Merge branch 'dev-5.10' into dev-5.10-inteldev-5.10-intel

Pull 5.10.67 stable from OpenBMC upstream.

Signed-off-by: Jae Hyun Yoo <jae.hyun.yoo@linux.intel.com>

68 files changed, 798 insertions, 440 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c
index d3e51d361179..eb68b0f1da82 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c
@@ -160,17 +160,28 @@ static int acp_poweron(struct generic_pm_domain *genpd)
 	return 0;
 }
 
-static struct device *get_mfd_cell_dev(const char *device_name, int r)
+static int acp_genpd_add_device(struct device *dev, void *data)
 {
-	char auto_dev_name[25];
-	struct device *dev;
+	struct generic_pm_domain *gpd = data;
+	int ret;
 
-	snprintf(auto_dev_name, sizeof(auto_dev_name),
-		 "%s.%d.auto", device_name, r);
-	dev = bus_find_device_by_name(&platform_bus_type, NULL, auto_dev_name);
-	dev_info(dev, "device %s added to pm domain\n", auto_dev_name);
+	ret = pm_genpd_add_device(gpd, dev);
+	if (ret)
+		dev_err(dev, "Failed to add dev to genpd %d\n", ret);
 
-	return dev;
+	return ret;
+}
+
+static int acp_genpd_remove_device(struct device *dev, void *data)
+{
+	int ret;
+
+	ret = pm_genpd_remove_device(dev);
+	if (ret)
+		dev_err(dev, "Failed to remove dev from genpd %d\n", ret);
+
+	/* Continue to remove */
+	return 0;
 }
 
 /**
@@ -181,11 +192,10 @@ static struct device *get_mfd_cell_dev(const char *device_name, int r)
  */
 static int acp_hw_init(void *handle)
 {
-	int r, i;
+	int r;
 	uint64_t acp_base;
 	u32 val = 0;
 	u32 count = 0;
-	struct device *dev;
 	struct i2s_platform_data *i2s_pdata = NULL;
 
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
@@ -341,15 +351,10 @@ static int acp_hw_init(void *handle)
 	if (r)
 		goto failure;
 
-	for (i = 0; i < ACP_DEVS ; i++) {
-		dev = get_mfd_cell_dev(adev->acp.acp_cell[i].name, i);
-		r = pm_genpd_add_device(&adev->acp.acp_genpd->gpd, dev);
-		if (r) {
-			dev_err(dev, "Failed to add dev to genpd\n");
-			goto failure;
-		}
-	}
-
+	r = device_for_each_child(adev->acp.parent, &adev->acp.acp_genpd->gpd,
+				  acp_genpd_add_device);
+	if (r)
+		goto failure;
 
 	/* Assert Soft reset of ACP */
 	val = cgs_read_register(adev->acp.cgs_device, mmACP_SOFT_RESET);
@@ -410,10 +415,8 @@ failure:
  */
 static int acp_hw_fini(void *handle)
 {
-	int i, ret;
 	u32 val = 0;
 	u32 count = 0;
-	struct device *dev;
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
 	/* return early if no ACP */
@@ -458,13 +461,8 @@ static int acp_hw_fini(void *handle)
 		udelay(100);
 	}
 
-	for (i = 0; i < ACP_DEVS ; i++) {
-		dev = get_mfd_cell_dev(adev->acp.acp_cell[i].name, i);
-		ret = pm_genpd_remove_device(dev);
-		/* If removal fails, dont giveup and try rest */
-		if (ret)
-			dev_err(dev, "remove dev from genpd failed\n");
-	}
+	device_for_each_child(adev->acp.parent, NULL,
+			      acp_genpd_remove_device);
 
 	mfd_remove_devices(adev->acp.parent);
 	kfree(adev->acp.acp_res);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index ffd310279a69..97723f2b5ece 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -2619,12 +2619,11 @@ static void amdgpu_device_delay_enable_gfx_off(struct work_struct *work)
 	struct amdgpu_device *adev =
 		container_of(work, struct amdgpu_device, gfx.gfx_off_delay_work.work);
 
-	mutex_lock(&adev->gfx.gfx_off_mutex);
-	if (!adev->gfx.gfx_off_state && !adev->gfx.gfx_off_req_count) {
-		if (!amdgpu_dpm_set_powergating_by_smu(adev, AMD_IP_BLOCK_TYPE_GFX, true))
-			adev->gfx.gfx_off_state = true;
-	}
-	mutex_unlock(&adev->gfx.gfx_off_mutex);
+	WARN_ON_ONCE(adev->gfx.gfx_off_state);
+	WARN_ON_ONCE(adev->gfx.gfx_off_req_count);
+
+	if (!amdgpu_dpm_set_powergating_by_smu(adev, AMD_IP_BLOCK_TYPE_GFX, true))
+		adev->gfx.gfx_off_state = true;
 }
 
 /**
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
index c485ec86804e..9f9f55a2b257 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
@@ -556,24 +556,38 @@ void amdgpu_gfx_off_ctrl(struct amdgpu_device *adev, bool enable)
 
 	mutex_lock(&adev->gfx.gfx_off_mutex);
 
-	if (!enable)
-		adev->gfx.gfx_off_req_count++;
-	else if (adev->gfx.gfx_off_req_count > 0)
+	if (enable) {
+		/* If the count is already 0, it means there's an imbalance bug somewhere.
+		 * Note that the bug may be in a different caller than the one which triggers the
+		 * WARN_ON_ONCE.
+		 */
+		if (WARN_ON_ONCE(adev->gfx.gfx_off_req_count == 0))
+			goto unlock;
+
 		adev->gfx.gfx_off_req_count--;
 
-	if (enable && !adev->gfx.gfx_off_state && !adev->gfx.gfx_off_req_count) {
-		schedule_delayed_work(&adev->gfx.gfx_off_delay_work, GFX_OFF_DELAY_ENABLE);
-	} else if (!enable && adev->gfx.gfx_off_state) {
-		if (!amdgpu_dpm_set_powergating_by_smu(adev, AMD_IP_BLOCK_TYPE_GFX, false)) {
-			adev->gfx.gfx_off_state = false;
+		if (adev->gfx.gfx_off_req_count == 0 && !adev->gfx.gfx_off_state)
+			schedule_delayed_work(&adev->gfx.gfx_off_delay_work, GFX_OFF_DELAY_ENABLE);
+	} else {
+		if (adev->gfx.gfx_off_req_count == 0) {
+			cancel_delayed_work_sync(&adev->gfx.gfx_off_delay_work);
+
+			if (adev->gfx.gfx_off_state &&
+			    !amdgpu_dpm_set_powergating_by_smu(adev, AMD_IP_BLOCK_TYPE_GFX, false)) {
+				adev->gfx.gfx_off_state = false;
 
-			if (adev->gfx.funcs->init_spm_golden) {
-				dev_dbg(adev->dev, "GFXOFF is disabled, re-init SPM golden settings\n");
-				amdgpu_gfx_init_spm_golden(adev);
+				if (adev->gfx.funcs->init_spm_golden) {
+					dev_dbg(adev->dev,
+						"GFXOFF is disabled, re-init SPM golden settings\n");
+					amdgpu_gfx_init_spm_golden(adev);
+				}
 			}
 		}
+
+		adev->gfx.gfx_off_req_count++;
 	}
 
+unlock:
 	mutex_unlock(&adev->gfx.gfx_off_mutex);
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_i2c.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_i2c.c
index 47cad23a6b9e..b91d3d29b410 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_i2c.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_i2c.c
@@ -339,7 +339,7 @@ static void amdgpu_i2c_put_byte(struct amdgpu_i2c_chan *i2c_bus,
 void
 amdgpu_i2c_router_select_ddc_port(const struct amdgpu_connector *amdgpu_connector)
 {
-	u8 val;
+	u8 val = 0;
 
 	if (!amdgpu_connector->router.ddc_valid)
 		return;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
index ac043baac05d..ad9863b84f1f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
@@ -207,7 +207,7 @@ void amdgpu_bo_placement_from_domain(struct amdgpu_bo *abo, u32 domain)
 		c++;
 	}
 
-	BUG_ON(c >= AMDGPU_BO_MAX_PLACEMENTS);
+	BUG_ON(c > AMDGPU_BO_MAX_PLACEMENTS);
 
 	placement->num_placement = c;
 	placement->placement = places;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
index 0e64c39a2372..7c3efc5f1be0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
@@ -305,7 +305,7 @@ int amdgpu_ras_eeprom_init(struct amdgpu_ras_eeprom_control *control,
 		return ret;
 	}
 
-	__decode_table_header_from_buff(hdr, &buff[2]);
+	__decode_table_header_from_buff(hdr, buff);
 
 	if (hdr->header == EEPROM_TABLE_HDR_VAL) {
 		control->num_recs = (hdr->tbl_size - EEPROM_TABLE_HEADER_SIZE) /
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index fb15e8b5af32..ac3a88197b2f 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -1271,6 +1271,16 @@ static bool is_raven_kicker(struct amdgpu_device *adev)
 		return false;
 }
 
+static bool check_if_enlarge_doorbell_range(struct amdgpu_device *adev)
+{
+	if ((adev->asic_type == CHIP_RENOIR) &&
+	    (adev->gfx.me_fw_version >= 0x000000a5) &&
+	    (adev->gfx.me_feature_version >= 52))
+		return true;
+	else
+		return false;
+}
+
 static void gfx_v9_0_check_if_need_gfxoff(struct amdgpu_device *adev)
 {
 	if (gfx_v9_0_should_disable_gfxoff(adev->pdev))
@@ -3619,7 +3629,16 @@ static int gfx_v9_0_kiq_init_register(struct amdgpu_ring *ring)
 	if (ring->use_doorbell) {
 		WREG32_SOC15(GC, 0, mmCP_MEC_DOORBELL_RANGE_LOWER,
 					(adev->doorbell_index.kiq * 2) << 2);
-		WREG32_SOC15(GC, 0, mmCP_MEC_DOORBELL_RANGE_UPPER,
+		/* If GC has entered CGPG, ringing doorbell > first page
+		 * doesn't wakeup GC. Enlarge CP_MEC_DOORBELL_RANGE_UPPER to
+		 * workaround this issue. And this change has to align with firmware
+		 * update.
+		 */
+		if (check_if_enlarge_doorbell_range(adev))
+			WREG32_SOC15(GC, 0, mmCP_MEC_DOORBELL_RANGE_UPPER,
+					(adev->doorbell.size - 4));
+		else
+			WREG32_SOC15(GC, 0, mmCP_MEC_DOORBELL_RANGE_UPPER,
 					(adev->doorbell_index.userqueue_end * 2) << 2);
 	}
 
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
index aa8ae0ca62f9..e8737fa438f0 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
@@ -120,7 +120,7 @@ static int vcn_v1_0_sw_init(void *handle)
 		adev->firmware.ucode[AMDGPU_UCODE_ID_VCN].fw = adev->vcn.fw;
 		adev->firmware.fw_size +=
 			ALIGN(le32_to_cpu(hdr->ucode_size_bytes), PAGE_SIZE);
-		DRM_INFO("PSP loading VCN firmware\n");
+		dev_info(adev->dev, "Will use PSP to load VCN firmware\n");
 	}
 
 	r = amdgpu_vcn_resume(adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c
index fc939d4f4841..f493b5c3d382 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c
@@ -122,7 +122,7 @@ static int vcn_v2_0_sw_init(void *handle)
 		adev->firmware.ucode[AMDGPU_UCODE_ID_VCN].fw = adev->vcn.fw;
 		adev->firmware.fw_size +=
 			ALIGN(le32_to_cpu(hdr->ucode_size_bytes), PAGE_SIZE);
-		DRM_INFO("PSP loading VCN firmware\n");
+		dev_info(adev->dev, "Will use PSP to load VCN firmware\n");
 	}
 
 	r = amdgpu_vcn_resume(adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c b/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c
index 2c328362eee3..ce64d4016f90 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c
@@ -152,7 +152,7 @@ static int vcn_v2_5_sw_init(void *handle)
 			adev->firmware.fw_size +=
 				ALIGN(le32_to_cpu(hdr->ucode_size_bytes), PAGE_SIZE);
 		}
-		DRM_INFO("PSP loading VCN firmware\n");
+		dev_info(adev->dev, "Will use PSP to load VCN firmware\n");
 	}
 
 	r = amdgpu_vcn_resume(adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c
index c9c888be1228..2099f6ebd833 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c
@@ -148,7 +148,7 @@ static int vcn_v3_0_sw_init(void *handle)
 			adev->firmware.fw_size +=
 				ALIGN(le32_to_cpu(hdr->ucode_size_bytes), PAGE_SIZE);
 		}
-		DRM_INFO("PSP loading VCN firmware\n");
+		dev_info(adev->dev, "Will use PSP to load VCN firmware\n");
 	}
 
 	r = amdgpu_vcn_resume(adev);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.c
index 88813dad731f..c021519af810 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.c
@@ -98,36 +98,78 @@ void mqd_symmetrically_map_cu_mask(struct mqd_manager *mm,
 		uint32_t *se_mask)
 {
 	struct kfd_cu_info cu_info;
-	uint32_t cu_per_se[KFD_MAX_NUM_SE] = {0};
-	int i, se, sh, cu = 0;
-
+	uint32_t cu_per_sh[KFD_MAX_NUM_SE][KFD_MAX_NUM_SH_PER_SE] = {0};
+	int i, se, sh, cu;
 	amdgpu_amdkfd_get_cu_info(mm->dev->kgd, &cu_info);
 
 	if (cu_mask_count > cu_info.cu_active_number)
 		cu_mask_count = cu_info.cu_active_number;
 
+	/* Exceeding these bounds corrupts the stack and indicates a coding error.
+	 * Returning with no CU's enabled will hang the queue, which should be
+	 * attention grabbing.
+	 */
+	if (cu_info.num_shader_engines > KFD_MAX_NUM_SE) {
+		pr_err("Exceeded KFD_MAX_NUM_SE, chip reports %d\n", cu_info.num_shader_engines);
+		return;
+	}
+	if (cu_info.num_shader_arrays_per_engine > KFD_MAX_NUM_SH_PER_SE) {
+		pr_err("Exceeded KFD_MAX_NUM_SH, chip reports %d\n",
+			cu_info.num_shader_arrays_per_engine * cu_info.num_shader_engines);
+		return;
+	}
+	/* Count active CUs per SH.
+	 *
+	 * Some CUs in an SH may be disabled.	HW expects disabled CUs to be
+	 * represented in the high bits of each SH's enable mask (the upper and lower
+	 * 16 bits of se_mask) and will take care of the actual distribution of
+	 * disabled CUs within each SH automatically.
+	 * Each half of se_mask must be filled only on bits 0-cu_per_sh[se][sh]-1.
+	 *
+	 * See note on Arcturus cu_bitmap layout in gfx_v9_0_get_cu_info.
+	 */
 	for (se = 0; se < cu_info.num_shader_engines; se++)
 		for (sh = 0; sh < cu_info.num_shader_arrays_per_engine; sh++)
-			cu_per_se[se] += hweight32(cu_info.cu_bitmap[se % 4][sh + (se / 4)]);
-
-	/* Symmetrically map cu_mask to all SEs:
-	 * cu_mask[0] bit0 -> se_mask[0] bit0;
-	 * cu_mask[0] bit1 -> se_mask[1] bit0;
-	 * ... (if # SE is 4)
-	 * cu_mask[0] bit4 -> se_mask[0] bit1;
+			cu_per_sh[se][sh] = hweight32(cu_info.cu_bitmap[se % 4][sh + (se / 4)]);
+
+	/* Symmetrically map cu_mask to all SEs & SHs:
+	 * se_mask programs up to 2 SH in the upper and lower 16 bits.
+	 *
+	 * Examples
+	 * Assuming 1 SH/SE, 4 SEs:
+	 * cu_mask[0] bit0 -> se_mask[0] bit0
+	 * cu_mask[0] bit1 -> se_mask[1] bit0
+	 * ...
+	 * cu_mask[0] bit4 -> se_mask[0] bit1
+	 * ...
+	 *
+	 * Assuming 2 SH/SE, 4 SEs
+	 * cu_mask[0] bit0 -> se_mask[0] bit0 (SE0,SH0,CU0)
+	 * cu_mask[0] bit1 -> se_mask[1] bit0 (SE1,SH0,CU0)
+	 * ...
+	 * cu_mask[0] bit4 -> se_mask[0] bit16 (SE0,SH1,CU0)
+	 * cu_mask[0] bit5 -> se_mask[1] bit16 (SE1,SH1,CU0)
+	 * ...
+	 * cu_mask[0] bit8 -> se_mask[0] bit1 (SE0,SH0,CU1)
 	 * ...
+	 *
+	 * First ensure all CUs are disabled, then enable user specified CUs.
 	 */
-	se = 0;
-	for (i = 0; i < cu_mask_count; i++) {
-		if (cu_mask[i / 32] & (1 << (i % 32)))
-			se_mask[se] |= 1 << cu;
-
-		do {
-			se++;
-			if (se == cu_info.num_shader_engines) {
-				se = 0;
-				cu++;
+	for (i = 0; i < cu_info.num_shader_engines; i++)
+		se_mask[i] = 0;
+
+	i = 0;
+	for (cu = 0; cu < 16; cu++) {
+		for (sh = 0; sh < cu_info.num_shader_arrays_per_engine; sh++) {
+			for (se = 0; se < cu_info.num_shader_engines; se++) {
+				if (cu_per_sh[se][sh] > cu) {
+					if (cu_mask[i / 32] & (1 << (i % 32)))
+						se_mask[se] |= 1 << (cu + sh * 16);
+					i++;
+					if (i == cu_mask_count)
+						return;
+				}
 			}
-		} while (cu >= cu_per_se[se] && cu < 32);
+		}
 	}
 }
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.h b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.h
index fbdb16418847..4edc012e3138 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.h
@@ -27,6 +27,7 @@
 #include "kfd_priv.h"
 
 #define KFD_MAX_NUM_SE 8
+#define KFD_MAX_NUM_SH_PER_SE 2
 
 /**
  * struct mqd_manager
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c
index e02a55fc1382..fbb65c95464b 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c
@@ -197,29 +197,29 @@ static ssize_t dp_link_settings_read(struct file *f, char __user *buf,
 
 	rd_buf_ptr = rd_buf;
 
-	str_len = strlen("Current:  %d  %d  %d  ");
-	snprintf(rd_buf_ptr, str_len, "Current:  %d  %d  %d  ",
+	str_len = strlen("Current:  %d  0x%x  %d  ");
+	snprintf(rd_buf_ptr, str_len, "Current:  %d  0x%x  %d  ",
 			link->cur_link_settings.lane_count,
 			link->cur_link_settings.link_rate,
 			link->cur_link_settings.link_spread);
 	rd_buf_ptr += str_len;
 
-	str_len = strlen("Verified:  %d  %d  %d  ");
-	snprintf(rd_buf_ptr, str_len, "Verified:  %d  %d  %d  ",
+	str_len = strlen("Verified:  %d  0x%x  %d  ");
+	snprintf(rd_buf_ptr, str_len, "Verified:  %d  0x%x  %d  ",
 			link->verified_link_cap.lane_count,
 			link->verified_link_cap.link_rate,
 			link->verified_link_cap.link_spread);
 	rd_buf_ptr += str_len;
 
-	str_len = strlen("Reported:  %d  %d  %d  ");
-	snprintf(rd_buf_ptr, str_len, "Reported:  %d  %d  %d  ",
+	str_len = strlen("Reported:  %d  0x%x  %d  ");
+	snprintf(rd_buf_ptr, str_len, "Reported:  %d  0x%x  %d  ",
 			link->reported_link_cap.lane_count,
 			link->reported_link_cap.link_rate,
 			link->reported_link_cap.link_spread);
 	rd_buf_ptr += str_len;
 
-	str_len = strlen("Preferred:  %d  %d  %d  ");
-	snprintf(rd_buf_ptr, str_len, "Preferred:  %d  %d  %d\n",
+	str_len = strlen("Preferred:  %d  0x%x  %d  ");
+	snprintf(rd_buf_ptr, str_len, "Preferred:  %d  0x%x  %d\n",
 			link->preferred_link_setting.lane_count,
 			link->preferred_link_setting.link_rate,
 			link->preferred_link_setting.link_spread);
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c
index 1c6e401dd4cc..0eba391e597f 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c
@@ -66,9 +66,11 @@ int rn_get_active_display_cnt_wa(
 	for (i = 0; i < context->stream_count; i++) {
 		const struct dc_stream_state *stream = context->streams[i];
 
+		/* Extend the WA to DP for Linux*/
 		if (stream->signal == SIGNAL_TYPE_HDMI_TYPE_A ||
 				stream->signal == SIGNAL_TYPE_DVI_SINGLE_LINK ||
-				stream->signal == SIGNAL_TYPE_DVI_DUAL_LINK)
+				stream->signal == SIGNAL_TYPE_DVI_DUAL_LINK ||
+				stream->signal == SIGNAL_TYPE_DISPLAY_PORT)
 			tmds_present = true;
 	}
 
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
index 0d1e7b56fb39..532f6a1145b5 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
@@ -3740,13 +3740,12 @@ enum dc_status dcn10_set_clock(struct dc *dc,
 	struct dc_clock_config clock_cfg = {0};
 	struct dc_clocks *current_clocks = &context->bw_ctx.bw.dcn.clk;
 
-	if (dc->clk_mgr && dc->clk_mgr->funcs->get_clock)
-				dc->clk_mgr->funcs->get_clock(dc->clk_mgr,
-						context, clock_type, &clock_cfg);
-
-	if (!dc->clk_mgr->funcs->get_clock)
+	if (!dc->clk_mgr || !dc->clk_mgr->funcs->get_clock)
 		return DC_FAIL_UNSUPPORTED_1;
 
+	dc->clk_mgr->funcs->get_clock(dc->clk_mgr,
+		context, clock_type, &clock_cfg);
+
 	if (clk_khz > clock_cfg.max_clock_khz)
 		return DC_FAIL_CLK_EXCEED_MAX;
 
@@ -3764,7 +3763,7 @@ enum dc_status dcn10_set_clock(struct dc *dc,
 	else
 		return DC_ERROR_UNEXPECTED;
 
-	if (dc->clk_mgr && dc->clk_mgr->funcs->update_clocks)
+	if (dc->clk_mgr->funcs->update_clocks)
 				dc->clk_mgr->funcs->update_clocks(dc->clk_mgr,
 				context, true);
 	return DC_OK;
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c
index 9d3ccdd35582..79a2b9c785f0 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c
@@ -1704,13 +1704,15 @@ void dcn20_program_front_end_for_ctx(
 				dcn20_program_pipe(dc, pipe, context);
 				pipe = pipe->bottom_pipe;
 			}
-			/* Program secondary blending tree and writeback pipes */
-			pipe = &context->res_ctx.pipe_ctx[i];
-			if (!pipe->prev_odm_pipe && pipe->stream->num_wb_info > 0
-					&& (pipe->update_flags.raw || pipe->plane_state->update_flags.raw || pipe->stream->update_flags.raw)
-					&& hws->funcs.program_all_writeback_pipes_in_tree)
-				hws->funcs.program_all_writeback_pipes_in_tree(dc, pipe->stream, context);
 		}
+		/* Program secondary blending tree and writeback pipes */
+		pipe = &context->res_ctx.pipe_ctx[i];
+		if (!pipe->top_pipe && !pipe->prev_odm_pipe
+				&& pipe->stream && pipe->stream->num_wb_info > 0
+				&& (pipe->update_flags.raw || (pipe->plane_state && pipe->plane_state->update_flags.raw)
+					|| pipe->stream->update_flags.raw)
+				&& hws->funcs.program_all_writeback_pipes_in_tree)
+			hws->funcs.program_all_writeback_pipes_in_tree(dc, pipe->stream, context);
 	}
 }
 
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_optc.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_optc.c
index d8b18c515d06..e3cfb442a062 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_optc.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_optc.c
@@ -357,7 +357,7 @@ void optc2_lock_doublebuffer_enable(struct timing_generator *optc)
 
 	REG_UPDATE_2(OTG_GLOBAL_CONTROL1,
 			MASTER_UPDATE_LOCK_DB_X,
-			h_blank_start - 200 - 1,
+			(h_blank_start - 200 - 1) / optc1->opp_count,
 			MASTER_UPDATE_LOCK_DB_Y,
 			v_blank_start - 1);
 }
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
index cfe85ba1018e..5dbc290bcbe8 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
@@ -2455,7 +2455,7 @@ void dcn20_set_mcif_arb_params(
 				wb_arb_params->cli_watermark[k] = get_wm_writeback_urgent(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
 				wb_arb_params->pstate_watermark[k] = get_wm_writeback_dram_clock_change(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
 			}
-			wb_arb_params->time_per_pixel = 16.0 / context->res_ctx.pipe_ctx[i].stream->phy_pix_clk; /* 4 bit fraction, ms */
+			wb_arb_params->time_per_pixel = 16.0 * 1000 / (context->res_ctx.pipe_ctx[i].stream->phy_pix_clk / 1000); /* 4 bit fraction, ms */
 			wb_arb_params->slice_lines = 32;
 			wb_arb_params->arbitration_slice = 2;
 			wb_arb_params->max_scaled_time = dcn20_calc_max_scaled_time(wb_arb_params->time_per_pixel,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dwb_cm.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dwb_cm.c
index 8593145379d9..6d621f07be48 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dwb_cm.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dwb_cm.c
@@ -49,6 +49,11 @@
 static void dwb3_get_reg_field_ogam(struct dcn30_dwbc *dwbc30,
 	struct dcn3_xfer_func_reg *reg)
 {
+	reg->shifts.field_region_start_base = dwbc30->dwbc_shift->DWB_OGAM_RAMA_EXP_REGION_START_BASE_B;
+	reg->masks.field_region_start_base = dwbc30->dwbc_mask->DWB_OGAM_RAMA_EXP_REGION_START_BASE_B;
+	reg->shifts.field_offset = dwbc30->dwbc_shift->DWB_OGAM_RAMA_OFFSET_B;
+	reg->masks.field_offset = dwbc30->dwbc_mask->DWB_OGAM_RAMA_OFFSET_B;
+
 	reg->shifts.exp_region0_lut_offset = dwbc30->dwbc_shift->DWB_OGAM_RAMA_EXP_REGION0_LUT_OFFSET;
 	reg->masks.exp_region0_lut_offset = dwbc30->dwbc_mask->DWB_OGAM_RAMA_EXP_REGION0_LUT_OFFSET;
 	reg->shifts.exp_region0_num_segments = dwbc30->dwbc_shift->DWB_OGAM_RAMA_EXP_REGION0_NUM_SEGMENTS;
@@ -66,8 +71,6 @@ static void dwb3_get_reg_field_ogam(struct dcn30_dwbc *dwbc30,
 	reg->masks.field_region_end_base = dwbc30->dwbc_mask->DWB_OGAM_RAMA_EXP_REGION_END_BASE_B;
 	reg->shifts.field_region_linear_slope = dwbc30->dwbc_shift->DWB_OGAM_RAMA_EXP_REGION_START_SLOPE_B;
 	reg->masks.field_region_linear_slope = dwbc30->dwbc_mask->DWB_OGAM_RAMA_EXP_REGION_START_SLOPE_B;
-	reg->masks.field_offset = dwbc30->dwbc_mask->DWB_OGAM_RAMA_OFFSET_B;
-	reg->shifts.field_offset = dwbc30->dwbc_shift->DWB_OGAM_RAMA_OFFSET_B;
 	reg->shifts.exp_region_start = dwbc30->dwbc_shift->DWB_OGAM_RAMA_EXP_REGION_START_B;
 	reg->masks.exp_region_start = dwbc30->dwbc_mask->DWB_OGAM_RAMA_EXP_REGION_START_B;
 	reg->shifts.exp_resion_start_segment = dwbc30->dwbc_shift->DWB_OGAM_RAMA_EXP_REGION_START_SEGMENT_B;
@@ -147,18 +150,19 @@ static enum dc_lut_mode dwb3_get_ogam_current(
 	uint32_t state_mode;
 	uint32_t ram_select;
 
-	REG_GET(DWB_OGAM_CONTROL,
-		DWB_OGAM_MODE, &state_mode);
-	REG_GET(DWB_OGAM_CONTROL,
-		DWB_OGAM_SELECT, &ram_select);
+	REG_GET_2(DWB_OGAM_CONTROL,
+		DWB_OGAM_MODE_CURRENT, &state_mode,
+		DWB_OGAM_SELECT_CURRENT, &ram_select);
 
 	if (state_mode == 0) {
 		mode = LUT_BYPASS;
 	} else if (state_mode == 2) {
 		if (ram_select == 0)
 			mode = LUT_RAM_A;
-		else
+		else if (ram_select == 1)
 			mode = LUT_RAM_B;
+		else
+			mode = LUT_BYPASS;
 	} else {
 		// Reserved value
 		mode = LUT_BYPASS;
@@ -172,10 +176,10 @@ static void dwb3_configure_ogam_lut(
 	struct dcn30_dwbc *dwbc30,
 	bool is_ram_a)
 {
-	REG_UPDATE(DWB_OGAM_LUT_CONTROL,
-		DWB_OGAM_LUT_READ_COLOR_SEL, 7);
-	REG_UPDATE(DWB_OGAM_CONTROL,
-		DWB_OGAM_SELECT, is_ram_a == true ? 0 : 1);
+	REG_UPDATE_2(DWB_OGAM_LUT_CONTROL,
+		DWB_OGAM_LUT_WRITE_COLOR_MASK, 7,
+		DWB_OGAM_LUT_HOST_SEL, (is_ram_a == true) ? 0 : 1);
+
 	REG_SET(DWB_OGAM_LUT_INDEX, 0, DWB_OGAM_LUT_INDEX, 0);
 }
 
@@ -185,17 +189,45 @@ static void dwb3_program_ogam_pwl(struct dcn30_dwbc *dwbc30,
 {
 	uint32_t i;
 
-    // triple base implementation
-	for (i = 0; i < num/2; i++) {
-		REG_SET(DWB_OGAM_LUT_DATA, 0, DWB_OGAM_LUT_DATA, rgb[2*i+0].red_reg);
-		REG_SET(DWB_OGAM_LUT_DATA, 0, DWB_OGAM_LUT_DATA, rgb[2*i+0].green_reg);
-		REG_SET(DWB_OGAM_LUT_DATA, 0, DWB_OGAM_LUT_DATA, rgb[2*i+0].blue_reg);
-		REG_SET(DWB_OGAM_LUT_DATA, 0, DWB_OGAM_LUT_DATA, rgb[2*i+1].red_reg);
-		REG_SET(DWB_OGAM_LUT_DATA, 0, DWB_OGAM_LUT_DATA, rgb[2*i+1].green_reg);
-		REG_SET(DWB_OGAM_LUT_DATA, 0, DWB_OGAM_LUT_DATA, rgb[2*i+1].blue_reg);
-		REG_SET(DWB_OGAM_LUT_DATA, 0, DWB_OGAM_LUT_DATA, rgb[2*i+2].red_reg);
-		REG_SET(DWB_OGAM_LUT_DATA, 0, DWB_OGAM_LUT_DATA, rgb[2*i+2].green_reg);
-		REG_SET(DWB_OGAM_LUT_DATA, 0, DWB_OGAM_LUT_DATA, rgb[2*i+2].blue_reg);
+	uint32_t last_base_value_red = rgb[num-1].red_reg + rgb[num-1].delta_red_reg;
+	uint32_t last_base_value_green = rgb[num-1].green_reg + rgb[num-1].delta_green_reg;
+	uint32_t last_base_value_blue = rgb[num-1].blue_reg + rgb[num-1].delta_blue_reg;
+
+	if (is_rgb_equal(rgb,  num)) {
+		for (i = 0 ; i < num; i++)
+			REG_SET(DWB_OGAM_LUT_DATA, 0, DWB_OGAM_LUT_DATA, rgb[i].red_reg);
+
+		REG_SET(DWB_OGAM_LUT_DATA, 0, DWB_OGAM_LUT_DATA, last_base_value_red);
+
+	} else {
+
+		REG_UPDATE(DWB_OGAM_LUT_CONTROL,
+				DWB_OGAM_LUT_WRITE_COLOR_MASK, 4);
+
+		for (i = 0 ; i < num; i++)
+			REG_SET(DWB_OGAM_LUT_DATA, 0, DWB_OGAM_LUT_DATA, rgb[i].red_reg);
+
+		REG_SET(DWB_OGAM_LUT_DATA, 0, DWB_OGAM_LUT_DATA, last_base_value_red);
+
+		REG_SET(DWB_OGAM_LUT_INDEX, 0, DWB_OGAM_LUT_INDEX, 0);
+
+		REG_UPDATE(DWB_OGAM_LUT_CONTROL,
+				DWB_OGAM_LUT_WRITE_COLOR_MASK, 2);
+
+		for (i = 0 ; i < num; i++)
+			REG_SET(DWB_OGAM_LUT_DATA, 0, DWB_OGAM_LUT_DATA, rgb[i].green_reg);
+
+		REG_SET(DWB_OGAM_LUT_DATA, 0, DWB_OGAM_LUT_DATA, last_base_value_green);
+
+		REG_SET(DWB_OGAM_LUT_INDEX, 0, DWB_OGAM_LUT_INDEX, 0);
+
+		REG_UPDATE(DWB_OGAM_LUT_CONTROL,
+				DWB_OGAM_LUT_WRITE_COLOR_MASK, 1);
+
+		for (i = 0 ; i < num; i++)
+			REG_SET(DWB_OGAM_LUT_DATA, 0, DWB_OGAM_LUT_DATA, rgb[i].blue_reg);
+
+		REG_SET(DWB_OGAM_LUT_DATA, 0, DWB_OGAM_LUT_DATA, last_base_value_blue);
 	}
 }
 
@@ -211,6 +243,8 @@ static bool dwb3_program_ogam_lut(
 		return false;
 	}
 
+	REG_SET(DWB_OGAM_CONTROL, 0, DWB_OGAM_MODE, 2);
+
 	current_mode = dwb3_get_ogam_current(dwbc30);
 	if (current_mode == LUT_BYPASS || current_mode == LUT_RAM_A)
 		next_mode = LUT_RAM_B;
@@ -227,8 +261,7 @@ static bool dwb3_program_ogam_lut(
 	dwb3_program_ogam_pwl(
 		dwbc30, params->rgb_resulted, params->hw_points_num);
 
-	REG_SET(DWB_OGAM_CONTROL, 0, DWB_OGAM_MODE, 2);
-	REG_SET(DWB_OGAM_CONTROL, 0, DWB_OGAM_SELECT, next_mode == LUT_RAM_A ? 0 : 1);
+	REG_UPDATE(DWB_OGAM_CONTROL, DWB_OGAM_SELECT, next_mode == LUT_RAM_A ? 0 : 1);
 
 	return true;
 }
@@ -271,14 +304,19 @@ static void dwb3_program_gamut_remap(
 
 	struct color_matrices_reg gam_regs;
 
-	REG_UPDATE(DWB_GAMUT_REMAP_COEF_FORMAT, DWB_GAMUT_REMAP_COEF_FORMAT, coef_format);
-
 	if (regval == NULL || select == CM_GAMUT_REMAP_MODE_BYPASS) {
 		REG_SET(DWB_GAMUT_REMAP_MODE, 0,
 				DWB_GAMUT_REMAP_MODE, 0);
 		return;
 	}
 
+	REG_UPDATE(DWB_GAMUT_REMAP_COEF_FORMAT, DWB_GAMUT_REMAP_COEF_FORMAT, coef_format);
+
+	gam_regs.shifts.csc_c11 = dwbc30->dwbc_shift->DWB_GAMUT_REMAPA_C11;
+	gam_regs.masks.csc_c11  = dwbc30->dwbc_mask->DWB_GAMUT_REMAPA_C11;
+	gam_regs.shifts.csc_c12 = dwbc30->dwbc_shift->DWB_GAMUT_REMAPA_C12;
+	gam_regs.masks.csc_c12 = dwbc30->dwbc_mask->DWB_GAMUT_REMAPA_C12;
+
 	switch (select) {
 	case CM_GAMUT_REMAP_MODE_RAMA_COEFF:
 		gam_regs.csc_c11_c12 = REG(DWB_GAMUT_REMAPA_C11_C12);
diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c
index 97909d5aab34..22c77e96f6a5 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c
@@ -396,12 +396,22 @@ void dcn30_program_all_writeback_pipes_in_tree(
 			for (i_pipe = 0; i_pipe < dc->res_pool->pipe_count; i_pipe++) {
 				struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[i_pipe];
 
+				if (!pipe_ctx->plane_state)
+					continue;
+
 				if (pipe_ctx->plane_state == wb_info.writeback_source_plane) {
 					wb_info.mpcc_inst = pipe_ctx->plane_res.mpcc_inst;
 					break;
 				}
 			}
-			ASSERT(wb_info.mpcc_inst != -1);
+
+			if (wb_info.mpcc_inst == -1) {
+				/* Disable writeback pipe and disconnect from MPCC
+				 * if source plane has been removed
+				 */
+				dc->hwss.disable_writeback(dc, wb_info.dwb_pipe_inst);
+				continue;
+			}
 
 			ASSERT(wb_info.dwb_pipe_inst < dc->res_pool->res_cap->num_dwb);
 			dwb = dc->res_pool->dwbc[wb_info.dwb_pipe_inst];
diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c
index e5f4f93317cf..32993ce24a58 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c
@@ -2455,16 +2455,37 @@ void dcn30_update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_params
 	dc->dml.soc.dispclk_dppclk_vco_speed_mhz = dc->clk_mgr->dentist_vco_freq_khz / 1000.0;
 
 	if (bw_params->clk_table.entries[0].memclk_mhz) {
+		int max_dcfclk_mhz = 0, max_dispclk_mhz = 0, max_dppclk_mhz = 0, max_phyclk_mhz = 0;
+
+		for (i = 0; i < MAX_NUM_DPM_LVL; i++) {
+			if (bw_params->clk_table.entries[i].dcfclk_mhz > max_dcfclk_mhz)
+				max_dcfclk_mhz = bw_params->clk_table.entries[i].dcfclk_mhz;
+			if (bw_params->clk_table.entries[i].dispclk_mhz > max_dispclk_mhz)
+				max_dispclk_mhz = bw_params->clk_table.entries[i].dispclk_mhz;
+			if (bw_params->clk_table.entries[i].dppclk_mhz > max_dppclk_mhz)
+				max_dppclk_mhz = bw_params->clk_table.entries[i].dppclk_mhz;
+			if (bw_params->clk_table.entries[i].phyclk_mhz > max_phyclk_mhz)
+				max_phyclk_mhz = bw_params->clk_table.entries[i].phyclk_mhz;
+		}
+
+		if (!max_dcfclk_mhz)
+			max_dcfclk_mhz = dcn3_0_soc.clock_limits[0].dcfclk_mhz;
+		if (!max_dispclk_mhz)
+			max_dispclk_mhz = dcn3_0_soc.clock_limits[0].dispclk_mhz;
+		if (!max_dppclk_mhz)
+			max_dppclk_mhz = dcn3_0_soc.clock_limits[0].dppclk_mhz;
+		if (!max_phyclk_mhz)
+			max_phyclk_mhz = dcn3_0_soc.clock_limits[0].phyclk_mhz;
 
-		if (bw_params->clk_table.entries[1].dcfclk_mhz > dcfclk_sta_targets[num_dcfclk_sta_targets-1]) {
+		if (max_dcfclk_mhz > dcfclk_sta_targets[num_dcfclk_sta_targets-1]) {
 			// If max DCFCLK is greater than the max DCFCLK STA target, insert into the DCFCLK STA target array
-			dcfclk_sta_targets[num_dcfclk_sta_targets] = bw_params->clk_table.entries[1].dcfclk_mhz;
+			dcfclk_sta_targets[num_dcfclk_sta_targets] = max_dcfclk_mhz;
 			num_dcfclk_sta_targets++;
-		} else if (bw_params->clk_table.entries[1].dcfclk_mhz < dcfclk_sta_targets[num_dcfclk_sta_targets-1]) {
+		} else if (max_dcfclk_mhz < dcfclk_sta_targets[num_dcfclk_sta_targets-1]) {
 			// If max DCFCLK is less than the max DCFCLK STA target, cap values and remove duplicates
 			for (i = 0; i < num_dcfclk_sta_targets; i++) {
-				if (dcfclk_sta_targets[i] > bw_params->clk_table.entries[1].dcfclk_mhz) {
-					dcfclk_sta_targets[i] = bw_params->clk_table.entries[1].dcfclk_mhz;
+				if (dcfclk_sta_targets[i] > max_dcfclk_mhz) {
+					dcfclk_sta_targets[i] = max_dcfclk_mhz;
 					break;
 				}
 			}
@@ -2502,7 +2523,7 @@ void dcn30_update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_params
 				dcfclk_mhz[num_states] = dcfclk_sta_targets[i];
 				dram_speed_mts[num_states++] = optimal_uclk_for_dcfclk_sta_targets[i++];
 			} else {
-				if (j < num_uclk_states && optimal_dcfclk_for_uclk[j] <= bw_params->clk_table.entries[1].dcfclk_mhz) {
+				if (j < num_uclk_states && optimal_dcfclk_for_uclk[j] <= max_dcfclk_mhz) {
 					dcfclk_mhz[num_states] = optimal_dcfclk_for_uclk[j];
 					dram_speed_mts[num_states++] = bw_params->clk_table.entries[j++].memclk_mhz * 16;
 				} else {
@@ -2517,11 +2538,12 @@ void dcn30_update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_params
 		}
 
 		while (j < num_uclk_states && num_states < DC__VOLTAGE_STATES &&
-				optimal_dcfclk_for_uclk[j] <= bw_params->clk_table.entries[1].dcfclk_mhz) {
+				optimal_dcfclk_for_uclk[j] <= max_dcfclk_mhz) {
 			dcfclk_mhz[num_states] = optimal_dcfclk_for_uclk[j];
 			dram_speed_mts[num_states++] = bw_params->clk_table.entries[j++].memclk_mhz * 16;
 		}
 
+		dcn3_0_soc.num_states = num_states;
 		for (i = 0; i < dcn3_0_soc.num_states; i++) {
 			dcn3_0_soc.clock_limits[i].state = i;
 			dcn3_0_soc.clock_limits[i].dcfclk_mhz = dcfclk_mhz[i];
@@ -2529,9 +2551,9 @@ void dcn30_update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_params
 			dcn3_0_soc.clock_limits[i].dram_speed_mts = dram_speed_mts[i];
 
 			/* Fill all states with max values of all other clocks */
-			dcn3_0_soc.clock_limits[i].dispclk_mhz = bw_params->clk_table.entries[1].dispclk_mhz;
-			dcn3_0_soc.clock_limits[i].dppclk_mhz  = bw_params->clk_table.entries[1].dppclk_mhz;
-			dcn3_0_soc.clock_limits[i].phyclk_mhz  = bw_params->clk_table.entries[1].phyclk_mhz;
+			dcn3_0_soc.clock_limits[i].dispclk_mhz = max_dispclk_mhz;
+			dcn3_0_soc.clock_limits[i].dppclk_mhz  = max_dppclk_mhz;
+			dcn3_0_soc.clock_limits[i].phyclk_mhz  = max_phyclk_mhz;
 			dcn3_0_soc.clock_limits[i].dtbclk_mhz = dcn3_0_soc.clock_limits[0].dtbclk_mhz;
 			/* These clocks cannot come from bw_params, always fill from dcn3_0_soc[1] */
 			/* FCLK, PHYCLK_D18, SOCCLK, DSCCLK */
diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c
index 132c269c7c89..4dc27ec4d012 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c
@@ -5122,6 +5122,13 @@ static int vega10_get_power_profile_mode(struct pp_hwmgr *hwmgr, char *buf)
 	return size;
 }
 
+static bool vega10_get_power_profile_mode_quirks(struct pp_hwmgr *hwmgr)
+{
+	struct amdgpu_device *adev = hwmgr->adev;
+
+	return (adev->pdev->device == 0x6860);
+}
+
 static int vega10_set_power_profile_mode(struct pp_hwmgr *hwmgr, long *input, uint32_t size)
 {
 	struct vega10_hwmgr *data = hwmgr->backend;
@@ -5158,9 +5165,15 @@ static int vega10_set_power_profile_mode(struct pp_hwmgr *hwmgr, long *input, ui
 	}
 
 out:
-	smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_SetWorkloadMask,
+	if (vega10_get_power_profile_mode_quirks(hwmgr))
+		smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_SetWorkloadMask,
+						1 << power_profile_mode,
+						NULL);
+	else
+		smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_SetWorkloadMask,
 						(!power_profile_mode) ? 0 : 1 << (power_profile_mode - 1),
 						NULL);
+
 	hwmgr->power_profile_mode = power_profile_mode;
 
 	return 0;
diff --git a/drivers/gpu/drm/bridge/nwl-dsi.c b/drivers/gpu/drm/bridge/nwl-dsi.c
index c65ca860712d..6cac2e58cd15 100644
--- a/drivers/gpu/drm/bridge/nwl-dsi.c
+++ b/drivers/gpu/drm/bridge/nwl-dsi.c
@@ -196,7 +196,7 @@ static u32 ps2bc(struct nwl_dsi *dsi, unsigned long long ps)
 	u32 bpp = mipi_dsi_pixel_format_to_bpp(dsi->format);
 
 	return DIV64_U64_ROUND_UP(ps * dsi->mode.clock * bpp,
-				  dsi->lanes * 8 * NSEC_PER_SEC);
+				  dsi->lanes * 8ULL * NSEC_PER_SEC);
 }
 
 /*
diff --git a/drivers/gpu/drm/drm_auth.c b/drivers/gpu/drm/drm_auth.c
index 232abbba3686..c7adbeaf10b1 100644
--- a/drivers/gpu/drm/drm_auth.c
+++ b/drivers/gpu/drm/drm_auth.c
@@ -135,16 +135,18 @@ static void drm_set_master(struct drm_device *dev, struct drm_file *fpriv,
 static int drm_new_set_master(struct drm_device *dev, struct drm_file *fpriv)
 {
 	struct drm_master *old_master;
+	struct drm_master *new_master;
 
 	lockdep_assert_held_once(&dev->master_mutex);
 
 	WARN_ON(fpriv->is_master);
 	old_master = fpriv->master;
-	fpriv->master = drm_master_create(dev);
-	if (!fpriv->master) {
-		fpriv->master = old_master;
+	new_master = drm_master_create(dev);
+	if (!new_master)
 		return -ENOMEM;
-	}
+	spin_lock(&fpriv->master_lookup_lock);
+	fpriv->master = new_master;
+	spin_unlock(&fpriv->master_lookup_lock);
 
 	fpriv->is_master = 1;
 	fpriv->authenticated = 1;
@@ -302,10 +304,13 @@ int drm_master_open(struct drm_file *file_priv)
 	/* if there is no current master make this fd it, but do not create
 	 * any master object for render clients */
 	mutex_lock(&dev->master_mutex);
-	if (!dev->master)
+	if (!dev->master) {
 		ret = drm_new_set_master(dev, file_priv);
-	else
+	} else {
+		spin_lock(&file_priv->master_lookup_lock);
 		file_priv->master = drm_master_get(dev->master);
+		spin_unlock(&file_priv->master_lookup_lock);
+	}
 	mutex_unlock(&dev->master_mutex);
 
 	return ret;
@@ -371,6 +376,31 @@ struct drm_master *drm_master_get(struct drm_master *master)
 }
 EXPORT_SYMBOL(drm_master_get);
 
+/**
+ * drm_file_get_master - reference &drm_file.master of @file_priv
+ * @file_priv: DRM file private
+ *
+ * Increments the reference count of @file_priv's &drm_file.master and returns
+ * the &drm_file.master. If @file_priv has no &drm_file.master, returns NULL.
+ *
+ * Master pointers returned from this function should be unreferenced using
+ * drm_master_put().
+ */
+struct drm_master *drm_file_get_master(struct drm_file *file_priv)
+{
+	struct drm_master *master = NULL;
+
+	spin_lock(&file_priv->master_lookup_lock);
+	if (!file_priv->master)
+		goto unlock;
+	master = drm_master_get(file_priv->master);
+
+unlock:
+	spin_unlock(&file_priv->master_lookup_lock);
+	return master;
+}
+EXPORT_SYMBOL(drm_file_get_master);
+
 static void drm_master_destroy(struct kref *kref)
 {
 	struct drm_master *master = container_of(kref, struct drm_master, refcount);
diff --git a/drivers/gpu/drm/drm_debugfs.c b/drivers/gpu/drm/drm_debugfs.c
index 3d7182001004..b0a826489488 100644
--- a/drivers/gpu/drm/drm_debugfs.c
+++ b/drivers/gpu/drm/drm_debugfs.c
@@ -91,6 +91,7 @@ static int drm_clients_info(struct seq_file *m, void *data)
 	mutex_lock(&dev->filelist_mutex);
 	list_for_each_entry_reverse(priv, &dev->filelist, lhead) {
 		struct task_struct *task;
+		bool is_current_master = drm_is_current_master(priv);
 
 		rcu_read_lock(); /* locks pid_task()->comm */
 		task = pid_task(priv->pid, PIDTYPE_PID);
@@ -99,7 +100,7 @@ static int drm_clients_info(struct seq_file *m, void *data)
 			   task ? task->comm : "<unknown>",
 			   pid_vnr(priv->pid),
 			   priv->minor->index,
-			   drm_is_current_master(priv) ? 'y' : 'n',
+			   is_current_master ? 'y' : 'n',
 			   priv->authenticated ? 'y' : 'n',
 			   from_kuid_munged(seq_user_ns(m), uid),
 			   priv->magic);
diff --git a/drivers/gpu/drm/drm_dp_mst_topology.c b/drivers/gpu/drm/drm_dp_mst_topology.c
index 861f16dfd1a3..1f54e9470165 100644
--- a/drivers/gpu/drm/drm_dp_mst_topology.c
+++ b/drivers/gpu/drm/drm_dp_mst_topology.c
@@ -2869,11 +2869,13 @@ static int process_single_tx_qlock(struct drm_dp_mst_topology_mgr *mgr,
 	idx += tosend + 1;
 
 	ret = drm_dp_send_sideband_msg(mgr, up, chunk, idx);
-	if (unlikely(ret) && drm_debug_enabled(DRM_UT_DP)) {
-		struct drm_printer p = drm_debug_printer(DBG_PREFIX);
+	if (ret) {
+		if (drm_debug_enabled(DRM_UT_DP)) {
+			struct drm_printer p = drm_debug_printer(DBG_PREFIX);
 
-		drm_printf(&p, "sideband msg failed to send\n");
-		drm_dp_mst_dump_sideband_msg_tx(&p, txmsg);
+			drm_printf(&p, "sideband msg failed to send\n");
+			drm_dp_mst_dump_sideband_msg_tx(&p, txmsg);
+		}
 		return ret;
 	}
 
diff --git a/drivers/gpu/drm/drm_file.c b/drivers/gpu/drm/drm_file.c
index 0ac4566ae3f4..537e7de8e9c3 100644
--- a/drivers/gpu/drm/drm_file.c
+++ b/drivers/gpu/drm/drm_file.c
@@ -177,6 +177,7 @@ struct drm_file *drm_file_alloc(struct drm_minor *minor)
 	init_waitqueue_head(&file->event_wait);
 	file->event_space = 4096; /* set aside 4k for event buffer */
 
+	spin_lock_init(&file->master_lookup_lock);
 	mutex_init(&file->event_read_lock);
 
 	if (drm_core_check_feature(dev, DRIVER_GEM))
diff --git a/drivers/gpu/drm/drm_ioc32.c b/drivers/gpu/drm/drm_ioc32.c
index dc734d4828a1..aaf8d625ce1a 100644
--- a/drivers/gpu/drm/drm_ioc32.c
+++ b/drivers/gpu/drm/drm_ioc32.c
@@ -865,8 +865,6 @@ static int compat_drm_wait_vblank(struct file *file, unsigned int cmd,
 	req.request.sequence = req32.request.sequence;
 	req.request.signal = req32.request.signal;
 	err = drm_ioctl_kernel(file, drm_wait_vblank_ioctl, &req, DRM_UNLOCKED);
-	if (err)
-		return err;
 
 	req32.reply.type = req.reply.type;
 	req32.reply.sequence = req.reply.sequence;
@@ -875,7 +873,7 @@ static int compat_drm_wait_vblank(struct file *file, unsigned int cmd,
 	if (copy_to_user(argp, &req32, sizeof(req32)))
 		return -EFAULT;
 
-	return 0;
+	return err;
 }
 
 #if defined(CONFIG_X86)
diff --git a/drivers/gpu/drm/drm_lease.c b/drivers/gpu/drm/drm_lease.c
index da4f085fc09e..aef22634005e 100644
--- a/drivers/gpu/drm/drm_lease.c
+++ b/drivers/gpu/drm/drm_lease.c
@@ -107,10 +107,19 @@ static bool _drm_has_leased(struct drm_master *master, int id)
  */
 bool _drm_lease_held(struct drm_file *file_priv, int id)
 {
-	if (!file_priv || !file_priv->master)
+	bool ret;
+	struct drm_master *master;
+
+	if (!file_priv)
 		return true;
 
-	return _drm_lease_held_master(file_priv->master, id);
+	master = drm_file_get_master(file_priv);
+	if (!master)
+		return true;
+	ret = _drm_lease_held_master(master, id);
+	drm_master_put(&master);
+
+	return ret;
 }
 
 /**
@@ -129,13 +138,22 @@ bool drm_lease_held(struct drm_file *file_priv, int id)
 	struct drm_master *master;
 	bool ret;
 
-	if (!file_priv || !file_priv->master || !file_priv->master->lessor)
+	if (!file_priv)
 		return true;
 
-	master = file_priv->master;
+	master = drm_file_get_master(file_priv);
+	if (!master)
+		return true;
+	if (!master->lessor) {
+		ret = true;
+		goto out;
+	}
 	mutex_lock(&master->dev->mode_config.idr_mutex);
 	ret = _drm_lease_held_master(master, id);
 	mutex_unlock(&master->dev->mode_config.idr_mutex);
+
+out:
+	drm_master_put(&master);
 	return ret;
 }
 
@@ -155,10 +173,16 @@ uint32_t drm_lease_filter_crtcs(struct drm_file *file_priv, uint32_t crtcs_in)
 	int count_in, count_out;
 	uint32_t crtcs_out = 0;
 
-	if (!file_priv || !file_priv->master || !file_priv->master->lessor)
+	if (!file_priv)
 		return crtcs_in;
 
-	master = file_priv->master;
+	master = drm_file_get_master(file_priv);
+	if (!master)
+		return crtcs_in;
+	if (!master->lessor) {
+		crtcs_out = crtcs_in;
+		goto out;
+	}
 	dev = master->dev;
 
 	count_in = count_out = 0;
@@ -177,6 +201,9 @@ uint32_t drm_lease_filter_crtcs(struct drm_file *file_priv, uint32_t crtcs_in)
 		count_in++;
 	}
 	mutex_unlock(&master->dev->mode_config.idr_mutex);
+
+out:
+	drm_master_put(&master);
 	return crtcs_out;
 }
 
@@ -490,7 +517,7 @@ int drm_mode_create_lease_ioctl(struct drm_device *dev,
 	size_t object_count;
 	int ret = 0;
 	struct idr leases;
-	struct drm_master *lessor = lessor_priv->master;
+	struct drm_master *lessor;
 	struct drm_master *lessee = NULL;
 	struct file *lessee_file = NULL;
 	struct file *lessor_file = lessor_priv->filp;
@@ -502,12 +529,6 @@ int drm_mode_create_lease_ioctl(struct drm_device *dev,
 	if (!drm_core_check_feature(dev, DRIVER_MODESET))
 		return -EOPNOTSUPP;
 
-	/* Do not allow sub-leases */
-	if (lessor->lessor) {
-		DRM_DEBUG_LEASE("recursive leasing not allowed\n");
-		return -EINVAL;
-	}
-
 	/* need some objects */
 	if (cl->object_count == 0) {
 		DRM_DEBUG_LEASE("no objects in lease\n");
@@ -519,12 +540,22 @@ int drm_mode_create_lease_ioctl(struct drm_device *dev,
 		return -EINVAL;
 	}
 
+	lessor = drm_file_get_master(lessor_priv);
+	/* Do not allow sub-leases */
+	if (lessor->lessor) {
+		DRM_DEBUG_LEASE("recursive leasing not allowed\n");
+		ret = -EINVAL;
+		goto out_lessor;
+	}
+
 	object_count = cl->object_count;
 
 	object_ids = memdup_user(u64_to_user_ptr(cl->object_ids),
 			array_size(object_count, sizeof(__u32)));
-	if (IS_ERR(object_ids))
-		return PTR_ERR(object_ids);
+	if (IS_ERR(object_ids)) {
+		ret = PTR_ERR(object_ids);
+		goto out_lessor;
+	}
 
 	idr_init(&leases);
 
@@ -535,14 +566,15 @@ int drm_mode_create_lease_ioctl(struct drm_device *dev,
 	if (ret) {
 		DRM_DEBUG_LEASE("lease object lookup failed: %i\n", ret);
 		idr_destroy(&leases);
-		return ret;
+		goto out_lessor;
 	}
 
 	/* Allocate a file descriptor for the lease */
 	fd = get_unused_fd_flags(cl->flags & (O_CLOEXEC | O_NONBLOCK));
 	if (fd < 0) {
 		idr_destroy(&leases);
-		return fd;
+		ret = fd;
+		goto out_lessor;
 	}
 
 	DRM_DEBUG_LEASE("Creating lease\n");
@@ -578,6 +610,7 @@ int drm_mode_create_lease_ioctl(struct drm_device *dev,
 	/* Hook up the fd */
 	fd_install(fd, lessee_file);
 
+	drm_master_put(&lessor);
 	DRM_DEBUG_LEASE("drm_mode_create_lease_ioctl succeeded\n");
 	return 0;
 
@@ -587,6 +620,8 @@ out_lessee:
 out_leases:
 	put_unused_fd(fd);
 
+out_lessor:
+	drm_master_put(&lessor);
 	DRM_DEBUG_LEASE("drm_mode_create_lease_ioctl failed: %d\n", ret);
 	return ret;
 }
@@ -609,7 +644,7 @@ int drm_mode_list_lessees_ioctl(struct drm_device *dev,
 	struct drm_mode_list_lessees *arg = data;
 	__u32 __user *lessee_ids = (__u32 __user *) (uintptr_t) (arg->lessees_ptr);
 	__u32 count_lessees = arg->count_lessees;
-	struct drm_master *lessor = lessor_priv->master, *lessee;
+	struct drm_master *lessor, *lessee;
 	int count;
 	int ret = 0;
 
@@ -620,6 +655,7 @@ int drm_mode_list_lessees_ioctl(struct drm_device *dev,
 	if (!drm_core_check_feature(dev, DRIVER_MODESET))
 		return -EOPNOTSUPP;
 
+	lessor = drm_file_get_master(lessor_priv);
 	DRM_DEBUG_LEASE("List lessees for %d\n", lessor->lessee_id);
 
 	mutex_lock(&dev->mode_config.idr_mutex);
@@ -643,6 +679,7 @@ int drm_mode_list_lessees_ioctl(struct drm_device *dev,
 		arg->count_lessees = count;
 
 	mutex_unlock(&dev->mode_config.idr_mutex);
+	drm_master_put(&lessor);
 
 	return ret;
 }
@@ -662,7 +699,7 @@ int drm_mode_get_lease_ioctl(struct drm_device *dev,
 	struct drm_mode_get_lease *arg = data;
 	__u32 __user *object_ids = (__u32 __user *) (uintptr_t) (arg->objects_ptr);
 	__u32 count_objects = arg->count_objects;
-	struct drm_master *lessee = lessee_priv->master;
+	struct drm_master *lessee;
 	struct idr *object_idr;
 	int count;
 	void *entry;
@@ -676,6 +713,7 @@ int drm_mode_get_lease_ioctl(struct drm_device *dev,
 	if (!drm_core_check_feature(dev, DRIVER_MODESET))
 		return -EOPNOTSUPP;
 
+	lessee = drm_file_get_master(lessee_priv);
 	DRM_DEBUG_LEASE("get lease for %d\n", lessee->lessee_id);
 
 	mutex_lock(&dev->mode_config.idr_mutex);
@@ -703,6 +741,7 @@ int drm_mode_get_lease_ioctl(struct drm_device *dev,
 		arg->count_objects = count;
 
 	mutex_unlock(&dev->mode_config.idr_mutex);
+	drm_master_put(&lessee);
 
 	return ret;
 }
@@ -721,7 +760,7 @@ int drm_mode_revoke_lease_ioctl(struct drm_device *dev,
 				void *data, struct drm_file *lessor_priv)
 {
 	struct drm_mode_revoke_lease *arg = data;
-	struct drm_master *lessor = lessor_priv->master;
+	struct drm_master *lessor;
 	struct drm_master *lessee;
 	int ret = 0;
 
@@ -731,6 +770,7 @@ int drm_mode_revoke_lease_ioctl(struct drm_device *dev,
 	if (!drm_core_check_feature(dev, DRIVER_MODESET))
 		return -EOPNOTSUPP;
 
+	lessor = drm_file_get_master(lessor_priv);
 	mutex_lock(&dev->mode_config.idr_mutex);
 
 	lessee = _drm_find_lessee(lessor, arg->lessee_id);
@@ -751,6 +791,7 @@ int drm_mode_revoke_lease_ioctl(struct drm_device *dev,
 
 fail:
 	mutex_unlock(&dev->mode_config.idr_mutex);
+	drm_master_put(&lessor);
 
 	return ret;
 }
diff --git a/drivers/gpu/drm/drm_of.c b/drivers/gpu/drm/drm_of.c
index ca04c34e8251..997b8827fed2 100644
--- a/drivers/gpu/drm/drm_of.c
+++ b/drivers/gpu/drm/drm_of.c
@@ -315,7 +315,7 @@ static int drm_of_lvds_get_remote_pixels_type(
 
 		remote_port = of_graph_get_remote_port(endpoint);
 		if (!remote_port) {
-			of_node_put(remote_port);
+			of_node_put(endpoint);
 			return -EPIPE;
 		}
 
@@ -331,8 +331,10 @@ static int drm_of_lvds_get_remote_pixels_type(
 		 * configurations by passing the endpoints explicitly to
 		 * drm_of_lvds_get_dual_link_pixel_order().
 		 */
-		if (!current_pt || pixels_type != current_pt)
+		if (!current_pt || pixels_type != current_pt) {
+			of_node_put(endpoint);
 			return -EINVAL;
+		}
 	}
 
 	return pixels_type;
diff --git a/drivers/gpu/drm/exynos/exynos_drm_dma.c b/drivers/gpu/drm/exynos/exynos_drm_dma.c
index 0644936afee2..bf33c3084cb4 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_dma.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_dma.c
@@ -115,6 +115,8 @@ int exynos_drm_register_dma(struct drm_device *drm, struct device *dev,
 				EXYNOS_DEV_ADDR_START, EXYNOS_DEV_ADDR_SIZE);
 		else if (IS_ENABLED(CONFIG_IOMMU_DMA))
 			mapping = iommu_get_domain_for_dev(priv->dma_dev);
+		else
+			mapping = ERR_PTR(-ENODEV);
 
 		if (IS_ERR(mapping))
 			return PTR_ERR(mapping);
diff --git a/drivers/gpu/drm/gma500/oaktrail_lvds.c b/drivers/gpu/drm/gma500/oaktrail_lvds.c
index 2828360153d1..30b949d6856c 100644
--- a/drivers/gpu/drm/gma500/oaktrail_lvds.c
+++ b/drivers/gpu/drm/gma500/oaktrail_lvds.c
@@ -117,7 +117,7 @@ static void oaktrail_lvds_mode_set(struct drm_encoder *encoder,
 			continue;
 	}
 
-	if (!connector) {
+	if (list_entry_is_head(connector, &mode_config->connector_list, head)) {
 		DRM_ERROR("Couldn't find connector when setting mode");
 		gma_power_end(dev);
 		return;
diff --git a/drivers/gpu/drm/i915/gt/intel_timeline.c b/drivers/gpu/drm/i915/gt/intel_timeline.c
index 8015964043eb..e25385ad2c1e 100644
--- a/drivers/gpu/drm/i915/gt/intel_timeline.c
+++ b/drivers/gpu/drm/i915/gt/intel_timeline.c
@@ -296,6 +296,14 @@ static void intel_timeline_fini(struct intel_timeline *timeline)
 		i915_gem_object_unpin_map(timeline->hwsp_ggtt->obj);
 
 	i915_vma_put(timeline->hwsp_ggtt);
+
+	/*
+	 * A small race exists between intel_gt_retire_requests_timeout and
+	 * intel_timeline_exit which could result in the syncmap not getting
+	 * free'd. Rather than work to hard to seal this race, simply cleanup
+	 * the syncmap on fini.
+	 */
+	i915_syncmap_free(&timeline->sync);
 }
 
 struct intel_timeline *
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c
index 3064eac1a750..e747ff7ba3dc 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c
@@ -34,6 +34,7 @@
 
 #define DISP_AAL_EN				0x0000
 #define DISP_AAL_SIZE				0x0030
+#define DISP_AAL_OUTPUT_SIZE			0x04d8
 
 #define DISP_CCORR_EN				0x0000
 #define CCORR_EN				BIT(0)
@@ -180,7 +181,8 @@ static void mtk_aal_config(struct mtk_ddp_comp *comp, unsigned int w,
 			   unsigned int h, unsigned int vrefresh,
 			   unsigned int bpc, struct cmdq_pkt *cmdq_pkt)
 {
-	mtk_ddp_write(cmdq_pkt, h << 16 | w, comp, DISP_AAL_SIZE);
+	mtk_ddp_write(cmdq_pkt, w << 16 | h, comp, DISP_AAL_SIZE);
+	mtk_ddp_write(cmdq_pkt, w << 16 | h, comp, DISP_AAL_OUTPUT_SIZE);
 }
 
 static void mtk_aal_start(struct mtk_ddp_comp *comp)
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.h b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.h
index 1d9e00b69462..5aa52b7afeec 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.h
+++ b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.h
@@ -7,6 +7,7 @@
 #define MTK_DRM_DDP_COMP_H
 
 #include <linux/io.h>
+#include <linux/soc/mediatek/mtk-mmsys.h>
 
 struct device;
 struct device_node;
@@ -35,39 +36,6 @@ enum mtk_ddp_comp_type {
 	MTK_DDP_COMP_TYPE_MAX,
 };
 
-enum mtk_ddp_comp_id {
-	DDP_COMPONENT_AAL0,
-	DDP_COMPONENT_AAL1,
-	DDP_COMPONENT_BLS,
-	DDP_COMPONENT_CCORR,
-	DDP_COMPONENT_COLOR0,
-	DDP_COMPONENT_COLOR1,
-	DDP_COMPONENT_DITHER,
-	DDP_COMPONENT_DPI0,
-	DDP_COMPONENT_DPI1,
-	DDP_COMPONENT_DSI0,
-	DDP_COMPONENT_DSI1,
-	DDP_COMPONENT_DSI2,
-	DDP_COMPONENT_DSI3,
-	DDP_COMPONENT_GAMMA,
-	DDP_COMPONENT_OD0,
-	DDP_COMPONENT_OD1,
-	DDP_COMPONENT_OVL0,
-	DDP_COMPONENT_OVL_2L0,
-	DDP_COMPONENT_OVL_2L1,
-	DDP_COMPONENT_OVL1,
-	DDP_COMPONENT_PWM0,
-	DDP_COMPONENT_PWM1,
-	DDP_COMPONENT_PWM2,
-	DDP_COMPONENT_RDMA0,
-	DDP_COMPONENT_RDMA1,
-	DDP_COMPONENT_RDMA2,
-	DDP_COMPONENT_UFOE,
-	DDP_COMPONENT_WDMA0,
-	DDP_COMPONENT_WDMA1,
-	DDP_COMPONENT_ID_MAX,
-};
-
 struct mtk_ddp_comp;
 struct cmdq_pkt;
 struct mtk_ddp_comp_funcs {
diff --git a/drivers/gpu/drm/mgag200/mgag200_drv.h b/drivers/gpu/drm/mgag200/mgag200_drv.h
index 749a075fe9e4..d1b51c133e27 100644
--- a/drivers/gpu/drm/mgag200/mgag200_drv.h
+++ b/drivers/gpu/drm/mgag200/mgag200_drv.h
@@ -43,6 +43,22 @@
 #define ATTR_INDEX 0x1fc0
 #define ATTR_DATA 0x1fc1
 
+#define WREG_MISC(v)						\
+	WREG8(MGA_MISC_OUT, v)
+
+#define RREG_MISC(v)						\
+	((v) = RREG8(MGA_MISC_IN))
+
+#define WREG_MISC_MASKED(v, mask)				\
+	do {							\
+		u8 misc_;					\
+		u8 mask_ = (mask);				\
+		RREG_MISC(misc_);				\
+		misc_ &= ~mask_;				\
+		misc_ |= ((v) & mask_);				\
+		WREG_MISC(misc_);				\
+	} while (0)
+
 #define WREG_ATTR(reg, v)					\
 	do {							\
 		RREG8(0x1fda);					\
diff --git a/drivers/gpu/drm/mgag200/mgag200_mode.c b/drivers/gpu/drm/mgag200/mgag200_mode.c
index 38672f9e5c4f..509968c0d16b 100644
--- a/drivers/gpu/drm/mgag200/mgag200_mode.c
+++ b/drivers/gpu/drm/mgag200/mgag200_mode.c
@@ -172,6 +172,8 @@ static int mgag200_g200_set_plls(struct mga_device *mdev, long clock)
 	drm_dbg_kms(dev, "clock: %ld vco: %ld m: %d n: %d p: %d s: %d\n",
 		    clock, f_vco, m, n, p, s);
 
+	WREG_MISC_MASKED(MGAREG_MISC_CLKSEL_MGA, MGAREG_MISC_CLKSEL_MASK);
+
 	WREG_DAC(MGA1064_PIX_PLLC_M, m);
 	WREG_DAC(MGA1064_PIX_PLLC_N, n);
 	WREG_DAC(MGA1064_PIX_PLLC_P, (p | (s << 3)));
@@ -287,6 +289,8 @@ static int mga_g200se_set_plls(struct mga_device *mdev, long clock)
 		return 1;
 	}
 
+	WREG_MISC_MASKED(MGAREG_MISC_CLKSEL_MGA, MGAREG_MISC_CLKSEL_MASK);
+
 	WREG_DAC(MGA1064_PIX_PLLC_M, m);
 	WREG_DAC(MGA1064_PIX_PLLC_N, n);
 	WREG_DAC(MGA1064_PIX_PLLC_P, p);
@@ -383,6 +387,8 @@ static int mga_g200wb_set_plls(struct mga_device *mdev, long clock)
 		}
 	}
 
+	WREG_MISC_MASKED(MGAREG_MISC_CLKSEL_MGA, MGAREG_MISC_CLKSEL_MASK);
+
 	for (i = 0; i <= 32 && pll_locked == false; i++) {
 		if (i > 0) {
 			WREG8(MGAREG_CRTC_INDEX, 0x1e);
@@ -520,6 +526,8 @@ static int mga_g200ev_set_plls(struct mga_device *mdev, long clock)
 		}
 	}
 
+	WREG_MISC_MASKED(MGAREG_MISC_CLKSEL_MGA, MGAREG_MISC_CLKSEL_MASK);
+
 	WREG8(DAC_INDEX, MGA1064_PIX_CLK_CTL);
 	tmp = RREG8(DAC_DATA);
 	tmp |= MGA1064_PIX_CLK_CTL_CLK_DIS;
@@ -652,6 +660,9 @@ static int mga_g200eh_set_plls(struct mga_device *mdev, long clock)
 			}
 		}
 	}
+
+	WREG_MISC_MASKED(MGAREG_MISC_CLKSEL_MGA, MGAREG_MISC_CLKSEL_MASK);
+
 	for (i = 0; i <= 32 && pll_locked == false; i++) {
 		WREG8(DAC_INDEX, MGA1064_PIX_CLK_CTL);
 		tmp = RREG8(DAC_DATA);
@@ -752,6 +763,8 @@ static int mga_g200er_set_plls(struct mga_device *mdev, long clock)
 		}
 	}
 
+	WREG_MISC_MASKED(MGAREG_MISC_CLKSEL_MGA, MGAREG_MISC_CLKSEL_MASK);
+
 	WREG8(DAC_INDEX, MGA1064_PIX_CLK_CTL);
 	tmp = RREG8(DAC_DATA);
 	tmp |= MGA1064_PIX_CLK_CTL_CLK_DIS;
@@ -785,8 +798,6 @@ static int mga_g200er_set_plls(struct mga_device *mdev, long clock)
 
 static int mgag200_crtc_set_plls(struct mga_device *mdev, long clock)
 {
-	u8 misc;
-
 	switch(mdev->type) {
 	case G200_PCI:
 	case G200_AGP:
@@ -811,11 +822,6 @@ static int mgag200_crtc_set_plls(struct mga_device *mdev, long clock)
 		break;
 	}
 
-	misc = RREG8(MGA_MISC_IN);
-	misc &= ~MGAREG_MISC_CLK_SEL_MASK;
-	misc |= MGAREG_MISC_CLK_SEL_MGA_MSK;
-	WREG8(MGA_MISC_OUT, misc);
-
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/mgag200/mgag200_reg.h b/drivers/gpu/drm/mgag200/mgag200_reg.h
index 977be0565c06..60e705283fe8 100644
--- a/drivers/gpu/drm/mgag200/mgag200_reg.h
+++ b/drivers/gpu/drm/mgag200/mgag200_reg.h
@@ -222,11 +222,10 @@
 
 #define MGAREG_MISC_IOADSEL	(0x1 << 0)
 #define MGAREG_MISC_RAMMAPEN	(0x1 << 1)
-#define MGAREG_MISC_CLK_SEL_MASK	GENMASK(3, 2)
-#define MGAREG_MISC_CLK_SEL_VGA25	(0x0 << 2)
-#define MGAREG_MISC_CLK_SEL_VGA28	(0x1 << 2)
-#define MGAREG_MISC_CLK_SEL_MGA_PIX	(0x2 << 2)
-#define MGAREG_MISC_CLK_SEL_MGA_MSK	(0x3 << 2)
+#define MGAREG_MISC_CLKSEL_MASK		GENMASK(3, 2)
+#define MGAREG_MISC_CLKSEL_VGA25	(0x0 << 2)
+#define MGAREG_MISC_CLKSEL_VGA28	(0x1 << 2)
+#define MGAREG_MISC_CLKSEL_MGA		(0x3 << 2)
 #define MGAREG_MISC_VIDEO_DIS	(0x1 << 4)
 #define MGAREG_MISC_HIGH_PG_SEL	(0x1 << 5)
 #define MGAREG_MISC_HSYNCPOL		BIT(6)
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.c
index 758c355b4fd8..f8c7100a8acb 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.c
@@ -340,10 +340,12 @@ static void dpu_hw_ctl_clear_all_blendstages(struct dpu_hw_ctl *ctx)
 	int i;
 
 	for (i = 0; i < ctx->mixer_count; i++) {
-		DPU_REG_WRITE(c, CTL_LAYER(LM_0 + i), 0);
-		DPU_REG_WRITE(c, CTL_LAYER_EXT(LM_0 + i), 0);
-		DPU_REG_WRITE(c, CTL_LAYER_EXT2(LM_0 + i), 0);
-		DPU_REG_WRITE(c, CTL_LAYER_EXT3(LM_0 + i), 0);
+		enum dpu_lm mixer_id = ctx->mixer_hw_caps[i].id;
+
+		DPU_REG_WRITE(c, CTL_LAYER(mixer_id), 0);
+		DPU_REG_WRITE(c, CTL_LAYER_EXT(mixer_id), 0);
+		DPU_REG_WRITE(c, CTL_LAYER_EXT2(mixer_id), 0);
+		DPU_REG_WRITE(c, CTL_LAYER_EXT3(mixer_id), 0);
 	}
 }
 
diff --git a/drivers/gpu/drm/msm/disp/mdp4/mdp4_kms.c b/drivers/gpu/drm/msm/disp/mdp4/mdp4_kms.c
index 2f75e3905202..913de5938782 100644
--- a/drivers/gpu/drm/msm/disp/mdp4/mdp4_kms.c
+++ b/drivers/gpu/drm/msm/disp/mdp4/mdp4_kms.c
@@ -19,30 +19,12 @@ static int mdp4_hw_init(struct msm_kms *kms)
 {
 	struct mdp4_kms *mdp4_kms = to_mdp4_kms(to_mdp_kms(kms));
 	struct drm_device *dev = mdp4_kms->dev;
-	uint32_t version, major, minor, dmap_cfg, vg_cfg;
+	u32 dmap_cfg, vg_cfg;
 	unsigned long clk;
 	int ret = 0;
 
 	pm_runtime_get_sync(dev->dev);
 
-	mdp4_enable(mdp4_kms);
-	version = mdp4_read(mdp4_kms, REG_MDP4_VERSION);
-	mdp4_disable(mdp4_kms);
-
-	major = FIELD(version, MDP4_VERSION_MAJOR);
-	minor = FIELD(version, MDP4_VERSION_MINOR);
-
-	DBG("found MDP4 version v%d.%d", major, minor);
-
-	if (major != 4) {
-		DRM_DEV_ERROR(dev->dev, "unexpected MDP version: v%d.%d\n",
-				major, minor);
-		ret = -ENXIO;
-		goto out;
-	}
-
-	mdp4_kms->rev = minor;
-
 	if (mdp4_kms->rev > 1) {
 		mdp4_write(mdp4_kms, REG_MDP4_CS_CONTROLLER0, 0x0707ffff);
 		mdp4_write(mdp4_kms, REG_MDP4_CS_CONTROLLER1, 0x03073f3f);
@@ -88,7 +70,6 @@ static int mdp4_hw_init(struct msm_kms *kms)
 	if (mdp4_kms->rev > 1)
 		mdp4_write(mdp4_kms, REG_MDP4_RESET_STATUS, 1);
 
-out:
 	pm_runtime_put_sync(dev->dev);
 
 	return ret;
@@ -108,13 +89,6 @@ static void mdp4_disable_commit(struct msm_kms *kms)
 
 static void mdp4_prepare_commit(struct msm_kms *kms, struct drm_atomic_state *state)
 {
-	int i;
-	struct drm_crtc *crtc;
-	struct drm_crtc_state *crtc_state;
-
-	/* see 119ecb7fd */
-	for_each_new_crtc_in_state(state, crtc, crtc_state, i)
-		drm_crtc_vblank_get(crtc);
 }
 
 static void mdp4_flush_commit(struct msm_kms *kms, unsigned crtc_mask)
@@ -133,12 +107,6 @@ static void mdp4_wait_flush(struct msm_kms *kms, unsigned crtc_mask)
 
 static void mdp4_complete_commit(struct msm_kms *kms, unsigned crtc_mask)
 {
-	struct mdp4_kms *mdp4_kms = to_mdp4_kms(to_mdp_kms(kms));
-	struct drm_crtc *crtc;
-
-	/* see 119ecb7fd */
-	for_each_crtc_mask(mdp4_kms->dev, crtc, crtc_mask)
-		drm_crtc_vblank_put(crtc);
 }
 
 static long mdp4_round_pixclk(struct msm_kms *kms, unsigned long rate,
@@ -409,14 +377,32 @@ fail:
 	return ret;
 }
 
+static void read_mdp_hw_revision(struct mdp4_kms *mdp4_kms,
+				 u32 *major, u32 *minor)
+{
+	struct drm_device *dev = mdp4_kms->dev;
+	u32 version;
+
+	mdp4_enable(mdp4_kms);
+	version = mdp4_read(mdp4_kms, REG_MDP4_VERSION);
+	mdp4_disable(mdp4_kms);
+
+	*major = FIELD(version, MDP4_VERSION_MAJOR);
+	*minor = FIELD(version, MDP4_VERSION_MINOR);
+
+	DRM_DEV_INFO(dev->dev, "MDP4 version v%d.%d", *major, *minor);
+}
+
 struct msm_kms *mdp4_kms_init(struct drm_device *dev)
 {
 	struct platform_device *pdev = to_platform_device(dev->dev);
 	struct mdp4_platform_config *config = mdp4_get_config(pdev);
+	struct msm_drm_private *priv = dev->dev_private;
 	struct mdp4_kms *mdp4_kms;
 	struct msm_kms *kms = NULL;
 	struct msm_gem_address_space *aspace;
 	int irq, ret;
+	u32 major, minor;
 
 	mdp4_kms = kzalloc(sizeof(*mdp4_kms), GFP_KERNEL);
 	if (!mdp4_kms) {
@@ -427,7 +413,8 @@ struct msm_kms *mdp4_kms_init(struct drm_device *dev)
 
 	mdp_kms_init(&mdp4_kms->base, &kms_funcs);
 
-	kms = &mdp4_kms->base.base;
+	priv->kms = &mdp4_kms->base.base;
+	kms = priv->kms;
 
 	mdp4_kms->dev = dev;
 
@@ -473,15 +460,6 @@ struct msm_kms *mdp4_kms_init(struct drm_device *dev)
 	if (IS_ERR(mdp4_kms->pclk))
 		mdp4_kms->pclk = NULL;
 
-	if (mdp4_kms->rev >= 2) {
-		mdp4_kms->lut_clk = devm_clk_get(&pdev->dev, "lut_clk");
-		if (IS_ERR(mdp4_kms->lut_clk)) {
-			DRM_DEV_ERROR(dev->dev, "failed to get lut_clk\n");
-			ret = PTR_ERR(mdp4_kms->lut_clk);
-			goto fail;
-		}
-	}
-
 	mdp4_kms->axi_clk = devm_clk_get(&pdev->dev, "bus_clk");
 	if (IS_ERR(mdp4_kms->axi_clk)) {
 		DRM_DEV_ERROR(dev->dev, "failed to get axi_clk\n");
@@ -490,8 +468,27 @@ struct msm_kms *mdp4_kms_init(struct drm_device *dev)
 	}
 
 	clk_set_rate(mdp4_kms->clk, config->max_clk);
-	if (mdp4_kms->lut_clk)
+
+	read_mdp_hw_revision(mdp4_kms, &major, &minor);
+
+	if (major != 4) {
+		DRM_DEV_ERROR(dev->dev, "unexpected MDP version: v%d.%d\n",
+			      major, minor);
+		ret = -ENXIO;
+		goto fail;
+	}
+
+	mdp4_kms->rev = minor;
+
+	if (mdp4_kms->rev >= 2) {
+		mdp4_kms->lut_clk = devm_clk_get(&pdev->dev, "lut_clk");
+		if (IS_ERR(mdp4_kms->lut_clk)) {
+			DRM_DEV_ERROR(dev->dev, "failed to get lut_clk\n");
+			ret = PTR_ERR(mdp4_kms->lut_clk);
+			goto fail;
+		}
 		clk_set_rate(mdp4_kms->lut_clk, config->max_clk);
+	}
 
 	pm_runtime_enable(dev->dev);
 	mdp4_kms->rpm_enabled = true;
diff --git a/drivers/gpu/drm/msm/dp/dp_panel.c b/drivers/gpu/drm/msm/dp/dp_panel.c
index 18cec4fc5e0b..2768d1d306f0 100644
--- a/drivers/gpu/drm/msm/dp/dp_panel.c
+++ b/drivers/gpu/drm/msm/dp/dp_panel.c
@@ -261,7 +261,7 @@ static u8 dp_panel_get_edid_checksum(struct edid *edid)
 {
 	struct edid *last_block;
 	u8 *raw_edid;
-	bool is_edid_corrupt;
+	bool is_edid_corrupt = false;
 
 	if (!edid) {
 		DRM_ERROR("invalid edid input\n");
@@ -293,7 +293,12 @@ void dp_panel_handle_sink_request(struct dp_panel *dp_panel)
 	panel = container_of(dp_panel, struct dp_panel_private, dp_panel);
 
 	if (panel->link->sink_request & DP_TEST_LINK_EDID_READ) {
-		u8 checksum = dp_panel_get_edid_checksum(dp_panel->edid);
+		u8 checksum;
+
+		if (dp_panel->edid)
+			checksum = dp_panel_get_edid_checksum(dp_panel->edid);
+		else
+			checksum = dp_panel->connector->real_edid_checksum;
 
 		dp_link_send_edid_checksum(panel->link, checksum);
 		dp_link_send_test_response(panel->link);
diff --git a/drivers/gpu/drm/msm/dsi/dsi.c b/drivers/gpu/drm/msm/dsi/dsi.c
index 627048851d99..7e364b9c9f9e 100644
--- a/drivers/gpu/drm/msm/dsi/dsi.c
+++ b/drivers/gpu/drm/msm/dsi/dsi.c
@@ -26,8 +26,10 @@ static int dsi_get_phy(struct msm_dsi *msm_dsi)
 	}
 
 	phy_pdev = of_find_device_by_node(phy_node);
-	if (phy_pdev)
+	if (phy_pdev) {
 		msm_dsi->phy = platform_get_drvdata(phy_pdev);
+		msm_dsi->phy_dev = &phy_pdev->dev;
+	}
 
 	of_node_put(phy_node);
 
@@ -36,8 +38,6 @@ static int dsi_get_phy(struct msm_dsi *msm_dsi)
 		return -EPROBE_DEFER;
 	}
 
-	msm_dsi->phy_dev = get_device(&phy_pdev->dev);
-
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/msm/dsi/dsi_cfg.c b/drivers/gpu/drm/msm/dsi/dsi_cfg.c
index b2ff68a15791..d255bea87ca4 100644
--- a/drivers/gpu/drm/msm/dsi/dsi_cfg.c
+++ b/drivers/gpu/drm/msm/dsi/dsi_cfg.c
@@ -158,7 +158,6 @@ static const struct msm_dsi_config sdm660_dsi_cfg = {
 	.reg_cfg = {
 		.num = 2,
 		.regs = {
-			{"vdd", 73400, 32 },	/* 0.9 V */
 			{"vdda", 12560, 4 },	/* 1.2 V */
 		},
 	},
diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_14nm.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_14nm.c
index 519400501bcd..1ca9e73c6e07 100644
--- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_14nm.c
+++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_14nm.c
@@ -168,7 +168,7 @@ const struct msm_dsi_phy_cfg dsi_phy_14nm_660_cfgs = {
 	.reg_cfg = {
 		.num = 1,
 		.regs = {
-			{"vcca", 17000, 32},
+			{"vcca", 73400, 32},
 		},
 	},
 	.ops = {
diff --git a/drivers/gpu/drm/mxsfb/mxsfb_drv.c b/drivers/gpu/drm/mxsfb/mxsfb_drv.c
index 17f26052e845..f31e8ef3c258 100644
--- a/drivers/gpu/drm/mxsfb/mxsfb_drv.c
+++ b/drivers/gpu/drm/mxsfb/mxsfb_drv.c
@@ -51,6 +51,7 @@ static const struct mxsfb_devdata mxsfb_devdata[] = {
 		.hs_wdth_mask	= 0xff,
 		.hs_wdth_shift	= 24,
 		.has_overlay	= false,
+		.has_ctrl2	= false,
 	},
 	[MXSFB_V4] = {
 		.transfer_count	= LCDC_V4_TRANSFER_COUNT,
@@ -59,6 +60,7 @@ static const struct mxsfb_devdata mxsfb_devdata[] = {
 		.hs_wdth_mask	= 0x3fff,
 		.hs_wdth_shift	= 18,
 		.has_overlay	= false,
+		.has_ctrl2	= true,
 	},
 	[MXSFB_V6] = {
 		.transfer_count	= LCDC_V4_TRANSFER_COUNT,
@@ -67,6 +69,7 @@ static const struct mxsfb_devdata mxsfb_devdata[] = {
 		.hs_wdth_mask	= 0x3fff,
 		.hs_wdth_shift	= 18,
 		.has_overlay	= true,
+		.has_ctrl2	= true,
 	},
 };
 
diff --git a/drivers/gpu/drm/mxsfb/mxsfb_drv.h b/drivers/gpu/drm/mxsfb/mxsfb_drv.h
index 399d23e91ed1..7c720e226fdf 100644
--- a/drivers/gpu/drm/mxsfb/mxsfb_drv.h
+++ b/drivers/gpu/drm/mxsfb/mxsfb_drv.h
@@ -22,6 +22,7 @@ struct mxsfb_devdata {
 	unsigned int	hs_wdth_mask;
 	unsigned int	hs_wdth_shift;
 	bool		has_overlay;
+	bool		has_ctrl2;
 };
 
 struct mxsfb_drm_private {
diff --git a/drivers/gpu/drm/mxsfb/mxsfb_kms.c b/drivers/gpu/drm/mxsfb/mxsfb_kms.c
index 9e1224d54729..b535621f4f78 100644
--- a/drivers/gpu/drm/mxsfb/mxsfb_kms.c
+++ b/drivers/gpu/drm/mxsfb/mxsfb_kms.c
@@ -107,6 +107,14 @@ static void mxsfb_enable_controller(struct mxsfb_drm_private *mxsfb)
 		clk_prepare_enable(mxsfb->clk_disp_axi);
 	clk_prepare_enable(mxsfb->clk);
 
+	/* Increase number of outstanding requests on all supported IPs */
+	if (mxsfb->devdata->has_ctrl2) {
+		reg = readl(mxsfb->base + LCDC_V4_CTRL2);
+		reg &= ~CTRL2_SET_OUTSTANDING_REQS_MASK;
+		reg |= CTRL2_SET_OUTSTANDING_REQS_16;
+		writel(reg, mxsfb->base + LCDC_V4_CTRL2);
+	}
+
 	/* If it was disabled, re-enable the mode again */
 	writel(CTRL_DOTCLK_MODE, mxsfb->base + LCDC_CTRL + REG_SET);
 
@@ -115,6 +123,35 @@ static void mxsfb_enable_controller(struct mxsfb_drm_private *mxsfb)
 	reg |= VDCTRL4_SYNC_SIGNALS_ON;
 	writel(reg, mxsfb->base + LCDC_VDCTRL4);
 
+	/*
+	 * Enable recovery on underflow.
+	 *
+	 * There is some sort of corner case behavior of the controller,
+	 * which could rarely be triggered at least on i.MX6SX connected
+	 * to 800x480 DPI panel and i.MX8MM connected to DPI->DSI->LVDS
+	 * bridged 1920x1080 panel (and likely on other setups too), where
+	 * the image on the panel shifts to the right and wraps around.
+	 * This happens either when the controller is enabled on boot or
+	 * even later during run time. The condition does not correct
+	 * itself automatically, i.e. the display image remains shifted.
+	 *
+	 * It seems this problem is known and is due to sporadic underflows
+	 * of the LCDIF FIFO. While the LCDIF IP does have underflow/overflow
+	 * IRQs, neither of the IRQs trigger and neither IRQ status bit is
+	 * asserted when this condition occurs.
+	 *
+	 * All known revisions of the LCDIF IP have CTRL1 RECOVER_ON_UNDERFLOW
+	 * bit, which is described in the reference manual since i.MX23 as
+	 * "
+	 *   Set this bit to enable the LCDIF block to recover in the next
+	 *   field/frame if there was an underflow in the current field/frame.
+	 * "
+	 * Enable this bit to mitigate the sporadic underflows.
+	 */
+	reg = readl(mxsfb->base + LCDC_CTRL1);
+	reg |= CTRL1_RECOVER_ON_UNDERFLOW;
+	writel(reg, mxsfb->base + LCDC_CTRL1);
+
 	writel(CTRL_RUN, mxsfb->base + LCDC_CTRL + REG_SET);
 }
 
@@ -206,6 +243,9 @@ static void mxsfb_crtc_mode_set_nofb(struct mxsfb_drm_private *mxsfb)
 
 	/* Clear the FIFOs */
 	writel(CTRL1_FIFO_CLEAR, mxsfb->base + LCDC_CTRL1 + REG_SET);
+	readl(mxsfb->base + LCDC_CTRL1);
+	writel(CTRL1_FIFO_CLEAR, mxsfb->base + LCDC_CTRL1 + REG_CLR);
+	readl(mxsfb->base + LCDC_CTRL1);
 
 	if (mxsfb->devdata->has_overlay)
 		writel(0, mxsfb->base + LCDC_AS_CTRL);
diff --git a/drivers/gpu/drm/mxsfb/mxsfb_regs.h b/drivers/gpu/drm/mxsfb/mxsfb_regs.h
index 55d28a27f912..694fea13e893 100644
--- a/drivers/gpu/drm/mxsfb/mxsfb_regs.h
+++ b/drivers/gpu/drm/mxsfb/mxsfb_regs.h
@@ -15,6 +15,7 @@
 #define LCDC_CTRL			0x00
 #define LCDC_CTRL1			0x10
 #define LCDC_V3_TRANSFER_COUNT		0x20
+#define LCDC_V4_CTRL2			0x20
 #define LCDC_V4_TRANSFER_COUNT		0x30
 #define LCDC_V4_CUR_BUF			0x40
 #define LCDC_V4_NEXT_BUF		0x50
@@ -54,12 +55,20 @@
 #define CTRL_DF24			BIT(1)
 #define CTRL_RUN			BIT(0)
 
+#define CTRL1_RECOVER_ON_UNDERFLOW	BIT(24)
 #define CTRL1_FIFO_CLEAR		BIT(21)
 #define CTRL1_SET_BYTE_PACKAGING(x)	(((x) & 0xf) << 16)
 #define CTRL1_GET_BYTE_PACKAGING(x)	(((x) >> 16) & 0xf)
 #define CTRL1_CUR_FRAME_DONE_IRQ_EN	BIT(13)
 #define CTRL1_CUR_FRAME_DONE_IRQ	BIT(9)
 
+#define CTRL2_SET_OUTSTANDING_REQS_1	0
+#define CTRL2_SET_OUTSTANDING_REQS_2	(0x1 << 21)
+#define CTRL2_SET_OUTSTANDING_REQS_4	(0x2 << 21)
+#define CTRL2_SET_OUTSTANDING_REQS_8	(0x3 << 21)
+#define CTRL2_SET_OUTSTANDING_REQS_16	(0x4 << 21)
+#define CTRL2_SET_OUTSTANDING_REQS_MASK	(0x7 << 21)
+
 #define TRANSFER_COUNT_SET_VCOUNT(x)	(((x) & 0xffff) << 16)
 #define TRANSFER_COUNT_GET_VCOUNT(x)	(((x) >> 16) & 0xffff)
 #define TRANSFER_COUNT_SET_HCOUNT(x)	((x) & 0xffff)
diff --git a/drivers/gpu/drm/nouveau/dispnv50/disp.c b/drivers/gpu/drm/nouveau/dispnv50/disp.c
index 5b8cabb099eb..c2d34c91e840 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/disp.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/disp.c
@@ -2202,6 +2202,33 @@ nv50_disp_atomic_commit_tail(struct drm_atomic_state *state)
 		interlock[NV50_DISP_INTERLOCK_CORE] = 0;
 	}
 
+	/* Finish updating head(s)...
+	 *
+	 * NVD is rather picky about both where window assignments can change,
+	 * *and* about certain core and window channel states matching.
+	 *
+	 * The EFI GOP driver on newer GPUs configures window channels with a
+	 * different output format to what we do, and the core channel update
+	 * in the assign_windows case above would result in a state mismatch.
+	 *
+	 * Delay some of the head update until after that point to workaround
+	 * the issue.  This only affects the initial modeset.
+	 *
+	 * TODO: handle this better when adding flexible window mapping
+	 */
+	for_each_oldnew_crtc_in_state(state, crtc, old_crtc_state, new_crtc_state, i) {
+		struct nv50_head_atom *asyh = nv50_head_atom(new_crtc_state);
+		struct nv50_head *head = nv50_head(crtc);
+
+		NV_ATOMIC(drm, "%s: set %04x (clr %04x)\n", crtc->name,
+			  asyh->set.mask, asyh->clr.mask);
+
+		if (asyh->set.mask) {
+			nv50_head_flush_set_wndw(head, asyh);
+			interlock[NV50_DISP_INTERLOCK_CORE] = 1;
+		}
+	}
+
 	/* Update plane(s). */
 	for_each_new_plane_in_state(state, plane, new_plane_state, i) {
 		struct nv50_wndw_atom *asyw = nv50_wndw_atom(new_plane_state);
diff --git a/drivers/gpu/drm/nouveau/dispnv50/head.c b/drivers/gpu/drm/nouveau/dispnv50/head.c
index 841edfaf5b9d..61826cac3061 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/head.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/head.c
@@ -49,11 +49,8 @@ nv50_head_flush_clr(struct nv50_head *head,
 }
 
 void
-nv50_head_flush_set(struct nv50_head *head, struct nv50_head_atom *asyh)
+nv50_head_flush_set_wndw(struct nv50_head *head, struct nv50_head_atom *asyh)
 {
-	if (asyh->set.view   ) head->func->view    (head, asyh);
-	if (asyh->set.mode   ) head->func->mode    (head, asyh);
-	if (asyh->set.core   ) head->func->core_set(head, asyh);
 	if (asyh->set.olut   ) {
 		asyh->olut.offset = nv50_lut_load(&head->olut,
 						  asyh->olut.buffer,
@@ -61,6 +58,14 @@ nv50_head_flush_set(struct nv50_head *head, struct nv50_head_atom *asyh)
 						  asyh->olut.load);
 		head->func->olut_set(head, asyh);
 	}
+}
+
+void
+nv50_head_flush_set(struct nv50_head *head, struct nv50_head_atom *asyh)
+{
+	if (asyh->set.view   ) head->func->view    (head, asyh);
+	if (asyh->set.mode   ) head->func->mode    (head, asyh);
+	if (asyh->set.core   ) head->func->core_set(head, asyh);
 	if (asyh->set.curs   ) head->func->curs_set(head, asyh);
 	if (asyh->set.base   ) head->func->base    (head, asyh);
 	if (asyh->set.ovly   ) head->func->ovly    (head, asyh);
diff --git a/drivers/gpu/drm/nouveau/dispnv50/head.h b/drivers/gpu/drm/nouveau/dispnv50/head.h
index dae841dc05fd..0bac6be9ba34 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/head.h
+++ b/drivers/gpu/drm/nouveau/dispnv50/head.h
@@ -21,6 +21,7 @@ struct nv50_head {
 
 struct nv50_head *nv50_head_create(struct drm_device *, int index);
 void nv50_head_flush_set(struct nv50_head *head, struct nv50_head_atom *asyh);
+void nv50_head_flush_set_wndw(struct nv50_head *head, struct nv50_head_atom *asyh);
 void nv50_head_flush_clr(struct nv50_head *head,
 			 struct nv50_head_atom *asyh, bool flush);
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/dp.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/dp.c
index 3800aeb507d0..2a7b8bc3ec4d 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/dp.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/dp.c
@@ -419,7 +419,7 @@ nvkm_dp_train(struct nvkm_dp *dp, u32 dataKBps)
 	return ret;
 }
 
-static void
+void
 nvkm_dp_disable(struct nvkm_outp *outp, struct nvkm_ior *ior)
 {
 	struct nvkm_dp *dp = nvkm_dp(outp);
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/dp.h b/drivers/gpu/drm/nouveau/nvkm/engine/disp/dp.h
index 428b3f488f03..e484d0c3b0d4 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/dp.h
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/dp.h
@@ -32,6 +32,7 @@ struct nvkm_dp {
 
 int nvkm_dp_new(struct nvkm_disp *, int index, struct dcb_output *,
 		struct nvkm_outp **);
+void nvkm_dp_disable(struct nvkm_outp *, struct nvkm_ior *);
 
 /* DPCD Receiver Capabilities */
 #define DPCD_RC00_DPCD_REV                                              0x00000
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/outp.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/outp.c
index dffcac249211..129982fef7ef 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/outp.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/outp.c
@@ -22,6 +22,7 @@
  * Authors: Ben Skeggs
  */
 #include "outp.h"
+#include "dp.h"
 #include "ior.h"
 
 #include <subdev/bios.h>
@@ -257,6 +258,14 @@ nvkm_outp_init_route(struct nvkm_outp *outp)
 	if (!ior->arm.head || ior->arm.proto != proto) {
 		OUTP_DBG(outp, "no heads (%x %d %d)", ior->arm.head,
 			 ior->arm.proto, proto);
+
+		/* The EFI GOP driver on Ampere can leave unused DP links routed,
+		 * which we don't expect.  The DisableLT IED script *should* get
+		 * us back to where we need to be.
+		 */
+		if (ior->func->route.get && !ior->arm.head && outp->info.type == DCB_OUTPUT_DP)
+			nvkm_dp_disable(outp, ior);
+
 		return;
 	}
 
diff --git a/drivers/gpu/drm/panfrost/panfrost_device.c b/drivers/gpu/drm/panfrost/panfrost_device.c
index bf7c34cfb84c..c256929e859b 100644
--- a/drivers/gpu/drm/panfrost/panfrost_device.c
+++ b/drivers/gpu/drm/panfrost/panfrost_device.c
@@ -60,7 +60,8 @@ static int panfrost_clk_init(struct panfrost_device *pfdev)
 	if (IS_ERR(pfdev->bus_clock)) {
 		dev_err(pfdev->dev, "get bus_clock failed %ld\n",
 			PTR_ERR(pfdev->bus_clock));
-		return PTR_ERR(pfdev->bus_clock);
+		err = PTR_ERR(pfdev->bus_clock);
+		goto disable_clock;
 	}
 
 	if (pfdev->bus_clock) {
diff --git a/drivers/gpu/drm/panfrost/panfrost_device.h b/drivers/gpu/drm/panfrost/panfrost_device.h
index 597cf1459b0a..4c6bdea5537b 100644
--- a/drivers/gpu/drm/panfrost/panfrost_device.h
+++ b/drivers/gpu/drm/panfrost/panfrost_device.h
@@ -120,8 +120,12 @@ struct panfrost_device {
 };
 
 struct panfrost_mmu {
+	struct panfrost_device *pfdev;
+	struct kref refcount;
 	struct io_pgtable_cfg pgtbl_cfg;
 	struct io_pgtable_ops *pgtbl_ops;
+	struct drm_mm mm;
+	spinlock_t mm_lock;
 	int as;
 	atomic_t as_count;
 	struct list_head list;
@@ -132,9 +136,7 @@ struct panfrost_file_priv {
 
 	struct drm_sched_entity sched_entity[NUM_JOB_SLOTS];
 
-	struct panfrost_mmu mmu;
-	struct drm_mm mm;
-	spinlock_t mm_lock;
+	struct panfrost_mmu *mmu;
 };
 
 static inline struct panfrost_device *to_panfrost_device(struct drm_device *ddev)
diff --git a/drivers/gpu/drm/panfrost/panfrost_drv.c b/drivers/gpu/drm/panfrost/panfrost_drv.c
index 689be734ed20..a70261809cdd 100644
--- a/drivers/gpu/drm/panfrost/panfrost_drv.c
+++ b/drivers/gpu/drm/panfrost/panfrost_drv.c
@@ -417,7 +417,7 @@ static int panfrost_ioctl_madvise(struct drm_device *dev, void *data,
 		 * anyway, so let's not bother.
 		 */
 		if (!list_is_singular(&bo->mappings.list) ||
-		    WARN_ON_ONCE(first->mmu != &priv->mmu)) {
+		    WARN_ON_ONCE(first->mmu != priv->mmu)) {
 			ret = -EINVAL;
 			goto out_unlock_mappings;
 		}
@@ -449,32 +449,6 @@ int panfrost_unstable_ioctl_check(void)
 	return 0;
 }
 
-#define PFN_4G		(SZ_4G >> PAGE_SHIFT)
-#define PFN_4G_MASK	(PFN_4G - 1)
-#define PFN_16M		(SZ_16M >> PAGE_SHIFT)
-
-static void panfrost_drm_mm_color_adjust(const struct drm_mm_node *node,
-					 unsigned long color,
-					 u64 *start, u64 *end)
-{
-	/* Executable buffers can't start or end on a 4GB boundary */
-	if (!(color & PANFROST_BO_NOEXEC)) {
-		u64 next_seg;
-
-		if ((*start & PFN_4G_MASK) == 0)
-			(*start)++;
-
-		if ((*end & PFN_4G_MASK) == 0)
-			(*end)--;
-
-		next_seg = ALIGN(*start, PFN_4G);
-		if (next_seg - *start <= PFN_16M)
-			*start = next_seg + 1;
-
-		*end = min(*end, ALIGN(*start, PFN_4G) - 1);
-	}
-}
-
 static int
 panfrost_open(struct drm_device *dev, struct drm_file *file)
 {
@@ -489,15 +463,11 @@ panfrost_open(struct drm_device *dev, struct drm_file *file)
 	panfrost_priv->pfdev = pfdev;
 	file->driver_priv = panfrost_priv;
 
-	spin_lock_init(&panfrost_priv->mm_lock);
-
-	/* 4G enough for now. can be 48-bit */
-	drm_mm_init(&panfrost_priv->mm, SZ_32M >> PAGE_SHIFT, (SZ_4G - SZ_32M) >> PAGE_SHIFT);
-	panfrost_priv->mm.color_adjust = panfrost_drm_mm_color_adjust;
-
-	ret = panfrost_mmu_pgtable_alloc(panfrost_priv);
-	if (ret)
-		goto err_pgtable;
+	panfrost_priv->mmu = panfrost_mmu_ctx_create(pfdev);
+	if (IS_ERR(panfrost_priv->mmu)) {
+		ret = PTR_ERR(panfrost_priv->mmu);
+		goto err_free;
+	}
 
 	ret = panfrost_job_open(panfrost_priv);
 	if (ret)
@@ -506,9 +476,8 @@ panfrost_open(struct drm_device *dev, struct drm_file *file)
 	return 0;
 
 err_job:
-	panfrost_mmu_pgtable_free(panfrost_priv);
-err_pgtable:
-	drm_mm_takedown(&panfrost_priv->mm);
+	panfrost_mmu_ctx_put(panfrost_priv->mmu);
+err_free:
 	kfree(panfrost_priv);
 	return ret;
 }
@@ -521,8 +490,7 @@ panfrost_postclose(struct drm_device *dev, struct drm_file *file)
 	panfrost_perfcnt_close(file);
 	panfrost_job_close(panfrost_priv);
 
-	panfrost_mmu_pgtable_free(panfrost_priv);
-	drm_mm_takedown(&panfrost_priv->mm);
+	panfrost_mmu_ctx_put(panfrost_priv->mmu);
 	kfree(panfrost_priv);
 }
 
diff --git a/drivers/gpu/drm/panfrost/panfrost_gem.c b/drivers/gpu/drm/panfrost/panfrost_gem.c
index 57a31dd0ffed..1d917cea5ceb 100644
--- a/drivers/gpu/drm/panfrost/panfrost_gem.c
+++ b/drivers/gpu/drm/panfrost/panfrost_gem.c
@@ -60,7 +60,7 @@ panfrost_gem_mapping_get(struct panfrost_gem_object *bo,
 
 	mutex_lock(&bo->mappings.lock);
 	list_for_each_entry(iter, &bo->mappings.list, node) {
-		if (iter->mmu == &priv->mmu) {
+		if (iter->mmu == priv->mmu) {
 			kref_get(&iter->refcount);
 			mapping = iter;
 			break;
@@ -74,16 +74,13 @@ panfrost_gem_mapping_get(struct panfrost_gem_object *bo,
 static void
 panfrost_gem_teardown_mapping(struct panfrost_gem_mapping *mapping)
 {
-	struct panfrost_file_priv *priv;
-
 	if (mapping->active)
 		panfrost_mmu_unmap(mapping);
 
-	priv = container_of(mapping->mmu, struct panfrost_file_priv, mmu);
-	spin_lock(&priv->mm_lock);
+	spin_lock(&mapping->mmu->mm_lock);
 	if (drm_mm_node_allocated(&mapping->mmnode))
 		drm_mm_remove_node(&mapping->mmnode);
-	spin_unlock(&priv->mm_lock);
+	spin_unlock(&mapping->mmu->mm_lock);
 }
 
 static void panfrost_gem_mapping_release(struct kref *kref)
@@ -94,6 +91,7 @@ static void panfrost_gem_mapping_release(struct kref *kref)
 
 	panfrost_gem_teardown_mapping(mapping);
 	drm_gem_object_put(&mapping->obj->base.base);
+	panfrost_mmu_ctx_put(mapping->mmu);
 	kfree(mapping);
 }
 
@@ -143,11 +141,11 @@ int panfrost_gem_open(struct drm_gem_object *obj, struct drm_file *file_priv)
 	else
 		align = size >= SZ_2M ? SZ_2M >> PAGE_SHIFT : 0;
 
-	mapping->mmu = &priv->mmu;
-	spin_lock(&priv->mm_lock);
-	ret = drm_mm_insert_node_generic(&priv->mm, &mapping->mmnode,
+	mapping->mmu = panfrost_mmu_ctx_get(priv->mmu);
+	spin_lock(&mapping->mmu->mm_lock);
+	ret = drm_mm_insert_node_generic(&mapping->mmu->mm, &mapping->mmnode,
 					 size >> PAGE_SHIFT, align, color, 0);
-	spin_unlock(&priv->mm_lock);
+	spin_unlock(&mapping->mmu->mm_lock);
 	if (ret)
 		goto err;
 
@@ -176,7 +174,7 @@ void panfrost_gem_close(struct drm_gem_object *obj, struct drm_file *file_priv)
 
 	mutex_lock(&bo->mappings.lock);
 	list_for_each_entry(iter, &bo->mappings.list, node) {
-		if (iter->mmu == &priv->mmu) {
+		if (iter->mmu == priv->mmu) {
 			mapping = iter;
 			list_del(&iter->node);
 			break;
diff --git a/drivers/gpu/drm/panfrost/panfrost_job.c b/drivers/gpu/drm/panfrost/panfrost_job.c
index 04e6f6f9b742..7e1a5664d452 100644
--- a/drivers/gpu/drm/panfrost/panfrost_job.c
+++ b/drivers/gpu/drm/panfrost/panfrost_job.c
@@ -165,7 +165,7 @@ static void panfrost_job_hw_submit(struct panfrost_job *job, int js)
 		return;
 	}
 
-	cfg = panfrost_mmu_as_get(pfdev, &job->file_priv->mmu);
+	cfg = panfrost_mmu_as_get(pfdev, job->file_priv->mmu);
 
 	job_write(pfdev, JS_HEAD_NEXT_LO(js), jc_head & 0xFFFFFFFF);
 	job_write(pfdev, JS_HEAD_NEXT_HI(js), jc_head >> 32);
@@ -524,7 +524,7 @@ static irqreturn_t panfrost_job_irq_handler(int irq, void *data)
 			if (job) {
 				pfdev->jobs[j] = NULL;
 
-				panfrost_mmu_as_put(pfdev, &job->file_priv->mmu);
+				panfrost_mmu_as_put(pfdev, job->file_priv->mmu);
 				panfrost_devfreq_record_idle(&pfdev->pfdevfreq);
 
 				dma_fence_signal_locked(job->done_fence);
diff --git a/drivers/gpu/drm/panfrost/panfrost_mmu.c b/drivers/gpu/drm/panfrost/panfrost_mmu.c
index 198686216317..7fc45b13a52c 100644
--- a/drivers/gpu/drm/panfrost/panfrost_mmu.c
+++ b/drivers/gpu/drm/panfrost/panfrost_mmu.c
@@ -1,5 +1,8 @@
 // SPDX-License-Identifier:	GPL-2.0
 /* Copyright 2019 Linaro, Ltd, Rob Herring <robh@kernel.org> */
+
+#include <drm/panfrost_drm.h>
+
 #include <linux/atomic.h>
 #include <linux/bitfield.h>
 #include <linux/delay.h>
@@ -52,25 +55,16 @@ static int write_cmd(struct panfrost_device *pfdev, u32 as_nr, u32 cmd)
 }
 
 static void lock_region(struct panfrost_device *pfdev, u32 as_nr,
-			u64 iova, size_t size)
+			u64 iova, u64 size)
 {
 	u8 region_width;
 	u64 region = iova & PAGE_MASK;
-	/*
-	 * fls returns:
-	 * 1 .. 32
-	 *
-	 * 10 + fls(num_pages)
-	 * results in the range (11 .. 42)
-	 */
-
-	size = round_up(size, PAGE_SIZE);
 
-	region_width = 10 + fls(size >> PAGE_SHIFT);
-	if ((size >> PAGE_SHIFT) != (1ul << (region_width - 11))) {
-		/* not pow2, so must go up to the next pow2 */
-		region_width += 1;
-	}
+	/* The size is encoded as ceil(log2) minus(1), which may be calculated
+	 * with fls. The size must be clamped to hardware bounds.
+	 */
+	size = max_t(u64, size, AS_LOCK_REGION_MIN_SIZE);
+	region_width = fls64(size - 1) - 1;
 	region |= region_width;
 
 	/* Lock the region that needs to be updated */
@@ -81,7 +75,7 @@ static void lock_region(struct panfrost_device *pfdev, u32 as_nr,
 
 
 static int mmu_hw_do_operation_locked(struct panfrost_device *pfdev, int as_nr,
-				      u64 iova, size_t size, u32 op)
+				      u64 iova, u64 size, u32 op)
 {
 	if (as_nr < 0)
 		return 0;
@@ -98,7 +92,7 @@ static int mmu_hw_do_operation_locked(struct panfrost_device *pfdev, int as_nr,
 
 static int mmu_hw_do_operation(struct panfrost_device *pfdev,
 			       struct panfrost_mmu *mmu,
-			       u64 iova, size_t size, u32 op)
+			       u64 iova, u64 size, u32 op)
 {
 	int ret;
 
@@ -115,7 +109,7 @@ static void panfrost_mmu_enable(struct panfrost_device *pfdev, struct panfrost_m
 	u64 transtab = cfg->arm_mali_lpae_cfg.transtab;
 	u64 memattr = cfg->arm_mali_lpae_cfg.memattr;
 
-	mmu_hw_do_operation_locked(pfdev, as_nr, 0, ~0UL, AS_COMMAND_FLUSH_MEM);
+	mmu_hw_do_operation_locked(pfdev, as_nr, 0, ~0ULL, AS_COMMAND_FLUSH_MEM);
 
 	mmu_write(pfdev, AS_TRANSTAB_LO(as_nr), transtab & 0xffffffffUL);
 	mmu_write(pfdev, AS_TRANSTAB_HI(as_nr), transtab >> 32);
@@ -131,7 +125,7 @@ static void panfrost_mmu_enable(struct panfrost_device *pfdev, struct panfrost_m
 
 static void panfrost_mmu_disable(struct panfrost_device *pfdev, u32 as_nr)
 {
-	mmu_hw_do_operation_locked(pfdev, as_nr, 0, ~0UL, AS_COMMAND_FLUSH_MEM);
+	mmu_hw_do_operation_locked(pfdev, as_nr, 0, ~0ULL, AS_COMMAND_FLUSH_MEM);
 
 	mmu_write(pfdev, AS_TRANSTAB_LO(as_nr), 0);
 	mmu_write(pfdev, AS_TRANSTAB_HI(as_nr), 0);
@@ -231,7 +225,7 @@ static size_t get_pgsize(u64 addr, size_t size)
 
 static void panfrost_mmu_flush_range(struct panfrost_device *pfdev,
 				     struct panfrost_mmu *mmu,
-				     u64 iova, size_t size)
+				     u64 iova, u64 size)
 {
 	if (mmu->as < 0)
 		return;
@@ -337,7 +331,7 @@ static void mmu_tlb_inv_context_s1(void *cookie)
 
 static void mmu_tlb_sync_context(void *cookie)
 {
-	//struct panfrost_device *pfdev = cookie;
+	//struct panfrost_mmu *mmu = cookie;
 	// TODO: Wait 1000 GPU cycles for HW_ISSUE_6367/T60X
 }
 
@@ -359,57 +353,10 @@ static const struct iommu_flush_ops mmu_tlb_ops = {
 	.tlb_flush_leaf = mmu_tlb_flush_leaf,
 };
 
-int panfrost_mmu_pgtable_alloc(struct panfrost_file_priv *priv)
-{
-	struct panfrost_mmu *mmu = &priv->mmu;
-	struct panfrost_device *pfdev = priv->pfdev;
-
-	INIT_LIST_HEAD(&mmu->list);
-	mmu->as = -1;
-
-	mmu->pgtbl_cfg = (struct io_pgtable_cfg) {
-		.pgsize_bitmap	= SZ_4K | SZ_2M,
-		.ias		= FIELD_GET(0xff, pfdev->features.mmu_features),
-		.oas		= FIELD_GET(0xff00, pfdev->features.mmu_features),
-		.coherent_walk	= pfdev->coherent,
-		.tlb		= &mmu_tlb_ops,
-		.iommu_dev	= pfdev->dev,
-	};
-
-	mmu->pgtbl_ops = alloc_io_pgtable_ops(ARM_MALI_LPAE, &mmu->pgtbl_cfg,
-					      priv);
-	if (!mmu->pgtbl_ops)
-		return -EINVAL;
-
-	return 0;
-}
-
-void panfrost_mmu_pgtable_free(struct panfrost_file_priv *priv)
-{
-	struct panfrost_device *pfdev = priv->pfdev;
-	struct panfrost_mmu *mmu = &priv->mmu;
-
-	spin_lock(&pfdev->as_lock);
-	if (mmu->as >= 0) {
-		pm_runtime_get_noresume(pfdev->dev);
-		if (pm_runtime_active(pfdev->dev))
-			panfrost_mmu_disable(pfdev, mmu->as);
-		pm_runtime_put_autosuspend(pfdev->dev);
-
-		clear_bit(mmu->as, &pfdev->as_alloc_mask);
-		clear_bit(mmu->as, &pfdev->as_in_use_mask);
-		list_del(&mmu->list);
-	}
-	spin_unlock(&pfdev->as_lock);
-
-	free_io_pgtable_ops(mmu->pgtbl_ops);
-}
-
 static struct panfrost_gem_mapping *
 addr_to_mapping(struct panfrost_device *pfdev, int as, u64 addr)
 {
 	struct panfrost_gem_mapping *mapping = NULL;
-	struct panfrost_file_priv *priv;
 	struct drm_mm_node *node;
 	u64 offset = addr >> PAGE_SHIFT;
 	struct panfrost_mmu *mmu;
@@ -422,11 +369,10 @@ addr_to_mapping(struct panfrost_device *pfdev, int as, u64 addr)
 	goto out;
 
 found_mmu:
-	priv = container_of(mmu, struct panfrost_file_priv, mmu);
 
-	spin_lock(&priv->mm_lock);
+	spin_lock(&mmu->mm_lock);
 
-	drm_mm_for_each_node(node, &priv->mm) {
+	drm_mm_for_each_node(node, &mmu->mm) {
 		if (offset >= node->start &&
 		    offset < (node->start + node->size)) {
 			mapping = drm_mm_node_to_panfrost_mapping(node);
@@ -436,7 +382,7 @@ found_mmu:
 		}
 	}
 
-	spin_unlock(&priv->mm_lock);
+	spin_unlock(&mmu->mm_lock);
 out:
 	spin_unlock(&pfdev->as_lock);
 	return mapping;
@@ -549,6 +495,107 @@ err_bo:
 	return ret;
 }
 
+static void panfrost_mmu_release_ctx(struct kref *kref)
+{
+	struct panfrost_mmu *mmu = container_of(kref, struct panfrost_mmu,
+						refcount);
+	struct panfrost_device *pfdev = mmu->pfdev;
+
+	spin_lock(&pfdev->as_lock);
+	if (mmu->as >= 0) {
+		pm_runtime_get_noresume(pfdev->dev);
+		if (pm_runtime_active(pfdev->dev))
+			panfrost_mmu_disable(pfdev, mmu->as);
+		pm_runtime_put_autosuspend(pfdev->dev);
+
+		clear_bit(mmu->as, &pfdev->as_alloc_mask);
+		clear_bit(mmu->as, &pfdev->as_in_use_mask);
+		list_del(&mmu->list);
+	}
+	spin_unlock(&pfdev->as_lock);
+
+	free_io_pgtable_ops(mmu->pgtbl_ops);
+	drm_mm_takedown(&mmu->mm);
+	kfree(mmu);
+}
+
+void panfrost_mmu_ctx_put(struct panfrost_mmu *mmu)
+{
+	kref_put(&mmu->refcount, panfrost_mmu_release_ctx);
+}
+
+struct panfrost_mmu *panfrost_mmu_ctx_get(struct panfrost_mmu *mmu)
+{
+	kref_get(&mmu->refcount);
+
+	return mmu;
+}
+
+#define PFN_4G		(SZ_4G >> PAGE_SHIFT)
+#define PFN_4G_MASK	(PFN_4G - 1)
+#define PFN_16M		(SZ_16M >> PAGE_SHIFT)
+
+static void panfrost_drm_mm_color_adjust(const struct drm_mm_node *node,
+					 unsigned long color,
+					 u64 *start, u64 *end)
+{
+	/* Executable buffers can't start or end on a 4GB boundary */
+	if (!(color & PANFROST_BO_NOEXEC)) {
+		u64 next_seg;
+
+		if ((*start & PFN_4G_MASK) == 0)
+			(*start)++;
+
+		if ((*end & PFN_4G_MASK) == 0)
+			(*end)--;
+
+		next_seg = ALIGN(*start, PFN_4G);
+		if (next_seg - *start <= PFN_16M)
+			*start = next_seg + 1;
+
+		*end = min(*end, ALIGN(*start, PFN_4G) - 1);
+	}
+}
+
+struct panfrost_mmu *panfrost_mmu_ctx_create(struct panfrost_device *pfdev)
+{
+	struct panfrost_mmu *mmu;
+
+	mmu = kzalloc(sizeof(*mmu), GFP_KERNEL);
+	if (!mmu)
+		return ERR_PTR(-ENOMEM);
+
+	mmu->pfdev = pfdev;
+	spin_lock_init(&mmu->mm_lock);
+
+	/* 4G enough for now. can be 48-bit */
+	drm_mm_init(&mmu->mm, SZ_32M >> PAGE_SHIFT, (SZ_4G - SZ_32M) >> PAGE_SHIFT);
+	mmu->mm.color_adjust = panfrost_drm_mm_color_adjust;
+
+	INIT_LIST_HEAD(&mmu->list);
+	mmu->as = -1;
+
+	mmu->pgtbl_cfg = (struct io_pgtable_cfg) {
+		.pgsize_bitmap	= SZ_4K | SZ_2M,
+		.ias		= FIELD_GET(0xff, pfdev->features.mmu_features),
+		.oas		= FIELD_GET(0xff00, pfdev->features.mmu_features),
+		.coherent_walk	= pfdev->coherent,
+		.tlb		= &mmu_tlb_ops,
+		.iommu_dev	= pfdev->dev,
+	};
+
+	mmu->pgtbl_ops = alloc_io_pgtable_ops(ARM_MALI_LPAE, &mmu->pgtbl_cfg,
+					      mmu);
+	if (!mmu->pgtbl_ops) {
+		kfree(mmu);
+		return ERR_PTR(-EINVAL);
+	}
+
+	kref_init(&mmu->refcount);
+
+	return mmu;
+}
+
 static const char *access_type_name(struct panfrost_device *pfdev,
 		u32 fault_status)
 {
diff --git a/drivers/gpu/drm/panfrost/panfrost_mmu.h b/drivers/gpu/drm/panfrost/panfrost_mmu.h
index 44fc2edf63ce..cc2a0d307feb 100644
--- a/drivers/gpu/drm/panfrost/panfrost_mmu.h
+++ b/drivers/gpu/drm/panfrost/panfrost_mmu.h
@@ -18,7 +18,8 @@ void panfrost_mmu_reset(struct panfrost_device *pfdev);
 u32 panfrost_mmu_as_get(struct panfrost_device *pfdev, struct panfrost_mmu *mmu);
 void panfrost_mmu_as_put(struct panfrost_device *pfdev, struct panfrost_mmu *mmu);
 
-int panfrost_mmu_pgtable_alloc(struct panfrost_file_priv *priv);
-void panfrost_mmu_pgtable_free(struct panfrost_file_priv *priv);
+struct panfrost_mmu *panfrost_mmu_ctx_get(struct panfrost_mmu *mmu);
+void panfrost_mmu_ctx_put(struct panfrost_mmu *mmu);
+struct panfrost_mmu *panfrost_mmu_ctx_create(struct panfrost_device *pfdev);
 
 #endif
diff --git a/drivers/gpu/drm/panfrost/panfrost_regs.h b/drivers/gpu/drm/panfrost/panfrost_regs.h
index eddaa62ad8b0..2ae3a4d301d3 100644
--- a/drivers/gpu/drm/panfrost/panfrost_regs.h
+++ b/drivers/gpu/drm/panfrost/panfrost_regs.h
@@ -318,6 +318,8 @@
 #define AS_FAULTSTATUS_ACCESS_TYPE_READ		(0x2 << 8)
 #define AS_FAULTSTATUS_ACCESS_TYPE_WRITE	(0x3 << 8)
 
+#define AS_LOCK_REGION_MIN_SIZE                 (1ULL << 15)
+
 #define gpu_write(dev, reg, data) writel(data, dev->iomem + reg)
 #define gpu_read(dev, reg) readl(dev->iomem + reg)
 
diff --git a/drivers/gpu/drm/vc4/vc4_hdmi.c b/drivers/gpu/drm/vc4/vc4_hdmi.c
index c58b8840090a..ee293f061f0a 100644
--- a/drivers/gpu/drm/vc4/vc4_hdmi.c
+++ b/drivers/gpu/drm/vc4/vc4_hdmi.c
@@ -1074,7 +1074,9 @@ static int vc4_hdmi_audio_trigger(struct snd_pcm_substream *substream, int cmd,
 		HDMI_WRITE(HDMI_MAI_CTL,
 			   VC4_SET_FIELD(vc4_hdmi->audio.channels,
 					 VC4_HD_MAI_CTL_CHNUM) |
-			   VC4_HD_MAI_CTL_ENABLE);
+					 VC4_HD_MAI_CTL_WHOLSMP |
+					 VC4_HD_MAI_CTL_CHALIGN |
+					 VC4_HD_MAI_CTL_ENABLE);
 		break;
 	case SNDRV_PCM_TRIGGER_STOP:
 		HDMI_WRITE(HDMI_MAI_CTL,
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
index f493b20c7a38..f1a51371de5b 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
@@ -866,7 +866,7 @@ int vmw_surface_define_ioctl(struct drm_device *dev, void *data,
 	user_srf->prime.base.shareable = false;
 	user_srf->prime.base.tfile = NULL;
 	if (drm_is_primary_client(file_priv))
-		user_srf->master = drm_master_get(file_priv->master);
+		user_srf->master = drm_file_get_master(file_priv);
 
 	/**
 	 * From this point, the generic resource management functions
@@ -1537,7 +1537,7 @@ vmw_gb_surface_define_internal(struct drm_device *dev,
 
 	user_srf = container_of(srf, struct vmw_user_surface, srf);
 	if (drm_is_primary_client(file_priv))
-		user_srf->master = drm_master_get(file_priv->master);
+		user_srf->master = drm_file_get_master(file_priv);
 
 	ret = ttm_read_lock(&dev_priv->reservation_sem, true);
 	if (unlikely(ret != 0))
diff --git a/drivers/gpu/drm/xlnx/zynqmp_disp.c b/drivers/gpu/drm/xlnx/zynqmp_disp.c
index 8cd8af35cfaa..205c72a249b7 100644
--- a/drivers/gpu/drm/xlnx/zynqmp_disp.c
+++ b/drivers/gpu/drm/xlnx/zynqmp_disp.c
@@ -1447,9 +1447,10 @@ zynqmp_disp_crtc_atomic_enable(struct drm_crtc *crtc,
 	struct drm_display_mode *adjusted_mode = &crtc->state->adjusted_mode;
 	int ret, vrefresh;
 
+	pm_runtime_get_sync(disp->dev);
+
 	zynqmp_disp_crtc_setup_clock(crtc, adjusted_mode);
 
-	pm_runtime_get_sync(disp->dev);
 	ret = clk_prepare_enable(disp->pclk);
 	if (ret) {
 		dev_err(disp->dev, "failed to enable a pixel clock\n");
diff --git a/drivers/gpu/drm/xlnx/zynqmp_dp.c b/drivers/gpu/drm/xlnx/zynqmp_dp.c
index 59d1fb017da0..13811332b349 100644
--- a/drivers/gpu/drm/xlnx/zynqmp_dp.c
+++ b/drivers/gpu/drm/xlnx/zynqmp_dp.c
@@ -402,10 +402,6 @@ static int zynqmp_dp_phy_init(struct zynqmp_dp *dp)
 		}
 	}
 
-	ret = zynqmp_dp_reset(dp, false);
-	if (ret < 0)
-		return ret;
-
 	zynqmp_dp_clr(dp, ZYNQMP_DP_PHY_RESET, ZYNQMP_DP_PHY_RESET_ALL_RESET);
 
 	/*
@@ -441,8 +437,6 @@ static void zynqmp_dp_phy_exit(struct zynqmp_dp *dp)
 				ret);
 	}
 
-	zynqmp_dp_reset(dp, true);
-
 	for (i = 0; i < dp->num_lanes; i++) {
 		ret = phy_exit(dp->phy[i]);
 		if (ret)
@@ -1682,9 +1676,13 @@ int zynqmp_dp_probe(struct zynqmp_dpsub *dpsub, struct drm_device *drm)
 		return PTR_ERR(dp->reset);
 	}
 
+	ret = zynqmp_dp_reset(dp, false);
+	if (ret < 0)
+		return ret;
+
 	ret = zynqmp_dp_phy_probe(dp);
 	if (ret)
-		return ret;
+		goto err_reset;
 
 	/* Initialize the hardware. */
 	zynqmp_dp_write(dp, ZYNQMP_DP_TX_PHY_POWER_DOWN,
@@ -1696,7 +1694,7 @@ int zynqmp_dp_probe(struct zynqmp_dpsub *dpsub, struct drm_device *drm)
 
 	ret = zynqmp_dp_phy_init(dp);
 	if (ret)
-		return ret;
+		goto err_reset;
 
 	zynqmp_dp_write(dp, ZYNQMP_DP_TRANSMITTER_ENABLE, 1);
 
@@ -1708,15 +1706,18 @@ int zynqmp_dp_probe(struct zynqmp_dpsub *dpsub, struct drm_device *drm)
 					zynqmp_dp_irq_handler, IRQF_ONESHOT,
 					dev_name(dp->dev), dp);
 	if (ret < 0)
-		goto error;
+		goto err_phy_exit;
 
 	dev_dbg(dp->dev, "ZynqMP DisplayPort Tx probed with %u lanes\n",
 		dp->num_lanes);
 
 	return 0;
 
-error:
+err_phy_exit:
 	zynqmp_dp_phy_exit(dp);
+err_reset:
+	zynqmp_dp_reset(dp, true);
+
 	return ret;
 }
 
@@ -1734,4 +1735,5 @@ void zynqmp_dp_remove(struct zynqmp_dpsub *dpsub)
 	zynqmp_dp_write(dp, ZYNQMP_DP_INT_DS, 0xffffffff);
 
 	zynqmp_dp_phy_exit(dp);
+	zynqmp_dp_reset(dp, true);
 }
diff --git a/drivers/gpu/ipu-v3/ipu-cpmem.c b/drivers/gpu/ipu-v3/ipu-cpmem.c
index a1c85d1521f5..82b244cb313e 100644
--- a/drivers/gpu/ipu-v3/ipu-cpmem.c
+++ b/drivers/gpu/ipu-v3/ipu-cpmem.c
@@ -585,21 +585,21 @@ static const struct ipu_rgb def_bgra_16 = {
 	.bits_per_pixel = 16,
 };
 
-#define Y_OFFSET(pix, x, y)	((x) + pix->width * (y))
-#define U_OFFSET(pix, x, y)	((pix->width * pix->height) +		\
-				 (pix->width * ((y) / 2) / 2) + (x) / 2)
-#define V_OFFSET(pix, x, y)	((pix->width * pix->height) +		\
-				 (pix->width * pix->height / 4) +	\
-				 (pix->width * ((y) / 2) / 2) + (x) / 2)
-#define U2_OFFSET(pix, x, y)	((pix->width * pix->height) +		\
-				 (pix->width * (y) / 2) + (x) / 2)
-#define V2_OFFSET(pix, x, y)	((pix->width * pix->height) +		\
-				 (pix->width * pix->height / 2) +	\
-				 (pix->width * (y) / 2) + (x) / 2)
-#define UV_OFFSET(pix, x, y)	((pix->width * pix->height) +	\
-				 (pix->width * ((y) / 2)) + (x))
-#define UV2_OFFSET(pix, x, y)	((pix->width * pix->height) +	\
-				 (pix->width * y) + (x))
+#define Y_OFFSET(pix, x, y)	((x) + pix->bytesperline * (y))
+#define U_OFFSET(pix, x, y)	((pix->bytesperline * pix->height) +	 \
+				 (pix->bytesperline * ((y) / 2) / 2) + (x) / 2)
+#define V_OFFSET(pix, x, y)	((pix->bytesperline * pix->height) +	 \
+				 (pix->bytesperline * pix->height / 4) + \
+				 (pix->bytesperline * ((y) / 2) / 2) + (x) / 2)
+#define U2_OFFSET(pix, x, y)	((pix->bytesperline * pix->height) +	 \
+				 (pix->bytesperline * (y) / 2) + (x) / 2)
+#define V2_OFFSET(pix, x, y)	((pix->bytesperline * pix->height) +	 \
+				 (pix->bytesperline * pix->height / 2) + \
+				 (pix->bytesperline * (y) / 2) + (x) / 2)
+#define UV_OFFSET(pix, x, y)	((pix->bytesperline * pix->height) +	 \
+				 (pix->bytesperline * ((y) / 2)) + (x))
+#define UV2_OFFSET(pix, x, y)	((pix->bytesperline * pix->height) +	 \
+				 (pix->bytesperline * y) + (x))
 
 #define NUM_ALPHA_CHANNELS	7