Merge tag 'amd-drm-fixes-6.5-2023-06-30-1' of https://gitlab.freedesktop.org/agd5f/linux into drm-next

amd-drm-fixes-6.5-2023-06-30-1:

amdgpu:
- Misc cleanups
- GFX 9.4.3 fixes
- DEBUGFS build fix
- Fix LPDDR5 reporting
- ASPM fixes
- DCN 3.1.4 fixes
- DP MST fixes
- DCN 3.2.x fixes
- Display PSR TCON fixes
- SMU 13.x fixes
- RAS fixes
- Vega12/20 SMU fixes
- PSP flashing cleanup
- GFX9 MCBP fixes
- SR-IOV fixes
- GPUVM clear mappings fix for always valid BOs
- Add FAMS quirk for problematic monitor
- Fix possible UAF
- Better handle monentary temperature fluctuations
- SDMA 4.4.2 fixes
- Fencing fix

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

From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230630175757.8128-1-alexander.deucher@amd.com

103 files changed, 1201 insertions, 311 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index a84bd4a0c421..2f9c14aca73c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -286,6 +286,9 @@ extern int amdgpu_user_partt_mode;
 #define AMDGPU_SMARTSHIFT_MAX_BIAS (100)
 #define AMDGPU_SMARTSHIFT_MIN_BIAS (-100)
 
+/* Extra time delay(in ms) to eliminate the influence of temperature momentary fluctuation */
+#define AMDGPU_SWCTF_EXTRA_DELAY		50
+
 struct amdgpu_xcp_mgr;
 struct amdgpu_device;
 struct amdgpu_irq_src;
@@ -1277,9 +1280,10 @@ int emu_soc_asic_init(struct amdgpu_device *adev);
 
 #define amdgpu_inc_vram_lost(adev) atomic_inc(&((adev)->vram_lost_counter));
 
-#define for_each_inst(i, inst_mask)                                            \
-	for (i = ffs(inst_mask) - 1; inst_mask;                                \
-	     inst_mask &= ~(1U << i), i = ffs(inst_mask) - 1)
+#define BIT_MASK_UPPER(i) ((i) >= BITS_PER_LONG ? 0 : ~0UL << (i))
+#define for_each_inst(i, inst_mask)        \
+	for (i = ffs(inst_mask); i-- != 0; \
+	     i = ffs(inst_mask & BIT_MASK_UPPER(i + 1)))
 
 #define MIN(X, Y) ((X) < (Y) ? (X) : (Y))
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c
index 9ba4817a9148..f4e3c133a16c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c
@@ -1791,6 +1791,15 @@ const struct attribute_group amdgpu_vbios_version_attr_group = {
 	.attrs = amdgpu_vbios_version_attrs
 };
 
+int amdgpu_atombios_sysfs_init(struct amdgpu_device *adev)
+{
+	if (adev->mode_info.atom_context)
+		return devm_device_add_group(adev->dev,
+					     &amdgpu_vbios_version_attr_group);
+
+	return 0;
+}
+
 /**
  * amdgpu_atombios_fini - free the driver info and callbacks for atombios
  *
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.h
index 4153d520e2a3..b639a80ee3fc 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.h
@@ -217,5 +217,6 @@ int amdgpu_atombios_get_data_table(struct amdgpu_device *adev,
 
 void amdgpu_atombios_fini(struct amdgpu_device *adev);
 int amdgpu_atombios_init(struct amdgpu_device *adev);
+int amdgpu_atombios_sysfs_init(struct amdgpu_device *adev);
 
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c
index ef4b9a41f20a..0b7f4c4d58e5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c
@@ -327,10 +327,13 @@ amdgpu_atomfirmware_get_vram_info(struct amdgpu_device *adev,
 					mem_channel_number = igp_info->v11.umachannelnumber;
 					if (!mem_channel_number)
 						mem_channel_number = 1;
-					/* channel width is 64 */
-					if (vram_width)
-						*vram_width = mem_channel_number * 64;
 					mem_type = igp_info->v11.memorytype;
+					if (mem_type == LpDdr5MemType)
+						mem_channel_width = 32;
+					else
+						mem_channel_width = 64;
+					if (vram_width)
+						*vram_width = mem_channel_number * mem_channel_width;
 					if (vram_type)
 						*vram_type = convert_atom_mem_type_to_vram_type(adev, mem_type);
 					break;
@@ -345,10 +348,13 @@ amdgpu_atomfirmware_get_vram_info(struct amdgpu_device *adev,
 					mem_channel_number = igp_info->v21.umachannelnumber;
 					if (!mem_channel_number)
 						mem_channel_number = 1;
-					/* channel width is 64 */
-					if (vram_width)
-						*vram_width = mem_channel_number * 64;
 					mem_type = igp_info->v21.memorytype;
+					if (mem_type == LpDdr5MemType)
+						mem_channel_width = 32;
+					else
+						mem_channel_width = 64;
+					if (vram_width)
+						*vram_width = mem_channel_number * mem_channel_width;
 					if (vram_type)
 						*vram_type = convert_atom_mem_type_to_vram_type(adev, mem_type);
 					break;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index d9503882ea97..040f4cb6ab2d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -136,9 +136,6 @@ static int amdgpu_cs_p1_user_fence(struct amdgpu_cs_parser *p,
 	bo = amdgpu_bo_ref(gem_to_amdgpu_bo(gobj));
 	p->uf_entry.priority = 0;
 	p->uf_entry.tv.bo = &bo->tbo;
-	/* One for TTM and two for the CS job */
-	p->uf_entry.tv.num_shared = 3;
-
 	drm_gem_object_put(gobj);
 
 	size = amdgpu_bo_size(bo);
@@ -912,15 +909,19 @@ static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p,
 
 	mutex_lock(&p->bo_list->bo_list_mutex);
 
-	/* One for TTM and one for the CS job */
+	/* One for TTM and one for each CS job */
 	amdgpu_bo_list_for_each_entry(e, p->bo_list)
-		e->tv.num_shared = 2;
+		e->tv.num_shared = 1 + p->gang_size;
+	p->uf_entry.tv.num_shared = 1 + p->gang_size;
 
 	amdgpu_bo_list_get_list(p->bo_list, &p->validated);
 
 	INIT_LIST_HEAD(&duplicates);
 	amdgpu_vm_get_pd_bo(&fpriv->vm, &p->validated, &p->vm_pd);
 
+	/* Two for VM updates, one for TTM and one for each CS job */
+	p->vm_pd.tv.num_shared = 3 + p->gang_size;
+
 	if (p->uf_entry.tv.bo && !ttm_to_amdgpu_bo(p->uf_entry.tv.bo)->parent)
 		list_add(&p->uf_entry.tv.head, &p->validated);
 
@@ -1653,15 +1654,15 @@ static int amdgpu_cs_wait_all_fences(struct amdgpu_device *adev,
 			continue;
 
 		r = dma_fence_wait_timeout(fence, true, timeout);
+		if (r > 0 && fence->error)
+			r = fence->error;
+
 		dma_fence_put(fence);
 		if (r < 0)
 			return r;
 
 		if (r == 0)
 			break;
-
-		if (fence->error)
-			return fence->error;
 	}
 
 	memset(wait, 0, sizeof(*wait));
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index e25f085ee886..a92c6189b4b6 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -2552,7 +2552,7 @@ static int amdgpu_device_ip_init(struct amdgpu_device *adev)
 			adev->ip_blocks[i].status.hw = true;
 
 			/* right after GMC hw init, we create CSA */
-			if (amdgpu_mcbp) {
+			if (adev->gfx.mcbp) {
 				r = amdgpu_allocate_static_csa(adev, &adev->virt.csa_obj,
 							       AMDGPU_GEM_DOMAIN_VRAM |
 							       AMDGPU_GEM_DOMAIN_GTT,
@@ -3673,6 +3673,23 @@ static const struct attribute *amdgpu_dev_attributes[] = {
 	NULL
 };
 
+static void amdgpu_device_set_mcbp(struct amdgpu_device *adev)
+{
+	if (amdgpu_mcbp == 1)
+		adev->gfx.mcbp = true;
+
+	if ((adev->ip_versions[GC_HWIP][0] >= IP_VERSION(9, 0, 0)) &&
+	    (adev->ip_versions[GC_HWIP][0] < IP_VERSION(10, 0, 0)) &&
+	    adev->gfx.num_gfx_rings)
+		adev->gfx.mcbp = true;
+
+	if (amdgpu_sriov_vf(adev))
+		adev->gfx.mcbp = true;
+
+	if (adev->gfx.mcbp)
+		DRM_INFO("MCBP is enabled\n");
+}
+
 /**
  * amdgpu_device_init - initialize the driver
  *
@@ -3824,9 +3841,6 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 	DRM_INFO("register mmio base: 0x%08X\n", (uint32_t)adev->rmmio_base);
 	DRM_INFO("register mmio size: %u\n", (unsigned)adev->rmmio_size);
 
-	if (amdgpu_mcbp)
-		DRM_INFO("MCBP is enabled\n");
-
 	/*
 	 * Reset domain needs to be present early, before XGMI hive discovered
 	 * (if any) and intitialized to use reset sem and in_gpu reset flag
@@ -3852,6 +3866,8 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 	if (r)
 		return r;
 
+	amdgpu_device_set_mcbp(adev);
+
 	/* Get rid of things like offb */
 	r = drm_aperture_remove_conflicting_pci_framebuffers(adev->pdev, &amdgpu_kms_driver);
 	if (r)
@@ -4018,6 +4034,11 @@ fence_driver_init:
 	/* Get a log2 for easy divisions. */
 	adev->mm_stats.log2_max_MBps = ilog2(max(1u, max_MBps));
 
+	r = amdgpu_atombios_sysfs_init(adev);
+	if (r)
+		drm_err(&adev->ddev,
+			"registering atombios sysfs failed (%d).\n", r);
+
 	r = amdgpu_pm_sysfs_init(adev);
 	if (r)
 		DRM_ERROR("registering pm sysfs failed (%d).\n", r);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 3b711babd4e2..0593ef8fe0a6 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -180,7 +180,7 @@ uint amdgpu_dc_feature_mask = 2;
 uint amdgpu_dc_debug_mask;
 uint amdgpu_dc_visual_confirm;
 int amdgpu_async_gfx_ring = 1;
-int amdgpu_mcbp;
+int amdgpu_mcbp = -1;
 int amdgpu_discovery = -1;
 int amdgpu_mes;
 int amdgpu_mes_kiq;
@@ -634,10 +634,10 @@ module_param_named(async_gfx_ring, amdgpu_async_gfx_ring, int, 0444);
 
 /**
  * DOC: mcbp (int)
- * It is used to enable mid command buffer preemption. (0 = disabled (default), 1 = enabled)
+ * It is used to enable mid command buffer preemption. (0 = disabled, 1 = enabled, -1 auto (default))
  */
 MODULE_PARM_DESC(mcbp,
-	"Enable Mid-command buffer preemption (0 = disabled (default), 1 = enabled)");
+	"Enable Mid-command buffer preemption (0 = disabled, 1 = enabled), -1 = auto (default)");
 module_param_named(mcbp, amdgpu_mcbp, int, 0444);
 
 /**
@@ -2899,12 +2899,10 @@ static struct pci_error_handlers amdgpu_pci_err_handler = {
 
 extern const struct attribute_group amdgpu_vram_mgr_attr_group;
 extern const struct attribute_group amdgpu_gtt_mgr_attr_group;
-extern const struct attribute_group amdgpu_vbios_version_attr_group;
 
 static const struct attribute_group *amdgpu_sysfs_groups[] = {
 	&amdgpu_vram_mgr_attr_group,
 	&amdgpu_gtt_mgr_attr_group,
-	&amdgpu_vbios_version_attr_group,
 	NULL,
 };
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h
index ce0f7a8ad4b8..a4ff515ce896 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h
@@ -434,6 +434,7 @@ struct amdgpu_gfx {
 	uint16_t 			xcc_mask;
 	uint32_t			num_xcc_per_xcp;
 	struct mutex			partition_mutex;
+	bool				mcbp; /* mid command buffer preemption */
 };
 
 struct amdgpu_gfx_ras_reg_entry {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_jpeg.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_jpeg.c
index 3add4b4f0667..2ff2897fd1db 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_jpeg.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_jpeg.c
@@ -255,7 +255,8 @@ int amdgpu_jpeg_ras_late_init(struct amdgpu_device *adev, struct ras_common_if *
 
 	if (amdgpu_ras_is_supported(adev, ras_block->block)) {
 		for (i = 0; i < adev->jpeg.num_jpeg_inst; ++i) {
-			if (adev->jpeg.harvest_config & (1 << i))
+			if (adev->jpeg.harvest_config & (1 << i) ||
+			    !adev->jpeg.inst[i].ras_poison_irq.funcs)
 				continue;
 
 			r = amdgpu_irq_get(adev, &adev->jpeg.inst[i].ras_poison_irq, 0);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
index e3531aa3c8bd..cca5a495611f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
@@ -805,7 +805,7 @@ int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
 		dev_info->ids_flags = 0;
 		if (adev->flags & AMD_IS_APU)
 			dev_info->ids_flags |= AMDGPU_IDS_FLAGS_FUSION;
-		if (amdgpu_mcbp)
+		if (adev->gfx.mcbp)
 			dev_info->ids_flags |= AMDGPU_IDS_FLAGS_PREEMPTION;
 		if (amdgpu_is_tmz(adev))
 			dev_info->ids_flags |= AMDGPU_IDS_FLAGS_TMZ;
@@ -1247,7 +1247,7 @@ int amdgpu_driver_open_kms(struct drm_device *dev, struct drm_file *file_priv)
 		goto error_vm;
 	}
 
-	if (amdgpu_mcbp) {
+	if (adev->gfx.mcbp) {
 		uint64_t csa_addr = amdgpu_csa_vaddr(adev) & AMDGPU_GMC_HOLE_MASK;
 
 		r = amdgpu_map_static_csa(adev, &fpriv->vm, adev->virt.csa_obj,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
index e15c27e05564..6d676bdd1505 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
@@ -839,6 +839,7 @@ static bool psp_skip_tmr(struct psp_context *psp)
 	case IP_VERSION(11, 0, 9):
 	case IP_VERSION(11, 0, 7):
 	case IP_VERSION(13, 0, 2):
+	case IP_VERSION(13, 0, 6):
 	case IP_VERSION(13, 0, 10):
 		return true;
 	default:
@@ -2039,6 +2040,8 @@ static int psp_securedisplay_initialize(struct psp_context *psp)
 		psp_securedisplay_parse_resp_status(psp, securedisplay_cmd->status);
 		dev_err(psp->adev->dev, "SECUREDISPLAY: query securedisplay TA failed. ret 0x%x\n",
 			securedisplay_cmd->securedisplay_out_message.query_ta.query_cmd_ret);
+		/* don't try again */
+		psp->securedisplay_context.context.bin_desc.size_bytes = 0;
 	}
 
 	return 0;
@@ -3703,7 +3706,6 @@ static DEVICE_ATTR(psp_vbflash_status, 0440, amdgpu_psp_vbflash_status, NULL);
 int amdgpu_psp_sysfs_init(struct amdgpu_device *adev)
 {
 	int ret = 0;
-	struct psp_context *psp = &adev->psp;
 
 	if (amdgpu_sriov_vf(adev))
 		return -EINVAL;
@@ -3712,10 +3714,6 @@ int amdgpu_psp_sysfs_init(struct amdgpu_device *adev)
 	case IP_VERSION(13, 0, 0):
 	case IP_VERSION(13, 0, 7):
 	case IP_VERSION(13, 0, 10):
-		if (!psp->adev) {
-			psp->adev = adev;
-			psp_v13_0_set_psp_funcs(psp);
-		}
 		ret = sysfs_create_bin_file(&adev->dev->kobj, &psp_vbflash_bin_attr);
 		if (ret)
 			dev_err(adev->dev, "Failed to create device file psp_vbflash");
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_rap.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_rap.c
index 12010c988c8b..123bcf5c2bb1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_rap.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_rap.c
@@ -116,7 +116,6 @@ static const struct file_operations amdgpu_rap_debugfs_ops = {
 
 void amdgpu_rap_debugfs_init(struct amdgpu_device *adev)
 {
-#if defined(CONFIG_DEBUG_FS)
 	struct drm_minor *minor = adev_to_drm(adev)->primary;
 
 	if (!adev->psp.rap_context.context.initialized)
@@ -124,5 +123,4 @@ void amdgpu_rap_debugfs_init(struct amdgpu_device *adev)
 
 	debugfs_create_file("rap_test", S_IWUSR, minor->debugfs_root,
 				adev, &amdgpu_rap_debugfs_ops);
-#endif
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index 4769a18304d7..8aaa427f8c0f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -2065,6 +2065,14 @@ static void amdgpu_ras_do_recovery(struct work_struct *work)
 				ras->gpu_reset_flags &= ~AMDGPU_RAS_GPU_RESET_MODE2_RESET;
 				reset_context.method = AMD_RESET_METHOD_MODE2;
 			}
+
+			/* Fatal error occurs in poison mode, mode1 reset is used to
+			 * recover gpu.
+			 */
+			if (ras->gpu_reset_flags & AMDGPU_RAS_GPU_RESET_MODE1_RESET) {
+				ras->gpu_reset_flags &= ~AMDGPU_RAS_GPU_RESET_MODE1_RESET;
+				set_bit(AMDGPU_NEED_FULL_RESET, &reset_context.flags);
+			}
 		}
 
 		amdgpu_device_gpu_recover(ras->adev, NULL, &reset_context);
@@ -2955,9 +2963,12 @@ void amdgpu_ras_global_ras_isr(struct amdgpu_device *adev)
 		return;
 
 	if (atomic_cmpxchg(&amdgpu_ras_in_intr, 0, 1) == 0) {
+		struct amdgpu_ras *ras = amdgpu_ras_get_context(adev);
+
 		dev_info(adev->dev, "uncorrectable hardware error"
 			"(ERREVENT_ATHUB_INTERRUPT) detected!\n");
 
+		ras->gpu_reset_flags |= AMDGPU_RAS_GPU_RESET_MODE1_RESET;
 		amdgpu_ras_reset_gpu(adev);
 	}
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
index 46bf1889a9d7..ffb49b2d533a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
@@ -340,6 +340,7 @@ enum amdgpu_ras_ret {
 #define AMDGPU_RAS_ERR_ADDRESS_VALID	(1 << 2)
 
 #define AMDGPU_RAS_GPU_RESET_MODE2_RESET  (0x1 << 0)
+#define AMDGPU_RAS_GPU_RESET_MODE1_RESET  (0x1 << 1)
 
 struct amdgpu_ras_err_status_reg_entry {
 	uint32_t hwip;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring_mux.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring_mux.c
index 73516abef662..b779ee4bbaa7 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring_mux.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring_mux.c
@@ -423,6 +423,9 @@ void amdgpu_sw_ring_ib_mark_offset(struct amdgpu_ring *ring, enum amdgpu_ring_mu
 	struct amdgpu_ring_mux *mux = &adev->gfx.muxer;
 	unsigned offset;
 
+	if (ring->hw_prio > AMDGPU_RING_PRIO_DEFAULT)
+		return;
+
 	offset = ring->wptr & ring->buf_mask;
 
 	amdgpu_ring_mux_ib_mark_offset(mux, ring, offset, type);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c
index 78ec3420ef85..dacf281d2b21 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c
@@ -72,7 +72,7 @@ uint64_t amdgpu_sdma_get_csa_mc_addr(struct amdgpu_ring *ring,
 	int r;
 
 	/* don't enable OS preemption on SDMA under SRIOV */
-	if (amdgpu_sriov_vf(adev) || vmid == 0 || !amdgpu_mcbp)
+	if (amdgpu_sriov_vf(adev) || vmid == 0 || !adev->gfx.mcbp)
 		return 0;
 
 	if (ring->is_mes_queue) {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
index acbef1a24b9c..ae455aab5d29 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
@@ -1198,7 +1198,8 @@ int amdgpu_vcn_ras_late_init(struct amdgpu_device *adev, struct ras_common_if *r
 
 	if (amdgpu_ras_is_supported(adev, ras_block->block)) {
 		for (i = 0; i < adev->vcn.num_vcn_inst; i++) {
-			if (adev->vcn.harvest_config & (1 << i))
+			if (adev->vcn.harvest_config & (1 << i) ||
+			    !adev->vcn.inst[i].ras_poison_irq.funcs)
 				continue;
 
 			r = amdgpu_irq_get(adev, &adev->vcn.inst[i].ras_poison_irq, 0);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
index 25b4d7f0bd35..41aa853a07d2 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
@@ -66,9 +66,6 @@ void amdgpu_virt_init_setting(struct amdgpu_device *adev)
 	adev->cg_flags = 0;
 	adev->pg_flags = 0;
 
-	/* enable mcbp for sriov */
-	amdgpu_mcbp = 1;
-
 	/* Reduce kcq number to 2 to reduce latency */
 	if (amdgpu_num_kcq == -1)
 		amdgpu_num_kcq = 2;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index 143d11afe0e5..291977b93b1d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -1771,18 +1771,30 @@ int amdgpu_vm_bo_clear_mappings(struct amdgpu_device *adev,
 
 	/* Insert partial mapping before the range */
 	if (!list_empty(&before->list)) {
+		struct amdgpu_bo *bo = before->bo_va->base.bo;
+
 		amdgpu_vm_it_insert(before, &vm->va);
 		if (before->flags & AMDGPU_PTE_PRT)
 			amdgpu_vm_prt_get(adev);
+
+		if (bo && bo->tbo.base.resv == vm->root.bo->tbo.base.resv &&
+		    !before->bo_va->base.moved)
+			amdgpu_vm_bo_moved(&before->bo_va->base);
 	} else {
 		kfree(before);
 	}
 
 	/* Insert partial mapping after the range */
 	if (!list_empty(&after->list)) {
+		struct amdgpu_bo *bo = after->bo_va->base.bo;
+
 		amdgpu_vm_it_insert(after, &vm->va);
 		if (after->flags & AMDGPU_PTE_PRT)
 			amdgpu_vm_prt_get(adev);
+
+		if (bo && bo->tbo.base.resv == vm->root.bo->tbo.base.resv &&
+		    !after->bo_va->base.moved)
+			amdgpu_vm_bo_moved(&after->bo_va->base);
 	} else {
 		kfree(after);
 	}
@@ -2233,16 +2245,16 @@ int amdgpu_vm_make_compute(struct amdgpu_device *adev, struct amdgpu_vm *vm)
 	if (r)
 		return r;
 
-	/* Sanity checks */
-	if (!amdgpu_vm_pt_is_root_clean(adev, vm)) {
-		r = -EINVAL;
-		goto unreserve_bo;
-	}
-
 	/* Check if PD needs to be reinitialized and do it before
 	 * changing any other state, in case it fails.
 	 */
 	if (pte_support_ats != vm->pte_support_ats) {
+		/* Sanity checks */
+		if (!amdgpu_vm_pt_is_root_clean(adev, vm)) {
+			r = -EINVAL;
+			goto unreserve_bo;
+		}
+
 		vm->pte_support_ats = pte_support_ats;
 		r = amdgpu_vm_pt_clear(adev, vm, to_amdgpu_bo_vm(vm->root.bo),
 				       false);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_xcp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_xcp.c
index d733fa6e7477..d175e862f222 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_xcp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_xcp.c
@@ -132,6 +132,9 @@ int amdgpu_xcp_init(struct amdgpu_xcp_mgr *xcp_mgr, int num_xcps, int mode)
 	for (i = 0; i < MAX_XCP; ++i)
 		xcp_mgr->xcp[i].valid = false;
 
+	/* This is needed for figuring out memory id of xcp */
+	xcp_mgr->num_xcp_per_mem_partition = num_xcps / xcp_mgr->adev->gmc.num_mem_partitions;
+
 	for (i = 0; i < num_xcps; ++i) {
 		for (j = AMDGPU_XCP_GFXHUB; j < AMDGPU_XCP_MAX_BLOCKS; ++j) {
 			ret = xcp_mgr->funcs->get_ip_details(xcp_mgr, i, j,
@@ -157,7 +160,6 @@ int amdgpu_xcp_init(struct amdgpu_xcp_mgr *xcp_mgr, int num_xcps, int mode)
 	xcp_mgr->num_xcps = num_xcps;
 	amdgpu_xcp_update_partition_sched_list(adev);
 
-	xcp_mgr->num_xcp_per_mem_partition = num_xcps / xcp_mgr->adev->gmc.num_mem_partitions;
 	return 0;
 }
 
@@ -232,7 +234,10 @@ static int amdgpu_xcp_dev_alloc(struct amdgpu_device *adev)
 
 	ddev = adev_to_drm(adev);
 
-	for (i = 0; i < MAX_XCP; i++) {
+	/* xcp #0 shares drm device setting with adev */
+	adev->xcp_mgr->xcp->ddev = ddev;
+
+	for (i = 1; i < MAX_XCP; i++) {
 		ret = amdgpu_xcp_drm_dev_alloc(&p_ddev);
 		if (ret)
 			return ret;
@@ -322,7 +327,7 @@ int amdgpu_xcp_dev_register(struct amdgpu_device *adev,
 	if (!adev->xcp_mgr)
 		return 0;
 
-	for (i = 0; i < MAX_XCP; i++) {
+	for (i = 1; i < MAX_XCP; i++) {
 		ret = drm_dev_register(adev->xcp_mgr->xcp[i].ddev, ent->driver_data);
 		if (ret)
 			return ret;
@@ -339,7 +344,7 @@ void amdgpu_xcp_dev_unplug(struct amdgpu_device *adev)
 	if (!adev->xcp_mgr)
 		return;
 
-	for (i = 0; i < MAX_XCP; i++) {
+	for (i = 1; i < MAX_XCP; i++) {
 		p_ddev = adev->xcp_mgr->xcp[i].ddev;
 		drm_dev_unplug(p_ddev);
 		p_ddev->render->dev = adev->xcp_mgr->xcp[i].rdev;
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
index be984f8c71c7..44af8022b89f 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
@@ -8307,7 +8307,7 @@ static void gfx_v10_0_ring_emit_ib_gfx(struct amdgpu_ring *ring,
 
 	control |= ib->length_dw | (vmid << 24);
 
-	if (amdgpu_mcbp && (ib->flags & AMDGPU_IB_FLAG_PREEMPT)) {
+	if (ring->adev->gfx.mcbp && (ib->flags & AMDGPU_IB_FLAG_PREEMPT)) {
 		control |= INDIRECT_BUFFER_PRE_ENB(1);
 
 		if (flags & AMDGPU_IB_PREEMPTED)
@@ -8482,7 +8482,7 @@ static void gfx_v10_0_ring_emit_cntxcntl(struct amdgpu_ring *ring,
 {
 	uint32_t dw2 = 0;
 
-	if (amdgpu_mcbp)
+	if (ring->adev->gfx.mcbp)
 		gfx_v10_0_ring_emit_ce_meta(ring,
 				    (!amdgpu_sriov_vf(ring->adev) && flags & AMDGPU_IB_PREEMPTED) ? true : false);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
index 690e121d9dda..3a7af59e83ca 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
@@ -5311,7 +5311,7 @@ static void gfx_v11_0_ring_emit_ib_gfx(struct amdgpu_ring *ring,
 
 	control |= ib->length_dw | (vmid << 24);
 
-	if (amdgpu_mcbp && (ib->flags & AMDGPU_IB_FLAG_PREEMPT)) {
+	if (ring->adev->gfx.mcbp && (ib->flags & AMDGPU_IB_FLAG_PREEMPT)) {
 		control |= INDIRECT_BUFFER_PRE_ENB(1);
 
 		if (flags & AMDGPU_IB_PREEMPTED)
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 c1ee54d4c3d3..9e3b835bdbb2 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c
@@ -623,12 +623,28 @@ static void gfx_v9_4_3_select_me_pipe_q(struct amdgpu_device *adev,
 static int gfx_v9_4_3_switch_compute_partition(struct amdgpu_device *adev,
 						int num_xccs_per_xcp)
 {
-	int ret;
-
-	ret = psp_spatial_partition(&adev->psp, NUM_XCC(adev->gfx.xcc_mask) /
-							num_xccs_per_xcp);
-	if (ret)
-		return ret;
+	int ret, i, num_xcc;
+	u32 tmp = 0;
+
+	if (adev->psp.funcs) {
+		ret = psp_spatial_partition(&adev->psp,
+					    NUM_XCC(adev->gfx.xcc_mask) /
+						    num_xccs_per_xcp);
+		if (ret)
+			return ret;
+	} else {
+		num_xcc = NUM_XCC(adev->gfx.xcc_mask);
+
+		for (i = 0; i < num_xcc; i++) {
+			tmp = REG_SET_FIELD(tmp, CP_HYP_XCP_CTL, NUM_XCC_IN_XCP,
+					    num_xccs_per_xcp);
+			tmp = REG_SET_FIELD(tmp, CP_HYP_XCP_CTL, VIRTUAL_XCC_ID,
+					    i % num_xccs_per_xcp);
+			WREG32_SOC15(GC, GET_INST(GC, i), regCP_HYP_XCP_CTL,
+				     tmp);
+		}
+		ret = 0;
+	}
 
 	adev->gfx.num_xcc_per_xcp = num_xccs_per_xcp;
 
@@ -1762,6 +1778,8 @@ static int gfx_v9_4_3_xcc_kiq_init_queue(struct amdgpu_ring *ring, int xcc_id)
 		((struct v9_mqd_allocation *)mqd)->dynamic_cu_mask = 0xFFFFFFFF;
 		((struct v9_mqd_allocation *)mqd)->dynamic_rb_mask = 0xFFFFFFFF;
 		mutex_lock(&adev->srbm_mutex);
+		if (amdgpu_sriov_vf(adev) && adev->in_suspend)
+			amdgpu_ring_clear_ring(ring);
 		soc15_grbm_select(adev, ring->me, ring->pipe, ring->queue, 0, GET_INST(GC, xcc_id));
 		gfx_v9_4_3_xcc_mqd_init(ring, xcc_id);
 		gfx_v9_4_3_xcc_kiq_init_register(ring, xcc_id);
@@ -1960,6 +1978,16 @@ static void gfx_v9_4_3_xcc_fini(struct amdgpu_device *adev, int xcc_id)
 	if (amdgpu_gfx_disable_kcq(adev, xcc_id))
 		DRM_ERROR("XCD %d KCQ disable failed\n", xcc_id);
 
+	if (amdgpu_sriov_vf(adev)) {
+		/* must disable polling for SRIOV when hw finished, otherwise
+		 * CPC engine may still keep fetching WB address which is already
+		 * invalid after sw finished and trigger DMAR reading error in
+		 * hypervisor side.
+		 */
+		WREG32_FIELD15_PREREG(GC, GET_INST(GC, xcc_id), CP_PQ_WPTR_POLL_CNTL, EN, 0);
+		return;
+	}
+
 	/* Use deinitialize sequence from CAIL when unbinding device
 	 * from driver, otherwise KIQ is hanging when binding back
 	 */
@@ -1984,7 +2012,8 @@ static int gfx_v9_4_3_hw_init(void *handle)
 	int r;
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
-	gfx_v9_4_3_init_golden_registers(adev);
+	if (!amdgpu_sriov_vf(adev))
+		gfx_v9_4_3_init_golden_registers(adev);
 
 	gfx_v9_4_3_constants_init(adev);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v2_3.c b/drivers/gpu/drm/amd/amdgpu/nbio_v2_3.c
index aa761ff3a5fa..4038455d7998 100644
--- a/drivers/gpu/drm/amd/amdgpu/nbio_v2_3.c
+++ b/drivers/gpu/drm/amd/amdgpu/nbio_v2_3.c
@@ -345,8 +345,8 @@ static void nbio_v2_3_init_registers(struct amdgpu_device *adev)
 }
 
 #define NAVI10_PCIE__LC_L0S_INACTIVITY_DEFAULT		0x00000000 // off by default, no gains over L1
-#define NAVI10_PCIE__LC_L1_INACTIVITY_DEFAULT		0x00000009 // 1=1us, 9=1ms
-#define NAVI10_PCIE__LC_L1_INACTIVITY_TBT_DEFAULT	0x0000000E // 4ms
+#define NAVI10_PCIE__LC_L1_INACTIVITY_DEFAULT		0x0000000A // 1=1us, 9=1ms, 10=4ms
+#define NAVI10_PCIE__LC_L1_INACTIVITY_TBT_DEFAULT	0x0000000E // 400ms
 
 static void nbio_v2_3_enable_aspm(struct amdgpu_device *adev,
 				  bool enable)
@@ -479,9 +479,12 @@ static void nbio_v2_3_program_aspm(struct amdgpu_device *adev)
 		WREG32_SOC15(NBIO, 0, mmRCC_BIF_STRAP5, data);
 
 	def = data = RREG32_PCIE(smnPCIE_LC_CNTL);
-	data &= ~PCIE_LC_CNTL__LC_L0S_INACTIVITY_MASK;
-	data |= 0x9 << PCIE_LC_CNTL__LC_L1_INACTIVITY__SHIFT;
-	data |= 0x1 << PCIE_LC_CNTL__LC_PMI_TO_L1_DIS__SHIFT;
+	data |= NAVI10_PCIE__LC_L0S_INACTIVITY_DEFAULT << PCIE_LC_CNTL__LC_L0S_INACTIVITY__SHIFT;
+	if (pci_is_thunderbolt_attached(adev->pdev))
+		data |= NAVI10_PCIE__LC_L1_INACTIVITY_TBT_DEFAULT  << PCIE_LC_CNTL__LC_L1_INACTIVITY__SHIFT;
+	else
+		data |= NAVI10_PCIE__LC_L1_INACTIVITY_DEFAULT << PCIE_LC_CNTL__LC_L1_INACTIVITY__SHIFT;
+	data &= ~PCIE_LC_CNTL__LC_PMI_TO_L1_DIS_MASK;
 	if (def != data)
 		WREG32_PCIE(smnPCIE_LC_CNTL, data);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c
index ea5e12390d18..f413898dda37 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c
@@ -578,6 +578,9 @@ static void sdma_v4_4_2_inst_enable(struct amdgpu_device *adev, bool enable,
 			return;
 	}
 
+	if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP)
+		return;
+
 	for_each_inst(i, inst_mask) {
 		f32_cntl = RREG32_SDMA(i, regSDMA_F32_CNTL);
 		f32_cntl = REG_SET_FIELD(f32_cntl, SDMA_F32_CNTL, HALT, enable ? 0 : 1);
@@ -899,15 +902,12 @@ static int sdma_v4_4_2_inst_start(struct amdgpu_device *adev,
 		WREG32_SDMA(i, regSDMA_CNTL, temp);
 
 		if (!amdgpu_sriov_vf(adev)) {
-			ring = &adev->sdma.instance[i].ring;
-			adev->nbio.funcs->sdma_doorbell_range(adev, i,
-				ring->use_doorbell, ring->doorbell_index,
-				adev->doorbell_index.sdma_doorbell_range);
-
-			/* unhalt engine */
-			temp = RREG32_SDMA(i, regSDMA_F32_CNTL);
-			temp = REG_SET_FIELD(temp, SDMA_F32_CNTL, HALT, 0);
-			WREG32_SDMA(i, regSDMA_F32_CNTL, temp);
+			if (adev->firmware.load_type != AMDGPU_FW_LOAD_PSP) {
+				/* unhalt engine */
+				temp = RREG32_SDMA(i, regSDMA_F32_CNTL);
+				temp = REG_SET_FIELD(temp, SDMA_F32_CNTL, HALT, 0);
+				WREG32_SDMA(i, regSDMA_F32_CNTL, temp);
+			}
 		}
 	}
 
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c
index b48bb5212488..259795098173 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c
@@ -1424,8 +1424,10 @@ static int vcn_v4_0_start_sriov(struct amdgpu_device *adev)
  */
 static void vcn_v4_0_stop_dpg_mode(struct amdgpu_device *adev, int inst_idx)
 {
+	struct dpg_pause_state state = {.fw_based = VCN_DPG_STATE__UNPAUSE};
 	uint32_t tmp;
 
+	vcn_v4_0_pause_dpg_mode(adev, inst_idx, &state);
 	/* Wait for power status to be 1 */
 	SOC15_WAIT_ON_RREG(VCN, inst_idx, regUVD_POWER_STATUS, 1,
 		UVD_POWER_STATUS__UVD_POWER_STATUS_MASK);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
index 9d4abfd8b55e..0b3dc754e06b 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
@@ -138,9 +138,12 @@ static void kfd_device_info_set_event_interrupt_class(struct kfd_dev *kfd)
 	case IP_VERSION(9, 4, 0): /* VEGA20 */
 	case IP_VERSION(9, 4, 1): /* ARCTURUS */
 	case IP_VERSION(9, 4, 2): /* ALDEBARAN */
-	case IP_VERSION(9, 4, 3): /* GC 9.4.3 */
 		kfd->device_info.event_interrupt_class = &event_interrupt_class_v9;
 		break;
+	case IP_VERSION(9, 4, 3): /* GC 9.4.3 */
+		kfd->device_info.event_interrupt_class =
+						&event_interrupt_class_v9_4_3;
+		break;
 	case IP_VERSION(10, 3, 1): /* VANGOGH */
 	case IP_VERSION(10, 3, 3): /* YELLOW_CARP */
 	case IP_VERSION(10, 3, 6): /* GC 10.3.6 */
@@ -518,6 +521,7 @@ static int kfd_gws_init(struct kfd_node *node)
 			&& kfd->mec2_fw_version >= 0x30)   ||
 		(KFD_GC_VERSION(node) == IP_VERSION(9, 4, 2)
 			&& kfd->mec2_fw_version >= 0x28) ||
+		(KFD_GC_VERSION(node) == IP_VERSION(9, 4, 3)) ||
 		(KFD_GC_VERSION(node) >= IP_VERSION(10, 3, 0)
 			&& KFD_GC_VERSION(node) < IP_VERSION(11, 0, 0)
 			&& kfd->mec2_fw_version >= 0x6b))))
@@ -598,6 +602,41 @@ static void kfd_cleanup_nodes(struct kfd_dev *kfd, unsigned int num_nodes)
 	}
 }
 
+static void kfd_setup_interrupt_bitmap(struct kfd_node *node,
+				       unsigned int kfd_node_idx)
+{
+	struct amdgpu_device *adev = node->adev;
+	uint32_t xcc_mask = node->xcc_mask;
+	uint32_t xcc, mapped_xcc;
+	/*
+	 * Interrupt bitmap is setup for processing interrupts from
+	 * different XCDs and AIDs.
+	 * Interrupt bitmap is defined as follows:
+	 * 1. Bits 0-15 - correspond to the NodeId field.
+	 *    Each bit corresponds to NodeId number. For example, if
+	 *    a KFD node has interrupt bitmap set to 0x7, then this
+	 *    KFD node will process interrupts with NodeId = 0, 1 and 2
+	 *    in the IH cookie.
+	 * 2. Bits 16-31 - unused.
+	 *
+	 * Please note that the kfd_node_idx argument passed to this
+	 * function is not related to NodeId field received in the
+	 * IH cookie.
+	 *
+	 * In CPX mode, a KFD node will process an interrupt if:
+	 * - the Node Id matches the corresponding bit set in
+	 *   Bits 0-15.
+	 * - AND VMID reported in the interrupt lies within the
+	 *   VMID range of the node.
+	 */
+	for_each_inst(xcc, xcc_mask) {
+		mapped_xcc = GET_INST(GC, xcc);
+		node->interrupt_bitmap |= (mapped_xcc % 2 ? 5 : 3) << (4 * (mapped_xcc / 2));
+	}
+	dev_info(kfd_device, "Node: %d, interrupt_bitmap: %x\n", kfd_node_idx,
+							node->interrupt_bitmap);
+}
+
 bool kgd2kfd_device_init(struct kfd_dev *kfd,
 			 const struct kgd2kfd_shared_resources *gpu_resources)
 {
@@ -797,6 +836,9 @@ bool kgd2kfd_device_init(struct kfd_dev *kfd,
 		amdgpu_amdkfd_get_local_mem_info(kfd->adev,
 					&node->local_mem_info, node->xcp);
 
+		if (KFD_GC_VERSION(kfd) == IP_VERSION(9, 4, 3))
+			kfd_setup_interrupt_bitmap(node, i);
+
 		/* Initialize the KFD node */
 		if (kfd_init_node(node)) {
 			dev_err(kfd_device, "Error initializing KFD node\n");
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c
index d5c9f30552e3..f0731a6a5306 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c
@@ -446,7 +446,36 @@ static void event_interrupt_wq_v9(struct kfd_node *dev,
 	}
 }
 
+static bool event_interrupt_isr_v9_4_3(struct kfd_node *node,
+				const uint32_t *ih_ring_entry,
+				uint32_t *patched_ihre,
+				bool *patched_flag)
+{
+	uint16_t node_id, vmid;
+
+	/*
+	 * For GFX 9.4.3, process the interrupt if:
+	 * - NodeID field in IH entry matches the corresponding bit
+	 *   set in interrupt_bitmap Bits 0-15.
+	 *   OR
+	 * - If partition mode is CPX and interrupt came from
+	 *   Node_id 0,4,8,12, then check if the Bit (16 + client id)
+	 *   is set in interrupt bitmap Bits 16-31.
+	 */
+	node_id = SOC15_NODEID_FROM_IH_ENTRY(ih_ring_entry);
+	vmid = SOC15_VMID_FROM_IH_ENTRY(ih_ring_entry);
+	if (kfd_irq_is_from_node(node, node_id, vmid))
+		return event_interrupt_isr_v9(node, ih_ring_entry,
+					patched_ihre, patched_flag);
+	return false;
+}
+
 const struct kfd_event_interrupt_class event_interrupt_class_v9 = {
 	.interrupt_isr = event_interrupt_isr_v9,
 	.interrupt_wq = event_interrupt_wq_v9,
 };
+
+const struct kfd_event_interrupt_class event_interrupt_class_v9_4_3 = {
+	.interrupt_isr = event_interrupt_isr_v9_4_3,
+	.interrupt_wq = event_interrupt_wq_v9,
+};
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
index 7364a5d77c6e..d4c9ee3f9953 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
@@ -1444,6 +1444,7 @@ uint64_t kfd_get_number_elems(struct kfd_dev *kfd);
 /* Events */
 extern const struct kfd_event_interrupt_class event_interrupt_class_cik;
 extern const struct kfd_event_interrupt_class event_interrupt_class_v9;
+extern const struct kfd_event_interrupt_class event_interrupt_class_v9_4_3;
 extern const struct kfd_event_interrupt_class event_interrupt_class_v10;
 extern const struct kfd_event_interrupt_class event_interrupt_class_v11;
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
index 3d3611705d41..a844e68211ac 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
@@ -2142,6 +2142,7 @@ void kfd_flush_tlb(struct kfd_process_device *pdd, enum TLB_FLUSH_TYPE type)
 int kfd_process_drain_interrupts(struct kfd_process_device *pdd)
 {
 	uint32_t irq_drain_fence[8];
+	uint8_t node_id = 0;
 	int r = 0;
 
 	if (!KFD_IS_SOC15(pdd->dev))
@@ -2154,6 +2155,14 @@ int kfd_process_drain_interrupts(struct kfd_process_device *pdd)
 							KFD_IRQ_FENCE_CLIENTID;
 	irq_drain_fence[3] = pdd->process->pasid;
 
+	/*
+	 * For GFX 9.4.3, send the NodeId also in IH cookie DW[3]
+	 */
+	if (KFD_GC_VERSION(pdd->dev->kfd) == IP_VERSION(9, 4, 3)) {
+		node_id = ffs(pdd->dev->interrupt_bitmap) - 1;
+		irq_drain_fence[3] |= node_id << 16;
+	}
+
 	/* ensure stale irqs scheduled KFD interrupts and send drain fence. */
 	if (amdgpu_amdkfd_send_close_event_drain_irq(pdd->dev->adev,
 						     irq_drain_fence)) {
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 9ad1a2186a24..ba9d69054119 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
@@ -123,16 +123,24 @@ int pqm_set_gws(struct process_queue_manager *pqm, unsigned int qid,
 	if (!gws && pdd->qpd.num_gws == 0)
 		return -EINVAL;
 
-	if (gws)
-		ret = amdgpu_amdkfd_add_gws_to_process(pdd->process->kgd_process_info,
-			gws, &mem);
-	else
-		ret = amdgpu_amdkfd_remove_gws_from_process(pdd->process->kgd_process_info,
-			pqn->q->gws);
-	if (unlikely(ret))
-		return ret;
+	if (KFD_GC_VERSION(dev) != IP_VERSION(9, 4, 3)) {
+		if (gws)
+			ret = amdgpu_amdkfd_add_gws_to_process(pdd->process->kgd_process_info,
+				gws, &mem);
+		else
+			ret = amdgpu_amdkfd_remove_gws_from_process(pdd->process->kgd_process_info,
+				pqn->q->gws);
+		if (unlikely(ret))
+			return ret;
+		pqn->q->gws = mem;
+	} else {
+		/*
+		 * Intentionally set GWS to a non-NULL value
+		 * for GFX 9.4.3.
+		 */
+		pqn->q->gws = gws ? ERR_PTR(-ENOMEM) : NULL;
+	}
 
-	pqn->q->gws = mem;
 	pdd->qpd.num_gws = gws ? dev->adev->gds.gws_size : 0;
 
 	return pqn->q->device->dqm->ops.update_queue(pqn->q->device->dqm,
@@ -164,7 +172,8 @@ 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)
+		if (pqn->q && pqn->q->gws &&
+		    KFD_GC_VERSION(pqn->q->device) != IP_VERSION(9, 4, 3))
 			amdgpu_amdkfd_remove_gws_from_process(pqm->process->kgd_process_info,
 				pqn->q->gws);
 		kfd_procfs_del_queue(pqn->q);
@@ -446,8 +455,10 @@ int pqm_destroy_queue(struct process_queue_manager *pqm, unsigned int qid)
 		}
 
 		if (pqn->q->gws) {
-			amdgpu_amdkfd_remove_gws_from_process(pqm->process->kgd_process_info,
-				pqn->q->gws);
+			if (KFD_GC_VERSION(pqn->q->device) != IP_VERSION(9, 4, 3))
+				amdgpu_amdkfd_remove_gws_from_process(
+						pqm->process->kgd_process_info,
+						pqn->q->gws);
 			pdd->qpd.num_gws = 0;
 		}
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
index 90b86a6ac7bd..61fc62f3e003 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
@@ -2107,6 +2107,10 @@ int kfd_topology_add_device(struct kfd_node *gpu)
 	if (KFD_IS_SVM_API_SUPPORTED(dev->gpu->adev))
 		dev->node_props.capability |= HSA_CAP_SVMAPI_SUPPORTED;
 
+	if (dev->gpu->adev->gmc.is_app_apu ||
+		dev->gpu->adev->gmc.xgmi.connected_to_cpu)
+		dev->node_props.capability |= HSA_CAP_FLAGS_COHERENTHOSTACCESS;
+
 	kfd_debug_print_topology();
 
 	kfd_notify_gpu_change(gpu_id, 1);
diff --git a/drivers/gpu/drm/amd/amdkfd/soc15_int.h b/drivers/gpu/drm/amd/amdkfd/soc15_int.h
index e3f3b0b93a59..10138676f27f 100644
--- a/drivers/gpu/drm/amd/amdkfd/soc15_int.h
+++ b/drivers/gpu/drm/amd/amdkfd/soc15_int.h
@@ -40,6 +40,7 @@
 #define SOC15_VMID_FROM_IH_ENTRY(entry) (le32_to_cpu(entry[0]) >> 24 & 0xf)
 #define SOC15_VMID_TYPE_FROM_IH_ENTRY(entry) (le32_to_cpu(entry[0]) >> 31 & 0x1)
 #define SOC15_PASID_FROM_IH_ENTRY(entry) (le32_to_cpu(entry[3]) & 0xffff)
+#define SOC15_NODEID_FROM_IH_ENTRY(entry) (le32_to_cpu(entry[3]) >> 16 & 0xff)
 #define SOC15_CONTEXT_ID0_FROM_IH_ENTRY(entry) (le32_to_cpu(entry[4]))
 #define SOC15_CONTEXT_ID1_FROM_IH_ENTRY(entry) (le32_to_cpu(entry[5]))
 #define SOC15_CONTEXT_ID2_FROM_IH_ENTRY(entry) (le32_to_cpu(entry[6]))
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 514f6785a020..ff0a217b9d56 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -5063,11 +5063,7 @@ static inline void fill_dc_dirty_rect(struct drm_plane *plane,
 				      s32 y, s32 width, s32 height,
 				      int *i, bool ffu)
 {
-	if (*i > DC_MAX_DIRTY_RECTS)
-		return;
-
-	if (*i == DC_MAX_DIRTY_RECTS)
-		goto out;
+	WARN_ON(*i >= DC_MAX_DIRTY_RECTS);
 
 	dirty_rect->x = x;
 	dirty_rect->y = y;
@@ -5083,7 +5079,6 @@ static inline void fill_dc_dirty_rect(struct drm_plane *plane,
 			"[PLANE:%d] PSR SU dirty rect at (%d, %d) size (%d, %d)",
 			plane->base.id, x, y, width, height);
 
-out:
 	(*i)++;
 }
 
@@ -5170,6 +5165,9 @@ static void fill_dc_dirty_rects(struct drm_plane *plane,
 
 	*dirty_regions_changed = bb_changed;
 
+	if ((num_clips + (bb_changed ? 2 : 0)) > DC_MAX_DIRTY_RECTS)
+		goto ffu;
+
 	if (bb_changed) {
 		fill_dc_dirty_rect(new_plane_state->plane, &dirty_rects[i],
 				   new_plane_state->crtc_x,
@@ -5199,9 +5197,6 @@ static void fill_dc_dirty_rects(struct drm_plane *plane,
 				   new_plane_state->crtc_h, &i, false);
 	}
 
-	if (i > DC_MAX_DIRTY_RECTS)
-		goto ffu;
-
 	flip_addrs->dirty_rect_count = i;
 	return;
 
@@ -7258,13 +7253,7 @@ static int amdgpu_dm_connector_get_modes(struct drm_connector *connector)
 				drm_add_modes_noedid(connector, 1920, 1080);
 	} else {
 		amdgpu_dm_connector_ddc_get_modes(connector, edid);
-		/* most eDP supports only timings from its edid,
-		 * usually only detailed timings are available
-		 * from eDP edid. timings which are not from edid
-		 * may damage eDP
-		 */
-		if (connector->connector_type != DRM_MODE_CONNECTOR_eDP)
-			amdgpu_dm_connector_add_common_modes(encoder, connector);
+		amdgpu_dm_connector_add_common_modes(encoder, connector);
 		amdgpu_dm_connector_add_freesync_modes(connector, edid);
 	}
 	amdgpu_dm_fbc_init(connector);
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 5ea3284b2b77..d63ee636483b 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
@@ -336,6 +336,153 @@ static ssize_t dp_link_settings_write(struct file *f, const char __user *buf,
 	return size;
 }
 
+static bool dp_mst_is_end_device(struct amdgpu_dm_connector *aconnector)
+{
+	bool is_end_device = false;
+	struct drm_dp_mst_topology_mgr *mgr = NULL;
+	struct drm_dp_mst_port *port = NULL;
+
+	if (aconnector->mst_root && aconnector->mst_root->mst_mgr.mst_state) {
+		mgr = &aconnector->mst_root->mst_mgr;
+		port = aconnector->mst_output_port;
+
+		drm_modeset_lock(&mgr->base.lock, NULL);
+		if (port->pdt == DP_PEER_DEVICE_SST_SINK ||
+			port->pdt == DP_PEER_DEVICE_DP_LEGACY_CONV)
+			is_end_device = true;
+		drm_modeset_unlock(&mgr->base.lock);
+	}
+
+	return is_end_device;
+}
+
+/* Change MST link setting
+ *
+ * valid lane count value: 1, 2, 4
+ * valid link rate value:
+ * 06h = 1.62Gbps per lane
+ * 0Ah = 2.7Gbps per lane
+ * 0Ch = 3.24Gbps per lane
+ * 14h = 5.4Gbps per lane
+ * 1Eh = 8.1Gbps per lane
+ * 3E8h = 10.0Gbps per lane
+ * 546h = 13.5Gbps per lane
+ * 7D0h = 20.0Gbps per lane
+ *
+ * debugfs is located at /sys/kernel/debug/dri/0/DP-x/mst_link_settings
+ *
+ * for example, to force to  2 lane, 10.0GHz,
+ * echo 2 0x3e8 > /sys/kernel/debug/dri/0/DP-x/mst_link_settings
+ *
+ * Valid input will trigger hotplug event to get new link setting applied
+ * Invalid input will trigger training setting reset
+ *
+ * The usage can be referred to link_settings entry
+ *
+ */
+static ssize_t dp_mst_link_setting(struct file *f, const char __user *buf,
+				 size_t size, loff_t *pos)
+{
+	struct amdgpu_dm_connector *aconnector = file_inode(f)->i_private;
+	struct dc_link *link = aconnector->dc_link;
+	struct amdgpu_device *adev = drm_to_adev(aconnector->base.dev);
+	struct dc *dc = (struct dc *)link->dc;
+	struct dc_link_settings prefer_link_settings;
+	char *wr_buf = NULL;
+	const uint32_t wr_buf_size = 40;
+	/* 0: lane_count; 1: link_rate */
+	int max_param_num = 2;
+	uint8_t param_nums = 0;
+	long param[2];
+	bool valid_input = true;
+
+	if (!dp_mst_is_end_device(aconnector))
+		return -EINVAL;
+
+	if (size == 0)
+		return -EINVAL;
+
+	wr_buf = kcalloc(wr_buf_size, sizeof(char), GFP_KERNEL);
+	if (!wr_buf)
+		return -ENOSPC;
+
+	if (parse_write_buffer_into_params(wr_buf, wr_buf_size,
+					   (long *)param, buf,
+					   max_param_num,
+					   &param_nums)) {
+		kfree(wr_buf);
+		return -EINVAL;
+	}
+
+	if (param_nums <= 0) {
+		kfree(wr_buf);
+		DRM_DEBUG_DRIVER("user data not be read\n");
+		return -EINVAL;
+	}
+
+	switch (param[0]) {
+	case LANE_COUNT_ONE:
+	case LANE_COUNT_TWO:
+	case LANE_COUNT_FOUR:
+		break;
+	default:
+		valid_input = false;
+		break;
+	}
+
+	switch (param[1]) {
+	case LINK_RATE_LOW:
+	case LINK_RATE_HIGH:
+	case LINK_RATE_RBR2:
+	case LINK_RATE_HIGH2:
+	case LINK_RATE_HIGH3:
+	case LINK_RATE_UHBR10:
+	case LINK_RATE_UHBR13_5:
+	case LINK_RATE_UHBR20:
+		break;
+	default:
+		valid_input = false;
+		break;
+	}
+
+	if (!valid_input) {
+		kfree(wr_buf);
+		DRM_DEBUG_DRIVER("Invalid Input value No HW will be programmed\n");
+		mutex_lock(&adev->dm.dc_lock);
+		dc_link_set_preferred_training_settings(dc, NULL, NULL, link, false);
+		mutex_unlock(&adev->dm.dc_lock);
+		return -EINVAL;
+	}
+
+	/* save user force lane_count, link_rate to preferred settings
+	 * spread spectrum will not be changed
+	 */
+	prefer_link_settings.link_spread = link->cur_link_settings.link_spread;
+	prefer_link_settings.use_link_rate_set = false;
+	prefer_link_settings.lane_count = param[0];
+	prefer_link_settings.link_rate = param[1];
+
+	/* skip immediate retrain, and train to new link setting after hotplug event triggered */
+	mutex_lock(&adev->dm.dc_lock);
+	dc_link_set_preferred_training_settings(dc, &prefer_link_settings, NULL, link, true);
+	mutex_unlock(&adev->dm.dc_lock);
+
+	mutex_lock(&aconnector->base.dev->mode_config.mutex);
+	aconnector->base.force = DRM_FORCE_OFF;
+	mutex_unlock(&aconnector->base.dev->mode_config.mutex);
+	drm_kms_helper_hotplug_event(aconnector->base.dev);
+
+	msleep(100);
+
+	mutex_lock(&aconnector->base.dev->mode_config.mutex);
+	aconnector->base.force = DRM_FORCE_UNSPECIFIED;
+	mutex_unlock(&aconnector->base.dev->mode_config.mutex);
+	drm_kms_helper_hotplug_event(aconnector->base.dev);
+
+	kfree(wr_buf);
+	return size;
+}
+
 /* function: get current DP PHY settings: voltage swing, pre-emphasis,
  * post-cursor2 (defined by VESA DP specification)
  *
@@ -2668,6 +2815,12 @@ static const struct file_operations dp_dsc_disable_passthrough_debugfs_fops = {
 	.llseek = default_llseek
 };
 
+static const struct file_operations dp_mst_link_settings_debugfs_fops = {
+	.owner = THIS_MODULE,
+	.write = dp_mst_link_setting,
+	.llseek = default_llseek
+};
+
 static const struct {
 	char *name;
 	const struct file_operations *fops;
@@ -2691,7 +2844,8 @@ static const struct {
 		{"dsc_disable_passthrough", &dp_dsc_disable_passthrough_debugfs_fops},
 		{"is_mst_connector", &dp_is_mst_connector_fops},
 		{"mst_progress_status", &dp_mst_progress_status_fops},
-		{"is_dpia_link", &is_dpia_link_fops}
+		{"is_dpia_link", &is_dpia_link_fops},
+		{"mst_link_settings", &dp_mst_link_settings_debugfs_fops}
 };
 
 static const struct {
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c
index cd20cfc04996..d9a482908380 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c
@@ -44,6 +44,30 @@
 #include "dm_helpers.h"
 #include "ddc_service_types.h"
 
+static u32 edid_extract_panel_id(struct edid *edid)
+{
+	return (u32)edid->mfg_id[0] << 24   |
+	       (u32)edid->mfg_id[1] << 16   |
+	       (u32)EDID_PRODUCT_ID(edid);
+}
+
+static void apply_edid_quirks(struct edid *edid, struct dc_edid_caps *edid_caps)
+{
+	uint32_t panel_id = edid_extract_panel_id(edid);
+
+	switch (panel_id) {
+	/* Workaround for some monitors which does not work well with FAMS */
+	case drm_edid_encode_panel_id('S', 'A', 'M', 0x0E5E):
+	case drm_edid_encode_panel_id('S', 'A', 'M', 0x7053):
+	case drm_edid_encode_panel_id('S', 'A', 'M', 0x71AC):
+		DRM_DEBUG_DRIVER("Disabling FAMS on monitor with panel id %X\n", panel_id);
+		edid_caps->panel_patch.disable_fams = true;
+		break;
+	default:
+		return;
+	}
+}
+
 /* dm_helpers_parse_edid_caps
  *
  * Parse edid caps
@@ -115,6 +139,8 @@ enum dc_edid_status dm_helpers_parse_edid_caps(
 	else
 		edid_caps->speaker_flags = DEFAULT_SPEAKER_LOCATION;
 
+	apply_edid_quirks(edid_buf, edid_caps);
+
 	kfree(sads);
 	kfree(sadb);
 
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.c
index d647f68fd563..4f61d4f257cd 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.c
@@ -24,6 +24,7 @@
  */
 
 #include "amdgpu_dm_psr.h"
+#include "dc_dmub_srv.h"
 #include "dc.h"
 #include "dm_helpers.h"
 #include "amdgpu_dm.h"
@@ -50,7 +51,7 @@ static bool link_supports_psrsu(struct dc_link *link)
 	    !link->dpcd_caps.psr_info.psr2_su_y_granularity_cap)
 		return false;
 
-	return true;
+	return dc_dmub_check_min_version(dc->ctx->dmub_srv->dmub);
 }
 
 /*
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn32/dcn32_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn32/dcn32_clk_mgr.c
index 6a811755e2e6..cb992aca760d 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn32/dcn32_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn32/dcn32_clk_mgr.c
@@ -541,9 +541,18 @@ static void dcn32_update_clocks(struct clk_mgr *clk_mgr_base,
 			clk_mgr_base->clks.p_state_change_support = p_state_change_support;
 
 			/* to disable P-State switching, set UCLK min = max */
-			if (!clk_mgr_base->clks.p_state_change_support)
-				dcn32_smu_set_hard_min_by_freq(clk_mgr, PPCLK_UCLK,
-						clk_mgr_base->bw_params->clk_table.entries[clk_mgr_base->bw_params->clk_table.num_entries_per_clk.num_memclk_levels - 1].memclk_mhz);
+			if (!clk_mgr_base->clks.p_state_change_support) {
+				if (dc->clk_mgr->dc_mode_softmax_enabled) {
+					/* On DCN32x we will never have the functional UCLK min above the softmax
+					 * since we calculate mode support based on softmax being the max UCLK
+					 * frequency.
+					 */
+					dcn32_smu_set_hard_min_by_freq(clk_mgr, PPCLK_UCLK,
+							dc->clk_mgr->bw_params->dc_mode_softmax_memclk);
+				} else {
+					dcn32_smu_set_hard_min_by_freq(clk_mgr, PPCLK_UCLK, dc->clk_mgr->bw_params->max_memclk_mhz);
+				}
+			}
 		}
 
 		/* Always update saved value, even if new value not set due to P-State switching unsupported. Also check safe_to_lower for FCLK */
@@ -808,8 +817,7 @@ static void dcn32_set_hard_max_memclk(struct clk_mgr *clk_mgr_base)
 	if (!clk_mgr->smu_present)
 		return;
 
-	dcn30_smu_set_hard_max_by_freq(clk_mgr, PPCLK_UCLK,
-			clk_mgr_base->bw_params->clk_table.entries[clk_mgr_base->bw_params->clk_table.num_entries_per_clk.num_memclk_levels - 1].memclk_mhz);
+	dcn30_smu_set_hard_max_by_freq(clk_mgr, PPCLK_UCLK, clk_mgr_base->bw_params->max_memclk_mhz);
 }
 
 /* Get current memclk states, update bounding box */
@@ -827,6 +835,7 @@ static void dcn32_get_memclk_states_from_smu(struct clk_mgr *clk_mgr_base)
 			&clk_mgr_base->bw_params->clk_table.entries[0].memclk_mhz,
 			&num_entries_per_clk->num_memclk_levels);
 	clk_mgr_base->bw_params->dc_mode_limit.memclk_mhz = dcn30_smu_get_dc_mode_max_dpm_freq(clk_mgr, PPCLK_UCLK);
+	clk_mgr_base->bw_params->dc_mode_softmax_memclk = clk_mgr_base->bw_params->dc_mode_limit.memclk_mhz;
 
 	/* memclk must have at least one level */
 	num_entries_per_clk->num_memclk_levels = num_entries_per_clk->num_memclk_levels ? num_entries_per_clk->num_memclk_levels : 1;
@@ -841,7 +850,8 @@ static void dcn32_get_memclk_states_from_smu(struct clk_mgr *clk_mgr_base)
 	} else {
 		num_levels = num_entries_per_clk->num_fclk_levels;
 	}
-
+	clk_mgr_base->bw_params->max_memclk_mhz =
+			clk_mgr_base->bw_params->clk_table.entries[num_entries_per_clk->num_memclk_levels - 1].memclk_mhz;
 	clk_mgr_base->bw_params->clk_table.num_entries = num_levels ? num_levels : 1;
 
 	if (clk_mgr->dpm_present && !num_levels)
@@ -894,6 +904,25 @@ static bool dcn32_is_smu_present(struct clk_mgr *clk_mgr_base)
 	return clk_mgr->smu_present;
 }
 
+static void dcn32_set_max_memclk(struct clk_mgr *clk_mgr_base, unsigned int memclk_mhz)
+{
+	struct clk_mgr_internal *clk_mgr = TO_CLK_MGR_INTERNAL(clk_mgr_base);
+
+	if (!clk_mgr->smu_present)
+		return;
+
+	dcn30_smu_set_hard_max_by_freq(clk_mgr, PPCLK_UCLK, memclk_mhz);
+}
+
+static void dcn32_set_min_memclk(struct clk_mgr *clk_mgr_base, unsigned int memclk_mhz)
+{
+	struct clk_mgr_internal *clk_mgr = TO_CLK_MGR_INTERNAL(clk_mgr_base);
+
+	if (!clk_mgr->smu_present)
+		return;
+
+	dcn32_smu_set_hard_min_by_freq(clk_mgr, PPCLK_UCLK, memclk_mhz);
+}
 
 static struct clk_mgr_funcs dcn32_funcs = {
 		.get_dp_ref_clk_frequency = dce12_get_dp_ref_freq_khz,
@@ -904,6 +933,8 @@ static struct clk_mgr_funcs dcn32_funcs = {
 		.notify_wm_ranges = dcn32_notify_wm_ranges,
 		.set_hard_min_memclk = dcn32_set_hard_min_memclk,
 		.set_hard_max_memclk = dcn32_set_hard_max_memclk,
+		.set_max_memclk = dcn32_set_max_memclk,
+		.set_min_memclk = dcn32_set_min_memclk,
 		.get_memclk_states_from_smu = dcn32_get_memclk_states_from_smu,
 		.are_clock_states_equal = dcn32_are_clock_states_equal,
 		.enable_pme_wa = dcn32_enable_pme_wa,
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c
index dd3a9d06c6e2..d133e4186a52 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc.c
@@ -1629,6 +1629,9 @@ bool dc_validate_boot_timing(const struct dc *dc,
 		return false;
 	}
 
+	if (dc->debug.force_odm_combine)
+		return false;
+
 	/* Check for enabled DIG to identify enabled display */
 	if (!link->link_enc->funcs->is_dig_enabled(link->link_enc))
 		return false;
@@ -3577,6 +3580,13 @@ static void commit_planes_for_stream_fast(struct dc *dc,
 	hwss_execute_sequence(dc,
 			context->block_sequence,
 			context->block_sequence_steps);
+	/* Clear update flags so next flip doesn't have redundant programming
+	 * (if there's no stream update, the update flags are not cleared).
+	 */
+	if (top_pipe_to_program->plane_state)
+		top_pipe_to_program->plane_state->update_flags.raw = 0;
+	if (top_pipe_to_program->stream)
+		top_pipe_to_program->stream->update_flags.raw = 0;
 }
 
 static void commit_planes_for_stream(struct dc *dc,
@@ -4233,6 +4243,117 @@ static void update_seamless_boot_flags(struct dc *dc,
 	}
 }
 
+static void populate_fast_updates(struct dc_fast_update *fast_update,
+		struct dc_surface_update *srf_updates,
+		int surface_count,
+		struct dc_stream_update *stream_update)
+{
+	int i = 0;
+
+	if (stream_update) {
+		fast_update[0].out_transfer_func = stream_update->out_transfer_func;
+		fast_update[0].output_csc_transform = stream_update->output_csc_transform;
+	}
+
+	for (i = 0; i < surface_count; i++) {
+		fast_update[i].flip_addr = srf_updates[i].flip_addr;
+		fast_update[i].gamma = srf_updates[i].gamma;
+		fast_update[i].gamut_remap_matrix = srf_updates[i].gamut_remap_matrix;
+		fast_update[i].input_csc_color_matrix = srf_updates[i].input_csc_color_matrix;
+		fast_update[i].coeff_reduction_factor = srf_updates[i].coeff_reduction_factor;
+	}
+}
+
+static bool fast_updates_exist(struct dc_fast_update *fast_update, int surface_count)
+{
+	int i;
+
+	if (fast_update[0].out_transfer_func ||
+		fast_update[0].output_csc_transform)
+		return true;
+
+	for (i = 0; i < surface_count; i++) {
+		if (fast_update[i].flip_addr ||
+				fast_update[i].gamma ||
+				fast_update[i].gamut_remap_matrix ||
+				fast_update[i].input_csc_color_matrix ||
+				fast_update[i].coeff_reduction_factor)
+			return true;
+	}
+
+	return false;
+}
+
+static bool full_update_required(struct dc_surface_update *srf_updates,
+		int surface_count,
+		struct dc_stream_update *stream_update,
+		struct dc_stream_state *stream)
+{
+
+	int i;
+	struct dc_stream_status *stream_status;
+
+	for (i = 0; i < surface_count; i++) {
+		if (srf_updates &&
+				(srf_updates[i].plane_info ||
+				srf_updates[i].scaling_info ||
+				(srf_updates[i].hdr_mult.value &&
+				srf_updates[i].hdr_mult.value != srf_updates->surface->hdr_mult.value) ||
+				srf_updates[i].in_transfer_func ||
+				srf_updates[i].func_shaper ||
+				srf_updates[i].lut3d_func ||
+				srf_updates[i].blend_tf))
+			return true;
+	}
+
+	if (stream_update &&
+			(((stream_update->src.height != 0 && stream_update->src.width != 0) ||
+			(stream_update->dst.height != 0 && stream_update->dst.width != 0) ||
+			stream_update->integer_scaling_update) ||
+			stream_update->hdr_static_metadata ||
+			stream_update->abm_level ||
+			stream_update->periodic_interrupt ||
+			stream_update->vrr_infopacket ||
+			stream_update->vsc_infopacket ||
+			stream_update->vsp_infopacket ||
+			stream_update->hfvsif_infopacket ||
+			stream_update->vtem_infopacket ||
+			stream_update->adaptive_sync_infopacket ||
+			stream_update->dpms_off ||
+			stream_update->allow_freesync ||
+			stream_update->vrr_active_variable ||
+			stream_update->vrr_active_fixed ||
+			stream_update->gamut_remap ||
+			stream_update->output_color_space ||
+			stream_update->dither_option ||
+			stream_update->wb_update ||
+			stream_update->dsc_config ||
+			stream_update->mst_bw_update ||
+			stream_update->func_shaper ||
+			stream_update->lut3d_func ||
+			stream_update->pending_test_pattern ||
+			stream_update->crtc_timing_adjust))
+		return true;
+
+	if (stream) {
+		stream_status = dc_stream_get_status(stream);
+		if (stream_status == NULL || stream_status->plane_count != surface_count)
+			return true;
+	}
+
+	return false;
+}
+
+static bool fast_update_only(struct dc_fast_update *fast_update,
+		struct dc_surface_update *srf_updates,
+		int surface_count,
+		struct dc_stream_update *stream_update,
+		struct dc_stream_state *stream)
+{
+	return fast_updates_exist(fast_update, surface_count)
+			&& !full_update_required(srf_updates, surface_count, stream_update, stream);
+}
+
 bool dc_update_planes_and_stream(struct dc *dc,
 		struct dc_surface_update *srf_updates, int surface_count,
 		struct dc_stream_state *stream,
@@ -4242,6 +4363,7 @@ bool dc_update_planes_and_stream(struct dc *dc,
 	enum surface_update_type update_type;
 	int i;
 	struct mall_temp_config mall_temp_config;
+	struct dc_fast_update fast_update[MAX_SURFACES] = {0};
 
 	/* In cases where MPO and split or ODM are used transitions can
 	 * cause underflow. Apply stream configuration with minimal pipe
@@ -4250,6 +4372,7 @@ bool dc_update_planes_and_stream(struct dc *dc,
 	bool force_minimal_pipe_splitting;
 	bool is_plane_addition;
 
+	populate_fast_updates(fast_update, srf_updates, surface_count, stream_update);
 	force_minimal_pipe_splitting = could_mpcc_tree_change_for_active_pipes(
 			dc,
 			stream,
@@ -4300,7 +4423,8 @@ bool dc_update_planes_and_stream(struct dc *dc,
 	}
 
 	update_seamless_boot_flags(dc, context, surface_count, stream);
-	if (!dc->debug.enable_legacy_fast_update && update_type == UPDATE_TYPE_FAST) {
+	if (fast_update_only(fast_update, srf_updates, surface_count, stream_update, stream) &&
+			!dc->debug.enable_legacy_fast_update) {
 		commit_planes_for_stream_fast(dc,
 				srf_updates,
 				surface_count,
@@ -4357,7 +4481,9 @@ void dc_commit_updates_for_stream(struct dc *dc,
 	struct dc_state *context;
 	struct dc_context *dc_ctx = dc->ctx;
 	int i, j;
+	struct dc_fast_update fast_update[MAX_SURFACES] = {0};
 
+	populate_fast_updates(fast_update, srf_updates, surface_count, stream_update);
 	stream_status = dc_stream_get_status(stream);
 	context = dc->current_state;
 
@@ -4443,7 +4569,8 @@ void dc_commit_updates_for_stream(struct dc *dc,
 	TRACE_DC_PIPE_STATE(pipe_ctx, i, MAX_PIPES);
 
 	update_seamless_boot_flags(dc, context, surface_count, stream);
-	if (!dc->debug.enable_legacy_fast_update && update_type == UPDATE_TYPE_FAST) {
+	if (fast_update_only(fast_update, srf_updates, surface_count, stream_update, stream) &&
+			!dc->debug.enable_legacy_fast_update) {
 		commit_planes_for_stream_fast(dc,
 				srf_updates,
 				surface_count,
@@ -4753,15 +4880,17 @@ static void blank_and_force_memclk(struct dc *dc, bool apply, unsigned int memcl
  */
 void dc_enable_dcmode_clk_limit(struct dc *dc, bool enable)
 {
-	uint32_t hw_internal_rev = dc->ctx->asic_id.hw_internal_rev;
-	unsigned int softMax, maxDPM, funcMin;
+	unsigned int softMax = 0, maxDPM = 0, funcMin = 0, i;
 	bool p_state_change_support;
 
-	if (!ASICREV_IS_BEIGE_GOBY_P(hw_internal_rev))
+	if (!dc->config.dc_mode_clk_limit_support)
 		return;
 
 	softMax = dc->clk_mgr->bw_params->dc_mode_softmax_memclk;
-	maxDPM = dc->clk_mgr->bw_params->clk_table.entries[dc->clk_mgr->bw_params->clk_table.num_entries - 1].memclk_mhz;
+	for (i = 0; i < dc->clk_mgr->bw_params->clk_table.num_entries; i++) {
+		if (dc->clk_mgr->bw_params->clk_table.entries[i].memclk_mhz > maxDPM)
+			maxDPM = dc->clk_mgr->bw_params->clk_table.entries[i].memclk_mhz;
+	}
 	funcMin = (dc->clk_mgr->clks.dramclk_khz + 999) / 1000;
 	p_state_change_support = dc->clk_mgr->clks.p_state_change_support;
 
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/core/dc_hw_sequencer.c
index d7d00fefaab9..cb2bf9a466f5 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_hw_sequencer.c
@@ -610,7 +610,7 @@ void hwss_build_fast_sequence(struct dc *dc,
 		current_mpc_pipe = current_pipe;
 
 		while (current_mpc_pipe) {
-			if (!current_mpc_pipe->bottom_pipe && !pipe_ctx->next_odm_pipe &&
+			if (!current_mpc_pipe->bottom_pipe && !current_mpc_pipe->next_odm_pipe &&
 					current_mpc_pipe->stream && current_mpc_pipe->plane_state &&
 					current_mpc_pipe->plane_state->update_flags.bits.addr_update &&
 					!current_mpc_pipe->plane_state->skip_manual_trigger) {
diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h
index 26d05e225088..63948170fd6d 100644
--- a/drivers/gpu/drm/amd/display/dc/dc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc.h
@@ -45,7 +45,7 @@ struct aux_payload;
 struct set_config_cmd_payload;
 struct dmub_notification;
 
-#define DC_VER "3.2.239"
+#define DC_VER "3.2.241"
 
 #define MAX_SURFACES 3
 #define MAX_PLANES 6
@@ -416,7 +416,7 @@ struct dc_config {
 	uint8_t force_bios_fixed_vs;
 	int sdpif_request_limit_words_per_umc;
 	bool use_old_fixed_vs_sequence;
-	bool disable_subvp_drr;
+	bool dc_mode_clk_limit_support;
 };
 
 enum visual_confirm {
@@ -850,6 +850,7 @@ struct dc_debug_options {
 	/* Enable dmub aux for legacy ddc */
 	bool enable_dmub_aux_for_legacy_ddc;
 	bool disable_fams;
+	bool disable_fams_gaming;
 	/* FEC/PSR1 sequence enable delay in 100us */
 	uint8_t fec_enable_delay_in100us;
 	bool enable_driver_sequence_debug;
@@ -1264,6 +1265,16 @@ struct dc_scaling_info {
 	struct scaling_taps scaling_quality;
 };
 
+struct dc_fast_update {
+	const struct dc_flip_addrs *flip_addr;
+	const struct dc_gamma *gamma;
+	const struct colorspace_transform *gamut_remap_matrix;
+	const struct dc_csc_transform *input_csc_color_matrix;
+	const struct fixed31_32 *coeff_reduction_factor;
+	struct dc_transfer_func *out_transfer_func;
+	struct dc_csc_transform *output_csc_transform;
+};
+
 struct dc_surface_update {
 	struct dc_plane_state *surface;
 
@@ -1525,6 +1536,7 @@ struct dc_link {
 		bool dpia_forced_tbt3_mode;
 		bool dongle_mode_timing_override;
 		bool blank_stream_on_ocs_change;
+		bool read_dpcd204h_on_irq_hpd;
 	} wa_flags;
 	struct link_mst_stream_allocation_table mst_stream_alloc_table;
 
diff --git a/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c b/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c
index c52c40b16387..c753c6f30dd7 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c
+++ b/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c
@@ -1011,3 +1011,10 @@ void dc_send_update_cursor_info_to_dmu(
 		dm_execute_dmub_cmd_list(pCtx->stream->ctx, 2, cmd, DM_DMUB_WAIT_TYPE_WAIT);
 	}
 }
+
+bool dc_dmub_check_min_version(struct dmub_srv *srv)
+{
+	if (!srv->hw_funcs.is_psrsu_supported)
+		return true;
+	return srv->hw_funcs.is_psrsu_supported(srv);
+}
diff --git a/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.h b/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.h
index a5196a9292b3..099f94b6107c 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.h
@@ -86,4 +86,5 @@ void dc_dmub_setup_subvp_dmub_command(struct dc *dc, struct dc_state *context, b
 void dc_dmub_srv_log_diagnostic_data(struct dc_dmub_srv *dc_dmub_srv);
 
 void dc_send_update_cursor_info_to_dmu(struct pipe_ctx *pCtx, uint8_t pipe_idx);
+bool dc_dmub_check_min_version(struct dmub_srv *srv);
 #endif /* _DMUB_DC_SRV_H_ */
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_abm.h b/drivers/gpu/drm/amd/display/dc/dce/dce_abm.h
index e6c06325742a..168cb7094c95 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_abm.h
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_abm.h
@@ -266,7 +266,24 @@
 	type MASTER_COMM_INTERRUPT; \
 	type MASTER_COMM_CMD_REG_BYTE0; \
 	type MASTER_COMM_CMD_REG_BYTE1; \
-	type MASTER_COMM_CMD_REG_BYTE2
+	type MASTER_COMM_CMD_REG_BYTE2; \
+	type ABM1_HG_BIN_33_40_SHIFT_INDEX; \
+	type ABM1_HG_BIN_33_64_SHIFT_FLAG; \
+	type ABM1_HG_BIN_41_48_SHIFT_INDEX; \
+	type ABM1_HG_BIN_49_56_SHIFT_INDEX; \
+	type ABM1_HG_BIN_57_64_SHIFT_INDEX; \
+	type ABM1_HG_RESULT_DATA; \
+	type ABM1_HG_RESULT_INDEX; \
+	type ABM1_ACE_SLOPE_DATA; \
+	type ABM1_ACE_OFFSET_DATA; \
+	type ABM1_ACE_OFFSET_SLOPE_INDEX; \
+	type ABM1_ACE_THRES_INDEX; \
+	type ABM1_ACE_IGNORE_MASTER_LOCK_EN; \
+	type ABM1_ACE_READBACK_DB_REG_VALUE_EN; \
+	type ABM1_ACE_DBUF_REG_UPDATE_PENDING; \
+	type ABM1_ACE_LOCK; \
+	type ABM1_ACE_THRES_DATA_1; \
+	type ABM1_ACE_THRES_DATA_2
 
 struct dce_abm_shift {
 	ABM_REG_FIELD_LIST(uint8_t);
@@ -288,6 +305,16 @@ struct dce_abm_registers {
 	uint32_t DC_ABM1_LS_MIN_MAX_PIXEL_VALUE_THRES;
 	uint32_t DC_ABM1_HGLS_REG_READ_PROGRESS;
 	uint32_t DC_ABM1_ACE_OFFSET_SLOPE_0;
+	uint32_t DC_ABM1_ACE_OFFSET_SLOPE_DATA;
+	uint32_t DC_ABM1_ACE_PWL_CNTL;
+	uint32_t DC_ABM1_HG_BIN_33_40_SHIFT_INDEX;
+	uint32_t DC_ABM1_HG_BIN_33_64_SHIFT_FLAG;
+	uint32_t DC_ABM1_HG_BIN_41_48_SHIFT_INDEX;
+	uint32_t DC_ABM1_HG_BIN_49_56_SHIFT_INDEX;
+	uint32_t DC_ABM1_HG_BIN_57_64_SHIFT_INDEX;
+	uint32_t DC_ABM1_HG_RESULT_DATA;
+	uint32_t DC_ABM1_HG_RESULT_INDEX;
+	uint32_t DC_ABM1_ACE_THRES_DATA;
 	uint32_t DC_ABM1_ACE_THRES_12;
 	uint32_t MASTER_COMM_CNTL_REG;
 	uint32_t MASTER_COMM_CMD_REG;
diff --git a/drivers/gpu/drm/amd/display/dc/dce112/dce112_resource.c b/drivers/gpu/drm/amd/display/dc/dce112/dce112_resource.c
index 808855886183..e115ff91aaaa 100644
--- a/drivers/gpu/drm/amd/display/dc/dce112/dce112_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dce112/dce112_resource.c
@@ -974,10 +974,12 @@ enum dc_status resource_map_phy_clock_resources(
 		|| dc_is_virtual_signal(pipe_ctx->stream->signal))
 		pipe_ctx->clock_source =
 				dc->res_pool->dp_clock_source;
-	else
-		pipe_ctx->clock_source = find_matching_pll(
-			&context->res_ctx, dc->res_pool,
-			stream);
+	else {
+		if (stream && stream->link && stream->link->link_enc)
+			pipe_ctx->clock_source = find_matching_pll(
+				&context->res_ctx, dc->res_pool,
+				stream);
+	}
 
 	if (pipe_ctx->clock_source == NULL)
 		return DC_NO_CLOCK_SOURCE_RESOURCE;
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_cm_common.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_cm_common.c
index 7a00fe525dfb..3538973bd0c6 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_cm_common.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_cm_common.c
@@ -308,7 +308,10 @@ bool cm_helper_convert_to_custom_float(
 #define NUMBER_REGIONS     32
 #define NUMBER_SW_SEGMENTS 16
 
-bool cm_helper_translate_curve_to_hw_format(
+#define DC_LOGGER \
+		ctx->logger
+
+bool cm_helper_translate_curve_to_hw_format(struct dc_context *ctx,
 				const struct dc_transfer_func *output_tf,
 				struct pwl_params *lut_params, bool fixpoint)
 {
@@ -482,10 +485,18 @@ bool cm_helper_translate_curve_to_hw_format(
 		rgb->delta_green = dc_fixpt_sub(rgb_plus_1->green, rgb->green);
 		rgb->delta_blue  = dc_fixpt_sub(rgb_plus_1->blue,  rgb->blue);
 
+
 		if (fixpoint == true) {
-			rgb->delta_red_reg   = dc_fixpt_clamp_u0d10(rgb->delta_red);
-			rgb->delta_green_reg = dc_fixpt_clamp_u0d10(rgb->delta_green);
-			rgb->delta_blue_reg  = dc_fixpt_clamp_u0d10(rgb->delta_blue);
+			uint32_t red_clamp = dc_fixpt_clamp_u0d14(rgb->delta_red);
+			uint32_t green_clamp = dc_fixpt_clamp_u0d14(rgb->delta_green);
+			uint32_t blue_clamp = dc_fixpt_clamp_u0d14(rgb->delta_blue);
+
+			if (red_clamp >> 10 || green_clamp >> 10 || blue_clamp >> 10)
+				DC_LOG_WARNING("Losing delta precision while programming shaper LUT.");
+
+			rgb->delta_red_reg   = red_clamp & 0x3ff;
+			rgb->delta_green_reg = green_clamp & 0x3ff;
+			rgb->delta_blue_reg  = blue_clamp & 0x3ff;
 			rgb->red_reg         = dc_fixpt_clamp_u0d14(rgb->red);
 			rgb->green_reg       = dc_fixpt_clamp_u0d14(rgb->green);
 			rgb->blue_reg        = dc_fixpt_clamp_u0d14(rgb->blue);
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_cm_common.h b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_cm_common.h
index 3b8cd7410498..0a68b63d6126 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_cm_common.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_cm_common.h
@@ -106,6 +106,7 @@ bool cm_helper_convert_to_custom_float(
 		bool fixpoint);
 
 bool cm_helper_translate_curve_to_hw_format(
+		struct dc_context *ctx,
 		const struct dc_transfer_func *output_tf,
 		struct pwl_params *lut_params, bool fixpoint);
 
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 20a1582be0b1..a50309039d08 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
@@ -1843,7 +1843,7 @@ bool dcn10_set_output_transfer_func(struct dc *dc, struct pipe_ctx *pipe_ctx,
 	/* dcn10_translate_regamma_to_hw_format takes 750us, only do it when full
 	 * update.
 	 */
-	else if (cm_helper_translate_curve_to_hw_format(
+	else if (cm_helper_translate_curve_to_hw_format(dc->ctx,
 			stream->out_transfer_func,
 			&dpp->regamma_params, false)) {
 		dpp->funcs->dpp_program_regamma_pwl(
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 eaf9e9ccad2a..4492bc2392b6 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c
@@ -867,7 +867,7 @@ bool dcn20_set_output_transfer_func(struct dc *dc, struct pipe_ctx *pipe_ctx,
 			params = &stream->out_transfer_func->pwl;
 		else if (pipe_ctx->stream->out_transfer_func->type ==
 			TF_TYPE_DISTRIBUTED_POINTS &&
-			cm_helper_translate_curve_to_hw_format(
+			cm_helper_translate_curve_to_hw_format(dc->ctx,
 			stream->out_transfer_func,
 			&mpc->blender_params, false))
 			params = &mpc->blender_params;
@@ -896,7 +896,7 @@ bool dcn20_set_blend_lut(
 		if (plane_state->blend_tf->type == TF_TYPE_HWPWL)
 			blend_lut = &plane_state->blend_tf->pwl;
 		else if (plane_state->blend_tf->type == TF_TYPE_DISTRIBUTED_POINTS) {
-			cm_helper_translate_curve_to_hw_format(
+			cm_helper_translate_curve_to_hw_format(plane_state->ctx,
 					plane_state->blend_tf,
 					&dpp_base->regamma_params, false);
 			blend_lut = &dpp_base->regamma_params;
@@ -918,7 +918,7 @@ bool dcn20_set_shaper_3dlut(
 		if (plane_state->in_shaper_func->type == TF_TYPE_HWPWL)
 			shaper_lut = &plane_state->in_shaper_func->pwl;
 		else if (plane_state->in_shaper_func->type == TF_TYPE_DISTRIBUTED_POINTS) {
-			cm_helper_translate_curve_to_hw_format(
+			cm_helper_translate_curve_to_hw_format(plane_state->ctx,
 					plane_state->in_shaper_func,
 					&dpp_base->shaper_params, true);
 			shaper_lut = &dpp_base->shaper_params;
@@ -1764,8 +1764,9 @@ static void dcn20_program_pipe(
 		hws->funcs.set_hdr_multiplier(pipe_ctx);
 
 	if (pipe_ctx->update_flags.bits.enable ||
-			pipe_ctx->plane_state->update_flags.bits.in_transfer_func_change ||
-			pipe_ctx->plane_state->update_flags.bits.gamma_change)
+	    pipe_ctx->plane_state->update_flags.bits.in_transfer_func_change ||
+	    pipe_ctx->plane_state->update_flags.bits.gamma_change ||
+	    pipe_ctx->plane_state->update_flags.bits.lut_3d)
 		hws->funcs.set_input_transfer_func(dc, pipe_ctx, pipe_ctx->plane_state);
 
 	/* dcn10_translate_regamma_to_hw_format takes 750us to finish
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 6a3d3a0ec0a3..701c7d8bc038 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
@@ -280,7 +280,7 @@ bool dwb3_ogam_set_input_transfer_func(
 	dwb_ogam_lut = kzalloc(sizeof(*dwb_ogam_lut), GFP_KERNEL);
 
 	if (dwb_ogam_lut) {
-		cm_helper_translate_curve_to_hw_format(
+		cm_helper_translate_curve_to_hw_format(dwbc->ctx,
 			in_transfer_func_dwb_ogam,
 			dwb_ogam_lut, false);
 
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 b9753867d97b..bf8864bc8a99 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c
@@ -106,7 +106,7 @@ static bool dcn30_set_mpc_shaper_3dlut(struct pipe_ctx *pipe_ctx,
 		if (stream->func_shaper->type == TF_TYPE_HWPWL) {
 			shaper_lut = &stream->func_shaper->pwl;
 		} else if (stream->func_shaper->type == TF_TYPE_DISTRIBUTED_POINTS) {
-			cm_helper_translate_curve_to_hw_format(stream->func_shaper,
+			cm_helper_translate_curve_to_hw_format(stream->ctx, stream->func_shaper,
 							       &dpp_base->shaper_params, true);
 			shaper_lut = &dpp_base->shaper_params;
 		}
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 1a0284a068b2..abe4c12a10b5 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c
@@ -725,7 +725,8 @@ static const struct dc_debug_options debug_defaults_drv = {
 	.dwb_fi_phase = -1, // -1 = disable,
 	.dmub_command_table = true,
 	.use_max_lb = true,
-	.exit_idle_opt_for_cursor_updates = true
+	.exit_idle_opt_for_cursor_updates = true,
+	.enable_legacy_fast_update = false,
 };
 
 static const struct dc_panel_config panel_config_defaults = {
@@ -1986,11 +1987,10 @@ bool dcn30_can_support_mclk_switch_using_fw_based_vblank_stretch(struct dc *dc,
 	if (!is_refresh_rate_support_mclk_switch_using_fw_based_vblank_stretch(context))
 		return false;
 
-	// check if freesync enabled
 	if (!context->streams[0]->allow_freesync)
 		return false;
 
-	if (context->streams[0]->vrr_active_variable)
+	if (context->streams[0]->vrr_active_variable && dc->debug.disable_fams_gaming)
 		return false;
 
 	context->streams[0]->fpo_in_use = true;
diff --git a/drivers/gpu/drm/amd/display/dc/dcn302/dcn302_resource.c b/drivers/gpu/drm/amd/display/dc/dcn302/dcn302_resource.c
index 7dc065ea247a..5ad6a22ee47d 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn302/dcn302_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn302/dcn302_resource.c
@@ -95,7 +95,8 @@ static const struct dc_debug_options debug_defaults_drv = {
 		.dwb_fi_phase = -1, // -1 = disable,
 		.dmub_command_table = true,
 		.use_max_lb = true,
-		.exit_idle_opt_for_cursor_updates = true
+		.exit_idle_opt_for_cursor_updates = true,
+		.enable_legacy_fast_update = false,
 };
 
 static const struct dc_panel_config panel_config_defaults = {
diff --git a/drivers/gpu/drm/amd/display/dc/dcn303/dcn303_resource.c b/drivers/gpu/drm/amd/display/dc/dcn303/dcn303_resource.c
index 6d9761395288..45956ef6f3f9 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn303/dcn303_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn303/dcn303_resource.c
@@ -1190,6 +1190,7 @@ static bool dcn303_resource_construct(
 
 	dc->caps.dp_hdmi21_pcon_support = true;
 
+	dc->config.dc_mode_clk_limit_support = true;
 	/* read VBIOS LTTPR caps */
 	if (ctx->dc_bios->funcs->get_lttpr_caps) {
 		enum bp_result bp_query_result;
diff --git a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_dccg.c b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_dccg.c
index cf23d7bc560a..0746ed31d1d1 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_dccg.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_dccg.c
@@ -332,7 +332,7 @@ static void dccg314_dpp_root_clock_control(
 {
 	struct dcn_dccg *dccg_dcn = TO_DCN_DCCG(dccg);
 
-	if (dccg->dpp_clock_gated[dpp_inst] == clock_on)
+	if (dccg->dpp_clock_gated[dpp_inst] != clock_on)
 		return;
 
 	if (clock_on) {
diff --git a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_hwseq.c
index 7a43f8868500..4d2820ffe468 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_hwseq.c
@@ -337,13 +337,14 @@ void dcn314_enable_power_gating_plane(struct dce_hwseq *hws, bool enable)
 		REG_SET(DC_IP_REQUEST_CNTL, 0, IP_REQUEST_EN, 0);
 }
 
-void dcn314_calculate_dccg_k1_k2_values(struct pipe_ctx *pipe_ctx, unsigned int *k1_div, unsigned int *k2_div)
+unsigned int dcn314_calculate_dccg_k1_k2_values(struct pipe_ctx *pipe_ctx, unsigned int *k1_div, unsigned int *k2_div)
 {
 	struct dc_stream_state *stream = pipe_ctx->stream;
+	unsigned int odm_combine_factor = 0;
 	bool two_pix_per_container = false;
 
 	two_pix_per_container = optc2_is_two_pixels_per_containter(&stream->timing);
-	get_odm_config(pipe_ctx, NULL);
+	odm_combine_factor = get_odm_config(pipe_ctx, NULL);
 
 	if (stream->ctx->dc->link_srv->dp_is_128b_132b_signal(pipe_ctx)) {
 		*k1_div = PIXEL_RATE_DIV_BY_1;
@@ -361,11 +362,15 @@ void dcn314_calculate_dccg_k1_k2_values(struct pipe_ctx *pipe_ctx, unsigned int
 		} else {
 			*k1_div = PIXEL_RATE_DIV_BY_1;
 			*k2_div = PIXEL_RATE_DIV_BY_4;
+			if (odm_combine_factor == 2)
+				*k2_div = PIXEL_RATE_DIV_BY_2;
 		}
 	}
 
 	if ((*k1_div == PIXEL_RATE_DIV_NA) && (*k2_div == PIXEL_RATE_DIV_NA))
 		ASSERT(false);
+
+	return odm_combine_factor;
 }
 
 void dcn314_set_pixels_per_cycle(struct pipe_ctx *pipe_ctx)
@@ -424,27 +429,6 @@ void dcn314_dpp_root_clock_control(struct dce_hwseq *hws, unsigned int dpp_inst,
 			hws->ctx->dc->res_pool->dccg, dpp_inst, clock_on);
 }
 
-void dcn314_hubp_pg_control(struct dce_hwseq *hws, unsigned int hubp_inst, bool power_on)
-{
-	struct dc_context *ctx = hws->ctx;
-	union dmub_rb_cmd cmd;
-
-	if (hws->ctx->dc->debug.disable_hubp_power_gate)
-		return;
-
-	PERF_TRACE();
-
-	memset(&cmd, 0, sizeof(cmd));
-	cmd.domain_control.header.type = DMUB_CMD__VBIOS;
-	cmd.domain_control.header.sub_type = DMUB_CMD__VBIOS_DOMAIN_CONTROL;
-	cmd.domain_control.header.payload_bytes = sizeof(cmd.domain_control.data);
-	cmd.domain_control.data.inst = hubp_inst;
-	cmd.domain_control.data.power_gate = !power_on;
-
-	dm_execute_dmub_cmd(ctx, &cmd, DM_DMUB_WAIT_TYPE_WAIT);
-
-	PERF_TRACE();
-}
 static void apply_symclk_on_tx_off_wa(struct dc_link *link)
 {
 	/* There are use cases where SYMCLK is referenced by OTG. For instance
diff --git a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_hwseq.h b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_hwseq.h
index 96035c75e0df..eafcc4ea6d24 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_hwseq.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_hwseq.h
@@ -37,14 +37,12 @@ void dcn314_dsc_pg_control(struct dce_hwseq *hws, unsigned int dsc_inst, bool po
 
 void dcn314_enable_power_gating_plane(struct dce_hwseq *hws, bool enable);
 
-void dcn314_calculate_dccg_k1_k2_values(struct pipe_ctx *pipe_ctx, unsigned int *k1_div, unsigned int *k2_div);
+unsigned int dcn314_calculate_dccg_k1_k2_values(struct pipe_ctx *pipe_ctx, unsigned int *k1_div, unsigned int *k2_div);
 
 void dcn314_set_pixels_per_cycle(struct pipe_ctx *pipe_ctx);
 
 void dcn314_resync_fifo_dccg_dio(struct dce_hwseq *hws, struct dc *dc, struct dc_state *context);
 
-void dcn314_hubp_pg_control(struct dce_hwseq *hws, unsigned int hubp_inst, bool power_on);
-
 void dcn314_dpp_root_clock_control(struct dce_hwseq *hws, unsigned int dpp_inst, bool clock_on);
 
 void dcn314_disable_link_output(struct dc_link *link, const struct link_resource *link_res, enum signal_type signal);
diff --git a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_init.c b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_init.c
index 86d6a514dec0..ca8fe55c33b8 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_init.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_init.c
@@ -139,7 +139,7 @@ static const struct hwseq_private_funcs dcn314_private_funcs = {
 	.plane_atomic_power_down = dcn10_plane_atomic_power_down,
 	.enable_power_gating_plane = dcn314_enable_power_gating_plane,
 	.dpp_root_clock_control = dcn314_dpp_root_clock_control,
-	.hubp_pg_control = dcn314_hubp_pg_control,
+	.hubp_pg_control = dcn31_hubp_pg_control,
 	.program_all_writeback_pipes_in_tree = dcn30_program_all_writeback_pipes_in_tree,
 	.update_odm = dcn314_update_odm,
 	.dsc_pg_control = dcn314_dsc_pg_control,
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 a840b008d660..6a9024aa3285 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c
@@ -1883,13 +1883,6 @@ static bool dcn314_resource_construct(
 	/* Use pipe context based otg sync logic */
 	dc->config.use_pipe_ctx_sync_logic = true;
 
-	/* Disable pipe power gating when unsupported */
-	if (ctx->asic_id.hw_internal_rev == 0x01 ||
-			ctx->asic_id.hw_internal_rev == 0x80) {
-		dc->debug.disable_dpp_power_gate = true;
-		dc->debug.disable_hubp_power_gate = true;
-	}
-
 	/* read VBIOS LTTPR caps */
 	{
 		if (ctx->dc_bios->funcs->get_lttpr_caps) {
@@ -1910,6 +1903,14 @@ static bool dcn314_resource_construct(
 		dc->debug = debug_defaults_drv;
 	else
 		dc->debug = debug_defaults_diags;
+
+	/* Disable pipe power gating */
+	dc->debug.disable_dpp_power_gate = true;
+	dc->debug.disable_hubp_power_gate = true;
+
+	/* Disable root clock optimization */
+	dc->debug.root_clock_optimization.u32All = 0;
+
 	// Init the vm_helper
 	if (dc->vm_helper)
 		vm_helper_init(dc->vm_helper, 16);
diff --git a/drivers/gpu/drm/amd/display/dc/dcn315/dcn315_resource.c b/drivers/gpu/drm/amd/display/dc/dcn315/dcn315_resource.c
index f1153941907e..df3a438abda8 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn315/dcn315_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn315/dcn315_resource.c
@@ -1610,7 +1610,7 @@ static int source_format_to_bpp (enum source_format_class SourcePixelFormat)
 {
 	if (SourcePixelFormat == dm_444_64)
 		return 8;
-	else if (SourcePixelFormat == dm_444_16 || SourcePixelFormat == dm_444_16)
+	else if (SourcePixelFormat == dm_444_16)
 		return 2;
 	else if (SourcePixelFormat == dm_444_8)
 		return 1;
diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hubp.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hubp.c
index 2d604f7ee782..ca5b4b28a664 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hubp.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hubp.c
@@ -179,6 +179,7 @@ static struct hubp_funcs dcn32_hubp_funcs = {
 	.hubp_setup_interdependent = hubp2_setup_interdependent,
 	.hubp_set_vm_system_aperture_settings = hubp3_set_vm_system_aperture_settings,
 	.set_blank = hubp2_set_blank,
+	.set_blank_regs = hubp2_set_blank_regs,
 	.dcc_control = hubp3_dcc_control,
 	.mem_program_viewport = min_set_viewport,
 	.set_cursor_attributes	= hubp32_cursor_set_attributes,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c
index c586468872e2..d52d5feeb311 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c
@@ -448,7 +448,7 @@ bool dcn32_set_mpc_shaper_3dlut(
 		if (stream->func_shaper->type == TF_TYPE_HWPWL)
 			shaper_lut = &stream->func_shaper->pwl;
 		else if (stream->func_shaper->type == TF_TYPE_DISTRIBUTED_POINTS) {
-			cm_helper_translate_curve_to_hw_format(
+			cm_helper_translate_curve_to_hw_format(stream->ctx,
 					stream->func_shaper,
 					&dpp_base->shaper_params, true);
 			shaper_lut = &dpp_base->shaper_params;
@@ -484,7 +484,7 @@ 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(
+			cm_helper_translate_curve_to_hw_format(plane_state->ctx,
 					plane_state->blend_tf,
 					&dpp_base->regamma_params, false);
 			lut_params = &dpp_base->regamma_params;
@@ -499,7 +499,7 @@ 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(
+			cm_helper_translate_curve_to_hw_format(plane_state->ctx,
 					plane_state->in_shaper_func,
 					&dpp_base->shaper_params, true);
 			lut_params = &dpp_base->shaper_params;
@@ -1141,16 +1141,14 @@ void dcn32_update_odm(struct dc *dc, struct dc_state *context, struct pipe_ctx *
 	}
 }
 
-void dcn32_calculate_dccg_k1_k2_values(struct pipe_ctx *pipe_ctx, unsigned int *k1_div, unsigned int *k2_div)
+unsigned int dcn32_calculate_dccg_k1_k2_values(struct pipe_ctx *pipe_ctx, unsigned int *k1_div, unsigned int *k2_div)
 {
 	struct dc_stream_state *stream = pipe_ctx->stream;
+	unsigned int odm_combine_factor = 0;
 	bool two_pix_per_container = false;
 
-	// For phantom pipes, use the same programming as the main pipes
-	if (pipe_ctx->stream->mall_stream_config.type == SUBVP_PHANTOM) {
-		stream = pipe_ctx->stream->mall_stream_config.paired_stream;
-	}
 	two_pix_per_container = optc2_is_two_pixels_per_containter(&stream->timing);
+	odm_combine_factor = get_odm_config(pipe_ctx, NULL);
 
 	if (stream->ctx->dc->link_srv->dp_is_128b_132b_signal(pipe_ctx)) {
 		*k1_div = PIXEL_RATE_DIV_BY_1;
@@ -1168,13 +1166,15 @@ void dcn32_calculate_dccg_k1_k2_values(struct pipe_ctx *pipe_ctx, unsigned int *
 		} else {
 			*k1_div = PIXEL_RATE_DIV_BY_1;
 			*k2_div = PIXEL_RATE_DIV_BY_4;
-			if (dcn32_is_dp_dig_pixel_rate_div_policy(pipe_ctx))
+			if ((odm_combine_factor == 2) || dcn32_is_dp_dig_pixel_rate_div_policy(pipe_ctx))
 				*k2_div = PIXEL_RATE_DIV_BY_2;
 		}
 	}
 
 	if ((*k1_div == PIXEL_RATE_DIV_NA) && (*k2_div == PIXEL_RATE_DIV_NA))
 		ASSERT(false);
+
+	return odm_combine_factor;
 }
 
 void dcn32_set_pixels_per_cycle(struct pipe_ctx *pipe_ctx)
diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.h b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.h
index bf9bffabe0c0..2d2628f31bed 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.h
@@ -71,7 +71,7 @@ void dcn32_update_force_pstate(struct dc *dc, struct dc_state *context);
 
 void dcn32_update_odm(struct dc *dc, struct dc_state *context, struct pipe_ctx *pipe_ctx);
 
-void dcn32_calculate_dccg_k1_k2_values(struct pipe_ctx *pipe_ctx, unsigned int *k1_div, unsigned int *k2_div);
+unsigned int dcn32_calculate_dccg_k1_k2_values(struct pipe_ctx *pipe_ctx, unsigned int *k1_div, unsigned int *k2_div);
 
 void dcn32_set_pixels_per_cycle(struct pipe_ctx *pipe_ctx);
 
diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_init.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_init.c
index c2490e16a66a..777b2fac20c4 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_init.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_init.c
@@ -56,6 +56,7 @@ static const struct hw_sequencer_funcs dcn32_funcs = {
 	.enable_audio_stream = dce110_enable_audio_stream,
 	.disable_audio_stream = dce110_disable_audio_stream,
 	.disable_plane = dcn20_disable_plane,
+	.disable_pixel_data = dcn20_disable_pixel_data,
 	.pipe_control_lock = dcn20_pipe_control_lock,
 	.interdependent_update_lock = dcn10_lock_all_pipes,
 	.cursor_lock = dcn10_cursor_lock,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c
index 19f134caa8ad..1cc09799f92d 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c
@@ -732,6 +732,7 @@ static const struct dc_debug_options debug_defaults_drv = {
 	.disable_dp_plus_plus_wa = true,
 	.fpo_vactive_min_active_margin_us = 200,
 	.fpo_vactive_max_blank_us = 1000,
+	.enable_legacy_fast_update = false,
 };
 
 static struct dce_aux *dcn32_aux_engine_create(
@@ -2214,6 +2215,7 @@ static bool dcn32_resource_construct(
 	/* Use pipe context based otg sync logic */
 	dc->config.use_pipe_ctx_sync_logic = true;
 
+	dc->config.dc_mode_clk_limit_support = true;
 	/* read VBIOS LTTPR caps */
 	{
 		if (ctx->dc_bios->funcs->get_lttpr_caps) {
diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource_helpers.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource_helpers.c
index a9c41ef0751f..5be242a1b82c 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource_helpers.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource_helpers.c
@@ -595,11 +595,10 @@ struct dc_stream_state *dcn32_can_support_mclk_switch_using_fw_based_vblank_stre
 	if (!is_refresh_rate_support_mclk_switch_using_fw_based_vblank_stretch(fpo_candidate_stream, fpo_vactive_margin_us))
 		return NULL;
 
-	// check if freesync enabled
 	if (!fpo_candidate_stream->allow_freesync)
 		return NULL;
 
-	if (fpo_candidate_stream->vrr_active_variable)
+	if (fpo_candidate_stream->vrr_active_variable && dc->debug.disable_fams_gaming)
 		return NULL;
 
 	return fpo_candidate_stream;
diff --git a/drivers/gpu/drm/amd/display/dc/dcn321/dcn321_resource.c b/drivers/gpu/drm/amd/display/dc/dcn321/dcn321_resource.c
index ea204742ad35..a53478e15ce3 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn321/dcn321_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn321/dcn321_resource.c
@@ -730,6 +730,8 @@ static const struct dc_debug_options debug_defaults_drv = {
 	.disable_subvp_high_refresh = false,
 	.fpo_vactive_min_active_margin_us = 200,
 	.fpo_vactive_max_blank_us = 1000,
+	.enable_legacy_fast_update = false,
+	.disable_dc_mode_overwrite = true,
 };
 
 static struct dce_aux *dcn321_aux_engine_create(
@@ -1754,6 +1756,7 @@ static bool dcn321_resource_construct(
 	dc->caps.color.mpc.ogam_rom_caps.hlg = 0;
 	dc->caps.color.mpc.ocsc = 1;
 
+	dc->config.dc_mode_clk_limit_support = true;
 	/* read VBIOS LTTPR caps */
 	{
 		if (ctx->dc_bios->funcs->get_lttpr_caps) {
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_mode_vba_20.c b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_mode_vba_20.c
index 6266b0788387..7bf4bb7ad044 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_mode_vba_20.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_mode_vba_20.c
@@ -4356,12 +4356,16 @@ void dml20_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 						locals->PSCL_FACTOR[k] / locals->ReturnBWPerState[i][0],
 						locals->EffectiveLBLatencyHidingSourceLinesLuma),
 						locals->SwathHeightYPerState[i][j][k]);
-
-				locals->EffectiveDETLBLinesChroma = dml_floor(locals->LinesInDETChroma + dml_min(
-						locals->LinesInDETChroma * locals->RequiredDISPCLK[i][j] * locals->BytePerPixelInDETC[k] *
-						locals->PSCL_FACTOR_CHROMA[k] / locals->ReturnBWPerState[i][0],
-						locals->EffectiveLBLatencyHidingSourceLinesChroma),
-						locals->SwathHeightCPerState[i][j][k]);
+				if (locals->LinesInDETChroma) {
+					locals->EffectiveDETLBLinesChroma = dml_floor(locals->LinesInDETChroma +
+						    dml_min(locals->LinesInDETChroma * locals->RequiredDISPCLK[i][j] *
+						    locals->BytePerPixelInDETC[k] *
+							locals->PSCL_FACTOR_CHROMA[k] / locals->ReturnBWPerState[i][0],
+							locals->EffectiveLBLatencyHidingSourceLinesChroma),
+							locals->SwathHeightCPerState[i][j][k]);
+				} else {
+					locals->EffectiveDETLBLinesChroma = 0;
+				}
 
 				if (locals->BytePerPixelInDETC[k] == 0) {
 					locals->UrgentLatencySupportUsPerState[i][j][k] = locals->EffectiveDETLBLinesLuma * (locals->HTotal[k] / locals->PixelClock[k])
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn314/dcn314_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn314/dcn314_fpu.c
index c9afddd11589..d9e049e7ff0a 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn314/dcn314_fpu.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn314/dcn314_fpu.c
@@ -33,7 +33,7 @@
 #include "dml/display_mode_vba.h"
 
 struct _vcs_dpi_ip_params_st dcn3_14_ip = {
-	.VBlankNomDefaultUS = 800,
+	.VBlankNomDefaultUS = 668,
 	.gpuvm_enable = 1,
 	.gpuvm_max_page_table_levels = 1,
 	.hostvm_enable = 1,
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 e2bb2b9971f3..a95034801712 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
@@ -485,24 +485,20 @@ static void get_optimal_ntuple(struct _vcs_dpi_voltage_scaling_st *entry)
 	}
 }
 
-void insert_entry_into_table_sorted(struct _vcs_dpi_voltage_scaling_st *table,
+static void insert_entry_into_table_sorted(struct _vcs_dpi_voltage_scaling_st *table,
 				    unsigned int *num_entries,
 				    struct _vcs_dpi_voltage_scaling_st *entry)
 {
 	int i = 0;
 	int index = 0;
-	float net_bw_of_new_state = 0;
 
 	dc_assert_fp_enabled();
 
-	get_optimal_ntuple(entry);
-
 	if (*num_entries == 0) {
 		table[0] = *entry;
 		(*num_entries)++;
 	} else {
-		net_bw_of_new_state = calculate_net_bw_in_kbytes_sec(entry);
-		while (net_bw_of_new_state > calculate_net_bw_in_kbytes_sec(&table[index])) {
+		while (entry->net_bw_in_kbytes_sec > table[index].net_bw_in_kbytes_sec) {
 			index++;
 			if (index >= *num_entries)
 				break;
@@ -2349,6 +2345,63 @@ void dcn32_patch_dpm_table(struct clk_bw_params *bw_params)
 		bw_params->clk_table.entries[0].memclk_mhz = dcn3_2_soc.clock_limits[0].dram_speed_mts / 16;
 }
 
+static void swap_table_entries(struct _vcs_dpi_voltage_scaling_st *first_entry,
+		struct _vcs_dpi_voltage_scaling_st *second_entry)
+{
+	struct _vcs_dpi_voltage_scaling_st temp_entry = *first_entry;
+	*first_entry = *second_entry;
+	*second_entry = temp_entry;
+}
+
+/*
+ * sort_entries_with_same_bw - Sort entries sharing the same bandwidth by DCFCLK
+ */
+static void sort_entries_with_same_bw(struct _vcs_dpi_voltage_scaling_st *table, unsigned int *num_entries)
+{
+	unsigned int start_index = 0;
+	unsigned int end_index = 0;
+	unsigned int current_bw = 0;
+
+	for (int i = 0; i < (*num_entries - 1); i++) {
+		if (table[i].net_bw_in_kbytes_sec == table[i+1].net_bw_in_kbytes_sec) {
+			current_bw = table[i].net_bw_in_kbytes_sec;
+			start_index = i;
+			end_index = ++i;
+
+			while ((i < (*num_entries - 1)) && (table[i+1].net_bw_in_kbytes_sec == current_bw))
+				end_index = ++i;
+		}
+
+		if (start_index != end_index) {
+			for (int j = start_index; j < end_index; j++) {
+				for (int k = start_index; k < end_index; k++) {
+					if (table[k].dcfclk_mhz > table[k+1].dcfclk_mhz)
+						swap_table_entries(&table[k], &table[k+1]);
+				}
+			}
+		}
+
+		start_index = 0;
+		end_index = 0;
+
+	}
+}
+
+/*
+ * remove_inconsistent_entries - Ensure entries with the same bandwidth have MEMCLK and FCLK monotonically increasing
+ *                               and remove entries that do not
+ */
+static void remove_inconsistent_entries(struct _vcs_dpi_voltage_scaling_st *table, unsigned int *num_entries)
+{
+	for (int i = 0; i < (*num_entries - 1); i++) {
+		if (table[i].net_bw_in_kbytes_sec == table[i+1].net_bw_in_kbytes_sec) {
+			if ((table[i].dram_speed_mts > table[i+1].dram_speed_mts) ||
+				(table[i].fabricclk_mhz > table[i+1].fabricclk_mhz))
+				remove_entry_from_table_at_index(table, num_entries, i);
+		}
+	}
+}
+
 /*
  * override_max_clk_values - Overwrite the max clock frequencies with the max DC mode timings
  * Input:
@@ -2480,6 +2533,8 @@ static int build_synthetic_soc_states(bool disable_dc_mode_overwrite, struct clk
 		entry.fabricclk_mhz = 0;
 		entry.dram_speed_mts = 0;
 
+		get_optimal_ntuple(&entry);
+		entry.net_bw_in_kbytes_sec = calculate_net_bw_in_kbytes_sec(&entry);
 		insert_entry_into_table_sorted(table, num_entries, &entry);
 	}
 
@@ -2488,6 +2543,8 @@ static int build_synthetic_soc_states(bool disable_dc_mode_overwrite, struct clk
 	entry.fabricclk_mhz = 0;
 	entry.dram_speed_mts = 0;
 
+	get_optimal_ntuple(&entry);
+	entry.net_bw_in_kbytes_sec = calculate_net_bw_in_kbytes_sec(&entry);
 	insert_entry_into_table_sorted(table, num_entries, &entry);
 
 	// Insert the UCLK DPMS
@@ -2496,6 +2553,8 @@ static int build_synthetic_soc_states(bool disable_dc_mode_overwrite, struct clk
 		entry.fabricclk_mhz = 0;
 		entry.dram_speed_mts = bw_params->clk_table.entries[i].memclk_mhz * 16;
 
+		get_optimal_ntuple(&entry);
+		entry.net_bw_in_kbytes_sec = calculate_net_bw_in_kbytes_sec(&entry);
 		insert_entry_into_table_sorted(table, num_entries, &entry);
 	}
 
@@ -2506,6 +2565,8 @@ static int build_synthetic_soc_states(bool disable_dc_mode_overwrite, struct clk
 			entry.fabricclk_mhz = bw_params->clk_table.entries[i].fclk_mhz;
 			entry.dram_speed_mts = 0;
 
+			get_optimal_ntuple(&entry);
+			entry.net_bw_in_kbytes_sec = calculate_net_bw_in_kbytes_sec(&entry);
 			insert_entry_into_table_sorted(table, num_entries, &entry);
 		}
 	}
@@ -2515,6 +2576,8 @@ static int build_synthetic_soc_states(bool disable_dc_mode_overwrite, struct clk
 		entry.fabricclk_mhz = max_clk_data.fclk_mhz;
 		entry.dram_speed_mts = 0;
 
+		get_optimal_ntuple(&entry);
+		entry.net_bw_in_kbytes_sec = calculate_net_bw_in_kbytes_sec(&entry);
 		insert_entry_into_table_sorted(table, num_entries, &entry);
 	}
 
@@ -2530,6 +2593,21 @@ static int build_synthetic_soc_states(bool disable_dc_mode_overwrite, struct clk
 			remove_entry_from_table_at_index(table, num_entries, i);
 	}
 
+	// Insert entry with all max dc limits without bandwidth matching
+	if (!disable_dc_mode_overwrite) {
+		struct _vcs_dpi_voltage_scaling_st max_dc_limits_entry = entry;
+
+		max_dc_limits_entry.dcfclk_mhz = max_clk_data.dcfclk_mhz;
+		max_dc_limits_entry.fabricclk_mhz = max_clk_data.fclk_mhz;
+		max_dc_limits_entry.dram_speed_mts = max_clk_data.memclk_mhz * 16;
+
+		max_dc_limits_entry.net_bw_in_kbytes_sec = calculate_net_bw_in_kbytes_sec(&max_dc_limits_entry);
+		insert_entry_into_table_sorted(table, num_entries, &max_dc_limits_entry);
+
+		sort_entries_with_same_bw(table, num_entries);
+		remove_inconsistent_entries(table, num_entries);
+	}
+
 	// At this point, the table only contains supported points of interest
 	// it could be used as is, but some states may be redundant due to
 	// coarse grained nature of some clocks, so we want to round up to
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.h b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.h
index a4206b71d650..defbee866be6 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.h
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.h
@@ -39,10 +39,6 @@ void dcn32_helper_populate_phantom_dlg_params(struct dc *dc,
 uint8_t dcn32_predict_pipe_split(struct dc_state *context,
 				  display_e2e_pipe_params_st *pipe_e2e);
 
-void insert_entry_into_table_sorted(struct _vcs_dpi_voltage_scaling_st *table,
-				    unsigned int *num_entries,
-				    struct _vcs_dpi_voltage_scaling_st *entry);
-
 void dcn32_set_phantom_stream_timing(struct dc *dc,
 				     struct dc_state *context,
 				     struct pipe_ctx *ref_pipe,
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn321/dcn321_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn321/dcn321_fpu.c
index f0683fd9d3f0..b26fcf86014c 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn321/dcn321_fpu.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn321/dcn321_fpu.c
@@ -207,24 +207,20 @@ static float calculate_net_bw_in_kbytes_sec(struct _vcs_dpi_voltage_scaling_st *
 	return limiting_bw_kbytes_sec;
 }
 
-void dcn321_insert_entry_into_table_sorted(struct _vcs_dpi_voltage_scaling_st *table,
+static void dcn321_insert_entry_into_table_sorted(struct _vcs_dpi_voltage_scaling_st *table,
 					   unsigned int *num_entries,
 					   struct _vcs_dpi_voltage_scaling_st *entry)
 {
 	int i = 0;
 	int index = 0;
-	float net_bw_of_new_state = 0;
 
 	dc_assert_fp_enabled();
 
-	get_optimal_ntuple(entry);
-
 	if (*num_entries == 0) {
 		table[0] = *entry;
 		(*num_entries)++;
 	} else {
-		net_bw_of_new_state = calculate_net_bw_in_kbytes_sec(entry);
-		while (net_bw_of_new_state > calculate_net_bw_in_kbytes_sec(&table[index])) {
+		while (entry->net_bw_in_kbytes_sec > table[index].net_bw_in_kbytes_sec) {
 			index++;
 			if (index >= *num_entries)
 				break;
@@ -252,6 +248,63 @@ static void remove_entry_from_table_at_index(struct _vcs_dpi_voltage_scaling_st
 	memset(&table[--(*num_entries)], 0, sizeof(struct _vcs_dpi_voltage_scaling_st));
 }
 
+static void swap_table_entries(struct _vcs_dpi_voltage_scaling_st *first_entry,
+		struct _vcs_dpi_voltage_scaling_st *second_entry)
+{
+	struct _vcs_dpi_voltage_scaling_st temp_entry = *first_entry;
+	*first_entry = *second_entry;
+	*second_entry = temp_entry;
+}
+
+/*
+ * sort_entries_with_same_bw - Sort entries sharing the same bandwidth by DCFCLK
+ */
+static void sort_entries_with_same_bw(struct _vcs_dpi_voltage_scaling_st *table, unsigned int *num_entries)
+{
+	unsigned int start_index = 0;
+	unsigned int end_index = 0;
+	unsigned int current_bw = 0;
+
+	for (int i = 0; i < (*num_entries - 1); i++) {
+		if (table[i].net_bw_in_kbytes_sec == table[i+1].net_bw_in_kbytes_sec) {
+			current_bw = table[i].net_bw_in_kbytes_sec;
+			start_index = i;
+			end_index = ++i;
+
+			while ((i < (*num_entries - 1)) && (table[i+1].net_bw_in_kbytes_sec == current_bw))
+				end_index = ++i;
+		}
+
+		if (start_index != end_index) {
+			for (int j = start_index; j < end_index; j++) {
+				for (int k = start_index; k < end_index; k++) {
+					if (table[k].dcfclk_mhz > table[k+1].dcfclk_mhz)
+						swap_table_entries(&table[k], &table[k+1]);
+				}
+			}
+		}
+
+		start_index = 0;
+		end_index = 0;
+
+	}
+}
+
+/*
+ * remove_inconsistent_entries - Ensure entries with the same bandwidth have MEMCLK and FCLK monotonically increasing
+ *                               and remove entries that do not follow this order
+ */
+static void remove_inconsistent_entries(struct _vcs_dpi_voltage_scaling_st *table, unsigned int *num_entries)
+{
+	for (int i = 0; i < (*num_entries - 1); i++) {
+		if (table[i].net_bw_in_kbytes_sec == table[i+1].net_bw_in_kbytes_sec) {
+			if ((table[i].dram_speed_mts > table[i+1].dram_speed_mts) ||
+				(table[i].fabricclk_mhz > table[i+1].fabricclk_mhz))
+				remove_entry_from_table_at_index(table, num_entries, i);
+		}
+	}
+}
+
 /*
  * override_max_clk_values - Overwrite the max clock frequencies with the max DC mode timings
  * Input:
@@ -362,11 +415,11 @@ static int build_synthetic_soc_states(bool disable_dc_mode_overwrite, struct clk
 
 	if (max_clk_data.fclk_mhz == 0)
 		max_clk_data.fclk_mhz = max_clk_data.dcfclk_mhz *
-				dcn3_2_soc.pct_ideal_sdp_bw_after_urgent /
-				dcn3_2_soc.pct_ideal_fabric_bw_after_urgent;
+				dcn3_21_soc.pct_ideal_sdp_bw_after_urgent /
+				dcn3_21_soc.pct_ideal_fabric_bw_after_urgent;
 
 	if (max_clk_data.phyclk_mhz == 0)
-		max_clk_data.phyclk_mhz = dcn3_2_soc.clock_limits[0].phyclk_mhz;
+		max_clk_data.phyclk_mhz = dcn3_21_soc.clock_limits[0].phyclk_mhz;
 
 	*num_entries = 0;
 	entry.dispclk_mhz = max_clk_data.dispclk_mhz;
@@ -374,8 +427,8 @@ static int build_synthetic_soc_states(bool disable_dc_mode_overwrite, struct clk
 	entry.dppclk_mhz = max_clk_data.dppclk_mhz;
 	entry.dtbclk_mhz = max_clk_data.dtbclk_mhz;
 	entry.phyclk_mhz = max_clk_data.phyclk_mhz;
-	entry.phyclk_d18_mhz = dcn3_2_soc.clock_limits[0].phyclk_d18_mhz;
-	entry.phyclk_d32_mhz = dcn3_2_soc.clock_limits[0].phyclk_d32_mhz;
+	entry.phyclk_d18_mhz = dcn3_21_soc.clock_limits[0].phyclk_d18_mhz;
+	entry.phyclk_d32_mhz = dcn3_21_soc.clock_limits[0].phyclk_d32_mhz;
 
 	// Insert all the DCFCLK STAs
 	for (i = 0; i < num_dcfclk_stas; i++) {
@@ -383,6 +436,8 @@ static int build_synthetic_soc_states(bool disable_dc_mode_overwrite, struct clk
 		entry.fabricclk_mhz = 0;
 		entry.dram_speed_mts = 0;
 
+		get_optimal_ntuple(&entry);
+		entry.net_bw_in_kbytes_sec = calculate_net_bw_in_kbytes_sec(&entry);
 		dcn321_insert_entry_into_table_sorted(table, num_entries, &entry);
 	}
 
@@ -391,6 +446,8 @@ static int build_synthetic_soc_states(bool disable_dc_mode_overwrite, struct clk
 	entry.fabricclk_mhz = 0;
 	entry.dram_speed_mts = 0;
 
+	get_optimal_ntuple(&entry);
+	entry.net_bw_in_kbytes_sec = calculate_net_bw_in_kbytes_sec(&entry);
 	dcn321_insert_entry_into_table_sorted(table, num_entries, &entry);
 
 	// Insert the UCLK DPMS
@@ -399,6 +456,8 @@ static int build_synthetic_soc_states(bool disable_dc_mode_overwrite, struct clk
 		entry.fabricclk_mhz = 0;
 		entry.dram_speed_mts = bw_params->clk_table.entries[i].memclk_mhz * 16;
 
+		get_optimal_ntuple(&entry);
+		entry.net_bw_in_kbytes_sec = calculate_net_bw_in_kbytes_sec(&entry);
 		dcn321_insert_entry_into_table_sorted(table, num_entries, &entry);
 	}
 
@@ -409,6 +468,8 @@ static int build_synthetic_soc_states(bool disable_dc_mode_overwrite, struct clk
 			entry.fabricclk_mhz = bw_params->clk_table.entries[i].fclk_mhz;
 			entry.dram_speed_mts = 0;
 
+			get_optimal_ntuple(&entry);
+			entry.net_bw_in_kbytes_sec = calculate_net_bw_in_kbytes_sec(&entry);
 			dcn321_insert_entry_into_table_sorted(table, num_entries, &entry);
 		}
 	}
@@ -418,6 +479,8 @@ static int build_synthetic_soc_states(bool disable_dc_mode_overwrite, struct clk
 		entry.fabricclk_mhz = max_clk_data.fclk_mhz;
 		entry.dram_speed_mts = 0;
 
+		get_optimal_ntuple(&entry);
+		entry.net_bw_in_kbytes_sec = calculate_net_bw_in_kbytes_sec(&entry);
 		dcn321_insert_entry_into_table_sorted(table, num_entries, &entry);
 	}
 
@@ -433,6 +496,23 @@ static int build_synthetic_soc_states(bool disable_dc_mode_overwrite, struct clk
 			remove_entry_from_table_at_index(table, num_entries, i);
 	}
 
+	// Insert entry with all max dc limits without bandwitch matching
+	if (!disable_dc_mode_overwrite) {
+		struct _vcs_dpi_voltage_scaling_st max_dc_limits_entry = entry;
+
+		max_dc_limits_entry.dcfclk_mhz = max_clk_data.dcfclk_mhz;
+		max_dc_limits_entry.fabricclk_mhz = max_clk_data.fclk_mhz;
+		max_dc_limits_entry.dram_speed_mts = max_clk_data.memclk_mhz * 16;
+
+		max_dc_limits_entry.net_bw_in_kbytes_sec = calculate_net_bw_in_kbytes_sec(&max_dc_limits_entry);
+		dcn321_insert_entry_into_table_sorted(table, num_entries, &max_dc_limits_entry);
+
+		sort_entries_with_same_bw(table, num_entries);
+		remove_inconsistent_entries(table, num_entries);
+	}
+
+
+
 	// At this point, the table only contains supported points of interest
 	// it could be used as is, but some states may be redundant due to
 	// coarse grained nature of some clocks, so we want to round up to
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn321/dcn321_fpu.h b/drivers/gpu/drm/amd/display/dc/dml/dcn321/dcn321_fpu.h
index e8fad9b4be69..c6623b3705ca 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn321/dcn321_fpu.h
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn321/dcn321_fpu.h
@@ -29,10 +29,6 @@
 
 #include "dml/display_mode_vba.h"
 
-void dcn321_insert_entry_into_table_sorted(struct _vcs_dpi_voltage_scaling_st *table,
-					   unsigned int *num_entries,
-					   struct _vcs_dpi_voltage_scaling_st *entry);
-
 void dcn321_update_bw_bounding_box_fpu(struct dc *dc, struct clk_bw_params *bw_params);
 
 #endif
diff --git a/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h b/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h
index ff0246a9458f..fb17f8868cb4 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h
+++ b/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h
@@ -167,6 +167,7 @@ struct _vcs_dpi_voltage_scaling_st {
 	double phyclk_mhz;
 	double dppclk_mhz;
 	double dtbclk_mhz;
+	float net_bw_in_kbytes_sec;
 };
 
 /**
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr.h b/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr.h
index 6faf40fa5c69..ecb7bcc39469 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr.h
@@ -230,6 +230,7 @@ struct clk_bw_params {
 	unsigned int dram_channel_width_bytes;
  	unsigned int dispclk_vco_khz;
 	unsigned int dc_mode_softmax_memclk;
+	unsigned int max_memclk_mhz;
 	struct clk_limit_table clk_table;
 	struct wm_table wm_table;
 	struct dummy_pstate_entry dummy_pstate_table[4];
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer_private.h b/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer_private.h
index a151865a3a20..4ca4192c1e12 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer_private.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer_private.h
@@ -156,7 +156,7 @@ struct hwseq_private_funcs {
 	void (*program_mall_pipe_config)(struct dc *dc, struct dc_state *context);
 	void (*update_force_pstate)(struct dc *dc, struct dc_state *context);
 	void (*update_mall_sel)(struct dc *dc, struct dc_state *context);
-	void (*calculate_dccg_k1_k2_values)(struct pipe_ctx *pipe_ctx,
+	unsigned int (*calculate_dccg_k1_k2_values)(struct pipe_ctx *pipe_ctx,
 			unsigned int *k1_div,
 			unsigned int *k2_div);
 	void (*set_pixels_per_cycle)(struct pipe_ctx *pipe_ctx);
diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_irq_handler.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_irq_handler.c
index ba95facc4ee8..ef8739df91bc 100644
--- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_irq_handler.c
+++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_irq_handler.c
@@ -82,8 +82,15 @@ bool dp_parse_link_loss_status(
 	}
 
 	/* Check interlane align.*/
-	if (sink_status_changed ||
-		!hpd_irq_dpcd_data->bytes.lane_status_updated.bits.INTERLANE_ALIGN_DONE) {
+	if (link_dp_get_encoding_format(&link->cur_link_settings) == DP_128b_132b_ENCODING &&
+			(!hpd_irq_dpcd_data->bytes.lane_status_updated.bits.EQ_INTERLANE_ALIGN_DONE_128b_132b ||
+			 !hpd_irq_dpcd_data->bytes.lane_status_updated.bits.CDS_INTERLANE_ALIGN_DONE_128b_132b)) {
+		sink_status_changed = true;
+	} else if (!hpd_irq_dpcd_data->bytes.lane_status_updated.bits.INTERLANE_ALIGN_DONE) {
+		sink_status_changed = true;
+	}
+
+	if (sink_status_changed) {
 
 		DC_LOG_HW_HPD_IRQ("%s: Link Status changed.\n", __func__);
 
@@ -201,6 +208,25 @@ void dp_handle_link_loss(struct dc_link *link)
 	}
 }
 
+static void read_dpcd204h_on_irq_hpd(struct dc_link *link, union hpd_irq_data *irq_data)
+{
+	enum dc_status retval;
+	union lane_align_status_updated dpcd_lane_status_updated;
+
+	retval = core_link_read_dpcd(
+			link,
+			DP_LANE_ALIGN_STATUS_UPDATED,
+			&dpcd_lane_status_updated.raw,
+			sizeof(union lane_align_status_updated));
+
+	if (retval == DC_OK) {
+		irq_data->bytes.lane_status_updated.bits.EQ_INTERLANE_ALIGN_DONE_128b_132b =
+				dpcd_lane_status_updated.bits.EQ_INTERLANE_ALIGN_DONE_128b_132b;
+		irq_data->bytes.lane_status_updated.bits.CDS_INTERLANE_ALIGN_DONE_128b_132b =
+				dpcd_lane_status_updated.bits.CDS_INTERLANE_ALIGN_DONE_128b_132b;
+	}
+}
+
 enum dc_status dp_read_hpd_rx_irq_data(
 	struct dc_link *link,
 	union hpd_irq_data *irq_data)
@@ -242,6 +268,13 @@ enum dc_status dp_read_hpd_rx_irq_data(
 		irq_data->bytes.lane23_status.raw = tmp[DP_LANE2_3_STATUS_ESI - DP_SINK_COUNT_ESI];
 		irq_data->bytes.lane_status_updated.raw = tmp[DP_LANE_ALIGN_STATUS_UPDATED_ESI - DP_SINK_COUNT_ESI];
 		irq_data->bytes.sink_status.raw = tmp[DP_SINK_STATUS_ESI - DP_SINK_COUNT_ESI];
+
+		/*
+		 * This display doesn't have correct values in DPCD200Eh.
+		 * Read and check DPCD204h instead.
+		 */
+		if (link->wa_flags.read_dpcd204h_on_irq_hpd)
+			read_dpcd204h_on_irq_hpd(link, irq_data);
 	}
 
 	return retval;
diff --git a/drivers/gpu/drm/amd/display/dmub/dmub_srv.h b/drivers/gpu/drm/amd/display/dmub/dmub_srv.h
index 7c9a2b34bd05..4585e0419da6 100644
--- a/drivers/gpu/drm/amd/display/dmub/dmub_srv.h
+++ b/drivers/gpu/drm/amd/display/dmub/dmub_srv.h
@@ -367,6 +367,8 @@ struct dmub_srv_hw_funcs {
 
 	bool (*is_supported)(struct dmub_srv *dmub);
 
+	bool (*is_psrsu_supported)(struct dmub_srv *dmub);
+
 	bool (*is_hw_init)(struct dmub_srv *dmub);
 
 	void (*enable_dmub_boot_options)(struct dmub_srv *dmub,
@@ -492,7 +494,7 @@ struct dmub_notification {
  * of a firmware to know if feature or functionality is supported or present.
  */
 #define DMUB_FW_VERSION(major, minor, revision) \
-	((((major) & 0xFF) << 24) | (((minor) & 0xFF) << 16) | ((revision) & 0xFFFF))
+	((((major) & 0xFF) << 24) | (((minor) & 0xFF) << 16) | (((revision) & 0xFF) << 8))
 
 /**
  * dmub_srv_create() - creates the DMUB service.
diff --git a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn31.c b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn31.c
index ebf7aeec4029..5e952541e72d 100644
--- a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn31.c
+++ b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn31.c
@@ -302,6 +302,11 @@ bool dmub_dcn31_is_supported(struct dmub_srv *dmub)
 	return supported;
 }
 
+bool dmub_dcn31_is_psrsu_supported(struct dmub_srv *dmub)
+{
+	return dmub->fw_version >= DMUB_FW_VERSION(4, 0, 59);
+}
+
 void dmub_dcn31_set_gpint(struct dmub_srv *dmub,
 			  union dmub_gpint_data_register reg)
 {
diff --git a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn31.h b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn31.h
index 7d5c10ee539b..89c5a948b67d 100644
--- a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn31.h
+++ b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn31.h
@@ -221,6 +221,8 @@ bool dmub_dcn31_is_hw_init(struct dmub_srv *dmub);
 
 bool dmub_dcn31_is_supported(struct dmub_srv *dmub);
 
+bool dmub_dcn31_is_psrsu_supported(struct dmub_srv *dmub);
+
 void dmub_dcn31_set_gpint(struct dmub_srv *dmub,
 			  union dmub_gpint_data_register reg);
 
diff --git a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn314.c b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn314.c
index 48a06dbd9be7..f161aeb7e7c4 100644
--- a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn314.c
+++ b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn314.c
@@ -60,3 +60,8 @@ const struct dmub_srv_dcn31_regs dmub_srv_dcn314_regs = {
 	{ DMUB_DCN31_FIELDS() },
 #undef DMUB_SF
 };
+
+bool dmub_dcn314_is_psrsu_supported(struct dmub_srv *dmub)
+{
+	return dmub->fw_version >= DMUB_FW_VERSION(8, 0, 16);
+}
diff --git a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn314.h b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn314.h
index 674267a2940e..f213bd82c911 100644
--- a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn314.h
+++ b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn314.h
@@ -30,4 +30,6 @@
 
 extern const struct dmub_srv_dcn31_regs dmub_srv_dcn314_regs;
 
+bool dmub_dcn314_is_psrsu_supported(struct dmub_srv *dmub);
+
 #endif /* _DMUB_DCN314_H_ */
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 9e9a6a44a7ac..bdaf43892f47 100644
--- a/drivers/gpu/drm/amd/display/dmub/src/dmub_srv.c
+++ b/drivers/gpu/drm/amd/display/dmub/src/dmub_srv.c
@@ -226,14 +226,17 @@ static bool dmub_srv_hw_setup(struct dmub_srv *dmub, enum dmub_asic asic)
 	case DMUB_ASIC_DCN314:
 	case DMUB_ASIC_DCN315:
 	case DMUB_ASIC_DCN316:
-		if (asic == DMUB_ASIC_DCN314)
+		if (asic == DMUB_ASIC_DCN314) {
 			dmub->regs_dcn31 = &dmub_srv_dcn314_regs;
-		else if (asic == DMUB_ASIC_DCN315)
+			funcs->is_psrsu_supported = dmub_dcn314_is_psrsu_supported;
+		} else if (asic == DMUB_ASIC_DCN315) {
 			dmub->regs_dcn31 = &dmub_srv_dcn315_regs;
-		else if (asic == DMUB_ASIC_DCN316)
+		} else if (asic == DMUB_ASIC_DCN316) {
 			dmub->regs_dcn31 = &dmub_srv_dcn316_regs;
-		else
+		} else {
 			dmub->regs_dcn31 = &dmub_srv_dcn31_regs;
+			funcs->is_psrsu_supported = dmub_dcn31_is_psrsu_supported;
+		}
 		funcs->reset = dmub_dcn31_reset;
 		funcs->reset_release = dmub_dcn31_reset_release;
 		funcs->backdoor_load = dmub_dcn31_backdoor_load;
diff --git a/drivers/gpu/drm/amd/pm/amdgpu_pm.c b/drivers/gpu/drm/amd/pm/amdgpu_pm.c
index a57952b93e73..9ef88a0b1b57 100644
--- a/drivers/gpu/drm/amd/pm/amdgpu_pm.c
+++ b/drivers/gpu/drm/amd/pm/amdgpu_pm.c
@@ -35,44 +35,6 @@
 #include <linux/pm_runtime.h>
 #include <asm/processor.h>
 
-static const struct cg_flag_name clocks[] = {
-	{AMD_CG_SUPPORT_GFX_FGCG, "Graphics Fine Grain Clock Gating"},
-	{AMD_CG_SUPPORT_GFX_MGCG, "Graphics Medium Grain Clock Gating"},
-	{AMD_CG_SUPPORT_GFX_MGLS, "Graphics Medium Grain memory Light Sleep"},
-	{AMD_CG_SUPPORT_GFX_CGCG, "Graphics Coarse Grain Clock Gating"},
-	{AMD_CG_SUPPORT_GFX_CGLS, "Graphics Coarse Grain memory Light Sleep"},
-	{AMD_CG_SUPPORT_GFX_CGTS, "Graphics Coarse Grain Tree Shader Clock Gating"},
-	{AMD_CG_SUPPORT_GFX_CGTS_LS, "Graphics Coarse Grain Tree Shader Light Sleep"},
-	{AMD_CG_SUPPORT_GFX_CP_LS, "Graphics Command Processor Light Sleep"},
-	{AMD_CG_SUPPORT_GFX_RLC_LS, "Graphics Run List Controller Light Sleep"},
-	{AMD_CG_SUPPORT_GFX_3D_CGCG, "Graphics 3D Coarse Grain Clock Gating"},
-	{AMD_CG_SUPPORT_GFX_3D_CGLS, "Graphics 3D Coarse Grain memory Light Sleep"},
-	{AMD_CG_SUPPORT_MC_LS, "Memory Controller Light Sleep"},
-	{AMD_CG_SUPPORT_MC_MGCG, "Memory Controller Medium Grain Clock Gating"},
-	{AMD_CG_SUPPORT_SDMA_LS, "System Direct Memory Access Light Sleep"},
-	{AMD_CG_SUPPORT_SDMA_MGCG, "System Direct Memory Access Medium Grain Clock Gating"},
-	{AMD_CG_SUPPORT_BIF_MGCG, "Bus Interface Medium Grain Clock Gating"},
-	{AMD_CG_SUPPORT_BIF_LS, "Bus Interface Light Sleep"},
-	{AMD_CG_SUPPORT_UVD_MGCG, "Unified Video Decoder Medium Grain Clock Gating"},
-	{AMD_CG_SUPPORT_VCE_MGCG, "Video Compression Engine Medium Grain Clock Gating"},
-	{AMD_CG_SUPPORT_HDP_LS, "Host Data Path Light Sleep"},
-	{AMD_CG_SUPPORT_HDP_MGCG, "Host Data Path Medium Grain Clock Gating"},
-	{AMD_CG_SUPPORT_DRM_MGCG, "Digital Right Management Medium Grain Clock Gating"},
-	{AMD_CG_SUPPORT_DRM_LS, "Digital Right Management Light Sleep"},
-	{AMD_CG_SUPPORT_ROM_MGCG, "Rom Medium Grain Clock Gating"},
-	{AMD_CG_SUPPORT_DF_MGCG, "Data Fabric Medium Grain Clock Gating"},
-	{AMD_CG_SUPPORT_VCN_MGCG, "VCN Medium Grain Clock Gating"},
-	{AMD_CG_SUPPORT_HDP_DS, "Host Data Path Deep Sleep"},
-	{AMD_CG_SUPPORT_HDP_SD, "Host Data Path Shutdown"},
-	{AMD_CG_SUPPORT_IH_CG, "Interrupt Handler Clock Gating"},
-	{AMD_CG_SUPPORT_JPEG_MGCG, "JPEG Medium Grain Clock Gating"},
-	{AMD_CG_SUPPORT_REPEATER_FGCG, "Repeater Fine Grain Clock Gating"},
-	{AMD_CG_SUPPORT_GFX_PERF_CLK, "Perfmon Clock Gating"},
-	{AMD_CG_SUPPORT_ATHUB_MGCG, "Address Translation Hub Medium Grain Clock Gating"},
-	{AMD_CG_SUPPORT_ATHUB_LS, "Address Translation Hub Light Sleep"},
-	{0, NULL},
-};
-
 static const struct hwmon_temp_label {
 	enum PP_HWMON_TEMP channel;
 	const char *label;
@@ -2110,6 +2072,7 @@ static int default_attr_update(struct amdgpu_device *adev, struct amdgpu_device_
 		case IP_VERSION(9, 4, 0):
 		case IP_VERSION(9, 4, 1):
 		case IP_VERSION(9, 4, 2):
+		case IP_VERSION(9, 4, 3):
 		case IP_VERSION(10, 3, 0):
 		case IP_VERSION(11, 0, 0):
 		case IP_VERSION(11, 0, 1):
@@ -2120,7 +2083,9 @@ static int default_attr_update(struct amdgpu_device *adev, struct amdgpu_device_
 			*states = ATTR_STATE_UNSUPPORTED;
 		}
 	} else if (DEVICE_ATTR_IS(pp_features)) {
-		if (adev->flags & AMD_IS_APU || gc_ver < IP_VERSION(9, 0, 0))
+		if ((adev->flags & AMD_IS_APU &&
+		     gc_ver != IP_VERSION(9, 4, 3)) ||
+		    gc_ver < IP_VERSION(9, 0, 0))
 			*states = ATTR_STATE_UNSUPPORTED;
 	} else if (DEVICE_ATTR_IS(gpu_metrics)) {
 		if (gc_ver < IP_VERSION(9, 1, 0))
@@ -3684,6 +3649,44 @@ static int amdgpu_debugfs_pm_info_pp(struct seq_file *m, struct amdgpu_device *a
 	return 0;
 }
 
+static const struct cg_flag_name clocks[] = {
+	{AMD_CG_SUPPORT_GFX_FGCG, "Graphics Fine Grain Clock Gating"},
+	{AMD_CG_SUPPORT_GFX_MGCG, "Graphics Medium Grain Clock Gating"},
+	{AMD_CG_SUPPORT_GFX_MGLS, "Graphics Medium Grain memory Light Sleep"},
+	{AMD_CG_SUPPORT_GFX_CGCG, "Graphics Coarse Grain Clock Gating"},
+	{AMD_CG_SUPPORT_GFX_CGLS, "Graphics Coarse Grain memory Light Sleep"},
+	{AMD_CG_SUPPORT_GFX_CGTS, "Graphics Coarse Grain Tree Shader Clock Gating"},
+	{AMD_CG_SUPPORT_GFX_CGTS_LS, "Graphics Coarse Grain Tree Shader Light Sleep"},
+	{AMD_CG_SUPPORT_GFX_CP_LS, "Graphics Command Processor Light Sleep"},
+	{AMD_CG_SUPPORT_GFX_RLC_LS, "Graphics Run List Controller Light Sleep"},
+	{AMD_CG_SUPPORT_GFX_3D_CGCG, "Graphics 3D Coarse Grain Clock Gating"},
+	{AMD_CG_SUPPORT_GFX_3D_CGLS, "Graphics 3D Coarse Grain memory Light Sleep"},
+	{AMD_CG_SUPPORT_MC_LS, "Memory Controller Light Sleep"},
+	{AMD_CG_SUPPORT_MC_MGCG, "Memory Controller Medium Grain Clock Gating"},
+	{AMD_CG_SUPPORT_SDMA_LS, "System Direct Memory Access Light Sleep"},
+	{AMD_CG_SUPPORT_SDMA_MGCG, "System Direct Memory Access Medium Grain Clock Gating"},
+	{AMD_CG_SUPPORT_BIF_MGCG, "Bus Interface Medium Grain Clock Gating"},
+	{AMD_CG_SUPPORT_BIF_LS, "Bus Interface Light Sleep"},
+	{AMD_CG_SUPPORT_UVD_MGCG, "Unified Video Decoder Medium Grain Clock Gating"},
+	{AMD_CG_SUPPORT_VCE_MGCG, "Video Compression Engine Medium Grain Clock Gating"},
+	{AMD_CG_SUPPORT_HDP_LS, "Host Data Path Light Sleep"},
+	{AMD_CG_SUPPORT_HDP_MGCG, "Host Data Path Medium Grain Clock Gating"},
+	{AMD_CG_SUPPORT_DRM_MGCG, "Digital Right Management Medium Grain Clock Gating"},
+	{AMD_CG_SUPPORT_DRM_LS, "Digital Right Management Light Sleep"},
+	{AMD_CG_SUPPORT_ROM_MGCG, "Rom Medium Grain Clock Gating"},
+	{AMD_CG_SUPPORT_DF_MGCG, "Data Fabric Medium Grain Clock Gating"},
+	{AMD_CG_SUPPORT_VCN_MGCG, "VCN Medium Grain Clock Gating"},
+	{AMD_CG_SUPPORT_HDP_DS, "Host Data Path Deep Sleep"},
+	{AMD_CG_SUPPORT_HDP_SD, "Host Data Path Shutdown"},
+	{AMD_CG_SUPPORT_IH_CG, "Interrupt Handler Clock Gating"},
+	{AMD_CG_SUPPORT_JPEG_MGCG, "JPEG Medium Grain Clock Gating"},
+	{AMD_CG_SUPPORT_REPEATER_FGCG, "Repeater Fine Grain Clock Gating"},
+	{AMD_CG_SUPPORT_GFX_PERF_CLK, "Perfmon Clock Gating"},
+	{AMD_CG_SUPPORT_ATHUB_MGCG, "Address Translation Hub Medium Grain Clock Gating"},
+	{AMD_CG_SUPPORT_ATHUB_LS, "Address Translation Hub Light Sleep"},
+	{0, NULL},
+};
+
 static void amdgpu_parse_cg_state(struct seq_file *m, u64 flags)
 {
 	int i;
diff --git a/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h b/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h
index d178f3f44081..42172b00be66 100644
--- a/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h
+++ b/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h
@@ -89,6 +89,8 @@ struct amdgpu_dpm_thermal {
 	int                max_mem_crit_temp;
 	/* memory max emergency(shutdown) temp */
 	int                max_mem_emergency_temp;
+	/* SWCTF threshold */
+	int                sw_ctf_threshold;
 	/* was last interrupt low to high or high to low */
 	bool               high_to_low;
 	/* interrupt source */
diff --git a/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c b/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c
index 11b7b4cffaae..ff360c699171 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c
@@ -26,6 +26,7 @@
 #include <linux/gfp.h>
 #include <linux/slab.h>
 #include <linux/firmware.h>
+#include <linux/reboot.h>
 #include "amd_shared.h"
 #include "amd_powerplay.h"
 #include "power_state.h"
@@ -91,6 +92,45 @@ static int pp_early_init(void *handle)
 	return 0;
 }
 
+static void pp_swctf_delayed_work_handler(struct work_struct *work)
+{
+	struct pp_hwmgr *hwmgr =
+		container_of(work, struct pp_hwmgr, swctf_delayed_work.work);
+	struct amdgpu_device *adev = hwmgr->adev;
+	struct amdgpu_dpm_thermal *range =
+				&adev->pm.dpm.thermal;
+	uint32_t gpu_temperature, size;
+	int ret;
+
+	/*
+	 * If the hotspot/edge temperature is confirmed as below SW CTF setting point
+	 * after the delay enforced, nothing will be done.
+	 * Otherwise, a graceful shutdown will be performed to prevent further damage.
+	 */
+	if (range->sw_ctf_threshold &&
+	    hwmgr->hwmgr_func->read_sensor) {
+		ret = hwmgr->hwmgr_func->read_sensor(hwmgr,
+						     AMDGPU_PP_SENSOR_HOTSPOT_TEMP,
+						     &gpu_temperature,
+						     &size);
+		/*
+		 * For some legacy ASICs, hotspot temperature retrieving might be not
+		 * supported. Check the edge temperature instead then.
+		 */
+		if (ret == -EOPNOTSUPP)
+			ret = hwmgr->hwmgr_func->read_sensor(hwmgr,
+							     AMDGPU_PP_SENSOR_EDGE_TEMP,
+							     &gpu_temperature,
+							     &size);
+		if (!ret && gpu_temperature / 1000 < range->sw_ctf_threshold)
+			return;
+	}
+
+	dev_emerg(adev->dev, "ERROR: GPU over temperature range(SW CTF) detected!\n");
+	dev_emerg(adev->dev, "ERROR: System is going to shutdown due to GPU SW CTF!\n");
+	orderly_poweroff(true);
+}
+
 static int pp_sw_init(void *handle)
 {
 	struct amdgpu_device *adev = handle;
@@ -101,6 +141,10 @@ static int pp_sw_init(void *handle)
 
 	pr_debug("powerplay sw init %s\n", ret ? "failed" : "successfully");
 
+	if (!ret)
+		INIT_DELAYED_WORK(&hwmgr->swctf_delayed_work,
+				  pp_swctf_delayed_work_handler);
+
 	return ret;
 }
 
@@ -135,6 +179,8 @@ static int pp_hw_fini(void *handle)
 	struct amdgpu_device *adev = handle;
 	struct pp_hwmgr *hwmgr = adev->powerplay.pp_handle;
 
+	cancel_delayed_work_sync(&hwmgr->swctf_delayed_work);
+
 	hwmgr_hw_fini(hwmgr);
 
 	return 0;
@@ -221,6 +267,8 @@ static int pp_suspend(void *handle)
 	struct amdgpu_device *adev = handle;
 	struct pp_hwmgr *hwmgr = adev->powerplay.pp_handle;
 
+	cancel_delayed_work_sync(&hwmgr->swctf_delayed_work);
+
 	return hwmgr_suspend(hwmgr);
 }
 
diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/hardwaremanager.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/hardwaremanager.c
index 981dc8c7112d..90452b66e107 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/hardwaremanager.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/hardwaremanager.c
@@ -241,7 +241,8 @@ int phm_start_thermal_controller(struct pp_hwmgr *hwmgr)
 		TEMP_RANGE_MAX,
 		TEMP_RANGE_MIN,
 		TEMP_RANGE_MAX,
-		TEMP_RANGE_MAX};
+		TEMP_RANGE_MAX,
+		0};
 	struct amdgpu_device *adev = hwmgr->adev;
 
 	if (!hwmgr->not_vf)
@@ -265,6 +266,7 @@ int phm_start_thermal_controller(struct pp_hwmgr *hwmgr)
 	adev->pm.dpm.thermal.min_mem_temp = range.mem_min;
 	adev->pm.dpm.thermal.max_mem_crit_temp = range.mem_crit_max;
 	adev->pm.dpm.thermal.max_mem_emergency_temp = range.mem_emergency_max;
+	adev->pm.dpm.thermal.sw_ctf_threshold = range.sw_ctf_threshold;
 
 	return ret;
 }
diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c
index e10cc5e7928e..6841a4bce186 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c
@@ -5432,6 +5432,8 @@ static int smu7_get_thermal_temperature_range(struct pp_hwmgr *hwmgr,
 		thermal_data->max = data->thermal_temp_setting.temperature_shutdown *
 			PP_TEMPERATURE_UNITS_PER_CENTIGRADES;
 
+	thermal_data->sw_ctf_threshold = thermal_data->max;
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu_helper.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu_helper.c
index bfe80ac0ad8c..d0b1ab6c4523 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu_helper.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu_helper.c
@@ -603,21 +603,17 @@ int phm_irq_process(struct amdgpu_device *adev,
 			   struct amdgpu_irq_src *source,
 			   struct amdgpu_iv_entry *entry)
 {
+	struct pp_hwmgr *hwmgr = adev->powerplay.pp_handle;
 	uint32_t client_id = entry->client_id;
 	uint32_t src_id = entry->src_id;
 
 	if (client_id == AMDGPU_IRQ_CLIENTID_LEGACY) {
 		if (src_id == VISLANDS30_IV_SRCID_CG_TSS_THERMAL_LOW_TO_HIGH) {
-			dev_emerg(adev->dev, "ERROR: GPU over temperature range(SW CTF) detected!\n");
-			/*
-			 * SW CTF just occurred.
-			 * Try to do a graceful shutdown to prevent further damage.
-			 */
-			dev_emerg(adev->dev, "ERROR: System is going to shutdown due to GPU SW CTF!\n");
-			orderly_poweroff(true);
-		} else if (src_id == VISLANDS30_IV_SRCID_CG_TSS_THERMAL_HIGH_TO_LOW)
+			schedule_delayed_work(&hwmgr->swctf_delayed_work,
+					      msecs_to_jiffies(AMDGPU_SWCTF_EXTRA_DELAY));
+		} else if (src_id == VISLANDS30_IV_SRCID_CG_TSS_THERMAL_HIGH_TO_LOW) {
 			dev_emerg(adev->dev, "ERROR: GPU under temperature range detected!\n");
-		else if (src_id == VISLANDS30_IV_SRCID_GPIO_19) {
+		} else if (src_id == VISLANDS30_IV_SRCID_GPIO_19) {
 			dev_emerg(adev->dev, "ERROR: GPU HW Critical Temperature Fault(aka CTF) detected!\n");
 			/*
 			 * HW CTF just occurred. Shutdown to prevent further damage.
@@ -626,15 +622,10 @@ int phm_irq_process(struct amdgpu_device *adev,
 			orderly_poweroff(true);
 		}
 	} else if (client_id == SOC15_IH_CLIENTID_THM) {
-		if (src_id == 0) {
-			dev_emerg(adev->dev, "ERROR: GPU over temperature range(SW CTF) detected!\n");
-			/*
-			 * SW CTF just occurred.
-			 * Try to do a graceful shutdown to prevent further damage.
-			 */
-			dev_emerg(adev->dev, "ERROR: System is going to shutdown due to GPU SW CTF!\n");
-			orderly_poweroff(true);
-		} else
+		if (src_id == 0)
+			schedule_delayed_work(&hwmgr->swctf_delayed_work,
+					      msecs_to_jiffies(AMDGPU_SWCTF_EXTRA_DELAY));
+		else
 			dev_emerg(adev->dev, "ERROR: GPU under temperature range detected!\n");
 	} else if (client_id == SOC15_IH_CLIENTID_ROM_SMUIO) {
 		dev_emerg(adev->dev, "ERROR: GPU HW Critical Temperature Fault(aka CTF) detected!\n");
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 99cd2e63afdd..c51dd4c74fe9 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c
@@ -5241,6 +5241,9 @@ static int vega10_get_thermal_temperature_range(struct pp_hwmgr *hwmgr,
 {
 	struct vega10_hwmgr *data = hwmgr->backend;
 	PPTable_t *pp_table = &(data->smc_state_table.pp_table);
+	struct phm_ppt_v2_information *pp_table_info =
+		(struct phm_ppt_v2_information *)(hwmgr->pptable);
+	struct phm_tdp_table *tdp_table = pp_table_info->tdp_table;
 
 	memcpy(thermal_data, &SMU7ThermalWithDelayPolicy[0], sizeof(struct PP_TemperatureRange));
 
@@ -5257,6 +5260,13 @@ static int vega10_get_thermal_temperature_range(struct pp_hwmgr *hwmgr,
 	thermal_data->mem_emergency_max = (pp_table->ThbmLimit + CTF_OFFSET_HBM)*
 		PP_TEMPERATURE_UNITS_PER_CENTIGRADES;
 
+	if (tdp_table->usSoftwareShutdownTemp > pp_table->ThotspotLimit &&
+	    tdp_table->usSoftwareShutdownTemp < VEGA10_THERMAL_MAXIMUM_ALERT_TEMP)
+		thermal_data->sw_ctf_threshold = tdp_table->usSoftwareShutdownTemp;
+	else
+		thermal_data->sw_ctf_threshold = VEGA10_THERMAL_MAXIMUM_ALERT_TEMP;
+	thermal_data->sw_ctf_threshold *= PP_TEMPERATURE_UNITS_PER_CENTIGRADES;
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_hwmgr.c
index e9db137cd1c6..1937be1cf5b4 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_hwmgr.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_hwmgr.c
@@ -2763,6 +2763,8 @@ static int vega12_notify_cac_buffer_info(struct pp_hwmgr *hwmgr,
 static int vega12_get_thermal_temperature_range(struct pp_hwmgr *hwmgr,
 		struct PP_TemperatureRange *thermal_data)
 {
+	struct phm_ppt_v3_information *pptable_information =
+		(struct phm_ppt_v3_information *)hwmgr->pptable;
 	struct vega12_hwmgr *data =
 			(struct vega12_hwmgr *)(hwmgr->backend);
 	PPTable_t *pp_table = &(data->smc_state_table.pp_table);
@@ -2781,6 +2783,8 @@ static int vega12_get_thermal_temperature_range(struct pp_hwmgr *hwmgr,
 		PP_TEMPERATURE_UNITS_PER_CENTIGRADES;
 	thermal_data->mem_emergency_max = (pp_table->ThbmLimit + CTF_OFFSET_HBM)*
 		PP_TEMPERATURE_UNITS_PER_CENTIGRADES;
+	thermal_data->sw_ctf_threshold = pptable_information->us_software_shutdown_temp *
+		PP_TEMPERATURE_UNITS_PER_CENTIGRADES;
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_thermal.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_thermal.c
index ed3dff0b52d2..ae342c58cd3e 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_thermal.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_thermal.c
@@ -192,7 +192,9 @@ static int vega12_thermal_set_temperature_range(struct pp_hwmgr *hwmgr,
 	val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, THERM_IH_HW_ENA, 1);
 	val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, DIG_THERM_INTH, high);
 	val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, DIG_THERM_INTL, low);
-	val = val & (~THM_THERMAL_INT_CTRL__THERM_TRIGGER_MASK_MASK);
+	val &= ~THM_THERMAL_INT_CTRL__THERM_TRIGGER_MASK_MASK;
+	val &= ~THM_THERMAL_INT_CTRL__THERM_INTH_MASK_MASK;
+	val &= ~THM_THERMAL_INT_CTRL__THERM_INTL_MASK_MASK;
 
 	WREG32_SOC15(THM, 0, mmTHM_THERMAL_INT_CTRL, val);
 
diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_hwmgr.c
index 0d4d4811527c..4e19ccbdb807 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_hwmgr.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_hwmgr.c
@@ -4206,6 +4206,8 @@ static int vega20_notify_cac_buffer_info(struct pp_hwmgr *hwmgr,
 static int vega20_get_thermal_temperature_range(struct pp_hwmgr *hwmgr,
 		struct PP_TemperatureRange *thermal_data)
 {
+	struct phm_ppt_v3_information *pptable_information =
+		(struct phm_ppt_v3_information *)hwmgr->pptable;
 	struct vega20_hwmgr *data =
 			(struct vega20_hwmgr *)(hwmgr->backend);
 	PPTable_t *pp_table = &(data->smc_state_table.pp_table);
@@ -4224,6 +4226,8 @@ static int vega20_get_thermal_temperature_range(struct pp_hwmgr *hwmgr,
 		PP_TEMPERATURE_UNITS_PER_CENTIGRADES;
 	thermal_data->mem_emergency_max = (pp_table->ThbmLimit + CTF_OFFSET_HBM)*
 		PP_TEMPERATURE_UNITS_PER_CENTIGRADES;
+	thermal_data->sw_ctf_threshold = pptable_information->us_software_shutdown_temp *
+		PP_TEMPERATURE_UNITS_PER_CENTIGRADES;
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_thermal.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_thermal.c
index f4f4efdbda79..e9737ca8418a 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_thermal.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_thermal.c
@@ -263,7 +263,9 @@ static int vega20_thermal_set_temperature_range(struct pp_hwmgr *hwmgr,
 	val = CGS_REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, THERM_IH_HW_ENA, 1);
 	val = CGS_REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, DIG_THERM_INTH, high);
 	val = CGS_REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, DIG_THERM_INTL, low);
-	val = val & (~THM_THERMAL_INT_CTRL__THERM_TRIGGER_MASK_MASK);
+	val &= ~THM_THERMAL_INT_CTRL__THERM_TRIGGER_MASK_MASK;
+	val &= ~THM_THERMAL_INT_CTRL__THERM_INTH_MASK_MASK;
+	val &= ~THM_THERMAL_INT_CTRL__THERM_INTL_MASK_MASK;
 
 	WREG32_SOC15(THM, 0, mmTHM_THERMAL_INT_CTRL, val);
 
diff --git a/drivers/gpu/drm/amd/pm/powerplay/inc/hwmgr.h b/drivers/gpu/drm/amd/pm/powerplay/inc/hwmgr.h
index f1580a26a850..612d66aeaab9 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/inc/hwmgr.h
+++ b/drivers/gpu/drm/amd/pm/powerplay/inc/hwmgr.h
@@ -811,6 +811,8 @@ struct pp_hwmgr {
 	bool gfxoff_state_changed_by_workload;
 	uint32_t pstate_sclk_peak;
 	uint32_t pstate_mclk_peak;
+
+	struct delayed_work swctf_delayed_work;
 };
 
 int hwmgr_early_init(struct pp_hwmgr *hwmgr);
diff --git a/drivers/gpu/drm/amd/pm/powerplay/inc/power_state.h b/drivers/gpu/drm/amd/pm/powerplay/inc/power_state.h
index a5f2227a3971..0ffc2347829d 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/inc/power_state.h
+++ b/drivers/gpu/drm/amd/pm/powerplay/inc/power_state.h
@@ -131,6 +131,7 @@ struct PP_TemperatureRange {
 	int mem_min;
 	int mem_crit_max;
 	int mem_emergency_max;
+	int sw_ctf_threshold;
 };
 
 struct PP_StateValidationBlock {
diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
index 4dea79a0c5b5..ce41a8309582 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
@@ -24,6 +24,7 @@
 
 #include <linux/firmware.h>
 #include <linux/pci.h>
+#include <linux/reboot.h>
 
 #include "amdgpu.h"
 #include "amdgpu_smu.h"
@@ -1078,6 +1079,34 @@ static void smu_interrupt_work_fn(struct work_struct *work)
 		smu->ppt_funcs->interrupt_work(smu);
 }
 
+static void smu_swctf_delayed_work_handler(struct work_struct *work)
+{
+	struct smu_context *smu =
+		container_of(work, struct smu_context, swctf_delayed_work.work);
+	struct smu_temperature_range *range =
+				&smu->thermal_range;
+	struct amdgpu_device *adev = smu->adev;
+	uint32_t hotspot_tmp, size;
+
+	/*
+	 * If the hotspot temperature is confirmed as below SW CTF setting point
+	 * after the delay enforced, nothing will be done.
+	 * Otherwise, a graceful shutdown will be performed to prevent further damage.
+	 */
+	if (range->software_shutdown_temp &&
+	    smu->ppt_funcs->read_sensor &&
+	    !smu->ppt_funcs->read_sensor(smu,
+					 AMDGPU_PP_SENSOR_HOTSPOT_TEMP,
+					 &hotspot_tmp,
+					 &size) &&
+	    hotspot_tmp / 1000 < range->software_shutdown_temp)
+		return;
+
+	dev_emerg(adev->dev, "ERROR: GPU over temperature range(SW CTF) detected!\n");
+	dev_emerg(adev->dev, "ERROR: System is going to shutdown due to GPU SW CTF!\n");
+	orderly_poweroff(true);
+}
+
 static int smu_sw_init(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
@@ -1120,6 +1149,9 @@ static int smu_sw_init(void *handle)
 	smu->smu_dpm.dpm_level = AMD_DPM_FORCED_LEVEL_AUTO;
 	smu->smu_dpm.requested_dpm_level = AMD_DPM_FORCED_LEVEL_AUTO;
 
+	INIT_DELAYED_WORK(&smu->swctf_delayed_work,
+			  smu_swctf_delayed_work_handler);
+
 	ret = smu_smc_table_sw_init(smu);
 	if (ret) {
 		dev_err(adev->dev, "Failed to sw init smc table!\n");
@@ -1600,6 +1632,8 @@ static int smu_smc_hw_cleanup(struct smu_context *smu)
 		return ret;
 	}
 
+	cancel_delayed_work_sync(&smu->swctf_delayed_work);
+
 	ret = smu_disable_dpms(smu);
 	if (ret) {
 		dev_err(adev->dev, "Fail to disable dpm features!\n");
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 09469c750a96..6e2069dcb6b9 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h
@@ -573,6 +573,8 @@ struct smu_context
 	u32 debug_param_reg;
 	u32 debug_msg_reg;
 	u32 debug_resp_reg;
+
+	struct delayed_work		swctf_delayed_work;
 };
 
 struct i2c_adapter;
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c
index 275f708db636..c94d825a871b 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c
@@ -1654,7 +1654,7 @@ static int navi10_force_clk_levels(struct smu_context *smu,
 				   enum smu_clk_type clk_type, uint32_t mask)
 {
 
-	int ret = 0, size = 0;
+	int ret = 0;
 	uint32_t soft_min_level = 0, soft_max_level = 0, min_freq = 0, max_freq = 0;
 
 	soft_min_level = mask ? (ffs(mask) - 1) : 0;
@@ -1675,15 +1675,15 @@ static int navi10_force_clk_levels(struct smu_context *smu,
 
 		ret = smu_v11_0_get_dpm_freq_by_index(smu, clk_type, soft_min_level, &min_freq);
 		if (ret)
-			return size;
+			return 0;
 
 		ret = smu_v11_0_get_dpm_freq_by_index(smu, clk_type, soft_max_level, &max_freq);
 		if (ret)
-			return size;
+			return 0;
 
 		ret = smu_v11_0_set_soft_freq_limited_range(smu, clk_type, min_freq, max_freq);
 		if (ret)
-			return size;
+			return 0;
 		break;
 	case SMU_DCEFCLK:
 		dev_info(smu->adev->dev,"Setting DCEFCLK min/max dpm level is not supported!\n");
@@ -1693,7 +1693,7 @@ static int navi10_force_clk_levels(struct smu_context *smu,
 		break;
 	}
 
-	return size;
+	return 0;
 }
 
 static int navi10_populate_umd_state_clk(struct smu_context *smu)
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c
index e1ef88ee1ed3..aa4a5498a12f 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c
@@ -1412,13 +1412,8 @@ static int smu_v11_0_irq_process(struct amdgpu_device *adev,
 	if (client_id == SOC15_IH_CLIENTID_THM) {
 		switch (src_id) {
 		case THM_11_0__SRCID__THM_DIG_THERM_L2H:
-			dev_emerg(adev->dev, "ERROR: GPU over temperature range(SW CTF) detected!\n");
-			/*
-			 * SW CTF just occurred.
-			 * Try to do a graceful shutdown to prevent further damage.
-			 */
-			dev_emerg(adev->dev, "ERROR: System is going to shutdown due to GPU SW CTF!\n");
-			orderly_poweroff(true);
+			schedule_delayed_work(&smu->swctf_delayed_work,
+					      msecs_to_jiffies(AMDGPU_SWCTF_EXTRA_DELAY));
 		break;
 		case THM_11_0__SRCID__THM_DIG_THERM_H2L:
 			dev_emerg(adev->dev, "ERROR: GPU under temperature range detected\n");
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c
index e52c563f0dac..3856da6c3f3d 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c
@@ -1353,13 +1353,8 @@ static int smu_v13_0_irq_process(struct amdgpu_device *adev,
 	if (client_id == SOC15_IH_CLIENTID_THM) {
 		switch (src_id) {
 		case THM_11_0__SRCID__THM_DIG_THERM_L2H:
-			dev_emerg(adev->dev, "ERROR: GPU over temperature range(SW CTF) detected!\n");
-			/*
-			 * SW CTF just occurred.
-			 * Try to do a graceful shutdown to prevent further damage.
-			 */
-			dev_emerg(adev->dev, "ERROR: System is going to shutdown due to GPU SW CTF!\n");
-			orderly_poweroff(true);
+			schedule_delayed_work(&smu->swctf_delayed_work,
+					      msecs_to_jiffies(AMDGPU_SWCTF_EXTRA_DELAY));
 			break;
 		case THM_11_0__SRCID__THM_DIG_THERM_H2L:
 			dev_emerg(adev->dev, "ERROR: GPU under temperature range detected\n");
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c
index a6083957ae51..124287cbbff8 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c
@@ -1710,6 +1710,7 @@ static int smu_v13_0_0_get_thermal_temperature_range(struct smu_context *smu,
 	range->mem_emergency_max = (pptable->SkuTable.TemperatureLimit[TEMP_MEM] + CTF_OFFSET_MEM)*
 		SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
 	range->software_shutdown_temp = powerplay_table->software_shutdown_temp;
+	range->software_shutdown_temp_offset = pptable->SkuTable.FanAbnormalTempLimitOffset;
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
index a92ea4601ea4..6ef12252beb5 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
@@ -200,7 +200,6 @@ struct PPTable_t {
 };
 
 #define SMUQ10_TO_UINT(x) ((x) >> 10)
-#define SMUQ16_TO_UINT(x) ((x) >> 16)
 
 struct smu_v13_0_6_dpm_map {
 	enum smu_clk_type clk_type;
@@ -1994,8 +1993,9 @@ static ssize_t smu_v13_0_6_get_gpu_metrics(struct smu_context *smu, void **table
 
 	gpu_metrics->average_socket_power =
 		SMUQ10_TO_UINT(metrics->SocketPower);
+	/* Energy is reported in 15.625mJ units */
 	gpu_metrics->energy_accumulator =
-		SMUQ16_TO_UINT(metrics->SocketEnergyAcc);
+		SMUQ10_TO_UINT(metrics->SocketEnergyAcc);
 
 	gpu_metrics->current_gfxclk =
 		SMUQ10_TO_UINT(metrics->GfxclkFrequency[xcc0]);