Merge tag 'amd-drm-fixes-6.7-2023-11-30' of https://gitlab.freedesktop.org/agd5f/linux into drm-fixes

amd-drm-fixes-6.7-2023-11-30:

amdgpu:
- DMUB fix
- DCN 3.5 fixes
- XGMI fix
- DCN 3.2 fixes
- Vangogh suspend fix
- NBIO 7.9 fix
- GFX11 golden register fix
- Backlight fix
- NBIO 7.11 fix
- IB test overflow fix
- DCN 3.1.4 fixes
- fix a runtime pm ref count
- Retimer fix
- ABM fix
- DCN 3.1.5 fix
- Fix AGP addressing
- Fix possible memory leak in SMU error path
- Make sure PME is enabled in D3
- Fix possible NULL pointer dereference in debugfs
- EEPROM fix
- GC 9.4.3 fix

amdkfd:
- IP version check fix
- Fix memory leak in pqm_uninit()

drm:
- Revert unexport of prime helpers for fd/handle conversion

Signed-off-by: Dave Airlie <airlied@redhat.com>

From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20231130213135.5083-1-alexander.deucher@amd.com

54 files changed, 464 insertions, 249 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
index b8412202a1b0..75dc58470393 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
@@ -547,7 +547,7 @@ int amdgpu_amdkfd_get_xgmi_bandwidth_mbytes(struct amdgpu_device *dst,
 	struct amdgpu_device *adev = dst, *peer_adev;
 	int num_links;
 
-	if (adev->asic_type != CHIP_ALDEBARAN)
+	if (amdgpu_ip_version(adev, GC_HWIP, 0) < IP_VERSION(9, 4, 2))
 		return 0;
 
 	if (src)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
index a53f436fa9f1..0e61ebdb3f3e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
@@ -638,6 +638,9 @@ static ssize_t amdgpu_debugfs_regs_didt_read(struct file *f, char __user *buf,
 	if (size & 0x3 || *pos & 0x3)
 		return -EINVAL;
 
+	if (!adev->didt_rreg)
+		return -EOPNOTSUPP;
+
 	r = pm_runtime_get_sync(adev_to_drm(adev)->dev);
 	if (r < 0) {
 		pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
@@ -694,6 +697,9 @@ static ssize_t amdgpu_debugfs_regs_didt_write(struct file *f, const char __user
 	if (size & 0x3 || *pos & 0x3)
 		return -EINVAL;
 
+	if (!adev->didt_wreg)
+		return -EOPNOTSUPP;
+
 	r = pm_runtime_get_sync(adev_to_drm(adev)->dev);
 	if (r < 0) {
 		pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 7eeaf0aa7f81..5c0817cbc7c2 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -4538,6 +4538,10 @@ int amdgpu_device_suspend(struct drm_device *dev, bool fbcon)
 	if (amdgpu_sriov_vf(adev))
 		amdgpu_virt_release_full_gpu(adev, false);
 
+	r = amdgpu_dpm_notify_rlc_state(adev, false);
+	if (r)
+		return r;
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
index 0cacd0b9f8be..b8fbe97efe1d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
@@ -340,14 +340,11 @@ int amdgpu_display_crtc_set_config(struct drm_mode_set *set,
 		adev->have_disp_power_ref = true;
 		return ret;
 	}
-	/* if we have no active crtcs, then drop the power ref
-	 * we got before
+	/* if we have no active crtcs, then go to
+	 * drop the power ref we got before
 	 */
-	if (!active && adev->have_disp_power_ref) {
-		pm_runtime_put_autosuspend(dev->dev);
+	if (!active && adev->have_disp_power_ref)
 		adev->have_disp_power_ref = false;
-	}
-
 out:
 	/* drop the power reference we got coming in here */
 	pm_runtime_put_autosuspend(dev->dev);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 8f24cabe2155..8b33b130ea36 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -2263,6 +2263,8 @@ retry_init:
 		pm_runtime_mark_last_busy(ddev->dev);
 		pm_runtime_put_autosuspend(ddev->dev);
 
+		pci_wake_from_d3(pdev, TRUE);
+
 		/*
 		 * For runpm implemented via BACO, PMFW will handle the
 		 * timing for BACO in and out:
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
index 5f71414190e9..d2f273d77e59 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
@@ -181,6 +181,9 @@ uint64_t amdgpu_gmc_agp_addr(struct ttm_buffer_object *bo)
 {
 	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->bdev);
 
+	if (!bo->ttm)
+		return AMDGPU_BO_INVALID_OFFSET;
+
 	if (bo->ttm->num_pages != 1 || bo->ttm->caching == ttm_cached)
 		return AMDGPU_BO_INVALID_OFFSET;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
index cef920a93924..d79b4ca1ecfc 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
@@ -1527,10 +1527,14 @@ u64 amdgpu_bo_gpu_offset(struct amdgpu_bo *bo)
 u64 amdgpu_bo_gpu_offset_no_check(struct amdgpu_bo *bo)
 {
 	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
-	uint64_t offset;
+	uint64_t offset = AMDGPU_BO_INVALID_OFFSET;
 
-	offset = (bo->tbo.resource->start << PAGE_SHIFT) +
-		 amdgpu_ttm_domain_start(adev, bo->tbo.resource->mem_type);
+	if (bo->tbo.resource->mem_type == TTM_PL_TT)
+		offset = amdgpu_gmc_agp_addr(&bo->tbo);
+
+	if (offset == AMDGPU_BO_INVALID_OFFSET)
+		offset = (bo->tbo.resource->start << PAGE_SHIFT) +
+			amdgpu_ttm_domain_start(adev, bo->tbo.resource->mem_type);
 
 	return amdgpu_gmc_sign_extend(offset);
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
index 65aa218380be..2fde93b00cab 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
@@ -214,6 +214,12 @@ static bool __get_eeprom_i2c_addr(struct amdgpu_device *adev,
 			control->i2c_address = EEPROM_I2C_MADDR_0;
 		return true;
 	case IP_VERSION(13, 0, 0):
+		if (strnstr(atom_ctx->vbios_pn, "D707",
+			    sizeof(atom_ctx->vbios_pn)))
+			control->i2c_address = EEPROM_I2C_MADDR_0;
+		else
+			control->i2c_address = EEPROM_I2C_MADDR_4;
+		return true;
 	case IP_VERSION(13, 0, 6):
 	case IP_VERSION(13, 0, 10):
 		control->i2c_address = EEPROM_I2C_MADDR_4;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index 05991c5c8ddb..ab4a762aed5b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -959,10 +959,8 @@ int amdgpu_ttm_alloc_gart(struct ttm_buffer_object *bo)
 		return 0;
 
 	addr = amdgpu_gmc_agp_addr(bo);
-	if (addr != AMDGPU_BO_INVALID_OFFSET) {
-		bo->resource->start = addr >> PAGE_SHIFT;
+	if (addr != AMDGPU_BO_INVALID_OFFSET)
 		return 0;
-	}
 
 	/* allocate GART space */
 	placement.num_placement = 1;
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
index 0c6133cc5e57..8ed4a6fb147a 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
@@ -89,6 +89,10 @@ MODULE_FIRMWARE("amdgpu/gc_11_5_0_me.bin");
 MODULE_FIRMWARE("amdgpu/gc_11_5_0_mec.bin");
 MODULE_FIRMWARE("amdgpu/gc_11_5_0_rlc.bin");
 
+static const struct soc15_reg_golden golden_settings_gc_11_0[] = {
+	SOC15_REG_GOLDEN_VALUE(GC, 0, regTCP_CNTL, 0x20000000, 0x20000000)
+};
+
 static const struct soc15_reg_golden golden_settings_gc_11_0_1[] =
 {
 	SOC15_REG_GOLDEN_VALUE(GC, 0, regCGTT_GS_NGG_CLK_CTRL, 0x9fff8fff, 0x00000010),
@@ -304,6 +308,10 @@ static void gfx_v11_0_init_golden_registers(struct amdgpu_device *adev)
 	default:
 		break;
 	}
+	soc15_program_register_sequence(adev,
+					golden_settings_gc_11_0,
+					(const u32)ARRAY_SIZE(golden_settings_gc_11_0));
+
 }
 
 static void gfx_v11_0_write_data_to_reg(struct amdgpu_ring *ring, int eng_sel,
@@ -419,7 +427,7 @@ static int gfx_v11_0_ring_test_ib(struct amdgpu_ring *ring, long timeout)
 		adev->wb.wb[index] = cpu_to_le32(0xCAFEDEAD);
 		cpu_ptr = &adev->wb.wb[index];
 
-		r = amdgpu_ib_get(adev, NULL, 16, AMDGPU_IB_POOL_DIRECT, &ib);
+		r = amdgpu_ib_get(adev, NULL, 20, AMDGPU_IB_POOL_DIRECT, &ib);
 		if (r) {
 			DRM_ERROR("amdgpu: failed to get ib (%ld).\n", r);
 			goto err1;
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
index 885ebd703260..1943beb135c4 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
@@ -883,8 +883,8 @@ static int gfx_v8_0_ring_test_ib(struct amdgpu_ring *ring, long timeout)
 	gpu_addr = adev->wb.gpu_addr + (index * 4);
 	adev->wb.wb[index] = cpu_to_le32(0xCAFEDEAD);
 	memset(&ib, 0, sizeof(ib));
-	r = amdgpu_ib_get(adev, NULL, 16,
-					AMDGPU_IB_POOL_DIRECT, &ib);
+
+	r = amdgpu_ib_get(adev, NULL, 20, AMDGPU_IB_POOL_DIRECT, &ib);
 	if (r)
 		goto err1;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index e3ff6e46f3f7..69c500910746 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -1039,8 +1039,8 @@ static int gfx_v9_0_ring_test_ib(struct amdgpu_ring *ring, long timeout)
 	gpu_addr = adev->wb.gpu_addr + (index * 4);
 	adev->wb.wb[index] = cpu_to_le32(0xCAFEDEAD);
 	memset(&ib, 0, sizeof(ib));
-	r = amdgpu_ib_get(adev, NULL, 16,
-					AMDGPU_IB_POOL_DIRECT, &ib);
+
+	r = amdgpu_ib_get(adev, NULL, 20, AMDGPU_IB_POOL_DIRECT, &ib);
 	if (r)
 		goto err1;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c
index 40d06d32bb74..4a09cc0d8ce0 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c
@@ -297,8 +297,8 @@ static int gfx_v9_4_3_ring_test_ib(struct amdgpu_ring *ring, long timeout)
 	gpu_addr = adev->wb.gpu_addr + (index * 4);
 	adev->wb.wb[index] = cpu_to_le32(0xCAFEDEAD);
 	memset(&ib, 0, sizeof(ib));
-	r = amdgpu_ib_get(adev, NULL, 16,
-			  AMDGPU_IB_POOL_DIRECT, &ib);
+
+	r = amdgpu_ib_get(adev, NULL, 20, AMDGPU_IB_POOL_DIRECT, &ib);
 	if (r)
 		goto err1;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_11.c b/drivers/gpu/drm/amd/amdgpu/nbio_v7_11.c
index 676ab1d20d2f..1f52b4b1db03 100644
--- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_11.c
+++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_11.c
@@ -259,17 +259,17 @@ const struct nbio_hdp_flush_reg nbio_v7_11_hdp_flush_reg = {
 
 static void nbio_v7_11_init_registers(struct amdgpu_device *adev)
 {
-/*	uint32_t def, data;
+	uint32_t def, data;
+
+	def = data = RREG32_SOC15(NBIO, 0, regBIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3);
+	data = REG_SET_FIELD(data, BIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3,
+				CI_SWUS_MAX_READ_REQUEST_SIZE_MODE, 1);
+	data = REG_SET_FIELD(data, BIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3,
+				CI_SWUS_MAX_READ_REQUEST_SIZE_PRIV, 1);
 
-		def = data = RREG32_SOC15(NBIO, 0, regBIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3);
-		data = REG_SET_FIELD(data, BIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3,
-			CI_SWUS_MAX_READ_REQUEST_SIZE_MODE, 1);
-		data = REG_SET_FIELD(data, BIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3,
-			CI_SWUS_MAX_READ_REQUEST_SIZE_PRIV, 1);
+	if (def != data)
+		WREG32_SOC15(NBIO, 0, regBIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3, data);
 
-		if (def != data)
-			WREG32_SOC15(NBIO, 0, regBIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3, data);
-*/
 }
 
 static void nbio_v7_11_update_medium_grain_clock_gating(struct amdgpu_device *adev,
diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_9.c b/drivers/gpu/drm/amd/amdgpu/nbio_v7_9.c
index 23f26f8caad4..25a3da83e0fb 100644
--- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_9.c
+++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_9.c
@@ -611,11 +611,6 @@ static void nbio_v7_9_handle_ras_controller_intr_no_bifring(struct amdgpu_device
 
 		dev_info(adev->dev, "RAS controller interrupt triggered "
 					"by NBIF error\n");
-
-		/* ras_controller_int is dedicated for nbif ras error,
-		 * not the global interrupt for sync flood
-		 */
-		amdgpu_ras_reset_gpu(adev);
 	}
 
 	amdgpu_ras_error_data_fini(&err_data);
diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c
index d4b8d62f4294..c82776e5e9aa 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc15.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc15.c
@@ -1161,6 +1161,11 @@ static int soc15_common_early_init(void *handle)
 			AMD_PG_SUPPORT_VCN_DPG |
 			AMD_PG_SUPPORT_JPEG;
 		adev->external_rev_id = adev->rev_id + 0x46;
+		/* GC 9.4.3 uses MMIO register region hole at a different offset */
+		if (!amdgpu_sriov_vf(adev)) {
+			adev->rmmio_remap.reg_offset = 0x1A000;
+			adev->rmmio_remap.bus_addr = adev->rmmio_base + 0x1A000;
+		}
 		break;
 	default:
 		/* FIXME: not supported yet */
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
index 9cc32f577e38..4c8e278a0d0c 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
@@ -1128,7 +1128,7 @@ static inline struct kfd_node *kfd_node_by_irq_ids(struct amdgpu_device *adev,
 	struct kfd_dev *dev = adev->kfd.dev;
 	uint32_t i;
 
-	if (adev->ip_versions[GC_HWIP][0] != IP_VERSION(9, 4, 3))
+	if (KFD_GC_VERSION(dev) != IP_VERSION(9, 4, 3))
 		return dev->nodes[0];
 
 	for (i = 0; i < dev->num_nodes; i++)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
index 77649392e233..77f493262e05 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
@@ -169,16 +169,43 @@ int pqm_init(struct process_queue_manager *pqm, struct kfd_process *p)
 	return 0;
 }
 
+static void pqm_clean_queue_resource(struct process_queue_manager *pqm,
+				     struct process_queue_node *pqn)
+{
+	struct kfd_node *dev;
+	struct kfd_process_device *pdd;
+
+	dev = pqn->q->device;
+
+	pdd = kfd_get_process_device_data(dev, pqm->process);
+	if (!pdd) {
+		pr_err("Process device data doesn't exist\n");
+		return;
+	}
+
+	if (pqn->q->gws) {
+		if (KFD_GC_VERSION(pqn->q->device) != IP_VERSION(9, 4, 3) &&
+		    !dev->kfd->shared_resources.enable_mes)
+			amdgpu_amdkfd_remove_gws_from_process(
+				pqm->process->kgd_process_info, pqn->q->gws);
+		pdd->qpd.num_gws = 0;
+	}
+
+	if (dev->kfd->shared_resources.enable_mes) {
+		amdgpu_amdkfd_free_gtt_mem(dev->adev, pqn->q->gang_ctx_bo);
+		if (pqn->q->wptr_bo)
+			amdgpu_amdkfd_free_gtt_mem(dev->adev, pqn->q->wptr_bo);
+	}
+}
+
 void pqm_uninit(struct process_queue_manager *pqm)
 {
 	struct process_queue_node *pqn, *next;
 
 	list_for_each_entry_safe(pqn, next, &pqm->queues, process_queue_list) {
-		if (pqn->q && pqn->q->gws &&
-		    KFD_GC_VERSION(pqn->q->device) != IP_VERSION(9, 4, 3) &&
-		    !pqn->q->device->kfd->shared_resources.enable_mes)
-			amdgpu_amdkfd_remove_gws_from_process(pqm->process->kgd_process_info,
-				pqn->q->gws);
+		if (pqn->q)
+			pqm_clean_queue_resource(pqm, pqn);
+
 		kfd_procfs_del_queue(pqn->q);
 		uninit_queue(pqn->q);
 		list_del(&pqn->process_queue_list);
@@ -461,22 +488,7 @@ int pqm_destroy_queue(struct process_queue_manager *pqm, unsigned int qid)
 				goto err_destroy_queue;
 		}
 
-		if (pqn->q->gws) {
-			if (KFD_GC_VERSION(pqn->q->device) != IP_VERSION(9, 4, 3) &&
-			    !dev->kfd->shared_resources.enable_mes)
-				amdgpu_amdkfd_remove_gws_from_process(
-						pqm->process->kgd_process_info,
-						pqn->q->gws);
-			pdd->qpd.num_gws = 0;
-		}
-
-		if (dev->kfd->shared_resources.enable_mes) {
-			amdgpu_amdkfd_free_gtt_mem(dev->adev,
-						   pqn->q->gang_ctx_bo);
-			if (pqn->q->wptr_bo)
-				amdgpu_amdkfd_free_gtt_mem(dev->adev, pqn->q->wptr_bo);
-
-		}
+		pqm_clean_queue_resource(pqm, pqn);
 		uninit_queue(pqn->q);
 	}
 
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index ee97814ebd99..b452796fc6d3 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -6267,7 +6267,7 @@ int amdgpu_dm_connector_atomic_set_property(struct drm_connector *connector,
 		dm_new_state->underscan_enable = val;
 		ret = 0;
 	} else if (property == adev->mode_info.abm_level_property) {
-		dm_new_state->abm_level = val;
+		dm_new_state->abm_level = val ?: ABM_LEVEL_IMMEDIATE_DISABLE;
 		ret = 0;
 	}
 
@@ -6312,7 +6312,8 @@ int amdgpu_dm_connector_atomic_get_property(struct drm_connector *connector,
 		*val = dm_state->underscan_enable;
 		ret = 0;
 	} else if (property == adev->mode_info.abm_level_property) {
-		*val = dm_state->abm_level;
+		*val = (dm_state->abm_level != ABM_LEVEL_IMMEDIATE_DISABLE) ?
+			dm_state->abm_level : 0;
 		ret = 0;
 	}
 
@@ -6385,7 +6386,8 @@ void amdgpu_dm_connector_funcs_reset(struct drm_connector *connector)
 		state->pbn = 0;
 
 		if (connector->connector_type == DRM_MODE_CONNECTOR_eDP)
-			state->abm_level = amdgpu_dm_abm_level;
+			state->abm_level = amdgpu_dm_abm_level ?:
+				ABM_LEVEL_IMMEDIATE_DISABLE;
 
 		__drm_atomic_helper_connector_reset(connector, &state->base);
 	}
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_clk_mgr.c
index b2c4f97afc8b..8776055bbeaa 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_clk_mgr.c
@@ -334,7 +334,7 @@ static struct wm_table lpddr5_wm_table = {
 		{
 			.wm_inst = WM_A,
 			.wm_type = WM_TYPE_PSTATE_CHG,
-			.pstate_latency_us = 11.65333,
+			.pstate_latency_us = 129.0,
 			.sr_exit_time_us = 11.5,
 			.sr_enter_plus_exit_time_us = 14.5,
 			.valid = true,
@@ -342,7 +342,7 @@ static struct wm_table lpddr5_wm_table = {
 		{
 			.wm_inst = WM_B,
 			.wm_type = WM_TYPE_PSTATE_CHG,
-			.pstate_latency_us = 11.65333,
+			.pstate_latency_us = 129.0,
 			.sr_exit_time_us = 11.5,
 			.sr_enter_plus_exit_time_us = 14.5,
 			.valid = true,
@@ -350,7 +350,7 @@ static struct wm_table lpddr5_wm_table = {
 		{
 			.wm_inst = WM_C,
 			.wm_type = WM_TYPE_PSTATE_CHG,
-			.pstate_latency_us = 11.65333,
+			.pstate_latency_us = 129.0,
 			.sr_exit_time_us = 11.5,
 			.sr_enter_plus_exit_time_us = 14.5,
 			.valid = true,
@@ -358,7 +358,7 @@ static struct wm_table lpddr5_wm_table = {
 		{
 			.wm_inst = WM_D,
 			.wm_type = WM_TYPE_PSTATE_CHG,
-			.pstate_latency_us = 11.65333,
+			.pstate_latency_us = 129.0,
 			.sr_exit_time_us = 11.5,
 			.sr_enter_plus_exit_time_us = 14.5,
 			.valid = true,
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c
index 507a7cf56711..d5fde7d23fbf 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c
@@ -232,6 +232,10 @@ void dcn35_update_clocks(struct clk_mgr *clk_mgr_base,
 	if (dc->work_arounds.skip_clock_update)
 		return;
 
+	/* DTBCLK is fixed, so set a default if unspecified. */
+	if (new_clocks->dtbclk_en && !new_clocks->ref_dtbclk_khz)
+		new_clocks->ref_dtbclk_khz = 600000;
+
 	/*
 	 * if it is safe to lower, but we are already in the lower state, we don't have to do anything
 	 * also if safe to lower is false, we just go in the higher state
@@ -265,8 +269,10 @@ void dcn35_update_clocks(struct clk_mgr *clk_mgr_base,
 
 		if (!clk_mgr_base->clks.dtbclk_en && new_clocks->dtbclk_en) {
 			dcn35_smu_set_dtbclk(clk_mgr, true);
-			dcn35_update_clocks_update_dtb_dto(clk_mgr, context, clk_mgr_base->clks.ref_dtbclk_khz);
 			clk_mgr_base->clks.dtbclk_en = new_clocks->dtbclk_en;
+
+			dcn35_update_clocks_update_dtb_dto(clk_mgr, context, new_clocks->ref_dtbclk_khz);
+			clk_mgr_base->clks.ref_dtbclk_khz = new_clocks->ref_dtbclk_khz;
 		}
 
 		/* check that we're not already in D0 */
@@ -314,17 +320,12 @@ void dcn35_update_clocks(struct clk_mgr *clk_mgr_base,
 		update_dispclk = true;
 	}
 
-	if (!new_clocks->dtbclk_en) {
-		new_clocks->ref_dtbclk_khz = 600000;
-	}
-
 	/* clock limits are received with MHz precision, divide by 1000 to prevent setting clocks at every call */
 	if (!dc->debug.disable_dtb_ref_clk_switch &&
-			should_set_clock(safe_to_lower, new_clocks->ref_dtbclk_khz / 1000, clk_mgr_base->clks.ref_dtbclk_khz / 1000)) {
-		/* DCCG requires KHz precision for DTBCLK */
-		dcn35_smu_set_dtbclk(clk_mgr, true);
-
-		dcn35_update_clocks_update_dtb_dto(clk_mgr, context, clk_mgr_base->clks.ref_dtbclk_khz);
+	    should_set_clock(safe_to_lower, new_clocks->ref_dtbclk_khz / 1000,
+			     clk_mgr_base->clks.ref_dtbclk_khz / 1000)) {
+		dcn35_update_clocks_update_dtb_dto(clk_mgr, context, new_clocks->ref_dtbclk_khz);
+		clk_mgr_base->clks.ref_dtbclk_khz = new_clocks->ref_dtbclk_khz;
 	}
 
 	if (dpp_clock_lowered) {
@@ -443,32 +444,32 @@ static struct wm_table ddr5_wm_table = {
 			.wm_inst = WM_A,
 			.wm_type = WM_TYPE_PSTATE_CHG,
 			.pstate_latency_us = 11.72,
-			.sr_exit_time_us = 9,
-			.sr_enter_plus_exit_time_us = 11,
+			.sr_exit_time_us = 14.0,
+			.sr_enter_plus_exit_time_us = 16.0,
 			.valid = true,
 		},
 		{
 			.wm_inst = WM_B,
 			.wm_type = WM_TYPE_PSTATE_CHG,
 			.pstate_latency_us = 11.72,
-			.sr_exit_time_us = 9,
-			.sr_enter_plus_exit_time_us = 11,
+			.sr_exit_time_us = 14.0,
+			.sr_enter_plus_exit_time_us = 16.0,
 			.valid = true,
 		},
 		{
 			.wm_inst = WM_C,
 			.wm_type = WM_TYPE_PSTATE_CHG,
 			.pstate_latency_us = 11.72,
-			.sr_exit_time_us = 9,
-			.sr_enter_plus_exit_time_us = 11,
+			.sr_exit_time_us = 14.0,
+			.sr_enter_plus_exit_time_us = 16.0,
 			.valid = true,
 		},
 		{
 			.wm_inst = WM_D,
 			.wm_type = WM_TYPE_PSTATE_CHG,
 			.pstate_latency_us = 11.72,
-			.sr_exit_time_us = 9,
-			.sr_enter_plus_exit_time_us = 11,
+			.sr_exit_time_us = 14.0,
+			.sr_enter_plus_exit_time_us = 16.0,
 			.valid = true,
 		},
 	}
@@ -480,32 +481,32 @@ static struct wm_table lpddr5_wm_table = {
 			.wm_inst = WM_A,
 			.wm_type = WM_TYPE_PSTATE_CHG,
 			.pstate_latency_us = 11.65333,
-			.sr_exit_time_us = 11.5,
-			.sr_enter_plus_exit_time_us = 14.5,
+			.sr_exit_time_us = 14.0,
+			.sr_enter_plus_exit_time_us = 16.0,
 			.valid = true,
 		},
 		{
 			.wm_inst = WM_B,
 			.wm_type = WM_TYPE_PSTATE_CHG,
 			.pstate_latency_us = 11.65333,
-			.sr_exit_time_us = 11.5,
-			.sr_enter_plus_exit_time_us = 14.5,
+			.sr_exit_time_us = 14.0,
+			.sr_enter_plus_exit_time_us = 16.0,
 			.valid = true,
 		},
 		{
 			.wm_inst = WM_C,
 			.wm_type = WM_TYPE_PSTATE_CHG,
 			.pstate_latency_us = 11.65333,
-			.sr_exit_time_us = 11.5,
-			.sr_enter_plus_exit_time_us = 14.5,
+			.sr_exit_time_us = 14.0,
+			.sr_enter_plus_exit_time_us = 16.0,
 			.valid = true,
 		},
 		{
 			.wm_inst = WM_D,
 			.wm_type = WM_TYPE_PSTATE_CHG,
 			.pstate_latency_us = 11.65333,
-			.sr_exit_time_us = 11.5,
-			.sr_enter_plus_exit_time_us = 14.5,
+			.sr_exit_time_us = 14.0,
+			.sr_enter_plus_exit_time_us = 16.0,
 			.valid = true,
 		},
 	}
@@ -515,11 +516,6 @@ static DpmClocks_t_dcn35 dummy_clocks;
 
 static struct dcn35_watermarks dummy_wms = { 0 };
 
-static struct dcn35_ss_info_table ss_info_table = {
-	.ss_divider = 1000,
-	.ss_percentage = {0, 0, 375, 375, 375}
-};
-
 static void dcn35_build_watermark_ranges(struct clk_bw_params *bw_params, struct dcn35_watermarks *table)
 {
 	int i, num_valid_sets;
@@ -653,27 +649,47 @@ static unsigned int convert_wck_ratio(uint8_t wck_ratio)
 	return 1;
 }
 
+static inline uint32_t calc_dram_speed_mts(const MemPstateTable_t *entry)
+{
+	return entry->UClk * convert_wck_ratio(entry->WckRatio) * 2;
+}
+
 static void dcn35_clk_mgr_helper_populate_bw_params(struct clk_mgr_internal *clk_mgr,
 						    struct integrated_info *bios_info,
 						    DpmClocks_t_dcn35 *clock_table)
 {
 	struct clk_bw_params *bw_params = clk_mgr->base.bw_params;
 	struct clk_limit_table_entry def_max = bw_params->clk_table.entries[bw_params->clk_table.num_entries - 1];
-	uint32_t max_pstate = 0,  max_uclk = 0, max_fclk = 0;
-	uint32_t min_pstate = 0, max_dispclk = 0, max_dppclk = 0;
+	uint32_t max_fclk = 0, min_pstate = 0, max_dispclk = 0, max_dppclk = 0;
+	uint32_t max_pstate = 0, max_dram_speed_mts = 0, min_dram_speed_mts = 0;
 	int i;
 
+	/* Determine min/max p-state values. */
 	for (i = 0; i < clock_table->NumMemPstatesEnabled; i++) {
-		if (is_valid_clock_value(clock_table->MemPstateTable[i].UClk) &&
-		    clock_table->MemPstateTable[i].UClk > max_uclk) {
-			max_uclk = clock_table->MemPstateTable[i].UClk;
+		uint32_t dram_speed_mts = calc_dram_speed_mts(&clock_table->MemPstateTable[i]);
+
+		if (is_valid_clock_value(dram_speed_mts) && dram_speed_mts > max_dram_speed_mts) {
+			max_dram_speed_mts = dram_speed_mts;
 			max_pstate = i;
 		}
 	}
 
-	/* We expect the table to contain at least one valid Uclk entry. */
-	ASSERT(is_valid_clock_value(max_uclk));
+	min_dram_speed_mts = max_dram_speed_mts;
+	min_pstate = max_pstate;
+
+	for (i = 0; i < clock_table->NumMemPstatesEnabled; i++) {
+		uint32_t dram_speed_mts = calc_dram_speed_mts(&clock_table->MemPstateTable[i]);
+
+		if (is_valid_clock_value(dram_speed_mts) && dram_speed_mts < min_dram_speed_mts) {
+			min_dram_speed_mts = dram_speed_mts;
+			min_pstate = i;
+		}
+	}
 
+	/* We expect the table to contain at least one valid P-state entry. */
+	ASSERT(clock_table->NumMemPstatesEnabled &&
+	       is_valid_clock_value(max_dram_speed_mts) &&
+	       is_valid_clock_value(min_dram_speed_mts));
 
 	/* dispclk and dppclk can be max at any voltage, same number of levels for both */
 	if (clock_table->NumDispClkLevelsEnabled <= NUM_DISPCLK_DPM_LEVELS &&
@@ -683,47 +699,46 @@ static void dcn35_clk_mgr_helper_populate_bw_params(struct clk_mgr_internal *clk
 		max_dppclk = find_max_clk_value(clock_table->DppClocks,
 			clock_table->NumDispClkLevelsEnabled);
 	} else {
+		/* Invalid number of entries in the table from PMFW. */
 		ASSERT(0);
 	}
-	if (clock_table->NumFclkLevelsEnabled <= NUM_FCLK_DPM_LEVELS)
-		max_fclk = find_max_clk_value(clock_table->FclkClocks_Freq,
-			clock_table->NumFclkLevelsEnabled);
 
-	for (i = 0; i < clock_table->NumMemPstatesEnabled; i++) {
-		uint32_t min_uclk = clock_table->MemPstateTable[0].UClk;
-		int j;
+	/* Base the clock table on dcfclk, need at least one entry regardless of pmfw table */
+	ASSERT(clock_table->NumDcfClkLevelsEnabled > 0);
 
-		for (j = 1; j < clock_table->NumMemPstatesEnabled; j++) {
-			if (is_valid_clock_value(clock_table->MemPstateTable[j].UClk) &&
-			    clock_table->MemPstateTable[j].UClk < min_uclk &&
-			    clock_table->MemPstateTable[j].Voltage <= clock_table->SocVoltage[i]) {
-				min_uclk = clock_table->MemPstateTable[j].UClk;
-				min_pstate = j;
-			}
-		}
+	max_fclk = find_max_clk_value(clock_table->FclkClocks_Freq, clock_table->NumFclkLevelsEnabled);
 
+	for (i = 0; i < clock_table->NumDcfClkLevelsEnabled; i++) {
+		int j;
+
+		/* First search defaults for the clocks we don't read using closest lower or equal default dcfclk */
 		for (j = bw_params->clk_table.num_entries - 1; j > 0; j--)
 			if (bw_params->clk_table.entries[j].dcfclk_mhz <= clock_table->DcfClocks[i])
-			break;
+				break;
 
 		bw_params->clk_table.entries[i].phyclk_mhz = bw_params->clk_table.entries[j].phyclk_mhz;
 		bw_params->clk_table.entries[i].phyclk_d18_mhz = bw_params->clk_table.entries[j].phyclk_d18_mhz;
 		bw_params->clk_table.entries[i].dtbclk_mhz = bw_params->clk_table.entries[j].dtbclk_mhz;
-		bw_params->clk_table.entries[i].fclk_mhz = max_fclk;
+
+		/* Now update clocks we do read */
 		bw_params->clk_table.entries[i].memclk_mhz = clock_table->MemPstateTable[min_pstate].MemClk;
 		bw_params->clk_table.entries[i].voltage = clock_table->MemPstateTable[min_pstate].Voltage;
 		bw_params->clk_table.entries[i].dcfclk_mhz = clock_table->DcfClocks[i];
 		bw_params->clk_table.entries[i].socclk_mhz = clock_table->SocClocks[i];
 		bw_params->clk_table.entries[i].dispclk_mhz = max_dispclk;
 		bw_params->clk_table.entries[i].dppclk_mhz = max_dppclk;
-		bw_params->clk_table.entries[i].wck_ratio = convert_wck_ratio(
-			clock_table->MemPstateTable[min_pstate].WckRatio);
-		}
+		bw_params->clk_table.entries[i].wck_ratio =
+			convert_wck_ratio(clock_table->MemPstateTable[min_pstate].WckRatio);
+
+		/* Dcfclk and Fclk are tied, but at a different ratio */
+		bw_params->clk_table.entries[i].fclk_mhz = min(max_fclk, 2 * clock_table->DcfClocks[i]);
+	}
 
 	/* Make sure to include at least one entry at highest pstate */
 	if (max_pstate != min_pstate || i == 0) {
 		if (i > MAX_NUM_DPM_LVL - 1)
 			i = MAX_NUM_DPM_LVL - 1;
+
 		bw_params->clk_table.entries[i].fclk_mhz = max_fclk;
 		bw_params->clk_table.entries[i].memclk_mhz = clock_table->MemPstateTable[max_pstate].MemClk;
 		bw_params->clk_table.entries[i].voltage = clock_table->MemPstateTable[max_pstate].Voltage;
@@ -739,6 +754,7 @@ static void dcn35_clk_mgr_helper_populate_bw_params(struct clk_mgr_internal *clk
 	}
 	bw_params->clk_table.num_entries = i--;
 
+	/* Make sure all highest clocks are included*/
 	bw_params->clk_table.entries[i].socclk_mhz =
 		find_max_clk_value(clock_table->SocClocks, NUM_SOCCLK_DPM_LEVELS);
 	bw_params->clk_table.entries[i].dispclk_mhz =
@@ -757,6 +773,11 @@ static void dcn35_clk_mgr_helper_populate_bw_params(struct clk_mgr_internal *clk
 	bw_params->clk_table.num_entries_per_clk.num_fclk_levels = clock_table->NumFclkLevelsEnabled;
 	bw_params->clk_table.num_entries_per_clk.num_memclk_levels = clock_table->NumMemPstatesEnabled;
 	bw_params->clk_table.num_entries_per_clk.num_socclk_levels = clock_table->NumSocClkLevelsEnabled;
+
+	/*
+	 * Set any 0 clocks to max default setting. Not an issue for
+	 * power since we aren't doing switching in such case anyway
+	 */
 	for (i = 0; i < bw_params->clk_table.num_entries; i++) {
 		if (!bw_params->clk_table.entries[i].fclk_mhz) {
 			bw_params->clk_table.entries[i].fclk_mhz = def_max.fclk_mhz;
@@ -965,21 +986,6 @@ struct clk_mgr_funcs dcn35_fpga_funcs = {
 	.get_dtb_ref_clk_frequency = dcn31_get_dtb_ref_freq_khz,
 };
 
-static void dcn35_read_ss_info_from_lut(struct clk_mgr_internal *clk_mgr)
-{
-	uint32_t clock_source;
-	struct dc_context *ctx = clk_mgr->base.ctx;
-
-	REG_GET(CLK1_CLK2_BYPASS_CNTL, CLK2_BYPASS_SEL, &clock_source);
-
-	clk_mgr->dprefclk_ss_percentage = ss_info_table.ss_percentage[clock_source];
-
-	if (clk_mgr->dprefclk_ss_percentage != 0) {
-		clk_mgr->ss_on_dprefclk = true;
-		clk_mgr->dprefclk_ss_divider = ss_info_table.ss_divider;
-	}
-}
-
 void dcn35_clk_mgr_construct(
 		struct dc_context *ctx,
 		struct clk_mgr_dcn35 *clk_mgr,
@@ -1043,17 +1049,11 @@ void dcn35_clk_mgr_construct(
 	dcn35_dump_clk_registers(&clk_mgr->base.base.boot_snapshot, &clk_mgr->base.base, &log_info);
 
 	clk_mgr->base.base.dprefclk_khz = dcn35_smu_get_dprefclk(&clk_mgr->base);
-	clk_mgr->base.base.clks.ref_dtbclk_khz = dcn35_smu_get_dtbclk(&clk_mgr->base);
+	clk_mgr->base.base.clks.ref_dtbclk_khz = 600000;
 
-	if (!clk_mgr->base.base.clks.ref_dtbclk_khz)
-		dcn35_smu_set_dtbclk(&clk_mgr->base, true);
-
-	clk_mgr->base.base.clks.dtbclk_en = true;
 	dce_clock_read_ss_info(&clk_mgr->base);
 	/*when clk src is from FCH, it could have ss, same clock src as DPREF clk*/
 
-	dcn35_read_ss_info_from_lut(&clk_mgr->base);
-
 	clk_mgr->base.base.bw_params = &dcn35_bw_params;
 
 	if (clk_mgr->base.base.ctx->dc->debug.pstate_enabled) {
@@ -1129,7 +1129,6 @@ void dcn35_clk_mgr_construct(
 			ctx->dc->debug.disable_dpp_power_gate = false;
 			ctx->dc->debug.disable_hubp_power_gate = false;
 			ctx->dc->debug.disable_dsc_power_gate = false;
-			ctx->dc->debug.disable_hpo_power_gate = false;
 		} else {
 			/*let's reset the config control flag*/
 			ctx->dc->config.disable_ips = DMUB_IPS_DISABLE_ALL; /*pmfw not support it, disable it all*/
diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h
index 9316b737a8ba..2cafd644baff 100644
--- a/drivers/gpu/drm/amd/display/dc/dc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc.h
@@ -874,6 +874,7 @@ struct dc_debug_options {
 	unsigned int seamless_boot_odm_combine;
 	unsigned int force_odm_combine_4to1; //bit vector based on otg inst
 	int minimum_z8_residency_time;
+	int minimum_z10_residency_time;
 	bool disable_z9_mpc;
 	unsigned int force_fclk_khz;
 	bool enable_tri_buf;
@@ -1608,7 +1609,6 @@ struct dc_link {
 	enum edp_revision edp_revision;
 	union dpcd_sink_ext_caps dpcd_sink_ext_caps;
 
-	struct backlight_settings backlight_settings;
 	struct psr_settings psr_settings;
 
 	struct replay_settings replay_settings;
diff --git a/drivers/gpu/drm/amd/display/dc/dc_types.h b/drivers/gpu/drm/amd/display/dc/dc_types.h
index fcb825e4f1bb..35d146217aef 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_types.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_types.h
@@ -991,10 +991,6 @@ struct link_mst_stream_allocation_table {
 	struct link_mst_stream_allocation stream_allocations[MAX_CONTROLLER_NUM];
 };
 
-struct backlight_settings {
-	uint32_t backlight_millinits;
-};
-
 /* PSR feature flags */
 struct psr_settings {
 	bool psr_feature_enabled;		// PSR is supported by sink
diff --git a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c
index 677361d74a4e..c97391edb5ff 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c
@@ -871,7 +871,7 @@ static const struct dc_plane_cap plane_cap = {
 static const struct dc_debug_options debug_defaults_drv = {
 	.disable_z10 = false,
 	.enable_z9_disable_interface = true,
-	.minimum_z8_residency_time = 2000,
+	.minimum_z8_residency_time = 2100,
 	.psr_skip_crtc_disable = true,
 	.replay_skip_crtc_disabled = true,
 	.disable_dmcu = true,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn35/dcn35_pg_cntl.c b/drivers/gpu/drm/amd/display/dc/dcn35/dcn35_pg_cntl.c
index 46f71ff08fd1..d19db8e9b8a5 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn35/dcn35_pg_cntl.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn35/dcn35_pg_cntl.c
@@ -261,6 +261,7 @@ void pg_cntl35_hpo_pg_control(struct pg_cntl *pg_cntl, bool power_on)
 	uint32_t power_gate = power_on ? 0 : 1;
 	uint32_t pwr_status = power_on ? 0 : 2;
 	uint32_t org_ip_request_cntl;
+	uint32_t power_forceon;
 	bool block_enabled;
 
 	if (pg_cntl->ctx->dc->debug.ignore_pg ||
@@ -277,6 +278,10 @@ void pg_cntl35_hpo_pg_control(struct pg_cntl *pg_cntl, bool power_on)
 			return;
 	}
 
+	REG_GET(DOMAIN25_PG_CONFIG, DOMAIN_POWER_FORCEON, &power_forceon);
+	if (power_forceon)
+		return;
+
 	REG_GET(DC_IP_REQUEST_CNTL, IP_REQUEST_EN, &org_ip_request_cntl);
 	if (org_ip_request_cntl == 0)
 		REG_SET(DC_IP_REQUEST_CNTL, 0, IP_REQUEST_EN, 1);
@@ -304,6 +309,7 @@ void pg_cntl35_io_clk_pg_control(struct pg_cntl *pg_cntl, bool power_on)
 	uint32_t power_gate = power_on ? 0 : 1;
 	uint32_t pwr_status = power_on ? 0 : 2;
 	uint32_t org_ip_request_cntl;
+	uint32_t power_forceon;
 	bool block_enabled;
 
 	if (pg_cntl->ctx->dc->debug.ignore_pg ||
@@ -319,6 +325,10 @@ void pg_cntl35_io_clk_pg_control(struct pg_cntl *pg_cntl, bool power_on)
 			return;
 	}
 
+	REG_GET(DOMAIN22_PG_CONFIG, DOMAIN_POWER_FORCEON, &power_forceon);
+	if (power_forceon)
+		return;
+
 	REG_GET(DC_IP_REQUEST_CNTL, IP_REQUEST_EN, &org_ip_request_cntl);
 	if (org_ip_request_cntl == 0)
 		REG_SET(DC_IP_REQUEST_CNTL, 0, IP_REQUEST_EN, 1);
diff --git a/drivers/gpu/drm/amd/display/dc/dcn35/dcn35_resource.c b/drivers/gpu/drm/amd/display/dc/dcn35/dcn35_resource.c
index c7e011d26d41..70ef1e7ff841 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn35/dcn35_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn35/dcn35_resource.c
@@ -1712,6 +1712,13 @@ static bool dcn35_validate_bandwidth(struct dc *dc,
 
 	out = dml2_validate(dc, context, fast_validate);
 
+	if (fast_validate)
+		return out;
+
+	DC_FP_START();
+	dcn35_decide_zstate_support(dc, context);
+	DC_FP_END();
+
 	return out;
 }
 
@@ -1857,7 +1864,7 @@ static bool dcn35_resource_construct(
 
 	/* Use pipe context based otg sync logic */
 	dc->config.use_pipe_ctx_sync_logic = true;
-	dc->config.use_default_clock_table = false;
+
 	/* read VBIOS LTTPR caps */
 	{
 		if (ctx->dc_bios->funcs->get_lttpr_caps) {
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dc_features.h b/drivers/gpu/drm/amd/display/dc/dml/dc_features.h
index 2cbdd75429ff..6e669a2c5b2d 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dc_features.h
+++ b/drivers/gpu/drm/amd/display/dc/dml/dc_features.h
@@ -36,7 +36,7 @@
  * Define the maximum amount of states supported by the ASIC. Every ASIC has a
  * specific number of states; this macro defines the maximum number of states.
  */
-#define DC__VOLTAGE_STATES 20
+#define DC__VOLTAGE_STATES 40
 #define DC__NUM_DPP__4 1
 #define DC__NUM_DPP__0_PRESENT 1
 #define DC__NUM_DPP__1_PRESENT 1
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c
index 7fc8b18096ba..ec77b2b41ba3 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c
@@ -950,10 +950,8 @@ static enum dcn_zstate_support_state  decide_zstate_support(struct dc *dc, struc
 {
 	int plane_count;
 	int i;
-	unsigned int min_dst_y_next_start_us;
 
 	plane_count = 0;
-	min_dst_y_next_start_us = 0;
 	for (i = 0; i < dc->res_pool->pipe_count; i++) {
 		if (context->res_ctx.pipe_ctx[i].plane_state)
 			plane_count++;
@@ -975,26 +973,15 @@ static enum dcn_zstate_support_state  decide_zstate_support(struct dc *dc, struc
 	else if (context->stream_count == 1 &&  context->streams[0]->signal == SIGNAL_TYPE_EDP) {
 		struct dc_link *link = context->streams[0]->sink->link;
 		struct dc_stream_status *stream_status = &context->stream_status[0];
-		struct dc_stream_state *current_stream = context->streams[0];
 		int minmum_z8_residency = dc->debug.minimum_z8_residency_time > 0 ? dc->debug.minimum_z8_residency_time : 1000;
 		bool allow_z8 = context->bw_ctx.dml.vba.StutterPeriod > (double)minmum_z8_residency;
 		bool is_pwrseq0 = link->link_index == 0;
-		bool isFreesyncVideo;
-
-		isFreesyncVideo = current_stream->adjust.v_total_min == current_stream->adjust.v_total_max;
-		isFreesyncVideo = isFreesyncVideo && current_stream->timing.v_total < current_stream->adjust.v_total_min;
-		for (i = 0; i < dc->res_pool->pipe_count; i++) {
-			if (context->res_ctx.pipe_ctx[i].stream == current_stream && isFreesyncVideo) {
-				min_dst_y_next_start_us = context->res_ctx.pipe_ctx[i].dlg_regs.min_dst_y_next_start_us;
-				break;
-			}
-		}
 
 		/* Don't support multi-plane configurations */
 		if (stream_status->plane_count > 1)
 			return DCN_ZSTATE_SUPPORT_DISALLOW;
 
-		if (is_pwrseq0 && (context->bw_ctx.dml.vba.StutterPeriod > 5000.0 || min_dst_y_next_start_us > 5000))
+		if (is_pwrseq0 && context->bw_ctx.dml.vba.StutterPeriod > 5000.0)
 			return DCN_ZSTATE_SUPPORT_ALLOW;
 		else if (is_pwrseq0 && link->psr_settings.psr_version == DC_PSR_VERSION_1 && !link->panel_config.psr.disable_psr)
 			return allow_z8 ? DCN_ZSTATE_SUPPORT_ALLOW_Z8_Z10_ONLY : DCN_ZSTATE_SUPPORT_ALLOW_Z10_ONLY;
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c
index 9ec4172d1c2d..b46cde525066 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c
@@ -1192,13 +1192,16 @@ static bool update_pipe_slice_table_with_split_flags(
 	 */
 	struct pipe_ctx *pipe;
 	bool odm;
-	int i;
+	int dc_pipe_idx, dml_pipe_idx = 0;
 	bool updated = false;
 
-	for (i = 0; i < dc->res_pool->pipe_count; i++) {
-		pipe = &context->res_ctx.pipe_ctx[i];
+	for (dc_pipe_idx = 0;
+			dc_pipe_idx < dc->res_pool->pipe_count; dc_pipe_idx++) {
+		pipe = &context->res_ctx.pipe_ctx[dc_pipe_idx];
+		if (resource_is_pipe_type(pipe, FREE_PIPE))
+			continue;
 
-		if (merge[i]) {
+		if (merge[dc_pipe_idx]) {
 			if (resource_is_pipe_type(pipe, OPP_HEAD))
 				/* merging OPP head means reducing ODM slice
 				 * count by 1
@@ -1213,17 +1216,18 @@ static bool update_pipe_slice_table_with_split_flags(
 			updated = true;
 		}
 
-		if (split[i]) {
-			odm = vba->ODMCombineEnabled[vba->pipe_plane[i]] !=
+		if (split[dc_pipe_idx]) {
+			odm = vba->ODMCombineEnabled[vba->pipe_plane[dml_pipe_idx]] !=
 					dm_odm_combine_mode_disabled;
 			if (odm && resource_is_pipe_type(pipe, OPP_HEAD))
 				update_slice_table_for_stream(
-						table, pipe->stream, split[i] - 1);
+						table, pipe->stream, split[dc_pipe_idx] - 1);
 			else if (!odm && resource_is_pipe_type(pipe, DPP_PIPE))
 				update_slice_table_for_plane(table, pipe,
-						pipe->plane_state, split[i] - 1);
+						pipe->plane_state, split[dc_pipe_idx] - 1);
 			updated = true;
 		}
+		dml_pipe_idx++;
 	}
 	return updated;
 }
@@ -2231,6 +2235,7 @@ void dcn32_calculate_wm_and_dlg_fpu(struct dc *dc, struct dc_state *context,
 	int i, pipe_idx, vlevel_temp = 0;
 	double dcfclk = dcn3_2_soc.clock_limits[0].dcfclk_mhz;
 	double dcfclk_from_validation = context->bw_ctx.dml.vba.DCFCLKState[vlevel][context->bw_ctx.dml.vba.maxMpcComb];
+	double dram_speed_from_validation = context->bw_ctx.dml.vba.DRAMSpeed;
 	double dcfclk_from_fw_based_mclk_switching = dcfclk_from_validation;
 	bool pstate_en = context->bw_ctx.dml.vba.DRAMClockChangeSupport[vlevel][context->bw_ctx.dml.vba.maxMpcComb] !=
 			dm_dram_clock_change_unsupported;
@@ -2418,7 +2423,7 @@ void dcn32_calculate_wm_and_dlg_fpu(struct dc *dc, struct dc_state *context,
 	}
 
 	if (dc->clk_mgr->bw_params->wm_table.nv_entries[WM_C].valid) {
-		min_dram_speed_mts = context->bw_ctx.dml.vba.DRAMSpeed;
+		min_dram_speed_mts = dram_speed_from_validation;
 		min_dram_speed_mts_margin = 160;
 
 		context->bw_ctx.dml.soc.dram_clock_change_latency_us =
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.c
index a5fe523668e9..39cf1ae3a3e1 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.c
@@ -164,10 +164,10 @@ struct _vcs_dpi_soc_bounding_box_st dcn3_5_soc = {
 		},
 	},
 	.num_states = 5,
-	.sr_exit_time_us = 9.0,
-	.sr_enter_plus_exit_time_us = 11.0,
-	.sr_exit_z8_time_us = 50.0, /*changed from 442.0*/
-	.sr_enter_plus_exit_z8_time_us = 50.0,/*changed from 560.0*/
+	.sr_exit_time_us = 14.0,
+	.sr_enter_plus_exit_time_us = 16.0,
+	.sr_exit_z8_time_us = 525.0,
+	.sr_enter_plus_exit_z8_time_us = 715.0,
 	.fclk_change_latency_us = 20.0,
 	.usr_retraining_latency_us = 2,
 	.writeback_latency_us = 12.0,
@@ -329,6 +329,48 @@ void dcn35_update_bw_bounding_box_fpu(struct dc *dc,
 	/*temp till dml2 fully work without dml1*/
 	dml_init_instance(&dc->dml, &dcn3_5_soc, &dcn3_5_ip,
 				DML_PROJECT_DCN31);
+
+	/*copy to dml2, before dml2_create*/
+	if (clk_table->num_entries > 2) {
+
+		for (i = 0; i < clk_table->num_entries; i++) {
+			dc->dml2_options.bbox_overrides.clks_table.num_states =
+				clk_table->num_entries;
+			dc->dml2_options.bbox_overrides.clks_table.clk_entries[i].dcfclk_mhz =
+				clock_limits[i].dcfclk_mhz;
+			dc->dml2_options.bbox_overrides.clks_table.clk_entries[i].fclk_mhz =
+				clock_limits[i].fabricclk_mhz;
+			dc->dml2_options.bbox_overrides.clks_table.clk_entries[i].dispclk_mhz =
+				clock_limits[i].dispclk_mhz;
+			dc->dml2_options.bbox_overrides.clks_table.clk_entries[i].dppclk_mhz =
+				clock_limits[i].dppclk_mhz;
+			dc->dml2_options.bbox_overrides.clks_table.clk_entries[i].socclk_mhz =
+				clock_limits[i].socclk_mhz;
+			dc->dml2_options.bbox_overrides.clks_table.clk_entries[i].memclk_mhz =
+				clk_table->entries[i].memclk_mhz * clk_table->entries[i].wck_ratio;
+			dc->dml2_options.bbox_overrides.clks_table.num_entries_per_clk.num_dcfclk_levels =
+				clk_table->num_entries;
+			dc->dml2_options.bbox_overrides.clks_table.num_entries_per_clk.num_fclk_levels =
+				clk_table->num_entries;
+			dc->dml2_options.bbox_overrides.clks_table.num_entries_per_clk.num_dispclk_levels =
+				clk_table->num_entries;
+			dc->dml2_options.bbox_overrides.clks_table.num_entries_per_clk.num_dppclk_levels =
+				clk_table->num_entries;
+			dc->dml2_options.bbox_overrides.clks_table.num_entries_per_clk.num_socclk_levels =
+				clk_table->num_entries;
+			dc->dml2_options.bbox_overrides.clks_table.num_entries_per_clk.num_memclk_levels =
+				clk_table->num_entries;
+		}
+	}
+
+	/* Update latency values */
+	dc->dml2_options.bbox_overrides.dram_clock_change_latency_us = dcn3_5_soc.dram_clock_change_latency_us;
+
+	dc->dml2_options.bbox_overrides.sr_exit_latency_us = dcn3_5_soc.sr_exit_time_us;
+	dc->dml2_options.bbox_overrides.sr_enter_plus_exit_latency_us = dcn3_5_soc.sr_enter_plus_exit_time_us;
+
+	dc->dml2_options.bbox_overrides.sr_exit_z8_time_us = dcn3_5_soc.sr_exit_z8_time_us;
+	dc->dml2_options.bbox_overrides.sr_enter_plus_exit_z8_time_us = dcn3_5_soc.sr_enter_plus_exit_z8_time_us;
 }
 
 static bool is_dual_plane(enum surface_pixel_format format)
@@ -507,3 +549,37 @@ int dcn35_populate_dml_pipes_from_context_fpu(struct dc *dc,
 
 	return pipe_cnt;
 }
+
+void dcn35_decide_zstate_support(struct dc *dc, struct dc_state *context)
+{
+	enum dcn_zstate_support_state support = DCN_ZSTATE_SUPPORT_DISALLOW;
+	unsigned int i, plane_count = 0;
+
+	for (i = 0; i < dc->res_pool->pipe_count; i++) {
+		if (context->res_ctx.pipe_ctx[i].plane_state)
+			plane_count++;
+	}
+
+	if (plane_count == 0) {
+		support = DCN_ZSTATE_SUPPORT_ALLOW;
+	} else if (plane_count == 1 && context->stream_count == 1 && context->streams[0]->signal == SIGNAL_TYPE_EDP) {
+		struct dc_link *link = context->streams[0]->sink->link;
+		bool is_pwrseq0 = link && link->link_index == 0;
+		bool is_psr1 = link && link->psr_settings.psr_version == DC_PSR_VERSION_1 && !link->panel_config.psr.disable_psr;
+		int minmum_z8_residency =
+			dc->debug.minimum_z8_residency_time > 0 ? dc->debug.minimum_z8_residency_time : 1000;
+		bool allow_z8 = context->bw_ctx.dml.vba.StutterPeriod > (double)minmum_z8_residency;
+		int minmum_z10_residency =
+			dc->debug.minimum_z10_residency_time > 0 ? dc->debug.minimum_z10_residency_time : 5000;
+		bool allow_z10 = context->bw_ctx.dml.vba.StutterPeriod > (double)minmum_z10_residency;
+
+		if (is_pwrseq0 && allow_z10)
+			support = DCN_ZSTATE_SUPPORT_ALLOW;
+		else if (is_pwrseq0 && is_psr1)
+			support = allow_z8 ? DCN_ZSTATE_SUPPORT_ALLOW_Z8_Z10_ONLY : DCN_ZSTATE_SUPPORT_ALLOW_Z10_ONLY;
+		else if (allow_z8)
+			support = DCN_ZSTATE_SUPPORT_ALLOW_Z8_ONLY;
+	}
+
+	context->bw_ctx.bw.dcn.clk.zstate_support = support;
+}
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.h b/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.h
index e8d5a170893e..067480fc3691 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.h
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.h
@@ -39,4 +39,6 @@ int dcn35_populate_dml_pipes_from_context_fpu(struct dc *dc,
 					      display_e2e_pipe_params_st *pipes,
 					      bool fast_validate);
 
+void dcn35_decide_zstate_support(struct dc *dc, struct dc_state *context);
+
 #endif
diff --git a/drivers/gpu/drm/amd/display/dc/dml2/display_mode_core.c b/drivers/gpu/drm/amd/display/dc/dml2/display_mode_core.c
index 510be909cd75..59718ee33e51 100644
--- a/drivers/gpu/drm/amd/display/dc/dml2/display_mode_core.c
+++ b/drivers/gpu/drm/amd/display/dc/dml2/display_mode_core.c
@@ -6329,7 +6329,7 @@ static void dml_prefetch_check(struct display_mode_lib_st *mode_lib)
 				mode_lib->ms.NoOfDPPThisState,
 				mode_lib->ms.dpte_group_bytes,
 				s->HostVMInefficiencyFactor,
-				mode_lib->ms.soc.hostvm_min_page_size_kbytes,
+				mode_lib->ms.soc.hostvm_min_page_size_kbytes * 1024,
 				mode_lib->ms.cache_display_cfg.plane.HostVMMaxPageTableLevels);
 
 		s->NextMaxVStartup = s->MaxVStartupAllPlanes[j];
@@ -6542,7 +6542,7 @@ static void dml_prefetch_check(struct display_mode_lib_st *mode_lib)
 						mode_lib->ms.cache_display_cfg.plane.HostVMEnable,
 						mode_lib->ms.cache_display_cfg.plane.HostVMMaxPageTableLevels,
 						mode_lib->ms.cache_display_cfg.plane.GPUVMEnable,
-						mode_lib->ms.soc.hostvm_min_page_size_kbytes,
+						mode_lib->ms.soc.hostvm_min_page_size_kbytes * 1024,
 						mode_lib->ms.PDEAndMetaPTEBytesPerFrame[j][k],
 						mode_lib->ms.MetaRowBytes[j][k],
 						mode_lib->ms.DPTEBytesPerRow[j][k],
@@ -7687,7 +7687,7 @@ dml_bool_t dml_core_mode_support(struct display_mode_lib_st *mode_lib)
 		CalculateVMRowAndSwath_params->HostVMMaxNonCachedPageTableLevels = mode_lib->ms.cache_display_cfg.plane.HostVMMaxPageTableLevels;
 		CalculateVMRowAndSwath_params->GPUVMMaxPageTableLevels = mode_lib->ms.cache_display_cfg.plane.GPUVMMaxPageTableLevels;
 		CalculateVMRowAndSwath_params->GPUVMMinPageSizeKBytes = mode_lib->ms.cache_display_cfg.plane.GPUVMMinPageSizeKBytes;
-		CalculateVMRowAndSwath_params->HostVMMinPageSize = mode_lib->ms.soc.hostvm_min_page_size_kbytes;
+		CalculateVMRowAndSwath_params->HostVMMinPageSize = mode_lib->ms.soc.hostvm_min_page_size_kbytes * 1024;
 		CalculateVMRowAndSwath_params->PTEBufferModeOverrideEn = mode_lib->ms.cache_display_cfg.plane.PTEBufferModeOverrideEn;
 		CalculateVMRowAndSwath_params->PTEBufferModeOverrideVal = mode_lib->ms.cache_display_cfg.plane.PTEBufferMode;
 		CalculateVMRowAndSwath_params->PTEBufferSizeNotExceeded = mode_lib->ms.PTEBufferSizeNotExceededPerState;
@@ -7957,7 +7957,7 @@ dml_bool_t dml_core_mode_support(struct display_mode_lib_st *mode_lib)
 		UseMinimumDCFCLK_params->GPUVMMaxPageTableLevels = mode_lib->ms.cache_display_cfg.plane.GPUVMMaxPageTableLevels;
 		UseMinimumDCFCLK_params->HostVMEnable = mode_lib->ms.cache_display_cfg.plane.HostVMEnable;
 		UseMinimumDCFCLK_params->NumberOfActiveSurfaces = mode_lib->ms.num_active_planes;
-		UseMinimumDCFCLK_params->HostVMMinPageSize = mode_lib->ms.soc.hostvm_min_page_size_kbytes;
+		UseMinimumDCFCLK_params->HostVMMinPageSize = mode_lib->ms.soc.hostvm_min_page_size_kbytes * 1024;
 		UseMinimumDCFCLK_params->HostVMMaxNonCachedPageTableLevels = mode_lib->ms.cache_display_cfg.plane.HostVMMaxPageTableLevels;
 		UseMinimumDCFCLK_params->DynamicMetadataVMEnabled = mode_lib->ms.ip.dynamic_metadata_vm_enabled;
 		UseMinimumDCFCLK_params->ImmediateFlipRequirement = s->ImmediateFlipRequiredFinal;
@@ -8699,7 +8699,7 @@ void dml_core_mode_programming(struct display_mode_lib_st *mode_lib, const struc
 	CalculateVMRowAndSwath_params->HostVMMaxNonCachedPageTableLevels = mode_lib->ms.cache_display_cfg.plane.HostVMMaxPageTableLevels;
 	CalculateVMRowAndSwath_params->GPUVMMaxPageTableLevels = mode_lib->ms.cache_display_cfg.plane.GPUVMMaxPageTableLevels;
 	CalculateVMRowAndSwath_params->GPUVMMinPageSizeKBytes = mode_lib->ms.cache_display_cfg.plane.GPUVMMinPageSizeKBytes;
-	CalculateVMRowAndSwath_params->HostVMMinPageSize = mode_lib->ms.soc.hostvm_min_page_size_kbytes;
+	CalculateVMRowAndSwath_params->HostVMMinPageSize = mode_lib->ms.soc.hostvm_min_page_size_kbytes * 1024;
 	CalculateVMRowAndSwath_params->PTEBufferModeOverrideEn = mode_lib->ms.cache_display_cfg.plane.PTEBufferModeOverrideEn;
 	CalculateVMRowAndSwath_params->PTEBufferModeOverrideVal = mode_lib->ms.cache_display_cfg.plane.PTEBufferMode;
 	CalculateVMRowAndSwath_params->PTEBufferSizeNotExceeded = s->dummy_boolean_array[0];
@@ -8805,7 +8805,7 @@ void dml_core_mode_programming(struct display_mode_lib_st *mode_lib, const struc
 			mode_lib->ms.cache_display_cfg.hw.DPPPerSurface,
 			locals->dpte_group_bytes,
 			s->HostVMInefficiencyFactor,
-			mode_lib->ms.soc.hostvm_min_page_size_kbytes,
+			mode_lib->ms.soc.hostvm_min_page_size_kbytes * 1024,
 			mode_lib->ms.cache_display_cfg.plane.HostVMMaxPageTableLevels);
 
 	locals->TCalc = 24.0 / locals->DCFCLKDeepSleep;
@@ -8995,7 +8995,7 @@ void dml_core_mode_programming(struct display_mode_lib_st *mode_lib, const struc
 			CalculatePrefetchSchedule_params->GPUVMEnable = mode_lib->ms.cache_display_cfg.plane.GPUVMEnable;
 			CalculatePrefetchSchedule_params->HostVMEnable = mode_lib->ms.cache_display_cfg.plane.HostVMEnable;
 			CalculatePrefetchSchedule_params->HostVMMaxNonCachedPageTableLevels = mode_lib->ms.cache_display_cfg.plane.HostVMMaxPageTableLevels;
-			CalculatePrefetchSchedule_params->HostVMMinPageSize = mode_lib->ms.soc.hostvm_min_page_size_kbytes;
+			CalculatePrefetchSchedule_params->HostVMMinPageSize = mode_lib->ms.soc.hostvm_min_page_size_kbytes * 1024;
 			CalculatePrefetchSchedule_params->DynamicMetadataEnable = mode_lib->ms.cache_display_cfg.plane.DynamicMetadataEnable[k];
 			CalculatePrefetchSchedule_params->DynamicMetadataVMEnabled = mode_lib->ms.ip.dynamic_metadata_vm_enabled;
 			CalculatePrefetchSchedule_params->DynamicMetadataLinesBeforeActiveRequired = mode_lib->ms.cache_display_cfg.plane.DynamicMetadataLinesBeforeActiveRequired[k];
@@ -9240,7 +9240,7 @@ void dml_core_mode_programming(struct display_mode_lib_st *mode_lib, const struc
 						mode_lib->ms.cache_display_cfg.plane.HostVMEnable,
 						mode_lib->ms.cache_display_cfg.plane.HostVMMaxPageTableLevels,
 						mode_lib->ms.cache_display_cfg.plane.GPUVMEnable,
-						mode_lib->ms.soc.hostvm_min_page_size_kbytes,
+						mode_lib->ms.soc.hostvm_min_page_size_kbytes * 1024,
 						locals->PDEAndMetaPTEBytesFrame[k],
 						locals->MetaRowByte[k],
 						locals->PixelPTEBytesPerRow[k],
diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c b/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c
index 75171bee6f71..fa8fe5bf7e57 100644
--- a/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c
+++ b/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c
@@ -341,25 +341,42 @@ void dml2_init_soc_states(struct dml2_context *dml2, const struct dc *in_dc,
 		break;
 	}
 
-	/* Override from passed values, mainly for debugging purposes, if available */
-	if (dml2->config.bbox_overrides.sr_exit_latency_us) {
-		p->in_states->state_array[0].sr_exit_time_us = dml2->config.bbox_overrides.sr_exit_latency_us;
-	}
+	/* Override from passed values, if available */
+	for (i = 0; i < p->in_states->num_states; i++) {
+		if (dml2->config.bbox_overrides.sr_exit_latency_us) {
+			p->in_states->state_array[i].sr_exit_time_us =
+				dml2->config.bbox_overrides.sr_exit_latency_us;
+		}
 
-	if (dml2->config.bbox_overrides.sr_enter_plus_exit_latency_us) {
-		p->in_states->state_array[0].sr_enter_plus_exit_time_us = dml2->config.bbox_overrides.sr_enter_plus_exit_latency_us;
-	}
+		if (dml2->config.bbox_overrides.sr_enter_plus_exit_latency_us) {
+			p->in_states->state_array[i].sr_enter_plus_exit_time_us =
+				dml2->config.bbox_overrides.sr_enter_plus_exit_latency_us;
+		}
 
-	if (dml2->config.bbox_overrides.urgent_latency_us) {
-		p->in_states->state_array[0].urgent_latency_pixel_data_only_us = dml2->config.bbox_overrides.urgent_latency_us;
-	}
+		if (dml2->config.bbox_overrides.sr_exit_z8_time_us) {
+			p->in_states->state_array[i].sr_exit_z8_time_us =
+				dml2->config.bbox_overrides.sr_exit_z8_time_us;
+		}
 
-	if (dml2->config.bbox_overrides.dram_clock_change_latency_us) {
-		p->in_states->state_array[0].dram_clock_change_latency_us = dml2->config.bbox_overrides.dram_clock_change_latency_us;
-	}
+		if (dml2->config.bbox_overrides.sr_enter_plus_exit_z8_time_us) {
+			p->in_states->state_array[i].sr_enter_plus_exit_z8_time_us =
+				dml2->config.bbox_overrides.sr_enter_plus_exit_z8_time_us;
+		}
+
+		if (dml2->config.bbox_overrides.urgent_latency_us) {
+			p->in_states->state_array[i].urgent_latency_pixel_data_only_us =
+				dml2->config.bbox_overrides.urgent_latency_us;
+		}
 
-	if (dml2->config.bbox_overrides.fclk_change_latency_us) {
-		p->in_states->state_array[0].fclk_change_latency_us = dml2->config.bbox_overrides.fclk_change_latency_us;
+		if (dml2->config.bbox_overrides.dram_clock_change_latency_us) {
+			p->in_states->state_array[i].dram_clock_change_latency_us =
+				dml2->config.bbox_overrides.dram_clock_change_latency_us;
+		}
+
+		if (dml2->config.bbox_overrides.fclk_change_latency_us) {
+			p->in_states->state_array[i].fclk_change_latency_us =
+				dml2->config.bbox_overrides.fclk_change_latency_us;
+		}
 	}
 
 	/* DCFCLK stas values are project specific */
@@ -498,8 +515,8 @@ void dml2_translate_socbb_params(const struct dc *in, struct soc_bounding_box_st
 	out->do_urgent_latency_adjustment = in_soc_params->do_urgent_latency_adjustment;
 	out->dram_channel_width_bytes = (dml_uint_t)in_soc_params->dram_channel_width_bytes;
 	out->fabric_datapath_to_dcn_data_return_bytes = (dml_uint_t)in_soc_params->fabric_datapath_to_dcn_data_return_bytes;
-	out->gpuvm_min_page_size_kbytes = in_soc_params->gpuvm_min_page_size_bytes * 1024;
-	out->hostvm_min_page_size_kbytes = in_soc_params->hostvm_min_page_size_bytes * 1024;
+	out->gpuvm_min_page_size_kbytes = in_soc_params->gpuvm_min_page_size_bytes / 1024;
+	out->hostvm_min_page_size_kbytes = in_soc_params->hostvm_min_page_size_bytes / 1024;
 	out->mall_allocated_for_dcn_mbytes = (dml_uint_t)in_soc_params->mall_allocated_for_dcn_mbytes;
 	out->max_avg_dram_bw_use_normal_percent = in_soc_params->max_avg_dram_bw_use_normal_percent;
 	out->max_avg_fabric_bw_use_normal_percent = in_soc_params->max_avg_fabric_bw_use_normal_percent;
@@ -1040,9 +1057,12 @@ void map_dc_state_into_dml_display_cfg(struct dml2_context *dml2, struct dc_stat
 	}
 
 	//Generally these are set by referencing our latest BB/IP params in dcn32_resource.c file
-	dml_dispcfg->plane.GPUVMEnable = true;
-	dml_dispcfg->plane.GPUVMMaxPageTableLevels = 4;
-	dml_dispcfg->plane.HostVMEnable = false;
+	dml_dispcfg->plane.GPUVMEnable = dml2->v20.dml_core_ctx.ip.gpuvm_enable;
+	dml_dispcfg->plane.GPUVMMaxPageTableLevels = dml2->v20.dml_core_ctx.ip.gpuvm_max_page_table_levels;
+	dml_dispcfg->plane.HostVMEnable = dml2->v20.dml_core_ctx.ip.hostvm_enable;
+	dml_dispcfg->plane.HostVMMaxPageTableLevels = dml2->v20.dml_core_ctx.ip.hostvm_max_page_table_levels;
+	if (dml2->v20.dml_core_ctx.ip.hostvm_enable)
+		dml2->v20.dml_core_ctx.policy.AllowForPStateChangeOrStutterInVBlankFinal = dml_prefetch_support_uclk_fclk_and_stutter;
 
 	dml2_populate_pipe_to_plane_index_mapping(dml2, context);
 
diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml2_wrapper.h b/drivers/gpu/drm/amd/display/dc/dml2/dml2_wrapper.h
index 317f90776d97..fe15baa4bf09 100644
--- a/drivers/gpu/drm/amd/display/dc/dml2/dml2_wrapper.h
+++ b/drivers/gpu/drm/amd/display/dc/dml2/dml2_wrapper.h
@@ -139,6 +139,8 @@ struct dml2_soc_bbox_overrides {
 	double urgent_latency_us;
 	double sr_exit_latency_us;
 	double sr_enter_plus_exit_latency_us;
+	double sr_exit_z8_time_us;
+	double sr_enter_plus_exit_z8_time_us;
 	double dram_clock_change_latency_us;
 	double fclk_change_latency_us;
 	unsigned int dram_num_chan;
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.c
index 6a65af8c36b9..5f7f474ef51c 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.c
@@ -487,8 +487,7 @@ bool dcn32_set_mcm_luts(
 		if (plane_state->blend_tf->type == TF_TYPE_HWPWL)
 			lut_params = &plane_state->blend_tf->pwl;
 		else if (plane_state->blend_tf->type == TF_TYPE_DISTRIBUTED_POINTS) {
-			cm_helper_translate_curve_to_hw_format(plane_state->ctx,
-					plane_state->blend_tf,
+			cm3_helper_translate_curve_to_hw_format(plane_state->blend_tf,
 					&dpp_base->regamma_params, false);
 			lut_params = &dpp_base->regamma_params;
 		}
@@ -503,8 +502,7 @@ bool dcn32_set_mcm_luts(
 		else if (plane_state->in_shaper_func->type == TF_TYPE_DISTRIBUTED_POINTS) {
 			// TODO: dpp_base replace
 			ASSERT(false);
-			cm_helper_translate_curve_to_hw_format(plane_state->ctx,
-					plane_state->in_shaper_func,
+			cm3_helper_translate_curve_to_hw_format(plane_state->in_shaper_func,
 					&dpp_base->shaper_params, true);
 			lut_params = &dpp_base->shaper_params;
 		}
diff --git a/drivers/gpu/drm/amd/display/dc/link/link_detection.c b/drivers/gpu/drm/amd/display/dc/link/link_detection.c
index f2fe523f914f..24153b0df503 100644
--- a/drivers/gpu/drm/amd/display/dc/link/link_detection.c
+++ b/drivers/gpu/drm/amd/display/dc/link/link_detection.c
@@ -879,7 +879,7 @@ static bool detect_link_and_local_sink(struct dc_link *link,
 			(link->dpcd_sink_ext_caps.bits.oled == 1)) {
 			dpcd_set_source_specific_data(link);
 			msleep(post_oui_delay);
-			set_cached_brightness_aux(link);
+			set_default_brightness_aux(link);
 		}
 
 		return true;
diff --git a/drivers/gpu/drm/amd/display/dc/link/link_dpms.c b/drivers/gpu/drm/amd/display/dc/link/link_dpms.c
index 34a4a8c0e18c..f8e01ca09d96 100644
--- a/drivers/gpu/drm/amd/display/dc/link/link_dpms.c
+++ b/drivers/gpu/drm/amd/display/dc/link/link_dpms.c
@@ -2142,8 +2142,7 @@ static enum dc_status enable_link_dp(struct dc_state *state,
 	if (link->dpcd_sink_ext_caps.bits.oled == 1 ||
 		link->dpcd_sink_ext_caps.bits.sdr_aux_backlight_control == 1 ||
 		link->dpcd_sink_ext_caps.bits.hdr_aux_backlight_control == 1) {
-		set_cached_brightness_aux(link);
-
+		set_default_brightness_aux(link);
 		if (link->dpcd_sink_ext_caps.bits.oled == 1)
 			msleep(bl_oled_enable_delay);
 		edp_backlight_enable_aux(link, true);
diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_fixed_vs_pe_retimer.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_fixed_vs_pe_retimer.c
index fd8f6f198146..68096d12f52f 100644
--- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_fixed_vs_pe_retimer.c
+++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_fixed_vs_pe_retimer.c
@@ -115,7 +115,7 @@ static enum link_training_result perform_fixed_vs_pe_nontransparent_training_seq
 		lt_settings->cr_pattern_time = 16000;
 
 	/* Fixed VS/PE specific: Toggle link rate */
-	apply_toggle_rate_wa = (link->vendor_specific_lttpr_link_rate_wa == target_rate);
+	apply_toggle_rate_wa = ((link->vendor_specific_lttpr_link_rate_wa == target_rate) || (link->vendor_specific_lttpr_link_rate_wa == 0));
 	target_rate = get_dpcd_link_rate(&lt_settings->link_settings);
 	toggle_rate = (target_rate == 0x6) ? 0xA : 0x6;
 
@@ -271,7 +271,7 @@ enum link_training_result dp_perform_fixed_vs_pe_training_sequence_legacy(
 	/* Vendor specific: Toggle link rate */
 	toggle_rate = (rate == 0x6) ? 0xA : 0x6;
 
-	if (link->vendor_specific_lttpr_link_rate_wa == rate) {
+	if (link->vendor_specific_lttpr_link_rate_wa == rate || link->vendor_specific_lttpr_link_rate_wa == 0) {
 		core_link_write_dpcd(
 				link,
 				DP_LINK_BW_SET,
@@ -617,7 +617,7 @@ enum link_training_result dp_perform_fixed_vs_pe_training_sequence(
 	/* Vendor specific: Toggle link rate */
 	toggle_rate = (rate == 0x6) ? 0xA : 0x6;
 
-	if (link->vendor_specific_lttpr_link_rate_wa == rate) {
+	if (link->vendor_specific_lttpr_link_rate_wa == rate || link->vendor_specific_lttpr_link_rate_wa == 0) {
 		core_link_write_dpcd(
 				link,
 				DP_LINK_BW_SET,
diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.c
index e32a7974a4bc..996e4ee99023 100644
--- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.c
+++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.c
@@ -170,7 +170,6 @@ bool edp_set_backlight_level_nits(struct dc_link *link,
 	*(uint32_t *)&dpcd_backlight_set.backlight_level_millinits = backlight_millinits;
 	*(uint16_t *)&dpcd_backlight_set.backlight_transition_time_ms = (uint16_t)transition_time_in_ms;
 
-	link->backlight_settings.backlight_millinits = backlight_millinits;
 
 	if (!link->dpcd_caps.panel_luminance_control) {
 		if (core_link_write_dpcd(link, DP_SOURCE_BACKLIGHT_LEVEL,
@@ -288,9 +287,9 @@ bool set_default_brightness_aux(struct dc_link *link)
 	if (link && link->dpcd_sink_ext_caps.bits.oled == 1) {
 		if (!read_default_bl_aux(link, &default_backlight))
 			default_backlight = 150000;
-		// if < 1 nits or > 5000, it might be wrong readback
-		if (default_backlight < 1000 || default_backlight > 5000000)
-			default_backlight = 150000; //
+		// if > 5000, it might be wrong readback
+		if (default_backlight > 5000000)
+			default_backlight = 150000;
 
 		return edp_set_backlight_level_nits(link, true,
 				default_backlight, 0);
@@ -298,15 +297,6 @@ bool set_default_brightness_aux(struct dc_link *link)
 	return false;
 }
 
-bool set_cached_brightness_aux(struct dc_link *link)
-{
-	if (link->backlight_settings.backlight_millinits)
-		return edp_set_backlight_level_nits(link, true,
-						    link->backlight_settings.backlight_millinits, 0);
-	else
-		return set_default_brightness_aux(link);
-	return false;
-}
 bool edp_is_ilr_optimization_enabled(struct dc_link *link)
 {
 	if (link->dpcd_caps.edp_supported_link_rates_count == 0 || !link->panel_config.ilr.optimize_edp_link_rate)
diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.h b/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.h
index ebf7deb63d13..a034288ad75d 100644
--- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.h
+++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.h
@@ -30,7 +30,6 @@
 enum dp_panel_mode dp_get_panel_mode(struct dc_link *link);
 void dp_set_panel_mode(struct dc_link *link, enum dp_panel_mode panel_mode);
 bool set_default_brightness_aux(struct dc_link *link);
-bool set_cached_brightness_aux(struct dc_link *link);
 void edp_panel_backlight_power_on(struct dc_link *link, bool wait_for_hpd);
 int edp_get_backlight_level(const struct dc_link *link);
 bool edp_get_backlight_level_nits(struct dc_link *link,
diff --git a/drivers/gpu/drm/amd/display/dmub/src/dmub_srv.c b/drivers/gpu/drm/amd/display/dmub/src/dmub_srv.c
index 22fc4ba96def..38360adc53d9 100644
--- a/drivers/gpu/drm/amd/display/dmub/src/dmub_srv.c
+++ b/drivers/gpu/drm/amd/display/dmub/src/dmub_srv.c
@@ -1077,6 +1077,7 @@ enum dmub_status dmub_srv_wait_for_inbox0_ack(struct dmub_srv *dmub, uint32_t ti
 		ack = dmub->hw_funcs.read_inbox0_ack_register(dmub);
 		if (ack)
 			return DMUB_STATUS_OK;
+		udelay(1);
 	}
 	return DMUB_STATUS_TIMEOUT;
 }
diff --git a/drivers/gpu/drm/amd/include/asic_reg/gc/gc_11_0_0_offset.h b/drivers/gpu/drm/amd/include/asic_reg/gc/gc_11_0_0_offset.h
index c92c4b83253f..4bff1ef8a9a6 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/gc/gc_11_0_0_offset.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/gc/gc_11_0_0_offset.h
@@ -6369,6 +6369,8 @@
 #define regTCP_INVALIDATE_BASE_IDX                                                                      1
 #define regTCP_STATUS                                                                                   0x19a1
 #define regTCP_STATUS_BASE_IDX                                                                          1
+#define regTCP_CNTL                                                                                     0x19a2
+#define regTCP_CNTL_BASE_IDX                                                                            1
 #define regTCP_CNTL2                                                                                    0x19a3
 #define regTCP_CNTL2_BASE_IDX                                                                           1
 #define regTCP_DEBUG_INDEX                                                                              0x19a5
diff --git a/drivers/gpu/drm/amd/include/asic_reg/nbio/nbio_7_11_0_offset.h b/drivers/gpu/drm/amd/include/asic_reg/nbio/nbio_7_11_0_offset.h
index ff30f04be591..7ee3d291120d 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/nbio/nbio_7_11_0_offset.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/nbio/nbio_7_11_0_offset.h
@@ -781,6 +781,8 @@
 #define regBIF_BIF256_CI256_RC3X4_USB4_PCIE_CNTL2_BASE_IDX                                              5
 #define regBIF_BIF256_CI256_RC3X4_USB4_PCIE_TX_POWER_CTRL_1                                             0x420187
 #define regBIF_BIF256_CI256_RC3X4_USB4_PCIE_TX_POWER_CTRL_1_BASE_IDX                                    5
+#define regBIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3                                                  0x4201c6
+#define regBIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3_BASE_IDX                                         5
 
 
 // addressBlock: nbio_nbif0_bif_cfg_dev0_rc_bifcfgdecp
diff --git a/drivers/gpu/drm/amd/include/asic_reg/nbio/nbio_7_11_0_sh_mask.h b/drivers/gpu/drm/amd/include/asic_reg/nbio/nbio_7_11_0_sh_mask.h
index 7f131999a263..eb8c556d9c93 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/nbio/nbio_7_11_0_sh_mask.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/nbio/nbio_7_11_0_sh_mask.h
@@ -24646,6 +24646,35 @@
 //BIF_BIF256_CI256_RC3X4_USB4_PCIE_TX_POWER_CTRL_1
 #define BIF_BIF256_CI256_RC3X4_USB4_PCIE_TX_POWER_CTRL_1__MST_MEM_LS_EN_MASK                                  0x00000001L
 #define BIF_BIF256_CI256_RC3X4_USB4_PCIE_TX_POWER_CTRL_1__REPLAY_MEM_LS_EN_MASK                               0x00000008L
+//BIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3
+#define BIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3__CI_SWUS_MAX_PAYLOAD_SIZE_MODE__SHIFT                     0x8
+#define BIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3__CI_SWUS_PRIV_MAX_PAYLOAD_SIZE__SHIFT                     0x9
+#define BIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3__CI_10BIT_TAG_EN_OVERRIDE__SHIFT                          0xb
+#define BIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3__CI_SWUS_10BIT_TAG_EN_OVERRIDE__SHIFT                     0xd
+#define BIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3__MST_DROP_SYNC_FLOOD_EN__SHIFT                            0xf
+#define BIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3__CI_MAX_PAYLOAD_SIZE_MODE__SHIFT                          0x10
+#define BIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3__CI_PRIV_MAX_PAYLOAD_SIZE__SHIFT                          0x11
+#define BIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3__CI_MAX_READ_REQUEST_SIZE_MODE__SHIFT                     0x14
+#define BIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3__CI_PRIV_MAX_READ_REQUEST_SIZE__SHIFT                     0x15
+#define BIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3__CI_MAX_READ_SAFE_MODE__SHIFT                             0x18
+#define BIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3__CI_EXTENDED_TAG_EN_OVERRIDE__SHIFT                       0x19
+#define BIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3__CI_SWUS_MAX_READ_REQUEST_SIZE_MODE__SHIFT                0x1b
+#define BIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3__CI_SWUS_MAX_READ_REQUEST_SIZE_PRIV__SHIFT                0x1c
+#define BIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3__CI_SWUS_EXTENDED_TAG_EN_OVERRIDE__SHIFT                  0x1e
+#define BIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3__CI_SWUS_MAX_PAYLOAD_SIZE_MODE_MASK                       0x00000100L
+#define BIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3__CI_SWUS_PRIV_MAX_PAYLOAD_SIZE_MASK                       0x00000600L
+#define BIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3__CI_10BIT_TAG_EN_OVERRIDE_MASK                            0x00001800L
+#define BIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3__CI_SWUS_10BIT_TAG_EN_OVERRIDE_MASK                       0x00006000L
+#define BIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3__MST_DROP_SYNC_FLOOD_EN_MASK                              0x00008000L
+#define BIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3__CI_MAX_PAYLOAD_SIZE_MODE_MASK                            0x00010000L
+#define BIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3__CI_PRIV_MAX_PAYLOAD_SIZE_MASK                            0x000E0000L
+#define BIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3__CI_MAX_READ_REQUEST_SIZE_MODE_MASK                       0x00100000L
+#define BIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3__CI_PRIV_MAX_READ_REQUEST_SIZE_MASK                       0x00E00000L
+#define BIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3__CI_MAX_READ_SAFE_MODE_MASK                               0x01000000L
+#define BIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3__CI_EXTENDED_TAG_EN_OVERRIDE_MASK                         0x06000000L
+#define BIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3__CI_SWUS_MAX_READ_REQUEST_SIZE_MODE_MASK                  0x08000000L
+#define BIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3__CI_SWUS_MAX_READ_REQUEST_SIZE_PRIV_MASK                  0x30000000L
+#define BIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3__CI_SWUS_EXTENDED_TAG_EN_OVERRIDE_MASK                    0xC0000000L
 
 // addressBlock: nbio_nbif0_bif_cfg_dev0_rc_bifcfgdecp
 //BIF_CFG_DEV0_RC0_VENDOR_ID
diff --git a/drivers/gpu/drm/amd/include/kgd_pp_interface.h b/drivers/gpu/drm/amd/include/kgd_pp_interface.h
index cd3c40a86029..0d1209f2cf31 100644
--- a/drivers/gpu/drm/amd/include/kgd_pp_interface.h
+++ b/drivers/gpu/drm/amd/include/kgd_pp_interface.h
@@ -444,6 +444,7 @@ struct amd_pm_funcs {
 				   struct dpm_clocks *clock_table);
 	int (*get_smu_prv_buf_details)(void *handle, void **addr, size_t *size);
 	void (*pm_compute_clocks)(void *handle);
+	int (*notify_rlc_state)(void *handle, bool en);
 };
 
 struct metrics_table_header {
diff --git a/drivers/gpu/drm/amd/pm/amdgpu_dpm.c b/drivers/gpu/drm/amd/pm/amdgpu_dpm.c
index 08cb79401410..8ec11da0319f 100644
--- a/drivers/gpu/drm/amd/pm/amdgpu_dpm.c
+++ b/drivers/gpu/drm/amd/pm/amdgpu_dpm.c
@@ -181,6 +181,24 @@ int amdgpu_dpm_set_mp1_state(struct amdgpu_device *adev,
 	return ret;
 }
 
+int amdgpu_dpm_notify_rlc_state(struct amdgpu_device *adev, bool en)
+{
+	int ret = 0;
+	const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs;
+
+	if (pp_funcs && pp_funcs->notify_rlc_state) {
+		mutex_lock(&adev->pm.mutex);
+
+		ret = pp_funcs->notify_rlc_state(
+				adev->powerplay.pp_handle,
+				en);
+
+		mutex_unlock(&adev->pm.mutex);
+	}
+
+	return ret;
+}
+
 bool amdgpu_dpm_is_baco_supported(struct amdgpu_device *adev)
 {
 	const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs;
diff --git a/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h b/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h
index feccd2a7120d..482ea30147ab 100644
--- a/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h
+++ b/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h
@@ -415,6 +415,8 @@ int amdgpu_dpm_mode1_reset(struct amdgpu_device *adev);
 int amdgpu_dpm_set_mp1_state(struct amdgpu_device *adev,
 			     enum pp_mp1_state mp1_state);
 
+int amdgpu_dpm_notify_rlc_state(struct amdgpu_device *adev, bool en);
+
 int amdgpu_dpm_set_gfx_power_up_by_imu(struct amdgpu_device *adev);
 
 int amdgpu_dpm_baco_exit(struct amdgpu_device *adev);
diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
index 1ead323f1c78..e1a5ee911dbb 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
@@ -1710,6 +1710,16 @@ static int smu_disable_dpms(struct smu_context *smu)
 		}
 	}
 
+	/* Notify SMU RLC is going to be off, stop RLC and SMU interaction.
+	 * otherwise SMU will hang while interacting with RLC if RLC is halted
+	 * this is a WA for Vangogh asic which fix the SMU hang issue.
+	 */
+	ret = smu_notify_rlc_state(smu, false);
+	if (ret) {
+		dev_err(adev->dev, "Fail to notify rlc status!\n");
+		return ret;
+	}
+
 	if (amdgpu_ip_version(adev, GC_HWIP, 0) >= IP_VERSION(9, 4, 2) &&
 	    !((adev->flags & AMD_IS_APU) && adev->gfx.imu.funcs) &&
 	    !amdgpu_sriov_vf(adev) && adev->gfx.rlc.funcs->stop)
diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h b/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h
index 8def291b18bc..23fa71cafb14 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h
@@ -1360,6 +1360,11 @@ struct pptable_funcs {
 	 *                       management.
 	 */
 	int (*dpm_set_umsch_mm_enable)(struct smu_context *smu, bool enable);
+
+	/**
+	 * @notify_rlc_state: Notify RLC power state to SMU.
+	 */
+	int (*notify_rlc_state)(struct smu_context *smu, bool en);
 };
 
 typedef enum {
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c
index 762b31455a0b..2ff6deedef95 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c
@@ -2193,8 +2193,7 @@ static int vangogh_get_dpm_clock_table(struct smu_context *smu, struct dpm_clock
 	return 0;
 }
 
-
-static int vangogh_system_features_control(struct smu_context *smu, bool en)
+static int vangogh_notify_rlc_state(struct smu_context *smu, bool en)
 {
 	struct amdgpu_device *adev = smu->adev;
 	int ret = 0;
@@ -2523,7 +2522,7 @@ static const struct pptable_funcs vangogh_ppt_funcs = {
 	.print_clk_levels = vangogh_common_print_clk_levels,
 	.set_default_dpm_table = vangogh_set_default_dpm_tables,
 	.set_fine_grain_gfx_freq_parameters = vangogh_set_fine_grain_gfx_freq_parameters,
-	.system_features_control = vangogh_system_features_control,
+	.notify_rlc_state = vangogh_notify_rlc_state,
 	.feature_is_enabled = smu_cmn_feature_is_enabled,
 	.set_power_profile_mode = vangogh_set_power_profile_mode,
 	.get_power_profile_mode = vangogh_get_power_profile_mode,
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c
index 1a6675d70a4b..f1440869d1ce 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c
@@ -257,8 +257,11 @@ static int aldebaran_tables_init(struct smu_context *smu)
 	}
 
 	smu_table->ecc_table = kzalloc(tables[SMU_TABLE_ECCINFO].size, GFP_KERNEL);
-	if (!smu_table->ecc_table)
+	if (!smu_table->ecc_table) {
+		kfree(smu_table->metrics_table);
+		kfree(smu_table->gpu_metrics_table);
 		return -ENOMEM;
+	}
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu_internal.h b/drivers/gpu/drm/amd/pm/swsmu/smu_internal.h
index 80b3c3efc006..64766ac69c53 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu_internal.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu_internal.h
@@ -97,6 +97,7 @@
 #define smu_get_default_config_table_settings(smu, config_table)	smu_ppt_funcs(get_default_config_table_settings, -EOPNOTSUPP, smu, config_table)
 #define smu_set_config_table(smu, config_table)				smu_ppt_funcs(set_config_table, -EOPNOTSUPP, smu, config_table)
 #define smu_init_pptable_microcode(smu)					smu_ppt_funcs(init_pptable_microcode, 0, smu)
+#define smu_notify_rlc_state(smu, en)					smu_ppt_funcs(notify_rlc_state, 0, smu, en)
 
 #endif
 #endif
diff --git a/drivers/gpu/drm/drm_prime.c b/drivers/gpu/drm/drm_prime.c
index 63b709a67471..834a5e28abbe 100644
--- a/drivers/gpu/drm/drm_prime.c
+++ b/drivers/gpu/drm/drm_prime.c
@@ -278,7 +278,7 @@ void drm_gem_dmabuf_release(struct dma_buf *dma_buf)
 }
 EXPORT_SYMBOL(drm_gem_dmabuf_release);
 
-/*
+/**
  * drm_gem_prime_fd_to_handle - PRIME import function for GEM drivers
  * @dev: drm_device to import into
  * @file_priv: drm file-private structure
@@ -292,9 +292,9 @@ EXPORT_SYMBOL(drm_gem_dmabuf_release);
  *
  * Returns 0 on success or a negative error code on failure.
  */
-static int drm_gem_prime_fd_to_handle(struct drm_device *dev,
-				      struct drm_file *file_priv, int prime_fd,
-				      uint32_t *handle)
+int drm_gem_prime_fd_to_handle(struct drm_device *dev,
+			       struct drm_file *file_priv, int prime_fd,
+			       uint32_t *handle)
 {
 	struct dma_buf *dma_buf;
 	struct drm_gem_object *obj;
@@ -360,6 +360,7 @@ out_put:
 	dma_buf_put(dma_buf);
 	return ret;
 }
+EXPORT_SYMBOL(drm_gem_prime_fd_to_handle);
 
 int drm_prime_fd_to_handle_ioctl(struct drm_device *dev, void *data,
 				 struct drm_file *file_priv)
@@ -408,7 +409,7 @@ static struct dma_buf *export_and_register_object(struct drm_device *dev,
 	return dmabuf;
 }
 
-/*
+/**
  * drm_gem_prime_handle_to_fd - PRIME export function for GEM drivers
  * @dev: dev to export the buffer from
  * @file_priv: drm file-private structure
@@ -421,10 +422,10 @@ static struct dma_buf *export_and_register_object(struct drm_device *dev,
  * The actual exporting from GEM object to a dma-buf is done through the
  * &drm_gem_object_funcs.export callback.
  */
-static int drm_gem_prime_handle_to_fd(struct drm_device *dev,
-				      struct drm_file *file_priv, uint32_t handle,
-				      uint32_t flags,
-				      int *prime_fd)
+int drm_gem_prime_handle_to_fd(struct drm_device *dev,
+			       struct drm_file *file_priv, uint32_t handle,
+			       uint32_t flags,
+			       int *prime_fd)
 {
 	struct drm_gem_object *obj;
 	int ret = 0;
@@ -506,6 +507,7 @@ out_unlock:
 
 	return ret;
 }
+EXPORT_SYMBOL(drm_gem_prime_handle_to_fd);
 
 int drm_prime_handle_to_fd_ioctl(struct drm_device *dev, void *data,
 				 struct drm_file *file_priv)
@@ -864,9 +866,9 @@ EXPORT_SYMBOL(drm_prime_get_contiguous_size);
  * @obj: GEM object to export
  * @flags: flags like DRM_CLOEXEC and DRM_RDWR
  *
- * This is the implementation of the &drm_gem_object_funcs.export functions
- * for GEM drivers using the PRIME helpers. It is used as the default for
- * drivers that do not set their own.
+ * This is the implementation of the &drm_gem_object_funcs.export functions for GEM drivers
+ * using the PRIME helpers. It is used as the default in
+ * drm_gem_prime_handle_to_fd().
  */
 struct dma_buf *drm_gem_prime_export(struct drm_gem_object *obj,
 				     int flags)
@@ -962,9 +964,10 @@ EXPORT_SYMBOL(drm_gem_prime_import_dev);
  * @dev: drm_device to import into
  * @dma_buf: dma-buf object to import
  *
- * This is the implementation of the gem_prime_import functions for GEM
- * drivers using the PRIME helpers. It is the default for drivers that do
- * not set their own &drm_driver.gem_prime_import.
+ * This is the implementation of the gem_prime_import functions for GEM drivers
+ * using the PRIME helpers. Drivers can use this as their
+ * &drm_driver.gem_prime_import implementation. It is used as the default
+ * implementation in drm_gem_prime_fd_to_handle().
  *
  * Drivers must arrange to call drm_prime_gem_destroy() from their
  * &drm_gem_object_funcs.free hook when using this function.
diff --git a/include/drm/drm_prime.h b/include/drm/drm_prime.h
index a7abf9f3e697..2a1d01e5b56b 100644
--- a/include/drm/drm_prime.h
+++ b/include/drm/drm_prime.h
@@ -60,12 +60,19 @@ enum dma_data_direction;
 
 struct drm_device;
 struct drm_gem_object;
+struct drm_file;
 
 /* core prime functions */
 struct dma_buf *drm_gem_dmabuf_export(struct drm_device *dev,
 				      struct dma_buf_export_info *exp_info);
 void drm_gem_dmabuf_release(struct dma_buf *dma_buf);
 
+int drm_gem_prime_fd_to_handle(struct drm_device *dev,
+			       struct drm_file *file_priv, int prime_fd, uint32_t *handle);
+int drm_gem_prime_handle_to_fd(struct drm_device *dev,
+			       struct drm_file *file_priv, uint32_t handle, uint32_t flags,
+			       int *prime_fd);
+
 /* helper functions for exporting */
 int drm_gem_map_attach(struct dma_buf *dma_buf,
 		       struct dma_buf_attachment *attach);