Merge drm/drm-next into drm-xe-next

Backmerging to bring in 6.18-rc1.

Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>

133 files changed, 1537 insertions, 821 deletions

diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig
index fda170730468..7e6bc0b3a589 100644
--- a/drivers/gpu/drm/Kconfig
+++ b/drivers/gpu/drm/Kconfig
@@ -400,7 +400,7 @@ source "drivers/gpu/drm/tyr/Kconfig"
 
 config DRM_HYPERV
 	tristate "DRM Support for Hyper-V synthetic video device"
-	depends on DRM && PCI && HYPERV
+	depends on DRM && PCI && HYPERV_VMBUS
 	select DRM_CLIENT_SELECTION
 	select DRM_KMS_HELPER
 	select DRM_GEM_SHMEM_HELPER
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c
index 04ef0ca10541..0239114fb6c4 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c
@@ -352,7 +352,7 @@ static int kgd_hqd_dump(struct amdgpu_device *adev,
 		(*dump)[i++][1] = RREG32_SOC15_IP(GC, addr);		\
 	} while (0)
 
-	*dump = kmalloc(HQD_N_REGS*2*sizeof(uint32_t), GFP_KERNEL);
+	*dump = kmalloc_array(HQD_N_REGS, sizeof(**dump), GFP_KERNEL);
 	if (*dump == NULL)
 		return -ENOMEM;
 
@@ -449,7 +449,7 @@ static int kgd_hqd_sdma_dump(struct amdgpu_device *adev,
 #undef HQD_N_REGS
 #define HQD_N_REGS (19+6+7+10)
 
-	*dump = kmalloc(HQD_N_REGS*2*sizeof(uint32_t), GFP_KERNEL);
+	*dump = kmalloc_array(HQD_N_REGS, sizeof(**dump), GFP_KERNEL);
 	if (*dump == NULL)
 		return -ENOMEM;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10_3.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10_3.c
index 6d08bc2781a3..f2278a0937ff 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10_3.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10_3.c
@@ -338,7 +338,7 @@ static int hqd_dump_v10_3(struct amdgpu_device *adev,
 		(*dump)[i++][1] = RREG32_SOC15_IP(GC, addr);		\
 	} while (0)
 
-	*dump = kmalloc(HQD_N_REGS*2*sizeof(uint32_t), GFP_KERNEL);
+	*dump = kmalloc_array(HQD_N_REGS, sizeof(**dump), GFP_KERNEL);
 	if (*dump == NULL)
 		return -ENOMEM;
 
@@ -435,7 +435,7 @@ static int hqd_sdma_dump_v10_3(struct amdgpu_device *adev,
 #undef HQD_N_REGS
 #define HQD_N_REGS (19+6+7+12)
 
-	*dump = kmalloc(HQD_N_REGS*2*sizeof(uint32_t), GFP_KERNEL);
+	*dump = kmalloc_array(HQD_N_REGS, sizeof(**dump), GFP_KERNEL);
 	if (*dump == NULL)
 		return -ENOMEM;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v11.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v11.c
index e0e6a6a49d90..aaccf0b9947d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v11.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v11.c
@@ -323,7 +323,7 @@ static int hqd_dump_v11(struct amdgpu_device *adev,
 		(*dump)[i++][1] = RREG32(addr);		\
 	} while (0)
 
-	*dump = kmalloc(HQD_N_REGS*2*sizeof(uint32_t), GFP_KERNEL);
+	*dump = kmalloc_array(HQD_N_REGS, sizeof(**dump), GFP_KERNEL);
 	if (*dump == NULL)
 		return -ENOMEM;
 
@@ -420,7 +420,7 @@ static int hqd_sdma_dump_v11(struct amdgpu_device *adev,
 #undef HQD_N_REGS
 #define HQD_N_REGS (7+11+1+12+12)
 
-	*dump = kmalloc(HQD_N_REGS*2*sizeof(uint32_t), GFP_KERNEL);
+	*dump = kmalloc_array(HQD_N_REGS, sizeof(**dump), GFP_KERNEL);
 	if (*dump == NULL)
 		return -ENOMEM;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v12.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v12.c
index 6f0dc23c901b..e0ceab400b2d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v12.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v12.c
@@ -115,7 +115,7 @@ static int hqd_dump_v12(struct amdgpu_device *adev,
 		(*dump)[i++][1] = RREG32(addr);		\
 	} while (0)
 
-	*dump = kmalloc(HQD_N_REGS*2*sizeof(uint32_t), GFP_KERNEL);
+	*dump = kmalloc_array(HQD_N_REGS, sizeof(**dump), GFP_KERNEL);
 	if (*dump == NULL)
 		return -ENOMEM;
 
@@ -146,7 +146,7 @@ static int hqd_sdma_dump_v12(struct amdgpu_device *adev,
 #undef HQD_N_REGS
 #define HQD_N_REGS (last_reg - first_reg + 1)
 
-	*dump = kmalloc(HQD_N_REGS*2*sizeof(uint32_t), GFP_KERNEL);
+	*dump = kmalloc_array(HQD_N_REGS, sizeof(**dump), GFP_KERNEL);
 	if (*dump == NULL)
 		return -ENOMEM;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
index c3b34a410375..83020963dfde 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@@ -1089,7 +1089,7 @@ static int init_user_pages(struct kgd_mem *mem, uint64_t user_addr,
 		return 0;
 	}
 
-	ret = amdgpu_ttm_tt_get_user_pages(bo, bo->tbo.ttm->pages, &range);
+	ret = amdgpu_ttm_tt_get_user_pages(bo, &range);
 	if (ret) {
 		if (ret == -EAGAIN)
 			pr_debug("Failed to get user pages, try again\n");
@@ -1103,6 +1103,9 @@ static int init_user_pages(struct kgd_mem *mem, uint64_t user_addr,
 		pr_err("%s: Failed to reserve BO\n", __func__);
 		goto release_out;
 	}
+
+	amdgpu_ttm_tt_set_user_pages(bo->tbo.ttm, range);
+
 	amdgpu_bo_placement_from_domain(bo, mem->domain);
 	ret = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx);
 	if (ret)
@@ -2565,8 +2568,7 @@ static int update_invalid_user_pages(struct amdkfd_process_info *process_info,
 		}
 
 		/* Get updated user pages */
-		ret = amdgpu_ttm_tt_get_user_pages(bo, bo->tbo.ttm->pages,
-						   &mem->range);
+		ret = amdgpu_ttm_tt_get_user_pages(bo, &mem->range);
 		if (ret) {
 			pr_debug("Failed %d to get user pages\n", ret);
 
@@ -2584,17 +2586,24 @@ static int update_invalid_user_pages(struct amdkfd_process_info *process_info,
 			 * from the KFD, trigger a segmentation fault in VM debug mode.
 			 */
 			if (amdgpu_ttm_adev(bo->tbo.bdev)->debug_vm_userptr) {
+				struct kfd_process *p;
+
 				pr_err("Pid %d unmapped memory before destroying userptr at GPU addr 0x%llx\n",
 								pid_nr(process_info->pid), mem->va);
 
 				// Send GPU VM fault to user space
-				kfd_signal_vm_fault_event_with_userptr(kfd_lookup_process_by_pid(process_info->pid),
-								mem->va);
+				p = kfd_lookup_process_by_pid(process_info->pid);
+				if (p) {
+					kfd_signal_vm_fault_event_with_userptr(p, mem->va);
+					kfd_unref_process(p);
+				}
 			}
 
 			ret = 0;
 		}
 
+		amdgpu_ttm_tt_set_user_pages(bo->tbo.ttm, mem->range);
+
 		mutex_lock(&process_info->notifier_lock);
 
 		/* Mark the BO as valid unless it was invalidated
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.h
index 555cd6d877c3..a716c9886c74 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.h
@@ -38,7 +38,6 @@ struct amdgpu_bo_list_entry {
 	struct amdgpu_bo		*bo;
 	struct amdgpu_bo_va		*bo_va;
 	uint32_t			priority;
-	struct page			**user_pages;
 	struct hmm_range		*range;
 	bool				user_invalidated;
 };
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c
index bf38fc69c1cf..47e9bfba0642 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c
@@ -398,30 +398,28 @@ static void amdgpu_connector_add_common_modes(struct drm_encoder *encoder,
 	struct drm_display_mode *mode = NULL;
 	struct drm_display_mode *native_mode = &amdgpu_encoder->native_mode;
 	int i;
-	static const struct mode_size {
+	int n;
+	struct mode_size {
+		char name[DRM_DISPLAY_MODE_LEN];
 		int w;
 		int h;
-	} common_modes[17] = {
-		{ 640,  480},
-		{ 720,  480},
-		{ 800,  600},
-		{ 848,  480},
-		{1024,  768},
-		{1152,  768},
-		{1280,  720},
-		{1280,  800},
-		{1280,  854},
-		{1280,  960},
-		{1280, 1024},
-		{1440,  900},
-		{1400, 1050},
-		{1680, 1050},
-		{1600, 1200},
-		{1920, 1080},
-		{1920, 1200}
+	} common_modes[] = {
+		{  "640x480",  640,  480},
+		{  "800x600",  800,  600},
+		{ "1024x768", 1024,  768},
+		{ "1280x720", 1280,  720},
+		{ "1280x800", 1280,  800},
+		{"1280x1024", 1280, 1024},
+		{ "1440x900", 1440,  900},
+		{"1680x1050", 1680, 1050},
+		{"1600x1200", 1600, 1200},
+		{"1920x1080", 1920, 1080},
+		{"1920x1200", 1920, 1200}
 	};
 
-	for (i = 0; i < 17; i++) {
+	n = ARRAY_SIZE(common_modes);
+
+	for (i = 0; i < n; i++) {
 		if (amdgpu_encoder->devices & (ATOM_DEVICE_TV_SUPPORT)) {
 			if (common_modes[i].w > 1024 ||
 			    common_modes[i].h > 768)
@@ -434,12 +432,11 @@ static void amdgpu_connector_add_common_modes(struct drm_encoder *encoder,
 			     common_modes[i].h == native_mode->vdisplay))
 				continue;
 		}
-		if (common_modes[i].w < 320 || common_modes[i].h < 200)
-			continue;
 
 		mode = drm_cvt_mode(dev, common_modes[i].w, common_modes[i].h, 60, false, false, false);
 		if (!mode)
 			return;
+		strscpy(mode->name, common_modes[i].name, DRM_DISPLAY_MODE_LEN);
 
 		drm_mode_probed_add(connector, mode);
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index defb511acc5a..9cd7741d2254 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -29,6 +29,7 @@
 #include <linux/pagemap.h>
 #include <linux/sync_file.h>
 #include <linux/dma-buf.h>
+#include <linux/hmm.h>
 
 #include <drm/amdgpu_drm.h>
 #include <drm/drm_syncobj.h>
@@ -883,26 +884,13 @@ static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p,
 	amdgpu_bo_list_for_each_userptr_entry(e, p->bo_list) {
 		bool userpage_invalidated = false;
 		struct amdgpu_bo *bo = e->bo;
-		int i;
-
-		e->user_pages = kvcalloc(bo->tbo.ttm->num_pages,
-					 sizeof(struct page *),
-					 GFP_KERNEL);
-		if (!e->user_pages) {
-			drm_err(adev_to_drm(p->adev), "kvmalloc_array failure\n");
-			r = -ENOMEM;
-			goto out_free_user_pages;
-		}
 
-		r = amdgpu_ttm_tt_get_user_pages(bo, e->user_pages, &e->range);
-		if (r) {
-			kvfree(e->user_pages);
-			e->user_pages = NULL;
+		r = amdgpu_ttm_tt_get_user_pages(bo, &e->range);
+		if (r)
 			goto out_free_user_pages;
-		}
 
 		for (i = 0; i < bo->tbo.ttm->num_pages; i++) {
-			if (bo->tbo.ttm->pages[i] != e->user_pages[i]) {
+			if (bo->tbo.ttm->pages[i] != hmm_pfn_to_page(e->range->hmm_pfns[i])) {
 				userpage_invalidated = true;
 				break;
 			}
@@ -946,7 +934,7 @@ static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p,
 		}
 
 		if (amdgpu_ttm_tt_is_userptr(e->bo->tbo.ttm) &&
-		    e->user_invalidated && e->user_pages) {
+		    e->user_invalidated) {
 			amdgpu_bo_placement_from_domain(e->bo,
 							AMDGPU_GEM_DOMAIN_CPU);
 			r = ttm_bo_validate(&e->bo->tbo, &e->bo->placement,
@@ -955,11 +943,8 @@ static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p,
 				goto out_free_user_pages;
 
 			amdgpu_ttm_tt_set_user_pages(e->bo->tbo.ttm,
-						     e->user_pages);
+						     e->range);
 		}
-
-		kvfree(e->user_pages);
-		e->user_pages = NULL;
 	}
 
 	amdgpu_cs_get_threshold_for_moves(p->adev, &p->bytes_moved_threshold,
@@ -1001,11 +986,7 @@ out_free_user_pages:
 	amdgpu_bo_list_for_each_userptr_entry(e, p->bo_list) {
 		struct amdgpu_bo *bo = e->bo;
 
-		if (!e->user_pages)
-			continue;
 		amdgpu_ttm_tt_get_user_pages_done(bo->tbo.ttm, e->range);
-		kvfree(e->user_pages);
-		e->user_pages = NULL;
 		e->range = NULL;
 	}
 	mutex_unlock(&p->bo_list->bo_list_mutex);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index a77000c2e0bb..7a899fb4de29 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -6389,23 +6389,28 @@ static int amdgpu_device_sched_resume(struct list_head *device_list,
 		if (!drm_drv_uses_atomic_modeset(adev_to_drm(tmp_adev)) && !job_signaled)
 			drm_helper_resume_force_mode(adev_to_drm(tmp_adev));
 
-		if (tmp_adev->asic_reset_res)
-			r = tmp_adev->asic_reset_res;
-
-		tmp_adev->asic_reset_res = 0;
-
-		if (r) {
+		if (tmp_adev->asic_reset_res) {
 			/* bad news, how to tell it to userspace ?
 			 * for ras error, we should report GPU bad status instead of
 			 * reset failure
 			 */
 			if (reset_context->src != AMDGPU_RESET_SRC_RAS ||
 			    !amdgpu_ras_eeprom_check_err_threshold(tmp_adev))
-				dev_info(tmp_adev->dev, "GPU reset(%d) failed\n",
-					atomic_read(&tmp_adev->gpu_reset_counter));
-			amdgpu_vf_error_put(tmp_adev, AMDGIM_ERROR_VF_GPU_RESET_FAIL, 0, r);
+				dev_info(
+					tmp_adev->dev,
+					"GPU reset(%d) failed with error %d \n",
+					atomic_read(
+						&tmp_adev->gpu_reset_counter),
+					tmp_adev->asic_reset_res);
+			amdgpu_vf_error_put(tmp_adev,
+					    AMDGIM_ERROR_VF_GPU_RESET_FAIL, 0,
+					    tmp_adev->asic_reset_res);
+			if (!r)
+				r = tmp_adev->asic_reset_res;
+			tmp_adev->asic_reset_res = 0;
 		} else {
-			dev_info(tmp_adev->dev, "GPU reset(%d) succeeded!\n", atomic_read(&tmp_adev->gpu_reset_counter));
+			dev_info(tmp_adev->dev, "GPU reset(%d) succeeded!\n",
+				 atomic_read(&tmp_adev->gpu_reset_counter));
 			if (amdgpu_acpi_smart_shift_update(tmp_adev,
 							   AMDGPU_SS_DEV_D0))
 				dev_warn(tmp_adev->dev,
@@ -7157,28 +7162,35 @@ void amdgpu_pci_resume(struct pci_dev *pdev)
 
 static void amdgpu_device_cache_switch_state(struct amdgpu_device *adev)
 {
-	struct pci_dev *parent = pci_upstream_bridge(adev->pdev);
+	struct pci_dev *swus, *swds;
 	int r;
 
-	if (!parent || parent->vendor != PCI_VENDOR_ID_ATI)
+	swds = pci_upstream_bridge(adev->pdev);
+	if (!swds || swds->vendor != PCI_VENDOR_ID_ATI ||
+	    pci_pcie_type(swds) != PCI_EXP_TYPE_DOWNSTREAM)
+		return;
+	swus = pci_upstream_bridge(swds);
+	if (!swus ||
+	    (swus->vendor != PCI_VENDOR_ID_ATI &&
+	     swus->vendor != PCI_VENDOR_ID_AMD) ||
+	    pci_pcie_type(swus) != PCI_EXP_TYPE_UPSTREAM)
 		return;
 
 	/* If already saved, return */
 	if (adev->pcie_reset_ctx.swus)
 		return;
 	/* Upstream bridge is ATI, assume it's SWUS/DS architecture */
-	r = pci_save_state(parent);
+	r = pci_save_state(swds);
 	if (r)
 		return;
-	adev->pcie_reset_ctx.swds_pcistate = pci_store_saved_state(parent);
+	adev->pcie_reset_ctx.swds_pcistate = pci_store_saved_state(swds);
 
-	parent = pci_upstream_bridge(parent);
-	r = pci_save_state(parent);
+	r = pci_save_state(swus);
 	if (r)
 		return;
-	adev->pcie_reset_ctx.swus_pcistate = pci_store_saved_state(parent);
+	adev->pcie_reset_ctx.swus_pcistate = pci_store_saved_state(swus);
 
-	adev->pcie_reset_ctx.swus = parent;
+	adev->pcie_reset_ctx.swus = swus;
 }
 
 static void amdgpu_device_load_switch_state(struct amdgpu_device *adev)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index ece251cbe8c3..bff25ef3e2d0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -960,7 +960,7 @@ module_param_named(tmz, amdgpu_tmz, int, 0444);
  */
 MODULE_PARM_DESC(
 	freesync_video,
-	"Enable freesync modesetting optimization feature (0 = off (default), 1 = on)");
+	"Adds additional modes via VRR for refresh changes without a full modeset (0 = off (default), 1 = on)");
 module_param_named(freesync_video, amdgpu_freesync_vid_mode, uint, 0444);
 
 /**
@@ -2674,7 +2674,7 @@ static int amdgpu_pmops_thaw(struct device *dev)
 	struct drm_device *drm_dev = dev_get_drvdata(dev);
 
 	/* do not resume device if it's normal hibernation */
-	if (!pm_hibernate_is_recovering())
+	if (!pm_hibernate_is_recovering() && !pm_hibernation_mode_is_suspend())
 		return 0;
 
 	return amdgpu_device_resume(drm_dev, true);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
index 1679c2c3d505..b7ebae289bea 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
@@ -572,8 +572,7 @@ int amdgpu_gem_userptr_ioctl(struct drm_device *dev, void *data,
 		goto release_object;
 
 	if (args->flags & AMDGPU_GEM_USERPTR_VALIDATE) {
-		r = amdgpu_ttm_tt_get_user_pages(bo, bo->tbo.ttm->pages,
-						 &range);
+		r = amdgpu_ttm_tt_get_user_pages(bo, &range);
 		if (r)
 			goto release_object;
 
@@ -581,6 +580,8 @@ int amdgpu_gem_userptr_ioctl(struct drm_device *dev, void *data,
 		if (r)
 			goto user_pages_done;
 
+		amdgpu_ttm_tt_set_user_pages(bo->tbo.ttm, range);
+
 		amdgpu_bo_placement_from_domain(bo, AMDGPU_GEM_DOMAIN_GTT);
 		r = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx);
 		amdgpu_bo_unreserve(bo);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
index a09ccf7d8aa2..ebe2b4c68b0f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
@@ -1102,6 +1102,9 @@ uint32_t amdgpu_kiq_rreg(struct amdgpu_device *adev, uint32_t reg, uint32_t xcc_
 
 	might_sleep();
 	while (r < 1 && cnt++ < MAX_KIQ_REG_TRY) {
+		if (amdgpu_in_reset(adev))
+			goto failed_kiq_read;
+
 		msleep(MAX_KIQ_REG_BAILOUT_INTERVAL);
 		r = amdgpu_fence_wait_polling(ring, seq, MAX_KIQ_REG_WAIT);
 	}
@@ -1171,6 +1174,8 @@ void amdgpu_kiq_wreg(struct amdgpu_device *adev, uint32_t reg, uint32_t v, uint3
 
 	might_sleep();
 	while (r < 1 && cnt++ < MAX_KIQ_REG_TRY) {
+		if (amdgpu_in_reset(adev))
+			goto failed_kiq_write;
 
 		msleep(MAX_KIQ_REG_BAILOUT_INTERVAL);
 		r = amdgpu_fence_wait_polling(ring, seq, MAX_KIQ_REG_WAIT);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_hmm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_hmm.c
index e36fede7f74c..2c6a6b858112 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_hmm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_hmm.c
@@ -167,13 +167,12 @@ void amdgpu_hmm_unregister(struct amdgpu_bo *bo)
 
 int amdgpu_hmm_range_get_pages(struct mmu_interval_notifier *notifier,
 			       uint64_t start, uint64_t npages, bool readonly,
-			       void *owner, struct page **pages,
+			       void *owner,
 			       struct hmm_range **phmm_range)
 {
 	struct hmm_range *hmm_range;
 	unsigned long end;
 	unsigned long timeout;
-	unsigned long i;
 	unsigned long *pfns;
 	int r = 0;
 
@@ -222,14 +221,6 @@ retry:
 	hmm_range->start = start;
 	hmm_range->hmm_pfns = pfns;
 
-	/*
-	 * Due to default_flags, all pages are HMM_PFN_VALID or
-	 * hmm_range_fault() fails. FIXME: The pages cannot be touched outside
-	 * the notifier_lock, and mmu_interval_read_retry() must be done first.
-	 */
-	for (i = 0; pages && i < npages; i++)
-		pages[i] = hmm_pfn_to_page(pfns[i]);
-
 	*phmm_range = hmm_range;
 
 	return 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_hmm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_hmm.h
index e2edcd010ccc..953e1d06de20 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_hmm.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_hmm.h
@@ -33,7 +33,7 @@
 
 int amdgpu_hmm_range_get_pages(struct mmu_interval_notifier *notifier,
 			       uint64_t start, uint64_t npages, bool readonly,
-			       void *owner, struct page **pages,
+			       void *owner,
 			       struct hmm_range **phmm_range);
 bool amdgpu_hmm_range_get_pages_done(struct hmm_range *hmm_range);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c
index 5dd78a9cb12d..3ef5bc95642c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c
@@ -275,13 +275,12 @@ static int amdgpu_vmid_grab_reserved(struct amdgpu_vm *vm,
 {
 	struct amdgpu_device *adev = ring->adev;
 	unsigned vmhub = ring->vm_hub;
-	struct amdgpu_vmid_mgr *id_mgr = &adev->vm_manager.id_mgr[vmhub];
 	uint64_t fence_context = adev->fence_context + ring->idx;
 	bool needs_flush = vm->use_cpu_for_update;
 	uint64_t updates = amdgpu_vm_tlb_seq(vm);
 	int r;
 
-	*id = id_mgr->reserved;
+	*id = vm->reserved_vmid[vmhub];
 	if ((*id)->owner != vm->immediate.fence_context ||
 	    !amdgpu_vmid_compatible(*id, job) ||
 	    (*id)->flushed_updates < updates ||
@@ -474,40 +473,61 @@ bool amdgpu_vmid_uses_reserved(struct amdgpu_vm *vm, unsigned int vmhub)
 	return vm->reserved_vmid[vmhub];
 }
 
-int amdgpu_vmid_alloc_reserved(struct amdgpu_device *adev,
+/*
+ * amdgpu_vmid_alloc_reserved - reserve a specific VMID for this vm
+ * @adev: amdgpu device structure
+ * @vm: the VM to reserve an ID for
+ * @vmhub: the VMHUB which should be used
+ *
+ * Mostly used to have a reserved VMID for debugging and SPM.
+ *
+ * Returns: 0 for success, -ENOENT if an ID is already reserved.
+ */
+int amdgpu_vmid_alloc_reserved(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 			       unsigned vmhub)
 {
 	struct amdgpu_vmid_mgr *id_mgr = &adev->vm_manager.id_mgr[vmhub];
+	struct amdgpu_vmid *id;
+	int r = 0;
 
 	mutex_lock(&id_mgr->lock);
-
-	++id_mgr->reserved_use_count;
-	if (!id_mgr->reserved) {
-		struct amdgpu_vmid *id;
-
-		id = list_first_entry(&id_mgr->ids_lru, struct amdgpu_vmid,
-				      list);
-		/* Remove from normal round robin handling */
-		list_del_init(&id->list);
-		id_mgr->reserved = id;
+	if (vm->reserved_vmid[vmhub])
+		goto unlock;
+	if (id_mgr->reserved_vmid) {
+		r = -ENOENT;
+		goto unlock;
 	}
-
+	/* Remove from normal round robin handling */
+	id = list_first_entry(&id_mgr->ids_lru, struct amdgpu_vmid, list);
+	list_del_init(&id->list);
+	vm->reserved_vmid[vmhub] = id;
+	id_mgr->reserved_vmid = true;
 	mutex_unlock(&id_mgr->lock);
+
 	return 0;
+unlock:
+	mutex_unlock(&id_mgr->lock);
+	return r;
 }
 
-void amdgpu_vmid_free_reserved(struct amdgpu_device *adev,
+/*
+ * amdgpu_vmid_free_reserved - free up a reserved VMID again
+ * @adev: amdgpu device structure
+ * @vm: the VM with the reserved ID
+ * @vmhub: the VMHUB which should be used
+ */
+void amdgpu_vmid_free_reserved(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 			       unsigned vmhub)
 {
 	struct amdgpu_vmid_mgr *id_mgr = &adev->vm_manager.id_mgr[vmhub];
 
 	mutex_lock(&id_mgr->lock);
-	if (!--id_mgr->reserved_use_count) {
-		/* give the reserved ID back to normal round robin */
-		list_add(&id_mgr->reserved->list, &id_mgr->ids_lru);
-		id_mgr->reserved = NULL;
+	if (vm->reserved_vmid[vmhub]) {
+		list_add(&vm->reserved_vmid[vmhub]->list,
+			&id_mgr->ids_lru);
+		vm->reserved_vmid[vmhub] = NULL;
+		id_mgr->reserved_vmid = false;
 	}
-
 	mutex_unlock(&id_mgr->lock);
 }
 
@@ -574,7 +594,6 @@ void amdgpu_vmid_mgr_init(struct amdgpu_device *adev)
 
 		mutex_init(&id_mgr->lock);
 		INIT_LIST_HEAD(&id_mgr->ids_lru);
-		id_mgr->reserved_use_count = 0;
 
 		/* for GC <10, SDMA uses MMHUB so use first_kfd_vmid for both GC and MM */
 		if (amdgpu_ip_version(adev, GC_HWIP, 0) < IP_VERSION(10, 0, 0))
@@ -594,11 +613,6 @@ void amdgpu_vmid_mgr_init(struct amdgpu_device *adev)
 			list_add_tail(&id_mgr->ids[j].list, &id_mgr->ids_lru);
 		}
 	}
-	/* alloc a default reserved vmid to enforce isolation */
-	for (i = 0; i < (adev->xcp_mgr ? adev->xcp_mgr->num_xcps : 1); i++) {
-		if (adev->enforce_isolation[i] != AMDGPU_ENFORCE_ISOLATION_DISABLE)
-			amdgpu_vmid_alloc_reserved(adev, AMDGPU_GFXHUB(i));
-	}
 }
 
 /**
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.h
index 240fa6751260..b3649cd3af56 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.h
@@ -67,8 +67,7 @@ struct amdgpu_vmid_mgr {
 	unsigned		num_ids;
 	struct list_head	ids_lru;
 	struct amdgpu_vmid	ids[AMDGPU_NUM_VMID];
-	struct amdgpu_vmid	*reserved;
-	unsigned int		reserved_use_count;
+	bool			reserved_vmid;
 };
 
 int amdgpu_pasid_alloc(unsigned int bits);
@@ -79,10 +78,10 @@ void amdgpu_pasid_free_delayed(struct dma_resv *resv,
 bool amdgpu_vmid_had_gpu_reset(struct amdgpu_device *adev,
 			       struct amdgpu_vmid *id);
 bool amdgpu_vmid_uses_reserved(struct amdgpu_vm *vm, unsigned int vmhub);
-int amdgpu_vmid_alloc_reserved(struct amdgpu_device *adev,
-				unsigned vmhub);
-void amdgpu_vmid_free_reserved(struct amdgpu_device *adev,
-				unsigned vmhub);
+int amdgpu_vmid_alloc_reserved(struct amdgpu_device *adev, struct amdgpu_vm *vm,
+			       unsigned vmhub);
+void amdgpu_vmid_free_reserved(struct amdgpu_device *adev, struct amdgpu_vm *vm,
+			       unsigned vmhub);
 int amdgpu_vmid_grab(struct amdgpu_vm *vm, struct amdgpu_ring *ring,
 		     struct amdgpu_job *job, struct dma_fence **fence);
 void amdgpu_vmid_reset(struct amdgpu_device *adev, unsigned vmhub,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
index 8676400834fc..a9327472c651 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
@@ -1421,14 +1421,10 @@ int amdgpu_driver_open_kms(struct drm_device *dev, struct drm_file *file_priv)
 
 	amdgpu_debugfs_vm_init(file_priv);
 
-	r = amdgpu_vm_init(adev, &fpriv->vm, fpriv->xcp_id);
+	r = amdgpu_vm_init(adev, &fpriv->vm, fpriv->xcp_id, pasid);
 	if (r)
 		goto error_pasid;
 
-	r = amdgpu_vm_set_pasid(adev, &fpriv->vm, pasid);
-	if (r)
-		goto error_vm;
-
 	fpriv->prt_va = amdgpu_vm_bo_add(adev, &fpriv->vm, NULL);
 	if (!fpriv->prt_va) {
 		r = -ENOMEM;
@@ -1468,10 +1464,8 @@ error_vm:
 	amdgpu_vm_fini(adev, &fpriv->vm);
 
 error_pasid:
-	if (pasid) {
+	if (pasid)
 		amdgpu_pasid_free(pasid);
-		amdgpu_vm_set_pasid(adev, &fpriv->vm, 0);
-	}
 
 	kfree(fpriv);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
index 1578e4e2bf84..8c0e5d03de50 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
@@ -2352,7 +2352,7 @@ static int psp_securedisplay_initialize(struct psp_context *psp)
 	}
 
 	ret = psp_ta_load(psp, &psp->securedisplay_context.context);
-	if (!ret) {
+	if (!ret && !psp->securedisplay_context.context.resp_status) {
 		psp->securedisplay_context.context.initialized = true;
 		mutex_init(&psp->securedisplay_context.mutex);
 	} else
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index 71b6691edab4..aa9ee5dffa45 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -708,7 +708,7 @@ struct amdgpu_ttm_tt {
  * Calling function must call amdgpu_ttm_tt_userptr_range_done() once and only
  * once afterwards to stop HMM tracking
  */
-int amdgpu_ttm_tt_get_user_pages(struct amdgpu_bo *bo, struct page **pages,
+int amdgpu_ttm_tt_get_user_pages(struct amdgpu_bo *bo,
 				 struct hmm_range **range)
 {
 	struct ttm_tt *ttm = bo->tbo.ttm;
@@ -745,7 +745,7 @@ int amdgpu_ttm_tt_get_user_pages(struct amdgpu_bo *bo, struct page **pages,
 
 	readonly = amdgpu_ttm_tt_is_readonly(ttm);
 	r = amdgpu_hmm_range_get_pages(&bo->notifier, start, ttm->num_pages,
-				       readonly, NULL, pages, range);
+				       readonly, NULL, range);
 out_unlock:
 	mmap_read_unlock(mm);
 	if (r)
@@ -797,12 +797,12 @@ bool amdgpu_ttm_tt_get_user_pages_done(struct ttm_tt *ttm,
  * that backs user memory and will ultimately be mapped into the device
  * address space.
  */
-void amdgpu_ttm_tt_set_user_pages(struct ttm_tt *ttm, struct page **pages)
+void amdgpu_ttm_tt_set_user_pages(struct ttm_tt *ttm, struct hmm_range *range)
 {
 	unsigned long i;
 
 	for (i = 0; i < ttm->num_pages; ++i)
-		ttm->pages[i] = pages ? pages[i] : NULL;
+		ttm->pages[i] = range ? hmm_pfn_to_page(range->hmm_pfns[i]) : NULL;
 }
 
 /*
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
index 1c5c7836ce4f..0be2728aa872 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
@@ -191,7 +191,7 @@ void amdgpu_ttm_recover_gart(struct ttm_buffer_object *tbo);
 uint64_t amdgpu_ttm_domain_start(struct amdgpu_device *adev, uint32_t type);
 
 #if IS_ENABLED(CONFIG_DRM_AMDGPU_USERPTR)
-int amdgpu_ttm_tt_get_user_pages(struct amdgpu_bo *bo, struct page **pages,
+int amdgpu_ttm_tt_get_user_pages(struct amdgpu_bo *bo,
 				 struct hmm_range **range);
 void amdgpu_ttm_tt_discard_user_pages(struct ttm_tt *ttm,
 				      struct hmm_range *range);
@@ -199,7 +199,6 @@ bool amdgpu_ttm_tt_get_user_pages_done(struct ttm_tt *ttm,
 				       struct hmm_range *range);
 #else
 static inline int amdgpu_ttm_tt_get_user_pages(struct amdgpu_bo *bo,
-					       struct page **pages,
 					       struct hmm_range **range)
 {
 	return -EPERM;
@@ -215,7 +214,7 @@ static inline bool amdgpu_ttm_tt_get_user_pages_done(struct ttm_tt *ttm,
 }
 #endif
 
-void amdgpu_ttm_tt_set_user_pages(struct ttm_tt *ttm, struct page **pages);
+void amdgpu_ttm_tt_set_user_pages(struct ttm_tt *ttm, struct hmm_range *range);
 int amdgpu_ttm_tt_get_userptr(const struct ttm_buffer_object *tbo,
 			      uint64_t *user_addr);
 int amdgpu_ttm_tt_set_userptr(struct ttm_buffer_object *bo,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c
index a22e6025de61..1add21160d21 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c
@@ -71,6 +71,7 @@ int amdgpu_userq_input_va_validate(struct amdgpu_vm *vm, u64 addr,
 		return 0;
 	}
 
+	r = -EINVAL;
 out_err:
 	amdgpu_bo_unreserve(vm->root.bo);
 	return r;
@@ -508,6 +509,7 @@ amdgpu_userq_create(struct drm_file *filp, union drm_amdgpu_userq *args)
 	if (amdgpu_userq_input_va_validate(&fpriv->vm, args->in.queue_va, args->in.queue_size) ||
 	    amdgpu_userq_input_va_validate(&fpriv->vm, args->in.rptr_va, AMDGPU_GPU_PAGE_SIZE) ||
 	    amdgpu_userq_input_va_validate(&fpriv->vm, args->in.wptr_va, AMDGPU_GPU_PAGE_SIZE)) {
+		r = -EINVAL;
 		kfree(queue);
 		goto unlock;
 	}
@@ -724,12 +726,12 @@ amdgpu_userq_bo_validate(struct amdgpu_device *adev, struct drm_exec *exec,
 	struct amdgpu_bo *bo;
 	int ret;
 
-	spin_lock(&vm->invalidated_lock);
+	spin_lock(&vm->status_lock);
 	while (!list_empty(&vm->invalidated)) {
 		bo_va = list_first_entry(&vm->invalidated,
 					 struct amdgpu_bo_va,
 					 base.vm_status);
-		spin_unlock(&vm->invalidated_lock);
+		spin_unlock(&vm->status_lock);
 
 		bo = bo_va->base.bo;
 		ret = drm_exec_prepare_obj(exec, &bo->tbo.base, 2);
@@ -746,9 +748,9 @@ amdgpu_userq_bo_validate(struct amdgpu_device *adev, struct drm_exec *exec,
 		if (ret)
 			return ret;
 
-		spin_lock(&vm->invalidated_lock);
+		spin_lock(&vm->status_lock);
 	}
-	spin_unlock(&vm->invalidated_lock);
+	spin_unlock(&vm->status_lock);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c
index 95e91d1dc58a..761bad98da3e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c
@@ -284,7 +284,7 @@ static int amdgpu_userq_fence_create(struct amdgpu_usermode_queue *userq,
 
 	/* Check if hardware has already processed the job */
 	spin_lock_irqsave(&fence_drv->fence_list_lock, flags);
-	if (!dma_fence_is_signaled_locked(fence))
+	if (!dma_fence_is_signaled(fence))
 		list_add_tail(&userq_fence->link, &fence_drv->fences);
 	else
 		dma_fence_put(fence);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h
index bebfc2b34afe..dc8a17bcc3c8 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h
@@ -501,7 +501,7 @@ struct amdgpu_vcn5_fw_shared {
 	struct amdgpu_fw_shared_rb_setup rb_setup;
 	struct amdgpu_fw_shared_smu_interface_info smu_dpm_interface;
 	struct amdgpu_fw_shared_drm_key_wa drm_key_wa;
-	uint8_t pad3[9];
+	uint8_t pad3[404];
 };
 
 #define VCN_BLOCK_ENCODE_DISABLE_MASK 0x80
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index 112ce584a5ad..c1a801203949 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -139,48 +139,6 @@ static void amdgpu_vm_assert_locked(struct amdgpu_vm *vm)
 }
 
 /**
- * amdgpu_vm_set_pasid - manage pasid and vm ptr mapping
- *
- * @adev: amdgpu_device pointer
- * @vm: amdgpu_vm pointer
- * @pasid: the pasid the VM is using on this GPU
- *
- * Set the pasid this VM is using on this GPU, can also be used to remove the
- * pasid by passing in zero.
- *
- */
-int amdgpu_vm_set_pasid(struct amdgpu_device *adev, struct amdgpu_vm *vm,
-			u32 pasid)
-{
-	int r;
-
-	amdgpu_vm_assert_locked(vm);
-
-	if (vm->pasid == pasid)
-		return 0;
-
-	if (vm->pasid) {
-		r = xa_err(xa_erase_irq(&adev->vm_manager.pasids, vm->pasid));
-		if (r < 0)
-			return r;
-
-		vm->pasid = 0;
-	}
-
-	if (pasid) {
-		r = xa_err(xa_store_irq(&adev->vm_manager.pasids, pasid, vm,
-					GFP_KERNEL));
-		if (r < 0)
-			return r;
-
-		vm->pasid = pasid;
-	}
-
-
-	return 0;
-}
-
-/**
  * amdgpu_vm_bo_evicted - vm_bo is evicted
  *
  * @vm_bo: vm_bo which is evicted
@@ -195,10 +153,12 @@ static void amdgpu_vm_bo_evicted(struct amdgpu_vm_bo_base *vm_bo)
 
 	vm_bo->moved = true;
 	amdgpu_vm_assert_locked(vm);
+	spin_lock(&vm_bo->vm->status_lock);
 	if (bo->tbo.type == ttm_bo_type_kernel)
 		list_move(&vm_bo->vm_status, &vm->evicted);
 	else
 		list_move_tail(&vm_bo->vm_status, &vm->evicted);
+	spin_unlock(&vm_bo->vm->status_lock);
 }
 /**
  * amdgpu_vm_bo_moved - vm_bo is moved
@@ -211,7 +171,9 @@ static void amdgpu_vm_bo_evicted(struct amdgpu_vm_bo_base *vm_bo)
 static void amdgpu_vm_bo_moved(struct amdgpu_vm_bo_base *vm_bo)
 {
 	amdgpu_vm_assert_locked(vm_bo->vm);
+	spin_lock(&vm_bo->vm->status_lock);
 	list_move(&vm_bo->vm_status, &vm_bo->vm->moved);
+	spin_unlock(&vm_bo->vm->status_lock);
 }
 
 /**
@@ -225,7 +187,9 @@ static void amdgpu_vm_bo_moved(struct amdgpu_vm_bo_base *vm_bo)
 static void amdgpu_vm_bo_idle(struct amdgpu_vm_bo_base *vm_bo)
 {
 	amdgpu_vm_assert_locked(vm_bo->vm);
+	spin_lock(&vm_bo->vm->status_lock);
 	list_move(&vm_bo->vm_status, &vm_bo->vm->idle);
+	spin_unlock(&vm_bo->vm->status_lock);
 	vm_bo->moved = false;
 }
 
@@ -239,9 +203,9 @@ static void amdgpu_vm_bo_idle(struct amdgpu_vm_bo_base *vm_bo)
  */
 static void amdgpu_vm_bo_invalidated(struct amdgpu_vm_bo_base *vm_bo)
 {
-	spin_lock(&vm_bo->vm->invalidated_lock);
+	spin_lock(&vm_bo->vm->status_lock);
 	list_move(&vm_bo->vm_status, &vm_bo->vm->invalidated);
-	spin_unlock(&vm_bo->vm->invalidated_lock);
+	spin_unlock(&vm_bo->vm->status_lock);
 }
 
 /**
@@ -254,9 +218,10 @@ static void amdgpu_vm_bo_invalidated(struct amdgpu_vm_bo_base *vm_bo)
  */
 static void amdgpu_vm_bo_evicted_user(struct amdgpu_vm_bo_base *vm_bo)
 {
-	amdgpu_vm_assert_locked(vm_bo->vm);
 	vm_bo->moved = true;
+	spin_lock(&vm_bo->vm->status_lock);
 	list_move(&vm_bo->vm_status, &vm_bo->vm->evicted_user);
+	spin_unlock(&vm_bo->vm->status_lock);
 }
 
 /**
@@ -270,10 +235,13 @@ static void amdgpu_vm_bo_evicted_user(struct amdgpu_vm_bo_base *vm_bo)
 static void amdgpu_vm_bo_relocated(struct amdgpu_vm_bo_base *vm_bo)
 {
 	amdgpu_vm_assert_locked(vm_bo->vm);
-	if (vm_bo->bo->parent)
+	if (vm_bo->bo->parent) {
+		spin_lock(&vm_bo->vm->status_lock);
 		list_move(&vm_bo->vm_status, &vm_bo->vm->relocated);
-	else
+		spin_unlock(&vm_bo->vm->status_lock);
+	} else {
 		amdgpu_vm_bo_idle(vm_bo);
+	}
 }
 
 /**
@@ -287,7 +255,9 @@ static void amdgpu_vm_bo_relocated(struct amdgpu_vm_bo_base *vm_bo)
 static void amdgpu_vm_bo_done(struct amdgpu_vm_bo_base *vm_bo)
 {
 	amdgpu_vm_assert_locked(vm_bo->vm);
+	spin_lock(&vm_bo->vm->status_lock);
 	list_move(&vm_bo->vm_status, &vm_bo->vm->done);
+	spin_unlock(&vm_bo->vm->status_lock);
 }
 
 /**
@@ -301,13 +271,13 @@ static void amdgpu_vm_bo_reset_state_machine(struct amdgpu_vm *vm)
 {
 	struct amdgpu_vm_bo_base *vm_bo, *tmp;
 
-	spin_lock(&vm->invalidated_lock);
+	amdgpu_vm_assert_locked(vm);
+
+	spin_lock(&vm->status_lock);
 	list_splice_init(&vm->done, &vm->invalidated);
 	list_for_each_entry(vm_bo, &vm->invalidated, vm_status)
 		vm_bo->moved = true;
-	spin_unlock(&vm->invalidated_lock);
 
-	amdgpu_vm_assert_locked(vm_bo->vm);
 	list_for_each_entry_safe(vm_bo, tmp, &vm->idle, vm_status) {
 		struct amdgpu_bo *bo = vm_bo->bo;
 
@@ -317,13 +287,14 @@ static void amdgpu_vm_bo_reset_state_machine(struct amdgpu_vm *vm)
 		else if (bo->parent)
 			list_move(&vm_bo->vm_status, &vm_bo->vm->relocated);
 	}
+	spin_unlock(&vm->status_lock);
 }
 
 /**
  * amdgpu_vm_update_shared - helper to update shared memory stat
  * @base: base structure for tracking BO usage in a VM
  *
- * Takes the vm stats_lock and updates the shared memory stat. If the basic
+ * Takes the vm status_lock and updates the shared memory stat. If the basic
  * stat changed (e.g. buffer was moved) amdgpu_vm_update_stats need to be called
  * as well.
  */
@@ -336,7 +307,7 @@ static void amdgpu_vm_update_shared(struct amdgpu_vm_bo_base *base)
 	bool shared;
 
 	dma_resv_assert_held(bo->tbo.base.resv);
-	spin_lock(&vm->stats_lock);
+	spin_lock(&vm->status_lock);
 	shared = drm_gem_object_is_shared_for_memory_stats(&bo->tbo.base);
 	if (base->shared != shared) {
 		base->shared = shared;
@@ -348,7 +319,7 @@ static void amdgpu_vm_update_shared(struct amdgpu_vm_bo_base *base)
 			vm->stats[bo_memtype].drm.private += size;
 		}
 	}
-	spin_unlock(&vm->stats_lock);
+	spin_unlock(&vm->status_lock);
 }
 
 /**
@@ -373,11 +344,11 @@ void amdgpu_vm_bo_update_shared(struct amdgpu_bo *bo)
  *        be bo->tbo.resource
  * @sign: if we should add (+1) or subtract (-1) from the stat
  *
- * Caller need to have the vm stats_lock held. Useful for when multiple update
+ * Caller need to have the vm status_lock held. Useful for when multiple update
  * need to happen at the same time.
  */
 static void amdgpu_vm_update_stats_locked(struct amdgpu_vm_bo_base *base,
-					  struct ttm_resource *res, int sign)
+			    struct ttm_resource *res, int sign)
 {
 	struct amdgpu_vm *vm = base->vm;
 	struct amdgpu_bo *bo = base->bo;
@@ -401,8 +372,7 @@ static void amdgpu_vm_update_stats_locked(struct amdgpu_vm_bo_base *base,
 		 */
 		if (bo->flags & AMDGPU_GEM_CREATE_DISCARDABLE)
 			vm->stats[res_memtype].drm.purgeable += size;
-		if (!(bo->preferred_domains &
-		      amdgpu_mem_type_to_domain(res_memtype)))
+		if (!(bo->preferred_domains & amdgpu_mem_type_to_domain(res_memtype)))
 			vm->stats[bo_memtype].evicted += size;
 	}
 }
@@ -421,9 +391,9 @@ void amdgpu_vm_update_stats(struct amdgpu_vm_bo_base *base,
 {
 	struct amdgpu_vm *vm = base->vm;
 
-	spin_lock(&vm->stats_lock);
+	spin_lock(&vm->status_lock);
 	amdgpu_vm_update_stats_locked(base, res, sign);
-	spin_unlock(&vm->stats_lock);
+	spin_unlock(&vm->status_lock);
 }
 
 /**
@@ -449,10 +419,10 @@ void amdgpu_vm_bo_base_init(struct amdgpu_vm_bo_base *base,
 	base->next = bo->vm_bo;
 	bo->vm_bo = base;
 
-	spin_lock(&vm->stats_lock);
+	spin_lock(&vm->status_lock);
 	base->shared = drm_gem_object_is_shared_for_memory_stats(&bo->tbo.base);
 	amdgpu_vm_update_stats_locked(base, bo->tbo.resource, +1);
-	spin_unlock(&vm->stats_lock);
+	spin_unlock(&vm->status_lock);
 
 	if (!amdgpu_vm_is_bo_always_valid(vm, bo))
 		return;
@@ -511,10 +481,10 @@ int amdgpu_vm_lock_done_list(struct amdgpu_vm *vm, struct drm_exec *exec,
 	int ret;
 
 	/* We can only trust prev->next while holding the lock */
-	spin_lock(&vm->invalidated_lock);
+	spin_lock(&vm->status_lock);
 	while (!list_is_head(prev->next, &vm->done)) {
 		bo_va = list_entry(prev->next, typeof(*bo_va), base.vm_status);
-		spin_unlock(&vm->invalidated_lock);
+		spin_unlock(&vm->status_lock);
 
 		bo = bo_va->base.bo;
 		if (bo) {
@@ -522,10 +492,10 @@ int amdgpu_vm_lock_done_list(struct amdgpu_vm *vm, struct drm_exec *exec,
 			if (unlikely(ret))
 				return ret;
 		}
-		spin_lock(&vm->invalidated_lock);
+		spin_lock(&vm->status_lock);
 		prev = prev->next;
 	}
-	spin_unlock(&vm->invalidated_lock);
+	spin_unlock(&vm->status_lock);
 
 	return 0;
 }
@@ -621,7 +591,7 @@ int amdgpu_vm_validate(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 		       void *param)
 {
 	uint64_t new_vm_generation = amdgpu_vm_generation(adev, vm);
-	struct amdgpu_vm_bo_base *bo_base, *tmp;
+	struct amdgpu_vm_bo_base *bo_base;
 	struct amdgpu_bo *bo;
 	int r;
 
@@ -634,7 +604,13 @@ int amdgpu_vm_validate(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 			return r;
 	}
 
-	list_for_each_entry_safe(bo_base, tmp, &vm->evicted, vm_status) {
+	spin_lock(&vm->status_lock);
+	while (!list_empty(&vm->evicted)) {
+		bo_base = list_first_entry(&vm->evicted,
+					   struct amdgpu_vm_bo_base,
+					   vm_status);
+		spin_unlock(&vm->status_lock);
+
 		bo = bo_base->bo;
 
 		r = validate(param, bo);
@@ -647,21 +623,26 @@ int amdgpu_vm_validate(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 			vm->update_funcs->map_table(to_amdgpu_bo_vm(bo));
 			amdgpu_vm_bo_relocated(bo_base);
 		}
+		spin_lock(&vm->status_lock);
 	}
+	while (ticket && !list_empty(&vm->evicted_user)) {
+		bo_base = list_first_entry(&vm->evicted_user,
+					   struct amdgpu_vm_bo_base,
+					   vm_status);
+		spin_unlock(&vm->status_lock);
 
-	if (ticket) {
-		list_for_each_entry_safe(bo_base, tmp, &vm->evicted_user,
-					 vm_status) {
-			bo = bo_base->bo;
-			dma_resv_assert_held(bo->tbo.base.resv);
+		bo = bo_base->bo;
+		dma_resv_assert_held(bo->tbo.base.resv);
 
-			r = validate(param, bo);
-			if (r)
-				return r;
+		r = validate(param, bo);
+		if (r)
+			return r;
 
-			amdgpu_vm_bo_invalidated(bo_base);
-		}
+		amdgpu_vm_bo_invalidated(bo_base);
+
+		spin_lock(&vm->status_lock);
 	}
+	spin_unlock(&vm->status_lock);
 
 	amdgpu_vm_eviction_lock(vm);
 	vm->evicting = false;
@@ -690,7 +671,9 @@ bool amdgpu_vm_ready(struct amdgpu_vm *vm)
 	ret = !vm->evicting;
 	amdgpu_vm_eviction_unlock(vm);
 
+	spin_lock(&vm->status_lock);
 	ret &= list_empty(&vm->evicted);
+	spin_unlock(&vm->status_lock);
 
 	spin_lock(&vm->immediate.lock);
 	ret &= !vm->immediate.stopped;
@@ -981,13 +964,18 @@ int amdgpu_vm_update_pdes(struct amdgpu_device *adev,
 			  struct amdgpu_vm *vm, bool immediate)
 {
 	struct amdgpu_vm_update_params params;
-	struct amdgpu_vm_bo_base *entry, *tmp;
+	struct amdgpu_vm_bo_base *entry;
 	bool flush_tlb_needed = false;
+	LIST_HEAD(relocated);
 	int r, idx;
 
 	amdgpu_vm_assert_locked(vm);
 
-	if (list_empty(&vm->relocated))
+	spin_lock(&vm->status_lock);
+	list_splice_init(&vm->relocated, &relocated);
+	spin_unlock(&vm->status_lock);
+
+	if (list_empty(&relocated))
 		return 0;
 
 	if (!drm_dev_enter(adev_to_drm(adev), &idx))
@@ -1003,7 +991,7 @@ int amdgpu_vm_update_pdes(struct amdgpu_device *adev,
 	if (r)
 		goto error;
 
-	list_for_each_entry(entry, &vm->relocated, vm_status) {
+	list_for_each_entry(entry, &relocated, vm_status) {
 		/* vm_flush_needed after updating moved PDEs */
 		flush_tlb_needed |= entry->moved;
 
@@ -1019,7 +1007,9 @@ int amdgpu_vm_update_pdes(struct amdgpu_device *adev,
 	if (flush_tlb_needed)
 		atomic64_inc(&vm->tlb_seq);
 
-	list_for_each_entry_safe(entry, tmp, &vm->relocated, vm_status) {
+	while (!list_empty(&relocated)) {
+		entry = list_first_entry(&relocated, struct amdgpu_vm_bo_base,
+					 vm_status);
 		amdgpu_vm_bo_idle(entry);
 	}
 
@@ -1246,9 +1236,9 @@ error_free:
 void amdgpu_vm_get_memory(struct amdgpu_vm *vm,
 			  struct amdgpu_mem_stats stats[__AMDGPU_PL_NUM])
 {
-	spin_lock(&vm->stats_lock);
+	spin_lock(&vm->status_lock);
 	memcpy(stats, vm->stats, sizeof(*stats) * __AMDGPU_PL_NUM);
-	spin_unlock(&vm->stats_lock);
+	spin_unlock(&vm->status_lock);
 }
 
 /**
@@ -1615,24 +1605,29 @@ int amdgpu_vm_handle_moved(struct amdgpu_device *adev,
 			   struct amdgpu_vm *vm,
 			   struct ww_acquire_ctx *ticket)
 {
-	struct amdgpu_bo_va *bo_va, *tmp;
+	struct amdgpu_bo_va *bo_va;
 	struct dma_resv *resv;
 	bool clear, unlock;
 	int r;
 
-	list_for_each_entry_safe(bo_va, tmp, &vm->moved, base.vm_status) {
+	spin_lock(&vm->status_lock);
+	while (!list_empty(&vm->moved)) {
+		bo_va = list_first_entry(&vm->moved, struct amdgpu_bo_va,
+					 base.vm_status);
+		spin_unlock(&vm->status_lock);
+
 		/* Per VM BOs never need to bo cleared in the page tables */
 		r = amdgpu_vm_bo_update(adev, bo_va, false);
 		if (r)
 			return r;
+		spin_lock(&vm->status_lock);
 	}
 
-	spin_lock(&vm->invalidated_lock);
 	while (!list_empty(&vm->invalidated)) {
 		bo_va = list_first_entry(&vm->invalidated, struct amdgpu_bo_va,
 					 base.vm_status);
 		resv = bo_va->base.bo->tbo.base.resv;
-		spin_unlock(&vm->invalidated_lock);
+		spin_unlock(&vm->status_lock);
 
 		/* Try to reserve the BO to avoid clearing its ptes */
 		if (!adev->debug_vm && dma_resv_trylock(resv)) {
@@ -1664,9 +1659,9 @@ int amdgpu_vm_handle_moved(struct amdgpu_device *adev,
 		     bo_va->base.bo->tbo.resource->mem_type == TTM_PL_SYSTEM))
 			amdgpu_vm_bo_evicted_user(&bo_va->base);
 
-		spin_lock(&vm->invalidated_lock);
+		spin_lock(&vm->status_lock);
 	}
-	spin_unlock(&vm->invalidated_lock);
+	spin_unlock(&vm->status_lock);
 
 	return 0;
 }
@@ -2195,9 +2190,9 @@ void amdgpu_vm_bo_del(struct amdgpu_device *adev,
 		}
 	}
 
-	spin_lock(&vm->invalidated_lock);
+	spin_lock(&vm->status_lock);
 	list_del(&bo_va->base.vm_status);
-	spin_unlock(&vm->invalidated_lock);
+	spin_unlock(&vm->status_lock);
 
 	list_for_each_entry_safe(mapping, next, &bo_va->valids, list) {
 		list_del(&mapping->list);
@@ -2305,10 +2300,10 @@ void amdgpu_vm_bo_move(struct amdgpu_bo *bo, struct ttm_resource *new_mem,
 	for (bo_base = bo->vm_bo; bo_base; bo_base = bo_base->next) {
 		struct amdgpu_vm *vm = bo_base->vm;
 
-		spin_lock(&vm->stats_lock);
+		spin_lock(&vm->status_lock);
 		amdgpu_vm_update_stats_locked(bo_base, bo->tbo.resource, -1);
 		amdgpu_vm_update_stats_locked(bo_base, new_mem, +1);
-		spin_unlock(&vm->stats_lock);
+		spin_unlock(&vm->status_lock);
 	}
 
 	amdgpu_vm_bo_invalidate(bo, evicted);
@@ -2554,6 +2549,7 @@ void amdgpu_vm_set_task_info(struct amdgpu_vm *vm)
  * @adev: amdgpu_device pointer
  * @vm: requested vm
  * @xcp_id: GPU partition selection id
+ * @pasid: the pasid the VM is using on this GPU
  *
  * Init @vm fields.
  *
@@ -2561,7 +2557,7 @@ void amdgpu_vm_set_task_info(struct amdgpu_vm *vm)
  * 0 for success, error for failure.
  */
 int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm,
-		   int32_t xcp_id)
+		   int32_t xcp_id, uint32_t pasid)
 {
 	struct amdgpu_bo *root_bo;
 	struct amdgpu_bo_vm *root;
@@ -2575,12 +2571,11 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 	INIT_LIST_HEAD(&vm->relocated);
 	INIT_LIST_HEAD(&vm->moved);
 	INIT_LIST_HEAD(&vm->idle);
-	spin_lock_init(&vm->invalidated_lock);
 	INIT_LIST_HEAD(&vm->invalidated);
+	spin_lock_init(&vm->status_lock);
 	INIT_LIST_HEAD(&vm->freed);
 	INIT_LIST_HEAD(&vm->done);
 	INIT_KFIFO(vm->faults);
-	spin_lock_init(&vm->stats_lock);
 
 	r = amdgpu_vm_init_entities(adev, vm);
 	if (r)
@@ -2638,12 +2633,26 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 	if (r)
 		dev_dbg(adev->dev, "Failed to create task info for VM\n");
 
+	/* Store new PASID in XArray (if non-zero) */
+	if (pasid != 0) {
+		r = xa_err(xa_store_irq(&adev->vm_manager.pasids, pasid, vm, GFP_KERNEL));
+		if (r < 0)
+			goto error_free_root;
+
+		vm->pasid = pasid;
+	}
+
 	amdgpu_bo_unreserve(vm->root.bo);
 	amdgpu_bo_unref(&root_bo);
 
 	return 0;
 
 error_free_root:
+	/* If PASID was partially set, erase it from XArray before failing */
+	if (vm->pasid != 0) {
+		xa_erase_irq(&adev->vm_manager.pasids, vm->pasid);
+		vm->pasid = 0;
+	}
 	amdgpu_vm_pt_free_root(adev, vm);
 	amdgpu_bo_unreserve(vm->root.bo);
 	amdgpu_bo_unref(&root_bo);
@@ -2749,7 +2758,11 @@ void amdgpu_vm_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm)
 
 	root = amdgpu_bo_ref(vm->root.bo);
 	amdgpu_bo_reserve(root, true);
-	amdgpu_vm_set_pasid(adev, vm, 0);
+	/* Remove PASID mapping before destroying VM */
+	if (vm->pasid != 0) {
+		xa_erase_irq(&adev->vm_manager.pasids, vm->pasid);
+		vm->pasid = 0;
+	}
 	dma_fence_wait(vm->last_unlocked, false);
 	dma_fence_put(vm->last_unlocked);
 	dma_fence_wait(vm->last_tlb_flush, false);
@@ -2790,10 +2803,7 @@ void amdgpu_vm_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm)
 	dma_fence_put(vm->last_update);
 
 	for (i = 0; i < AMDGPU_MAX_VMHUBS; i++) {
-		if (vm->reserved_vmid[i]) {
-			amdgpu_vmid_free_reserved(adev, i);
-			vm->reserved_vmid[i] = false;
-		}
+		amdgpu_vmid_free_reserved(adev, vm, i);
 	}
 
 	ttm_lru_bulk_move_fini(&adev->mman.bdev, &vm->lru_bulk_move);
@@ -2889,6 +2899,7 @@ int amdgpu_vm_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
 	union drm_amdgpu_vm *args = data;
 	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct amdgpu_fpriv *fpriv = filp->driver_priv;
+	struct amdgpu_vm *vm = &fpriv->vm;
 
 	/* No valid flags defined yet */
 	if (args->in.flags)
@@ -2897,17 +2908,10 @@ int amdgpu_vm_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
 	switch (args->in.op) {
 	case AMDGPU_VM_OP_RESERVE_VMID:
 		/* We only have requirement to reserve vmid from gfxhub */
-		if (!fpriv->vm.reserved_vmid[AMDGPU_GFXHUB(0)]) {
-			amdgpu_vmid_alloc_reserved(adev, AMDGPU_GFXHUB(0));
-			fpriv->vm.reserved_vmid[AMDGPU_GFXHUB(0)] = true;
-		}
-
+		amdgpu_vmid_alloc_reserved(adev, vm, AMDGPU_GFXHUB(0));
 		break;
 	case AMDGPU_VM_OP_UNRESERVE_VMID:
-		if (fpriv->vm.reserved_vmid[AMDGPU_GFXHUB(0)]) {
-			amdgpu_vmid_free_reserved(adev, AMDGPU_GFXHUB(0));
-			fpriv->vm.reserved_vmid[AMDGPU_GFXHUB(0)] = false;
-		}
+		amdgpu_vmid_free_reserved(adev, vm, AMDGPU_GFXHUB(0));
 		break;
 	default:
 		return -EINVAL;
@@ -3047,6 +3051,7 @@ void amdgpu_debugfs_vm_bo_info(struct amdgpu_vm *vm, struct seq_file *m)
 
 	amdgpu_vm_assert_locked(vm);
 
+	spin_lock(&vm->status_lock);
 	seq_puts(m, "\tIdle BOs:\n");
 	list_for_each_entry_safe(bo_va, tmp, &vm->idle, base.vm_status) {
 		if (!bo_va->base.bo)
@@ -3084,13 +3089,11 @@ void amdgpu_debugfs_vm_bo_info(struct amdgpu_vm *vm, struct seq_file *m)
 	id = 0;
 
 	seq_puts(m, "\tInvalidated BOs:\n");
-	spin_lock(&vm->invalidated_lock);
 	list_for_each_entry_safe(bo_va, tmp, &vm->invalidated, base.vm_status) {
 		if (!bo_va->base.bo)
 			continue;
 		total_invalidated += amdgpu_bo_print_info(id++,	bo_va->base.bo, m);
 	}
-	spin_unlock(&vm->invalidated_lock);
 	total_invalidated_objs = id;
 	id = 0;
 
@@ -3100,6 +3103,7 @@ void amdgpu_debugfs_vm_bo_info(struct amdgpu_vm *vm, struct seq_file *m)
 			continue;
 		total_done += amdgpu_bo_print_info(id++, bo_va->base.bo, m);
 	}
+	spin_unlock(&vm->status_lock);
 	total_done_objs = id;
 
 	seq_printf(m, "\tTotal idle size:        %12lld\tobjs:\t%d\n", total_idle,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
index 988e970d9e96..cf0ec94e8a07 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
@@ -203,11 +203,11 @@ struct amdgpu_vm_bo_base {
 	/* protected by bo being reserved */
 	struct amdgpu_vm_bo_base	*next;
 
-	/* protected by vm reservation and invalidated_lock */
+	/* protected by vm status_lock */
 	struct list_head		vm_status;
 
 	/* if the bo is counted as shared in mem stats
-	 * protected by vm BO being reserved */
+	 * protected by vm status_lock */
 	bool				shared;
 
 	/* protected by the BO being reserved */
@@ -343,8 +343,10 @@ struct amdgpu_vm {
 	bool			evicting;
 	unsigned int		saved_flags;
 
-	/* Memory statistics for this vm, protected by stats_lock */
-	spinlock_t		stats_lock;
+	/* Lock to protect vm_bo add/del/move on all lists of vm */
+	spinlock_t		status_lock;
+
+	/* Memory statistics for this vm, protected by status_lock */
 	struct amdgpu_mem_stats stats[__AMDGPU_PL_NUM];
 
 	/*
@@ -352,8 +354,6 @@ struct amdgpu_vm {
 	 * PDs, PTs or per VM BOs. The state transits are:
 	 *
 	 * evicted -> relocated (PDs, PTs) or moved (per VM BOs) -> idle
-	 *
-	 * Lists are protected by the root PD dma_resv lock.
 	 */
 
 	/* Per-VM and PT BOs who needs a validation */
@@ -374,10 +374,7 @@ struct amdgpu_vm {
 	 * state transits are:
 	 *
 	 * evicted_user or invalidated -> done
-	 *
-	 * Lists are protected by the invalidated_lock.
 	 */
-	spinlock_t		invalidated_lock;
 
 	/* BOs for user mode queues that need a validation */
 	struct list_head	evicted_user;
@@ -415,7 +412,7 @@ struct amdgpu_vm {
 	struct dma_fence	*last_unlocked;
 
 	unsigned int		pasid;
-	bool			reserved_vmid[AMDGPU_MAX_VMHUBS];
+	struct amdgpu_vmid	*reserved_vmid[AMDGPU_MAX_VMHUBS];
 
 	/* Flag to indicate if VM tables are updated by CPU or GPU (SDMA) */
 	bool					use_cpu_for_update;
@@ -503,11 +500,8 @@ extern const struct amdgpu_vm_update_funcs amdgpu_vm_sdma_funcs;
 void amdgpu_vm_manager_init(struct amdgpu_device *adev);
 void amdgpu_vm_manager_fini(struct amdgpu_device *adev);
 
-int amdgpu_vm_set_pasid(struct amdgpu_device *adev, struct amdgpu_vm *vm,
-			u32 pasid);
-
 long amdgpu_vm_wait_idle(struct amdgpu_vm *vm, long timeout);
-int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm, int32_t xcp_id);
+int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm, int32_t xcp_id, uint32_t pasid);
 int amdgpu_vm_make_compute(struct amdgpu_device *adev, struct amdgpu_vm *vm);
 void amdgpu_vm_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm);
 int amdgpu_vm_lock_pd(struct amdgpu_vm *vm, struct drm_exec *exec,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c
index 7a4c12ff9b18..f794fb1cc06e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c
@@ -543,7 +543,9 @@ static void amdgpu_vm_pt_free(struct amdgpu_vm_bo_base *entry)
 	entry->bo->vm_bo = NULL;
 	ttm_bo_set_bulk_move(&entry->bo->tbo, NULL);
 
+	spin_lock(&entry->vm->status_lock);
 	list_del(&entry->vm_status);
+	spin_unlock(&entry->vm->status_lock);
 	amdgpu_bo_unref(&entry->bo);
 }
 
@@ -587,6 +589,7 @@ static void amdgpu_vm_pt_add_list(struct amdgpu_vm_update_params *params,
 	struct amdgpu_vm_pt_cursor seek;
 	struct amdgpu_vm_bo_base *entry;
 
+	spin_lock(&params->vm->status_lock);
 	for_each_amdgpu_vm_pt_dfs_safe(params->adev, params->vm, cursor, seek, entry) {
 		if (entry && entry->bo)
 			list_move(&entry->vm_status, &params->tlb_flush_waitlist);
@@ -594,6 +597,7 @@ static void amdgpu_vm_pt_add_list(struct amdgpu_vm_update_params *params,
 
 	/* enter start node now */
 	list_move(&cursor->entry->vm_status, &params->tlb_flush_waitlist);
+	spin_unlock(&params->vm->status_lock);
 }
 
 /**
diff --git a/drivers/gpu/drm/amd/amdgpu/atom.c b/drivers/gpu/drm/amd/amdgpu/atom.c
index be5d67c2c7a1..7a063e44d429 100644
--- a/drivers/gpu/drm/amd/amdgpu/atom.c
+++ b/drivers/gpu/drm/amd/amdgpu/atom.c
@@ -1502,7 +1502,7 @@ static void atom_get_vbios_build(struct atom_context *ctx)
 {
 	unsigned char *atom_rom_hdr;
 	unsigned char *str;
-	uint16_t base;
+	uint16_t base, len;
 
 	base = CU16(ATOM_ROM_TABLE_PTR);
 	atom_rom_hdr = CSTR(base);
@@ -1515,8 +1515,9 @@ static void atom_get_vbios_build(struct atom_context *ctx)
 	while (str < atom_rom_hdr && *str++)
 		;
 
-	if ((str + STRLEN_NORMAL) < atom_rom_hdr)
-		strscpy(ctx->build_num, str, STRLEN_NORMAL);
+	len = min(atom_rom_hdr - str, STRLEN_NORMAL);
+	if (len)
+		strscpy(ctx->build_num, str, len);
 }
 
 struct atom_context *amdgpu_atom_parse(struct card_info *card, void *bios)
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c
index 8ba66d4dfe86..77f9d5b9a556 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c
@@ -3560,6 +3560,7 @@ static int gfx_v9_4_3_reset_kcq(struct amdgpu_ring *ring,
 	struct amdgpu_device *adev = ring->adev;
 	struct amdgpu_kiq *kiq = &adev->gfx.kiq[ring->xcc_id];
 	struct amdgpu_ring *kiq_ring = &kiq->ring;
+	int reset_mode = AMDGPU_RESET_TYPE_PER_QUEUE;
 	unsigned long flags;
 	int r;
 
@@ -3597,6 +3598,7 @@ pipe_reset:
 		if (!(adev->gfx.compute_supported_reset & AMDGPU_RESET_TYPE_PER_PIPE))
 			return -EOPNOTSUPP;
 		r = gfx_v9_4_3_reset_hw_pipe(ring);
+		reset_mode = AMDGPU_RESET_TYPE_PER_PIPE;
 		dev_info(adev->dev, "ring: %s pipe reset :%s\n", ring->name,
 				r ? "failed" : "successfully");
 		if (r)
@@ -3619,10 +3621,20 @@ pipe_reset:
 	r = amdgpu_ring_test_ring(kiq_ring);
 	spin_unlock_irqrestore(&kiq->ring_lock, flags);
 	if (r) {
+		if (reset_mode == AMDGPU_RESET_TYPE_PER_QUEUE)
+			goto pipe_reset;
+
 		dev_err(adev->dev, "fail to remap queue\n");
 		return r;
 	}
 
+	if (reset_mode == AMDGPU_RESET_TYPE_PER_QUEUE) {
+		r = amdgpu_ring_test_ring(ring);
+		if (r)
+			goto pipe_reset;
+	}
+
+
 	return amdgpu_ring_reset_helper_end(ring, timedout_fence);
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v12_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v12_0.c
index 404cc8c2ff2c..f4a19357ccbc 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v12_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v12_0.c
@@ -337,7 +337,7 @@ static void gmc_v12_0_flush_gpu_tlb_pasid(struct amdgpu_device *adev,
 	int vmid, i;
 
 	if (adev->enable_uni_mes && adev->mes.ring[AMDGPU_MES_SCHED_PIPE].sched.ready &&
-	    (adev->mes.sched_version & AMDGPU_MES_VERSION_MASK) >= 0x83) {
+	    (adev->mes.sched_version & AMDGPU_MES_VERSION_MASK) >= 0x84) {
 		struct mes_inv_tlbs_pasid_input input = {0};
 		input.pasid = pasid;
 		input.flush_type = flush_type;
diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
index 3b91ea601add..e82188431f79 100644
--- a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
@@ -713,6 +713,12 @@ static int mes_v11_0_set_hw_resources(struct amdgpu_mes *mes)
 	mes_set_hw_res_pkt.enable_reg_active_poll = 1;
 	mes_set_hw_res_pkt.enable_level_process_quantum_check = 1;
 	mes_set_hw_res_pkt.oversubscription_timer = 50;
+	if ((mes->adev->mes.sched_version & AMDGPU_MES_VERSION_MASK) >= 0x7f)
+		mes_set_hw_res_pkt.enable_lr_compute_wa = 1;
+	else
+		dev_info_once(mes->adev->dev,
+			      "MES FW version must be >= 0x7f to enable LR compute workaround.\n");
+
 	if (amdgpu_mes_log_enable) {
 		mes_set_hw_res_pkt.enable_mes_event_int_logging = 1;
 		mes_set_hw_res_pkt.event_intr_history_gpu_mc_ptr =
diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c
index 998893dff08e..aff06f06aeee 100644
--- a/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c
@@ -769,6 +769,11 @@ static int mes_v12_0_set_hw_resources(struct amdgpu_mes *mes, int pipe)
 	mes_set_hw_res_pkt.use_different_vmid_compute = 1;
 	mes_set_hw_res_pkt.enable_reg_active_poll = 1;
 	mes_set_hw_res_pkt.enable_level_process_quantum_check = 1;
+	if ((mes->adev->mes.sched_version & AMDGPU_MES_VERSION_MASK) >= 0x82)
+		mes_set_hw_res_pkt.enable_lr_compute_wa = 1;
+	else
+		dev_info_once(adev->dev,
+			      "MES FW version must be >= 0x82 to enable LR compute workaround.\n");
 
 	/*
 	 * Keep oversubscribe timer for sdma . When we have unmapped doorbell
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.c b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.c
index 9c281ba6bced..714350cabf2f 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.c
@@ -113,6 +113,25 @@ static int vcn_v5_0_1_early_init(struct amdgpu_ip_block *ip_block)
 	return 0;
 }
 
+static int vcn_v5_0_1_late_init(struct amdgpu_ip_block *ip_block)
+{
+	struct amdgpu_device *adev = ip_block->adev;
+
+	adev->vcn.supported_reset =
+		amdgpu_get_soft_full_reset_mask(&adev->vcn.inst[0].ring_enc[0]);
+
+	switch (amdgpu_ip_version(adev, MP0_HWIP, 0)) {
+	case IP_VERSION(13, 0, 12):
+		if ((adev->psp.sos.fw_version >= 0x00450025) && amdgpu_dpm_reset_vcn_is_supported(adev))
+			adev->vcn.supported_reset |= AMDGPU_RESET_TYPE_PER_QUEUE;
+		break;
+	default:
+		break;
+	}
+
+	return 0;
+}
+
 static void vcn_v5_0_1_fw_shared_init(struct amdgpu_device *adev, int inst_idx)
 {
 	struct amdgpu_vcn5_fw_shared *fw_shared;
@@ -187,10 +206,6 @@ static int vcn_v5_0_1_sw_init(struct amdgpu_ip_block *ip_block)
 		vcn_v5_0_1_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)
@@ -253,6 +268,23 @@ static int vcn_v5_0_1_sw_fini(struct amdgpu_ip_block *ip_block)
 	return 0;
 }
 
+static int vcn_v5_0_1_hw_init_inst(struct amdgpu_device *adev, int i)
+{
+	struct amdgpu_ring *ring;
+	int vcn_inst;
+
+	vcn_inst = GET_INST(VCN, i);
+	ring = &adev->vcn.inst[i].ring_enc[0];
+
+	if (ring->use_doorbell)
+		adev->nbio.funcs->vcn_doorbell_range(adev, ring->use_doorbell,
+			((adev->doorbell_index.vcn.vcn_ring0_1 << 1) +
+			11 * vcn_inst),
+			adev->vcn.inst[i].aid_id);
+
+	return 0;
+}
+
 /**
  * vcn_v5_0_1_hw_init - start and test VCN block
  *
@@ -264,7 +296,7 @@ static int vcn_v5_0_1_hw_init(struct amdgpu_ip_block *ip_block)
 {
 	struct amdgpu_device *adev = ip_block->adev;
 	struct amdgpu_ring *ring;
-	int i, r, vcn_inst;
+	int i, r;
 
 	if (amdgpu_sriov_vf(adev)) {
 		r = vcn_v5_0_1_start_sriov(adev);
@@ -282,14 +314,8 @@ static int vcn_v5_0_1_hw_init(struct amdgpu_ip_block *ip_block)
 		if (RREG32_SOC15(VCN, GET_INST(VCN, 0), regVCN_RRMT_CNTL) & 0x100)
 			adev->vcn.caps |= AMDGPU_VCN_CAPS(RRMT_ENABLED);
 		for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
-			vcn_inst = GET_INST(VCN, i);
 			ring = &adev->vcn.inst[i].ring_enc[0];
-
-			if (ring->use_doorbell)
-				adev->nbio.funcs->vcn_doorbell_range(adev, ring->use_doorbell,
-					((adev->doorbell_index.vcn.vcn_ring0_1 << 1) +
-					11 * vcn_inst),
-					adev->vcn.inst[i].aid_id);
+			vcn_v5_0_1_hw_init_inst(adev, i);
 
 			/* Re-init fw_shared, if required */
 			vcn_v5_0_1_fw_shared_init(adev, i);
@@ -1273,6 +1299,31 @@ static void vcn_v5_0_1_unified_ring_set_wptr(struct amdgpu_ring *ring)
 	}
 }
 
+static int vcn_v5_0_1_ring_reset(struct amdgpu_ring *ring,
+				 unsigned int vmid,
+				 struct amdgpu_fence *timedout_fence)
+{
+	int r = 0;
+	int vcn_inst;
+	struct amdgpu_device *adev = ring->adev;
+	struct amdgpu_vcn_inst *vinst = &adev->vcn.inst[ring->me];
+
+	amdgpu_ring_reset_helper_begin(ring, timedout_fence);
+
+	vcn_inst = GET_INST(VCN, ring->me);
+	r = amdgpu_dpm_reset_vcn(adev, 1 << vcn_inst);
+
+	if (r) {
+		DRM_DEV_ERROR(adev->dev, "VCN reset fail : %d\n", r);
+		return r;
+	}
+
+	vcn_v5_0_1_hw_init_inst(adev, ring->me);
+	vcn_v5_0_1_start_dpg_mode(vinst, vinst->indirect_sram);
+
+	return amdgpu_ring_reset_helper_end(ring, timedout_fence);
+}
+
 static const struct amdgpu_ring_funcs vcn_v5_0_1_unified_ring_vm_funcs = {
 	.type = AMDGPU_RING_TYPE_VCN_ENC,
 	.align_mask = 0x3f,
@@ -1301,6 +1352,7 @@ static const struct amdgpu_ring_funcs vcn_v5_0_1_unified_ring_vm_funcs = {
 	.emit_wreg = vcn_v4_0_3_enc_ring_emit_wreg,
 	.emit_reg_wait = vcn_v4_0_3_enc_ring_emit_reg_wait,
 	.emit_reg_write_reg_wait = amdgpu_ring_emit_reg_write_reg_wait_helper,
+	.reset = vcn_v5_0_1_ring_reset,
 };
 
 /**
@@ -1504,7 +1556,7 @@ static void vcn_v5_0_1_set_irq_funcs(struct amdgpu_device *adev)
 static const struct amd_ip_funcs vcn_v5_0_1_ip_funcs = {
 	.name = "vcn_v5_0_1",
 	.early_init = vcn_v5_0_1_early_init,
-	.late_init = NULL,
+	.late_init = vcn_v5_0_1_late_init,
 	.sw_init = vcn_v5_0_1_sw_init,
 	.sw_fini = vcn_v5_0_1_sw_fini,
 	.hw_init = vcn_v5_0_1_hw_init,
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
index 349c351e242b..e9cfb80bd436 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
@@ -495,6 +495,7 @@ struct kfd_dev *kgd2kfd_probe(struct amdgpu_device *adev, bool vf)
 	mutex_init(&kfd->doorbell_mutex);
 
 	ida_init(&kfd->doorbell_ida);
+	atomic_set(&kfd->kfd_processes_count, 0);
 
 	return kfd;
 }
@@ -1133,7 +1134,15 @@ void kgd2kfd_interrupt(struct kfd_dev *kfd, const void *ih_ring_entry)
 	}
 
 	for (i = 0; i < kfd->num_nodes; i++) {
-		node = kfd->nodes[i];
+		/* Race if another thread in b/w
+		 * kfd_cleanup_nodes and kfree(kfd),
+		 * when kfd->nodes[i] = NULL
+		 */
+		if (kfd->nodes[i])
+			node = kfd->nodes[i];
+		else
+			return;
+
 		spin_lock_irqsave(&node->interrupt_lock, flags);
 
 		if (node->interrupts_active
@@ -1485,6 +1494,15 @@ int kgd2kfd_check_and_lock_kfd(struct kfd_dev *kfd)
 
 	mutex_lock(&kfd_processes_mutex);
 
+	/* kfd_processes_count is per kfd_dev, return -EBUSY without
+	 * further check
+	 */
+	if (!!atomic_read(&kfd->kfd_processes_count)) {
+		pr_debug("process_wq_release not finished\n");
+		r = -EBUSY;
+		goto out;
+	}
+
 	if (hash_empty(kfd_processes_table) && !kfd_is_locked(kfd))
 		goto out;
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
index d01ef5ac0766..70ef051511bb 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
@@ -382,6 +382,8 @@ struct kfd_dev {
 
 	/* for dynamic partitioning */
 	int kfd_dev_lock;
+
+	atomic_t kfd_processes_count;
 };
 
 enum kfd_mempool {
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
index 5be28c6c4f6a..ddfe30c13e9d 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
@@ -1088,6 +1088,8 @@ static void kfd_process_destroy_pdds(struct kfd_process *p)
 			pdd->runtime_inuse = false;
 		}
 
+		atomic_dec(&pdd->dev->kfd->kfd_processes_count);
+
 		kfree(pdd);
 		p->pdds[i] = NULL;
 	}
@@ -1649,6 +1651,8 @@ struct kfd_process_device *kfd_create_process_device_data(struct kfd_node *dev,
 	/* Init idr used for memory handle translation */
 	idr_init(&pdd->alloc_idr);
 
+	atomic_inc(&dev->kfd->kfd_processes_count);
+
 	return pdd;
 }
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
index 68ba239b2e5d..9d72411c3379 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
@@ -1738,7 +1738,7 @@ static int svm_range_validate_and_map(struct mm_struct *mm,
 
 			WRITE_ONCE(p->svms.faulting_task, current);
 			r = amdgpu_hmm_range_get_pages(&prange->notifier, addr, npages,
-						       readonly, owner, NULL,
+						       readonly, owner,
 						       &hmm_range);
 			WRITE_ONCE(p->svms.faulting_task, NULL);
 			if (r)
@@ -3045,6 +3045,8 @@ retry_write_locked:
 	if (svms->checkpoint_ts[gpuidx] != 0) {
 		if (amdgpu_ih_ts_after_or_equal(ts,  svms->checkpoint_ts[gpuidx])) {
 			pr_debug("draining retry fault, drop fault 0x%llx\n", addr);
+			if (write_locked)
+				mmap_write_downgrade(mm);
 			r = -EAGAIN;
 			goto out_unlock_svms;
 		} else {
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index 7012b2c692b3..0d03e324d5b9 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -233,6 +233,7 @@ static int amdgpu_dm_encoder_init(struct drm_device *dev,
 
 static int amdgpu_dm_connector_get_modes(struct drm_connector *connector);
 
+static int amdgpu_dm_atomic_setup_commit(struct drm_atomic_state *state);
 static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state);
 
 static int amdgpu_dm_atomic_check(struct drm_device *dev,
@@ -417,8 +418,7 @@ static inline bool update_planes_and_stream_adapter(struct dc *dc,
 	/*
 	 * Previous frame finished and HW is ready for optimization.
 	 */
-	if (update_type == UPDATE_TYPE_FAST)
-		dc_post_update_surfaces_to_stream(dc);
+	dc_post_update_surfaces_to_stream(dc);
 
 	return dc_update_planes_and_stream(dc,
 					   array_of_surface_update,
@@ -2000,6 +2000,10 @@ static int amdgpu_dm_init(struct amdgpu_device *adev)
 
 	init_data.flags.disable_ips_in_vpb = 0;
 
+	/* DCN35 and above supports dynamic DTBCLK switch */
+	if (amdgpu_ip_version(adev, DCE_HWIP, 0) >= IP_VERSION(3, 5, 0))
+		init_data.flags.allow_0_dtb_clk = true;
+
 	/* Enable DWB for tested platforms only */
 	if (amdgpu_ip_version(adev, DCE_HWIP, 0) >= IP_VERSION(3, 0, 0))
 		init_data.num_virtual_links = 1;
@@ -3637,7 +3641,7 @@ static const struct drm_mode_config_funcs amdgpu_dm_mode_funcs = {
 
 static struct drm_mode_config_helper_funcs amdgpu_dm_mode_config_helperfuncs = {
 	.atomic_commit_tail = amdgpu_dm_atomic_commit_tail,
-	.atomic_commit_setup = drm_dp_mst_atomic_setup_commit,
+	.atomic_commit_setup = amdgpu_dm_atomic_setup_commit,
 };
 
 static void update_connector_ext_caps(struct amdgpu_dm_connector *aconnector)
@@ -4829,6 +4833,16 @@ static void convert_custom_brightness(const struct amdgpu_dm_backlight_caps *cap
 	if (!caps->data_points)
 		return;
 
+	/*
+	 * Handle the case where brightness is below the first data point
+	 * Interpolate between (0,0) and (first_signal, first_lum)
+	 */
+	if (brightness < caps->luminance_data[0].input_signal) {
+		lum = DIV_ROUND_CLOSEST(caps->luminance_data[0].luminance * brightness,
+					caps->luminance_data[0].input_signal);
+		goto scale;
+	}
+
 	left = 0;
 	right = caps->data_points - 1;
 	while (left <= right) {
@@ -8261,6 +8275,10 @@ static void amdgpu_dm_connector_add_common_modes(struct drm_encoder *encoder,
 		{"1920x1200", 1920, 1200}
 	};
 
+	if ((connector->connector_type != DRM_MODE_CONNECTOR_eDP) &&
+	    (connector->connector_type != DRM_MODE_CONNECTOR_LVDS))
+		return;
+
 	n = ARRAY_SIZE(common_modes);
 
 	for (i = 0; i < n; i++) {
@@ -10353,6 +10371,39 @@ static void amdgpu_dm_update_hdcp(struct drm_atomic_state *state)
 	}
 }
 
+static int amdgpu_dm_atomic_setup_commit(struct drm_atomic_state *state)
+{
+	struct drm_crtc *crtc;
+	struct drm_crtc_state *old_crtc_state, *new_crtc_state;
+	struct dm_crtc_state *dm_old_crtc_state, *dm_new_crtc_state;
+	int i, ret;
+
+	ret = drm_dp_mst_atomic_setup_commit(state);
+	if (ret)
+		return ret;
+
+	for_each_oldnew_crtc_in_state(state, crtc, old_crtc_state, new_crtc_state, i) {
+		dm_old_crtc_state = to_dm_crtc_state(old_crtc_state);
+		dm_new_crtc_state = to_dm_crtc_state(new_crtc_state);
+		/*
+		 * Color management settings. We also update color properties
+		 * when a modeset is needed, to ensure it gets reprogrammed.
+		 */
+		if (dm_new_crtc_state->base.active && dm_new_crtc_state->stream &&
+		    (dm_new_crtc_state->base.color_mgmt_changed ||
+		     dm_old_crtc_state->regamma_tf != dm_new_crtc_state->regamma_tf ||
+		     drm_atomic_crtc_needs_modeset(new_crtc_state))) {
+			ret = amdgpu_dm_update_crtc_color_mgmt(dm_new_crtc_state);
+			if (ret) {
+				drm_dbg_atomic(state->dev, "Failed to update color state\n");
+				return ret;
+			}
+		}
+	}
+
+	return 0;
+}
+
 /**
  * amdgpu_dm_atomic_commit_tail() - AMDgpu DM's commit tail implementation.
  * @state: The atomic state to commit
@@ -11167,7 +11218,7 @@ skip_modeset:
 	if (dm_new_crtc_state->base.color_mgmt_changed ||
 	    dm_old_crtc_state->regamma_tf != dm_new_crtc_state->regamma_tf ||
 	    drm_atomic_crtc_needs_modeset(new_crtc_state)) {
-		ret = amdgpu_dm_update_crtc_color_mgmt(dm_new_crtc_state);
+		ret = amdgpu_dm_check_crtc_color_mgmt(dm_new_crtc_state, true);
 		if (ret)
 			goto fail;
 	}
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
index c41c0ee4687f..009f206226f0 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
@@ -1054,6 +1054,8 @@ void amdgpu_dm_init_color_mod(void);
 int amdgpu_dm_create_color_properties(struct amdgpu_device *adev);
 int amdgpu_dm_verify_lut_sizes(const struct drm_crtc_state *crtc_state);
 int amdgpu_dm_update_crtc_color_mgmt(struct dm_crtc_state *crtc);
+int amdgpu_dm_check_crtc_color_mgmt(struct dm_crtc_state *crtc,
+				    bool check_only);
 int amdgpu_dm_update_plane_color_mgmt(struct dm_crtc_state *crtc,
 				      struct drm_plane_state *plane_state,
 				      struct dc_plane_state *dc_plane_state);
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c
index c7387af725d6..a4ac6d442278 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c
@@ -566,12 +566,11 @@ static int __set_output_tf(struct dc_transfer_func *func,
 	return res ? 0 : -ENOMEM;
 }
 
-static int amdgpu_dm_set_atomic_regamma(struct dc_stream_state *stream,
+static int amdgpu_dm_set_atomic_regamma(struct dc_transfer_func *out_tf,
 					const struct drm_color_lut *regamma_lut,
 					uint32_t regamma_size, bool has_rom,
 					enum dc_transfer_func_predefined tf)
 {
-	struct dc_transfer_func *out_tf = &stream->out_transfer_func;
 	int ret = 0;
 
 	if (regamma_size || tf != TRANSFER_FUNCTION_LINEAR) {
@@ -821,7 +820,7 @@ int amdgpu_dm_verify_lut3d_size(struct amdgpu_device *adev,
 	struct dm_plane_state *dm_plane_state = to_dm_plane_state(plane_state);
 	const struct drm_color_lut *shaper = NULL, *lut3d = NULL;
 	uint32_t exp_size, size, dim_size = MAX_COLOR_3DLUT_SIZE;
-	bool has_3dlut = adev->dm.dc->caps.color.dpp.hw_3d_lut;
+	bool has_3dlut = adev->dm.dc->caps.color.dpp.hw_3d_lut || adev->dm.dc->caps.color.mpc.preblend;
 
 	/* shaper LUT is only available if 3D LUT color caps */
 	exp_size = has_3dlut ? MAX_COLOR_LUT_ENTRIES : 0;
@@ -885,33 +884,33 @@ int amdgpu_dm_verify_lut_sizes(const struct drm_crtc_state *crtc_state)
 }
 
 /**
- * amdgpu_dm_update_crtc_color_mgmt: Maps DRM color management to DC stream.
+ * amdgpu_dm_check_crtc_color_mgmt: Check if DRM color props are programmable by DC.
  * @crtc: amdgpu_dm crtc state
+ * @check_only: only check color state without update dc stream
  *
- * With no plane level color management properties we're free to use any
- * of the HW blocks as long as the CRTC CTM always comes before the
- * CRTC RGM and after the CRTC DGM.
- *
- * - The CRTC RGM block will be placed in the RGM LUT block if it is non-linear.
- * - The CRTC DGM block will be placed in the DGM LUT block if it is non-linear.
- * - The CRTC CTM will be placed in the gamut remap block if it is non-linear.
+ * This function just verifies CRTC LUT sizes, if there is enough space for
+ * output transfer function and if its parameters can be calculated by AMD
+ * color module. It also adjusts some settings for programming CRTC degamma at
+ * plane stage, using plane DGM block.
  *
  * The RGM block is typically more fully featured and accurate across
  * all ASICs - DCE can't support a custom non-linear CRTC DGM.
  *
  * For supporting both plane level color management and CRTC level color
- * management at once we have to either restrict the usage of CRTC properties
- * or blend adjustments together.
+ * management at once we have to either restrict the usage of some CRTC
+ * properties or blend adjustments together.
  *
  * Returns:
- * 0 on success. Error code if setup fails.
+ * 0 on success. Error code if validation fails.
  */
-int amdgpu_dm_update_crtc_color_mgmt(struct dm_crtc_state *crtc)
+
+int amdgpu_dm_check_crtc_color_mgmt(struct dm_crtc_state *crtc,
+				    bool check_only)
 {
 	struct dc_stream_state *stream = crtc->stream;
 	struct amdgpu_device *adev = drm_to_adev(crtc->base.state->dev);
 	bool has_rom = adev->asic_type <= CHIP_RAVEN;
-	struct drm_color_ctm *ctm = NULL;
+	struct dc_transfer_func *out_tf;
 	const struct drm_color_lut *degamma_lut, *regamma_lut;
 	uint32_t degamma_size, regamma_size;
 	bool has_regamma, has_degamma;
@@ -940,6 +939,14 @@ int amdgpu_dm_update_crtc_color_mgmt(struct dm_crtc_state *crtc)
 	crtc->cm_has_degamma = false;
 	crtc->cm_is_degamma_srgb = false;
 
+	if (check_only) {
+		out_tf = kvzalloc(sizeof(*out_tf), GFP_KERNEL);
+		if (!out_tf)
+			return -ENOMEM;
+	} else {
+		out_tf = &stream->out_transfer_func;
+	}
+
 	/* Setup regamma and degamma. */
 	if (is_legacy) {
 		/*
@@ -954,8 +961,8 @@ int amdgpu_dm_update_crtc_color_mgmt(struct dm_crtc_state *crtc)
 		 * inverse color ramp in legacy userspace.
 		 */
 		crtc->cm_is_degamma_srgb = true;
-		stream->out_transfer_func.type = TF_TYPE_DISTRIBUTED_POINTS;
-		stream->out_transfer_func.tf = TRANSFER_FUNCTION_SRGB;
+		out_tf->type = TF_TYPE_DISTRIBUTED_POINTS;
+		out_tf->tf = TRANSFER_FUNCTION_SRGB;
 		/*
 		 * Note: although we pass has_rom as parameter here, we never
 		 * actually use ROM because the color module only takes the ROM
@@ -963,16 +970,12 @@ int amdgpu_dm_update_crtc_color_mgmt(struct dm_crtc_state *crtc)
 		 *
 		 * See more in mod_color_calculate_regamma_params()
 		 */
-		r = __set_legacy_tf(&stream->out_transfer_func, regamma_lut,
+		r = __set_legacy_tf(out_tf, regamma_lut,
 				    regamma_size, has_rom);
-		if (r)
-			return r;
 	} else {
 		regamma_size = has_regamma ? regamma_size : 0;
-		r = amdgpu_dm_set_atomic_regamma(stream, regamma_lut,
+		r = amdgpu_dm_set_atomic_regamma(out_tf, regamma_lut,
 						 regamma_size, has_rom, tf);
-		if (r)
-			return r;
 	}
 
 	/*
@@ -981,6 +984,43 @@ int amdgpu_dm_update_crtc_color_mgmt(struct dm_crtc_state *crtc)
 	 * have to place the CTM in the OCSC in that case.
 	 */
 	crtc->cm_has_degamma = has_degamma;
+	if (check_only)
+		kvfree(out_tf);
+
+	return r;
+}
+
+/**
+ * amdgpu_dm_update_crtc_color_mgmt: Maps DRM color management to DC stream.
+ * @crtc: amdgpu_dm crtc state
+ *
+ * With no plane level color management properties we're free to use any
+ * of the HW blocks as long as the CRTC CTM always comes before the
+ * CRTC RGM and after the CRTC DGM.
+ *
+ * - The CRTC RGM block will be placed in the RGM LUT block if it is non-linear.
+ * - The CRTC DGM block will be placed in the DGM LUT block if it is non-linear.
+ * - The CRTC CTM will be placed in the gamut remap block if it is non-linear.
+ *
+ * The RGM block is typically more fully featured and accurate across
+ * all ASICs - DCE can't support a custom non-linear CRTC DGM.
+ *
+ * For supporting both plane level color management and CRTC level color
+ * management at once we have to either restrict the usage of CRTC properties
+ * or blend adjustments together.
+ *
+ * Returns:
+ * 0 on success. Error code if setup fails.
+ */
+int amdgpu_dm_update_crtc_color_mgmt(struct dm_crtc_state *crtc)
+{
+	struct dc_stream_state *stream = crtc->stream;
+	struct drm_color_ctm *ctm = NULL;
+	int ret;
+
+	ret = amdgpu_dm_check_crtc_color_mgmt(crtc, false);
+	if (ret)
+		return ret;
 
 	/* Setup CRTC CTM. */
 	if (crtc->base.ctm) {
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c
index 466dccb355d7..1ec9d03ad747 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c
@@ -218,8 +218,10 @@ static void amdgpu_dm_idle_worker(struct work_struct *work)
 			break;
 		}
 
-		if (idle_work->enable)
+		if (idle_work->enable) {
+			dc_post_update_surfaces_to_stream(idle_work->dm->dc);
 			dc_allow_idle_optimizations(idle_work->dm->dc, true);
+		}
 		mutex_unlock(&idle_work->dm->dc_lock);
 	}
 	idle_work->dm->idle_workqueue->running = false;
@@ -273,8 +275,10 @@ static void amdgpu_dm_crtc_vblank_control_worker(struct work_struct *work)
 			vblank_work->acrtc->dm_irq_params.allow_sr_entry);
 	}
 
-	if (dm->active_vblank_irq_count == 0)
+	if (dm->active_vblank_irq_count == 0) {
+		dc_post_update_surfaces_to_stream(dm->dc);
 		dc_allow_idle_optimizations(dm->dc, true);
+	}
 
 	mutex_unlock(&dm->dc_lock);
 
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c
index 58e084f52526..19038f336155 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c
@@ -768,14 +768,18 @@ struct hdcp_workqueue *hdcp_create_workqueue(struct amdgpu_device *adev,
 		struct mod_hdcp_ddc_funcs *ddc_funcs = &config->ddc.funcs;
 
 		config->psp.handle = &adev->psp;
-		if (dc->ctx->dce_version == DCN_VERSION_3_1 ||
+		if (dc->ctx->dce_version == DCN_VERSION_3_1  ||
 		    dc->ctx->dce_version == DCN_VERSION_3_14 ||
 		    dc->ctx->dce_version == DCN_VERSION_3_15 ||
-		    dc->ctx->dce_version == DCN_VERSION_3_5 ||
+		    dc->ctx->dce_version == DCN_VERSION_3_16 ||
+		    dc->ctx->dce_version == DCN_VERSION_3_2  ||
+		    dc->ctx->dce_version == DCN_VERSION_3_21 ||
+		    dc->ctx->dce_version == DCN_VERSION_3_5  ||
 		    dc->ctx->dce_version == DCN_VERSION_3_51 ||
-		    dc->ctx->dce_version == DCN_VERSION_3_6 ||
-		    dc->ctx->dce_version == DCN_VERSION_3_16)
+		    dc->ctx->dce_version == DCN_VERSION_3_6  ||
+		    dc->ctx->dce_version == DCN_VERSION_4_01)
 			config->psp.caps.dtm_v3_supported = 1;
+
 		config->ddc.handle = dc_get_link_at_index(dc, i);
 
 		ddc_funcs->write_i2c = lp_write_i2c;
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c
index 08f629c64df3..e027798ece03 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c
@@ -1633,7 +1633,7 @@ dm_atomic_plane_attach_color_mgmt_properties(struct amdgpu_display_manager *dm,
 		drm_object_attach_property(&plane->base,
 					   dm->adev->mode_info.plane_ctm_property, 0);
 
-	if (dpp_color_caps.hw_3d_lut) {
+	if (dpp_color_caps.hw_3d_lut || dm->dc->caps.color.mpc.preblend) {
 		drm_object_attach_property(&plane->base,
 					   mode_info.plane_shaper_lut_property, 0);
 		drm_object_attach_property(&plane->base,
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_services.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_services.c
index 132de4071efd..8550d5e8b753 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_services.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_services.c
@@ -53,11 +53,11 @@ void dm_perf_trace_timestamp(const char *func_name, unsigned int line, struct dc
 				    func_name, line);
 }
 
-void dm_trace_smu_msg(uint32_t msg_id, uint32_t param_in, struct dc_context *ctx)
+void dm_trace_smu_enter(uint32_t msg_id, uint32_t param_in, unsigned int delay, struct dc_context *ctx)
 {
 }
 
-void dm_trace_smu_delay(uint32_t delay, struct dc_context *ctx)
+void dm_trace_smu_exit(bool success, uint32_t response, struct dc_context *ctx)
 {
 }
 
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dce100/dce_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dce100/dce_clk_mgr.c
index dbd6ef1b60a0..6131ede2db7a 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dce100/dce_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dce100/dce_clk_mgr.c
@@ -463,6 +463,9 @@ void dce_clk_mgr_construct(
 		clk_mgr->max_clks_state = DM_PP_CLOCKS_STATE_NOMINAL;
 	clk_mgr->cur_min_clks_state = DM_PP_CLOCKS_STATE_INVALID;
 
+	base->clks.max_supported_dispclk_khz =
+		clk_mgr->max_clks_by_state[DM_PP_CLOCKS_STATE_PERFORMANCE].display_clk_khz;
+
 	dce_clock_read_integrated_info(clk_mgr);
 	dce_clock_read_ss_info(clk_mgr);
 }
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dce60/dce60_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dce60/dce60_clk_mgr.c
index a39641a0ff09..69dd80d9f738 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dce60/dce60_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dce60/dce60_clk_mgr.c
@@ -147,6 +147,8 @@ void dce60_clk_mgr_construct(
 		struct dc_context *ctx,
 		struct clk_mgr_internal *clk_mgr)
 {
+	struct clk_mgr *base = &clk_mgr->base;
+
 	dce_clk_mgr_construct(ctx, clk_mgr);
 
 	memcpy(clk_mgr->max_clks_by_state,
@@ -157,5 +159,8 @@ void dce60_clk_mgr_construct(
 	clk_mgr->clk_mgr_shift = &disp_clk_shift;
 	clk_mgr->clk_mgr_mask = &disp_clk_mask;
 	clk_mgr->base.funcs = &dce60_funcs;
+
+	base->clks.max_supported_dispclk_khz =
+		clk_mgr->max_clks_by_state[DM_PP_CLOCKS_STATE_PERFORMANCE].display_clk_khz;
 }
 
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn30/dcn30_clk_mgr_smu_msg.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn30/dcn30_clk_mgr_smu_msg.c
index 3253115a153d..827bc2431d5d 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn30/dcn30_clk_mgr_smu_msg.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn30/dcn30_clk_mgr_smu_msg.c
@@ -69,7 +69,7 @@ static uint32_t dcn30_smu_wait_for_response(struct clk_mgr_internal *clk_mgr, un
 
 	/* handle DALSMC_Result_CmdRejectedBusy? */
 
-	TRACE_SMU_DELAY(delay_us * (initial_max_retries - max_retries), clk_mgr->base.ctx);
+	TRACE_SMU_MSG_DELAY(0, 0, delay_us * (initial_max_retries - max_retries), clk_mgr->base.ctx);
 
 	return reg;
 }
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.c
index 790bbd8235b1..9e63fa72101c 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.c
@@ -77,6 +77,7 @@ static const struct IP_BASE CLK_BASE = { { { { 0x00016C00, 0x02401800, 0, 0, 0,
 #undef DC_LOGGER
 #define DC_LOGGER \
 	clk_mgr->base.base.ctx->logger
+
 #define regCLK1_CLK_PLL_REQ			0x0237
 #define regCLK1_CLK_PLL_REQ_BASE_IDX		0
 
@@ -87,8 +88,70 @@ static const struct IP_BASE CLK_BASE = { { { { 0x00016C00, 0x02401800, 0, 0, 0,
 #define CLK1_CLK_PLL_REQ__PllSpineDiv_MASK	0x0000F000L
 #define CLK1_CLK_PLL_REQ__FbMult_frac_MASK	0xFFFF0000L
 
+#define regCLK1_CLK0_DFS_CNTL				0x0269
+#define regCLK1_CLK0_DFS_CNTL_BASE_IDX		0
+#define regCLK1_CLK1_DFS_CNTL				0x026c
+#define regCLK1_CLK1_DFS_CNTL_BASE_IDX		0
+#define regCLK1_CLK2_DFS_CNTL				0x026f
+#define regCLK1_CLK2_DFS_CNTL_BASE_IDX		0
+#define regCLK1_CLK3_DFS_CNTL				0x0272
+#define regCLK1_CLK3_DFS_CNTL_BASE_IDX		0
+#define regCLK1_CLK4_DFS_CNTL				0x0275
+#define regCLK1_CLK4_DFS_CNTL_BASE_IDX		0
+#define regCLK1_CLK5_DFS_CNTL				0x0278
+#define regCLK1_CLK5_DFS_CNTL_BASE_IDX		0
+
+#define regCLK1_CLK0_CURRENT_CNT			0x02fb
+#define regCLK1_CLK0_CURRENT_CNT_BASE_IDX	0
+#define regCLK1_CLK1_CURRENT_CNT			0x02fc
+#define regCLK1_CLK1_CURRENT_CNT_BASE_IDX	0
+#define regCLK1_CLK2_CURRENT_CNT			0x02fd
+#define regCLK1_CLK2_CURRENT_CNT_BASE_IDX	0
+#define regCLK1_CLK3_CURRENT_CNT			0x02fe
+#define regCLK1_CLK3_CURRENT_CNT_BASE_IDX	0
+#define regCLK1_CLK4_CURRENT_CNT			0x02ff
+#define regCLK1_CLK4_CURRENT_CNT_BASE_IDX	0
+#define regCLK1_CLK5_CURRENT_CNT			0x0300
+#define regCLK1_CLK5_CURRENT_CNT_BASE_IDX	0
+
+#define regCLK1_CLK0_BYPASS_CNTL			0x028a
+#define regCLK1_CLK0_BYPASS_CNTL_BASE_IDX	0
+#define regCLK1_CLK1_BYPASS_CNTL			0x0293
+#define regCLK1_CLK1_BYPASS_CNTL_BASE_IDX	0
 #define regCLK1_CLK2_BYPASS_CNTL			0x029c
 #define regCLK1_CLK2_BYPASS_CNTL_BASE_IDX	0
+#define regCLK1_CLK3_BYPASS_CNTL			0x02a5
+#define regCLK1_CLK3_BYPASS_CNTL_BASE_IDX	0
+#define regCLK1_CLK4_BYPASS_CNTL			0x02ae
+#define regCLK1_CLK4_BYPASS_CNTL_BASE_IDX	0
+#define regCLK1_CLK5_BYPASS_CNTL			0x02b7
+#define regCLK1_CLK5_BYPASS_CNTL_BASE_IDX	0
+
+#define regCLK1_CLK0_DS_CNTL				0x0283
+#define regCLK1_CLK0_DS_CNTL_BASE_IDX		0
+#define regCLK1_CLK1_DS_CNTL				0x028c
+#define regCLK1_CLK1_DS_CNTL_BASE_IDX		0
+#define regCLK1_CLK2_DS_CNTL				0x0295
+#define regCLK1_CLK2_DS_CNTL_BASE_IDX		0
+#define regCLK1_CLK3_DS_CNTL				0x029e
+#define regCLK1_CLK3_DS_CNTL_BASE_IDX		0
+#define regCLK1_CLK4_DS_CNTL				0x02a7
+#define regCLK1_CLK4_DS_CNTL_BASE_IDX		0
+#define regCLK1_CLK5_DS_CNTL				0x02b0
+#define regCLK1_CLK5_DS_CNTL_BASE_IDX		0
+
+#define regCLK1_CLK0_ALLOW_DS				0x0284
+#define regCLK1_CLK0_ALLOW_DS_BASE_IDX		0
+#define regCLK1_CLK1_ALLOW_DS				0x028d
+#define regCLK1_CLK1_ALLOW_DS_BASE_IDX		0
+#define regCLK1_CLK2_ALLOW_DS				0x0296
+#define regCLK1_CLK2_ALLOW_DS_BASE_IDX		0
+#define regCLK1_CLK3_ALLOW_DS				0x029f
+#define regCLK1_CLK3_ALLOW_DS_BASE_IDX		0
+#define regCLK1_CLK4_ALLOW_DS				0x02a8
+#define regCLK1_CLK4_ALLOW_DS_BASE_IDX		0
+#define regCLK1_CLK5_ALLOW_DS				0x02b1
+#define regCLK1_CLK5_ALLOW_DS_BASE_IDX		0
 
 #define CLK1_CLK2_BYPASS_CNTL__CLK2_BYPASS_SEL__SHIFT	0x0
 #define CLK1_CLK2_BYPASS_CNTL__CLK2_BYPASS_DIV__SHIFT	0x10
@@ -185,6 +248,8 @@ void dcn314_init_clocks(struct clk_mgr *clk_mgr)
 {
 	struct clk_mgr_internal *clk_mgr_int = TO_CLK_MGR_INTERNAL(clk_mgr);
 	uint32_t ref_dtbclk = clk_mgr->clks.ref_dtbclk_khz;
+	struct clk_mgr_dcn314 *clk_mgr_dcn314 = TO_CLK_MGR_DCN314(clk_mgr_int);
+	struct clk_log_info log_info = {0};
 
 	memset(&(clk_mgr->clks), 0, sizeof(struct dc_clocks));
 	// Assumption is that boot state always supports pstate
@@ -200,6 +265,9 @@ void dcn314_init_clocks(struct clk_mgr *clk_mgr)
 			dce_adjust_dp_ref_freq_for_ss(clk_mgr_int, clk_mgr->dprefclk_khz);
 	else
 		clk_mgr->dp_dto_source_clock_in_khz = clk_mgr->dprefclk_khz;
+
+	dcn314_dump_clk_registers(&clk_mgr->boot_snapshot, &clk_mgr_dcn314->base.base, &log_info);
+	clk_mgr->clks.dispclk_khz =  clk_mgr->boot_snapshot.dispclk * 1000;
 }
 
 void dcn314_update_clocks(struct clk_mgr *clk_mgr_base,
@@ -218,6 +286,8 @@ void dcn314_update_clocks(struct clk_mgr *clk_mgr_base,
 	if (dc->work_arounds.skip_clock_update)
 		return;
 
+	display_count = dcn314_get_active_display_cnt_wa(dc, context);
+
 	/*
 	 * if it is safe to lower, but we are already in the lower state, we don't have to do anything
 	 * also if safe to lower is false, we just go in the higher state
@@ -236,7 +306,6 @@ void dcn314_update_clocks(struct clk_mgr *clk_mgr_base,
 		}
 		/* check that we're not already in lower */
 		if (clk_mgr_base->clks.pwr_state != DCN_PWR_STATE_LOW_POWER) {
-			display_count = dcn314_get_active_display_cnt_wa(dc, context);
 			/* if we can go lower, go lower */
 			if (display_count == 0) {
 				union display_idle_optimization_u idle_info = { 0 };
@@ -293,11 +362,19 @@ void dcn314_update_clocks(struct clk_mgr *clk_mgr_base,
 		update_dppclk = true;
 	}
 
-	if (should_set_clock(safe_to_lower, new_clocks->dispclk_khz, clk_mgr_base->clks.dispclk_khz)) {
+	if (should_set_clock(safe_to_lower, new_clocks->dispclk_khz, clk_mgr_base->clks.dispclk_khz) &&
+	    (new_clocks->dispclk_khz > 0 || (safe_to_lower && display_count == 0))) {
+		int requested_dispclk_khz = new_clocks->dispclk_khz;
+
 		dcn314_disable_otg_wa(clk_mgr_base, context, safe_to_lower, true);
 
+		/* Clamp the requested clock to PMFW based on their limit. */
+		if (dc->debug.min_disp_clk_khz > 0 && requested_dispclk_khz < dc->debug.min_disp_clk_khz)
+			requested_dispclk_khz = dc->debug.min_disp_clk_khz;
+
+		dcn314_smu_set_dispclk(clk_mgr, requested_dispclk_khz);
 		clk_mgr_base->clks.dispclk_khz = new_clocks->dispclk_khz;
-		dcn314_smu_set_dispclk(clk_mgr, clk_mgr_base->clks.dispclk_khz);
+
 		dcn314_disable_otg_wa(clk_mgr_base, context, safe_to_lower, false);
 
 		update_dispclk = true;
@@ -385,10 +462,65 @@ bool dcn314_are_clock_states_equal(struct dc_clocks *a,
 	return true;
 }
 
-static void dcn314_dump_clk_registers(struct clk_state_registers_and_bypass *regs_and_bypass,
+
+static void dcn314_dump_clk_registers_internal(struct dcn35_clk_internal *internal, struct clk_mgr *clk_mgr_base)
+{
+	struct clk_mgr_internal *clk_mgr = TO_CLK_MGR_INTERNAL(clk_mgr_base);
+
+	// read dtbclk
+	internal->CLK1_CLK4_CURRENT_CNT = REG_READ(CLK1_CLK4_CURRENT_CNT);
+	internal->CLK1_CLK4_BYPASS_CNTL = REG_READ(CLK1_CLK4_BYPASS_CNTL);
+
+	// read dcfclk
+	internal->CLK1_CLK3_CURRENT_CNT = REG_READ(CLK1_CLK3_CURRENT_CNT);
+	internal->CLK1_CLK3_BYPASS_CNTL = REG_READ(CLK1_CLK3_BYPASS_CNTL);
+
+	// read dcf deep sleep divider
+	internal->CLK1_CLK3_DS_CNTL = REG_READ(CLK1_CLK3_DS_CNTL);
+	internal->CLK1_CLK3_ALLOW_DS = REG_READ(CLK1_CLK3_ALLOW_DS);
+
+	// read dppclk
+	internal->CLK1_CLK1_CURRENT_CNT = REG_READ(CLK1_CLK1_CURRENT_CNT);
+	internal->CLK1_CLK1_BYPASS_CNTL = REG_READ(CLK1_CLK1_BYPASS_CNTL);
+
+	// read dprefclk
+	internal->CLK1_CLK2_CURRENT_CNT = REG_READ(CLK1_CLK2_CURRENT_CNT);
+	internal->CLK1_CLK2_BYPASS_CNTL = REG_READ(CLK1_CLK2_BYPASS_CNTL);
+
+	// read dispclk
+	internal->CLK1_CLK0_CURRENT_CNT = REG_READ(CLK1_CLK0_CURRENT_CNT);
+	internal->CLK1_CLK0_BYPASS_CNTL = REG_READ(CLK1_CLK0_BYPASS_CNTL);
+}
+
+void dcn314_dump_clk_registers(struct clk_state_registers_and_bypass *regs_and_bypass,
 		struct clk_mgr *clk_mgr_base, struct clk_log_info *log_info)
 {
-	return;
+
+	struct dcn35_clk_internal internal = {0};
+
+	dcn314_dump_clk_registers_internal(&internal, clk_mgr_base);
+
+	regs_and_bypass->dcfclk = internal.CLK1_CLK3_CURRENT_CNT / 10;
+	regs_and_bypass->dcf_deep_sleep_divider = internal.CLK1_CLK3_DS_CNTL / 10;
+	regs_and_bypass->dcf_deep_sleep_allow = internal.CLK1_CLK3_ALLOW_DS;
+	regs_and_bypass->dprefclk = internal.CLK1_CLK2_CURRENT_CNT / 10;
+	regs_and_bypass->dispclk = internal.CLK1_CLK0_CURRENT_CNT / 10;
+	regs_and_bypass->dppclk = internal.CLK1_CLK1_CURRENT_CNT / 10;
+	regs_and_bypass->dtbclk = internal.CLK1_CLK4_CURRENT_CNT / 10;
+
+	regs_and_bypass->dppclk_bypass = internal.CLK1_CLK1_BYPASS_CNTL & 0x0007;
+	if (regs_and_bypass->dppclk_bypass < 0 || regs_and_bypass->dppclk_bypass > 4)
+		regs_and_bypass->dppclk_bypass = 0;
+	regs_and_bypass->dcfclk_bypass = internal.CLK1_CLK3_BYPASS_CNTL & 0x0007;
+	if (regs_and_bypass->dcfclk_bypass < 0 || regs_and_bypass->dcfclk_bypass > 4)
+		regs_and_bypass->dcfclk_bypass = 0;
+	regs_and_bypass->dispclk_bypass = internal.CLK1_CLK0_BYPASS_CNTL & 0x0007;
+	if (regs_and_bypass->dispclk_bypass < 0 || regs_and_bypass->dispclk_bypass > 4)
+		regs_and_bypass->dispclk_bypass = 0;
+	regs_and_bypass->dprefclk_bypass = internal.CLK1_CLK2_BYPASS_CNTL & 0x0007;
+	if (regs_and_bypass->dprefclk_bypass < 0 || regs_and_bypass->dprefclk_bypass > 4)
+		regs_and_bypass->dprefclk_bypass = 0;
+
 }
 
 static struct clk_bw_params dcn314_bw_params = {
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.h b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.h
index 002c28e80720..0577eb527bc3 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.h
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.h
@@ -65,4 +65,9 @@ void dcn314_clk_mgr_construct(struct dc_context *ctx,
 
 void dcn314_clk_mgr_destroy(struct clk_mgr_internal *clk_mgr_int);
 
+
+void dcn314_dump_clk_registers(struct clk_state_registers_and_bypass *regs_and_bypass,
+		struct clk_mgr *clk_mgr_base, struct clk_log_info *log_info);
+
+
 #endif //__DCN314_CLK_MGR_H__
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn32/dcn32_clk_mgr_smu_msg.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn32/dcn32_clk_mgr_smu_msg.c
index cf2d35363e8b..5d80fdf63ffc 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn32/dcn32_clk_mgr_smu_msg.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn32/dcn32_clk_mgr_smu_msg.c
@@ -63,7 +63,8 @@ static uint32_t dcn32_smu_wait_for_response(struct clk_mgr_internal *clk_mgr, un
 			udelay(delay_us);
 	} while (max_retries--);
 
-	TRACE_SMU_DELAY(delay_us * (initial_max_retries - max_retries), clk_mgr->base.ctx);
+	TRACE_SMU_MSG_DELAY(0, 0, delay_us * (initial_max_retries - max_retries), clk_mgr->base.ctx);
+
 
 	return reg;
 }
@@ -120,7 +121,7 @@ static uint32_t dcn32_smu_wait_for_response_delay(struct clk_mgr_internal *clk_m
 		*total_delay_us += delay_us;
 	} while (max_retries--);
 
-	TRACE_SMU_DELAY(*total_delay_us, clk_mgr->base.ctx);
+	TRACE_SMU_MSG_DELAY(0, 0, *total_delay_us, clk_mgr->base.ctx);
 
 	return reg;
 }
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c
index 86edf11b8c5a..b11383fba35f 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c
@@ -587,9 +587,118 @@ bool dcn35_are_clock_states_equal(struct dc_clocks *a,
 	return true;
 }
 
-static void dcn35_dump_clk_registers(struct clk_state_registers_and_bypass *regs_and_bypass,
+static void dcn35_save_clk_registers_internal(struct dcn35_clk_internal *internal, struct clk_mgr *clk_mgr_base)
+{
+	struct clk_mgr_internal *clk_mgr = TO_CLK_MGR_INTERNAL(clk_mgr_base);
+
+	// read dtbclk
+	internal->CLK1_CLK4_CURRENT_CNT = REG_READ(CLK1_CLK4_CURRENT_CNT);
+	internal->CLK1_CLK4_BYPASS_CNTL = REG_READ(CLK1_CLK4_BYPASS_CNTL);
+
+	// read dcfclk
+	internal->CLK1_CLK3_CURRENT_CNT = REG_READ(CLK1_CLK3_CURRENT_CNT);
+	internal->CLK1_CLK3_BYPASS_CNTL = REG_READ(CLK1_CLK3_BYPASS_CNTL);
+
+	// read dcf deep sleep divider
+	internal->CLK1_CLK3_DS_CNTL = REG_READ(CLK1_CLK3_DS_CNTL);
+	internal->CLK1_CLK3_ALLOW_DS = REG_READ(CLK1_CLK3_ALLOW_DS);
+
+	// read dppclk
+	internal->CLK1_CLK1_CURRENT_CNT = REG_READ(CLK1_CLK1_CURRENT_CNT);
+	internal->CLK1_CLK1_BYPASS_CNTL = REG_READ(CLK1_CLK1_BYPASS_CNTL);
+
+	// read dprefclk
+	internal->CLK1_CLK2_CURRENT_CNT = REG_READ(CLK1_CLK2_CURRENT_CNT);
+	internal->CLK1_CLK2_BYPASS_CNTL = REG_READ(CLK1_CLK2_BYPASS_CNTL);
+
+	// read dispclk
+	internal->CLK1_CLK0_CURRENT_CNT = REG_READ(CLK1_CLK0_CURRENT_CNT);
+	internal->CLK1_CLK0_BYPASS_CNTL = REG_READ(CLK1_CLK0_BYPASS_CNTL);
+}
+
+static void dcn35_save_clk_registers(struct clk_state_registers_and_bypass *regs_and_bypass,
 		struct clk_mgr_dcn35 *clk_mgr)
 {
+	struct dcn35_clk_internal internal = {0};
+	char *bypass_clks[5] = {"0x0 DFS", "0x1 REFCLK", "0x2 ERROR", "0x3 400 FCH", "0x4 600 FCH"};
+
+	dcn35_save_clk_registers_internal(&internal, &clk_mgr->base.base);
+
+	regs_and_bypass->dcfclk = internal.CLK1_CLK3_CURRENT_CNT / 10;
+	regs_and_bypass->dcf_deep_sleep_divider = internal.CLK1_CLK3_DS_CNTL / 10;
+	regs_and_bypass->dcf_deep_sleep_allow = internal.CLK1_CLK3_ALLOW_DS;
+	regs_and_bypass->dprefclk = internal.CLK1_CLK2_CURRENT_CNT / 10;
+	regs_and_bypass->dispclk = internal.CLK1_CLK0_CURRENT_CNT / 10;
+	regs_and_bypass->dppclk = internal.CLK1_CLK1_CURRENT_CNT / 10;
+	regs_and_bypass->dtbclk = internal.CLK1_CLK4_CURRENT_CNT / 10;
+
+	regs_and_bypass->dppclk_bypass = internal.CLK1_CLK1_BYPASS_CNTL & 0x0007;
+	if (regs_and_bypass->dppclk_bypass < 0 || regs_and_bypass->dppclk_bypass > 4)
+		regs_and_bypass->dppclk_bypass = 0;
+	regs_and_bypass->dcfclk_bypass = internal.CLK1_CLK3_BYPASS_CNTL & 0x0007;
+	if (regs_and_bypass->dcfclk_bypass < 0 || regs_and_bypass->dcfclk_bypass > 4)
+		regs_and_bypass->dcfclk_bypass = 0;
+	regs_and_bypass->dispclk_bypass = internal.CLK1_CLK0_BYPASS_CNTL & 0x0007;
+	if (regs_and_bypass->dispclk_bypass < 0 || regs_and_bypass->dispclk_bypass > 4)
+		regs_and_bypass->dispclk_bypass = 0;
+	regs_and_bypass->dprefclk_bypass = internal.CLK1_CLK2_BYPASS_CNTL & 0x0007;
+	if (regs_and_bypass->dprefclk_bypass < 0 || regs_and_bypass->dprefclk_bypass > 4)
+		regs_and_bypass->dprefclk_bypass = 0;
+
+	if (clk_mgr->base.base.ctx->dc->debug.pstate_enabled) {
+		DC_LOG_SMU("clk_type,clk_value,deepsleep_cntl,deepsleep_allow,bypass\n");
+
+		DC_LOG_SMU("dcfclk,%d,%d,%d,%s\n",
+				   regs_and_bypass->dcfclk,
+				   regs_and_bypass->dcf_deep_sleep_divider,
+				   regs_and_bypass->dcf_deep_sleep_allow,
+				   bypass_clks[(int) regs_and_bypass->dcfclk_bypass]);
+
+		DC_LOG_SMU("dprefclk,%d,N/A,N/A,%s\n",
+			regs_and_bypass->dprefclk,
+			bypass_clks[(int) regs_and_bypass->dprefclk_bypass]);
+
+		DC_LOG_SMU("dispclk,%d,N/A,N/A,%s\n",
+			regs_and_bypass->dispclk,
+			bypass_clks[(int) regs_and_bypass->dispclk_bypass]);
+
+		// REGISTER VALUES
+		DC_LOG_SMU("reg_name,value,clk_type");
+
+		DC_LOG_SMU("CLK1_CLK3_CURRENT_CNT,%d,dcfclk",
+				internal.CLK1_CLK3_CURRENT_CNT);
+
+		DC_LOG_SMU("CLK1_CLK4_CURRENT_CNT,%d,dtbclk",
+					internal.CLK1_CLK4_CURRENT_CNT);
+
+		DC_LOG_SMU("CLK1_CLK3_DS_CNTL,%d,dcf_deep_sleep_divider",
+					internal.CLK1_CLK3_DS_CNTL);
+
+		DC_LOG_SMU("CLK1_CLK3_ALLOW_DS,%d,dcf_deep_sleep_allow",
+					internal.CLK1_CLK3_ALLOW_DS);
+
+		DC_LOG_SMU("CLK1_CLK2_CURRENT_CNT,%d,dprefclk",
+					internal.CLK1_CLK2_CURRENT_CNT);
+
+		DC_LOG_SMU("CLK1_CLK0_CURRENT_CNT,%d,dispclk",
+					internal.CLK1_CLK0_CURRENT_CNT);
+
+		DC_LOG_SMU("CLK1_CLK1_CURRENT_CNT,%d,dppclk",
+					internal.CLK1_CLK1_CURRENT_CNT);
+
+		DC_LOG_SMU("CLK1_CLK3_BYPASS_CNTL,%d,dcfclk_bypass",
+					internal.CLK1_CLK3_BYPASS_CNTL);
+
+		DC_LOG_SMU("CLK1_CLK2_BYPASS_CNTL,%d,dprefclk_bypass",
+					internal.CLK1_CLK2_BYPASS_CNTL);
+
+		DC_LOG_SMU("CLK1_CLK0_BYPASS_CNTL,%d,dispclk_bypass",
+					internal.CLK1_CLK0_BYPASS_CNTL);
+
+		DC_LOG_SMU("CLK1_CLK1_BYPASS_CNTL,%d,dppclk_bypass",
+					internal.CLK1_CLK1_BYPASS_CNTL);
+
+	}
 }
 
 static bool dcn35_is_spll_ssc_enabled(struct clk_mgr *clk_mgr_base)
@@ -623,6 +732,7 @@ static void init_clk_states(struct clk_mgr *clk_mgr)
 void dcn35_init_clocks(struct clk_mgr *clk_mgr)
 {
 	struct clk_mgr_internal *clk_mgr_int = TO_CLK_MGR_INTERNAL(clk_mgr);
+	struct clk_mgr_dcn35 *clk_mgr_dcn35 = TO_CLK_MGR_DCN35(clk_mgr_int);
 
 	init_clk_states(clk_mgr);
 
@@ -633,6 +743,13 @@ void dcn35_init_clocks(struct clk_mgr *clk_mgr)
 	else
 		clk_mgr->dp_dto_source_clock_in_khz = clk_mgr->dprefclk_khz;
 
+	dcn35_save_clk_registers(&clk_mgr->boot_snapshot, clk_mgr_dcn35);
+
+	clk_mgr->clks.ref_dtbclk_khz =  clk_mgr->boot_snapshot.dtbclk * 10;
+	if (clk_mgr->boot_snapshot.dtbclk > 59000) {
+		/*dtbclk enabled based on */
+		clk_mgr->clks.dtbclk_en = true;
+	}
 }
 static struct clk_bw_params dcn35_bw_params = {
 	.vram_type = Ddr4MemType,
@@ -1323,7 +1440,7 @@ void dcn35_clk_mgr_construct(
 		dcn35_bw_params.wm_table = ddr5_wm_table;
 	}
 	/* Saved clocks configured at boot for debug purposes */
-	dcn35_dump_clk_registers(&clk_mgr->base.base.boot_snapshot, clk_mgr);
+	dcn35_save_clk_registers(&clk_mgr->base.base.boot_snapshot, clk_mgr);
 
 	clk_mgr->base.base.dprefclk_khz = dcn35_smu_get_dprefclk(&clk_mgr->base);
 	clk_mgr->base.base.clks.ref_dtbclk_khz = 600000;
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn401/dcn401_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn401/dcn401_clk_mgr.c
index 47461f249e83..306016c1f109 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn401/dcn401_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn401/dcn401_clk_mgr.c
@@ -162,7 +162,7 @@ static void dcn401_init_single_clock(struct clk_mgr_internal *clk_mgr, PPCLK_e c
 	unsigned int i;
 	char *entry_i = (char *)entry_0;
 
-	uint32_t ret = dcn30_smu_get_dpm_freq_by_index(clk_mgr, clk, 0xFF);
+	uint32_t ret = dcn401_smu_get_dpm_freq_by_index(clk_mgr, clk, 0xFF);
 
 	if (ret & (1 << 31))
 		/* fine-grained, only min and max */
@@ -174,7 +174,7 @@ static void dcn401_init_single_clock(struct clk_mgr_internal *clk_mgr, PPCLK_e c
 
 	/* if the initial message failed, num_levels will be 0 */
 	for (i = 0; i < *num_levels && i < ARRAY_SIZE(clk_mgr->base.bw_params->clk_table.entries); i++) {
-		*((unsigned int *)entry_i) = (dcn30_smu_get_dpm_freq_by_index(clk_mgr, clk, i) & 0xFFFF);
+		*((unsigned int *)entry_i) = (dcn401_smu_get_dpm_freq_by_index(clk_mgr, clk, i) & 0xFFFF);
 		entry_i += sizeof(clk_mgr->base.bw_params->clk_table.entries[0]);
 	}
 }
@@ -231,20 +231,20 @@ void dcn401_init_clocks(struct clk_mgr *clk_mgr_base)
 	clk_mgr->smu_present = false;
 	clk_mgr->dpm_present = false;
 
-	if (!clk_mgr_base->force_smu_not_present && dcn30_smu_get_smu_version(clk_mgr, &clk_mgr->smu_ver))
+	if (!clk_mgr_base->force_smu_not_present && dcn401_smu_get_smu_version(clk_mgr, &clk_mgr->smu_ver))
 		clk_mgr->smu_present = true;
 
 	if (!clk_mgr->smu_present)
 		return;
 
-	dcn30_smu_check_driver_if_version(clk_mgr);
-	dcn30_smu_check_msg_header_version(clk_mgr);
+	dcn401_smu_check_driver_if_version(clk_mgr);
+	dcn401_smu_check_msg_header_version(clk_mgr);
 
 	/* DCFCLK */
 	dcn401_init_single_clock(clk_mgr, PPCLK_DCFCLK,
 			&clk_mgr_base->bw_params->clk_table.entries[0].dcfclk_mhz,
 			&num_entries_per_clk->num_dcfclk_levels);
-	clk_mgr_base->bw_params->dc_mode_limit.dcfclk_mhz = dcn30_smu_get_dc_mode_max_dpm_freq(clk_mgr, PPCLK_DCFCLK);
+	clk_mgr_base->bw_params->dc_mode_limit.dcfclk_mhz = dcn401_smu_get_dc_mode_max_dpm_freq(clk_mgr, PPCLK_DCFCLK);
 	if (num_entries_per_clk->num_dcfclk_levels && clk_mgr_base->bw_params->dc_mode_limit.dcfclk_mhz ==
 			clk_mgr_base->bw_params->clk_table.entries[num_entries_per_clk->num_dcfclk_levels - 1].dcfclk_mhz)
 		clk_mgr_base->bw_params->dc_mode_limit.dcfclk_mhz = 0;
@@ -253,7 +253,7 @@ void dcn401_init_clocks(struct clk_mgr *clk_mgr_base)
 	dcn401_init_single_clock(clk_mgr, PPCLK_SOCCLK,
 					&clk_mgr_base->bw_params->clk_table.entries[0].socclk_mhz,
 					&num_entries_per_clk->num_socclk_levels);
-	clk_mgr_base->bw_params->dc_mode_limit.socclk_mhz = dcn30_smu_get_dc_mode_max_dpm_freq(clk_mgr, PPCLK_SOCCLK);
+	clk_mgr_base->bw_params->dc_mode_limit.socclk_mhz = dcn401_smu_get_dc_mode_max_dpm_freq(clk_mgr, PPCLK_SOCCLK);
 	if (num_entries_per_clk->num_socclk_levels && clk_mgr_base->bw_params->dc_mode_limit.socclk_mhz ==
 			clk_mgr_base->bw_params->clk_table.entries[num_entries_per_clk->num_socclk_levels - 1].socclk_mhz)
 		clk_mgr_base->bw_params->dc_mode_limit.socclk_mhz = 0;
@@ -263,7 +263,7 @@ void dcn401_init_clocks(struct clk_mgr *clk_mgr_base)
 		dcn401_init_single_clock(clk_mgr, PPCLK_DTBCLK,
 				&clk_mgr_base->bw_params->clk_table.entries[0].dtbclk_mhz,
 				&num_entries_per_clk->num_dtbclk_levels);
-		clk_mgr_base->bw_params->dc_mode_limit.dtbclk_mhz = dcn30_smu_get_dc_mode_max_dpm_freq(clk_mgr, PPCLK_DTBCLK);
+		clk_mgr_base->bw_params->dc_mode_limit.dtbclk_mhz = dcn401_smu_get_dc_mode_max_dpm_freq(clk_mgr, PPCLK_DTBCLK);
 		if (num_entries_per_clk->num_dtbclk_levels && clk_mgr_base->bw_params->dc_mode_limit.dtbclk_mhz ==
 				clk_mgr_base->bw_params->clk_table.entries[num_entries_per_clk->num_dtbclk_levels - 1].dtbclk_mhz)
 			clk_mgr_base->bw_params->dc_mode_limit.dtbclk_mhz = 0;
@@ -273,7 +273,7 @@ void dcn401_init_clocks(struct clk_mgr *clk_mgr_base)
 	dcn401_init_single_clock(clk_mgr, PPCLK_DISPCLK,
 			&clk_mgr_base->bw_params->clk_table.entries[0].dispclk_mhz,
 			&num_entries_per_clk->num_dispclk_levels);
-	clk_mgr_base->bw_params->dc_mode_limit.dispclk_mhz = dcn30_smu_get_dc_mode_max_dpm_freq(clk_mgr, PPCLK_DISPCLK);
+	clk_mgr_base->bw_params->dc_mode_limit.dispclk_mhz = dcn401_smu_get_dc_mode_max_dpm_freq(clk_mgr, PPCLK_DISPCLK);
 	if (num_entries_per_clk->num_dispclk_levels && clk_mgr_base->bw_params->dc_mode_limit.dispclk_mhz ==
 			clk_mgr_base->bw_params->clk_table.entries[num_entries_per_clk->num_dispclk_levels - 1].dispclk_mhz)
 		clk_mgr_base->bw_params->dc_mode_limit.dispclk_mhz = 0;
@@ -1318,8 +1318,8 @@ static void dcn401_notify_wm_ranges(struct clk_mgr *clk_mgr_base)
 			table->Watermarks.WatermarkRow[i].WmSetting = i;
 			table->Watermarks.WatermarkRow[i].Flags = clk_mgr->base.bw_params->wm_table.nv_entries[i].pmfw_breakdown.wm_type;
 		}
-	dcn30_smu_set_dram_addr_high(clk_mgr, clk_mgr->wm_range_table_addr >> 32);
-	dcn30_smu_set_dram_addr_low(clk_mgr, clk_mgr->wm_range_table_addr & 0xFFFFFFFF);
+	dcn401_smu_set_dram_addr_high(clk_mgr, clk_mgr->wm_range_table_addr >> 32);
+	dcn401_smu_set_dram_addr_low(clk_mgr, clk_mgr->wm_range_table_addr & 0xFFFFFFFF);
 	dcn401_smu_transfer_wm_table_dram_2_smu(clk_mgr);
 }
 
@@ -1390,7 +1390,7 @@ static void dcn401_get_memclk_states_from_smu(struct clk_mgr *clk_mgr_base)
 				clk_mgr_base->bw_params->clk_table.entries[num_entries_per_clk->num_memclk_levels - 1].memclk_mhz;
 	}
 
-	clk_mgr_base->bw_params->dc_mode_limit.memclk_mhz = dcn30_smu_get_dc_mode_max_dpm_freq(clk_mgr, PPCLK_UCLK);
+	clk_mgr_base->bw_params->dc_mode_limit.memclk_mhz = dcn401_smu_get_dc_mode_max_dpm_freq(clk_mgr, PPCLK_UCLK);
 	if (num_entries_per_clk->num_memclk_levels && clk_mgr_base->bw_params->dc_mode_limit.memclk_mhz ==
 			clk_mgr_base->bw_params->clk_table.entries[num_entries_per_clk->num_memclk_levels - 1].memclk_mhz)
 		clk_mgr_base->bw_params->dc_mode_limit.memclk_mhz = 0;
@@ -1399,7 +1399,7 @@ static void dcn401_get_memclk_states_from_smu(struct clk_mgr *clk_mgr_base)
 	dcn401_init_single_clock(clk_mgr, PPCLK_FCLK,
 			&clk_mgr_base->bw_params->clk_table.entries[0].fclk_mhz,
 			&num_entries_per_clk->num_fclk_levels);
-	clk_mgr_base->bw_params->dc_mode_limit.fclk_mhz = dcn30_smu_get_dc_mode_max_dpm_freq(clk_mgr, PPCLK_FCLK);
+	clk_mgr_base->bw_params->dc_mode_limit.fclk_mhz = dcn401_smu_get_dc_mode_max_dpm_freq(clk_mgr, PPCLK_FCLK);
 	if (num_entries_per_clk->num_fclk_levels && clk_mgr_base->bw_params->dc_mode_limit.fclk_mhz ==
 			clk_mgr_base->bw_params->clk_table.entries[num_entries_per_clk->num_fclk_levels - 1].fclk_mhz)
 		clk_mgr_base->bw_params->dc_mode_limit.fclk_mhz = 0;
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn401/dcn401_clk_mgr_smu_msg.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn401/dcn401_clk_mgr_smu_msg.c
index 21c35528f61f..3a263840893e 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn401/dcn401_clk_mgr_smu_msg.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn401/dcn401_clk_mgr_smu_msg.c
@@ -57,6 +57,8 @@ static bool dcn401_smu_send_msg_with_param(struct clk_mgr_internal *clk_mgr, uin
 	/* Wait for response register to be ready */
 	dcn401_smu_wait_for_response(clk_mgr, 10, 200000);
 
+	TRACE_SMU_MSG_ENTER(msg_id, param_in, clk_mgr->base.ctx);
+
 	/* Clear response register */
 	REG_WRITE(DAL_RESP_REG, 0);
 
@@ -71,9 +73,11 @@ static bool dcn401_smu_send_msg_with_param(struct clk_mgr_internal *clk_mgr, uin
 		if (param_out)
 			*param_out = REG_READ(DAL_ARG_REG);
 
+		TRACE_SMU_MSG_EXIT(true, param_out ? *param_out : 0, clk_mgr->base.ctx);
 		return true;
 	}
 
+	TRACE_SMU_MSG_EXIT(false, 0, clk_mgr->base.ctx);
 	return false;
 }
 
@@ -102,8 +106,6 @@ static uint32_t dcn401_smu_wait_for_response_delay(struct clk_mgr_internal *clk_
 		*total_delay_us += delay_us;
 	} while (max_retries--);
 
-	TRACE_SMU_DELAY(*total_delay_us, clk_mgr->base.ctx);
-
 	return reg;
 }
 
@@ -115,6 +117,8 @@ static bool dcn401_smu_send_msg_with_param_delay(struct clk_mgr_internal *clk_mg
 	/* Wait for response register to be ready */
 	dcn401_smu_wait_for_response_delay(clk_mgr, 10, 200000, &delay1_us);
 
+	TRACE_SMU_MSG_ENTER(msg_id, param_in, clk_mgr->base.ctx);
+
 	/* Clear response register */
 	REG_WRITE(DAL_RESP_REG, 0);
 
@@ -124,18 +128,71 @@ static bool dcn401_smu_send_msg_with_param_delay(struct clk_mgr_internal *clk_mg
 	/* Trigger the message transaction by writing the message ID */
 	REG_WRITE(DAL_MSG_REG, msg_id);
 
-	TRACE_SMU_MSG(msg_id, param_in, clk_mgr->base.ctx);
-
 	/* Wait for response */
 	if (dcn401_smu_wait_for_response_delay(clk_mgr, 10, 200000, &delay2_us) == DALSMC_Result_OK) {
 		if (param_out)
 			*param_out = REG_READ(DAL_ARG_REG);
 
 		*total_delay_us = delay1_us + delay2_us;
+		TRACE_SMU_MSG_EXIT(true, param_out ? *param_out : 0, clk_mgr->base.ctx);
 		return true;
 	}
 
 	*total_delay_us = delay1_us + 2000000;
+	TRACE_SMU_MSG_EXIT(false, 0, clk_mgr->base.ctx);
+	return false;
+}
+
+bool dcn401_smu_get_smu_version(struct clk_mgr_internal *clk_mgr, unsigned int *version)
+{
+	smu_print("SMU Get SMU version\n");
+
+	if (dcn401_smu_send_msg_with_param(clk_mgr,
+			DALSMC_MSG_GetSmuVersion, 0, version)) {
+
+		smu_print("SMU version: %d\n", *version);
+
+		return true;
+	}
+
+	return false;
+}
+
+/* Message output should match SMU11_DRIVER_IF_VERSION in smu11_driver_if.h */
+bool dcn401_smu_check_driver_if_version(struct clk_mgr_internal *clk_mgr)
+{
+	uint32_t response = 0;
+
+	smu_print("SMU Check driver if version\n");
+
+	if (dcn401_smu_send_msg_with_param(clk_mgr,
+			DALSMC_MSG_GetDriverIfVersion, 0, &response)) {
+
+		smu_print("SMU driver if version: %d\n", response);
+
+		if (response == SMU14_DRIVER_IF_VERSION)
+			return true;
+	}
+
+	return false;
+}
+
+/* Message output should match DALSMC_VERSION in dalsmc.h */
+bool dcn401_smu_check_msg_header_version(struct clk_mgr_internal *clk_mgr)
+{
+	uint32_t response = 0;
+
+	smu_print("SMU Check msg header version\n");
+
+	if (dcn401_smu_send_msg_with_param(clk_mgr,
+			DALSMC_MSG_GetMsgHeaderVersion, 0, &response)) {
+
+		smu_print("SMU msg header version: %d\n", response);
+
+		if (response == DALSMC_VERSION)
+			return true;
+	}
+
 	return false;
 }
 
@@ -163,6 +220,22 @@ void dcn401_smu_send_cab_for_uclk_message(struct clk_mgr_internal *clk_mgr, unsi
 	smu_print("Numways for SubVP : %d\n", num_ways);
 }
 
+void dcn401_smu_set_dram_addr_high(struct clk_mgr_internal *clk_mgr, uint32_t addr_high)
+{
+	smu_print("SMU Set DRAM addr high: %d\n", addr_high);
+
+	dcn401_smu_send_msg_with_param(clk_mgr,
+			DALSMC_MSG_SetDalDramAddrHigh, addr_high, NULL);
+}
+
+void dcn401_smu_set_dram_addr_low(struct clk_mgr_internal *clk_mgr, uint32_t addr_low)
+{
+	smu_print("SMU Set DRAM addr low: %d\n", addr_low);
+
+	dcn401_smu_send_msg_with_param(clk_mgr,
+			DALSMC_MSG_SetDalDramAddrLow, addr_low, NULL);
+}
+
 void dcn401_smu_transfer_wm_table_dram_2_smu(struct clk_mgr_internal *clk_mgr)
 {
 	smu_print("SMU Transfer WM table DRAM 2 SMU\n");
@@ -348,3 +421,52 @@ unsigned int dcn401_smu_get_num_of_umc_channels(struct clk_mgr_internal *clk_mgr
 
 	return response;
 }
+
+/*
+ * Frequency in MHz returned in lower 16 bits for valid DPM level
+ *
+ * Call with dpm_level = 0xFF to query features, return value will be:
+ *     Bits 7:0 - number of DPM levels
+ *     Bit   28 - 1 = auto DPM on
+ *     Bit   29 - 1 = sweep DPM on
+ *     Bit   30 - 1 = forced DPM on
+ *     Bit   31 - 0 = discrete, 1 = fine-grained
+ *
+ * With fine-grained DPM, only min and max frequencies will be reported
+ *
+ * Returns 0 on failure
+ */
+unsigned int dcn401_smu_get_dpm_freq_by_index(struct clk_mgr_internal *clk_mgr, uint32_t clk, uint8_t dpm_level)
+{
+	uint32_t response = 0;
+
+	/* bits 23:16 for clock type, lower 8 bits for DPM level */
+	uint32_t param = (clk << 16) | dpm_level;
+
+	smu_print("SMU Get dpm freq by index: clk = %d, dpm_level = %d\n", clk, dpm_level);
+
+	dcn401_smu_send_msg_with_param(clk_mgr,
+			DALSMC_MSG_GetDpmFreqByIndex, param, &response);
+
+	smu_print("SMU dpm freq: %d MHz\n", response);
+
+	return response;
+}
+
+/* Returns the max DPM frequency in DC mode in MHz, 0 on failure */
+unsigned int dcn401_smu_get_dc_mode_max_dpm_freq(struct clk_mgr_internal *clk_mgr, uint32_t clk)
+{
+	uint32_t response = 0;
+
+	/* bits 23:16 for clock type */
+	uint32_t param = clk << 16;
+
+	smu_print("SMU Get DC mode max DPM freq: clk = %d\n", clk);
+
+	dcn401_smu_send_msg_with_param(clk_mgr,
+			DALSMC_MSG_GetDcModeMaxDpmFreq, param, &response);
+
+	smu_print("SMU DC mode max DMP freq: %d MHz\n", response);
+
+	return response;
+}
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn401/dcn401_clk_mgr_smu_msg.h b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn401/dcn401_clk_mgr_smu_msg.h
index e02eb1294b37..4f5ac603e822 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn401/dcn401_clk_mgr_smu_msg.h
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn401/dcn401_clk_mgr_smu_msg.h
@@ -7,11 +7,17 @@
 
 #include "os_types.h"
 #include "core_types.h"
-#include "dcn32/dcn32_clk_mgr_smu_msg.h"
 
+struct clk_mgr_internal;
+
+bool dcn401_smu_get_smu_version(struct clk_mgr_internal *clk_mgr, unsigned int *version);
+bool dcn401_smu_check_driver_if_version(struct clk_mgr_internal *clk_mgr);
+bool dcn401_smu_check_msg_header_version(struct clk_mgr_internal *clk_mgr);
 void dcn401_smu_send_fclk_pstate_message(struct clk_mgr_internal *clk_mgr, bool support);
 void dcn401_smu_send_uclk_pstate_message(struct clk_mgr_internal *clk_mgr, bool support);
 void dcn401_smu_send_cab_for_uclk_message(struct clk_mgr_internal *clk_mgr, unsigned int num_ways);
+void dcn401_smu_set_dram_addr_high(struct clk_mgr_internal *clk_mgr, uint32_t addr_high);
+void dcn401_smu_set_dram_addr_low(struct clk_mgr_internal *clk_mgr, uint32_t addr_low);
 void dcn401_smu_transfer_wm_table_dram_2_smu(struct clk_mgr_internal *clk_mgr);
 void dcn401_smu_set_pme_workaround(struct clk_mgr_internal *clk_mgr);
 unsigned int dcn401_smu_set_hard_min_by_freq(struct clk_mgr_internal *clk_mgr, uint32_t clk, uint16_t freq_mhz);
@@ -29,5 +35,7 @@ bool dcn401_smu_set_subvp_uclk_fclk_hardmin(struct clk_mgr_internal *clk_mgr,
 void dcn401_smu_set_min_deep_sleep_dcef_clk(struct clk_mgr_internal *clk_mgr, uint32_t freq_mhz);
 void dcn401_smu_set_num_of_displays(struct clk_mgr_internal *clk_mgr, uint32_t num_displays);
 unsigned int dcn401_smu_get_num_of_umc_channels(struct clk_mgr_internal *clk_mgr);
+unsigned int dcn401_smu_get_dc_mode_max_dpm_freq(struct clk_mgr_internal *clk_mgr, uint32_t clk);
+unsigned int dcn401_smu_get_dpm_freq_by_index(struct clk_mgr_internal *clk_mgr, uint32_t clk, uint8_t dpm_level);
 
 #endif /* __DCN401_CLK_MGR_SMU_MSG_H_ */
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c
index c4dd52ed377d..5f2d5638c819 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc.c
@@ -460,7 +460,7 @@ bool dc_stream_adjust_vmin_vmax(struct dc *dc,
 	 * avoid conflicting with firmware updates.
 	 */
 	if (dc->ctx->dce_version > DCE_VERSION_MAX) {
-		if ((dc->optimized_required || dc->wm_optimized_required) &&
+		if (dc->optimized_required &&
 			(stream->adjust.v_total_max != adjust->v_total_max ||
 			stream->adjust.v_total_min != adjust->v_total_min)) {
 			stream->adjust.timing_adjust_pending = true;
@@ -2577,7 +2577,6 @@ void dc_post_update_surfaces_to_stream(struct dc *dc)
 	}
 
 	dc->optimized_required = false;
-	dc->wm_optimized_required = false;
 }
 
 bool dc_set_generic_gpio_for_stereo(bool enable,
@@ -3056,8 +3055,6 @@ enum surface_update_type dc_check_update_surfaces_for_stream(
 		} else if (memcmp(&dc->current_state->bw_ctx.bw.dcn.clk, &dc->clk_mgr->clks, offsetof(struct dc_clocks, prev_p_state_change_support)) != 0) {
 			dc->optimized_required = true;
 		}
-
-		dc->optimized_required |= dc->wm_optimized_required;
 	}
 
 	return type;
@@ -3313,6 +3310,9 @@ static void copy_stream_update_to_stream(struct dc *dc,
 	if (update->adaptive_sync_infopacket)
 		stream->adaptive_sync_infopacket = *update->adaptive_sync_infopacket;
 
+	if (update->avi_infopacket)
+		stream->avi_infopacket = *update->avi_infopacket;
+
 	if (update->dither_option)
 		stream->dither_option = *update->dither_option;
 
@@ -3607,7 +3607,8 @@ static void commit_planes_do_stream_update(struct dc *dc,
 					stream_update->vsp_infopacket ||
 					stream_update->hfvsif_infopacket ||
 					stream_update->adaptive_sync_infopacket ||
-					stream_update->vtem_infopacket) {
+					stream_update->vtem_infopacket ||
+					stream_update->avi_infopacket) {
 				resource_build_info_frame(pipe_ctx);
 				dc->hwss.update_info_frame(pipe_ctx);
 
@@ -5079,6 +5080,7 @@ static bool full_update_required(struct dc *dc,
 			stream_update->hfvsif_infopacket ||
 			stream_update->vtem_infopacket ||
 			stream_update->adaptive_sync_infopacket ||
+			stream_update->avi_infopacket ||
 			stream_update->dpms_off ||
 			stream_update->allow_freesync ||
 			stream_update->vrr_active_variable ||
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 cbca3c67f439..bc5dedf5f60c 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
@@ -4410,8 +4410,14 @@ static void set_avi_info_frame(
 	unsigned int fr_ind = pipe_ctx->stream->timing.fr_index;
 	enum dc_timing_3d_format format;
 
+	if (stream->avi_infopacket.valid) {
+		*info_packet = stream->avi_infopacket;
+		return;
+	}
+
 	memset(&hdmi_info, 0, sizeof(union hdmi_info_packet));
 
+
 	color_space = pipe_ctx->stream->output_color_space;
 	if (color_space == COLOR_SPACE_UNKNOWN)
 		color_space = (stream->timing.pixel_encoding == PIXEL_ENCODING_RGB) ?
diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h
index 9d15ba591772..98f0b6b3c213 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 "3.2.350"
+#define DC_VER "3.2.351"
 
 /**
  * MAX_SURFACES - representative of the upper bound of surfaces that can be piped to a single CRTC
@@ -1163,6 +1163,7 @@ struct dc_debug_options {
 	unsigned int auxless_alpm_lfps_silence_ns;
 	unsigned int auxless_alpm_lfps_t1t2_us;
 	short auxless_alpm_lfps_t1t2_offset_us;
+	bool disable_stutter_for_wm_program;
 };
 
 
@@ -1391,7 +1392,6 @@ union surface_update_flags {
 		uint32_t in_transfer_func_change:1;
 		uint32_t input_csc_change:1;
 		uint32_t coeff_reduction_change:1;
-		uint32_t output_tf_change:1;
 		uint32_t pixel_format_change:1;
 		uint32_t plane_size_change:1;
 		uint32_t gamut_remap_change:1;
@@ -1735,7 +1735,6 @@ struct dc {
 
 	/* Require to optimize clocks and bandwidth for added/removed planes */
 	bool optimized_required;
-	bool wm_optimized_required;
 	bool idle_optimizations_allowed;
 	bool enable_c20_dtm_b0;
 
diff --git a/drivers/gpu/drm/amd/display/dc/dc_stream.h b/drivers/gpu/drm/amd/display/dc/dc_stream.h
index 5fc6fea211de..76cf9fdedab0 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_stream.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_stream.h
@@ -203,6 +203,7 @@ struct dc_stream_state {
 	struct dc_info_packet hfvsif_infopacket;
 	struct dc_info_packet vtem_infopacket;
 	struct dc_info_packet adaptive_sync_infopacket;
+	struct dc_info_packet avi_infopacket;
 	uint8_t dsc_packed_pps[128];
 	struct rect src; /* composition area */
 	struct rect dst; /* stream addressable area */
@@ -335,6 +336,8 @@ struct dc_stream_update {
 	struct dc_info_packet *hfvsif_infopacket;
 	struct dc_info_packet *vtem_infopacket;
 	struct dc_info_packet *adaptive_sync_infopacket;
+	struct dc_info_packet *avi_infopacket;
+
 	bool *dpms_off;
 	bool integer_scaling_update;
 	bool *allow_freesync;
diff --git a/drivers/gpu/drm/amd/display/dc/dc_types.h b/drivers/gpu/drm/amd/display/dc/dc_types.h
index 619834a328a3..b5aa03a3e39c 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_types.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_types.h
@@ -1217,6 +1217,7 @@ struct dc_panel_config {
 		bool rc_disable;
 		bool rc_allow_static_screen;
 		bool rc_allow_fullscreen_VPB;
+		bool read_psrcap_again;
 		unsigned int replay_enable_option;
 	} psr;
 	/* ABM */
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 0ce9489ac6b7..de6d62401362 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
@@ -39,6 +39,7 @@
 
 #define CTX \
 	dccg_dcn->base.ctx
+#include "logger_types.h"
 #define DC_LOGGER \
 	dccg->ctx->logger
 
@@ -1136,7 +1137,7 @@ static void dcn35_set_dppclk_enable(struct dccg *dccg,
 	default:
 		break;
 	}
-	//DC_LOG_DEBUG("%s: dpp_inst(%d) DPPCLK_EN = %d\n", __func__, dpp_inst, enable);
+	DC_LOG_DEBUG("%s: dpp_inst(%d) DPPCLK_EN = %d\n", __func__, dpp_inst, enable);
 
 }
 
@@ -1406,6 +1407,10 @@ static void dccg35_set_dtbclk_dto(
 		 * 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.
 		 */
+		DC_LOG_DEBUG("%s: OTG%d DTBCLK DTO enabled: pixclk_khz=%d, ref_dtbclk_khz=%d, req_dtbclk_khz=%d, phase=%d, modulo=%d\n",
+				__func__, params->otg_inst, params->pixclk_khz,
+				params->ref_dtbclk_khz, req_dtbclk_khz, phase, modulo);
+
 	} else {
 		switch (params->otg_inst) {
 		case 0:
@@ -1431,6 +1436,8 @@ static void dccg35_set_dtbclk_dto(
 
 		REG_WRITE(DTBCLK_DTO_MODULO[params->otg_inst], 0);
 		REG_WRITE(DTBCLK_DTO_PHASE[params->otg_inst], 0);
+
+		DC_LOG_DEBUG("%s: OTG%d DTBCLK DTO disabled\n", __func__, params->otg_inst);
 	}
 }
 
@@ -1475,6 +1482,8 @@ static void dccg35_set_dpstreamclk(
 		BREAK_TO_DEBUGGER();
 		return;
 	}
+	DC_LOG_DEBUG("%s: dp_hpo_inst(%d) DPSTREAMCLK_EN = %d, DPSTREAMCLK_SRC_SEL = %d\n",
+			__func__, dp_hpo_inst, (src == REFCLK) ? 0 : 1, otg_inst);
 }
 
 
@@ -1514,6 +1523,8 @@ static void dccg35_set_dpstreamclk_root_clock_gating(
 		BREAK_TO_DEBUGGER();
 		return;
 	}
+	DC_LOG_DEBUG("%s: dp_hpo_inst(%d) DPSTREAMCLK_ROOT_GATE_DISABLE = %d\n",
+			__func__, dp_hpo_inst, enable ? 1 : 0);
 }
 
 
@@ -1553,7 +1564,7 @@ static void dccg35_set_physymclk_root_clock_gating(
 		BREAK_TO_DEBUGGER();
 		return;
 	}
-	//DC_LOG_DEBUG("%s: dpp_inst(%d) PHYESYMCLK_ROOT_GATE_DISABLE:\n", __func__, phy_inst, enable ? 0 : 1);
+	DC_LOG_DEBUG("%s: dpp_inst(%d) PHYESYMCLK_ROOT_GATE_DISABLE: %d\n", __func__, phy_inst, enable ? 0 : 1);
 
 }
 
@@ -1626,6 +1637,8 @@ static void dccg35_set_physymclk(
 		BREAK_TO_DEBUGGER();
 		return;
 	}
+	DC_LOG_DEBUG("%s: phy_inst(%d) PHYxSYMCLK_EN = %d, PHYxSYMCLK_SRC_SEL = %d\n",
+			__func__, phy_inst, force_enable ? 1 : 0, clk_src);
 }
 
 static void dccg35_set_valid_pixel_rate(
@@ -1673,6 +1686,7 @@ static void dccg35_dpp_root_clock_control(
 	}
 
 	dccg->dpp_clock_gated[dpp_inst] = !clock_on;
+	DC_LOG_DEBUG("%s: dpp_inst(%d) clock_on = %d\n", __func__, dpp_inst, clock_on);
 }
 
 static void dccg35_disable_symclk32_se(
@@ -1731,6 +1745,7 @@ static void dccg35_disable_symclk32_se(
 		BREAK_TO_DEBUGGER();
 		return;
 	}
+
 }
 
 static void dccg35_init_cb(struct dccg *dccg)
@@ -1738,7 +1753,6 @@ static void dccg35_init_cb(struct dccg *dccg)
 	(void)dccg;
 	/* Any RCG should be done when driver enter low power mode*/
 }
-
 void dccg35_init(struct dccg *dccg)
 {
 	int otg_inst;
@@ -1753,6 +1767,8 @@ void dccg35_init(struct dccg *dccg)
 		for (otg_inst = 0; otg_inst < 2; otg_inst++) {
 			dccg31_disable_symclk32_le(dccg, otg_inst);
 			dccg31_set_symclk32_le_root_clock_gating(dccg, otg_inst, false);
+			DC_LOG_DEBUG("%s: OTG%d SYMCLK32_LE disabled and root clock gating disabled\n",
+					__func__, otg_inst);
 		}
 
 //	if (dccg->ctx->dc->debug.root_clock_optimization.bits.symclk32_se)
@@ -1765,6 +1781,8 @@ void dccg35_init(struct dccg *dccg)
 			dccg35_set_dpstreamclk(dccg, REFCLK, otg_inst,
 						otg_inst);
 			dccg35_set_dpstreamclk_root_clock_gating(dccg, otg_inst, false);
+			DC_LOG_DEBUG("%s: OTG%d DPSTREAMCLK disabled and root clock gating disabled\n",
+					__func__, otg_inst);
 		}
 
 /*
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_transform.c b/drivers/gpu/drm/amd/display/dc/dce/dce_transform.c
index 2b1673d69ea8..1ab5ae9b5ea5 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_transform.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_transform.c
@@ -154,10 +154,13 @@ static bool dce60_setup_scaling_configuration(
 	REG_SET(SCL_BYPASS_CONTROL, 0, SCL_BYPASS_MODE, 0);
 
 	if (data->taps.h_taps + data->taps.v_taps <= 2) {
-		/* Set bypass */
-
-		/* DCE6 has no SCL_MODE register, skip scale mode programming */
+		/* Disable scaler functionality */
+		REG_WRITE(SCL_SCALER_ENABLE, 0);
 
+		/* Clear registers that can cause glitches even when the scaler is off */
+		REG_WRITE(SCL_TAP_CONTROL, 0);
+		REG_WRITE(SCL_AUTOMATIC_MODE_CONTROL, 0);
+		REG_WRITE(SCL_F_SHARP_CONTROL, 0);
 		return false;
 	}
 
@@ -165,7 +168,7 @@ static bool dce60_setup_scaling_configuration(
 			SCL_H_NUM_OF_TAPS, data->taps.h_taps - 1,
 			SCL_V_NUM_OF_TAPS, data->taps.v_taps - 1);
 
-	/* DCE6 has no SCL_MODE register, skip scale mode programming */
+	REG_WRITE(SCL_SCALER_ENABLE, 1);
 
 	/* DCE6 has no SCL_BOUNDARY_MODE bit, skip replace out of bound pixels */
 
@@ -502,6 +505,8 @@ static void dce60_transform_set_scaler(
 	REG_SET(DC_LB_MEM_SIZE, 0,
 		DC_LB_MEM_SIZE, xfm_dce->lb_memory_size);
 
+	REG_WRITE(SCL_UPDATE, 0x00010000);
+
 	/* Clear SCL_F_SHARP_CONTROL value to 0 */
 	REG_WRITE(SCL_F_SHARP_CONTROL, 0);
 
@@ -527,8 +532,7 @@ static void dce60_transform_set_scaler(
 		if (coeffs_v != xfm_dce->filter_v || coeffs_h != xfm_dce->filter_h) {
 			/* 4. Program vertical filters */
 			if (xfm_dce->filter_v == NULL)
-				REG_SET(SCL_VERT_FILTER_CONTROL, 0,
-						SCL_V_2TAP_HARDCODE_COEF_EN, 0);
+				REG_WRITE(SCL_VERT_FILTER_CONTROL, 0);
 			program_multi_taps_filter(
 					xfm_dce,
 					data->taps.v_taps,
@@ -542,8 +546,7 @@ static void dce60_transform_set_scaler(
 
 			/* 5. Program horizontal filters */
 			if (xfm_dce->filter_h == NULL)
-				REG_SET(SCL_HORZ_FILTER_CONTROL, 0,
-						SCL_H_2TAP_HARDCODE_COEF_EN, 0);
+				REG_WRITE(SCL_HORZ_FILTER_CONTROL, 0);
 			program_multi_taps_filter(
 					xfm_dce,
 					data->taps.h_taps,
@@ -566,6 +569,8 @@ static void dce60_transform_set_scaler(
 	/* DCE6 has no SCL_COEF_UPDATE_COMPLETE bit to flip to new coefficient memory */
 
 	/* DCE6 DATA_FORMAT register does not support ALPHA_EN */
+
+	REG_WRITE(SCL_UPDATE, 0);
 }
 #endif
 
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_transform.h b/drivers/gpu/drm/amd/display/dc/dce/dce_transform.h
index cbce194ec7b8..eb716e8337e2 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_transform.h
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_transform.h
@@ -155,6 +155,9 @@
 	SRI(SCL_COEF_RAM_TAP_DATA, SCL, id), \
 	SRI(VIEWPORT_START, SCL, id), \
 	SRI(VIEWPORT_SIZE, SCL, id), \
+	SRI(SCL_SCALER_ENABLE, SCL, id), \
+	SRI(SCL_HORZ_FILTER_INIT_RGB_LUMA, SCL, id), \
+	SRI(SCL_HORZ_FILTER_INIT_CHROMA, SCL, id), \
 	SRI(SCL_HORZ_FILTER_SCALE_RATIO, SCL, id), \
 	SRI(SCL_VERT_FILTER_SCALE_RATIO, SCL, id), \
 	SRI(SCL_VERT_FILTER_INIT, SCL, id), \
@@ -590,6 +593,7 @@ struct dce_transform_registers {
 	uint32_t SCL_VERT_FILTER_SCALE_RATIO;
 	uint32_t SCL_HORZ_FILTER_INIT;
 #if defined(CONFIG_DRM_AMD_DC_SI)
+	uint32_t SCL_SCALER_ENABLE;
 	uint32_t SCL_HORZ_FILTER_INIT_RGB_LUMA;
 	uint32_t SCL_HORZ_FILTER_INIT_CHROMA;
 #endif
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dmub_replay.c b/drivers/gpu/drm/amd/display/dc/dce/dmub_replay.c
index 9e2a473a8852..f9542edff14b 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dmub_replay.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dmub_replay.c
@@ -169,6 +169,7 @@ static bool dmub_replay_copy_settings(struct dmub_replay *dmub,
 	copy_settings_data->max_deviation_line			= link->dpcd_caps.pr_info.max_deviation_line;
 	copy_settings_data->smu_optimizations_en		= link->replay_settings.replay_smu_opt_enable;
 	copy_settings_data->replay_timing_sync_supported = link->replay_settings.config.replay_timing_sync_supported;
+	copy_settings_data->replay_support_fast_resync_in_ultra_sleep_mode = link->replay_settings.config.replay_support_fast_resync_in_ultra_sleep_mode;
 
 	copy_settings_data->debug.bitfields.enable_ips_visual_confirm = dc->dc->debug.enable_ips_visual_confirm;
 
diff --git a/drivers/gpu/drm/amd/display/dc/dm_services.h b/drivers/gpu/drm/amd/display/dc/dm_services.h
index 7b398d4f4439..fbbf9c757b3c 100644
--- a/drivers/gpu/drm/amd/display/dc/dm_services.h
+++ b/drivers/gpu/drm/amd/display/dc/dm_services.h
@@ -277,12 +277,13 @@ void dm_perf_trace_timestamp(const char *func_name, unsigned int line, struct dc
 /*
  * SMU message tracing
  */
-void dm_trace_smu_msg(uint32_t msg_id, uint32_t param_in, struct dc_context *ctx);
-void dm_trace_smu_delay(uint32_t delay, struct dc_context *ctx);
-
-#define TRACE_SMU_MSG(msg_id, param_in, ctx)	dm_trace_smu_msg(msg_id, param_in, ctx)
-#define TRACE_SMU_DELAY(response_delay, ctx)	dm_trace_smu_delay(response_delay, ctx)
+void dm_trace_smu_enter(uint32_t msg_id, uint32_t param_in, unsigned int delay, struct dc_context *ctx);
+void dm_trace_smu_exit(bool success, uint32_t response, struct dc_context *ctx);
 
+#define TRACE_SMU_MSG_DELAY(msg_id, param_in, delay, ctx)	dm_trace_smu_enter(msg_id, param_in, delay, ctx)
+#define TRACE_SMU_MSG(msg_id, param_in, ctx)	dm_trace_smu_enter(msg_id, param_in, 0, ctx)
+#define TRACE_SMU_MSG_ENTER(msg_id, param_in, ctx)	dm_trace_smu_enter(msg_id, param_in, 0, ctx)
+#define TRACE_SMU_MSG_EXIT(success, response, ctx)	dm_trace_smu_exit(success, response, ctx)
 
 /*
  * DMUB Interfaces
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn31/dcn31_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn31/dcn31_fpu.c
index 17a21bcbde17..1a28061bb9ff 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn31/dcn31_fpu.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn31/dcn31_fpu.c
@@ -808,6 +808,8 @@ void dcn316_update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_param
 
 int dcn_get_max_non_odm_pix_rate_100hz(struct _vcs_dpi_soc_bounding_box_st *soc)
 {
+	dc_assert_fp_enabled();
+
 	return soc->clock_limits[0].dispclk_mhz * 10000.0 / (1.0 + soc->dcn_downspread_percent / 100.0);
 }
 
@@ -815,6 +817,8 @@ int dcn_get_approx_det_segs_required_for_pstate(
 		struct _vcs_dpi_soc_bounding_box_st *soc,
 		int pix_clk_100hz, int bpp, int seg_size_kb)
 {
+	dc_assert_fp_enabled();
+
 	/* Roughly calculate required crb to hide latency. In practice there is slightly
 	 * more buffer available for latency hiding
 	 */
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.c
index c9dd920744c9..817a370e80a7 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn35/dcn35_fpu.c
@@ -445,6 +445,8 @@ int dcn35_populate_dml_pipes_from_context_fpu(struct dc *dc,
 	bool upscaled = false;
 	const unsigned int max_allowed_vblank_nom = 1023;
 
+	dc_assert_fp_enabled();
+
 	dcn31_populate_dml_pipes_from_context(dc, context, pipes,
 					      validate_mode);
 
@@ -498,9 +500,7 @@ int dcn35_populate_dml_pipes_from_context_fpu(struct dc *dc,
 
 		pipes[pipe_cnt].pipe.src.unbounded_req_mode = false;
 
-		DC_FP_START();
 		dcn31_zero_pipe_dcc_fraction(pipes, pipe_cnt);
-		DC_FP_END();
 
 		pipes[pipe_cnt].pipe.dest.vfront_porch = timing->v_front_porch;
 		pipes[pipe_cnt].pipe.src.dcc_rate = 3;
@@ -581,6 +581,8 @@ void dcn35_decide_zstate_support(struct dc *dc, struct dc_state *context)
 	unsigned int i, plane_count = 0;
 	DC_LOGGER_INIT(dc->ctx->logger);
 
+	dc_assert_fp_enabled();
+
 	for (i = 0; i < dc->res_pool->pipe_count; i++) {
 		if (context->res_ctx.pipe_ctx[i].plane_state)
 			plane_count++;
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn351/dcn351_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn351/dcn351_fpu.c
index 8cda18ce1a76..77023b619f1e 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn351/dcn351_fpu.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn351/dcn351_fpu.c
@@ -478,6 +478,8 @@ int dcn351_populate_dml_pipes_from_context_fpu(struct dc *dc,
 	bool upscaled = false;
 	const unsigned int max_allowed_vblank_nom = 1023;
 
+	dc_assert_fp_enabled();
+
 	dcn31_populate_dml_pipes_from_context(dc, context, pipes,
 					      validate_mode);
 
@@ -531,9 +533,7 @@ int dcn351_populate_dml_pipes_from_context_fpu(struct dc *dc,
 
 		pipes[pipe_cnt].pipe.src.unbounded_req_mode = false;
 
-		DC_FP_START();
 		dcn31_zero_pipe_dcc_fraction(pipes, pipe_cnt);
-		DC_FP_END();
 
 		pipes[pipe_cnt].pipe.dest.vfront_porch = timing->v_front_porch;
 		pipes[pipe_cnt].pipe.src.dcc_rate = 3;
diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_pmo/dml2_pmo_dcn3.c b/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_pmo/dml2_pmo_dcn3.c
index e763c8e45da8..1b9579a32ff2 100644
--- a/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_pmo/dml2_pmo_dcn3.c
+++ b/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_pmo/dml2_pmo_dcn3.c
@@ -48,18 +48,19 @@ static void set_reserved_time_on_all_planes_with_stream_index(struct display_con
 
 static void remove_duplicates(double *list_a, int *list_a_size)
 {
-	int cur_element = 0;
-	// For all elements b[i] in list_b[]
-	while (cur_element < *list_a_size - 1) {
-		if (list_a[cur_element] == list_a[cur_element + 1]) {
-			for (int j = cur_element + 1; j < *list_a_size - 1; j++) {
-				list_a[j] = list_a[j + 1];
-			}
-			*list_a_size = *list_a_size - 1;
-		} else {
-			cur_element++;
+	int j = 0;
+
+	if (*list_a_size == 0)
+		return;
+
+	for (int i = 1; i < *list_a_size; i++) {
+		if (list_a[j] != list_a[i]) {
+			j++;
+			list_a[j] = list_a[i];
 		}
 	}
+
+	*list_a_size = j + 1;
 }
 
 static bool increase_mpc_combine_factor(unsigned int *mpc_combine_factor, unsigned int limit)
diff --git a/drivers/gpu/drm/amd/display/dc/hubbub/dcn32/dcn32_hubbub.c b/drivers/gpu/drm/amd/display/dc/hubbub/dcn32/dcn32_hubbub.c
index 92957398ac0a..4d4ca6d77bbd 100644
--- a/drivers/gpu/drm/amd/display/dc/hubbub/dcn32/dcn32_hubbub.c
+++ b/drivers/gpu/drm/amd/display/dc/hubbub/dcn32/dcn32_hubbub.c
@@ -28,6 +28,7 @@
 #include "dcn32_hubbub.h"
 #include "dm_services.h"
 #include "reg_helper.h"
+#include "dal_asic_id.h"
 
 
 #define CTX \
@@ -72,6 +73,14 @@ static void dcn32_init_crb(struct hubbub *hubbub)
 	REG_UPDATE(DCHUBBUB_DEBUG_CTRL_0, DET_DEPTH, 0x47F);
 }
 
+static void hubbub32_set_sdp_control(struct hubbub *hubbub, bool dc_control)
+{
+	struct dcn20_hubbub *hubbub2 = TO_DCN20_HUBBUB(hubbub);
+
+	REG_UPDATE(DCHUBBUB_SDPIF_CFG0,
+			SDPIF_PORT_CONTROL, dc_control);
+}
+
 void hubbub32_set_request_limit(struct hubbub *hubbub, int memory_channel_count, int words_per_channel)
 {
 	struct dcn20_hubbub *hubbub2 = TO_DCN20_HUBBUB(hubbub);
@@ -754,8 +763,18 @@ static bool hubbub32_program_watermarks(
 		unsigned int refclk_mhz,
 		bool safe_to_lower)
 {
+	struct dc *dc = hubbub->ctx->dc;
 	bool wm_pending = false;
 
+	if (!safe_to_lower && dc->debug.disable_stutter_for_wm_program &&
+			(ASICREV_IS_GC_11_0_0(dc->ctx->asic_id.hw_internal_rev) ||
+			ASICREV_IS_GC_11_0_3(dc->ctx->asic_id.hw_internal_rev))) {
+		/* before raising watermarks, SDP control give to DF, stutter must be disabled */
+		wm_pending = true;
+		hubbub32_set_sdp_control(hubbub, false);
+		hubbub1_allow_self_refresh_control(hubbub, false);
+	}
+
 	if (hubbub32_program_urgent_watermarks(hubbub, watermarks, refclk_mhz, safe_to_lower))
 		wm_pending = true;
 
@@ -786,10 +805,20 @@ static bool hubbub32_program_watermarks(
 	REG_UPDATE(DCHUBBUB_ARB_DF_REQ_OUTSTAND,
 			DCHUBBUB_ARB_MIN_REQ_OUTSTAND, 0x1FF);*/
 
-	if (safe_to_lower || hubbub->ctx->dc->debug.disable_stutter)
-		hubbub1_allow_self_refresh_control(hubbub, !hubbub->ctx->dc->debug.disable_stutter);
+	if (safe_to_lower) {
+		/* after lowering watermarks, stutter setting is restored, SDP control given to DC */
+		hubbub1_allow_self_refresh_control(hubbub, !dc->debug.disable_stutter);
+
+		if (dc->debug.disable_stutter_for_wm_program &&
+				(ASICREV_IS_GC_11_0_0(dc->ctx->asic_id.hw_internal_rev) ||
+				ASICREV_IS_GC_11_0_3(dc->ctx->asic_id.hw_internal_rev))) {
+			hubbub32_set_sdp_control(hubbub, true);
+		}
+	} else if (dc->debug.disable_stutter) {
+		hubbub1_allow_self_refresh_control(hubbub, !dc->debug.disable_stutter);
+	}
 
-	hubbub32_force_usr_retraining_allow(hubbub, hubbub->ctx->dc->debug.force_usr_allow);
+	hubbub32_force_usr_retraining_allow(hubbub, dc->debug.force_usr_allow);
 
 	return wm_pending;
 }
@@ -974,8 +1003,7 @@ void hubbub32_init(struct hubbub *hubbub)
 	ignore the "df_pre_cstate_req" from the SDP port control.
 	only the DCN will determine when to connect the SDP port
 	*/
-	REG_UPDATE(DCHUBBUB_SDPIF_CFG0,
-			SDPIF_PORT_CONTROL, 1);
+	hubbub32_set_sdp_control(hubbub, true);
 	/*Set SDP's max outstanding request to 512
 	must set the register back to 0 (max outstanding = 256) in zero frame buffer mode*/
 	REG_UPDATE(DCHUBBUB_SDPIF_CFG1,
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c
index 74f5e05f9cb4..e9fe97f0c4ea 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c
@@ -3347,7 +3347,7 @@ void dcn10_prepare_bandwidth(
 			context,
 			false);
 
-	dc->wm_optimized_required = hubbub->funcs->program_watermarks(hubbub,
+	dc->optimized_required = hubbub->funcs->program_watermarks(hubbub,
 			&context->bw_ctx.bw.dcn.watermarks,
 			dc->res_pool->ref_clocks.dchub_ref_clock_inKhz / 1000,
 			true);
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 417f2679723e..9477c9f9e196 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
@@ -1982,10 +1982,8 @@ static void dcn20_program_pipe(
 	 * updating on slave planes
 	 */
 	if (pipe_ctx->update_flags.bits.enable ||
-		pipe_ctx->update_flags.bits.plane_changed ||
-		pipe_ctx->stream->update_flags.bits.out_tf ||
-		(pipe_ctx->plane_state &&
-			pipe_ctx->plane_state->update_flags.bits.output_tf_change))
+	    pipe_ctx->update_flags.bits.plane_changed ||
+	    pipe_ctx->stream->update_flags.bits.out_tf)
 		hws->funcs.set_output_transfer_func(dc, pipe_ctx, pipe_ctx->stream);
 
 	/* If the pipe has been enabled or has a different opp, we
@@ -2390,10 +2388,10 @@ void dcn20_prepare_bandwidth(
 	}
 
 	/* program dchubbub watermarks:
-	 * For assigning wm_optimized_required, use |= operator since we don't want
+	 * For assigning optimized_required, use |= operator since we don't want
 	 * to clear the value if the optimize has not happened yet
 	 */
-	dc->wm_optimized_required |= hubbub->funcs->program_watermarks(hubbub,
+	dc->optimized_required |= hubbub->funcs->program_watermarks(hubbub,
 					&context->bw_ctx.bw.dcn.watermarks,
 					dc->res_pool->ref_clocks.dchub_ref_clock_inKhz / 1000,
 					false);
@@ -2406,10 +2404,10 @@ void dcn20_prepare_bandwidth(
 	if (hubbub->funcs->program_compbuf_size) {
 		if (context->bw_ctx.dml.ip.min_comp_buffer_size_kbytes) {
 			compbuf_size_kb = context->bw_ctx.dml.ip.min_comp_buffer_size_kbytes;
-			dc->wm_optimized_required |= (compbuf_size_kb != dc->current_state->bw_ctx.dml.ip.min_comp_buffer_size_kbytes);
+			dc->optimized_required |= (compbuf_size_kb != dc->current_state->bw_ctx.dml.ip.min_comp_buffer_size_kbytes);
 		} else {
 			compbuf_size_kb = context->bw_ctx.bw.dcn.compbuf_size_kb;
-			dc->wm_optimized_required |= (compbuf_size_kb != dc->current_state->bw_ctx.bw.dcn.compbuf_size_kb);
+			dc->optimized_required |= (compbuf_size_kb != dc->current_state->bw_ctx.bw.dcn.compbuf_size_kb);
 		}
 
 		hubbub->funcs->program_compbuf_size(hubbub, compbuf_size_kb, false);
@@ -3131,7 +3129,8 @@ void dcn20_fpga_init_hw(struct dc *dc)
 		res_pool->dccg->funcs->dccg_init(res_pool->dccg);
 
 	//Enable ability to power gate / don't force power on permanently
-	hws->funcs.enable_power_gating_plane(hws, true);
+	if (hws->funcs.enable_power_gating_plane)
+		hws->funcs.enable_power_gating_plane(hws, true);
 
 	// Specific to FPGA dccg and registers
 	REG_WRITE(RBBMIF_TIMEOUT_DIS, 0xFFFFFFFF);
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 1b0b772fc5dd..7c276c319086 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
@@ -1383,22 +1383,22 @@ void dcn401_prepare_bandwidth(struct dc *dc,
 			false);
 
 	/* program dchubbub watermarks:
-	 * For assigning wm_optimized_required, use |= operator since we don't want
+	 * For assigning optimized_required, use |= operator since we don't want
 	 * to clear the value if the optimize has not happened yet
 	 */
-	dc->wm_optimized_required |= hubbub->funcs->program_watermarks(hubbub,
+	dc->optimized_required |= hubbub->funcs->program_watermarks(hubbub,
 					&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);
+		dc->optimized_required |= hubbub->funcs->program_arbiter(hubbub, &context->bw_ctx.bw.dcn.arb_regs, false);
 	}
 
 	/* decrease compbuf size */
 	if (hubbub->funcs->program_compbuf_segments) {
 		compbuf_size = context->bw_ctx.bw.dcn.arb_regs.compbuf_size;
-		dc->wm_optimized_required |= (compbuf_size != dc->current_state->bw_ctx.bw.dcn.arb_regs.compbuf_size);
+		dc->optimized_required |= (compbuf_size != dc->current_state->bw_ctx.bw.dcn.arb_regs.compbuf_size);
 
 		hubbub->funcs->program_compbuf_segments(hubbub, compbuf_size, false);
 	}
@@ -2032,10 +2032,8 @@ void dcn401_program_pipe(
 	 * updating on slave planes
 	 */
 	if (pipe_ctx->update_flags.bits.enable ||
-		pipe_ctx->update_flags.bits.plane_changed ||
-		pipe_ctx->stream->update_flags.bits.out_tf ||
-		(pipe_ctx->plane_state &&
-			pipe_ctx->plane_state->update_flags.bits.output_tf_change))
+	    pipe_ctx->update_flags.bits.plane_changed ||
+	    pipe_ctx->stream->update_flags.bits.out_tf)
 		hws->funcs.set_output_transfer_func(dc, pipe_ctx, pipe_ctx->stream);
 
 	/* If the pipe has been enabled or has a different opp, we
diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.c
index 8b7b87b21c2e..5e806edbb9f6 100644
--- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.c
+++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.c
@@ -703,6 +703,20 @@ bool edp_setup_psr(struct dc_link *link,
 	if (!link)
 		return false;
 
+	/* This is a workaround: some vendors require the source to
+	 * read the PSR cap; otherwise, the vendor's PSR feature will
+	 * fall back to its default behavior, causing a misconfiguration
+	 * of this feature.
+	 */
+	if (link->panel_config.psr.read_psrcap_again) {
+		dm_helpers_dp_read_dpcd(
+			link->ctx,
+			link,
+			DP_PSR_SUPPORT,
+			&link->dpcd_caps.psr_info.psr_version,
+			sizeof(link->dpcd_caps.psr_info.psr_version));
+	}
+
 	//Clear PSR cfg
 	memset(&psr_configuration, 0, sizeof(psr_configuration));
 	dm_helpers_dp_write_dpcd(
diff --git a/drivers/gpu/drm/amd/display/dc/resource/dce100/dce100_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dce100/dce100_resource.c
index 3a51be63f020..c4b4dc3ad8c9 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dce100/dce100_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/resource/dce100/dce100_resource.c
@@ -29,6 +29,7 @@
 #include "stream_encoder.h"
 
 #include "resource.h"
+#include "clk_mgr.h"
 #include "include/irq_service_interface.h"
 #include "virtual/virtual_stream_encoder.h"
 #include "dce110/dce110_resource.h"
@@ -836,17 +837,24 @@ static enum dc_status build_mapped_resource(
 	return DC_OK;
 }
 
-static enum dc_status dce100_validate_bandwidth(
+enum dc_status dce100_validate_bandwidth(
 	struct dc  *dc,
 	struct dc_state *context,
 	enum dc_validate_mode validate_mode)
 {
 	int i;
 	bool at_least_one_pipe = false;
+	struct dc_stream_state *stream = NULL;
+	const uint32_t max_pix_clk_khz = max(dc->clk_mgr->clks.max_supported_dispclk_khz, 400000);
 
 	for (i = 0; i < dc->res_pool->pipe_count; i++) {
-		if (context->res_ctx.pipe_ctx[i].stream)
+		stream = context->res_ctx.pipe_ctx[i].stream;
+		if (stream) {
 			at_least_one_pipe = true;
+
+			if (stream->timing.pix_clk_100hz >= max_pix_clk_khz * 10)
+				return DC_FAIL_BANDWIDTH_VALIDATE;
+		}
 	}
 
 	if (at_least_one_pipe) {
@@ -854,7 +862,16 @@ static enum dc_status dce100_validate_bandwidth(
 		context->bw_ctx.bw.dce.dispclk_khz = 681000;
 		context->bw_ctx.bw.dce.yclk_khz = 250000 * MEMORY_TYPE_MULTIPLIER_CZ;
 	} else {
-		context->bw_ctx.bw.dce.dispclk_khz = 0;
+		/* On DCE 6.0 and 6.4 the PLL0 is both the display engine clock and
+		 * the DP clock, and shouldn't be turned off. Just select the display
+		 * clock value from its low power mode.
+		 */
+		if (dc->ctx->dce_version == DCE_VERSION_6_0 ||
+			dc->ctx->dce_version == DCE_VERSION_6_4)
+			context->bw_ctx.bw.dce.dispclk_khz = 352000;
+		else
+			context->bw_ctx.bw.dce.dispclk_khz = 0;
+
 		context->bw_ctx.bw.dce.yclk_khz = 0;
 	}
 
@@ -881,7 +898,7 @@ static bool dce100_validate_surface_sets(
 	return true;
 }
 
-static enum dc_status dce100_validate_global(
+enum dc_status dce100_validate_global(
 		struct dc  *dc,
 		struct dc_state *context)
 {
diff --git a/drivers/gpu/drm/amd/display/dc/resource/dce100/dce100_resource.h b/drivers/gpu/drm/amd/display/dc/resource/dce100/dce100_resource.h
index fecab7c560f5..dd150a4b4610 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dce100/dce100_resource.h
+++ b/drivers/gpu/drm/amd/display/dc/resource/dce100/dce100_resource.h
@@ -41,6 +41,15 @@ struct resource_pool *dce100_create_resource_pool(
 
 enum dc_status dce100_validate_plane(const struct dc_plane_state *plane_state, struct dc_caps *caps);
 
+enum dc_status dce100_validate_global(
+		struct dc  *dc,
+		struct dc_state *context);
+
+enum dc_status dce100_validate_bandwidth(
+		struct dc  *dc,
+		struct dc_state *context,
+		enum dc_validate_mode validate_mode);
+
 enum dc_status dce100_add_stream_to_ctx(
 		struct dc *dc,
 		struct dc_state *new_ctx,
diff --git a/drivers/gpu/drm/amd/display/dc/resource/dce60/dce60_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dce60/dce60_resource.c
index c164d2500c2a..b75be6ad64f6 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dce60/dce60_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/resource/dce60/dce60_resource.c
@@ -34,6 +34,7 @@
 #include "stream_encoder.h"
 
 #include "resource.h"
+#include "clk_mgr.h"
 #include "include/irq_service_interface.h"
 #include "irq/dce60/irq_service_dce60.h"
 #include "dce110/dce110_timing_generator.h"
@@ -403,13 +404,13 @@ static const struct dc_plane_cap plane_cap = {
 	},
 
 	.max_upscale_factor = {
-			.argb8888 = 16000,
+			.argb8888 = 1,
 			.nv12 = 1,
 			.fp16 = 1
 	},
 
 	.max_downscale_factor = {
-			.argb8888 = 250,
+			.argb8888 = 1,
 			.nv12 = 1,
 			.fp16 = 1
 	}
@@ -863,70 +864,6 @@ static void dce60_resource_destruct(struct dce110_resource_pool *pool)
 	}
 }
 
-static enum dc_status dce60_validate_bandwidth(
-	struct dc *dc,
-	struct dc_state *context,
-	enum dc_validate_mode validate_mode)
-{
-	int i;
-	bool at_least_one_pipe = false;
-
-	for (i = 0; i < dc->res_pool->pipe_count; i++) {
-		if (context->res_ctx.pipe_ctx[i].stream)
-			at_least_one_pipe = true;
-	}
-
-	if (at_least_one_pipe) {
-		/* TODO implement when needed but for now hardcode max value*/
-		context->bw_ctx.bw.dce.dispclk_khz = 681000;
-		context->bw_ctx.bw.dce.yclk_khz = 250000 * MEMORY_TYPE_MULTIPLIER_CZ;
-	} else {
-		/* On DCE 6.0 and 6.4 the PLL0 is both the display engine clock and
-		 * the DP clock, and shouldn't be turned off. Just select the display
-		 * clock value from its low power mode.
-		 */
-		if (dc->ctx->dce_version == DCE_VERSION_6_0 ||
-			dc->ctx->dce_version == DCE_VERSION_6_4)
-			context->bw_ctx.bw.dce.dispclk_khz = 352000;
-		else
-			context->bw_ctx.bw.dce.dispclk_khz = 0;
-
-		context->bw_ctx.bw.dce.yclk_khz = 0;
-	}
-
-	return DC_OK;
-}
-
-static bool dce60_validate_surface_sets(
-		struct dc_state *context)
-{
-	int i;
-
-	for (i = 0; i < context->stream_count; i++) {
-		if (context->stream_status[i].plane_count == 0)
-			continue;
-
-		if (context->stream_status[i].plane_count > 1)
-			return false;
-
-		if (context->stream_status[i].plane_states[0]->format
-				>= SURFACE_PIXEL_FORMAT_VIDEO_BEGIN)
-			return false;
-	}
-
-	return true;
-}
-
-static enum dc_status dce60_validate_global(
-		struct dc *dc,
-		struct dc_state *context)
-{
-	if (!dce60_validate_surface_sets(context))
-		return DC_FAIL_SURFACE_VALIDATE;
-
-	return DC_OK;
-}
-
 static void dce60_destroy_resource_pool(struct resource_pool **pool)
 {
 	struct dce110_resource_pool *dce110_pool = TO_DCE110_RES_POOL(*pool);
@@ -940,10 +877,10 @@ static const struct resource_funcs dce60_res_pool_funcs = {
 	.destroy = dce60_destroy_resource_pool,
 	.link_enc_create = dce60_link_encoder_create,
 	.panel_cntl_create = dce60_panel_cntl_create,
-	.validate_bandwidth = dce60_validate_bandwidth,
+	.validate_bandwidth = dce100_validate_bandwidth,
 	.validate_plane = dce100_validate_plane,
 	.add_stream_to_ctx = dce100_add_stream_to_ctx,
-	.validate_global = dce60_validate_global,
+	.validate_global = dce100_validate_global,
 	.find_first_free_match_stream_enc_for_link = dce100_find_first_free_match_stream_enc_for_link
 };
 
diff --git a/drivers/gpu/drm/amd/display/dc/resource/dce80/dce80_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dce80/dce80_resource.c
index 3e8b0ac11d90..5b7769745202 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dce80/dce80_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/resource/dce80/dce80_resource.c
@@ -32,6 +32,7 @@
 #include "stream_encoder.h"
 
 #include "resource.h"
+#include "clk_mgr.h"
 #include "include/irq_service_interface.h"
 #include "irq/dce80/irq_service_dce80.h"
 #include "dce110/dce110_timing_generator.h"
@@ -869,61 +870,6 @@ static void dce80_resource_destruct(struct dce110_resource_pool *pool)
 	}
 }
 
-static enum dc_status dce80_validate_bandwidth(
-	struct dc *dc,
-	struct dc_state *context,
-	enum dc_validate_mode validate_mode)
-{
-	int i;
-	bool at_least_one_pipe = false;
-
-	for (i = 0; i < dc->res_pool->pipe_count; i++) {
-		if (context->res_ctx.pipe_ctx[i].stream)
-			at_least_one_pipe = true;
-	}
-
-	if (at_least_one_pipe) {
-		/* TODO implement when needed but for now hardcode max value*/
-		context->bw_ctx.bw.dce.dispclk_khz = 681000;
-		context->bw_ctx.bw.dce.yclk_khz = 250000 * MEMORY_TYPE_MULTIPLIER_CZ;
-	} else {
-		context->bw_ctx.bw.dce.dispclk_khz = 0;
-		context->bw_ctx.bw.dce.yclk_khz = 0;
-	}
-
-	return DC_OK;
-}
-
-static bool dce80_validate_surface_sets(
-		struct dc_state *context)
-{
-	int i;
-
-	for (i = 0; i < context->stream_count; i++) {
-		if (context->stream_status[i].plane_count == 0)
-			continue;
-
-		if (context->stream_status[i].plane_count > 1)
-			return false;
-
-		if (context->stream_status[i].plane_states[0]->format
-				>= SURFACE_PIXEL_FORMAT_VIDEO_BEGIN)
-			return false;
-	}
-
-	return true;
-}
-
-static enum dc_status dce80_validate_global(
-		struct dc *dc,
-		struct dc_state *context)
-{
-	if (!dce80_validate_surface_sets(context))
-		return DC_FAIL_SURFACE_VALIDATE;
-
-	return DC_OK;
-}
-
 static void dce80_destroy_resource_pool(struct resource_pool **pool)
 {
 	struct dce110_resource_pool *dce110_pool = TO_DCE110_RES_POOL(*pool);
@@ -937,10 +883,10 @@ static const struct resource_funcs dce80_res_pool_funcs = {
 	.destroy = dce80_destroy_resource_pool,
 	.link_enc_create = dce80_link_encoder_create,
 	.panel_cntl_create = dce80_panel_cntl_create,
-	.validate_bandwidth = dce80_validate_bandwidth,
+	.validate_bandwidth = dce100_validate_bandwidth,
 	.validate_plane = dce100_validate_plane,
 	.add_stream_to_ctx = dce100_add_stream_to_ctx,
-	.validate_global = dce80_validate_global,
+	.validate_global = dce100_validate_global,
 	.find_first_free_match_stream_enc_for_link = dce100_find_first_free_match_stream_enc_for_link
 };
 
diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn314/dcn314_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn314/dcn314_resource.c
index 663c49cce4aa..d4917a35b991 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dcn314/dcn314_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/resource/dcn314/dcn314_resource.c
@@ -927,6 +927,7 @@ static const struct dc_debug_options debug_defaults_drv = {
 	.enable_legacy_fast_update = true,
 	.using_dml2 = false,
 	.disable_dsc_power_gate = true,
+	.min_disp_clk_khz = 100000,
 };
 
 static const struct dc_panel_config panel_config_defaults = {
diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.c
index 8f80ccb846d7..3965a7f1b64b 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.c
@@ -739,6 +739,7 @@ static const struct dc_debug_options debug_defaults_drv = {
 	.fpo_vactive_min_active_margin_us = 200,
 	.fpo_vactive_max_blank_us = 1000,
 	.enable_legacy_fast_update = false,
+	.disable_stutter_for_wm_program = true
 };
 
 static struct dce_aux *dcn32_aux_engine_create(
diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.h b/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.h
index 20d714596021..99f0432288b4 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.h
+++ b/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.h
@@ -1230,7 +1230,8 @@ unsigned int dcn32_get_max_hw_cursor_size(const struct dc *dc,
       SR(DCHUBBUB_ARB_MALL_CNTL),                                              \
       SR(DCN_VM_FAULT_ADDR_MSB), SR(DCN_VM_FAULT_ADDR_LSB),                    \
       SR(DCN_VM_FAULT_CNTL), SR(DCN_VM_FAULT_STATUS),                          \
-      SR(SDPIF_REQUEST_RATE_LIMIT)
+      SR(SDPIF_REQUEST_RATE_LIMIT),                                            \
+      SR(DCHUBBUB_SDPIF_CFG0)
 
 /* DCCG */
 
diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c
index 07552445e424..fff57f23f4f7 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c
@@ -1760,6 +1760,20 @@ enum dc_status dcn35_patch_unknown_plane_state(struct dc_plane_state *plane_stat
 }
 
 
+static int populate_dml_pipes_from_context_fpu(struct dc *dc,
+					       struct dc_state *context,
+					       display_e2e_pipe_params_st *pipes,
+					       enum dc_validate_mode validate_mode)
+{
+	int ret;
+
+	DC_FP_START();
+	ret = dcn35_populate_dml_pipes_from_context_fpu(dc, context, pipes, validate_mode);
+	DC_FP_END();
+
+	return ret;
+}
+
 static struct resource_funcs dcn35_res_pool_funcs = {
 	.destroy = dcn35_destroy_resource_pool,
 	.link_enc_create = dcn35_link_encoder_create,
@@ -1770,7 +1784,7 @@ static struct resource_funcs dcn35_res_pool_funcs = {
 	.validate_bandwidth = dcn35_validate_bandwidth,
 	.calculate_wm_and_dlg = NULL,
 	.update_soc_for_wm_a = dcn31_update_soc_for_wm_a,
-	.populate_dml_pipes = dcn35_populate_dml_pipes_from_context_fpu,
+	.populate_dml_pipes = populate_dml_pipes_from_context_fpu,
 	.acquire_free_pipe_as_secondary_dpp_pipe = dcn20_acquire_free_pipe_for_layer,
 	.release_pipe = dcn20_release_pipe,
 	.add_stream_to_ctx = dcn30_add_stream_to_ctx,
diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn351/dcn351_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn351/dcn351_resource.c
index cb0478a9a34d..0abd163b425e 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dcn351/dcn351_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/resource/dcn351/dcn351_resource.c
@@ -1732,6 +1732,21 @@ static enum dc_status dcn351_validate_bandwidth(struct dc *dc,
 	return out ? DC_OK : DC_FAIL_BANDWIDTH_VALIDATE;
 }
 
+static int populate_dml_pipes_from_context_fpu(struct dc *dc,
+					       struct dc_state *context,
+					       display_e2e_pipe_params_st *pipes,
+					       enum dc_validate_mode validate_mode)
+{
+	int ret;
+
+	DC_FP_START();
+	ret = dcn351_populate_dml_pipes_from_context_fpu(dc, context, pipes, validate_mode);
+	DC_FP_END();
+
+	return ret;
+
+}
+
 static struct resource_funcs dcn351_res_pool_funcs = {
 	.destroy = dcn351_destroy_resource_pool,
 	.link_enc_create = dcn35_link_encoder_create,
@@ -1742,7 +1757,7 @@ static struct resource_funcs dcn351_res_pool_funcs = {
 	.validate_bandwidth = dcn351_validate_bandwidth,
 	.calculate_wm_and_dlg = NULL,
 	.update_soc_for_wm_a = dcn31_update_soc_for_wm_a,
-	.populate_dml_pipes = dcn351_populate_dml_pipes_from_context_fpu,
+	.populate_dml_pipes = populate_dml_pipes_from_context_fpu,
 	.acquire_free_pipe_as_secondary_dpp_pipe = dcn20_acquire_free_pipe_for_layer,
 	.release_pipe = dcn20_release_pipe,
 	.add_stream_to_ctx = dcn30_add_stream_to_ctx,
diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn36/dcn36_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn36/dcn36_resource.c
index 126090c9bb8a..ca125ee6c2fb 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dcn36/dcn36_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/resource/dcn36/dcn36_resource.c
@@ -1734,6 +1734,20 @@ static enum dc_status dcn35_validate_bandwidth(struct dc *dc,
 }
 
 
+static int populate_dml_pipes_from_context_fpu(struct dc *dc,
+					       struct dc_state *context,
+					       display_e2e_pipe_params_st *pipes,
+					       enum dc_validate_mode validate_mode)
+{
+	int ret;
+
+	DC_FP_START();
+	ret = dcn35_populate_dml_pipes_from_context_fpu(dc, context, pipes, validate_mode);
+	DC_FP_END();
+
+	return ret;
+}
+
 static struct resource_funcs dcn36_res_pool_funcs = {
 	.destroy = dcn36_destroy_resource_pool,
 	.link_enc_create = dcn35_link_encoder_create,
@@ -1744,7 +1758,7 @@ static struct resource_funcs dcn36_res_pool_funcs = {
 	.validate_bandwidth = dcn35_validate_bandwidth,
 	.calculate_wm_and_dlg = NULL,
 	.update_soc_for_wm_a = dcn31_update_soc_for_wm_a,
-	.populate_dml_pipes = dcn35_populate_dml_pipes_from_context_fpu,
+	.populate_dml_pipes = populate_dml_pipes_from_context_fpu,
 	.acquire_free_pipe_as_secondary_dpp_pipe = dcn20_acquire_free_pipe_for_layer,
 	.release_pipe = dcn20_release_pipe,
 	.add_stream_to_ctx = dcn30_add_stream_to_ctx,
diff --git a/drivers/gpu/drm/amd/display/dc/sspl/dc_spl.c b/drivers/gpu/drm/amd/display/dc/sspl/dc_spl.c
index 55b929ca7982..b1fb0f8a253a 100644
--- a/drivers/gpu/drm/amd/display/dc/sspl/dc_spl.c
+++ b/drivers/gpu/drm/amd/display/dc/sspl/dc_spl.c
@@ -641,16 +641,16 @@ static void spl_calculate_inits_and_viewports(struct spl_in *spl_in,
 		/* this gives the direction of the cositing (negative will move
 		 * left, right otherwise)
 		 */
-		int sign = 1;
+		int h_sign = flip_horz_scan_dir ? -1 : 1;
+		int v_sign = flip_vert_scan_dir ? -1 : 1;
 
 		switch (spl_in->basic_in.cositing) {
-
 		case CHROMA_COSITING_TOPLEFT:
-			init_adj_h = spl_fixpt_from_fraction(sign, 4);
-			init_adj_v = spl_fixpt_from_fraction(sign, 4);
+			init_adj_h = spl_fixpt_from_fraction(h_sign, 4);
+			init_adj_v = spl_fixpt_from_fraction(v_sign, 4);
 			break;
 		case CHROMA_COSITING_LEFT:
-			init_adj_h = spl_fixpt_from_fraction(sign, 4);
+			init_adj_h = spl_fixpt_from_fraction(h_sign, 4);
 			init_adj_v = spl_fixpt_zero;
 			break;
 		case CHROMA_COSITING_NONE:
diff --git a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h
index e65747f7f12f..92248224b713 100644
--- a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h
+++ b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h
@@ -4143,9 +4143,13 @@ struct dmub_cmd_replay_copy_settings_data {
 	 */
 	uint8_t hpo_link_enc_inst;
 	/**
+	 * Determines if fast resync in ultra sleep mode is enabled/disabled.
+	 */
+	uint8_t replay_support_fast_resync_in_ultra_sleep_mode;
+	/**
 	 * @pad: Align structure to 4 byte boundary.
 	 */
-	uint8_t pad[2];
+	uint8_t pad[1];
 };
 
 
diff --git a/drivers/gpu/drm/amd/include/asic_reg/dce/dce_6_0_d.h b/drivers/gpu/drm/amd/include/asic_reg/dce/dce_6_0_d.h
index 9de01ae574c0..067eddd9c62d 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/dce/dce_6_0_d.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/dce/dce_6_0_d.h
@@ -4115,6 +4115,7 @@
 #define mmSCL0_SCL_COEF_RAM_CONFLICT_STATUS 0x1B55
 #define mmSCL0_SCL_COEF_RAM_SELECT 0x1B40
 #define mmSCL0_SCL_COEF_RAM_TAP_DATA 0x1B41
+#define mmSCL0_SCL_SCALER_ENABLE 0x1B42
 #define mmSCL0_SCL_CONTROL 0x1B44
 #define mmSCL0_SCL_DEBUG 0x1B6A
 #define mmSCL0_SCL_DEBUG2 0x1B69
@@ -4144,6 +4145,7 @@
 #define mmSCL1_SCL_COEF_RAM_CONFLICT_STATUS 0x1E55
 #define mmSCL1_SCL_COEF_RAM_SELECT 0x1E40
 #define mmSCL1_SCL_COEF_RAM_TAP_DATA 0x1E41
+#define mmSCL1_SCL_SCALER_ENABLE 0x1E42
 #define mmSCL1_SCL_CONTROL 0x1E44
 #define mmSCL1_SCL_DEBUG 0x1E6A
 #define mmSCL1_SCL_DEBUG2 0x1E69
@@ -4173,6 +4175,7 @@
 #define mmSCL2_SCL_COEF_RAM_CONFLICT_STATUS 0x4155
 #define mmSCL2_SCL_COEF_RAM_SELECT 0x4140
 #define mmSCL2_SCL_COEF_RAM_TAP_DATA 0x4141
+#define mmSCL2_SCL_SCALER_ENABLE 0x4142
 #define mmSCL2_SCL_CONTROL 0x4144
 #define mmSCL2_SCL_DEBUG 0x416A
 #define mmSCL2_SCL_DEBUG2 0x4169
@@ -4202,6 +4205,7 @@
 #define mmSCL3_SCL_COEF_RAM_CONFLICT_STATUS 0x4455
 #define mmSCL3_SCL_COEF_RAM_SELECT 0x4440
 #define mmSCL3_SCL_COEF_RAM_TAP_DATA 0x4441
+#define mmSCL3_SCL_SCALER_ENABLE 0x4442
 #define mmSCL3_SCL_CONTROL 0x4444
 #define mmSCL3_SCL_DEBUG 0x446A
 #define mmSCL3_SCL_DEBUG2 0x4469
@@ -4231,6 +4235,7 @@
 #define mmSCL4_SCL_COEF_RAM_CONFLICT_STATUS 0x4755
 #define mmSCL4_SCL_COEF_RAM_SELECT 0x4740
 #define mmSCL4_SCL_COEF_RAM_TAP_DATA 0x4741
+#define mmSCL4_SCL_SCALER_ENABLE 0x4742
 #define mmSCL4_SCL_CONTROL 0x4744
 #define mmSCL4_SCL_DEBUG 0x476A
 #define mmSCL4_SCL_DEBUG2 0x4769
@@ -4260,6 +4265,7 @@
 #define mmSCL5_SCL_COEF_RAM_CONFLICT_STATUS 0x4A55
 #define mmSCL5_SCL_COEF_RAM_SELECT 0x4A40
 #define mmSCL5_SCL_COEF_RAM_TAP_DATA 0x4A41
+#define mmSCL5_SCL_SCALER_ENABLE 0x4A42
 #define mmSCL5_SCL_CONTROL 0x4A44
 #define mmSCL5_SCL_DEBUG 0x4A6A
 #define mmSCL5_SCL_DEBUG2 0x4A69
@@ -4287,6 +4293,7 @@
 #define mmSCL_COEF_RAM_CONFLICT_STATUS 0x1B55
 #define mmSCL_COEF_RAM_SELECT 0x1B40
 #define mmSCL_COEF_RAM_TAP_DATA 0x1B41
+#define mmSCL_SCALER_ENABLE 0x1B42
 #define mmSCL_CONTROL 0x1B44
 #define mmSCL_DEBUG 0x1B6A
 #define mmSCL_DEBUG2 0x1B69
diff --git a/drivers/gpu/drm/amd/include/asic_reg/dce/dce_6_0_sh_mask.h b/drivers/gpu/drm/amd/include/asic_reg/dce/dce_6_0_sh_mask.h
index 2d6a598a6c25..9317a7afa621 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/dce/dce_6_0_sh_mask.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/dce/dce_6_0_sh_mask.h
@@ -8650,6 +8650,8 @@
 #define REGAMMA_LUT_INDEX__REGAMMA_LUT_INDEX__SHIFT 0x00000000
 #define REGAMMA_LUT_WRITE_EN_MASK__REGAMMA_LUT_WRITE_EN_MASK_MASK 0x00000007L
 #define REGAMMA_LUT_WRITE_EN_MASK__REGAMMA_LUT_WRITE_EN_MASK__SHIFT 0x00000000
+#define SCL_SCALER_ENABLE__SCL_SCALE_EN_MASK 0x00000001L
+#define SCL_SCALER_ENABLE__SCL_SCALE_EN__SHIFT 0x00000000
 #define SCL_ALU_CONTROL__SCL_ALU_DISABLE_MASK 0x00000001L
 #define SCL_ALU_CONTROL__SCL_ALU_DISABLE__SHIFT 0x00000000
 #define SCL_BYPASS_CONTROL__SCL_BYPASS_MODE_MASK 0x00000003L
diff --git a/drivers/gpu/drm/amd/include/mes_v11_api_def.h b/drivers/gpu/drm/amd/include/mes_v11_api_def.h
index 15680c3f4970..ab1cfc92dbeb 100644
--- a/drivers/gpu/drm/amd/include/mes_v11_api_def.h
+++ b/drivers/gpu/drm/amd/include/mes_v11_api_def.h
@@ -238,7 +238,8 @@ union MESAPI_SET_HW_RESOURCES {
 				uint32_t enable_mes_sch_stb_log : 1;
 				uint32_t limit_single_process : 1;
 				uint32_t is_strix_tmz_wa_enabled  :1;
-				uint32_t reserved : 13;
+				uint32_t enable_lr_compute_wa : 1;
+				uint32_t reserved : 12;
 			};
 			uint32_t	uint32_t_all;
 		};
diff --git a/drivers/gpu/drm/amd/include/mes_v12_api_def.h b/drivers/gpu/drm/amd/include/mes_v12_api_def.h
index c04bd351b250..69611c7e30e3 100644
--- a/drivers/gpu/drm/amd/include/mes_v12_api_def.h
+++ b/drivers/gpu/drm/amd/include/mes_v12_api_def.h
@@ -287,7 +287,8 @@ union MESAPI_SET_HW_RESOURCES {
 				uint32_t limit_single_process : 1;
 				uint32_t unmapped_doorbell_handling: 2;
 				uint32_t enable_mes_fence_int: 1;
-				uint32_t reserved : 10;
+				uint32_t enable_lr_compute_wa : 1;
+				uint32_t reserved : 9;
 			};
 			uint32_t uint32_all;
 		};
diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_12_ppsmc.h b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_12_ppsmc.h
index aff2776a8b6f..4b066c42e0ec 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_12_ppsmc.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_12_ppsmc.h
@@ -120,7 +120,8 @@
 #define PPSMC_MSG_GetBadPageSeverity                0x5B
 #define PPSMC_MSG_GetSystemMetricsTable             0x5C
 #define PPSMC_MSG_GetSystemMetricsVersion           0x5D
-#define PPSMC_Message_Count                         0x5E
+#define PPSMC_MSG_ResetVCN                          0x5E
+#define PPSMC_Message_Count                         0x5F
 
 //PPSMC Reset Types for driver msg argument
 #define PPSMC_RESET_TYPE_DRIVER_MODE_1_RESET        0x1
diff --git a/drivers/gpu/drm/amd/pm/inc/smu_v13_0_0_pptable.h b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0_0_pptable.h
index 251ed011b3b0..251ed011b3b0 100644
--- a/drivers/gpu/drm/amd/pm/inc/smu_v13_0_0_pptable.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0_0_pptable.h
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c
index 1a1f2a6b2e52..a89075e25717 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c
@@ -288,7 +288,8 @@ int smu_v13_0_check_fw_version(struct smu_context *smu)
 	 * Considering above, we just leave user a verbal message instead
 	 * of halt driver loading.
 	 */
-	if (if_version != smu->smc_driver_if_version) {
+	if (smu->smc_driver_if_version != SMU_IGNORE_IF_VERSION &&
+	    if_version != smu->smc_driver_if_version) {
 		dev_info(adev->dev, "smu driver if version = 0x%08x, smu fw if version = 0x%08x, "
 			 "smu fw program = %d, smu fw version = 0x%08x (%d.%d.%d)\n",
 			 smu->smc_driver_if_version, if_version,
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_12_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_12_ppt.c
index 1842a33b2bce..cb3fea9e8cf3 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_12_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_12_ppt.c
@@ -136,6 +136,7 @@ const struct cmn2asic_msg_mapping smu_v13_0_12_message_map[SMU_MSG_MAX_COUNT] =
 	MSG_MAP(RmaDueToBadPageThreshold,            PPSMC_MSG_RmaDueToBadPageThreshold,        0),
 	MSG_MAP(SetThrottlingPolicy,                 PPSMC_MSG_SetThrottlingPolicy,             0),
 	MSG_MAP(ResetSDMA,                           PPSMC_MSG_ResetSDMA,                       0),
+	MSG_MAP(ResetVCN,                            PPSMC_MSG_ResetVCN,                        0),
 	MSG_MAP(GetStaticMetricsTable,               PPSMC_MSG_GetStaticMetricsTable,           1),
 	MSG_MAP(GetSystemMetricsTable,               PPSMC_MSG_GetSystemMetricsTable,           1),
 };
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 349b6b8be010..285cf7979693 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
@@ -353,6 +353,9 @@ static void smu_v13_0_12_init_caps(struct smu_context *smu)
 		smu_v13_0_6_cap_set(smu, SMU_CAP(PLDM_VERSION));
 	}
 
+	if (fw_ver > 0x04560900)
+		smu_v13_0_6_cap_set(smu, SMU_CAP(VCN_RESET));
+
 	if (fw_ver >= 0x04560700) {
 		if (fw_ver >= 0x04560900) {
 			smu_v13_0_6_cap_set(smu, SMU_CAP(TEMP_METRICS));
@@ -447,8 +450,7 @@ static void smu_v13_0_6_init_caps(struct smu_context *smu)
 	    ((pgm == 4) && (fw_ver >= 0x4557000)))
 		smu_v13_0_6_cap_set(smu, SMU_CAP(SDMA_RESET));
 
-	if (((pgm == 0) && (fw_ver >= 0x00558200)) ||
-	    ((pgm == 4) && (fw_ver >= 0x04557100)))
+	if ((pgm == 0) && (fw_ver >= 0x00558200))
 		smu_v13_0_6_cap_set(smu, SMU_CAP(VCN_RESET));
 }
 
@@ -3930,7 +3932,7 @@ void smu_v13_0_6_set_ppt_funcs(struct smu_context *smu)
 	smu->feature_map = (amdgpu_ip_version(smu->adev, MP1_HWIP, 0) == IP_VERSION(13, 0, 12)) ?
 		smu_v13_0_12_feature_mask_map : smu_v13_0_6_feature_mask_map;
 	smu->table_map = smu_v13_0_6_table_map;
-	smu->smc_driver_if_version = SMU13_0_6_DRIVER_IF_VERSION;
+	smu->smc_driver_if_version = SMU_IGNORE_IF_VERSION;
 	smu->smc_fw_caps |= SMU_FW_CAP_RAS_PRI;
 	smu_v13_0_set_smu_mailbox_registers(smu);
 	smu_v13_0_6_set_temp_funcs(smu);
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.h b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.h
index d588f74b98de..0ae91c8b6d72 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.h
@@ -40,6 +40,8 @@
 #define SMU_IH_INTERRUPT_CONTEXT_ID_FAN_ABNORMAL        0x8
 #define SMU_IH_INTERRUPT_CONTEXT_ID_FAN_RECOVERY        0x9
 
+#define SMU_IGNORE_IF_VERSION 0xFFFFFFFF
+
 #define smu_cmn_init_soft_gpu_metrics(ptr, frev, crev)                   \
 	do {                                                             \
 		typecheck(struct gpu_metrics_v##frev##_##crev *, (ptr)); \
diff --git a/drivers/gpu/drm/amd/ras/rascore/Makefile b/drivers/gpu/drm/amd/ras/rascore/Makefile
new file mode 100644
index 000000000000..e69de29bb2d1
--- /dev/null
+++ b/drivers/gpu/drm/amd/ras/rascore/Makefile
diff --git a/drivers/gpu/drm/amd/ras/rascore/ras_core_status.h b/drivers/gpu/drm/amd/ras/rascore/ras_core_status.h
new file mode 100644
index 000000000000..144fbe4ceb9a
--- /dev/null
+++ b/drivers/gpu/drm/amd/ras/rascore/ras_core_status.h
@@ -0,0 +1,37 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright 2025 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+
+#ifndef __RAS_CORE_STATUS_H__
+#define __RAS_CORE_STATUS_H__
+
+#define RAS_CORE_OK                       0
+#define RAS_CORE_NOT_SUPPORTED            248
+#define RAS_CORE_FAIL_ERROR_QUERY         249
+#define RAS_CORE_FAIL_ERROR_INJECTION     250
+#define RAS_CORE_FAIL_FATAL_RECOVERY      251
+#define RAS_CORE_FAIL_POISON_CONSUMPTION  252
+#define RAS_CORE_FAIL_POISON_CREATION     253
+#define RAS_CORE_FAIL_NO_VALID_BANKS      254
+#define RAS_CORE_GPU_IN_MODE1_RESET       255
+#endif
diff --git a/drivers/gpu/drm/ast/ast_dp.c b/drivers/gpu/drm/ast/ast_dp.c
index 19c04687b0fe..8e650a02c528 100644
--- a/drivers/gpu/drm/ast/ast_dp.c
+++ b/drivers/gpu/drm/ast/ast_dp.c
@@ -134,7 +134,7 @@ static int ast_astdp_read_edid_block(void *data, u8 *buf, unsigned int block, si
 			 * 3. The Delays are often longer a lot when system resume from S3/S4.
 			 */
 			if (j)
-				mdelay(j + 1);
+				msleep(j + 1);
 
 			/* Wait for EDID offset to show up in mirror register */
 			vgacrd7 = ast_get_index_reg(ast, AST_IO_VGACRI, 0xd7);
diff --git a/drivers/gpu/drm/bridge/analogix/anx7625.c b/drivers/gpu/drm/bridge/analogix/anx7625.c
index 609cdb9d371e..6f3fdcb6afdb 100644
--- a/drivers/gpu/drm/bridge/analogix/anx7625.c
+++ b/drivers/gpu/drm/bridge/analogix/anx7625.c
@@ -2678,7 +2678,7 @@ static int anx7625_i2c_probe(struct i2c_client *client)
 		ret = devm_request_threaded_irq(dev, platform->pdata.intp_irq,
 						NULL, anx7625_intr_hpd_isr,
 						IRQF_TRIGGER_FALLING |
-						IRQF_ONESHOT,
+						IRQF_ONESHOT | IRQF_NO_AUTOEN,
 						"anx7625-intp", platform);
 		if (ret) {
 			DRM_DEV_ERROR(dev, "fail to request irq\n");
@@ -2747,8 +2747,10 @@ static int anx7625_i2c_probe(struct i2c_client *client)
 	}
 
 	/* Add work function */
-	if (platform->pdata.intp_irq)
+	if (platform->pdata.intp_irq) {
+		enable_irq(platform->pdata.intp_irq);
 		queue_work(platform->workqueue, &platform->work);
+	}
 
 	if (platform->pdata.audio_en)
 		anx7625_register_audio(dev, platform);
diff --git a/drivers/gpu/drm/bridge/cadence/cdns-mhdp8546-core.c b/drivers/gpu/drm/bridge/cadence/cdns-mhdp8546-core.c
index a614d1384f71..38726ae1bf15 100644
--- a/drivers/gpu/drm/bridge/cadence/cdns-mhdp8546-core.c
+++ b/drivers/gpu/drm/bridge/cadence/cdns-mhdp8546-core.c
@@ -1984,8 +1984,10 @@ static void cdns_mhdp_atomic_enable(struct drm_bridge *bridge,
 	mhdp_state = to_cdns_mhdp_bridge_state(new_state);
 
 	mhdp_state->current_mode = drm_mode_duplicate(bridge->dev, mode);
-	if (!mhdp_state->current_mode)
-		return;
+	if (!mhdp_state->current_mode) {
+		ret = -EINVAL;
+		goto out;
+	}
 
 	drm_mode_set_name(mhdp_state->current_mode);
 
diff --git a/drivers/gpu/drm/bridge/waveshare-dsi.c b/drivers/gpu/drm/bridge/waveshare-dsi.c
index 01c70e7d3d3b..43f4e7412d72 100644
--- a/drivers/gpu/drm/bridge/waveshare-dsi.c
+++ b/drivers/gpu/drm/bridge/waveshare-dsi.c
@@ -147,8 +147,8 @@ static int ws_bridge_probe(struct i2c_client *i2c)
 	int ret;
 
 	ws = devm_drm_bridge_alloc(dev, struct ws_bridge, bridge, &ws_bridge_bridge_funcs);
-	if (!ws)
-		return -ENOMEM;
+	if (IS_ERR(ws))
+		return PTR_ERR(ws);
 
 	ws->dev = dev;
 
diff --git a/drivers/gpu/drm/display/drm_dp_cec.c b/drivers/gpu/drm/display/drm_dp_cec.c
index 3b50d817c839..436bfe9f9081 100644
--- a/drivers/gpu/drm/display/drm_dp_cec.c
+++ b/drivers/gpu/drm/display/drm_dp_cec.c
@@ -42,7 +42,7 @@
  *
  * https://hverkuil.home.xs4all.nl/cec-status.txt
  *
- * Please mail me (hverkuil@xs4all.nl) if you find an adapter that works
+ * Please mail me (hverkuil@kernel.org) if you find an adapter that works
  * and is not yet listed there.
  *
  * Note that the current implementation does not support CEC over an MST hub.
diff --git a/drivers/gpu/drm/drm_gem.c b/drivers/gpu/drm/drm_gem.c
index 8d25cc65707d..f884d155a832 100644
--- a/drivers/gpu/drm/drm_gem.c
+++ b/drivers/gpu/drm/drm_gem.c
@@ -628,7 +628,7 @@ struct page **drm_gem_get_pages(struct drm_gem_object *obj)
 	struct page **pages;
 	struct folio *folio;
 	struct folio_batch fbatch;
-	long i, j, npages;
+	unsigned long i, j, npages;
 
 	if (WARN_ON(!obj->filp))
 		return ERR_PTR(-EINVAL);
@@ -652,7 +652,7 @@ struct page **drm_gem_get_pages(struct drm_gem_object *obj)
 
 	i = 0;
 	while (i < npages) {
-		long nr;
+		unsigned long nr;
 		folio = shmem_read_folio_gfp(mapping, i,
 				mapping_gfp_mask(mapping));
 		if (IS_ERR(folio))
diff --git a/drivers/gpu/drm/drm_gpuvm.c b/drivers/gpu/drm/drm_gpuvm.c
index a52e95555549..af63f4d00315 100644
--- a/drivers/gpu/drm/drm_gpuvm.c
+++ b/drivers/gpu/drm/drm_gpuvm.c
@@ -2533,8 +2533,6 @@ static const struct drm_gpuvm_ops lock_ops = {
  *
  * The expected usage is::
  *
- * .. code-block:: c
- *
  *    vm_bind {
  *        struct drm_exec exec;
  *
diff --git a/drivers/gpu/drm/drm_panic_qr.rs b/drivers/gpu/drm/drm_panic_qr.rs
index 50c286c5cee8..ac27e86c601c 100644
--- a/drivers/gpu/drm/drm_panic_qr.rs
+++ b/drivers/gpu/drm/drm_panic_qr.rs
@@ -968,7 +968,7 @@ pub unsafe extern "C" fn drm_panic_qr_generate(
         // nul-terminated string.
         let url_cstr: &CStr = unsafe { CStr::from_char_ptr(url) };
         let segments = &[
-            &Segment::Binary(url_cstr.as_bytes()),
+            &Segment::Binary(url_cstr.to_bytes()),
             &Segment::Numeric(&data_slice[0..data_len]),
         ];
         match EncodedMsg::new(segments, tmp_slice) {
diff --git a/drivers/gpu/drm/gma500/oaktrail_hdmi.c b/drivers/gpu/drm/gma500/oaktrail_hdmi.c
index 1cf394369127..c0feca58511d 100644
--- a/drivers/gpu/drm/gma500/oaktrail_hdmi.c
+++ b/drivers/gpu/drm/gma500/oaktrail_hdmi.c
@@ -726,8 +726,8 @@ void oaktrail_hdmi_teardown(struct drm_device *dev)
 
 	if (hdmi_dev) {
 		pdev = hdmi_dev->dev;
-		pci_set_drvdata(pdev, NULL);
 		oaktrail_hdmi_i2c_exit(pdev);
+		pci_set_drvdata(pdev, NULL);
 		iounmap(hdmi_dev->regs);
 		kfree(hdmi_dev);
 		pci_dev_put(pdev);
diff --git a/drivers/gpu/drm/i915/display/intel_ddi.c b/drivers/gpu/drm/i915/display/intel_ddi.c
index 08083ac83a74..c09aa759f4d4 100644
--- a/drivers/gpu/drm/i915/display/intel_ddi.c
+++ b/drivers/gpu/drm/i915/display/intel_ddi.c
@@ -597,8 +597,9 @@ intel_ddi_transcoder_func_reg_val_get(struct intel_encoder *encoder,
 			enum transcoder master;
 
 			master = crtc_state->mst_master_transcoder;
-			drm_WARN_ON(display->drm,
-				    master == INVALID_TRANSCODER);
+			if (drm_WARN_ON(display->drm,
+					master == INVALID_TRANSCODER))
+				master = TRANSCODER_A;
 			temp |= TRANS_DDI_MST_TRANSPORT_SELECT(master);
 		}
 	} else {
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_pages.c b/drivers/gpu/drm/i915/gem/i915_gem_pages.c
index 76d2178572b6..3f09cbce05bb 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_pages.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_pages.c
@@ -765,7 +765,7 @@ __i915_gem_object_get_page(struct drm_i915_gem_object *obj, pgoff_t n)
 	GEM_BUG_ON(!i915_gem_object_has_struct_page(obj));
 
 	sg = i915_gem_object_get_sg(obj, n, &offset);
-	return nth_page(sg_page(sg), offset);
+	return sg_page(sg) + offset;
 }
 
 /* Like i915_gem_object_get_page(), but mark the returned page dirty */
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
index e3d188455f67..b9dae15c1d16 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
@@ -514,6 +514,13 @@ static int __create_shmem(struct drm_i915_private *i915,
 	if (IS_ERR(filp))
 		return PTR_ERR(filp);
 
+	/*
+	 * Prevent -EFBIG by allowing large writes beyond MAX_NON_LFS on shmem
+	 * objects by setting O_LARGEFILE.
+	 */
+	if (force_o_largefile())
+		filp->f_flags |= O_LARGEFILE;
+
 	obj->filp = filp;
 	return 0;
 }
diff --git a/drivers/gpu/drm/i915/gem/i915_gemfs.c b/drivers/gpu/drm/i915/gem/i915_gemfs.c
index a09e2eb47175..8f13ec4ff0d0 100644
--- a/drivers/gpu/drm/i915/gem/i915_gemfs.c
+++ b/drivers/gpu/drm/i915/gem/i915_gemfs.c
@@ -11,11 +11,6 @@
 #include "i915_gemfs.h"
 #include "i915_utils.h"
 
-static int add_param(struct fs_context *fc, const char *key, const char *val)
-{
-	return vfs_parse_fs_string(fc, key, val, strlen(val));
-}
-
 void i915_gemfs_init(struct drm_i915_private *i915)
 {
 	struct file_system_type *type;
@@ -48,9 +43,9 @@ void i915_gemfs_init(struct drm_i915_private *i915)
 	fc = fs_context_for_mount(type, SB_KERNMOUNT);
 	if (IS_ERR(fc))
 		goto err;
-	ret = add_param(fc, "source", "tmpfs");
+	ret = vfs_parse_fs_string(fc, "source", "tmpfs");
 	if (!ret)
-		ret = add_param(fc, "huge", "within_size");
+		ret = vfs_parse_fs_string(fc, "huge", "within_size");
 	if (!ret)
 		gemfs = fc_mount_longterm(fc);
 	put_fs_context(fc);
diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c
index b96f0555ca14..f26562eafffc 100644
--- a/drivers/gpu/drm/nouveau/nouveau_bo.c
+++ b/drivers/gpu/drm/nouveau/nouveau_bo.c
@@ -929,7 +929,7 @@ done:
 		nvif_vmm_put(vmm, &old_mem->vma[1]);
 		nvif_vmm_put(vmm, &old_mem->vma[0]);
 	}
-	return 0;
+	return ret;
 }
 
 static int
diff --git a/drivers/gpu/drm/panthor/panthor_sched.c b/drivers/gpu/drm/panthor/panthor_sched.c
index ba5dc3e443d9..3d1f57e3990f 100644
--- a/drivers/gpu/drm/panthor/panthor_sched.c
+++ b/drivers/gpu/drm/panthor/panthor_sched.c
@@ -895,8 +895,7 @@ static void group_free_queue(struct panthor_group *group, struct panthor_queue *
 	if (IS_ERR_OR_NULL(queue))
 		return;
 
-	if (queue->entity.fence_context)
-		drm_sched_entity_destroy(&queue->entity);
+	drm_sched_entity_destroy(&queue->entity);
 
 	if (queue->scheduler.ops)
 		drm_sched_fini(&queue->scheduler);
@@ -3591,11 +3590,6 @@ int panthor_group_destroy(struct panthor_file *pfile, u32 group_handle)
 	if (!group)
 		return -EINVAL;
 
-	for (u32 i = 0; i < group->queue_count; i++) {
-		if (group->queues[i])
-			drm_sched_entity_destroy(&group->queues[i]->entity);
-	}
-
 	mutex_lock(&sched->reset.lock);
 	mutex_lock(&sched->lock);
 	group->destroyed = true;
diff --git a/drivers/gpu/drm/rockchip/dw-mipi-dsi-rockchip.c b/drivers/gpu/drm/rockchip/dw-mipi-dsi-rockchip.c
index 3398160ad75e..5523911b990d 100644
--- a/drivers/gpu/drm/rockchip/dw-mipi-dsi-rockchip.c
+++ b/drivers/gpu/drm/rockchip/dw-mipi-dsi-rockchip.c
@@ -7,6 +7,7 @@
  */
 
 #include <linux/clk.h>
+#include <linux/hw_bitfield.h>
 #include <linux/iopoll.h>
 #include <linux/math64.h>
 #include <linux/mfd/syscon.h>
@@ -148,7 +149,7 @@
 #define DW_MIPI_NEEDS_GRF_CLK		BIT(1)
 
 #define PX30_GRF_PD_VO_CON1		0x0438
-#define PX30_DSI_FORCETXSTOPMODE	(0xf << 7)
+#define PX30_DSI_FORCETXSTOPMODE	(0xfUL << 7)
 #define PX30_DSI_FORCERXMODE		BIT(6)
 #define PX30_DSI_TURNDISABLE		BIT(5)
 #define PX30_DSI_LCDC_SEL		BIT(0)
@@ -167,16 +168,16 @@
 #define RK3399_DSI1_LCDC_SEL		BIT(4)
 
 #define RK3399_GRF_SOC_CON22		0x6258
-#define RK3399_DSI0_TURNREQUEST		(0xf << 12)
-#define RK3399_DSI0_TURNDISABLE		(0xf << 8)
-#define RK3399_DSI0_FORCETXSTOPMODE	(0xf << 4)
-#define RK3399_DSI0_FORCERXMODE		(0xf << 0)
+#define RK3399_DSI0_TURNREQUEST		(0xfUL << 12)
+#define RK3399_DSI0_TURNDISABLE		(0xfUL << 8)
+#define RK3399_DSI0_FORCETXSTOPMODE	(0xfUL << 4)
+#define RK3399_DSI0_FORCERXMODE		(0xfUL << 0)
 
 #define RK3399_GRF_SOC_CON23		0x625c
-#define RK3399_DSI1_TURNDISABLE		(0xf << 12)
-#define RK3399_DSI1_FORCETXSTOPMODE	(0xf << 8)
-#define RK3399_DSI1_FORCERXMODE		(0xf << 4)
-#define RK3399_DSI1_ENABLE		(0xf << 0)
+#define RK3399_DSI1_TURNDISABLE		(0xfUL << 12)
+#define RK3399_DSI1_FORCETXSTOPMODE	(0xfUL << 8)
+#define RK3399_DSI1_FORCERXMODE		(0xfUL << 4)
+#define RK3399_DSI1_ENABLE		(0xfUL << 0)
 
 #define RK3399_GRF_SOC_CON24		0x6260
 #define RK3399_TXRX_MASTERSLAVEZ	BIT(7)
@@ -186,8 +187,8 @@
 #define RK3399_TXRX_TURNREQUEST		GENMASK(3, 0)
 
 #define RK3568_GRF_VO_CON2		0x0368
-#define RK3568_DSI0_SKEWCALHS		(0x1f << 11)
-#define RK3568_DSI0_FORCETXSTOPMODE	(0xf << 4)
+#define RK3568_DSI0_SKEWCALHS		(0x1fUL << 11)
+#define RK3568_DSI0_FORCETXSTOPMODE	(0xfUL << 4)
 #define RK3568_DSI0_TURNDISABLE		BIT(2)
 #define RK3568_DSI0_FORCERXMODE		BIT(0)
 
@@ -197,18 +198,16 @@
  * come from. Name GRF_VO_CON3 is assumed.
  */
 #define RK3568_GRF_VO_CON3		0x36c
-#define RK3568_DSI1_SKEWCALHS		(0x1f << 11)
-#define RK3568_DSI1_FORCETXSTOPMODE	(0xf << 4)
+#define RK3568_DSI1_SKEWCALHS		(0x1fUL << 11)
+#define RK3568_DSI1_FORCETXSTOPMODE	(0xfUL << 4)
 #define RK3568_DSI1_TURNDISABLE		BIT(2)
 #define RK3568_DSI1_FORCERXMODE		BIT(0)
 
 #define RV1126_GRF_DSIPHY_CON		0x10220
-#define RV1126_DSI_FORCETXSTOPMODE	(0xf << 4)
+#define RV1126_DSI_FORCETXSTOPMODE	(0xfUL << 4)
 #define RV1126_DSI_TURNDISABLE		BIT(2)
 #define RV1126_DSI_FORCERXMODE		BIT(0)
 
-#define HIWORD_UPDATE(val, mask)	(val | (mask) << 16)
-
 enum {
 	DW_DSI_USAGE_IDLE,
 	DW_DSI_USAGE_DSI,
@@ -1484,14 +1483,13 @@ static const struct rockchip_dw_dsi_chip_data px30_chip_data[] = {
 	{
 		.reg = 0xff450000,
 		.lcdsel_grf_reg = PX30_GRF_PD_VO_CON1,
-		.lcdsel_big = HIWORD_UPDATE(0, PX30_DSI_LCDC_SEL),
-		.lcdsel_lit = HIWORD_UPDATE(PX30_DSI_LCDC_SEL,
-					    PX30_DSI_LCDC_SEL),
+		.lcdsel_big = FIELD_PREP_WM16_CONST(PX30_DSI_LCDC_SEL, 0),
+		.lcdsel_lit = FIELD_PREP_WM16_CONST(PX30_DSI_LCDC_SEL, 1),
 
 		.lanecfg1_grf_reg = PX30_GRF_PD_VO_CON1,
-		.lanecfg1 = HIWORD_UPDATE(0, PX30_DSI_TURNDISABLE |
-					     PX30_DSI_FORCERXMODE |
-					     PX30_DSI_FORCETXSTOPMODE),
+		.lanecfg1 = FIELD_PREP_WM16_CONST((PX30_DSI_TURNDISABLE |
+						PX30_DSI_FORCERXMODE |
+						PX30_DSI_FORCETXSTOPMODE), 0),
 
 		.max_data_lanes = 4,
 	},
@@ -1502,9 +1500,9 @@ static const struct rockchip_dw_dsi_chip_data rk3128_chip_data[] = {
 	{
 		.reg = 0x10110000,
 		.lanecfg1_grf_reg = RK3128_GRF_LVDS_CON0,
-		.lanecfg1 = HIWORD_UPDATE(0, RK3128_DSI_TURNDISABLE |
-					     RK3128_DSI_FORCERXMODE |
-					     RK3128_DSI_FORCETXSTOPMODE),
+		.lanecfg1 = FIELD_PREP_WM16_CONST((RK3128_DSI_TURNDISABLE |
+						RK3128_DSI_FORCERXMODE |
+						RK3128_DSI_FORCETXSTOPMODE), 0),
 		.max_data_lanes = 4,
 	},
 	{ /* sentinel */ }
@@ -1514,16 +1512,16 @@ static const struct rockchip_dw_dsi_chip_data rk3288_chip_data[] = {
 	{
 		.reg = 0xff960000,
 		.lcdsel_grf_reg = RK3288_GRF_SOC_CON6,
-		.lcdsel_big = HIWORD_UPDATE(0, RK3288_DSI0_LCDC_SEL),
-		.lcdsel_lit = HIWORD_UPDATE(RK3288_DSI0_LCDC_SEL, RK3288_DSI0_LCDC_SEL),
+		.lcdsel_big = FIELD_PREP_WM16_CONST(RK3288_DSI0_LCDC_SEL, 0),
+		.lcdsel_lit = FIELD_PREP_WM16_CONST(RK3288_DSI0_LCDC_SEL, 1),
 
 		.max_data_lanes = 4,
 	},
 	{
 		.reg = 0xff964000,
 		.lcdsel_grf_reg = RK3288_GRF_SOC_CON6,
-		.lcdsel_big = HIWORD_UPDATE(0, RK3288_DSI1_LCDC_SEL),
-		.lcdsel_lit = HIWORD_UPDATE(RK3288_DSI1_LCDC_SEL, RK3288_DSI1_LCDC_SEL),
+		.lcdsel_big = FIELD_PREP_WM16_CONST(RK3288_DSI1_LCDC_SEL, 0),
+		.lcdsel_lit = FIELD_PREP_WM16_CONST(RK3288_DSI1_LCDC_SEL, 1),
 
 		.max_data_lanes = 4,
 	},
@@ -1539,13 +1537,13 @@ static int rk3399_dphy_tx1rx1_init(struct phy *phy)
 	 * Assume ISP0 is supplied by the RX0 dphy.
 	 */
 	regmap_write(dsi->grf_regmap, RK3399_GRF_SOC_CON24,
-		     HIWORD_UPDATE(0, RK3399_TXRX_SRC_SEL_ISP0));
+		     FIELD_PREP_WM16(RK3399_TXRX_SRC_SEL_ISP0, 0));
 	regmap_write(dsi->grf_regmap, RK3399_GRF_SOC_CON24,
-		     HIWORD_UPDATE(0, RK3399_TXRX_MASTERSLAVEZ));
+		     FIELD_PREP_WM16(RK3399_TXRX_MASTERSLAVEZ, 0));
 	regmap_write(dsi->grf_regmap, RK3399_GRF_SOC_CON24,
-		     HIWORD_UPDATE(0, RK3399_TXRX_BASEDIR));
+		     FIELD_PREP_WM16(RK3399_TXRX_BASEDIR, 0));
 	regmap_write(dsi->grf_regmap, RK3399_GRF_SOC_CON23,
-		     HIWORD_UPDATE(0, RK3399_DSI1_ENABLE));
+		     FIELD_PREP_WM16(RK3399_DSI1_ENABLE, 0));
 
 	return 0;
 }
@@ -1559,21 +1557,20 @@ static int rk3399_dphy_tx1rx1_power_on(struct phy *phy)
 	usleep_range(100, 150);
 
 	regmap_write(dsi->grf_regmap, RK3399_GRF_SOC_CON24,
-		     HIWORD_UPDATE(0, RK3399_TXRX_MASTERSLAVEZ));
+		     FIELD_PREP_WM16(RK3399_TXRX_MASTERSLAVEZ, 0));
 	regmap_write(dsi->grf_regmap, RK3399_GRF_SOC_CON24,
-		     HIWORD_UPDATE(RK3399_TXRX_BASEDIR, RK3399_TXRX_BASEDIR));
+		     FIELD_PREP_WM16(RK3399_TXRX_BASEDIR, 1));
 
 	regmap_write(dsi->grf_regmap, RK3399_GRF_SOC_CON23,
-		     HIWORD_UPDATE(0, RK3399_DSI1_FORCERXMODE));
+		     FIELD_PREP_WM16(RK3399_DSI1_FORCERXMODE, 0));
 	regmap_write(dsi->grf_regmap, RK3399_GRF_SOC_CON23,
-		     HIWORD_UPDATE(0, RK3399_DSI1_FORCETXSTOPMODE));
+		     FIELD_PREP_WM16(RK3399_DSI1_FORCETXSTOPMODE, 0));
 
 	/* Disable lane turn around, which is ignored in receive mode */
 	regmap_write(dsi->grf_regmap, RK3399_GRF_SOC_CON24,
-		     HIWORD_UPDATE(0, RK3399_TXRX_TURNREQUEST));
+		     FIELD_PREP_WM16(RK3399_TXRX_TURNREQUEST, 0));
 	regmap_write(dsi->grf_regmap, RK3399_GRF_SOC_CON23,
-		     HIWORD_UPDATE(RK3399_DSI1_TURNDISABLE,
-				   RK3399_DSI1_TURNDISABLE));
+		     FIELD_PREP_WM16(RK3399_DSI1_TURNDISABLE, 0xf));
 	usleep_range(100, 150);
 
 	dsi_write(dsi, DSI_PHY_TST_CTRL0, PHY_TESTCLK | PHY_UNTESTCLR);
@@ -1581,8 +1578,8 @@ static int rk3399_dphy_tx1rx1_power_on(struct phy *phy)
 
 	/* Enable dphy lanes */
 	regmap_write(dsi->grf_regmap, RK3399_GRF_SOC_CON23,
-		     HIWORD_UPDATE(GENMASK(dsi->dphy_config.lanes - 1, 0),
-				   RK3399_DSI1_ENABLE));
+		     FIELD_PREP_WM16(RK3399_DSI1_ENABLE,
+				  GENMASK(dsi->dphy_config.lanes - 1, 0)));
 
 	usleep_range(100, 150);
 
@@ -1594,7 +1591,7 @@ static int rk3399_dphy_tx1rx1_power_off(struct phy *phy)
 	struct dw_mipi_dsi_rockchip *dsi = phy_get_drvdata(phy);
 
 	regmap_write(dsi->grf_regmap, RK3399_GRF_SOC_CON23,
-		     HIWORD_UPDATE(0, RK3399_DSI1_ENABLE));
+		     FIELD_PREP_WM16(RK3399_DSI1_ENABLE, 0));
 
 	return 0;
 }
@@ -1603,15 +1600,14 @@ static const struct rockchip_dw_dsi_chip_data rk3399_chip_data[] = {
 	{
 		.reg = 0xff960000,
 		.lcdsel_grf_reg = RK3399_GRF_SOC_CON20,
-		.lcdsel_big = HIWORD_UPDATE(0, RK3399_DSI0_LCDC_SEL),
-		.lcdsel_lit = HIWORD_UPDATE(RK3399_DSI0_LCDC_SEL,
-					    RK3399_DSI0_LCDC_SEL),
+		.lcdsel_big = FIELD_PREP_WM16_CONST(RK3399_DSI0_LCDC_SEL, 0),
+		.lcdsel_lit = FIELD_PREP_WM16_CONST(RK3399_DSI0_LCDC_SEL, 1),
 
 		.lanecfg1_grf_reg = RK3399_GRF_SOC_CON22,
-		.lanecfg1 = HIWORD_UPDATE(0, RK3399_DSI0_TURNREQUEST |
-					     RK3399_DSI0_TURNDISABLE |
-					     RK3399_DSI0_FORCETXSTOPMODE |
-					     RK3399_DSI0_FORCERXMODE),
+		.lanecfg1 = FIELD_PREP_WM16_CONST((RK3399_DSI0_TURNREQUEST |
+						RK3399_DSI0_TURNDISABLE |
+						RK3399_DSI0_FORCETXSTOPMODE |
+						RK3399_DSI0_FORCERXMODE), 0),
 
 		.flags = DW_MIPI_NEEDS_PHY_CFG_CLK | DW_MIPI_NEEDS_GRF_CLK,
 		.max_data_lanes = 4,
@@ -1619,25 +1615,23 @@ static const struct rockchip_dw_dsi_chip_data rk3399_chip_data[] = {
 	{
 		.reg = 0xff968000,
 		.lcdsel_grf_reg = RK3399_GRF_SOC_CON20,
-		.lcdsel_big = HIWORD_UPDATE(0, RK3399_DSI1_LCDC_SEL),
-		.lcdsel_lit = HIWORD_UPDATE(RK3399_DSI1_LCDC_SEL,
-					    RK3399_DSI1_LCDC_SEL),
+		.lcdsel_big = FIELD_PREP_WM16_CONST(RK3399_DSI1_LCDC_SEL, 0),
+		.lcdsel_lit = FIELD_PREP_WM16_CONST(RK3399_DSI1_LCDC_SEL, 1),
+
 
 		.lanecfg1_grf_reg = RK3399_GRF_SOC_CON23,
-		.lanecfg1 = HIWORD_UPDATE(0, RK3399_DSI1_TURNDISABLE |
-					     RK3399_DSI1_FORCETXSTOPMODE |
-					     RK3399_DSI1_FORCERXMODE |
-					     RK3399_DSI1_ENABLE),
+		.lanecfg1 = FIELD_PREP_WM16_CONST((RK3399_DSI1_TURNDISABLE |
+						RK3399_DSI1_FORCETXSTOPMODE |
+						RK3399_DSI1_FORCERXMODE |
+						RK3399_DSI1_ENABLE), 0),
 
 		.lanecfg2_grf_reg = RK3399_GRF_SOC_CON24,
-		.lanecfg2 = HIWORD_UPDATE(RK3399_TXRX_MASTERSLAVEZ |
-					  RK3399_TXRX_ENABLECLK,
-					  RK3399_TXRX_MASTERSLAVEZ |
-					  RK3399_TXRX_ENABLECLK |
-					  RK3399_TXRX_BASEDIR),
+		.lanecfg2 = (FIELD_PREP_WM16_CONST(RK3399_TXRX_MASTERSLAVEZ, 1) |
+			     FIELD_PREP_WM16_CONST(RK3399_TXRX_ENABLECLK, 1) |
+			     FIELD_PREP_WM16_CONST(RK3399_TXRX_BASEDIR, 0)),
 
 		.enable_grf_reg = RK3399_GRF_SOC_CON23,
-		.enable = HIWORD_UPDATE(RK3399_DSI1_ENABLE, RK3399_DSI1_ENABLE),
+		.enable = FIELD_PREP_WM16_CONST(RK3399_DSI1_ENABLE, RK3399_DSI1_ENABLE),
 
 		.flags = DW_MIPI_NEEDS_PHY_CFG_CLK | DW_MIPI_NEEDS_GRF_CLK,
 		.max_data_lanes = 4,
@@ -1653,19 +1647,19 @@ static const struct rockchip_dw_dsi_chip_data rk3568_chip_data[] = {
 	{
 		.reg = 0xfe060000,
 		.lanecfg1_grf_reg = RK3568_GRF_VO_CON2,
-		.lanecfg1 = HIWORD_UPDATE(0, RK3568_DSI0_SKEWCALHS |
-					  RK3568_DSI0_FORCETXSTOPMODE |
-					  RK3568_DSI0_TURNDISABLE |
-					  RK3568_DSI0_FORCERXMODE),
+		.lanecfg1 = (FIELD_PREP_WM16_CONST(RK3568_DSI0_SKEWCALHS, 0) |
+			     FIELD_PREP_WM16_CONST(RK3568_DSI0_FORCETXSTOPMODE, 0) |
+			     FIELD_PREP_WM16_CONST(RK3568_DSI0_TURNDISABLE, 0) |
+			     FIELD_PREP_WM16_CONST(RK3568_DSI0_FORCERXMODE, 0)),
 		.max_data_lanes = 4,
 	},
 	{
 		.reg = 0xfe070000,
 		.lanecfg1_grf_reg = RK3568_GRF_VO_CON3,
-		.lanecfg1 = HIWORD_UPDATE(0, RK3568_DSI1_SKEWCALHS |
-					  RK3568_DSI1_FORCETXSTOPMODE |
-					  RK3568_DSI1_TURNDISABLE |
-					  RK3568_DSI1_FORCERXMODE),
+		.lanecfg1 = (FIELD_PREP_WM16_CONST(RK3568_DSI1_SKEWCALHS, 0) |
+			     FIELD_PREP_WM16_CONST(RK3568_DSI1_FORCETXSTOPMODE, 0) |
+			     FIELD_PREP_WM16_CONST(RK3568_DSI1_TURNDISABLE, 0) |
+			     FIELD_PREP_WM16_CONST(RK3568_DSI1_FORCERXMODE, 0)),
 		.max_data_lanes = 4,
 	},
 	{ /* sentinel */ }
@@ -1675,9 +1669,9 @@ static const struct rockchip_dw_dsi_chip_data rv1126_chip_data[] = {
 	{
 		.reg = 0xffb30000,
 		.lanecfg1_grf_reg = RV1126_GRF_DSIPHY_CON,
-		.lanecfg1 = HIWORD_UPDATE(0, RV1126_DSI_TURNDISABLE |
-					     RV1126_DSI_FORCERXMODE |
-					     RV1126_DSI_FORCETXSTOPMODE),
+		.lanecfg1 = (FIELD_PREP_WM16_CONST(RV1126_DSI_TURNDISABLE, 0) |
+			     FIELD_PREP_WM16_CONST(RV1126_DSI_FORCERXMODE, 0) |
+			     FIELD_PREP_WM16_CONST(RV1126_DSI_FORCETXSTOPMODE, 0)),
 		.max_data_lanes = 4,
 	},
 	{ /* sentinel */ }
diff --git a/drivers/gpu/drm/rockchip/dw_hdmi-rockchip.c b/drivers/gpu/drm/rockchip/dw_hdmi-rockchip.c
index acb59b25d928..7b613997bb50 100644
--- a/drivers/gpu/drm/rockchip/dw_hdmi-rockchip.c
+++ b/drivers/gpu/drm/rockchip/dw_hdmi-rockchip.c
@@ -4,6 +4,7 @@
  */
 
 #include <linux/clk.h>
+#include <linux/hw_bitfield.h>
 #include <linux/mfd/syscon.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
@@ -54,8 +55,6 @@
 #define RK3568_HDMI_SDAIN_MSK		BIT(15)
 #define RK3568_HDMI_SCLIN_MSK		BIT(14)
 
-#define HIWORD_UPDATE(val, mask)	(val | (mask) << 16)
-
 /**
  * struct rockchip_hdmi_chip_data - splite the grf setting of kind of chips
  * @lcdsel_grf_reg: grf register offset of lcdc select
@@ -355,17 +354,14 @@ static void dw_hdmi_rk3228_setup_hpd(struct dw_hdmi *dw_hdmi, void *data)
 
 	dw_hdmi_phy_setup_hpd(dw_hdmi, data);
 
-	regmap_write(hdmi->regmap,
-		RK3228_GRF_SOC_CON6,
-		HIWORD_UPDATE(RK3228_HDMI_HPD_VSEL | RK3228_HDMI_SDA_VSEL |
-			      RK3228_HDMI_SCL_VSEL,
-			      RK3228_HDMI_HPD_VSEL | RK3228_HDMI_SDA_VSEL |
-			      RK3228_HDMI_SCL_VSEL));
-
-	regmap_write(hdmi->regmap,
-		RK3228_GRF_SOC_CON2,
-		HIWORD_UPDATE(RK3228_HDMI_SDAIN_MSK | RK3228_HDMI_SCLIN_MSK,
-			      RK3228_HDMI_SDAIN_MSK | RK3228_HDMI_SCLIN_MSK));
+	regmap_write(hdmi->regmap, RK3228_GRF_SOC_CON6,
+		     FIELD_PREP_WM16(RK3228_HDMI_HPD_VSEL, 1) |
+		     FIELD_PREP_WM16(RK3228_HDMI_SDA_VSEL, 1) |
+		     FIELD_PREP_WM16(RK3228_HDMI_SCL_VSEL, 1));
+
+	regmap_write(hdmi->regmap, RK3228_GRF_SOC_CON2,
+		     FIELD_PREP_WM16(RK3228_HDMI_SDAIN_MSK, 1) |
+		     FIELD_PREP_WM16(RK3328_HDMI_SCLIN_MSK, 1));
 }
 
 static enum drm_connector_status
@@ -377,15 +373,13 @@ dw_hdmi_rk3328_read_hpd(struct dw_hdmi *dw_hdmi, void *data)
 	status = dw_hdmi_phy_read_hpd(dw_hdmi, data);
 
 	if (status == connector_status_connected)
-		regmap_write(hdmi->regmap,
-			RK3328_GRF_SOC_CON4,
-			HIWORD_UPDATE(RK3328_HDMI_SDA_5V | RK3328_HDMI_SCL_5V,
-				      RK3328_HDMI_SDA_5V | RK3328_HDMI_SCL_5V));
+		regmap_write(hdmi->regmap, RK3328_GRF_SOC_CON4,
+			     FIELD_PREP_WM16(RK3328_HDMI_SDA_5V, 1) |
+			     FIELD_PREP_WM16(RK3328_HDMI_SCL_5V, 1));
 	else
-		regmap_write(hdmi->regmap,
-			RK3328_GRF_SOC_CON4,
-			HIWORD_UPDATE(0, RK3328_HDMI_SDA_5V |
-					 RK3328_HDMI_SCL_5V));
+		regmap_write(hdmi->regmap, RK3328_GRF_SOC_CON4,
+			     FIELD_PREP_WM16(RK3328_HDMI_SDA_5V, 0) |
+			     FIELD_PREP_WM16(RK3328_HDMI_SCL_5V, 0));
 	return status;
 }
 
@@ -396,21 +390,21 @@ static void dw_hdmi_rk3328_setup_hpd(struct dw_hdmi *dw_hdmi, void *data)
 	dw_hdmi_phy_setup_hpd(dw_hdmi, data);
 
 	/* Enable and map pins to 3V grf-controlled io-voltage */
-	regmap_write(hdmi->regmap,
-		RK3328_GRF_SOC_CON4,
-		HIWORD_UPDATE(0, RK3328_HDMI_HPD_SARADC | RK3328_HDMI_CEC_5V |
-				 RK3328_HDMI_SDA_5V | RK3328_HDMI_SCL_5V |
-				 RK3328_HDMI_HPD_5V));
-	regmap_write(hdmi->regmap,
-		RK3328_GRF_SOC_CON3,
-		HIWORD_UPDATE(0, RK3328_HDMI_SDA5V_GRF | RK3328_HDMI_SCL5V_GRF |
-				 RK3328_HDMI_HPD5V_GRF |
-				 RK3328_HDMI_CEC5V_GRF));
-	regmap_write(hdmi->regmap,
-		RK3328_GRF_SOC_CON2,
-		HIWORD_UPDATE(RK3328_HDMI_SDAIN_MSK | RK3328_HDMI_SCLIN_MSK,
-			      RK3328_HDMI_SDAIN_MSK | RK3328_HDMI_SCLIN_MSK |
-			      RK3328_HDMI_HPD_IOE));
+	regmap_write(hdmi->regmap, RK3328_GRF_SOC_CON4,
+		     FIELD_PREP_WM16(RK3328_HDMI_HPD_SARADC, 0) |
+		     FIELD_PREP_WM16(RK3328_HDMI_CEC_5V, 0) |
+		     FIELD_PREP_WM16(RK3328_HDMI_SDA_5V, 0) |
+		     FIELD_PREP_WM16(RK3328_HDMI_SCL_5V, 0) |
+		     FIELD_PREP_WM16(RK3328_HDMI_HPD_5V, 0));
+	regmap_write(hdmi->regmap, RK3328_GRF_SOC_CON3,
+		     FIELD_PREP_WM16(RK3328_HDMI_SDA5V_GRF, 0) |
+		     FIELD_PREP_WM16(RK3328_HDMI_SCL5V_GRF, 0) |
+		     FIELD_PREP_WM16(RK3328_HDMI_HPD5V_GRF, 0) |
+		     FIELD_PREP_WM16(RK3328_HDMI_CEC5V_GRF, 0));
+	regmap_write(hdmi->regmap, RK3328_GRF_SOC_CON2,
+		     FIELD_PREP_WM16(RK3328_HDMI_SDAIN_MSK, 1) |
+		     FIELD_PREP_WM16(RK3328_HDMI_SCLIN_MSK, 1) |
+		     FIELD_PREP_WM16(RK3328_HDMI_HPD_IOE, 0));
 
 	dw_hdmi_rk3328_read_hpd(dw_hdmi, data);
 }
@@ -438,8 +432,8 @@ static const struct dw_hdmi_plat_data rk3228_hdmi_drv_data = {
 
 static struct rockchip_hdmi_chip_data rk3288_chip_data = {
 	.lcdsel_grf_reg = RK3288_GRF_SOC_CON6,
-	.lcdsel_big = HIWORD_UPDATE(0, RK3288_HDMI_LCDC_SEL),
-	.lcdsel_lit = HIWORD_UPDATE(RK3288_HDMI_LCDC_SEL, RK3288_HDMI_LCDC_SEL),
+	.lcdsel_big = FIELD_PREP_WM16_CONST(RK3288_HDMI_LCDC_SEL, 0),
+	.lcdsel_lit = FIELD_PREP_WM16_CONST(RK3288_HDMI_LCDC_SEL, 1),
 	.max_tmds_clock = 340000,
 };
 
@@ -475,8 +469,8 @@ static const struct dw_hdmi_plat_data rk3328_hdmi_drv_data = {
 
 static struct rockchip_hdmi_chip_data rk3399_chip_data = {
 	.lcdsel_grf_reg = RK3399_GRF_SOC_CON20,
-	.lcdsel_big = HIWORD_UPDATE(0, RK3399_HDMI_LCDC_SEL),
-	.lcdsel_lit = HIWORD_UPDATE(RK3399_HDMI_LCDC_SEL, RK3399_HDMI_LCDC_SEL),
+	.lcdsel_big = FIELD_PREP_WM16_CONST(RK3399_HDMI_LCDC_SEL, 0),
+	.lcdsel_lit = FIELD_PREP_WM16_CONST(RK3399_HDMI_LCDC_SEL, 1),
 	.max_tmds_clock = 594000,
 };
 
@@ -589,10 +583,8 @@ static int dw_hdmi_rockchip_bind(struct device *dev, struct device *master,
 
 	if (hdmi->chip_data == &rk3568_chip_data) {
 		regmap_write(hdmi->regmap, RK3568_GRF_VO_CON1,
-			     HIWORD_UPDATE(RK3568_HDMI_SDAIN_MSK |
-					   RK3568_HDMI_SCLIN_MSK,
-					   RK3568_HDMI_SDAIN_MSK |
-					   RK3568_HDMI_SCLIN_MSK));
+			     FIELD_PREP_WM16(RK3568_HDMI_SDAIN_MSK, 1) |
+			     FIELD_PREP_WM16(RK3568_HDMI_SCLIN_MSK, 1));
 	}
 
 	drm_encoder_helper_add(encoder, &dw_hdmi_rockchip_encoder_helper_funcs);
diff --git a/drivers/gpu/drm/rockchip/dw_hdmi_qp-rockchip.c b/drivers/gpu/drm/rockchip/dw_hdmi_qp-rockchip.c
index 7d531b6f4c09..ed6e8f036f4b 100644
--- a/drivers/gpu/drm/rockchip/dw_hdmi_qp-rockchip.c
+++ b/drivers/gpu/drm/rockchip/dw_hdmi_qp-rockchip.c
@@ -9,6 +9,7 @@
 
 #include <linux/clk.h>
 #include <linux/gpio/consumer.h>
+#include <linux/hw_bitfield.h>
 #include <linux/mfd/syscon.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
@@ -66,7 +67,8 @@
 #define RK3588_HDMI1_HPD_INT_MSK	BIT(15)
 #define RK3588_HDMI1_HPD_INT_CLR	BIT(14)
 #define RK3588_GRF_SOC_CON7		0x031c
-#define RK3588_SET_HPD_PATH_MASK	GENMASK(13, 12)
+#define RK3588_HPD_HDMI0_IO_EN_MASK	BIT(12)
+#define RK3588_HPD_HDMI1_IO_EN_MASK	BIT(13)
 #define RK3588_GRF_SOC_STATUS1		0x0384
 #define RK3588_HDMI0_LEVEL_INT		BIT(16)
 #define RK3588_HDMI1_LEVEL_INT		BIT(24)
@@ -80,7 +82,6 @@
 #define RK3588_HDMI0_GRANT_SEL		BIT(10)
 #define RK3588_HDMI1_GRANT_SEL		BIT(12)
 
-#define HIWORD_UPDATE(val, mask)	((val) | (mask) << 16)
 #define HOTPLUG_DEBOUNCE_MS		150
 #define MAX_HDMI_PORT_NUM		2
 
@@ -185,11 +186,11 @@ static void dw_hdmi_qp_rk3588_setup_hpd(struct dw_hdmi_qp *dw_hdmi, void *data)
 	u32 val;
 
 	if (hdmi->port_id)
-		val = HIWORD_UPDATE(RK3588_HDMI1_HPD_INT_CLR,
-				    RK3588_HDMI1_HPD_INT_CLR | RK3588_HDMI1_HPD_INT_MSK);
+		val = (FIELD_PREP_WM16(RK3588_HDMI1_HPD_INT_CLR, 1) |
+		       FIELD_PREP_WM16(RK3588_HDMI1_HPD_INT_MSK, 0));
 	else
-		val = HIWORD_UPDATE(RK3588_HDMI0_HPD_INT_CLR,
-				    RK3588_HDMI0_HPD_INT_CLR | RK3588_HDMI0_HPD_INT_MSK);
+		val = (FIELD_PREP_WM16(RK3588_HDMI0_HPD_INT_CLR, 1) |
+		       FIELD_PREP_WM16(RK3588_HDMI0_HPD_INT_MSK, 0));
 
 	regmap_write(hdmi->regmap, RK3588_GRF_SOC_CON2, val);
 }
@@ -218,8 +219,8 @@ static void dw_hdmi_qp_rk3576_setup_hpd(struct dw_hdmi_qp *dw_hdmi, void *data)
 	struct rockchip_hdmi_qp *hdmi = (struct rockchip_hdmi_qp *)data;
 	u32 val;
 
-	val = HIWORD_UPDATE(RK3576_HDMI_HPD_INT_CLR,
-			    RK3576_HDMI_HPD_INT_CLR | RK3576_HDMI_HPD_INT_MSK);
+	val = (FIELD_PREP_WM16(RK3576_HDMI_HPD_INT_CLR, 1) |
+	       FIELD_PREP_WM16(RK3576_HDMI_HPD_INT_MSK, 0));
 
 	regmap_write(hdmi->regmap, RK3576_IOC_MISC_CON0, val);
 	regmap_write(hdmi->regmap, 0xa404, 0xffff0102);
@@ -254,7 +255,7 @@ static irqreturn_t dw_hdmi_qp_rk3576_hardirq(int irq, void *dev_id)
 
 	regmap_read(hdmi->regmap, RK3576_IOC_HDMI_HPD_STATUS, &intr_stat);
 	if (intr_stat) {
-		val = HIWORD_UPDATE(RK3576_HDMI_HPD_INT_MSK, RK3576_HDMI_HPD_INT_MSK);
+		val = FIELD_PREP_WM16(RK3576_HDMI_HPD_INT_MSK, 1);
 
 		regmap_write(hdmi->regmap, RK3576_IOC_MISC_CON0, val);
 		return IRQ_WAKE_THREAD;
@@ -273,12 +274,12 @@ static irqreturn_t dw_hdmi_qp_rk3576_irq(int irq, void *dev_id)
 	if (!intr_stat)
 		return IRQ_NONE;
 
-	val = HIWORD_UPDATE(RK3576_HDMI_HPD_INT_CLR, RK3576_HDMI_HPD_INT_CLR);
+	val = FIELD_PREP_WM16(RK3576_HDMI_HPD_INT_CLR, 1);
 	regmap_write(hdmi->regmap, RK3576_IOC_MISC_CON0, val);
 	mod_delayed_work(system_wq, &hdmi->hpd_work,
 			 msecs_to_jiffies(HOTPLUG_DEBOUNCE_MS));
 
-	val = HIWORD_UPDATE(0, RK3576_HDMI_HPD_INT_MSK);
+	val = FIELD_PREP_WM16(RK3576_HDMI_HPD_INT_MSK, 0);
 	regmap_write(hdmi->regmap, RK3576_IOC_MISC_CON0, val);
 
 	return IRQ_HANDLED;
@@ -293,11 +294,9 @@ static irqreturn_t dw_hdmi_qp_rk3588_hardirq(int irq, void *dev_id)
 
 	if (intr_stat) {
 		if (hdmi->port_id)
-			val = HIWORD_UPDATE(RK3588_HDMI1_HPD_INT_MSK,
-					    RK3588_HDMI1_HPD_INT_MSK);
+			val = FIELD_PREP_WM16(RK3588_HDMI1_HPD_INT_MSK, 1);
 		else
-			val = HIWORD_UPDATE(RK3588_HDMI0_HPD_INT_MSK,
-					    RK3588_HDMI0_HPD_INT_MSK);
+			val = FIELD_PREP_WM16(RK3588_HDMI0_HPD_INT_MSK, 1);
 		regmap_write(hdmi->regmap, RK3588_GRF_SOC_CON2, val);
 		return IRQ_WAKE_THREAD;
 	}
@@ -315,20 +314,18 @@ static irqreturn_t dw_hdmi_qp_rk3588_irq(int irq, void *dev_id)
 		return IRQ_NONE;
 
 	if (hdmi->port_id)
-		val = HIWORD_UPDATE(RK3588_HDMI1_HPD_INT_CLR,
-				    RK3588_HDMI1_HPD_INT_CLR);
+		val = FIELD_PREP_WM16(RK3588_HDMI1_HPD_INT_CLR, 1);
 	else
-		val = HIWORD_UPDATE(RK3588_HDMI0_HPD_INT_CLR,
-				    RK3588_HDMI0_HPD_INT_CLR);
+		val = FIELD_PREP_WM16(RK3588_HDMI0_HPD_INT_CLR, 1);
 	regmap_write(hdmi->regmap, RK3588_GRF_SOC_CON2, val);
 
 	mod_delayed_work(system_wq, &hdmi->hpd_work,
 			 msecs_to_jiffies(HOTPLUG_DEBOUNCE_MS));
 
 	if (hdmi->port_id)
-		val |= HIWORD_UPDATE(0, RK3588_HDMI1_HPD_INT_MSK);
+		val |= FIELD_PREP_WM16(RK3588_HDMI1_HPD_INT_MSK, 0);
 	else
-		val |= HIWORD_UPDATE(0, RK3588_HDMI0_HPD_INT_MSK);
+		val |= FIELD_PREP_WM16(RK3588_HDMI0_HPD_INT_MSK, 0);
 	regmap_write(hdmi->regmap, RK3588_GRF_SOC_CON2, val);
 
 	return IRQ_HANDLED;
@@ -338,14 +335,14 @@ static void dw_hdmi_qp_rk3576_io_init(struct rockchip_hdmi_qp *hdmi)
 {
 	u32 val;
 
-	val = HIWORD_UPDATE(RK3576_SCLIN_MASK, RK3576_SCLIN_MASK) |
-	      HIWORD_UPDATE(RK3576_SDAIN_MASK, RK3576_SDAIN_MASK) |
-	      HIWORD_UPDATE(RK3576_HDMI_GRANT_SEL, RK3576_HDMI_GRANT_SEL) |
-	      HIWORD_UPDATE(RK3576_I2S_SEL_MASK, RK3576_I2S_SEL_MASK);
+	val = FIELD_PREP_WM16(RK3576_SCLIN_MASK, 1) |
+	      FIELD_PREP_WM16(RK3576_SDAIN_MASK, 1) |
+	      FIELD_PREP_WM16(RK3576_HDMI_GRANT_SEL, 1) |
+	      FIELD_PREP_WM16(RK3576_I2S_SEL_MASK, 1);
 
 	regmap_write(hdmi->vo_regmap, RK3576_VO0_GRF_SOC_CON14, val);
 
-	val = HIWORD_UPDATE(0, RK3576_HDMI_HPD_INT_MSK);
+	val = FIELD_PREP_WM16(RK3576_HDMI_HPD_INT_MSK, 0);
 	regmap_write(hdmi->regmap, RK3576_IOC_MISC_CON0, val);
 }
 
@@ -353,27 +350,28 @@ static void dw_hdmi_qp_rk3588_io_init(struct rockchip_hdmi_qp *hdmi)
 {
 	u32 val;
 
-	val = HIWORD_UPDATE(RK3588_SCLIN_MASK, RK3588_SCLIN_MASK) |
-	      HIWORD_UPDATE(RK3588_SDAIN_MASK, RK3588_SDAIN_MASK) |
-	      HIWORD_UPDATE(RK3588_MODE_MASK, RK3588_MODE_MASK) |
-	      HIWORD_UPDATE(RK3588_I2S_SEL_MASK, RK3588_I2S_SEL_MASK);
+	val = FIELD_PREP_WM16(RK3588_SCLIN_MASK, 1) |
+	      FIELD_PREP_WM16(RK3588_SDAIN_MASK, 1) |
+	      FIELD_PREP_WM16(RK3588_MODE_MASK, 1) |
+	      FIELD_PREP_WM16(RK3588_I2S_SEL_MASK, 1);
 	regmap_write(hdmi->vo_regmap,
 		     hdmi->port_id ? RK3588_GRF_VO1_CON6 : RK3588_GRF_VO1_CON3,
 		     val);
 
-	val = HIWORD_UPDATE(RK3588_SET_HPD_PATH_MASK, RK3588_SET_HPD_PATH_MASK);
+	val = FIELD_PREP_WM16(RK3588_HPD_HDMI0_IO_EN_MASK, 1) |
+	      FIELD_PREP_WM16(RK3588_HPD_HDMI1_IO_EN_MASK, 1);
 	regmap_write(hdmi->regmap, RK3588_GRF_SOC_CON7, val);
 
 	if (hdmi->port_id)
-		val = HIWORD_UPDATE(RK3588_HDMI1_GRANT_SEL, RK3588_HDMI1_GRANT_SEL);
+		val = FIELD_PREP_WM16(RK3588_HDMI1_GRANT_SEL, 1);
 	else
-		val = HIWORD_UPDATE(RK3588_HDMI0_GRANT_SEL, RK3588_HDMI0_GRANT_SEL);
+		val = FIELD_PREP_WM16(RK3588_HDMI0_GRANT_SEL, 1);
 	regmap_write(hdmi->vo_regmap, RK3588_GRF_VO1_CON9, val);
 
 	if (hdmi->port_id)
-		val = HIWORD_UPDATE(RK3588_HDMI1_HPD_INT_MSK, RK3588_HDMI1_HPD_INT_MSK);
+		val = FIELD_PREP_WM16(RK3588_HDMI1_HPD_INT_MSK, 1);
 	else
-		val = HIWORD_UPDATE(RK3588_HDMI0_HPD_INT_MSK, RK3588_HDMI0_HPD_INT_MSK);
+		val = FIELD_PREP_WM16(RK3588_HDMI0_HPD_INT_MSK, 1);
 	regmap_write(hdmi->regmap, RK3588_GRF_SOC_CON2, val);
 }
 
diff --git a/drivers/gpu/drm/rockchip/inno_hdmi.c b/drivers/gpu/drm/rockchip/inno_hdmi.c
index 1ab3ad4bde9e..f24827dc1421 100644
--- a/drivers/gpu/drm/rockchip/inno_hdmi.c
+++ b/drivers/gpu/drm/rockchip/inno_hdmi.c
@@ -10,6 +10,7 @@
 #include <linux/delay.h>
 #include <linux/err.h>
 #include <linux/hdmi.h>
+#include <linux/hw_bitfield.h>
 #include <linux/mfd/syscon.h>
 #include <linux/mod_devicetable.h>
 #include <linux/module.h>
@@ -382,8 +383,6 @@ enum {
 #define HDMI_CEC_BUSFREETIME_H		0xdd
 #define HDMI_CEC_LOGICADDR		0xde
 
-#define HIWORD_UPDATE(val, mask)	((val) | (mask) << 16)
-
 #define RK3036_GRF_SOC_CON2	0x148
 #define RK3036_HDMI_PHSYNC	BIT(4)
 #define RK3036_HDMI_PVSYNC	BIT(5)
@@ -756,10 +755,10 @@ static int inno_hdmi_config_video_timing(struct inno_hdmi *hdmi,
 	int value, psync;
 
 	if (hdmi->variant->dev_type == RK3036_HDMI) {
-		psync = mode->flags & DRM_MODE_FLAG_PHSYNC ? RK3036_HDMI_PHSYNC : 0;
-		value = HIWORD_UPDATE(psync, RK3036_HDMI_PHSYNC);
-		psync = mode->flags & DRM_MODE_FLAG_PVSYNC ? RK3036_HDMI_PVSYNC : 0;
-		value |= HIWORD_UPDATE(psync, RK3036_HDMI_PVSYNC);
+		psync = mode->flags & DRM_MODE_FLAG_PHSYNC ? 1 : 0;
+		value = FIELD_PREP_WM16(RK3036_HDMI_PHSYNC, psync);
+		psync = mode->flags & DRM_MODE_FLAG_PVSYNC ? 1 : 0;
+		value |= FIELD_PREP_WM16(RK3036_HDMI_PVSYNC, psync);
 		regmap_write(hdmi->grf, RK3036_GRF_SOC_CON2, value);
 	}
 
diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop2.h b/drivers/gpu/drm/rockchip/rockchip_drm_vop2.h
index fa5c56f16047..9124191899ba 100644
--- a/drivers/gpu/drm/rockchip/rockchip_drm_vop2.h
+++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop2.h
@@ -33,7 +33,6 @@
 #define WIN_FEATURE_AFBDC		BIT(0)
 #define WIN_FEATURE_CLUSTER		BIT(1)
 
-#define HIWORD_UPDATE(v, h, l)  ((GENMASK(h, l) << 16) | ((v) << (l)))
 /*
  *  the delay number of a window in different mode.
  */
diff --git a/drivers/gpu/drm/rockchip/rockchip_lvds.h b/drivers/gpu/drm/rockchip/rockchip_lvds.h
index ca83d7b6bea7..2d92447d819b 100644
--- a/drivers/gpu/drm/rockchip/rockchip_lvds.h
+++ b/drivers/gpu/drm/rockchip/rockchip_lvds.h
@@ -9,6 +9,9 @@
 #ifndef _ROCKCHIP_LVDS_
 #define _ROCKCHIP_LVDS_
 
+#include <linux/bits.h>
+#include <linux/hw_bitfield.h>
+
 #define RK3288_LVDS_CH0_REG0			0x00
 #define RK3288_LVDS_CH0_REG0_LVDS_EN		BIT(7)
 #define RK3288_LVDS_CH0_REG0_TTL_EN		BIT(6)
@@ -106,18 +109,16 @@
 #define LVDS_VESA_18				2
 #define LVDS_JEIDA_18				3
 
-#define HIWORD_UPDATE(v, h, l)  ((GENMASK(h, l) << 16) | ((v) << (l)))
-
 #define PX30_LVDS_GRF_PD_VO_CON0		0x434
-#define   PX30_LVDS_TIE_CLKS(val)		HIWORD_UPDATE(val,  8,  8)
-#define   PX30_LVDS_INVERT_CLKS(val)		HIWORD_UPDATE(val,  9,  9)
-#define   PX30_LVDS_INVERT_DCLK(val)		HIWORD_UPDATE(val,  5,  5)
+#define   PX30_LVDS_TIE_CLKS(val)		FIELD_PREP_WM16(BIT(8), (val))
+#define   PX30_LVDS_INVERT_CLKS(val)		FIELD_PREP_WM16(BIT(9), (val))
+#define   PX30_LVDS_INVERT_DCLK(val)		FIELD_PREP_WM16(BIT(5), (val))
 
 #define PX30_LVDS_GRF_PD_VO_CON1		0x438
-#define   PX30_LVDS_FORMAT(val)			HIWORD_UPDATE(val, 14, 13)
-#define   PX30_LVDS_MODE_EN(val)		HIWORD_UPDATE(val, 12, 12)
-#define   PX30_LVDS_MSBSEL(val)			HIWORD_UPDATE(val, 11, 11)
-#define   PX30_LVDS_P2S_EN(val)			HIWORD_UPDATE(val,  6,  6)
-#define   PX30_LVDS_VOP_SEL(val)		HIWORD_UPDATE(val,  1,  1)
+#define   PX30_LVDS_FORMAT(val)			FIELD_PREP_WM16(GENMASK(14, 13), (val))
+#define   PX30_LVDS_MODE_EN(val)		FIELD_PREP_WM16(BIT(12), (val))
+#define   PX30_LVDS_MSBSEL(val)			FIELD_PREP_WM16(BIT(11), (val))
+#define   PX30_LVDS_P2S_EN(val)			FIELD_PREP_WM16(BIT(6), (val))
+#define   PX30_LVDS_VOP_SEL(val)		FIELD_PREP_WM16(BIT(1), (val))
 
 #endif /* _ROCKCHIP_LVDS_ */
diff --git a/drivers/gpu/drm/rockchip/rockchip_vop2_reg.c b/drivers/gpu/drm/rockchip/rockchip_vop2_reg.c
index 45c5e3987813..38c49030c7ab 100644
--- a/drivers/gpu/drm/rockchip/rockchip_vop2_reg.c
+++ b/drivers/gpu/drm/rockchip/rockchip_vop2_reg.c
@@ -7,6 +7,7 @@
 #include <linux/bitfield.h>
 #include <linux/kernel.h>
 #include <linux/component.h>
+#include <linux/hw_bitfield.h>
 #include <linux/mod_devicetable.h>
 #include <linux/platform_device.h>
 #include <linux/of.h>
@@ -1695,8 +1696,9 @@ static unsigned long rk3588_set_intf_mux(struct vop2_video_port *vp, int id, u32
 		die |= RK3588_SYS_DSP_INFACE_EN_HDMI0 |
 			    FIELD_PREP(RK3588_SYS_DSP_INFACE_EN_EDP_HDMI0_MUX, vp->id);
 		val = rk3588_get_hdmi_pol(polflags);
-		regmap_write(vop2->vop_grf, RK3588_GRF_VOP_CON2, HIWORD_UPDATE(1, 1, 1));
-		regmap_write(vop2->vo1_grf, RK3588_GRF_VO1_CON0, HIWORD_UPDATE(val, 6, 5));
+		regmap_write(vop2->vop_grf, RK3588_GRF_VOP_CON2, FIELD_PREP_WM16(BIT(1), 1));
+		regmap_write(vop2->vo1_grf, RK3588_GRF_VO1_CON0,
+			     FIELD_PREP_WM16(GENMASK(6, 5), val));
 		break;
 	case ROCKCHIP_VOP2_EP_HDMI1:
 		div &= ~RK3588_DSP_IF_EDP_HDMI1_DCLK_DIV;
@@ -1707,8 +1709,9 @@ static unsigned long rk3588_set_intf_mux(struct vop2_video_port *vp, int id, u32
 		die |= RK3588_SYS_DSP_INFACE_EN_HDMI1 |
 			    FIELD_PREP(RK3588_SYS_DSP_INFACE_EN_EDP_HDMI1_MUX, vp->id);
 		val = rk3588_get_hdmi_pol(polflags);
-		regmap_write(vop2->vop_grf, RK3588_GRF_VOP_CON2, HIWORD_UPDATE(1, 4, 4));
-		regmap_write(vop2->vo1_grf, RK3588_GRF_VO1_CON0, HIWORD_UPDATE(val, 8, 7));
+		regmap_write(vop2->vop_grf, RK3588_GRF_VOP_CON2, FIELD_PREP_WM16(BIT(4), 1));
+		regmap_write(vop2->vo1_grf, RK3588_GRF_VO1_CON0,
+			     FIELD_PREP_WM16(GENMASK(8, 7), val));
 		break;
 	case ROCKCHIP_VOP2_EP_EDP0:
 		div &= ~RK3588_DSP_IF_EDP_HDMI0_DCLK_DIV;
@@ -1718,7 +1721,7 @@ static unsigned long rk3588_set_intf_mux(struct vop2_video_port *vp, int id, u32
 		die &= ~RK3588_SYS_DSP_INFACE_EN_EDP_HDMI0_MUX;
 		die |= RK3588_SYS_DSP_INFACE_EN_EDP0 |
 			   FIELD_PREP(RK3588_SYS_DSP_INFACE_EN_EDP_HDMI0_MUX, vp->id);
-		regmap_write(vop2->vop_grf, RK3588_GRF_VOP_CON2, HIWORD_UPDATE(1, 0, 0));
+		regmap_write(vop2->vop_grf, RK3588_GRF_VOP_CON2, FIELD_PREP_WM16(BIT(0), 1));
 		break;
 	case ROCKCHIP_VOP2_EP_EDP1:
 		div &= ~RK3588_DSP_IF_EDP_HDMI1_DCLK_DIV;
@@ -1728,7 +1731,7 @@ static unsigned long rk3588_set_intf_mux(struct vop2_video_port *vp, int id, u32
 		die &= ~RK3588_SYS_DSP_INFACE_EN_EDP_HDMI1_MUX;
 		die |= RK3588_SYS_DSP_INFACE_EN_EDP1 |
 			   FIELD_PREP(RK3588_SYS_DSP_INFACE_EN_EDP_HDMI1_MUX, vp->id);
-		regmap_write(vop2->vop_grf, RK3588_GRF_VOP_CON2, HIWORD_UPDATE(1, 3, 3));
+		regmap_write(vop2->vop_grf, RK3588_GRF_VOP_CON2, FIELD_PREP_WM16(BIT(3), 1));
 		break;
 	case ROCKCHIP_VOP2_EP_MIPI0:
 		div &= ~RK3588_DSP_IF_MIPI0_PCLK_DIV;
diff --git a/drivers/gpu/drm/tiny/Kconfig b/drivers/gpu/drm/tiny/Kconfig
index 94a5bf61a115..7d9e85e932d7 100644
--- a/drivers/gpu/drm/tiny/Kconfig
+++ b/drivers/gpu/drm/tiny/Kconfig
@@ -86,7 +86,7 @@ config DRM_PIXPAPER
         tristate "DRM support for PIXPAPER display panels"
         depends on DRM && SPI
         select DRM_CLIENT_SELECTION
-        select DRM_GEM_DMA_HELPER
+        select DRM_GEM_SHMEM_HELPER
         select DRM_KMS_HELPER
         help
 	  DRM driver for the Mayqueen Pixpaper e-ink display panel.
diff --git a/drivers/gpu/drm/v3d/v3d_drv.h b/drivers/gpu/drm/v3d/v3d_drv.h
index 0317f3d7452a..1884686985b8 100644
--- a/drivers/gpu/drm/v3d/v3d_drv.h
+++ b/drivers/gpu/drm/v3d/v3d_drv.h
@@ -62,6 +62,8 @@ struct v3d_queue_state {
 	/* Currently active job for this queue */
 	struct v3d_job *active_job;
 	spinlock_t queue_lock;
+	/* Protect dma fence for signalling job completion */
+	spinlock_t fence_lock;
 };
 
 /* Performance monitor object. The perform lifetime is controlled by userspace
diff --git a/drivers/gpu/drm/v3d/v3d_fence.c b/drivers/gpu/drm/v3d/v3d_fence.c
index 8f8471adae34..c82500a1df73 100644
--- a/drivers/gpu/drm/v3d/v3d_fence.c
+++ b/drivers/gpu/drm/v3d/v3d_fence.c
@@ -15,7 +15,7 @@ struct dma_fence *v3d_fence_create(struct v3d_dev *v3d, enum v3d_queue q)
 	fence->dev = &v3d->drm;
 	fence->queue = q;
 	fence->seqno = ++queue->emit_seqno;
-	dma_fence_init(&fence->base, &v3d_fence_ops, &queue->queue_lock,
+	dma_fence_init(&fence->base, &v3d_fence_ops, &queue->fence_lock,
 		       queue->fence_context, fence->seqno);
 
 	return &fence->base;
diff --git a/drivers/gpu/drm/v3d/v3d_gem.c b/drivers/gpu/drm/v3d/v3d_gem.c
index c77d90aa9b82..bb110d35f749 100644
--- a/drivers/gpu/drm/v3d/v3d_gem.c
+++ b/drivers/gpu/drm/v3d/v3d_gem.c
@@ -273,6 +273,7 @@ v3d_gem_init(struct drm_device *dev)
 		seqcount_init(&queue->stats.lock);
 
 		spin_lock_init(&queue->queue_lock);
+		spin_lock_init(&queue->fence_lock);
 	}
 
 	spin_lock_init(&v3d->mm_lock);
diff --git a/drivers/gpu/drm/v3d/v3d_gemfs.c b/drivers/gpu/drm/v3d/v3d_gemfs.c
index 8ec6ed82b3d9..c1a30166c099 100644
--- a/drivers/gpu/drm/v3d/v3d_gemfs.c
+++ b/drivers/gpu/drm/v3d/v3d_gemfs.c
@@ -7,11 +7,6 @@
 
 #include "v3d_drv.h"
 
-static int add_param(struct fs_context *fc, const char *key, const char *val)
-{
-	return vfs_parse_fs_string(fc, key, val, strlen(val));
-}
-
 void v3d_gemfs_init(struct v3d_dev *v3d)
 {
 	struct file_system_type *type;
@@ -38,9 +33,9 @@ void v3d_gemfs_init(struct v3d_dev *v3d)
 	fc = fs_context_for_mount(type, SB_KERNMOUNT);
 	if (IS_ERR(fc))
 		goto err;
-	ret = add_param(fc, "source", "tmpfs");
+	ret = vfs_parse_fs_string(fc, "source", "tmpfs");
 	if (!ret)
-		ret = add_param(fc, "huge", "within_size");
+		ret = vfs_parse_fs_string(fc, "huge", "within_size");
 	if (!ret)
 		gemfs = fc_mount_longterm(fc);
 	put_fs_context(fc);
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
index 819704ac675d..d539f25b5fbe 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
@@ -1497,6 +1497,7 @@ static int vmw_cmd_dma(struct vmw_private *dev_priv,
 		       SVGA3dCmdHeader *header)
 {
 	struct vmw_bo *vmw_bo = NULL;
+	struct vmw_resource *res;
 	struct vmw_surface *srf = NULL;
 	VMW_DECLARE_CMD_VAR(*cmd, SVGA3dCmdSurfaceDMA);
 	int ret;
@@ -1532,18 +1533,24 @@ static int vmw_cmd_dma(struct vmw_private *dev_priv,
 
 	dirty = (cmd->body.transfer == SVGA3D_WRITE_HOST_VRAM) ?
 		VMW_RES_DIRTY_SET : 0;
-	ret = vmw_cmd_res_check(dev_priv, sw_context, vmw_res_surface,
-				dirty, user_surface_converter,
-				&cmd->body.host.sid, NULL);
+	ret = vmw_cmd_res_check(dev_priv, sw_context, vmw_res_surface, dirty,
+				user_surface_converter, &cmd->body.host.sid,
+				NULL);
 	if (unlikely(ret != 0)) {
 		if (unlikely(ret != -ERESTARTSYS))
 			VMW_DEBUG_USER("could not find surface for DMA.\n");
 		return ret;
 	}
 
-	srf = vmw_res_to_srf(sw_context->res_cache[vmw_res_surface].res);
+	res = sw_context->res_cache[vmw_res_surface].res;
+	if (!res) {
+		VMW_DEBUG_USER("Invalid DMA surface.\n");
+		return -EINVAL;
+	}
 
-	vmw_kms_cursor_snoop(srf, sw_context->fp->tfile, &vmw_bo->tbo, header);
+	srf = vmw_res_to_srf(res);
+	vmw_kms_cursor_snoop(srf, sw_context->fp->tfile, &vmw_bo->tbo,
+			     header);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_validation.c b/drivers/gpu/drm/vmwgfx/vmwgfx_validation.c
index 7ee93e7191c7..35dc94c3db39 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_validation.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_validation.c
@@ -308,8 +308,10 @@ int vmw_validation_add_resource(struct vmw_validation_context *ctx,
 		hash_add_rcu(ctx->sw_context->res_ht, &node->hash.head, node->hash.key);
 	}
 	node->res = vmw_resource_reference_unless_doomed(res);
-	if (!node->res)
+	if (!node->res) {
+		hash_del_rcu(&node->hash.head);
 		return -ESRCH;
+	}
 
 	node->first_usage = 1;
 	if (!res->dev_priv->has_mob) {
@@ -636,7 +638,7 @@ void vmw_validation_drop_ht(struct vmw_validation_context *ctx)
 		hash_del_rcu(&val->hash.head);
 
 	list_for_each_entry(val, &ctx->resource_ctx_list, head)
-		hash_del_rcu(&entry->hash.head);
+		hash_del_rcu(&val->hash.head);
 
 	ctx->sw_context = NULL;
 }
diff --git a/drivers/gpu/drm/xe/tests/xe_pci.c b/drivers/gpu/drm/xe/tests/xe_pci.c
index 0f136bc85b76..69e2840c7ef0 100644
--- a/drivers/gpu/drm/xe/tests/xe_pci.c
+++ b/drivers/gpu/drm/xe/tests/xe_pci.c
@@ -75,9 +75,9 @@ KUNIT_ARRAY_PARAM(platform, cases, xe_pci_fake_data_desc);
  *
  * Return: pointer to the next parameter or NULL if no more parameters
  */
-const void *xe_pci_fake_data_gen_params(const void *prev, char *desc)
+const void *xe_pci_fake_data_gen_params(struct kunit *test, const void *prev, char *desc)
 {
-	return platform_gen_params(prev, desc);
+	return platform_gen_params(test, prev, desc);
 }
 EXPORT_SYMBOL_IF_KUNIT(xe_pci_fake_data_gen_params);
 
@@ -251,16 +251,16 @@ KUNIT_ARRAY_PARAM(pci_id, pciidlist, xe_pci_id_kunit_desc);
  *
  * Return: pointer to the next parameter or NULL if no more parameters
  */
-const void *xe_pci_graphics_ip_gen_param(const void *prev, char *desc)
+const void *xe_pci_graphics_ip_gen_param(struct kunit *test, const void *prev, char *desc)
 {
-	const void *next = pre_gmdid_graphics_ip_gen_params(prev, desc);
+	const void *next = pre_gmdid_graphics_ip_gen_params(test, prev, desc);
 
 	if (next)
 		return next;
 	if (is_insidevar(prev, pre_gmdid_graphics_ips))
 		prev = NULL;
 
-	return graphics_ip_gen_params(prev, desc);
+	return graphics_ip_gen_params(test, prev, desc);
 }
 EXPORT_SYMBOL_IF_KUNIT(xe_pci_graphics_ip_gen_param);
 
@@ -275,16 +275,16 @@ EXPORT_SYMBOL_IF_KUNIT(xe_pci_graphics_ip_gen_param);
  *
  * Return: pointer to the next parameter or NULL if no more parameters
  */
-const void *xe_pci_media_ip_gen_param(const void *prev, char *desc)
+const void *xe_pci_media_ip_gen_param(struct kunit *test, const void *prev, char *desc)
 {
-	const void *next = pre_gmdid_media_ip_gen_params(prev, desc);
+	const void *next = pre_gmdid_media_ip_gen_params(test, prev, desc);
 
 	if (next)
 		return next;
 	if (is_insidevar(prev, pre_gmdid_media_ips))
 		prev = NULL;
 
-	return media_ip_gen_params(prev, desc);
+	return media_ip_gen_params(test, prev, desc);
 }
 EXPORT_SYMBOL_IF_KUNIT(xe_pci_media_ip_gen_param);
 
@@ -299,9 +299,9 @@ EXPORT_SYMBOL_IF_KUNIT(xe_pci_media_ip_gen_param);
  *
  * Return: pointer to the next parameter or NULL if no more parameters
  */
-const void *xe_pci_id_gen_param(const void *prev, char *desc)
+const void *xe_pci_id_gen_param(struct kunit *test, const void *prev, char *desc)
 {
-	const struct pci_device_id *pci = pci_id_gen_params(prev, desc);
+	const struct pci_device_id *pci = pci_id_gen_params(test, prev, desc);
 
 	return pci->driver_data ? pci : NULL;
 }
@@ -387,7 +387,7 @@ EXPORT_SYMBOL_IF_KUNIT(xe_pci_fake_device_init);
  * Return: pointer to the next &struct xe_device ready to be used as a parameter
  *         or NULL if there are no more Xe devices on the system.
  */
-const void *xe_pci_live_device_gen_param(const void *prev, char *desc)
+const void *xe_pci_live_device_gen_param(struct kunit *test, const void *prev, char *desc)
 {
 	const struct xe_device *xe = prev;
 	struct device *dev = xe ? xe->drm.dev : NULL;
diff --git a/drivers/gpu/drm/xe/tests/xe_pci_test.h b/drivers/gpu/drm/xe/tests/xe_pci_test.h
index 5e9a7ffc747f..30505d1cbefc 100644
--- a/drivers/gpu/drm/xe/tests/xe_pci_test.h
+++ b/drivers/gpu/drm/xe/tests/xe_pci_test.h
@@ -7,6 +7,7 @@
 #define _XE_PCI_TEST_H_
 
 #include <linux/types.h>
+#include <kunit/test.h>
 
 #include "xe_platform_types.h"
 #include "xe_sriov_types.h"
@@ -24,12 +25,12 @@ struct xe_pci_fake_data {
 };
 
 int xe_pci_fake_device_init(struct xe_device *xe);
-const void *xe_pci_fake_data_gen_params(const void *prev, char *desc);
+const void *xe_pci_fake_data_gen_params(struct kunit *test, const void *prev, char *desc);
 void xe_pci_fake_data_desc(const struct xe_pci_fake_data *param, char *desc);
 
-const void *xe_pci_graphics_ip_gen_param(const void *prev, char *desc);
-const void *xe_pci_media_ip_gen_param(const void *prev, char *desc);
-const void *xe_pci_id_gen_param(const void *prev, char *desc);
-const void *xe_pci_live_device_gen_param(const void *prev, char *desc);
+const void *xe_pci_graphics_ip_gen_param(struct kunit *test, const void *prev, char *desc);
+const void *xe_pci_media_ip_gen_param(struct kunit *test, const void *prev, char *desc);
+const void *xe_pci_id_gen_param(struct kunit *test, const void *prev, char *desc);
+const void *xe_pci_live_device_gen_param(struct kunit *test, const void *prev, char *desc);
 
 #endif
diff --git a/drivers/gpu/nova-core/driver.rs b/drivers/gpu/nova-core/driver.rs
index 1380b47617f7..edc72052e27a 100644
--- a/drivers/gpu/nova-core/driver.rs
+++ b/drivers/gpu/nova-core/driver.rs
@@ -1,6 +1,14 @@
 // SPDX-License-Identifier: GPL-2.0
 
-use kernel::{auxiliary, bindings, c_str, device::Core, pci, prelude::*, sizes::SZ_16M, sync::Arc};
+use kernel::{
+    auxiliary, c_str,
+    device::Core,
+    pci,
+    pci::{Class, ClassMask, Vendor},
+    prelude::*,
+    sizes::SZ_16M,
+    sync::Arc,
+};
 
 use crate::gpu::Gpu;
 
@@ -18,10 +26,25 @@ kernel::pci_device_table!(
     PCI_TABLE,
     MODULE_PCI_TABLE,
     <NovaCore as pci::Driver>::IdInfo,
-    [(
-        pci::DeviceId::from_id(bindings::PCI_VENDOR_ID_NVIDIA, bindings::PCI_ANY_ID as u32),
-        ()
-    )]
+    [
+        // Modern NVIDIA GPUs will show up as either VGA or 3D controllers.
+        (
+            pci::DeviceId::from_class_and_vendor(
+                Class::DISPLAY_VGA,
+                ClassMask::ClassSubclass,
+                Vendor::NVIDIA
+            ),
+            ()
+        ),
+        (
+            pci::DeviceId::from_class_and_vendor(
+                Class::DISPLAY_3D,
+                ClassMask::ClassSubclass,
+                Vendor::NVIDIA
+            ),
+            ()
+        ),
+    ]
 );
 
 impl pci::Driver for NovaCore {
diff --git a/drivers/gpu/nova-core/fb.rs b/drivers/gpu/nova-core/fb.rs
index 68559902ae78..27d9edab8347 100644
--- a/drivers/gpu/nova-core/fb.rs
+++ b/drivers/gpu/nova-core/fb.rs
@@ -3,6 +3,7 @@
 use core::ops::Range;
 
 use kernel::prelude::*;
+use kernel::ptr::{Alignable, Alignment};
 use kernel::sizes::*;
 use kernel::sync::aref::ARef;
 use kernel::{dev_warn, device};
@@ -130,10 +131,9 @@ impl FbLayout {
         };
 
         let frts = {
-            const FRTS_DOWN_ALIGN: u64 = SZ_128K as u64;
+            const FRTS_DOWN_ALIGN: Alignment = Alignment::new::<SZ_128K>();
             const FRTS_SIZE: u64 = SZ_1M as u64;
-            // TODO[NUMM]: replace with `align_down` once it lands.
-            let frts_base = (vga_workspace.start & !(FRTS_DOWN_ALIGN - 1)) - FRTS_SIZE;
+            let frts_base = vga_workspace.start.align_down(FRTS_DOWN_ALIGN) - FRTS_SIZE;
 
             frts_base..frts_base + FRTS_SIZE
         };
diff --git a/drivers/gpu/nova-core/gpu.rs b/drivers/gpu/nova-core/gpu.rs
index 5da9ad726483..af20e2daea24 100644
--- a/drivers/gpu/nova-core/gpu.rs
+++ b/drivers/gpu/nova-core/gpu.rs
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 
-use kernel::{device, devres::Devres, error::code::*, pci, prelude::*, sync::Arc};
+use kernel::{device, devres::Devres, error::code::*, fmt, pci, prelude::*, sync::Arc};
 
 use crate::driver::Bar0;
 use crate::falcon::{gsp::Gsp as GspFalcon, sec2::Sec2 as Sec2Falcon, Falcon};
@@ -8,7 +8,6 @@ use crate::fb::SysmemFlush;
 use crate::gfw;
 use crate::gsp::Gsp;
 use crate::regs;
-use core::fmt;
 
 macro_rules! define_chipset {
     ({ $($variant:ident = $value:expr),* $(,)* }) =>
diff --git a/drivers/gpu/nova-core/regs/macros.rs b/drivers/gpu/nova-core/regs/macros.rs
index 754c14ee7f40..8058e1696df9 100644
--- a/drivers/gpu/nova-core/regs/macros.rs
+++ b/drivers/gpu/nova-core/regs/macros.rs
@@ -569,10 +569,10 @@ macro_rules! register {
 
     // Generates the `Debug` implementation for `$name`.
     (@debug $name:ident { $($field:ident;)* }) => {
-        impl ::core::fmt::Debug for $name {
-            fn fmt(&self, f: &mut ::core::fmt::Formatter<'_>) -> ::core::fmt::Result {
+        impl ::kernel::fmt::Debug for $name {
+            fn fmt(&self, f: &mut ::kernel::fmt::Formatter<'_>) -> ::kernel::fmt::Result {
                 f.debug_struct(stringify!($name))
-                    .field("<raw>", &format_args!("{:#x}", &self.0))
+                    .field("<raw>", &::kernel::prelude::fmt!("{:#x}", &self.0))
                 $(
                     .field(stringify!($field), &self.$field())
                 )*
diff --git a/drivers/gpu/nova-core/vbios.rs b/drivers/gpu/nova-core/vbios.rs
index e6a060714205..71fbe71b84db 100644
--- a/drivers/gpu/nova-core/vbios.rs
+++ b/drivers/gpu/nova-core/vbios.rs
@@ -9,6 +9,7 @@ use core::convert::TryFrom;
 use kernel::device;
 use kernel::error::Result;
 use kernel::prelude::*;
+use kernel::ptr::{Alignable, Alignment};
 use kernel::types::ARef;
 
 /// The offset of the VBIOS ROM in the BAR0 space.
@@ -174,8 +175,7 @@ impl<'a> Iterator for VbiosIterator<'a> {
 
         // Advance to next image (aligned to 512 bytes).
         self.current_offset += image_size;
-        // TODO[NUMM]: replace with `align_up` once it lands.
-        self.current_offset = self.current_offset.next_multiple_of(512);
+        self.current_offset = self.current_offset.align_up(Alignment::new::<512>())?;
 
         Some(Ok(full_image))
     }