane_create_alpha_property(plane);
 	drm_plane_create_rotation_property(plane, DRM_MODE_ROTATE_0,
diff --git a/drivers/gpu/drm/vc4/vc4_render_cl.c b/drivers/gpu/drm/vc4/vc4_render_cl.c
index 3c918eeaf56e..f6b7dc3df08c 100644
--- a/drivers/gpu/drm/vc4/vc4_render_cl.c
+++ b/drivers/gpu/drm/vc4/vc4_render_cl.c
@@ -593,11 +593,15 @@ vc4_rcl_render_config_surface_setup(struct vc4_exec_info *exec,
 
 int vc4_get_rcl(struct drm_device *dev, struct vc4_exec_info *exec)
 {
+	struct vc4_dev *vc4 = to_vc4_dev(dev);
 	struct vc4_rcl_setup setup = {0};
 	struct drm_vc4_submit_cl *args = exec->args;
 	bool has_bin = args->bin_cl_size != 0;
 	int ret;
 
+	if (WARN_ON_ONCE(vc4->is_vc5))
+		return -ENODEV;
+
 	if (args->min_x_tile > args->max_x_tile ||
 	    args->min_y_tile > args->max_y_tile) {
 		DRM_DEBUG("Bad render tile set (%d,%d)-(%d,%d)\n",
diff --git a/drivers/gpu/drm/vc4/vc4_v3d.c b/drivers/gpu/drm/vc4/vc4_v3d.c
index 7bb3067f8425..cc714dcfe1f2 100644
--- a/drivers/gpu/drm/vc4/vc4_v3d.c
+++ b/drivers/gpu/drm/vc4/vc4_v3d.c
@@ -127,6 +127,9 @@ static int vc4_v3d_debugfs_ident(struct seq_file *m, void *unused)
 int
 vc4_v3d_pm_get(struct vc4_dev *vc4)
 {
+	if (WARN_ON_ONCE(vc4->is_vc5))
+		return -ENODEV;
+
 	mutex_lock(&vc4->power_lock);
 	if (vc4->power_refcount++ == 0) {
 		int ret = pm_runtime_get_sync(&vc4->v3d->pdev->dev);
@@ -145,6 +148,9 @@ vc4_v3d_pm_get(struct vc4_dev *vc4)
 void
 vc4_v3d_pm_put(struct vc4_dev *vc4)
 {
+	if (WARN_ON_ONCE(vc4->is_vc5))
+		return;
+
 	mutex_lock(&vc4->power_lock);
 	if (--vc4->power_refcount == 0) {
 		pm_runtime_mark_last_busy(&vc4->v3d->pdev->dev);
@@ -172,6 +178,9 @@ int vc4_v3d_get_bin_slot(struct vc4_dev *vc4)
 	uint64_t seqno = 0;
 	struct vc4_exec_info *exec;
 
+	if (WARN_ON_ONCE(vc4->is_vc5))
+		return -ENODEV;
+
 try_again:
 	spin_lock_irqsave(&vc4->job_lock, irqflags);
 	slot = ffs(~vc4->bin_alloc_used);
@@ -316,6 +325,9 @@ int vc4_v3d_bin_bo_get(struct vc4_dev *vc4, bool *used)
 {
 	int ret = 0;
 
+	if (WARN_ON_ONCE(vc4->is_vc5))
+		return -ENODEV;
+
 	mutex_lock(&vc4->bin_bo_lock);
 
 	if (used && *used)
@@ -348,6 +360,9 @@ static void bin_bo_release(struct kref *ref)
 
 void vc4_v3d_bin_bo_put(struct vc4_dev *vc4)
 {
+	if (WARN_ON_ONCE(vc4->is_vc5))
+		return;
+
 	mutex_lock(&vc4->bin_bo_lock);
 	kref_put(&vc4->bin_bo_kref, bin_bo_release);
 	mutex_unlock(&vc4->bin_bo_lock);
diff --git a/drivers/gpu/drm/vc4/vc4_validate.c b/drivers/gpu/drm/vc4/vc4_validate.c
index eec76af49f04..2feba55bcef7 100644
--- a/drivers/gpu/drm/vc4/vc4_validate.c
+++ b/drivers/gpu/drm/vc4/vc4_validate.c
@@ -105,9 +105,13 @@ size_is_lt(uint32_t width, uint32_t height, int cpp)
 struct drm_gem_cma_object *
 vc4_use_bo(struct vc4_exec_info *exec, uint32_t hindex)
 {
+	struct vc4_dev *vc4 = exec->dev;
 	struct drm_gem_cma_object *obj;
 	struct vc4_bo *bo;
 
+	if (WARN_ON_ONCE(vc4->is_vc5))
+		return NULL;
+
 	if (hindex >= exec->bo_count) {
 		DRM_DEBUG("BO index %d greater than BO count %d\n",
 			  hindex, exec->bo_count);
@@ -160,10 +164,14 @@ vc4_check_tex_size(struct vc4_exec_info *exec, struct drm_gem_cma_object *fbo,
 		   uint32_t offset, uint8_t tiling_format,
 		   uint32_t width, uint32_t height, uint8_t cpp)
 {
+	struct vc4_dev *vc4 = exec->dev;
 	uint32_t aligned_width, aligned_height, stride, size;
 	uint32_t utile_w = utile_width(cpp);
 	uint32_t utile_h = utile_height(cpp);
 
+	if (WARN_ON_ONCE(vc4->is_vc5))
+		return false;
+
 	/* The shaded vertex format stores signed 12.4 fixed point
 	 * (-2048,2047) offsets from the viewport center, so we should
 	 * never have a render target larger than 4096.  The texture
@@ -482,10 +490,14 @@ vc4_validate_bin_cl(struct drm_device *dev,
 		    void *unvalidated,
 		    struct vc4_exec_info *exec)
 {
+	struct vc4_dev *vc4 = to_vc4_dev(dev);
 	uint32_t len = exec->args->bin_cl_size;
 	uint32_t dst_offset = 0;
 	uint32_t src_offset = 0;
 
+	if (WARN_ON_ONCE(vc4->is_vc5))
+		return -ENODEV;
+
 	while (src_offset < len) {
 		void *dst_pkt = validated + dst_offset;
 		void *src_pkt = unvalidated + src_offset;
@@ -926,9 +938,13 @@ int
 vc4_validate_shader_recs(struct drm_device *dev,
 			 struct vc4_exec_info *exec)
 {
+	struct vc4_dev *vc4 = to_vc4_dev(dev);
 	uint32_t i;
 	int ret = 0;
 
+	if (WARN_ON_ONCE(vc4->is_vc5))
+		return -ENODEV;
+
 	for (i = 0; i < exec->shader_state_count; i++) {
 		ret = validate_gl_shader_rec(dev, exec, &exec->shader_state[i]);
 		if (ret)
diff --git a/drivers/gpu/drm/vc4/vc4_validate_shaders.c b/drivers/gpu/drm/vc4/vc4_validate_shaders.c
index 7cf82b071de2..e315aeb5fef5 100644
--- a/drivers/gpu/drm/vc4/vc4_validate_shaders.c
+++ b/drivers/gpu/drm/vc4/vc4_validate_shaders.c
@@ -778,6 +778,7 @@ vc4_handle_branch_target(struct vc4_shader_validation_state *validation_state)
 struct vc4_validated_shader_info *
 vc4_validate_shader(struct drm_gem_cma_object *shader_obj)
 {
+	struct vc4_dev *vc4 = to_vc4_dev(shader_obj->base.dev);
 	bool found_shader_end = false;
 	int shader_end_ip = 0;
 	uint32_t last_thread_switch_ip = -3;
@@ -785,6 +786,9 @@ vc4_validate_shader(struct drm_gem_cma_object *shader_obj)
 	struct vc4_validated_shader_info *validated_shader = NULL;
 	struct vc4_shader_validation_state validation_state;
 
+	if (WARN_ON_ONCE(vc4->is_vc5))
+		return NULL;
+
 	memset(&validation_state, 0, sizeof(validation_state));
 	validation_state.shader = shader_obj->vaddr;
 	validation_state.max_ip = shader_obj->base.size / sizeof(uint64_t);
diff --git a/drivers/gpu/drm/xen/xen_drm_front_gem.c b/drivers/gpu/drm/xen/xen_drm_front_gem.c
index 5a5bf4e5b717..e31554d7139f 100644
--- a/drivers/gpu/drm/xen/xen_drm_front_gem.c
+++ b/drivers/gpu/drm/xen/xen_drm_front_gem.c
@@ -71,7 +71,7 @@ static int xen_drm_front_gem_object_mmap(struct drm_gem_object *gem_obj,
 	 * the whole buffer.
 	 */
 	vma->vm_flags &= ~VM_PFNMAP;
-	vma->vm_flags |= VM_MIXEDMAP;
+	vma->vm_flags |= VM_MIXEDMAP | VM_DONTEXPAND;
 	vma->vm_pgoff = 0;
 
 	/*