Merge tag 'drm-next-2024-11-29' of https://gitlab.freedesktop.org/drm/kernel

Pull drm fixes from Dave Airlie:
 "Merge window fixes, mostly amdgpu and xe, with a few other minor ones,
  all looks fairly normal,

  i915:
   - hdcp: Fix when the first read and write are retried

  xe:
   - Wake up waiters after wait condition set to true
   - Mark the preempt fence workqueue as reclaim
   - Update xe2 graphics name string
   - Fix a couple of guc submit races
   - Fix pat index usage in migrate
   - Ensure non-cached migrate pagetable bo mappings
   - Take a PM ref in the delayed snapshot capture worker

  amdgpu:
   - SMU 13.0.6 fixes
   - XGMI fixes
   - SMU 13.0.7 fixes
   - Misc code cleanups
   - Plane refcount fixes
   - DCN 4.0.1 fixes
   - DC power fixes
   - DTO fixes
   - NBIO 7.11 fixes
   - SMU 14.0.x fixes
   - Reset fixes
   - Enable DC on LoongArch
   - Sysfs hotplug warning fix
   - Misc small fixes
   - VCN 4.0.3 fix
   - Slab usage fix
   - Jpeg delayed work fix

  amdkfd:
   - wptr handling fixes

  radeon:
   - Use ttm_bo_move_null()
   - Constify struct pci_device_id
   - Fix spurious hotplug
   - HPD fix

  rockchip
   - fix 32-bit build"

* tag 'drm-next-2024-11-29' of https://gitlab.freedesktop.org/drm/kernel: (48 commits)
  drm/xe: Take PM ref in delayed snapshot capture worker
  drm/xe/migrate: use XE_BO_FLAG_PAGETABLE
  drm/xe/migrate: fix pat index usage
  drm/xe/guc_submit: fix race around suspend_pending
  drm/xe/guc_submit: fix race around pending_disable
  drm/xe: Update xe2_graphics name string
  drm/rockchip: avoid 64-bit division
  Revert "drm/radeon: Delay Connector detecting when HPD singals is unstable"
  drm/amdgpu/jpeg: cancel the jpeg worker
  drm/amdgpu: fix usage slab after free
  drm/amdgpu/vcn: reset fw_shared when VCPU buffers corrupted on vcn v4.0.3
  drm/amdgpu: Fix sysfs warning when hotplugging
  drm/amdgpu: Add sysfs interface for vcn reset mask
  drm/amdgpu/gmc7: fix wait_for_idle callers
  drm/amd/pm: Remove arcturus min power limit
  drm/amd/pm: skip setting the power source on smu v14.0.2/3
  drm/amd/pm: disable pcie speed switching on Intel platform for smu v14.0.2/3
  drm/amdkfd: Use the correct wptr size
  drm/xe: Mark preempt fence workqueue as reclaim
  drm/xe/ufence: Wake up waiters after setting ufence->signalled
  ...

75 files changed, 690 insertions, 193 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/aldebaran.c b/drivers/gpu/drm/amd/amdgpu/aldebaran.c
index 3a588fecb0c5..f44de9d4b6a1 100644
--- a/drivers/gpu/drm/amd/amdgpu/aldebaran.c
+++ b/drivers/gpu/drm/amd/amdgpu/aldebaran.c
@@ -330,6 +330,8 @@ aldebaran_mode2_restore_hwcontext(struct amdgpu_reset_control *reset_ctl,
 	}
 
 	list_for_each_entry(tmp_adev, reset_device_list, reset_list) {
+		amdgpu_set_init_level(tmp_adev,
+				AMDGPU_INIT_LEVEL_RESET_RECOVERY);
 		dev_info(tmp_adev->dev,
 			 "GPU reset succeeded, trying to resume\n");
 		r = aldebaran_mode2_restore_ip(tmp_adev);
@@ -375,6 +377,8 @@ aldebaran_mode2_restore_hwcontext(struct amdgpu_reset_control *reset_ctl,
 							tmp_adev);
 
 		if (!r) {
+			amdgpu_set_init_level(tmp_adev,
+					      AMDGPU_INIT_LEVEL_DEFAULT);
 			amdgpu_irq_gpu_reset_resume_helper(tmp_adev);
 
 			r = amdgpu_ib_ring_tests(tmp_adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index d8bc6da50016..4653a8d2823a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -839,6 +839,7 @@ struct amdgpu_mqd {
 enum amdgpu_init_lvl_id {
 	AMDGPU_INIT_LEVEL_DEFAULT,
 	AMDGPU_INIT_LEVEL_MINIMAL_XGMI,
+	AMDGPU_INIT_LEVEL_RESET_RECOVERY,
 };
 
 struct amdgpu_init_level {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 0171d240fcb0..9095c05e0269 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -156,6 +156,11 @@ struct amdgpu_init_level amdgpu_init_default = {
 	.hwini_ip_block_mask = AMDGPU_IP_BLK_MASK_ALL,
 };
 
+struct amdgpu_init_level amdgpu_init_recovery = {
+	.level = AMDGPU_INIT_LEVEL_RESET_RECOVERY,
+	.hwini_ip_block_mask = AMDGPU_IP_BLK_MASK_ALL,
+};
+
 /*
  * Minimal blocks needed to be initialized before a XGMI hive can be reset. This
  * is used for cases like reset on initialization where the entire hive needs to
@@ -182,6 +187,9 @@ void amdgpu_set_init_level(struct amdgpu_device *adev,
 	case AMDGPU_INIT_LEVEL_MINIMAL_XGMI:
 		adev->init_lvl = &amdgpu_init_minimal_xgmi;
 		break;
+	case AMDGPU_INIT_LEVEL_RESET_RECOVERY:
+		adev->init_lvl = &amdgpu_init_recovery;
+		break;
 	case AMDGPU_INIT_LEVEL_DEFAULT:
 		fallthrough;
 	default:
@@ -3250,7 +3258,7 @@ static int amdgpu_device_ip_late_init(struct amdgpu_device *adev)
 		return r;
 	}
 
-	if (!amdgpu_in_reset(adev))
+	if (!amdgpu_reset_in_recovery(adev))
 		amdgpu_ras_set_error_query_ready(adev, true);
 
 	amdgpu_device_set_cg_state(adev, AMD_CG_STATE_GATE);
@@ -4669,8 +4677,8 @@ void amdgpu_device_fini_sw(struct amdgpu_device *adev)
 	int idx;
 	bool px;
 
-	amdgpu_fence_driver_sw_fini(adev);
 	amdgpu_device_ip_fini(adev);
+	amdgpu_fence_driver_sw_fini(adev);
 	amdgpu_ucode_release(&adev->firmware.gpu_info_fw);
 	adev->accel_working = false;
 	dma_fence_put(rcu_dereference_protected(adev->gang_submit, true));
@@ -5419,7 +5427,7 @@ int amdgpu_device_reinit_after_reset(struct amdgpu_reset_context *reset_context)
 	struct list_head *device_list_handle;
 	bool full_reset, vram_lost = false;
 	struct amdgpu_device *tmp_adev;
-	int r;
+	int r, init_level;
 
 	device_list_handle = reset_context->reset_device_list;
 
@@ -5428,10 +5436,18 @@ int amdgpu_device_reinit_after_reset(struct amdgpu_reset_context *reset_context)
 
 	full_reset = test_bit(AMDGPU_NEED_FULL_RESET, &reset_context->flags);
 
+	/**
+	 * If it's reset on init, it's default init level, otherwise keep level
+	 * as recovery level.
+	 */
+	if (reset_context->method == AMD_RESET_METHOD_ON_INIT)
+			init_level = AMDGPU_INIT_LEVEL_DEFAULT;
+	else
+			init_level = AMDGPU_INIT_LEVEL_RESET_RECOVERY;
+
 	r = 0;
 	list_for_each_entry(tmp_adev, device_list_handle, reset_list) {
-		/* After reset, it's default init level */
-		amdgpu_set_init_level(tmp_adev, AMDGPU_INIT_LEVEL_DEFAULT);
+		amdgpu_set_init_level(tmp_adev, init_level);
 		if (full_reset) {
 			/* post card */
 			amdgpu_ras_set_fed(tmp_adev, false);
@@ -5518,6 +5534,9 @@ int amdgpu_device_reinit_after_reset(struct amdgpu_reset_context *reset_context)
 
 out:
 		if (!r) {
+			/* IP init is complete now, set level as default */
+			amdgpu_set_init_level(tmp_adev,
+					      AMDGPU_INIT_LEVEL_DEFAULT);
 			amdgpu_irq_gpu_reset_resume_helper(tmp_adev);
 			r = amdgpu_ib_ring_tests(tmp_adev);
 			if (r) {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
index f57cc72c43cf..69a6b6dba0a5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
@@ -1778,9 +1778,11 @@ int amdgpu_gfx_sysfs_init(struct amdgpu_device *adev)
 
 void amdgpu_gfx_sysfs_fini(struct amdgpu_device *adev)
 {
-	amdgpu_gfx_sysfs_xcp_fini(adev);
-	amdgpu_gfx_sysfs_isolation_shader_fini(adev);
-	amdgpu_gfx_sysfs_reset_mask_fini(adev);
+	if (adev->dev->kobj.sd) {
+		amdgpu_gfx_sysfs_xcp_fini(adev);
+		amdgpu_gfx_sysfs_isolation_shader_fini(adev);
+		amdgpu_gfx_sysfs_reset_mask_fini(adev);
+	}
 }
 
 int amdgpu_gfx_cleaner_shader_sw_init(struct amdgpu_device *adev,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_jpeg.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_jpeg.c
index 04eb51674596..b6d2eb049f54 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_jpeg.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_jpeg.c
@@ -447,6 +447,8 @@ int amdgpu_jpeg_sysfs_reset_mask_init(struct amdgpu_device *adev)
 
 void amdgpu_jpeg_sysfs_reset_mask_fini(struct amdgpu_device *adev)
 {
-	if (adev->jpeg.num_jpeg_inst)
-		device_remove_file(adev->dev, &dev_attr_jpeg_reset_mask);
+	if (adev->dev->kobj.sd) {
+		if (adev->jpeg.num_jpeg_inst)
+			device_remove_file(adev->dev, &dev_attr_jpeg_reset_mask);
+	}
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_preempt_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_preempt_mgr.c
index e8adfd0a570a..34b5e22b44e5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_preempt_mgr.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_preempt_mgr.c
@@ -137,7 +137,8 @@ void amdgpu_preempt_mgr_fini(struct amdgpu_device *adev)
 	if (ret)
 		return;
 
-	device_remove_file(adev->dev, &dev_attr_mem_info_preempt_used);
+	if (adev->dev->kobj.sd)
+		device_remove_file(adev->dev, &dev_attr_mem_info_preempt_used);
 
 	ttm_resource_manager_cleanup(man);
 	ttm_set_driver_manager(&adev->mman.bdev, AMDGPU_PL_PREEMPT, NULL);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index 1bc95b0cdbb8..4c9fa24dd972 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -1298,7 +1298,7 @@ int amdgpu_ras_bind_aca(struct amdgpu_device *adev, enum amdgpu_ras_block blk,
 	struct ras_manager *obj;
 
 	/* in resume phase, no need to create aca fs node */
-	if (adev->in_suspend || amdgpu_in_reset(adev))
+	if (adev->in_suspend || amdgpu_reset_in_recovery(adev))
 		return 0;
 
 	obj = get_ras_manager(adev, blk);
@@ -3610,7 +3610,7 @@ static void amdgpu_ras_event_mgr_init(struct amdgpu_device *adev)
 	ras->event_mgr = hive ? &hive->event_mgr : &ras->__event_mgr;
 
 	/* init event manager with node 0 on xgmi system */
-	if (!amdgpu_in_reset(adev)) {
+	if (!amdgpu_reset_in_recovery(adev)) {
 		if (!hive || adev->gmc.xgmi.node_id == 0)
 			ras_event_mgr_init(ras->event_mgr);
 	}
@@ -3825,7 +3825,7 @@ int amdgpu_ras_block_late_init(struct amdgpu_device *adev,
 
 	r = amdgpu_ras_feature_enable_on_boot(adev, ras_block, 1);
 	if (r) {
-		if (adev->in_suspend || amdgpu_in_reset(adev)) {
+		if (adev->in_suspend || amdgpu_reset_in_recovery(adev)) {
 			/* in resume phase, if fail to enable ras,
 			 * clean up all ras fs nodes, and disable ras */
 			goto cleanup;
@@ -3837,7 +3837,7 @@ int amdgpu_ras_block_late_init(struct amdgpu_device *adev,
 	amdgpu_persistent_edc_harvesting(adev, ras_block);
 
 	/* in resume phase, no need to create ras fs node */
-	if (adev->in_suspend || amdgpu_in_reset(adev))
+	if (adev->in_suspend || amdgpu_reset_in_recovery(adev))
 		return 0;
 
 	ras_obj = container_of(ras_block, struct amdgpu_ras_block_object, ras_comm);
@@ -3967,7 +3967,7 @@ int amdgpu_ras_late_init(struct amdgpu_device *adev)
 	amdgpu_ras_event_mgr_init(adev);
 
 	if (amdgpu_ras_aca_is_supported(adev)) {
-		if (amdgpu_in_reset(adev)) {
+		if (amdgpu_reset_in_recovery(adev)) {
 			if (amdgpu_aca_is_enabled(adev))
 				r = amdgpu_aca_reset(adev);
 			else
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.c
index 24dae7cdbe95..a0acb65f4b40 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.c
@@ -342,3 +342,8 @@ void amdgpu_reset_get_desc(struct amdgpu_reset_context *rst_ctxt, char *buf,
 		strscpy(buf, "unknown", len);
 	}
 }
+
+bool amdgpu_reset_in_recovery(struct amdgpu_device *adev)
+{
+	return (adev->init_lvl->level == AMDGPU_INIT_LEVEL_RESET_RECOVERY);
+}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.h
index f8628bc898df..4d9b9701139b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.h
@@ -158,4 +158,6 @@ extern struct amdgpu_reset_handler xgmi_reset_on_init_handler;
 int amdgpu_reset_do_xgmi_reset_on_init(
 	struct amdgpu_reset_context *reset_context);
 
+bool amdgpu_reset_in_recovery(struct amdgpu_device *adev);
+
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c
index 8c89b69edc20..113f0d242618 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c
@@ -451,6 +451,8 @@ void amdgpu_sdma_sysfs_reset_mask_fini(struct amdgpu_device *adev)
 	if (!amdgpu_gpu_recovery)
 		return;
 
-	if (adev->sdma.num_instances)
-		device_remove_file(adev->dev, &dev_attr_sdma_reset_mask);
+	if (adev->dev->kobj.sd) {
+		if (adev->sdma.num_instances)
+			device_remove_file(adev->dev, &dev_attr_sdma_reset_mask);
+	}
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
index 74fdbf71d95b..599d3ca4e0ef 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
@@ -214,15 +214,15 @@ int amdgpu_vce_sw_fini(struct amdgpu_device *adev)
 
 	drm_sched_entity_destroy(&adev->vce.entity);
 
-	amdgpu_bo_free_kernel(&adev->vce.vcpu_bo, &adev->vce.gpu_addr,
-		(void **)&adev->vce.cpu_addr);
-
 	for (i = 0; i < adev->vce.num_rings; i++)
 		amdgpu_ring_fini(&adev->vce.ring[i]);
 
 	amdgpu_ucode_release(&adev->vce.fw);
 	mutex_destroy(&adev->vce.idle_mutex);
 
+	amdgpu_bo_free_kernel(&adev->vce.vcpu_bo, &adev->vce.gpu_addr,
+		(void **)&adev->vce.cpu_addr);
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
index aecb78e0519f..3e94c3ba1ba2 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
@@ -1283,3 +1283,40 @@ int amdgpu_vcn_psp_update_sram(struct amdgpu_device *adev, int inst_idx,
 
 	return psp_execute_ip_fw_load(&adev->psp, &ucode);
 }
+
+static ssize_t amdgpu_get_vcn_reset_mask(struct device *dev,
+						struct device_attribute *attr,
+						char *buf)
+{
+	struct drm_device *ddev = dev_get_drvdata(dev);
+	struct amdgpu_device *adev = drm_to_adev(ddev);
+
+	if (!adev)
+		return -ENODEV;
+
+	return amdgpu_show_reset_mask(buf, adev->vcn.supported_reset);
+}
+
+static DEVICE_ATTR(vcn_reset_mask, 0444,
+		   amdgpu_get_vcn_reset_mask, NULL);
+
+int amdgpu_vcn_sysfs_reset_mask_init(struct amdgpu_device *adev)
+{
+	int r = 0;
+
+	if (adev->vcn.num_vcn_inst) {
+		r = device_create_file(adev->dev, &dev_attr_vcn_reset_mask);
+		if (r)
+			return r;
+	}
+
+	return r;
+}
+
+void amdgpu_vcn_sysfs_reset_mask_fini(struct amdgpu_device *adev)
+{
+	if (adev->dev->kobj.sd) {
+		if (adev->vcn.num_vcn_inst)
+			device_remove_file(adev->dev, &dev_attr_vcn_reset_mask);
+	}
+}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h
index 765b809d48a2..1e32311c1dff 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h
@@ -333,6 +333,8 @@ struct amdgpu_vcn {
 
 	/* IP reg dump */
 	uint32_t		*ip_dump;
+
+	uint32_t		supported_reset;
 };
 
 struct amdgpu_fw_shared_rb_ptrs_struct {
@@ -519,5 +521,7 @@ int amdgpu_vcn_ras_sw_init(struct amdgpu_device *adev);
 int amdgpu_vcn_psp_update_sram(struct amdgpu_device *adev, int inst_idx,
 			       enum AMDGPU_UCODE_ID ucode_id);
 int amdgpu_vcn_save_vcpu_bo(struct amdgpu_device *adev);
+int amdgpu_vcn_sysfs_reset_mask_init(struct amdgpu_device *adev);
+void amdgpu_vcn_sysfs_reset_mask_fini(struct amdgpu_device *adev);
 
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c
index 3e6f9dfb61bb..110b120d7375 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vpe.c
@@ -904,8 +904,10 @@ int amdgpu_vpe_sysfs_reset_mask_init(struct amdgpu_device *adev)
 
 void amdgpu_vpe_sysfs_reset_mask_fini(struct amdgpu_device *adev)
 {
-	if (adev->vpe.num_instances)
-		device_remove_file(adev->dev, &dev_attr_vpe_reset_mask);
+	if (adev->dev->kobj.sd) {
+		if (adev->vpe.num_instances)
+			device_remove_file(adev->dev, &dev_attr_vpe_reset_mask);
+	}
 }
 
 static const struct amdgpu_ring_funcs vpe_ring_funcs = {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
index b47422b0b5b1..74b4349e345a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
@@ -40,6 +40,11 @@
 #define smnPCS_GOPX1_PCS_ERROR_STATUS    0x12200210
 #define smnPCS_GOPX1_PCS_ERROR_NONCORRECTABLE_MASK      0x12200218
 
+#define XGMI_STATE_DISABLE                      0xD1
+#define XGMI_STATE_LS0                          0x81
+#define XGMI_LINK_ACTIVE			1
+#define XGMI_LINK_INACTIVE			0
+
 static DEFINE_MUTEX(xgmi_mutex);
 
 #define AMDGPU_MAX_XGMI_DEVICE_PER_HIVE		4
@@ -289,6 +294,42 @@ static const struct amdgpu_pcs_ras_field xgmi3x16_pcs_ras_fields[] = {
 	 SOC15_REG_FIELD(PCS_XGMI3X16_PCS_ERROR_STATUS, RxCMDPktErr)},
 };
 
+static u32 xgmi_v6_4_get_link_status(struct amdgpu_device *adev, int global_link_num)
+{
+	const u32 smnpcs_xgmi3x16_pcs_state_hist1 = 0x11a00070;
+	const int xgmi_inst = 2;
+	u32 link_inst;
+	u64 addr;
+
+	link_inst = global_link_num % xgmi_inst;
+
+	addr = (smnpcs_xgmi3x16_pcs_state_hist1 | (link_inst << 20)) +
+		adev->asic_funcs->encode_ext_smn_addressing(global_link_num / xgmi_inst);
+
+	return RREG32_PCIE_EXT(addr);
+}
+
+int amdgpu_get_xgmi_link_status(struct amdgpu_device *adev, int global_link_num)
+{
+	u32 xgmi_state_reg_val;
+
+	switch (amdgpu_ip_version(adev, XGMI_HWIP, 0)) {
+	case IP_VERSION(6, 4, 0):
+		xgmi_state_reg_val = xgmi_v6_4_get_link_status(adev, global_link_num);
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	if ((xgmi_state_reg_val & 0xFF) == XGMI_STATE_DISABLE)
+		return -ENOLINK;
+
+	if ((xgmi_state_reg_val & 0xFF) == XGMI_STATE_LS0)
+		return XGMI_LINK_ACTIVE;
+
+	return XGMI_LINK_INACTIVE;
+}
+
 /**
  * DOC: AMDGPU XGMI Support
  *
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.h
index 8cc7ab38db7c..d1282b4c6348 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.h
@@ -84,5 +84,7 @@ int amdgpu_xgmi_reset_on_init(struct amdgpu_device *adev);
 int amdgpu_xgmi_request_nps_change(struct amdgpu_device *adev,
 				   struct amdgpu_hive_info *hive,
 				   int req_nps_mode);
+int amdgpu_get_xgmi_link_status(struct amdgpu_device *adev,
+				int global_link_num);
 
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/df_v3_6.c b/drivers/gpu/drm/amd/amdgpu/df_v3_6.c
index 483a441b46aa..621aeca53880 100644
--- a/drivers/gpu/drm/amd/amdgpu/df_v3_6.c
+++ b/drivers/gpu/drm/amd/amdgpu/df_v3_6.c
@@ -254,8 +254,8 @@ static void df_v3_6_sw_init(struct amdgpu_device *adev)
 
 static void df_v3_6_sw_fini(struct amdgpu_device *adev)
 {
-
-	device_remove_file(adev->dev, &dev_attr_df_cntr_avail);
+	if (adev->dev->kobj.sd)
+		device_remove_file(adev->dev, &dev_attr_df_cntr_avail);
 
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
index 07f45f1a503a..b6016f11956e 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
@@ -87,9 +87,14 @@ static void gmc_v7_0_init_golden_registers(struct amdgpu_device *adev)
 
 static void gmc_v7_0_mc_stop(struct amdgpu_device *adev)
 {
+	struct amdgpu_ip_block *ip_block;
 	u32 blackout;
 
-	gmc_v7_0_wait_for_idle((void *)adev);
+	ip_block = amdgpu_device_ip_get_ip_block(adev, AMD_IP_BLOCK_TYPE_GMC);
+	if (!ip_block)
+		return;
+
+	gmc_v7_0_wait_for_idle(ip_block);
 
 	blackout = RREG32(mmMC_SHARED_BLACKOUT_CNTL);
 	if (REG_GET_FIELD(blackout, MC_SHARED_BLACKOUT_CNTL, BLACKOUT_MODE) != 1) {
@@ -251,9 +256,14 @@ static void gmc_v7_0_vram_gtt_location(struct amdgpu_device *adev,
  */
 static void gmc_v7_0_mc_program(struct amdgpu_device *adev)
 {
+	struct amdgpu_ip_block *ip_block;
 	u32 tmp;
 	int i, j;
 
+	ip_block = amdgpu_device_ip_get_ip_block(adev, AMD_IP_BLOCK_TYPE_GMC);
+	if (!ip_block)
+		return;
+
 	/* Initialize HDP */
 	for (i = 0, j = 0; i < 32; i++, j += 0x6) {
 		WREG32((0xb05 + j), 0x00000000);
@@ -264,7 +274,7 @@ static void gmc_v7_0_mc_program(struct amdgpu_device *adev)
 	}
 	WREG32(mmHDP_REG_COHERENCY_FLUSH_CNTL, 0);
 
-	if (gmc_v7_0_wait_for_idle((void *)adev))
+	if (gmc_v7_0_wait_for_idle(ip_block))
 		dev_warn(adev->dev, "Wait for MC idle timedout !\n");
 
 	if (adev->mode_info.num_crtc) {
@@ -288,7 +298,7 @@ static void gmc_v7_0_mc_program(struct amdgpu_device *adev)
 	WREG32(mmMC_VM_AGP_BASE, 0);
 	WREG32(mmMC_VM_AGP_TOP, adev->gmc.agp_end >> 22);
 	WREG32(mmMC_VM_AGP_BOT, adev->gmc.agp_start >> 22);
-	if (gmc_v7_0_wait_for_idle((void *)adev))
+	if (gmc_v7_0_wait_for_idle(ip_block))
 		dev_warn(adev->dev, "Wait for MC idle timedout !\n");
 
 	WREG32(mmBIF_FB_EN, BIF_FB_EN__FB_READ_EN_MASK | BIF_FB_EN__FB_WRITE_EN_MASK);
@@ -1183,7 +1193,7 @@ static int gmc_v7_0_soft_reset(struct amdgpu_ip_block *ip_block)
 
 	if (srbm_soft_reset) {
 		gmc_v7_0_mc_stop(adev);
-		if (gmc_v7_0_wait_for_idle((void *)adev))
+		if (gmc_v7_0_wait_for_idle(ip_block))
 			dev_warn(adev->dev, "Wait for GMC idle timed out !\n");
 
 		tmp = RREG32(mmSRBM_SOFT_RESET);
diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v1_0.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v1_0.c
index 03b8b7cd5229..7319299f25ae 100644
--- a/drivers/gpu/drm/amd/amdgpu/jpeg_v1_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v1_0.c
@@ -604,7 +604,7 @@ static void jpeg_v1_0_set_irq_funcs(struct amdgpu_device *adev)
 static void jpeg_v1_0_ring_begin_use(struct amdgpu_ring *ring)
 {
 	struct	amdgpu_device *adev = ring->adev;
-	bool	set_clocks = !cancel_delayed_work_sync(&adev->vcn.idle_work);
+	bool	set_clocks = !cancel_delayed_work_sync(&adev->jpeg.idle_work);
 	int		cnt = 0;
 
 	mutex_lock(&adev->vcn.vcn1_jpeg1_workaround);
diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.c
index d6823fb45d32..6e29b69894a5 100644
--- a/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.c
@@ -150,7 +150,7 @@ static int jpeg_v2_0_hw_fini(struct amdgpu_ip_block *ip_block)
 {
 	struct amdgpu_device *adev = ip_block->adev;
 
-	cancel_delayed_work_sync(&adev->vcn.idle_work);
+	cancel_delayed_work_sync(&adev->jpeg.idle_work);
 
 	if (adev->jpeg.cur_state != AMD_PG_STATE_GATE &&
 	      RREG32_SOC15(JPEG, 0, mmUVD_JRBC_STATUS))
diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v2_5.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_5.c
index 5063a38801d6..9ac421486f05 100644
--- a/drivers/gpu/drm/amd/amdgpu/jpeg_v2_5.c
+++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_5.c
@@ -211,7 +211,7 @@ static int jpeg_v2_5_hw_fini(struct amdgpu_ip_block *ip_block)
 	struct amdgpu_device *adev = ip_block->adev;
 	int i;
 
-	cancel_delayed_work_sync(&adev->vcn.idle_work);
+	cancel_delayed_work_sync(&adev->jpeg.idle_work);
 
 	for (i = 0; i < adev->jpeg.num_jpeg_inst; ++i) {
 		if (adev->jpeg.harvest_config & (1 << i))
diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v3_0.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v3_0.c
index 10adbb7cbf53..e0df6800502c 100644
--- a/drivers/gpu/drm/amd/amdgpu/jpeg_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v3_0.c
@@ -164,7 +164,7 @@ static int jpeg_v3_0_hw_fini(struct amdgpu_ip_block *ip_block)
 {
 	struct amdgpu_device *adev = ip_block->adev;
 
-	cancel_delayed_work_sync(&adev->vcn.idle_work);
+	cancel_delayed_work_sync(&adev->jpeg.idle_work);
 
 	if (adev->jpeg.cur_state != AMD_PG_STATE_GATE &&
 	      RREG32_SOC15(JPEG, 0, mmUVD_JRBC_STATUS))
diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c
index 193dfac5dc76..eca1963c33b6 100644
--- a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c
@@ -202,7 +202,7 @@ static int jpeg_v4_0_hw_fini(struct amdgpu_ip_block *ip_block)
 {
 	struct amdgpu_device *adev = ip_block->adev;
 
-	cancel_delayed_work_sync(&adev->vcn.idle_work);
+	cancel_delayed_work_sync(&adev->jpeg.idle_work);
 	if (!amdgpu_sriov_vf(adev)) {
 		if (adev->jpeg.cur_state != AMD_PG_STATE_GATE &&
 			RREG32_SOC15(JPEG, 0, regUVD_JRBC_STATUS))
diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_5.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_5.c
index b48e2412e6cc..1d9e3b101c3a 100644
--- a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_5.c
+++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_5.c
@@ -227,7 +227,7 @@ static int jpeg_v4_0_5_hw_fini(struct amdgpu_ip_block *ip_block)
 	struct amdgpu_device *adev = ip_block->adev;
 	int i;
 
-	cancel_delayed_work_sync(&adev->vcn.idle_work);
+	cancel_delayed_work_sync(&adev->jpeg.idle_work);
 
 	for (i = 0; i < adev->jpeg.num_jpeg_inst; ++i) {
 		if (adev->jpeg.harvest_config & (1 << i))
diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_0.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_0.c
index 686f9605239d..58fb1e5fa89c 100644
--- a/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_0.c
@@ -168,7 +168,7 @@ static int jpeg_v5_0_0_hw_fini(struct amdgpu_ip_block *ip_block)
 {
 	struct amdgpu_device *adev = ip_block->adev;
 
-	cancel_delayed_work_sync(&adev->vcn.idle_work);
+	cancel_delayed_work_sync(&adev->jpeg.idle_work);
 
 	if (adev->jpeg.cur_state != AMD_PG_STATE_GATE &&
 	      RREG32_SOC15(JPEG, 0, regUVD_JRBC_STATUS))
diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_11.c b/drivers/gpu/drm/amd/amdgpu/nbio_v7_11.c
index 7a9adfda5814..814ab59fdd4a 100644
--- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_11.c
+++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_11.c
@@ -275,6 +275,15 @@ static void nbio_v7_11_init_registers(struct amdgpu_device *adev)
 	if (def != data)
 		WREG32_SOC15(NBIO, 0, regBIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3, data);
 
+	switch (adev->ip_versions[NBIO_HWIP][0]) {
+	case IP_VERSION(7, 11, 0):
+	case IP_VERSION(7, 11, 1):
+	case IP_VERSION(7, 11, 2):
+	case IP_VERSION(7, 11, 3):
+		data = RREG32_SOC15(NBIO, 0, regRCC_DEV0_EPF5_STRAP4) & ~BIT(23);
+		WREG32_SOC15(NBIO, 0, regRCC_DEV0_EPF5_STRAP4, data);
+		break;
+	}
 }
 
 static void nbio_v7_11_update_medium_grain_clock_gating(struct amdgpu_device *adev,
diff --git a/drivers/gpu/drm/amd/amdgpu/sienna_cichlid.c b/drivers/gpu/drm/amd/amdgpu/sienna_cichlid.c
index 9b01e074af47..2594467bdd87 100644
--- a/drivers/gpu/drm/amd/amdgpu/sienna_cichlid.c
+++ b/drivers/gpu/drm/amd/amdgpu/sienna_cichlid.c
@@ -220,6 +220,7 @@ sienna_cichlid_mode2_restore_hwcontext(struct amdgpu_reset_control *reset_ctl,
 	int r;
 	struct amdgpu_device *tmp_adev = (struct amdgpu_device *)reset_ctl->handle;
 
+	amdgpu_set_init_level(tmp_adev, AMDGPU_INIT_LEVEL_RESET_RECOVERY);
 	dev_info(tmp_adev->dev,
 			"GPU reset succeeded, trying to resume\n");
 	r = sienna_cichlid_mode2_restore_ip(tmp_adev);
@@ -237,6 +238,7 @@ sienna_cichlid_mode2_restore_hwcontext(struct amdgpu_reset_control *reset_ctl,
 
 	amdgpu_irq_gpu_reset_resume_helper(tmp_adev);
 
+	amdgpu_set_init_level(tmp_adev, AMDGPU_INIT_LEVEL_DEFAULT);
 	r = amdgpu_ib_ring_tests(tmp_adev);
 	if (r) {
 		dev_err(tmp_adev->dev,
diff --git a/drivers/gpu/drm/amd/amdgpu/smu_v13_0_10.c b/drivers/gpu/drm/amd/amdgpu/smu_v13_0_10.c
index e70ebad3f9fa..70569ea906bc 100644
--- a/drivers/gpu/drm/amd/amdgpu/smu_v13_0_10.c
+++ b/drivers/gpu/drm/amd/amdgpu/smu_v13_0_10.c
@@ -221,6 +221,7 @@ smu_v13_0_10_mode2_restore_hwcontext(struct amdgpu_reset_control *reset_ctl,
 	int r;
 	struct amdgpu_device *tmp_adev = (struct amdgpu_device *)reset_ctl->handle;
 
+	amdgpu_set_init_level(tmp_adev, AMDGPU_INIT_LEVEL_RESET_RECOVERY);
 	dev_info(tmp_adev->dev,
 			"GPU reset succeeded, trying to resume\n");
 	r = smu_v13_0_10_mode2_restore_ip(tmp_adev);
@@ -234,6 +235,7 @@ smu_v13_0_10_mode2_restore_hwcontext(struct amdgpu_reset_control *reset_ctl,
 
 	amdgpu_irq_gpu_reset_resume_helper(tmp_adev);
 
+	amdgpu_set_init_level(tmp_adev, AMDGPU_INIT_LEVEL_DEFAULT);
 	r = amdgpu_ib_ring_tests(tmp_adev);
 	if (r) {
 		dev_err(tmp_adev->dev,
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c
index 5512259cac79..fcc8511e91ee 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c
@@ -225,6 +225,10 @@ static int vcn_v4_0_sw_init(struct amdgpu_ip_block *ip_block)
 		vcn_v4_0_fw_shared_init(adev, i);
 	}
 
+	/* TODO: Add queue reset mask when FW fully supports it */
+	adev->vcn.supported_reset =
+		amdgpu_get_soft_full_reset_mask(&adev->vcn.inst[0].ring_enc[0]);
+
 	if (amdgpu_sriov_vf(adev)) {
 		r = amdgpu_virt_alloc_mm_table(adev);
 		if (r)
@@ -247,6 +251,10 @@ static int vcn_v4_0_sw_init(struct amdgpu_ip_block *ip_block)
 		adev->vcn.ip_dump = ptr;
 	}
 
+	r = amdgpu_vcn_sysfs_reset_mask_init(adev);
+	if (r)
+		return r;
+
 	return 0;
 }
 
@@ -284,6 +292,7 @@ static int vcn_v4_0_sw_fini(struct amdgpu_ip_block *ip_block)
 	if (r)
 		return r;
 
+	amdgpu_vcn_sysfs_reset_mask_fini(adev);
 	r = amdgpu_vcn_sw_fini(adev);
 
 	kfree(adev->vcn.ip_dump);
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c
index cf808a153fce..3f69b9b2bcd0 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c
@@ -123,6 +123,20 @@ static int vcn_v4_0_3_early_init(struct amdgpu_ip_block *ip_block)
 	return amdgpu_vcn_early_init(adev);
 }
 
+static int vcn_v4_0_3_fw_shared_init(struct amdgpu_device *adev, int inst_idx)
+{
+	struct amdgpu_vcn4_fw_shared *fw_shared;
+
+	fw_shared = adev->vcn.inst[inst_idx].fw_shared.cpu_addr;
+	fw_shared->present_flag_0 = cpu_to_le32(AMDGPU_FW_SHARED_FLAG_0_UNIFIED_QUEUE);
+	fw_shared->sq.is_enabled = 1;
+
+	if (amdgpu_vcnfw_log)
+		amdgpu_vcn_fwlog_init(&adev->vcn.inst[inst_idx]);
+
+	return 0;
+}
+
 /**
  * vcn_v4_0_3_sw_init - sw init for VCN block
  *
@@ -155,8 +169,6 @@ static int vcn_v4_0_3_sw_init(struct amdgpu_ip_block *ip_block)
 		return r;
 
 	for (i = 0; i < adev->vcn.num_vcn_inst; i++) {
-		volatile struct amdgpu_vcn4_fw_shared *fw_shared;
-
 		vcn_inst = GET_INST(VCN, i);
 
 		ring = &adev->vcn.inst[i].ring_enc[0];
@@ -179,14 +191,13 @@ static int vcn_v4_0_3_sw_init(struct amdgpu_ip_block *ip_block)
 		if (r)
 			return r;
 
-		fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr;
-		fw_shared->present_flag_0 = cpu_to_le32(AMDGPU_FW_SHARED_FLAG_0_UNIFIED_QUEUE);
-		fw_shared->sq.is_enabled = true;
-
-		if (amdgpu_vcnfw_log)
-			amdgpu_vcn_fwlog_init(&adev->vcn.inst[i]);
+		vcn_v4_0_3_fw_shared_init(adev, i);
 	}
 
+	/* TODO: Add queue reset mask when FW fully supports it */
+	adev->vcn.supported_reset =
+		amdgpu_get_soft_full_reset_mask(&adev->vcn.inst[0].ring_enc[0]);
+
 	if (amdgpu_sriov_vf(adev)) {
 		r = amdgpu_virt_alloc_mm_table(adev);
 		if (r)
@@ -213,6 +224,10 @@ static int vcn_v4_0_3_sw_init(struct amdgpu_ip_block *ip_block)
 		adev->vcn.ip_dump = ptr;
 	}
 
+	r = amdgpu_vcn_sysfs_reset_mask_init(adev);
+	if (r)
+		return r;
+
 	return 0;
 }
 
@@ -246,6 +261,7 @@ static int vcn_v4_0_3_sw_fini(struct amdgpu_ip_block *ip_block)
 	if (r)
 		return r;
 
+	amdgpu_vcn_sysfs_reset_mask_fini(adev);
 	r = amdgpu_vcn_sw_fini(adev);
 
 	kfree(adev->vcn.ip_dump);
@@ -280,6 +296,8 @@ static int vcn_v4_0_3_hw_init(struct amdgpu_ip_block *ip_block)
 		}
 	} else {
 		for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
+			struct amdgpu_vcn4_fw_shared *fw_shared;
+
 			vcn_inst = GET_INST(VCN, i);
 			ring = &adev->vcn.inst[i].ring_enc[0];
 
@@ -303,6 +321,11 @@ static int vcn_v4_0_3_hw_init(struct amdgpu_ip_block *ip_block)
 					regVCN_RB1_DB_CTRL);
 			}
 
+			/* Re-init fw_shared when RAS fatal error occurred */
+			fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr;
+			if (!fw_shared->sq.is_enabled)
+				vcn_v4_0_3_fw_shared_init(adev, i);
+
 			r = amdgpu_ring_test_helper(ring);
 			if (r)
 				return r;
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c
index fe2cc1a80c13..bd3d2bbdc16b 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c
@@ -170,6 +170,10 @@ static int vcn_v5_0_0_sw_init(struct amdgpu_ip_block *ip_block)
 			amdgpu_vcn_fwlog_init(&adev->vcn.inst[i]);
 	}
 
+	/* TODO: Add queue reset mask when FW fully supports it */
+	adev->vcn.supported_reset =
+		amdgpu_get_soft_full_reset_mask(&adev->vcn.inst[0].ring_enc[0]);
+
 	if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG)
 		adev->vcn.pause_dpg_mode = vcn_v5_0_0_pause_dpg_mode;
 
@@ -181,6 +185,11 @@ static int vcn_v5_0_0_sw_init(struct amdgpu_ip_block *ip_block)
 	} else {
 		adev->vcn.ip_dump = ptr;
 	}
+
+	r = amdgpu_vcn_sysfs_reset_mask_init(adev);
+	if (r)
+		return r;
+
 	return 0;
 }
 
@@ -215,6 +224,7 @@ static int vcn_v5_0_0_sw_fini(struct amdgpu_ip_block *ip_block)
 	if (r)
 		return r;
 
+	amdgpu_vcn_sysfs_reset_mask_fini(adev);
 	r = amdgpu_vcn_sw_fini(adev);
 
 	kfree(adev->vcn.ip_dump);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c b/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c
index 4843dcb9a5f7..2b0a830f5b29 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c
@@ -125,7 +125,7 @@ static bool kq_initialize(struct kernel_queue *kq, struct kfd_node *dev,
 
 	memset(kq->pq_kernel_addr, 0, queue_size);
 	memset(kq->rptr_kernel, 0, sizeof(*kq->rptr_kernel));
-	memset(kq->wptr_kernel, 0, sizeof(*kq->wptr_kernel));
+	memset(kq->wptr_kernel, 0, dev->kfd->device_info.doorbell_size);
 
 	prop.queue_size = queue_size;
 	prop.is_interop = false;
@@ -306,12 +306,17 @@ int kq_submit_packet(struct kernel_queue *kq)
 	if (amdgpu_amdkfd_is_fed(kq->dev->adev))
 		return -EIO;
 
+	/* Make sure ring buffer is updated before wptr updated */
+	mb();
+
 	if (kq->dev->kfd->device_info.doorbell_size == 8) {
 		*kq->wptr64_kernel = kq->pending_wptr64;
+		mb(); /* Make sure wptr updated before ring doorbell */
 		write_kernel_doorbell64(kq->queue->properties.doorbell_ptr,
 					kq->pending_wptr64);
 	} else {
 		*kq->wptr_kernel = kq->pending_wptr;
+		mb(); /* Make sure wptr updated before ring doorbell */
 		write_kernel_doorbell(kq->queue->properties.doorbell_ptr,
 					kq->pending_wptr);
 	}
diff --git a/drivers/gpu/drm/amd/display/Kconfig b/drivers/gpu/drm/amd/display/Kconfig
index df17e79c45c7..11e3f2f3b174 100644
--- a/drivers/gpu/drm/amd/display/Kconfig
+++ b/drivers/gpu/drm/amd/display/Kconfig
@@ -7,20 +7,21 @@ menu "Display Engine Configuration"
 config DRM_AMD_DC
 	bool "AMD DC - Enable new display engine"
 	default y
-	depends on BROKEN || !CC_IS_CLANG || ARM64 || RISCV || SPARC64 || X86_64
+	depends on BROKEN || !CC_IS_CLANG || ARM64 || LOONGARCH || RISCV || SPARC64 || X86_64
 	select SND_HDA_COMPONENT if SND_HDA_CORE
 	# !CC_IS_CLANG: https://github.com/ClangBuiltLinux/linux/issues/1752
-	select DRM_AMD_DC_FP if ARCH_HAS_KERNEL_FPU_SUPPORT && !(CC_IS_CLANG && (ARM64 || RISCV))
+	select DRM_AMD_DC_FP if ARCH_HAS_KERNEL_FPU_SUPPORT && !(CC_IS_CLANG && (ARM64 || LOONGARCH || RISCV))
 	help
 	  Choose this option if you want to use the new display engine
 	  support for AMDGPU. This adds required support for Vega and
 	  Raven ASICs.
 
-	  calculate_bandwidth() is presently broken on all !(X86_64 || SPARC64 || ARM64)
-	  architectures built with Clang (all released versions), whereby the stack
-	  frame gets blown up to well over 5k.  This would cause an immediate kernel
-	  panic on most architectures.  We'll revert this when the following bug report
-	  has been resolved: https://github.com/llvm/llvm-project/issues/41896.
+	  calculate_bandwidth() is presently broken on all !(X86_64 || SPARC64 ||
+	  ARM64 || LOONGARCH || RISCV) architectures built with Clang (all released
+	  versions), whereby the stack frame gets blown up to well over 5k.  This
+	  would cause an immediate kernel panic on most architectures.  We'll revert
+	  this when the following bug report has been resolved:
+	  https://github.com/llvm/llvm-project/issues/41896.
 
 config DRM_AMD_DC_FP
 	def_bool n
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c
index 7872c6cabb14..1dd26d5df6b9 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc.c
@@ -3141,7 +3141,10 @@ static void restore_planes_and_stream_state(
 		return;
 
 	for (i = 0; i < status->plane_count; i++) {
+		/* refcount will always be valid, restore everything else */
+		struct kref refcount = status->plane_states[i]->refcount;
 		*status->plane_states[i] = scratch->plane_states[i];
+		status->plane_states[i]->refcount = refcount;
 	}
 	*stream = scratch->stream_state;
 }
@@ -6097,11 +6100,11 @@ struct dc_power_profile dc_get_power_profile_for_dc_state(const struct dc_state
 {
 	struct dc_power_profile profile = { 0 };
 
-	if (!context || !context->clk_mgr || !context->clk_mgr->ctx || !context->clk_mgr->ctx->dc)
+	profile.power_level = !context->bw_ctx.bw.dcn.clk.p_state_change_support;
+	if (!context->clk_mgr || !context->clk_mgr->ctx || !context->clk_mgr->ctx->dc)
 		return profile;
 	struct dc *dc = context->clk_mgr->ctx->dc;
 
-
 	if (dc->res_pool->funcs->get_power_profile)
 		profile.power_level = dc->res_pool->funcs->get_power_profile(context);
 	return profile;
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 0419ee7f22a5..252af83e34a5 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
@@ -898,6 +898,9 @@ void hwss_setup_dpp(union block_sequence_params *params)
 	struct dpp *dpp = pipe_ctx->plane_res.dpp;
 	struct dc_plane_state *plane_state = pipe_ctx->plane_state;
 
+	if (!plane_state)
+		return;
+
 	if (dpp && dpp->funcs->dpp_setup) {
 		// program the input csc
 		dpp->funcs->dpp_setup(dpp,
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
index 33125b95c3a1..619fad17de55 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
@@ -1501,6 +1501,10 @@ bool resource_build_scaling_params(struct pipe_ctx *pipe_ctx)
 		res = spl_calculate_scaler_params(spl_in, spl_out);
 		// Convert respective out params from SPL to scaler data
 		translate_SPL_out_params_to_pipe_ctx(pipe_ctx, spl_out);
+
+		/* Ignore scaler failure if pipe context plane is phantom plane */
+		if (!res && plane_state->is_phantom)
+			res = true;
 	} else {
 #endif
 	/* depends on h_active */
@@ -1571,6 +1575,10 @@ bool resource_build_scaling_params(struct pipe_ctx *pipe_ctx)
 					&plane_state->scaling_quality);
 	}
 
+	/* Ignore scaler failure if pipe context plane is phantom plane */
+	if (!res && plane_state->is_phantom)
+		res = true;
+
 	if (res && (pipe_ctx->plane_res.scl_data.taps.v_taps != temp.v_taps ||
 		pipe_ctx->plane_res.scl_data.taps.h_taps != temp.h_taps ||
 		pipe_ctx->plane_res.scl_data.taps.v_taps_c != temp.v_taps_c ||
diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h
index e143fab00a86..104051935884 100644
--- a/drivers/gpu/drm/amd/display/dc/dc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc.h
@@ -55,7 +55,7 @@ struct aux_payload;
 struct set_config_cmd_payload;
 struct dmub_notification;
 
-#define DC_VER "3.2.309"
+#define DC_VER "3.2.310"
 
 #define MAX_SURFACES 3
 #define MAX_PLANES 6
diff --git a/drivers/gpu/drm/amd/display/dc/dccg/dcn35/dcn35_dccg.c b/drivers/gpu/drm/amd/display/dc/dccg/dcn35/dcn35_dccg.c
index 838d72eaa87f..b363f5360818 100644
--- a/drivers/gpu/drm/amd/display/dc/dccg/dcn35/dcn35_dccg.c
+++ b/drivers/gpu/drm/amd/display/dc/dccg/dcn35/dcn35_dccg.c
@@ -1392,10 +1392,10 @@ static void dccg35_set_dtbclk_dto(
 
 		/* The recommended programming sequence to enable DTBCLK DTO to generate
 		 * valid pixel HPO DPSTREAM ENCODER, specifies that DTO source select should
-		 * be set only after DTO is enabled
+		 * be set only after DTO is enabled.
+		 * PIPEx_DTO_SRC_SEL should not be programmed during DTBCLK update since OTG may still be on, and the
+		 * programming is handled in program_pix_clk() regardless, so it can be removed from here.
 		 */
-		REG_UPDATE(OTG_PIXEL_RATE_CNTL[params->otg_inst],
-				PIPE_DTO_SRC_SEL[params->otg_inst], 2);
 	} else {
 		switch (params->otg_inst) {
 		case 0:
@@ -1412,9 +1412,12 @@ static void dccg35_set_dtbclk_dto(
 			break;
 		}
 
-		REG_UPDATE_2(OTG_PIXEL_RATE_CNTL[params->otg_inst],
-				DTBCLK_DTO_ENABLE[params->otg_inst], 0,
-				PIPE_DTO_SRC_SEL[params->otg_inst], params->is_hdmi ? 0 : 1);
+		/**
+		 * PIPEx_DTO_SRC_SEL should not be programmed during DTBCLK update since OTG may still be on, and the
+		 * programming is handled in program_pix_clk() regardless, so it can be removed from here.
+		 */
+		REG_UPDATE(OTG_PIXEL_RATE_CNTL[params->otg_inst],
+				DTBCLK_DTO_ENABLE[params->otg_inst], 0);
 
 		REG_WRITE(DTBCLK_DTO_MODULO[params->otg_inst], 0);
 		REG_WRITE(DTBCLK_DTO_PHASE[params->otg_inst], 0);
diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_core/dml2_core_dcn4_calcs.c b/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_core/dml2_core_dcn4_calcs.c
index 92e43a1e4dd4..601320b1be81 100644
--- a/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_core/dml2_core_dcn4_calcs.c
+++ b/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_core/dml2_core_dcn4_calcs.c
@@ -11,6 +11,7 @@
 
 #define DML2_MAX_FMT_420_BUFFER_WIDTH 4096
 #define DML_MAX_NUM_OF_SLICES_PER_DSC 4
+#define ALLOW_SDPIF_RATE_LIMIT_PRE_CSTATE
 
 const char *dml2_core_internal_bw_type_str(enum dml2_core_internal_bw_type bw_type)
 {
@@ -3886,6 +3887,10 @@ static void CalculateSwathAndDETConfiguration(struct dml2_core_internal_scratch
 #endif
 
 	*p->hw_debug5 = false;
+#ifdef ALLOW_SDPIF_RATE_LIMIT_PRE_CSTATE
+	if (p->NumberOfActiveSurfaces > 1)
+		*p->hw_debug5 = true;
+#else
 	for (unsigned int k = 0; k < p->NumberOfActiveSurfaces; ++k) {
 		if (!(p->mrq_present) && (!(*p->UnboundedRequestEnabled)) && (TotalActiveDPP == 1)
 			&& p->display_cfg->plane_descriptors[k].surface.dcc.enable
@@ -3901,6 +3906,7 @@ static void CalculateSwathAndDETConfiguration(struct dml2_core_internal_scratch
 		dml2_printf("DML::%s: k=%u hw_debug5 = %u\n", __func__, k, *p->hw_debug5);
 #endif
 	}
+#endif
 }
 
 static enum dml2_odm_mode DecideODMMode(unsigned int HActive,
diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml2_dc_resource_mgmt.c b/drivers/gpu/drm/amd/display/dc/dml2/dml2_dc_resource_mgmt.c
index 6eccf0241d85..1ed21c1b86a5 100644
--- a/drivers/gpu/drm/amd/display/dc/dml2/dml2_dc_resource_mgmt.c
+++ b/drivers/gpu/drm/amd/display/dc/dml2/dml2_dc_resource_mgmt.c
@@ -258,12 +258,25 @@ static unsigned int find_preferred_pipe_candidates(const struct dc_state *existi
 	 * However this condition comes with a caveat. We need to ignore pipes that will
 	 * require a change in OPP but still have the same stream id. For example during
 	 * an MPC to ODM transiton.
+	 *
+	 * Adding check to avoid pipe select on the head pipe by utilizing dc resource
+	 * helper function resource_get_primary_dpp_pipe and comparing the pipe index.
 	 */
 	if (existing_state) {
 		for (i = 0; i < pipe_count; i++) {
 			if (existing_state->res_ctx.pipe_ctx[i].stream && existing_state->res_ctx.pipe_ctx[i].stream->stream_id == stream_id) {
+				struct pipe_ctx *head_pipe =
+					resource_is_pipe_type(&existing_state->res_ctx.pipe_ctx[i], DPP_PIPE) ?
+						resource_get_primary_dpp_pipe(&existing_state->res_ctx.pipe_ctx[i]) :
+							NULL;
+
+				// we should always respect the head pipe from selection
+				if (head_pipe && head_pipe->pipe_idx == i)
+					continue;
 				if (existing_state->res_ctx.pipe_ctx[i].plane_res.hubp &&
-					existing_state->res_ctx.pipe_ctx[i].plane_res.hubp->opp_id != i)
+					existing_state->res_ctx.pipe_ctx[i].plane_res.hubp->opp_id != i &&
+						(existing_state->res_ctx.pipe_ctx[i].prev_odm_pipe ||
+						existing_state->res_ctx.pipe_ctx[i].next_odm_pipe))
 					continue;
 
 				preferred_pipe_candidates[num_preferred_candidates++] = i;
@@ -292,6 +305,14 @@ static unsigned int find_last_resort_pipe_candidates(const struct dc_state *exis
 	 */
 	if (existing_state) {
 		for (i  = 0; i < pipe_count; i++) {
+			struct pipe_ctx *head_pipe =
+				resource_is_pipe_type(&existing_state->res_ctx.pipe_ctx[i], DPP_PIPE) ?
+					resource_get_primary_dpp_pipe(&existing_state->res_ctx.pipe_ctx[i]) :
+						NULL;
+
+			// we should always respect the head pipe from selection
+			if (head_pipe && head_pipe->pipe_idx == i)
+				continue;
 			if ((existing_state->res_ctx.pipe_ctx[i].plane_res.hubp &&
 				existing_state->res_ctx.pipe_ctx[i].plane_res.hubp->opp_id != i) ||
 				existing_state->res_ctx.pipe_ctx[i].stream_res.tg)
diff --git a/drivers/gpu/drm/amd/display/dc/dsc/dc_dsc.c b/drivers/gpu/drm/amd/display/dc/dsc/dc_dsc.c
index ebd5df1a36e8..d9aaebfa3a0a 100644
--- a/drivers/gpu/drm/amd/display/dc/dsc/dc_dsc.c
+++ b/drivers/gpu/drm/amd/display/dc/dsc/dc_dsc.c
@@ -1093,14 +1093,11 @@ static bool setup_dsc_config(
 	if (!is_dsc_possible)
 		goto done;
 
-	// Final decission: can we do DSC or not?
-	if (is_dsc_possible) {
-		// Fill out the rest of DSC settings
-		dsc_cfg->block_pred_enable = dsc_common_caps.is_block_pred_supported;
-		dsc_cfg->linebuf_depth = dsc_common_caps.lb_bit_depth;
-		dsc_cfg->version_minor = (dsc_common_caps.dsc_version & 0xf0) >> 4;
-		dsc_cfg->is_dp = dsc_sink_caps->is_dp;
-	}
+	/* Fill out the rest of DSC settings */
+	dsc_cfg->block_pred_enable = dsc_common_caps.is_block_pred_supported;
+	dsc_cfg->linebuf_depth = dsc_common_caps.lb_bit_depth;
+	dsc_cfg->version_minor = (dsc_common_caps.dsc_version & 0xf0) >> 4;
+	dsc_cfg->is_dp = dsc_sink_caps->is_dp;
 
 done:
 	if (!is_dsc_possible)
diff --git a/drivers/gpu/drm/amd/display/dc/hubbub/dcn10/dcn10_hubbub.h b/drivers/gpu/drm/amd/display/dc/hubbub/dcn10/dcn10_hubbub.h
index 4bd1dda07719..9fbd45c7dfef 100644
--- a/drivers/gpu/drm/amd/display/dc/hubbub/dcn10/dcn10_hubbub.h
+++ b/drivers/gpu/drm/amd/display/dc/hubbub/dcn10/dcn10_hubbub.h
@@ -200,6 +200,7 @@ struct dcn_hubbub_registers {
 	uint32_t DCHUBBUB_ARB_FRAC_URG_BW_MALL_B;
 	uint32_t DCHUBBUB_TIMEOUT_DETECTION_CTRL1;
 	uint32_t DCHUBBUB_TIMEOUT_DETECTION_CTRL2;
+	uint32_t DCHUBBUB_CTRL_STATUS;
 };
 
 #define HUBBUB_REG_FIELD_LIST_DCN32(type) \
@@ -320,7 +321,12 @@ struct dcn_hubbub_registers {
 		type DCHUBBUB_TIMEOUT_REQ_STALL_THRESHOLD;\
 		type DCHUBBUB_TIMEOUT_PSTATE_STALL_THRESHOLD;\
 		type DCHUBBUB_TIMEOUT_DETECTION_EN;\
-		type DCHUBBUB_TIMEOUT_TIMER_RESET
+		type DCHUBBUB_TIMEOUT_TIMER_RESET;\
+		type ROB_UNDERFLOW_STATUS;\
+		type ROB_OVERFLOW_STATUS;\
+		type ROB_OVERFLOW_CLEAR;\
+		type DCHUBBUB_HW_DEBUG;\
+		type CSTATE_SWATH_CHK_GOOD_MODE
 
 #define HUBBUB_STUTTER_REG_FIELD_LIST(type) \
 		type DCHUBBUB_ARB_ALLOW_SR_ENTER_WATERMARK_A;\
diff --git a/drivers/gpu/drm/amd/display/dc/hubbub/dcn20/dcn20_hubbub.h b/drivers/gpu/drm/amd/display/dc/hubbub/dcn20/dcn20_hubbub.h
index 036bb3e6c957..46d8f5c70750 100644
--- a/drivers/gpu/drm/amd/display/dc/hubbub/dcn20/dcn20_hubbub.h
+++ b/drivers/gpu/drm/amd/display/dc/hubbub/dcn20/dcn20_hubbub.h
@@ -96,6 +96,7 @@ struct dcn20_hubbub {
 	unsigned int det1_size;
 	unsigned int det2_size;
 	unsigned int det3_size;
+	bool allow_sdpif_rate_limit_when_cstate_req;
 };
 
 void hubbub2_construct(struct dcn20_hubbub *hubbub,
diff --git a/drivers/gpu/drm/amd/display/dc/hubbub/dcn401/dcn401_hubbub.c b/drivers/gpu/drm/amd/display/dc/hubbub/dcn401/dcn401_hubbub.c
index 5d658e9bef64..92fab471b183 100644
--- a/drivers/gpu/drm/amd/display/dc/hubbub/dcn401/dcn401_hubbub.c
+++ b/drivers/gpu/drm/amd/display/dc/hubbub/dcn401/dcn401_hubbub.c
@@ -1192,15 +1192,35 @@ static void dcn401_wait_for_det_update(struct hubbub *hubbub, int hubp_inst)
 	}
 }
 
-static void dcn401_program_timeout_thresholds(struct hubbub *hubbub, struct dml2_display_arb_regs *arb_regs)
+static bool dcn401_program_arbiter(struct hubbub *hubbub, struct dml2_display_arb_regs *arb_regs, bool safe_to_lower)
 {
 	struct dcn20_hubbub *hubbub2 = TO_DCN20_HUBBUB(hubbub);
 
+	bool wm_pending = false;
+	uint32_t temp;
+
 	/* request backpressure and outstanding return threshold (unused)*/
 	//REG_UPDATE(DCHUBBUB_TIMEOUT_DETECTION_CTRL1, DCHUBBUB_TIMEOUT_REQ_STALL_THRESHOLD, arb_regs->req_stall_threshold);
 
 	/* P-State stall threshold */
 	REG_UPDATE(DCHUBBUB_TIMEOUT_DETECTION_CTRL2, DCHUBBUB_TIMEOUT_PSTATE_STALL_THRESHOLD, arb_regs->pstate_stall_threshold);
+
+	if (safe_to_lower || arb_regs->allow_sdpif_rate_limit_when_cstate_req > hubbub2->allow_sdpif_rate_limit_when_cstate_req) {
+		hubbub2->allow_sdpif_rate_limit_when_cstate_req = arb_regs->allow_sdpif_rate_limit_when_cstate_req;
+
+		/* only update the required bits */
+		REG_GET(DCHUBBUB_CTRL_STATUS, DCHUBBUB_HW_DEBUG, &temp);
+		if (hubbub2->allow_sdpif_rate_limit_when_cstate_req) {
+			temp |= (1 << 5);
+		} else {
+			temp &= ~(1 << 5);
+		}
+		REG_UPDATE(DCHUBBUB_CTRL_STATUS, DCHUBBUB_HW_DEBUG, temp);
+	} else {
+		wm_pending = true;
+	}
+
+	return wm_pending;
 }
 
 static const struct hubbub_funcs hubbub4_01_funcs = {
@@ -1226,7 +1246,7 @@ static const struct hubbub_funcs hubbub4_01_funcs = {
 	.program_det_segments = dcn401_program_det_segments,
 	.program_compbuf_segments = dcn401_program_compbuf_segments,
 	.wait_for_det_update = dcn401_wait_for_det_update,
-	.program_timeout_thresholds = dcn401_program_timeout_thresholds,
+	.program_arbiter = dcn401_program_arbiter,
 };
 
 void hubbub401_construct(struct dcn20_hubbub *hubbub2,
diff --git a/drivers/gpu/drm/amd/display/dc/hubbub/dcn401/dcn401_hubbub.h b/drivers/gpu/drm/amd/display/dc/hubbub/dcn401/dcn401_hubbub.h
index 5f1960722ebd..b1d9ea9d1c3d 100644
--- a/drivers/gpu/drm/amd/display/dc/hubbub/dcn401/dcn401_hubbub.h
+++ b/drivers/gpu/drm/amd/display/dc/hubbub/dcn401/dcn401_hubbub.h
@@ -128,7 +128,12 @@
 	HUBBUB_SF(DCHUBBUB_TIMEOUT_DETECTION_CTRL1, DCHUBBUB_TIMEOUT_REQ_STALL_THRESHOLD, mask_sh),\
 	HUBBUB_SF(DCHUBBUB_TIMEOUT_DETECTION_CTRL2, DCHUBBUB_TIMEOUT_PSTATE_STALL_THRESHOLD, mask_sh),\
 	HUBBUB_SF(DCHUBBUB_TIMEOUT_DETECTION_CTRL2, DCHUBBUB_TIMEOUT_DETECTION_EN, mask_sh),\
-	HUBBUB_SF(DCHUBBUB_TIMEOUT_DETECTION_CTRL2, DCHUBBUB_TIMEOUT_TIMER_RESET, mask_sh)
+	HUBBUB_SF(DCHUBBUB_TIMEOUT_DETECTION_CTRL2, DCHUBBUB_TIMEOUT_TIMER_RESET, mask_sh),\
+	HUBBUB_SF(DCHUBBUB_CTRL_STATUS, ROB_UNDERFLOW_STATUS, mask_sh),\
+	HUBBUB_SF(DCHUBBUB_CTRL_STATUS, ROB_OVERFLOW_STATUS, mask_sh),\
+	HUBBUB_SF(DCHUBBUB_CTRL_STATUS, ROB_OVERFLOW_CLEAR, mask_sh),\
+	HUBBUB_SF(DCHUBBUB_CTRL_STATUS, DCHUBBUB_HW_DEBUG, mask_sh),\
+	HUBBUB_SF(DCHUBBUB_CTRL_STATUS, CSTATE_SWATH_CHK_GOOD_MODE, mask_sh)
 
 bool hubbub401_program_urgent_watermarks(
 		struct hubbub *hubbub,
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c
index 05424a9af58b..b029ec1b26d3 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c
@@ -1925,9 +1925,9 @@ static void dcn20_program_pipe(
 				dc->res_pool->hubbub, pipe_ctx->plane_res.hubp->inst, pipe_ctx->hubp_regs.det_size);
 	}
 
-	if (pipe_ctx->update_flags.raw ||
-	    (pipe_ctx->plane_state && pipe_ctx->plane_state->update_flags.raw) ||
-	    pipe_ctx->stream->update_flags.raw)
+	if (pipe_ctx->plane_state && (pipe_ctx->update_flags.raw ||
+	    pipe_ctx->plane_state->update_flags.raw ||
+	    pipe_ctx->stream->update_flags.raw))
 		dcn20_update_dchubp_dpp(dc, pipe_ctx, context);
 
 	if (pipe_ctx->plane_state && (pipe_ctx->update_flags.bits.enable ||
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn401/dcn401_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn401/dcn401_hwseq.c
index e8cc1bfa73f3..5de11e2837c0 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn401/dcn401_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn401/dcn401_hwseq.c
@@ -1488,6 +1488,10 @@ void dcn401_prepare_bandwidth(struct dc *dc,
 					&context->bw_ctx.bw.dcn.watermarks,
 					dc->res_pool->ref_clocks.dchub_ref_clock_inKhz / 1000,
 					false);
+	/* update timeout thresholds */
+	if (hubbub->funcs->program_arbiter) {
+		dc->wm_optimized_required |= hubbub->funcs->program_arbiter(hubbub, &context->bw_ctx.bw.dcn.arb_regs, false);
+	}
 
 	/* decrease compbuf size */
 	if (hubbub->funcs->program_compbuf_segments) {
@@ -1529,6 +1533,10 @@ void dcn401_optimize_bandwidth(
 					&context->bw_ctx.bw.dcn.watermarks,
 					dc->res_pool->ref_clocks.dchub_ref_clock_inKhz / 1000,
 					true);
+	/* update timeout thresholds */
+	if (hubbub->funcs->program_arbiter) {
+		hubbub->funcs->program_arbiter(hubbub, &context->bw_ctx.bw.dcn.arb_regs, true);
+	}
 
 	if (dc->clk_mgr->dc_mode_softmax_enabled)
 		if (dc->clk_mgr->clks.dramclk_khz > dc->clk_mgr->bw_params->dc_mode_softmax_memclk * 1000 &&
@@ -1554,11 +1562,6 @@ void dcn401_optimize_bandwidth(
 						pipe_ctx->dlg_regs.min_dst_y_next_start);
 		}
 	}
-
-	/* update timeout thresholds */
-	if (hubbub->funcs->program_timeout_thresholds) {
-		hubbub->funcs->program_timeout_thresholds(hubbub, &context->bw_ctx.bw.dcn.arb_regs);
-	}
 }
 
 void dcn401_fams2_global_control_lock(struct dc *dc,
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/dchubbub.h b/drivers/gpu/drm/amd/display/dc/inc/hw/dchubbub.h
index 6c1d41c0f099..52b745667ef7 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/dchubbub.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/dchubbub.h
@@ -228,7 +228,7 @@ struct hubbub_funcs {
 	void (*program_det_segments)(struct hubbub *hubbub, int hubp_inst, unsigned det_buffer_size_seg);
 	void (*program_compbuf_segments)(struct hubbub *hubbub, unsigned compbuf_size_seg, bool safe_to_increase);
 	void (*wait_for_det_update)(struct hubbub *hubbub, int hubp_inst);
-	void (*program_timeout_thresholds)(struct hubbub *hubbub, struct dml2_display_arb_regs *arb_regs);
+	bool (*program_arbiter)(struct hubbub *hubbub, struct dml2_display_arb_regs *arb_regs, bool safe_to_lower);
 };
 
 struct hubbub {
diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn401/dcn401_resource.h b/drivers/gpu/drm/amd/display/dc/resource/dcn401/dcn401_resource.h
index 7c8d61db153d..19568c359669 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dcn401/dcn401_resource.h
+++ b/drivers/gpu/drm/amd/display/dc/resource/dcn401/dcn401_resource.h
@@ -612,7 +612,8 @@ void dcn401_prepare_mcache_programming(struct dc *dc, struct dc_state *context);
 	SR(DCHUBBUB_SDPIF_CFG1),                                                 \
 	SR(DCHUBBUB_MEM_PWR_MODE_CTRL),                                          \
 	SR(DCHUBBUB_TIMEOUT_DETECTION_CTRL1),                                    \
-	SR(DCHUBBUB_TIMEOUT_DETECTION_CTRL2)
+	SR(DCHUBBUB_TIMEOUT_DETECTION_CTRL2),									 \
+	SR(DCHUBBUB_CTRL_STATUS)
 
 /* DCCG */
 
diff --git a/drivers/gpu/drm/amd/display/dc/spl/dc_spl.c b/drivers/gpu/drm/amd/display/dc/spl/dc_spl.c
index 614276200aa0..73a65913cb12 100644
--- a/drivers/gpu/drm/amd/display/dc/spl/dc_spl.c
+++ b/drivers/gpu/drm/amd/display/dc/spl/dc_spl.c
@@ -99,7 +99,7 @@ static struct spl_rect calculate_plane_rec_in_timing_active(
 	 *
 	 * recout_x = 128 + round(plane_x * 2304 / 1920)
 	 * recout_w = 128 + round((plane_x + plane_w) * 2304 / 1920) - recout_x
-	 * recout_y = 0 + round(plane_y * 1440 / 1280)
+	 * recout_y = 0 + round(plane_y * 1440 / 1200)
 	 * recout_h = 0 + round((plane_y + plane_h) * 1440 / 1200) - recout_y
 	 *
 	 * NOTE: fixed point division is not error free. To reduce errors
@@ -739,14 +739,13 @@ static enum scl_mode spl_get_dscl_mode(const struct spl_in *spl_in,
 			return SCL_MODE_SCALING_444_RGB_ENABLE;
 	}
 
-	/* Bypass YUV if at 1:1 with no ISHARP or if doing 2:1 YUV
-	 *  downscale without EASF
+	/*
+	 * Bypass YUV if Y is 1:1 with no ISHARP
+	 * Do not bypass UV at 1:1 for cositing to be applied
 	 */
-	if ((!enable_isharp) && (!enable_easf)) {
+	if (!enable_isharp) {
 		if (data->ratios.horz.value == one && data->ratios.vert.value == one)
 			return SCL_MODE_SCALING_420_LUMA_BYPASS;
-		if (data->ratios.horz_c.value == one && data->ratios.vert_c.value == one)
-			return SCL_MODE_SCALING_420_CHROMA_BYPASS;
 	}
 
 	return SCL_MODE_SCALING_420_YCBCR_ENABLE;
@@ -933,6 +932,7 @@ static bool spl_get_optimal_number_of_taps(
 	int min_taps_y, min_taps_c;
 	enum lb_memory_config lb_config;
 	bool skip_easf = false;
+	bool is_ycbcr = spl_dscl_is_video_format(spl_in->basic_in.format);
 
 	if (spl_scratch->scl_data.viewport.width > spl_scratch->scl_data.h_active &&
 		max_downscale_src_width != 0 &&
@@ -1074,10 +1074,9 @@ static bool spl_get_optimal_number_of_taps(
 
 	/* Sharpener requires scaler to be enabled, including for 1:1
 	 * Check if ISHARP can be enabled
-	 * If ISHARP is not enabled, for 1:1, set taps to 1 and disable
-	 *  EASF
-	 * For case of 2:1 YUV where chroma is 1:1, set taps to 1 if
-	 *  EASF is not enabled
+	 * If ISHARP is not enabled, set taps to 1 if ratio is 1:1
+	 *  except for chroma taps.  Keep previous taps so it can
+	 *  handle cositing
 	 */
 
 	*enable_isharp = spl_get_isharp_en(spl_in, spl_scratch);
@@ -1087,20 +1086,28 @@ static bool spl_get_optimal_number_of_taps(
 			spl_scratch->scl_data.taps.h_taps = 1;
 			spl_scratch->scl_data.taps.v_taps = 1;
 
-			if (IDENTITY_RATIO(spl_scratch->scl_data.ratios.horz_c))
+			if (IDENTITY_RATIO(spl_scratch->scl_data.ratios.horz_c) && !is_ycbcr)
 				spl_scratch->scl_data.taps.h_taps_c = 1;
 
-			if (IDENTITY_RATIO(spl_scratch->scl_data.ratios.vert_c))
+			if (IDENTITY_RATIO(spl_scratch->scl_data.ratios.vert_c) && !is_ycbcr)
 				spl_scratch->scl_data.taps.v_taps_c = 1;
 
 			*enable_easf_v = false;
 			*enable_easf_h = false;
 		} else {
 			if ((!*enable_easf_h) &&
+				(IDENTITY_RATIO(spl_scratch->scl_data.ratios.horz)))
+				spl_scratch->scl_data.taps.h_taps = 1;
+
+			if ((!*enable_easf_v) &&
+				(IDENTITY_RATIO(spl_scratch->scl_data.ratios.vert)))
+				spl_scratch->scl_data.taps.v_taps = 1;
+
+			if ((!*enable_easf_h) && !is_ycbcr &&
 				(IDENTITY_RATIO(spl_scratch->scl_data.ratios.horz_c)))
 				spl_scratch->scl_data.taps.h_taps_c = 1;
 
-			if ((!*enable_easf_v) &&
+			if ((!*enable_easf_v) && !is_ycbcr &&
 				(IDENTITY_RATIO(spl_scratch->scl_data.ratios.vert_c)))
 				spl_scratch->scl_data.taps.v_taps_c = 1;
 		}
@@ -1111,8 +1118,7 @@ static bool spl_get_optimal_number_of_taps(
 static void spl_set_black_color_data(enum spl_pixel_format format,
 			struct scl_black_color *scl_black_color)
 {
-	bool ycbcr = format >= SPL_PIXEL_FORMAT_VIDEO_BEGIN
-					&& format <= SPL_PIXEL_FORMAT_VIDEO_END;
+	bool ycbcr = spl_dscl_is_video_format(format);
 	if (ycbcr)	{
 		scl_black_color->offset_rgb_y = BLACK_OFFSET_RGB_Y;
 		scl_black_color->offset_rgb_cbcr = BLACK_OFFSET_CBCR;
@@ -1746,6 +1752,32 @@ static void spl_set_isharp_data(struct dscl_prog_data *dscl_prog_data,
 	spl_set_blur_scale_data(dscl_prog_data, data);
 }
 
+/* Calculate recout, scaling ratio, and viewport, then get optimal number of taps */
+static bool spl_calculate_number_of_taps(struct spl_in *spl_in, struct spl_scratch *spl_scratch, struct spl_out *spl_out,
+	bool *enable_easf_v, bool *enable_easf_h, bool *enable_isharp)
+{
+	bool res = false;
+
+	memset(spl_scratch, 0, sizeof(struct spl_scratch));
+	spl_scratch->scl_data.h_active = spl_in->h_active;
+	spl_scratch->scl_data.v_active = spl_in->v_active;
+
+	// All SPL calls
+	/* recout calculation */
+	/* depends on h_active */
+	spl_calculate_recout(spl_in, spl_scratch, spl_out);
+	/* depends on pixel format */
+	spl_calculate_scaling_ratios(spl_in, spl_scratch, spl_out);
+	/* depends on scaling ratios and recout, does not calculate offset yet */
+	spl_calculate_viewport_size(spl_in, spl_scratch);
+
+	res = spl_get_optimal_number_of_taps(
+			  spl_in->basic_out.max_downscale_src_width, spl_in,
+			  spl_scratch, &spl_in->scaling_quality, enable_easf_v,
+			  enable_easf_h, enable_isharp);
+	return res;
+}
+
 /* Calculate scaler parameters */
 bool spl_calculate_scaler_params(struct spl_in *spl_in, struct spl_out *spl_out)
 {
@@ -1760,23 +1792,9 @@ bool spl_calculate_scaler_params(struct spl_in *spl_in, struct spl_out *spl_out)
 	bool enable_isharp = false;
 	const struct spl_scaler_data *data = &spl_scratch.scl_data;
 
-	memset(&spl_scratch, 0, sizeof(struct spl_scratch));
-	spl_scratch.scl_data.h_active = spl_in->h_active;
-	spl_scratch.scl_data.v_active = spl_in->v_active;
+	res = spl_calculate_number_of_taps(spl_in, &spl_scratch, spl_out,
+		&enable_easf_v, &enable_easf_h, &enable_isharp);
 
-	// All SPL calls
-	/* recout calculation */
-	/* depends on h_active */
-	spl_calculate_recout(spl_in, &spl_scratch, spl_out);
-	/* depends on pixel format */
-	spl_calculate_scaling_ratios(spl_in, &spl_scratch, spl_out);
-	/* depends on scaling ratios and recout, does not calculate offset yet */
-	spl_calculate_viewport_size(spl_in, &spl_scratch);
-
-	res = spl_get_optimal_number_of_taps(
-			  spl_in->basic_out.max_downscale_src_width, spl_in,
-			  &spl_scratch, &spl_in->scaling_quality, &enable_easf_v,
-			  &enable_easf_h, &enable_isharp);
 	/*
 	 * Depends on recout, scaling ratios, h_active and taps
 	 * May need to re-check lb size after this in some obscure scenario
@@ -1824,3 +1842,20 @@ bool spl_calculate_scaler_params(struct spl_in *spl_in, struct spl_out *spl_out)
 
 	return res;
 }
+
+/* External interface to get number of taps only */
+bool spl_get_number_of_taps(struct spl_in *spl_in, struct spl_out *spl_out)
+{
+	bool res = false;
+	bool enable_easf_v = false;
+	bool enable_easf_h = false;
+	bool enable_isharp = false;
+	struct spl_scratch spl_scratch;
+	struct dscl_prog_data *dscl_prog_data = spl_out->dscl_prog_data;
+	const struct spl_scaler_data *data = &spl_scratch.scl_data;
+
+	res = spl_calculate_number_of_taps(spl_in, &spl_scratch, spl_out,
+		&enable_easf_v, &enable_easf_h, &enable_isharp);
+	spl_set_taps_data(dscl_prog_data, data);
+	return res;
+}
diff --git a/drivers/gpu/drm/amd/display/dc/spl/dc_spl.h b/drivers/gpu/drm/amd/display/dc/spl/dc_spl.h
index 205e59a2a8ee..02a2d6725ed5 100644
--- a/drivers/gpu/drm/amd/display/dc/spl/dc_spl.h
+++ b/drivers/gpu/drm/amd/display/dc/spl/dc_spl.h
@@ -13,4 +13,6 @@
 
 bool spl_calculate_scaler_params(struct spl_in *spl_in, struct spl_out *spl_out);
 
+bool spl_get_number_of_taps(struct spl_in *spl_in, struct spl_out *spl_out);
+
 #endif /* __DC_SPL_H__ */
diff --git a/drivers/gpu/drm/amd/include/asic_reg/nbio/nbio_7_11_0_offset.h b/drivers/gpu/drm/amd/include/asic_reg/nbio/nbio_7_11_0_offset.h
index 5ebe4cb40f9d..c38a01742d6f 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/nbio/nbio_7_11_0_offset.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/nbio/nbio_7_11_0_offset.h
@@ -7571,6 +7571,8 @@
 // base address: 0x10100000
 #define regRCC_STRAP0_RCC_DEV0_EPF0_STRAP0                                                              0xd000
 #define regRCC_STRAP0_RCC_DEV0_EPF0_STRAP0_BASE_IDX                                                     5
+#define regRCC_DEV0_EPF5_STRAP4                                                                         0xd284
+#define regRCC_DEV0_EPF5_STRAP4_BASE_IDX                                                                5
 
 
 // addressBlock: nbio_nbif0_bif_rst_bif_rst_regblk
diff --git a/drivers/gpu/drm/amd/include/asic_reg/nbio/nbio_7_11_0_sh_mask.h b/drivers/gpu/drm/amd/include/asic_reg/nbio/nbio_7_11_0_sh_mask.h
index eb8c556d9c93..3b96f1e5a180 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/nbio/nbio_7_11_0_sh_mask.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/nbio/nbio_7_11_0_sh_mask.h
@@ -50665,6 +50665,19 @@
 #define RCC_STRAP0_RCC_DEV0_EPF0_STRAP0__STRAP_D1_SUPPORT_DEV0_F0_MASK                                        0x40000000L
 #define RCC_STRAP0_RCC_DEV0_EPF0_STRAP0__STRAP_D2_SUPPORT_DEV0_F0_MASK                                        0x80000000L
 
+//RCC_DEV0_EPF5_STRAP4
+#define RCC_DEV0_EPF5_STRAP4__STRAP_ATOMIC_64BIT_EN_DEV0_F5__SHIFT                                            0x14
+#define RCC_DEV0_EPF5_STRAP4__STRAP_ATOMIC_EN_DEV0_F5__SHIFT                                                  0x15
+#define RCC_DEV0_EPF5_STRAP4__STRAP_FLR_EN_DEV0_F5__SHIFT                                                     0x16
+#define RCC_DEV0_EPF5_STRAP4__STRAP_PME_SUPPORT_DEV0_F5__SHIFT                                                0x17
+#define RCC_DEV0_EPF5_STRAP4__STRAP_INTERRUPT_PIN_DEV0_F5__SHIFT                                              0x1c
+#define RCC_DEV0_EPF5_STRAP4__STRAP_AUXPWR_SUPPORT_DEV0_F5__SHIFT                                             0x1f
+#define RCC_DEV0_EPF5_STRAP4__STRAP_ATOMIC_64BIT_EN_DEV0_F5_MASK                                              0x00100000L
+#define RCC_DEV0_EPF5_STRAP4__STRAP_ATOMIC_EN_DEV0_F5_MASK                                                    0x00200000L
+#define RCC_DEV0_EPF5_STRAP4__STRAP_FLR_EN_DEV0_F5_MASK                                                       0x00400000L
+#define RCC_DEV0_EPF5_STRAP4__STRAP_PME_SUPPORT_DEV0_F5_MASK                                                  0x0F800000L
+#define RCC_DEV0_EPF5_STRAP4__STRAP_INTERRUPT_PIN_DEV0_F5_MASK                                                0x70000000L
+#define RCC_DEV0_EPF5_STRAP4__STRAP_AUXPWR_SUPPORT_DEV0_F5_MASK                                               0x80000000L
 
 // addressBlock: nbio_nbif0_bif_rst_bif_rst_regblk
 //HARD_RST_CTRL
diff --git a/drivers/gpu/drm/amd/include/kgd_pp_interface.h b/drivers/gpu/drm/amd/include/kgd_pp_interface.h
index bb27c0d2a9ae..67a5de573943 100644
--- a/drivers/gpu/drm/amd/include/kgd_pp_interface.h
+++ b/drivers/gpu/drm/amd/include/kgd_pp_interface.h
@@ -357,11 +357,22 @@ struct dpm_clocks;
 
 struct amdgpu_xcp_metrics {
 	/* Utilization Instantaneous (%) */
-	u32 gfx_busy_inst[MAX_XCC];
-	u16 jpeg_busy[NUM_JPEG_ENG];
-	u16 vcn_busy[NUM_VCN];
+	uint32_t gfx_busy_inst[MAX_XCC];
+	uint16_t jpeg_busy[NUM_JPEG_ENG];
+	uint16_t vcn_busy[NUM_VCN];
 	/* Utilization Accumulated (%) */
-	u64 gfx_busy_acc[MAX_XCC];
+	uint64_t gfx_busy_acc[MAX_XCC];
+};
+
+struct amdgpu_xcp_metrics_v1_1 {
+	/* Utilization Instantaneous (%) */
+	uint32_t gfx_busy_inst[MAX_XCC];
+	uint16_t jpeg_busy[NUM_JPEG_ENG];
+	uint16_t vcn_busy[NUM_VCN];
+	/* Utilization Accumulated (%) */
+	uint64_t gfx_busy_acc[MAX_XCC];
+	/* Total App Clock Counter Accumulated */
+	uint64_t gfx_below_host_limit_acc[MAX_XCC];
 };
 
 struct amd_pm_funcs {
@@ -977,6 +988,105 @@ struct gpu_metrics_v1_6 {
 	uint32_t			pcie_lc_perf_other_end_recovery;
 };
 
+struct gpu_metrics_v1_7 {
+	struct metrics_table_header	common_header;
+
+	/* Temperature (Celsius) */
+	uint16_t			temperature_hotspot;
+	uint16_t			temperature_mem;
+	uint16_t			temperature_vrsoc;
+
+	/* Power (Watts) */
+	uint16_t			curr_socket_power;
+
+	/* Utilization (%) */
+	uint16_t			average_gfx_activity;
+	uint16_t			average_umc_activity; // memory controller
+
+	/* VRAM max bandwidthi (in GB/sec) at max memory clock */
+	uint64_t			mem_max_bandwidth;
+
+	/* Energy (15.259uJ (2^-16) units) */
+	uint64_t			energy_accumulator;
+
+	/* Driver attached timestamp (in ns) */
+	uint64_t			system_clock_counter;
+
+	/* Accumulation cycle counter */
+	uint32_t                        accumulation_counter;
+
+	/* Accumulated throttler residencies */
+	uint32_t                        prochot_residency_acc;
+	uint32_t                        ppt_residency_acc;
+	uint32_t                        socket_thm_residency_acc;
+	uint32_t                        vr_thm_residency_acc;
+	uint32_t                        hbm_thm_residency_acc;
+
+	/* Clock Lock Status. Each bit corresponds to clock instance */
+	uint32_t			gfxclk_lock_status;
+
+	/* Link width (number of lanes) and speed (in 0.1 GT/s) */
+	uint16_t			pcie_link_width;
+	uint16_t			pcie_link_speed;
+
+	/* XGMI bus width and bitrate (in Gbps) */
+	uint16_t			xgmi_link_width;
+	uint16_t			xgmi_link_speed;
+
+	/* Utilization Accumulated (%) */
+	uint32_t			gfx_activity_acc;
+	uint32_t			mem_activity_acc;
+
+	/*PCIE accumulated bandwidth (GB/sec) */
+	uint64_t			pcie_bandwidth_acc;
+
+	/*PCIE instantaneous bandwidth (GB/sec) */
+	uint64_t			pcie_bandwidth_inst;
+
+	/* PCIE L0 to recovery state transition accumulated count */
+	uint64_t			pcie_l0_to_recov_count_acc;
+
+	/* PCIE replay accumulated count */
+	uint64_t			pcie_replay_count_acc;
+
+	/* PCIE replay rollover accumulated count */
+	uint64_t			pcie_replay_rover_count_acc;
+
+	/* PCIE NAK sent  accumulated count */
+	uint32_t			pcie_nak_sent_count_acc;
+
+	/* PCIE NAK received accumulated count */
+	uint32_t			pcie_nak_rcvd_count_acc;
+
+	/* XGMI accumulated data transfer size(KiloBytes) */
+	uint64_t			xgmi_read_data_acc[NUM_XGMI_LINKS];
+	uint64_t			xgmi_write_data_acc[NUM_XGMI_LINKS];
+
+	/* XGMI link status(active/inactive) */
+	uint16_t			xgmi_link_status[NUM_XGMI_LINKS];
+
+	uint16_t			padding;
+
+	/* PMFW attached timestamp (10ns resolution) */
+	uint64_t			firmware_timestamp;
+
+	/* Current clocks (Mhz) */
+	uint16_t			current_gfxclk[MAX_GFX_CLKS];
+	uint16_t			current_socclk[MAX_CLKS];
+	uint16_t			current_vclk0[MAX_CLKS];
+	uint16_t			current_dclk0[MAX_CLKS];
+	uint16_t			current_uclk;
+
+	/* Number of current partition */
+	uint16_t			num_partition;
+
+	/* XCP metrics stats */
+	struct amdgpu_xcp_metrics_v1_1	xcp_stats[NUM_XCP];
+
+	/* PCIE other end recovery counter */
+	uint32_t			pcie_lc_perf_other_end_recovery;
+};
+
 /*
  * gpu_metrics_v2_0 is not recommended as it's not naturally aligned.
  * Use gpu_metrics_v2_1 or later instead.
diff --git a/drivers/gpu/drm/amd/pm/powerplay/smumgr/vega12_smumgr.c b/drivers/gpu/drm/amd/pm/powerplay/smumgr/vega12_smumgr.c
index b52ce135d84d..d3ff6a831ed5 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/smumgr/vega12_smumgr.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/smumgr/vega12_smumgr.c
@@ -257,20 +257,18 @@ static int vega12_smu_init(struct pp_hwmgr *hwmgr)
 	priv->smu_tables.entry[TABLE_WATERMARKS].size = sizeof(Watermarks_t);
 
 	tools_size = 0x19000;
-	if (tools_size) {
-		ret = amdgpu_bo_create_kernel((struct amdgpu_device *)hwmgr->adev,
-					      tools_size,
-					      PAGE_SIZE,
-					      AMDGPU_GEM_DOMAIN_VRAM,
-					      &priv->smu_tables.entry[TABLE_PMSTATUSLOG].handle,
-					      &priv->smu_tables.entry[TABLE_PMSTATUSLOG].mc_addr,
-					      &priv->smu_tables.entry[TABLE_PMSTATUSLOG].table);
-		if (ret)
-			goto err1;
+	ret = amdgpu_bo_create_kernel((struct amdgpu_device *)hwmgr->adev,
+				      tools_size,
+				      PAGE_SIZE,
+				      AMDGPU_GEM_DOMAIN_VRAM,
+				      &priv->smu_tables.entry[TABLE_PMSTATUSLOG].handle,
+				      &priv->smu_tables.entry[TABLE_PMSTATUSLOG].mc_addr,
+				      &priv->smu_tables.entry[TABLE_PMSTATUSLOG].table);
+	if (ret)
+		goto err1;
 
-		priv->smu_tables.entry[TABLE_PMSTATUSLOG].version = 0x01;
-		priv->smu_tables.entry[TABLE_PMSTATUSLOG].size = tools_size;
-	}
+	priv->smu_tables.entry[TABLE_PMSTATUSLOG].version = 0x01;
+	priv->smu_tables.entry[TABLE_PMSTATUSLOG].size = tools_size;
 
 	/* allocate space for AVFS Fuse table */
 	ret = amdgpu_bo_create_kernel((struct amdgpu_device *)hwmgr->adev,
diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
index 64f917959576..b8355293518f 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
@@ -1704,7 +1704,9 @@ static int smu_smc_hw_setup(struct smu_context *smu)
 		return ret;
 	}
 
-	if (adev->pm.pcie_gen_mask & CAIL_PCIE_LINK_SPEED_SUPPORT_GEN4)
+	if (adev->pm.pcie_gen_mask & CAIL_PCIE_LINK_SPEED_SUPPORT_GEN5)
+		pcie_gen = 4;
+	else if (adev->pm.pcie_gen_mask & CAIL_PCIE_LINK_SPEED_SUPPORT_GEN4)
 		pcie_gen = 3;
 	else if (adev->pm.pcie_gen_mask & CAIL_PCIE_LINK_SPEED_SUPPORT_GEN3)
 		pcie_gen = 2;
@@ -1717,7 +1719,9 @@ static int smu_smc_hw_setup(struct smu_context *smu)
 	 * Bit 15:8:  PCIE GEN, 0 to 3 corresponds to GEN1 to GEN4
 	 * Bit 7:0:   PCIE lane width, 1 to 7 corresponds is x1 to x32
 	 */
-	if (adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X16)
+	if (adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X32)
+		pcie_width = 7;
+	else if (adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X16)
 		pcie_width = 6;
 	else if (adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X12)
 		pcie_width = 5;
diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v14_0.h b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v14_0.h
index 0546b02e198d..29a4583db873 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v14_0.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v14_0.h
@@ -53,7 +53,7 @@
 #define CTF_OFFSET_MEM			5
 
 extern const int decoded_link_speed[5];
-extern const int decoded_link_width[7];
+extern const int decoded_link_width[8];
 
 #define DECODE_GEN_SPEED(gen_speed_idx)		(decoded_link_speed[gen_speed_idx])
 #define DECODE_LANE_WIDTH(lane_width_idx)	(decoded_link_width[lane_width_idx])
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c
index 4b36c230e43a..12125303bb79 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c
@@ -1344,8 +1344,12 @@ static int arcturus_get_power_limit(struct smu_context *smu,
 		*default_power_limit = power_limit;
 	if (max_power_limit)
 		*max_power_limit = power_limit;
+	/**
+	 * No lower bound is imposed on the limit. Any unreasonable limit set
+	 * will result in frequent throttling.
+	 */
 	if (min_power_limit)
-		*min_power_limit = power_limit;
+		*min_power_limit = 0;
 
 	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 fa30a9e1f27a..ab3c93ddce46 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
@@ -96,7 +96,6 @@ MODULE_FIRMWARE("amdgpu/smu_13_0_14.bin");
 #define PCIE_LC_SPEED_CNTL__LC_CURRENT_DATA_RATE_MASK 0xE0
 #define PCIE_LC_SPEED_CNTL__LC_CURRENT_DATA_RATE__SHIFT 0x5
 #define LINK_SPEED_MAX				4
-
 #define SMU_13_0_6_DSCLK_THRESHOLD 140
 
 #define MCA_BANK_IPID(_ip, _hwid, _type) \
@@ -370,7 +369,7 @@ static int smu_v13_0_6_tables_init(struct smu_context *smu)
 		return -ENOMEM;
 	smu_table->metrics_time = 0;
 
-	smu_table->gpu_metrics_table_size = sizeof(struct gpu_metrics_v1_6);
+	smu_table->gpu_metrics_table_size = sizeof(struct gpu_metrics_v1_7);
 	smu_table->gpu_metrics_table =
 		kzalloc(smu_table->gpu_metrics_table_size, GFP_KERNEL);
 	if (!smu_table->gpu_metrics_table) {
@@ -2321,8 +2320,8 @@ static ssize_t smu_v13_0_6_get_gpu_metrics(struct smu_context *smu, void **table
 {
 	bool per_inst, smu_13_0_6_per_inst, smu_13_0_14_per_inst, apu_per_inst;
 	struct smu_table_context *smu_table = &smu->smu_table;
-	struct gpu_metrics_v1_6 *gpu_metrics =
-		(struct gpu_metrics_v1_6 *)smu_table->gpu_metrics_table;
+	struct gpu_metrics_v1_7 *gpu_metrics =
+		(struct gpu_metrics_v1_7 *)smu_table->gpu_metrics_table;
 	bool flag = smu_v13_0_6_is_unified_metrics(smu);
 	int ret = 0, xcc_id, inst, i, j, k, idx;
 	struct amdgpu_device *adev = smu->adev;
@@ -2341,7 +2340,7 @@ static ssize_t smu_v13_0_6_get_gpu_metrics(struct smu_context *smu, void **table
 
 	metrics_a = (MetricsTableA_t *)metrics_x;
 
-	smu_cmn_init_soft_gpu_metrics(gpu_metrics, 1, 6);
+	smu_cmn_init_soft_gpu_metrics(gpu_metrics, 1, 7);
 
 	gpu_metrics->temperature_hotspot =
 		SMUQ10_ROUND(GET_METRIC_FIELD(MaxSocketTemperature, flag));
@@ -2448,6 +2447,9 @@ static ssize_t smu_v13_0_6_get_gpu_metrics(struct smu_context *smu, void **table
 			SMUQ10_ROUND(GET_METRIC_FIELD(XgmiReadDataSizeAcc, flag)[i]);
 		gpu_metrics->xgmi_write_data_acc[i] =
 			SMUQ10_ROUND(GET_METRIC_FIELD(XgmiWriteDataSizeAcc, flag)[i]);
+		ret = amdgpu_get_xgmi_link_status(adev, i);
+		if (ret >= 0)
+			gpu_metrics->xgmi_link_status[i] = ret;
 	}
 
 	gpu_metrics->num_partition = adev->xcp_mgr->num_xcps;
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c
index c5d3e25cc967..4fd0354bd312 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c
@@ -2147,6 +2147,8 @@ static ssize_t smu_v13_0_7_get_gpu_metrics(struct smu_context *smu,
 	gpu_metrics->average_dclk1_frequency = metrics->AverageDclk1Frequency;
 
 	gpu_metrics->current_gfxclk = metrics->CurrClock[PPCLK_GFXCLK];
+	gpu_metrics->current_socclk = metrics->CurrClock[PPCLK_SOCCLK];
+	gpu_metrics->current_uclk = metrics->CurrClock[PPCLK_UCLK];
 	gpu_metrics->current_vclk0 = metrics->CurrClock[PPCLK_VCLK_0];
 	gpu_metrics->current_dclk0 = metrics->CurrClock[PPCLK_DCLK_0];
 	gpu_metrics->current_vclk1 = metrics->CurrClock[PPCLK_VCLK_1];
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c
index ecb0164d533e..a87040cb2f2e 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c
@@ -49,7 +49,7 @@
 #define regMP1_SMN_IH_SW_INT_CTRL_mp1_14_0_0_BASE_IDX   0
 
 const int decoded_link_speed[5] = {1, 2, 3, 4, 5};
-const int decoded_link_width[7] = {0, 1, 2, 4, 8, 12, 16};
+const int decoded_link_width[8] = {0, 1, 2, 4, 8, 12, 16, 32};
 /*
  * DO NOT use these for err/warn/info/debug messages.
  * Use dev_err, dev_warn, dev_info and dev_dbg instead.
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c
index 59b369eff30f..687a0f5ac94f 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c
@@ -1173,13 +1173,15 @@ static int smu_v14_0_2_print_clk_levels(struct smu_context *smu,
 					(pcie_table->pcie_gen[i] == 0) ? "2.5GT/s," :
 					(pcie_table->pcie_gen[i] == 1) ? "5.0GT/s," :
 					(pcie_table->pcie_gen[i] == 2) ? "8.0GT/s," :
-					(pcie_table->pcie_gen[i] == 3) ? "16.0GT/s," : "",
+					(pcie_table->pcie_gen[i] == 3) ? "16.0GT/s," :
+					(pcie_table->pcie_gen[i] == 4) ? "32.0GT/s," : "",
 					(pcie_table->pcie_lane[i] == 1) ? "x1" :
 					(pcie_table->pcie_lane[i] == 2) ? "x2" :
 					(pcie_table->pcie_lane[i] == 3) ? "x4" :
 					(pcie_table->pcie_lane[i] == 4) ? "x8" :
 					(pcie_table->pcie_lane[i] == 5) ? "x12" :
-					(pcie_table->pcie_lane[i] == 6) ? "x16" : "",
+					(pcie_table->pcie_lane[i] == 6) ? "x16" :
+					(pcie_table->pcie_lane[i] == 7) ? "x32" : "",
 					pcie_table->clk_freq[i],
 					(gen_speed == DECODE_GEN_SPEED(pcie_table->pcie_gen[i])) &&
 					(lane_width == DECODE_LANE_WIDTH(pcie_table->pcie_lane[i])) ?
@@ -1463,15 +1465,35 @@ static int smu_v14_0_2_update_pcie_parameters(struct smu_context *smu,
 	struct smu_14_0_dpm_context *dpm_context = smu->smu_dpm.dpm_context;
 	struct smu_14_0_pcie_table *pcie_table =
 				&dpm_context->dpm_tables.pcie_table;
+	int num_of_levels = pcie_table->num_of_link_levels;
 	uint32_t smu_pcie_arg;
 	int ret, i;
 
-	for (i = 0; i < pcie_table->num_of_link_levels; i++) {
-		if (pcie_table->pcie_gen[i] > pcie_gen_cap)
+	if (!num_of_levels)
+		return 0;
+
+	if (!(smu->adev->pm.pp_feature & PP_PCIE_DPM_MASK)) {
+		if (pcie_table->pcie_gen[num_of_levels - 1] < pcie_gen_cap)
+			pcie_gen_cap = pcie_table->pcie_gen[num_of_levels - 1];
+
+		if (pcie_table->pcie_lane[num_of_levels - 1] < pcie_width_cap)
+			pcie_width_cap = pcie_table->pcie_lane[num_of_levels - 1];
+
+		/* Force all levels to use the same settings */
+		for (i = 0; i < num_of_levels; i++) {
 			pcie_table->pcie_gen[i] = pcie_gen_cap;
-		if (pcie_table->pcie_lane[i] > pcie_width_cap)
 			pcie_table->pcie_lane[i] = pcie_width_cap;
+		}
+	} else {
+		for (i = 0; i < num_of_levels; i++) {
+			if (pcie_table->pcie_gen[i] > pcie_gen_cap)
+				pcie_table->pcie_gen[i] = pcie_gen_cap;
+			if (pcie_table->pcie_lane[i] > pcie_width_cap)
+				pcie_table->pcie_lane[i] = pcie_width_cap;
+		}
+	}
 
+	for (i = 0; i < num_of_levels; i++) {
 		smu_pcie_arg = i << 16;
 		smu_pcie_arg |= pcie_table->pcie_gen[i] << 8;
 		smu_pcie_arg |= pcie_table->pcie_lane[i];
@@ -2753,7 +2775,6 @@ static const struct pptable_funcs smu_v14_0_2_ppt_funcs = {
 	.get_unique_id = smu_v14_0_2_get_unique_id,
 	.get_power_limit = smu_v14_0_2_get_power_limit,
 	.set_power_limit = smu_v14_0_2_set_power_limit,
-	.set_power_source = smu_v14_0_set_power_source,
 	.get_power_profile_mode = smu_v14_0_2_get_power_profile_mode,
 	.set_power_profile_mode = smu_v14_0_2_set_power_profile_mode,
 	.run_btc = smu_v14_0_run_btc,
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c
index f1ab1a6bb467..dbbd3759bff3 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c
@@ -1081,6 +1081,9 @@ void smu_cmn_init_soft_gpu_metrics(void *table, uint8_t frev, uint8_t crev)
 	case METRICS_VERSION(1, 6):
 		structure_size = sizeof(struct gpu_metrics_v1_6);
 		break;
+	case METRICS_VERSION(1, 7):
+		structure_size = sizeof(struct gpu_metrics_v1_7);
+		break;
 	case METRICS_VERSION(2, 0):
 		structure_size = sizeof(struct gpu_metrics_v2_0);
 		break;
diff --git a/drivers/gpu/drm/i915/display/intel_hdcp.c b/drivers/gpu/drm/i915/display/intel_hdcp.c
index f6d42ec6949e..f57e4dba2873 100644
--- a/drivers/gpu/drm/i915/display/intel_hdcp.c
+++ b/drivers/gpu/drm/i915/display/intel_hdcp.c
@@ -1503,6 +1503,8 @@ static int hdcp2_deauthenticate_port(struct intel_connector *connector)
 static int hdcp2_authentication_key_exchange(struct intel_connector *connector)
 {
 	struct intel_display *display = to_intel_display(connector);
+	struct intel_digital_port *dig_port =
+		intel_attached_dig_port(connector);
 	struct intel_hdcp *hdcp = &connector->hdcp;
 	union {
 		struct hdcp2_ake_init ake_init;
@@ -1513,30 +1515,36 @@ static int hdcp2_authentication_key_exchange(struct intel_connector *connector)
 	} msgs;
 	const struct intel_hdcp_shim *shim = hdcp->shim;
 	size_t size;
-	int ret, i;
+	int ret, i, max_retries;
 
 	/* Init for seq_num */
 	hdcp->seq_num_v = 0;
 	hdcp->seq_num_m = 0;
 
+	if (intel_encoder_is_dp(&dig_port->base) ||
+	    intel_encoder_is_mst(&dig_port->base))
+		max_retries = 10;
+	else
+		max_retries = 1;
+
 	ret = hdcp2_prepare_ake_init(connector, &msgs.ake_init);
 	if (ret < 0)
 		return ret;
 
 	/*
 	 * Retry the first read and write to downstream at least 10 times
-	 * with a 50ms delay if not hdcp2 capable(dock decides to stop advertising
-	 * hdcp2 capability for some reason). The reason being that
-	 * during suspend resume dock usually keeps the HDCP2 registers inaccesible
-	 * causing AUX error. This wouldn't be a big problem if the userspace
-	 * just kept retrying with some delay while it continues to play low
-	 * value content but most userpace applications end up throwing an error
-	 * when it receives one from KMD. This makes sure we give the dock
-	 * and the sink devices to complete its power cycle and then try HDCP
-	 * authentication. The values of 10 and delay of 50ms was decided based
-	 * on multiple trial and errors.
+	 * with a 50ms delay if not hdcp2 capable for DP/DPMST encoders
+	 * (dock decides to stop advertising hdcp2 capability for some reason).
+	 * The reason being that during suspend resume dock usually keeps the
+	 * HDCP2 registers inaccesible causing AUX error. This wouldn't be a
+	 * big problem if the userspace just kept retrying with some delay while
+	 * it continues to play low value content but most userpace applications
+	 * end up throwing an error when it receives one from KMD. This makes
+	 * sure we give the dock and the sink devices to complete its power cycle
+	 * and then try HDCP authentication. The values of 10 and delay of 50ms
+	 * was decided based on multiple trial and errors.
 	 */
-	for (i = 0; i < 10; i++) {
+	for (i = 0; i < max_retries; i++) {
 		if (!intel_hdcp2_get_capability(connector)) {
 			msleep(50);
 			continue;
diff --git a/drivers/gpu/drm/radeon/radeon_audio.c b/drivers/gpu/drm/radeon/radeon_audio.c
index 47aa06a9a942..5b69cc8011b4 100644
--- a/drivers/gpu/drm/radeon/radeon_audio.c
+++ b/drivers/gpu/drm/radeon/radeon_audio.c
@@ -760,16 +760,20 @@ static int radeon_audio_component_get_eld(struct device *kdev, int port,
 	if (!rdev->audio.enabled || !rdev->mode_info.mode_config_initialized)
 		return 0;
 
-	list_for_each_entry(encoder, &rdev_to_drm(rdev)->mode_config.encoder_list, head) {
+	list_for_each_entry(connector, &dev->mode_config.connector_list, head) {
+		const struct drm_connector_helper_funcs *connector_funcs =
+				connector->helper_private;
+		encoder = connector_funcs->best_encoder(connector);
+
+		if (!encoder)
+			continue;
+
 		if (!radeon_encoder_is_digital(encoder))
 			continue;
 		radeon_encoder = to_radeon_encoder(encoder);
 		dig = radeon_encoder->enc_priv;
 		if (!dig->pin || dig->pin->id != port)
 			continue;
-		connector = radeon_get_connector_for_encoder(encoder);
-		if (!connector)
-			continue;
 		*enabled = true;
 		ret = drm_eld_size(connector->eld);
 		memcpy(buf, connector->eld, min(max_bytes, ret));
diff --git a/drivers/gpu/drm/radeon/radeon_connectors.c b/drivers/gpu/drm/radeon/radeon_connectors.c
index f9c73c55f04f..f9996304d943 100644
--- a/drivers/gpu/drm/radeon/radeon_connectors.c
+++ b/drivers/gpu/drm/radeon/radeon_connectors.c
@@ -1255,16 +1255,6 @@ radeon_dvi_detect(struct drm_connector *connector, bool force)
 			goto exit;
 		}
 	}
-
-	if (dret && radeon_connector->hpd.hpd != RADEON_HPD_NONE &&
-	    !radeon_hpd_sense(rdev, radeon_connector->hpd.hpd) &&
-	    connector->connector_type == DRM_MODE_CONNECTOR_HDMIA) {
-		DRM_DEBUG_KMS("EDID is readable when HPD disconnected\n");
-		schedule_delayed_work(&rdev->hotplug_work, msecs_to_jiffies(1000));
-		ret = connector_status_disconnected;
-		goto exit;
-	}
-
 	if (dret) {
 		radeon_connector->detected_by_load = false;
 		radeon_connector_free_edid(connector);
diff --git a/drivers/gpu/drm/radeon/radeon_drv.c b/drivers/gpu/drm/radeon/radeon_drv.c
index 23d6d1a2586d..5e958cc223f4 100644
--- a/drivers/gpu/drm/radeon/radeon_drv.c
+++ b/drivers/gpu/drm/radeon/radeon_drv.c
@@ -248,10 +248,9 @@ int radeon_cik_support = 1;
 MODULE_PARM_DESC(cik_support, "CIK support (1 = enabled (default), 0 = disabled)");
 module_param_named(cik_support, radeon_cik_support, int, 0444);
 
-static struct pci_device_id pciidlist[] = {
+static const struct pci_device_id pciidlist[] = {
 	radeon_PCI_IDS
 };
-
 MODULE_DEVICE_TABLE(pci, pciidlist);
 
 static const struct drm_driver kms_driver;
diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c
index 69d0c12fa419..616d25c8c2de 100644
--- a/drivers/gpu/drm/radeon/radeon_ttm.c
+++ b/drivers/gpu/drm/radeon/radeon_ttm.c
@@ -219,8 +219,7 @@ static int radeon_bo_move(struct ttm_buffer_object *bo, bool evict,
 	if (old_mem->mem_type == TTM_PL_TT &&
 	    new_mem->mem_type == TTM_PL_SYSTEM) {
 		radeon_ttm_tt_unbind(bo->bdev, bo->ttm);
-		ttm_resource_free(bo, &bo->resource);
-		ttm_bo_assign_mem(bo, new_mem);
+		ttm_bo_move_null(bo, new_mem);
 		goto out;
 	}
 	if (rdev->ring[radeon_copy_ring_index(rdev)].ready &&
diff --git a/drivers/gpu/drm/rockchip/dw_hdmi_qp-rockchip.c b/drivers/gpu/drm/rockchip/dw_hdmi_qp-rockchip.c
index 9c796ee4c303..c8b362cc2b95 100644
--- a/drivers/gpu/drm/rockchip/dw_hdmi_qp-rockchip.c
+++ b/drivers/gpu/drm/rockchip/dw_hdmi_qp-rockchip.c
@@ -82,7 +82,7 @@ static void dw_hdmi_qp_rockchip_encoder_enable(struct drm_encoder *encoder)
 		 * comment in rk_hdptx_phy_power_on() from
 		 * drivers/phy/rockchip/phy-rockchip-samsung-hdptx.c
 		 */
-		phy_set_bus_width(hdmi->phy, rate / 100);
+		phy_set_bus_width(hdmi->phy, div_u64(rate, 100));
 	}
 }
 
diff --git a/drivers/gpu/drm/xe/xe_devcoredump.c b/drivers/gpu/drm/xe/xe_devcoredump.c
index d2679c5d976b..0b0cd6aa1d9f 100644
--- a/drivers/gpu/drm/xe/xe_devcoredump.c
+++ b/drivers/gpu/drm/xe/xe_devcoredump.c
@@ -23,6 +23,7 @@
 #include "xe_guc_submit.h"
 #include "xe_hw_engine.h"
 #include "xe_module.h"
+#include "xe_pm.h"
 #include "xe_sched_job.h"
 #include "xe_vm.h"
 
@@ -158,8 +159,11 @@ static void xe_devcoredump_deferred_snap_work(struct work_struct *work)
 {
 	struct xe_devcoredump_snapshot *ss = container_of(work, typeof(*ss), work);
 	struct xe_devcoredump *coredump = container_of(ss, typeof(*coredump), snapshot);
+	struct xe_device *xe = coredump_to_xe(coredump);
 	unsigned int fw_ref;
 
+	xe_pm_runtime_get(xe);
+
 	/* keep going if fw fails as we still want to save the memory and SW data */
 	fw_ref = xe_force_wake_get(gt_to_fw(ss->gt), XE_FORCEWAKE_ALL);
 	if (!xe_force_wake_ref_has_domain(fw_ref, XE_FORCEWAKE_ALL))
@@ -168,6 +172,8 @@ static void xe_devcoredump_deferred_snap_work(struct work_struct *work)
 	xe_guc_exec_queue_snapshot_capture_delayed(ss->ge);
 	xe_force_wake_put(gt_to_fw(ss->gt), fw_ref);
 
+	xe_pm_runtime_put(xe);
+
 	/* Calculate devcoredump size */
 	ss->read.size = __xe_devcoredump_read(NULL, INT_MAX, coredump);
 
diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c
index 0e2dd691bdae..06d6db8b50f9 100644
--- a/drivers/gpu/drm/xe/xe_device.c
+++ b/drivers/gpu/drm/xe/xe_device.c
@@ -350,7 +350,8 @@ struct xe_device *xe_device_create(struct pci_dev *pdev,
 	INIT_LIST_HEAD(&xe->pinned.external_vram);
 	INIT_LIST_HEAD(&xe->pinned.evicted);
 
-	xe->preempt_fence_wq = alloc_ordered_workqueue("xe-preempt-fence-wq", 0);
+	xe->preempt_fence_wq = alloc_ordered_workqueue("xe-preempt-fence-wq",
+						       WQ_MEM_RECLAIM);
 	xe->ordered_wq = alloc_ordered_workqueue("xe-ordered-wq", 0);
 	xe->unordered_wq = alloc_workqueue("xe-unordered-wq", 0, 0);
 	xe->destroy_wq = alloc_workqueue("xe-destroy-wq", 0, 0);
diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c
index 9a8564ea06b5..6f4a9812b4f4 100644
--- a/drivers/gpu/drm/xe/xe_guc_submit.c
+++ b/drivers/gpu/drm/xe/xe_guc_submit.c
@@ -767,17 +767,19 @@ static void disable_scheduling_deregister(struct xe_guc *guc,
 					  struct xe_exec_queue *q)
 {
 	MAKE_SCHED_CONTEXT_ACTION(q, DISABLE);
-	struct xe_device *xe = guc_to_xe(guc);
 	int ret;
 
 	set_min_preemption_timeout(guc, q);
 	smp_rmb();
-	ret = wait_event_timeout(guc->ct.wq, !exec_queue_pending_enable(q) ||
-				 xe_guc_read_stopped(guc), HZ * 5);
+	ret = wait_event_timeout(guc->ct.wq,
+				 (!exec_queue_pending_enable(q) &&
+				  !exec_queue_pending_disable(q)) ||
+					 xe_guc_read_stopped(guc),
+				 HZ * 5);
 	if (!ret) {
 		struct xe_gpu_scheduler *sched = &q->guc->sched;
 
-		drm_warn(&xe->drm, "Pending enable failed to respond");
+		xe_gt_warn(q->gt, "Pending enable/disable failed to respond\n");
 		xe_sched_submission_start(sched);
 		xe_gt_reset_async(q->gt);
 		xe_sched_tdr_queue_imm(sched);
@@ -1099,7 +1101,8 @@ guc_exec_queue_timedout_job(struct drm_sched_job *drm_job)
 			 * modifying state
 			 */
 			ret = wait_event_timeout(guc->ct.wq,
-						 !exec_queue_pending_enable(q) ||
+						 (!exec_queue_pending_enable(q) &&
+						  !exec_queue_pending_disable(q)) ||
 						 xe_guc_read_stopped(guc), HZ * 5);
 			if (!ret || xe_guc_read_stopped(guc))
 				goto trigger_reset;
@@ -1328,8 +1331,8 @@ static void __guc_exec_queue_process_msg_suspend(struct xe_sched_msg *msg)
 
 	if (guc_exec_queue_allowed_to_change_state(q) && !exec_queue_suspended(q) &&
 	    exec_queue_enabled(q)) {
-		wait_event(guc->ct.wq, q->guc->resume_time != RESUME_PENDING ||
-			   xe_guc_read_stopped(guc));
+		wait_event(guc->ct.wq, (q->guc->resume_time != RESUME_PENDING ||
+			   xe_guc_read_stopped(guc)) && !exec_queue_pending_disable(q));
 
 		if (!xe_guc_read_stopped(guc)) {
 			s64 since_resume_ms =
@@ -1866,16 +1869,29 @@ static void handle_sched_done(struct xe_guc *guc, struct xe_exec_queue *q,
 		xe_gt_assert(guc_to_gt(guc), runnable_state == 0);
 		xe_gt_assert(guc_to_gt(guc), exec_queue_pending_disable(q));
 
-		clear_exec_queue_pending_disable(q);
 		if (q->guc->suspend_pending) {
 			suspend_fence_signal(q);
+			clear_exec_queue_pending_disable(q);
 		} else {
 			if (exec_queue_banned(q) || check_timeout) {
 				smp_wmb();
 				wake_up_all(&guc->ct.wq);
 			}
-			if (!check_timeout)
+			if (!check_timeout && exec_queue_destroyed(q)) {
+				/*
+				 * Make sure to clear the pending_disable only
+				 * after sampling the destroyed state. We want
+				 * to ensure we don't trigger the unregister too
+				 * early with something intending to only
+				 * disable scheduling. The caller doing the
+				 * destroy must wait for an ongoing
+				 * pending_disable before marking as destroyed.
+				 */
+				clear_exec_queue_pending_disable(q);
 				deregister_exec_queue(guc, q);
+			} else {
+				clear_exec_queue_pending_disable(q);
+			}
 		}
 	}
 }
diff --git a/drivers/gpu/drm/xe/xe_migrate.c b/drivers/gpu/drm/xe/xe_migrate.c
index cfd31ae49cc1..1b97d90aadda 100644
--- a/drivers/gpu/drm/xe/xe_migrate.c
+++ b/drivers/gpu/drm/xe/xe_migrate.c
@@ -209,7 +209,8 @@ static int xe_migrate_prepare_vm(struct xe_tile *tile, struct xe_migrate *m,
 				  num_entries * XE_PAGE_SIZE,
 				  ttm_bo_type_kernel,
 				  XE_BO_FLAG_VRAM_IF_DGFX(tile) |
-				  XE_BO_FLAG_PINNED);
+				  XE_BO_FLAG_PINNED |
+				  XE_BO_FLAG_PAGETABLE);
 	if (IS_ERR(bo))
 		return PTR_ERR(bo);
 
@@ -1350,6 +1351,7 @@ __xe_migrate_update_pgtables(struct xe_migrate *m,
 
 	/* For sysmem PTE's, need to map them in our hole.. */
 	if (!IS_DGFX(xe)) {
+		u16 pat_index = xe->pat.idx[XE_CACHE_WB];
 		u32 ptes, ofs;
 
 		ppgtt_ofs = NUM_KERNEL_PDE - 1;
@@ -1409,7 +1411,7 @@ __xe_migrate_update_pgtables(struct xe_migrate *m,
 						pt_bo->update_index = current_update;
 
 					addr = vm->pt_ops->pte_encode_bo(pt_bo, 0,
-									 XE_CACHE_WB, 0);
+									 pat_index, 0);
 					bb->cs[bb->len++] = lower_32_bits(addr);
 					bb->cs[bb->len++] = upper_32_bits(addr);
 				}
diff --git a/drivers/gpu/drm/xe/xe_pci.c b/drivers/gpu/drm/xe/xe_pci.c
index e6640283893f..6b7f77425c7f 100644
--- a/drivers/gpu/drm/xe/xe_pci.c
+++ b/drivers/gpu/drm/xe/xe_pci.c
@@ -174,7 +174,7 @@ static const struct xe_graphics_desc graphics_xelpg = {
 		GENMASK(XE_HW_ENGINE_CCS3, XE_HW_ENGINE_CCS0)
 
 static const struct xe_graphics_desc graphics_xe2 = {
-	.name = "Xe2_LPG / Xe2_HPG",
+	.name = "Xe2_LPG / Xe2_HPG / Xe3_LPG",
 
 	XE2_GFX_FEATURES,
 };
diff --git a/drivers/gpu/drm/xe/xe_sync.c b/drivers/gpu/drm/xe/xe_sync.c
index a90480c6aecf..42f5bebd09e5 100644
--- a/drivers/gpu/drm/xe/xe_sync.c
+++ b/drivers/gpu/drm/xe/xe_sync.c
@@ -87,8 +87,12 @@ static void user_fence_worker(struct work_struct *w)
 		drm_dbg(&ufence->xe->drm, "mmget_not_zero() failed, ufence wasn't signaled\n");
 	}
 
-	wake_up_all(&ufence->xe->ufence_wq);
+	/*
+	 * Wake up waiters only after updating the ufence state, allowing the UMD
+	 * to safely reuse the same ufence without encountering -EBUSY errors.
+	 */
 	WRITE_ONCE(ufence->signalled, 1);
+	wake_up_all(&ufence->xe->ufence_wq);
 	user_fence_put(ufence);
 }