Merge drm/drm-next into drm-misc-next

Start the 6.5 release cycle.

Signed-off-by: Maxime Ripard <maxime@cerno.tech>

83 files changed, 570 insertions, 368 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index 08eced097bd8..2eb2c66843a8 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -1276,7 +1276,7 @@ static int amdgpu_cs_submit(struct amdgpu_cs_parser *p,
 		r = drm_sched_job_add_dependency(&leader->base, fence);
 		if (r) {
 			dma_fence_put(fence);
-			goto error_cleanup;
+			return r;
 		}
 	}
 
@@ -1303,7 +1303,8 @@ static int amdgpu_cs_submit(struct amdgpu_cs_parser *p,
 	}
 	if (r) {
 		r = -EAGAIN;
-		goto error_unlock;
+		mutex_unlock(&p->adev->notifier_lock);
+		return r;
 	}
 
 	p->fence = dma_fence_get(&leader->base.s_fence->finished);
@@ -1350,14 +1351,6 @@ static int amdgpu_cs_submit(struct amdgpu_cs_parser *p,
 	mutex_unlock(&p->adev->notifier_lock);
 	mutex_unlock(&p->bo_list->bo_list_mutex);
 	return 0;
-
-error_unlock:
-	mutex_unlock(&p->adev->notifier_lock);
-
-error_cleanup:
-	for (i = 0; i < p->gang_size; ++i)
-		drm_sched_job_cleanup(&p->jobs[i]->base);
-	return r;
 }
 
 /* Cleanup the parser structure */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index a2292acf06d0..981a9cfb63b5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -2539,8 +2539,6 @@ static int amdgpu_device_ip_init(struct amdgpu_device *adev)
 	amdgpu_fru_get_product_info(adev);
 
 init_failed:
-	if (amdgpu_sriov_vf(adev))
-		amdgpu_virt_release_full_gpu(adev, true);
 
 	return r;
 }
@@ -3580,6 +3578,7 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 	int r, i;
 	bool px = false;
 	u32 max_MBps;
+	int tmp;
 
 	adev->shutdown = false;
 	adev->flags = flags;
@@ -3801,7 +3800,13 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 				}
 			}
 		} else {
+			tmp = amdgpu_reset_method;
+			/* It should do a default reset when loading or reloading the driver,
+			 * regardless of the module parameter reset_method.
+			 */
+			amdgpu_reset_method = AMD_RESET_METHOD_NONE;
 			r = amdgpu_asic_reset(adev);
+			amdgpu_reset_method = tmp;
 			if (r) {
 				dev_err(adev->dev, "asic reset on init failed\n");
 				goto failed;
@@ -3859,18 +3864,6 @@ fence_driver_init:
 
 	r = amdgpu_device_ip_init(adev);
 	if (r) {
-		/* failed in exclusive mode due to timeout */
-		if (amdgpu_sriov_vf(adev) &&
-		    !amdgpu_sriov_runtime(adev) &&
-		    amdgpu_virt_mmio_blocked(adev) &&
-		    !amdgpu_virt_wait_reset(adev)) {
-			dev_err(adev->dev, "VF exclusive mode timeout\n");
-			/* Don't send request since VF is inactive. */
-			adev->virt.caps &= ~AMDGPU_SRIOV_CAPS_RUNTIME;
-			adev->virt.ops = NULL;
-			r = -EAGAIN;
-			goto release_ras_con;
-		}
 		dev_err(adev->dev, "amdgpu_device_ip_init failed\n");
 		amdgpu_vf_error_put(adev, AMDGIM_ERROR_VF_AMDGPU_INIT_FAIL, 0, 0);
 		goto release_ras_con;
@@ -3939,8 +3932,10 @@ fence_driver_init:
 				   msecs_to_jiffies(AMDGPU_RESUME_MS));
 	}
 
-	if (amdgpu_sriov_vf(adev))
+	if (amdgpu_sriov_vf(adev)) {
+		amdgpu_virt_release_full_gpu(adev, true);
 		flush_delayed_work(&adev->delayed_init_work);
+	}
 
 	r = sysfs_create_files(&adev->dev->kobj, amdgpu_dev_attributes);
 	if (r)
@@ -3980,6 +3975,20 @@ fence_driver_init:
 	return 0;
 
 release_ras_con:
+	if (amdgpu_sriov_vf(adev))
+		amdgpu_virt_release_full_gpu(adev, true);
+
+	/* failed in exclusive mode due to timeout */
+	if (amdgpu_sriov_vf(adev) &&
+		!amdgpu_sriov_runtime(adev) &&
+		amdgpu_virt_mmio_blocked(adev) &&
+		!amdgpu_virt_wait_reset(adev)) {
+		dev_err(adev->dev, "VF exclusive mode timeout\n");
+		/* Don't send request since VF is inactive. */
+		adev->virt.caps &= ~AMDGPU_SRIOV_CAPS_RUNTIME;
+		adev->virt.ops = NULL;
+		r = -EAGAIN;
+	}
 	amdgpu_release_ras_context(adev);
 
 failed:
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c
index d0a1cc88832c..fafebec5b7b6 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c
@@ -596,6 +596,9 @@ int amdgpu_irq_put(struct amdgpu_device *adev, struct amdgpu_irq_src *src,
 	if (!src->enabled_types || !src->funcs->set)
 		return -EINVAL;
 
+	if (WARN_ON(!amdgpu_irq_enabled(adev, src, type)))
+		return -EINVAL;
+
 	if (atomic_dec_and_test(&src->enabled_types[type]))
 		return amdgpu_irq_update(adev, src, type);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sched.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_sched.c
index e9b45089a28a..863b2a34b2d6 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sched.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sched.c
@@ -38,6 +38,7 @@ static int amdgpu_sched_process_priority_override(struct amdgpu_device *adev,
 {
 	struct fd f = fdget(fd);
 	struct amdgpu_fpriv *fpriv;
+	struct amdgpu_ctx_mgr *mgr;
 	struct amdgpu_ctx *ctx;
 	uint32_t id;
 	int r;
@@ -51,8 +52,11 @@ static int amdgpu_sched_process_priority_override(struct amdgpu_device *adev,
 		return r;
 	}
 
-	idr_for_each_entry(&fpriv->ctx_mgr.ctx_handles, ctx, id)
+	mgr = &fpriv->ctx_mgr;
+	mutex_lock(&mgr->lock);
+	idr_for_each_entry(&mgr->ctx_handles, ctx, id)
 		amdgpu_ctx_priority_override(ctx, priority);
+	mutex_unlock(&mgr->lock);
 
 	fdput(f);
 	return 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
index 7d6f4a68f416..b213dcf8ca06 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
@@ -1143,7 +1143,6 @@ static int gmc_v10_0_hw_fini(void *handle)
 		return 0;
 	}
 
-	amdgpu_irq_put(adev, &adev->gmc.ecc_irq, 0);
 	amdgpu_irq_put(adev, &adev->gmc.vm_fault, 0);
 
 	return 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c
index d809f2ed5600..d95f9fe8f1c5 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c
@@ -951,7 +951,6 @@ static int gmc_v11_0_hw_fini(void *handle)
 		return 0;
 	}
 
-	amdgpu_irq_put(adev, &adev->gmc.ecc_irq, 0);
 	amdgpu_irq_put(adev, &adev->gmc.vm_fault, 0);
 	gmc_v11_0_gart_disable(adev);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
index 64ab1a306dfe..2fe21cefd772 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
@@ -1999,7 +1999,6 @@ static int gmc_v9_0_hw_fini(void *handle)
 	if (adev->mmhub.funcs->update_power_gating)
 		adev->mmhub.funcs->update_power_gating(adev, false);
 
-	amdgpu_irq_put(adev, &adev->gmc.ecc_irq, 0);
 	amdgpu_irq_put(adev, &adev->gmc.vm_fault, 0);
 
 	return 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c
index a6ad678fd507..77e1e64aa1d1 100644
--- a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c
@@ -430,7 +430,7 @@ static int jpeg_v4_0_start_sriov(struct amdgpu_device *adev)
 		MMSCH_COMMAND__END;
 
 	header.version = MMSCH_VERSION;
-	header.total_size = sizeof(struct mmsch_v4_0_init_header) >> 2;
+	header.total_size = RREG32_SOC15(VCN, 0, regMMSCH_VF_CTX_SIZE);
 
 	header.jpegdec.init_status = 0;
 	header.jpegdec.table_offset = 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/nv.c b/drivers/gpu/drm/amd/amdgpu/nv.c
index 47420b403871..98c826f1f89b 100644
--- a/drivers/gpu/drm/amd/amdgpu/nv.c
+++ b/drivers/gpu/drm/amd/amdgpu/nv.c
@@ -531,13 +531,6 @@ static void nv_program_aspm(struct amdgpu_device *adev)
 
 }
 
-static void nv_enable_doorbell_aperture(struct amdgpu_device *adev,
-					bool enable)
-{
-	adev->nbio.funcs->enable_doorbell_aperture(adev, enable);
-	adev->nbio.funcs->enable_doorbell_selfring_aperture(adev, enable);
-}
-
 const struct amdgpu_ip_block_version nv_common_ip_block =
 {
 	.type = AMD_IP_BLOCK_TYPE_COMMON,
@@ -999,6 +992,11 @@ static int nv_common_late_init(void *handle)
 		}
 	}
 
+	/* Enable selfring doorbell aperture late because doorbell BAR
+	 * aperture will change if resize BAR successfully in gmc sw_init.
+	 */
+	adev->nbio.funcs->enable_doorbell_selfring_aperture(adev, true);
+
 	return 0;
 }
 
@@ -1038,7 +1036,7 @@ static int nv_common_hw_init(void *handle)
 	if (adev->nbio.funcs->remap_hdp_registers && !amdgpu_sriov_vf(adev))
 		adev->nbio.funcs->remap_hdp_registers(adev);
 	/* enable the doorbell aperture */
-	nv_enable_doorbell_aperture(adev, true);
+	adev->nbio.funcs->enable_doorbell_aperture(adev, true);
 
 	return 0;
 }
@@ -1047,8 +1045,13 @@ static int nv_common_hw_fini(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
-	/* disable the doorbell aperture */
-	nv_enable_doorbell_aperture(adev, false);
+	/* Disable the doorbell aperture and selfring doorbell aperture
+	 * separately in hw_fini because nv_enable_doorbell_aperture
+	 * has been removed and there is no need to delay disabling
+	 * selfring doorbell.
+	 */
+	adev->nbio.funcs->enable_doorbell_aperture(adev, false);
+	adev->nbio.funcs->enable_doorbell_selfring_aperture(adev, false);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c
index eb722830531f..3d9a80511a45 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c
@@ -510,10 +510,7 @@ static int sdma_v6_0_gfx_resume(struct amdgpu_device *adev)
 		       lower_32_bits(ring->rptr_gpu_addr) & 0xFFFFFFFC);
 
 		rb_cntl = REG_SET_FIELD(rb_cntl, SDMA0_QUEUE0_RB_CNTL, RPTR_WRITEBACK_ENABLE, 1);
-		if (amdgpu_sriov_vf(adev))
-			rb_cntl = REG_SET_FIELD(rb_cntl, SDMA0_QUEUE0_RB_CNTL, WPTR_POLL_ENABLE, 1);
-		else
-			rb_cntl = REG_SET_FIELD(rb_cntl, SDMA0_QUEUE0_RB_CNTL, WPTR_POLL_ENABLE, 0);
+		rb_cntl = REG_SET_FIELD(rb_cntl, SDMA0_QUEUE0_RB_CNTL, WPTR_POLL_ENABLE, 0);
 		rb_cntl = REG_SET_FIELD(rb_cntl, SDMA0_QUEUE0_RB_CNTL, F32_WPTR_POLL_ENABLE, 1);
 
 		WREG32_SOC15_IP(GC, sdma_v6_0_get_reg_offset(adev, i, regSDMA0_QUEUE0_RB_BASE), ring->gpu_addr >> 8);
diff --git a/drivers/gpu/drm/amd/amdgpu/sienna_cichlid.c b/drivers/gpu/drm/amd/amdgpu/sienna_cichlid.c
index 81a6d5b94987..8b8086d5c864 100644
--- a/drivers/gpu/drm/amd/amdgpu/sienna_cichlid.c
+++ b/drivers/gpu/drm/amd/amdgpu/sienna_cichlid.c
@@ -40,7 +40,7 @@ static bool sienna_cichlid_is_mode2_default(struct amdgpu_reset_control *reset_c
 	    adev->pm.fw_version >= 0x3a5500 && !amdgpu_sriov_vf(adev))
 		return true;
 #endif
-	return false;
+	return amdgpu_reset_method == AMD_RESET_METHOD_MODE2;
 }
 
 static struct amdgpu_reset_handler *
diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c
index bc5dd80f10c1..6d15d5cd9e07 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc15.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc15.c
@@ -619,13 +619,6 @@ static void soc15_program_aspm(struct amdgpu_device *adev)
 		adev->nbio.funcs->program_aspm(adev);
 }
 
-static void soc15_enable_doorbell_aperture(struct amdgpu_device *adev,
-					   bool enable)
-{
-	adev->nbio.funcs->enable_doorbell_aperture(adev, enable);
-	adev->nbio.funcs->enable_doorbell_selfring_aperture(adev, enable);
-}
-
 const struct amdgpu_ip_block_version vega10_common_ip_block =
 {
 	.type = AMD_IP_BLOCK_TYPE_COMMON,
@@ -1125,6 +1118,11 @@ static int soc15_common_late_init(void *handle)
 	if (amdgpu_sriov_vf(adev))
 		xgpu_ai_mailbox_get_irq(adev);
 
+	/* Enable selfring doorbell aperture late because doorbell BAR
+	 * aperture will change if resize BAR successfully in gmc sw_init.
+	 */
+	adev->nbio.funcs->enable_doorbell_selfring_aperture(adev, true);
+
 	return 0;
 }
 
@@ -1182,7 +1180,8 @@ static int soc15_common_hw_init(void *handle)
 		adev->nbio.funcs->remap_hdp_registers(adev);
 
 	/* enable the doorbell aperture */
-	soc15_enable_doorbell_aperture(adev, true);
+	adev->nbio.funcs->enable_doorbell_aperture(adev, true);
+
 	/* HW doorbell routing policy: doorbell writing not
 	 * in SDMA/IH/MM/ACV range will be routed to CP. So
 	 * we need to init SDMA doorbell range prior
@@ -1198,8 +1197,14 @@ static int soc15_common_hw_fini(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
-	/* disable the doorbell aperture */
-	soc15_enable_doorbell_aperture(adev, false);
+	/* Disable the doorbell aperture and selfring doorbell aperture
+	 * separately in hw_fini because soc15_enable_doorbell_aperture
+	 * has been removed and there is no need to delay disabling
+	 * selfring doorbell.
+	 */
+	adev->nbio.funcs->enable_doorbell_aperture(adev, false);
+	adev->nbio.funcs->enable_doorbell_selfring_aperture(adev, false);
+
 	if (amdgpu_sriov_vf(adev))
 		xgpu_ai_mailbox_put_irq(adev);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/soc21.c b/drivers/gpu/drm/amd/amdgpu/soc21.c
index 514bfc705d5a..744be2a05623 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc21.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc21.c
@@ -450,13 +450,6 @@ static void soc21_program_aspm(struct amdgpu_device *adev)
 		adev->nbio.funcs->program_aspm(adev);
 }
 
-static void soc21_enable_doorbell_aperture(struct amdgpu_device *adev,
-					bool enable)
-{
-	adev->nbio.funcs->enable_doorbell_aperture(adev, enable);
-	adev->nbio.funcs->enable_doorbell_selfring_aperture(adev, enable);
-}
-
 const struct amdgpu_ip_block_version soc21_common_ip_block =
 {
 	.type = AMD_IP_BLOCK_TYPE_COMMON,
@@ -764,6 +757,11 @@ static int soc21_common_late_init(void *handle)
 			amdgpu_irq_get(adev, &adev->nbio.ras_err_event_athub_irq, 0);
 	}
 
+	/* Enable selfring doorbell aperture late because doorbell BAR
+	 * aperture will change if resize BAR successfully in gmc sw_init.
+	 */
+	adev->nbio.funcs->enable_doorbell_selfring_aperture(adev, true);
+
 	return 0;
 }
 
@@ -797,7 +795,7 @@ static int soc21_common_hw_init(void *handle)
 	if (adev->nbio.funcs->remap_hdp_registers)
 		adev->nbio.funcs->remap_hdp_registers(adev);
 	/* enable the doorbell aperture */
-	soc21_enable_doorbell_aperture(adev, true);
+	adev->nbio.funcs->enable_doorbell_aperture(adev, true);
 
 	return 0;
 }
@@ -806,8 +804,13 @@ static int soc21_common_hw_fini(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
-	/* disable the doorbell aperture */
-	soc21_enable_doorbell_aperture(adev, false);
+	/* Disable the doorbell aperture and selfring doorbell aperture
+	 * separately in hw_fini because soc21_enable_doorbell_aperture
+	 * has been removed and there is no need to delay disabling
+	 * selfring doorbell.
+	 */
+	adev->nbio.funcs->enable_doorbell_aperture(adev, false);
+	adev->nbio.funcs->enable_doorbell_selfring_aperture(adev, false);
 
 	if (amdgpu_sriov_vf(adev)) {
 		xgpu_nv_mailbox_put_irq(adev);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
index 81d07ecf666d..1b54a9aaae70 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
@@ -93,7 +93,7 @@ int kfd_chardev_init(void)
 	if (err < 0)
 		goto err_register_chrdev;
 
-	kfd_class = class_create(THIS_MODULE, kfd_dev_name);
+	kfd_class = class_create(kfd_dev_name);
 	err = PTR_ERR(kfd_class);
 	if (IS_ERR(kfd_class))
 		goto err_class_create;
diff --git a/drivers/gpu/drm/amd/display/Kconfig b/drivers/gpu/drm/amd/display/Kconfig
index 06b438217c61..2d8e55e29637 100644
--- a/drivers/gpu/drm/amd/display/Kconfig
+++ b/drivers/gpu/drm/amd/display/Kconfig
@@ -8,7 +8,7 @@ config DRM_AMD_DC
 	depends on BROKEN || !CC_IS_CLANG || X86_64 || SPARC64 || ARM64
 	select SND_HDA_COMPONENT if SND_HDA_CORE
 	# !CC_IS_CLANG: https://github.com/ClangBuiltLinux/linux/issues/1752
-	select DRM_AMD_DC_FP if (X86 || PPC64 || (ARM64 && KERNEL_MODE_NEON && !CC_IS_CLANG))
+	select DRM_AMD_DC_FP if (X86 || (PPC64 && ALTIVEC) || (ARM64 && KERNEL_MODE_NEON && !CC_IS_CLANG))
 	help
 	  Choose this option if you want to use the new display engine
 	  support for AMDGPU. This adds required support for Vega and
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 6cacb76f389e..8b4b186c57f5 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -3128,9 +3128,12 @@ void amdgpu_dm_update_connector_after_detect(
 						    aconnector->edid);
 		}
 
-		aconnector->timing_requested = kzalloc(sizeof(struct dc_crtc_timing), GFP_KERNEL);
-		if (!aconnector->timing_requested)
-			dm_error("%s: failed to create aconnector->requested_timing\n", __func__);
+		if (!aconnector->timing_requested) {
+			aconnector->timing_requested =
+				kzalloc(sizeof(struct dc_crtc_timing), GFP_KERNEL);
+			if (!aconnector->timing_requested)
+				dm_error("failed to create aconnector->requested_timing\n");
+		}
 
 		drm_connector_update_edid_property(connector, aconnector->edid);
 		amdgpu_dm_update_freesync_caps(connector, aconnector->edid);
@@ -4471,10 +4474,6 @@ static int amdgpu_dm_initialize_drm_device(struct amdgpu_device *adev)
 		amdgpu_set_panel_orientation(&aconnector->base);
 	}
 
-	/* If we didn't find a panel, notify the acpi video detection */
-	if (dm->adev->flags & AMD_IS_APU && dm->num_of_edps == 0)
-		acpi_video_report_nolcd();
-
 	/* Software is initialized. Now we can register interrupt handlers. */
 	switch (adev->asic_type) {
 #if defined(CONFIG_DRM_AMD_DC_SI)
@@ -7898,6 +7897,13 @@ static void amdgpu_dm_commit_cursors(struct drm_atomic_state *state)
 			amdgpu_dm_plane_handle_cursor_update(plane, old_plane_state);
 }
 
+static inline uint32_t get_mem_type(struct drm_framebuffer *fb)
+{
+	struct amdgpu_bo *abo = gem_to_amdgpu_bo(fb->obj[0]);
+
+	return abo->tbo.resource ? abo->tbo.resource->mem_type : 0;
+}
+
 static void amdgpu_dm_commit_planes(struct drm_atomic_state *state,
 				    struct dc_state *dc_state,
 				    struct drm_device *dev,
@@ -7972,6 +7978,8 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state,
 			continue;
 
 		dc_plane = dm_new_plane_state->dc_state;
+		if (!dc_plane)
+			continue;
 
 		bundle->surface_updates[planes_count].surface = dc_plane;
 		if (new_pcrtc_state->color_mgmt_changed) {
@@ -8038,11 +8046,13 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state,
 
 		/*
 		 * Only allow immediate flips for fast updates that don't
-		 * change FB pitch, DCC state, rotation or mirroing.
+		 * change memory domain, FB pitch, DCC state, rotation or
+		 * mirroring.
 		 */
 		bundle->flip_addrs[planes_count].flip_immediate =
 			crtc->state->async_flip &&
-			acrtc_state->update_type == UPDATE_TYPE_FAST;
+			acrtc_state->update_type == UPDATE_TYPE_FAST &&
+			get_mem_type(old_plane_state->fb) == get_mem_type(fb);
 
 		timestamp_ns = ktime_get_ns();
 		bundle->flip_addrs[planes_count].flip_timestamp_in_us = div_u64(timestamp_ns, 1000);
@@ -8554,6 +8564,9 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state)
 		struct amdgpu_crtc *acrtc = to_amdgpu_crtc(dm_new_con_state->base.crtc);
 		struct amdgpu_dm_connector *aconnector = to_amdgpu_dm_connector(connector);
 
+		if (!adev->dm.hdcp_workqueue)
+			continue;
+
 		pr_debug("[HDCP_DM] -------------- i : %x ----------\n", i);
 
 		if (!connector)
@@ -8602,6 +8615,9 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state)
 		struct amdgpu_crtc *acrtc = to_amdgpu_crtc(dm_new_con_state->base.crtc);
 		struct amdgpu_dm_connector *aconnector = to_amdgpu_dm_connector(connector);
 
+		if (!adev->dm.hdcp_workqueue)
+			continue;
+
 		new_crtc_state = NULL;
 		old_crtc_state = NULL;
 
@@ -9620,8 +9636,9 @@ static int dm_update_plane_state(struct dc *dc,
 			return -EINVAL;
 		}
 
+		if (dm_old_plane_state->dc_state)
+			dc_plane_state_release(dm_old_plane_state->dc_state);
 
-		dc_plane_state_release(dm_old_plane_state->dc_state);
 		dm_new_plane_state->dc_state = NULL;
 
 		*lock_and_validation_needed = true;
@@ -10158,6 +10175,7 @@ static int amdgpu_dm_atomic_check(struct drm_device *dev,
 		ret = compute_mst_dsc_configs_for_state(state, dm_state->context, vars);
 		if (ret) {
 			DRM_DEBUG_DRIVER("compute_mst_dsc_configs_for_state() failed\n");
+			ret = -EINVAL;
 			goto fail;
 		}
 
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 1d924dc51a3e..e3762e806617 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
@@ -169,10 +169,21 @@ static inline int dm_set_vblank(struct drm_crtc *crtc, bool enable)
 	if (rc)
 		return rc;
 
-	irq_source = IRQ_TYPE_VBLANK + acrtc->otg_inst;
+	if (amdgpu_in_reset(adev)) {
+		irq_source = IRQ_TYPE_VBLANK + acrtc->otg_inst;
+		/* During gpu-reset we disable and then enable vblank irq, so
+		 * don't use amdgpu_irq_get/put() to avoid refcount change.
+		 */
+		if (!dc_interrupt_set(adev->dm.dc, irq_source, enable))
+			rc = -EBUSY;
+	} else {
+		rc = (enable)
+			? amdgpu_irq_get(adev, &adev->crtc_irq, acrtc->crtc_id)
+			: amdgpu_irq_put(adev, &adev->crtc_irq, acrtc->crtc_id);
+	}
 
-	if (!dc_interrupt_set(adev->dm.dc, irq_source, enable))
-		return -EBUSY;
+	if (rc)
+		return rc;
 
 skip:
 	if (amdgpu_in_reset(adev))
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c
index 330ab036c830..c6ce2b7123b7 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c
@@ -687,7 +687,6 @@ static void apply_synaptics_fifo_reset_wa(struct drm_dp_aux *aux)
 		return;
 
 	data[0] |= (1 << 1); // set bit 1 to 1
-		return;
 
 	if (!execute_synaptics_rc_command(aux, false, 0x31, 4, 0x221198, data))
 		return;
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
index 994ba426ca66..810ab682f424 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
@@ -379,13 +379,17 @@ static int dm_dp_mst_get_modes(struct drm_connector *connector)
 		if (aconnector->dc_sink && connector->state) {
 			struct drm_device *dev = connector->dev;
 			struct amdgpu_device *adev = drm_to_adev(dev);
-			struct hdcp_workqueue *hdcp_work = adev->dm.hdcp_workqueue;
-			struct hdcp_workqueue *hdcp_w = &hdcp_work[aconnector->dc_link->link_index];
 
-			connector->state->hdcp_content_type =
-			hdcp_w->hdcp_content_type[connector->index];
-			connector->state->content_protection =
-			hdcp_w->content_protection[connector->index];
+			if (adev->dm.hdcp_workqueue) {
+				struct hdcp_workqueue *hdcp_work = adev->dm.hdcp_workqueue;
+				struct hdcp_workqueue *hdcp_w =
+					&hdcp_work[aconnector->dc_link->link_index];
+
+				connector->state->hdcp_content_type =
+				hdcp_w->hdcp_content_type[connector->index];
+				connector->state->content_protection =
+				hdcp_w->content_protection[connector->index];
+			}
 		}
 
 		if (aconnector->dc_sink) {
@@ -1406,6 +1410,7 @@ int pre_validate_dsc(struct drm_atomic_state *state,
 	ret = pre_compute_mst_dsc_configs_for_state(state, local_dc_state, vars);
 	if (ret != 0) {
 		DRM_INFO_ONCE("pre_compute_mst_dsc_configs_for_state() failed\n");
+		ret = -EINVAL;
 		goto clean_exit;
 	}
 
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/dc_fpu.c b/drivers/gpu/drm/amd/display/amdgpu_dm/dc_fpu.c
index 1743ca0a3641..c42aa947c969 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/dc_fpu.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/dc_fpu.c
@@ -89,6 +89,7 @@ void dc_fpu_begin(const char *function_name, const int line)
 
 	if (*pcpu == 1) {
 #if defined(CONFIG_X86)
+		migrate_disable();
 		kernel_fpu_begin();
 #elif defined(CONFIG_PPC64)
 		if (cpu_has_feature(CPU_FTR_VSX_COMP)) {
@@ -129,6 +130,7 @@ void dc_fpu_end(const char *function_name, const int line)
 	if (*pcpu <= 0) {
 #if defined(CONFIG_X86)
 		kernel_fpu_end();
+		migrate_enable();
 #elif defined(CONFIG_PPC64)
 		if (cpu_has_feature(CPU_FTR_VSX_COMP)) {
 			disable_kernel_vsx();
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn32/dcn32_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn32/dcn32_clk_mgr.c
index ea753f8fa175..8d9444db092a 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn32/dcn32_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn32/dcn32_clk_mgr.c
@@ -878,6 +878,8 @@ void dcn32_clk_mgr_construct(
 		struct pp_smu_funcs *pp_smu,
 		struct dccg *dccg)
 {
+	struct clk_log_info log_info = {0};
+
 	clk_mgr->base.ctx = ctx;
 	clk_mgr->base.funcs = &dcn32_funcs;
 	if (ASICREV_IS_GC_11_0_2(clk_mgr->base.ctx->asic_id.hw_internal_rev)) {
@@ -911,6 +913,7 @@ void dcn32_clk_mgr_construct(
 			clk_mgr->base.clks.ref_dtbclk_khz = 268750;
 	}
 
+
 	/* integer part is now VCO frequency in kHz */
 	clk_mgr->base.dentist_vco_freq_khz = dcn32_get_vco_frequency_from_reg(clk_mgr);
 
@@ -918,6 +921,8 @@ void dcn32_clk_mgr_construct(
 	if (clk_mgr->base.dentist_vco_freq_khz == 0)
 		clk_mgr->base.dentist_vco_freq_khz = 4300000; /* Updated as per HW docs */
 
+	dcn32_dump_clk_registers(&clk_mgr->base.boot_snapshot, &clk_mgr->base, &log_info);
+
 	if (ctx->dc->debug.disable_dtb_ref_clk_switch &&
 			clk_mgr->base.clks.ref_dtbclk_khz != clk_mgr->base.boot_snapshot.dtbclk) {
 		clk_mgr->base.clks.ref_dtbclk_khz = clk_mgr->base.boot_snapshot.dtbclk;
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 85d54bfb595c..117d80cb36fb 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
@@ -1707,6 +1707,9 @@ bool dc_remove_plane_from_context(
 	struct dc_stream_status *stream_status = NULL;
 	struct resource_pool *pool = dc->res_pool;
 
+	if (!plane_state)
+		return true;
+
 	for (i = 0; i < context->stream_count; i++)
 		if (context->streams[i] == stream) {
 			stream_status = &context->stream_status[i];
diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h
index 23ee63b98dcd..30f0ba05a6e6 100644
--- a/drivers/gpu/drm/amd/display/dc/dc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc.h
@@ -1454,6 +1454,7 @@ struct dc_link {
 
 	struct ddc_service *ddc;
 
+	enum dp_panel_mode panel_mode;
 	bool aux_mode;
 
 	/* Private to DC core */
diff --git a/drivers/gpu/drm/amd/display/dc/dc_stream.h b/drivers/gpu/drm/amd/display/dc/dc_stream.h
index 181a3408cc61..25284006019c 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_stream.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_stream.h
@@ -144,7 +144,7 @@ struct test_pattern {
 	unsigned int cust_pattern_size;
 };
 
-#define SUBVP_DRR_MARGIN_US 600 // 600us for DRR margin (SubVP + DRR)
+#define SUBVP_DRR_MARGIN_US 100 // 100us for DRR margin (SubVP + DRR)
 
 enum mall_stream_type {
 	SUBVP_NONE, // subvp not in use
diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
index 9fe0ce91db00..8d2460d06bce 100644
--- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
@@ -3031,10 +3031,12 @@ void dce110_enable_dp_link_output(
 	const struct link_hwss *link_hwss = get_link_hwss(link, link_res);
 	unsigned int i;
 
-
+	/*
+	 * Add the logic to extract BOTH power up and power down sequences
+	 * from enable/disable link output and only call edp panel control
+	 * in enable_link_dp and disable_link_dp once.
+	 */
 	if (link->connector_signal == SIGNAL_TYPE_EDP) {
-		if (!link->dc->config.edp_no_power_sequencing)
-			link->dc->hwss.edp_power_control(link, true);
 		link->dc->hwss.edp_wait_for_hpd_ready(link, true);
 	}
 
@@ -3096,11 +3098,12 @@ void dce110_disable_link_output(struct dc_link *link,
 
 	link_hwss->disable_link_output(link, link_res, signal);
 	link->phy_state.symclk_state = SYMCLK_OFF_TX_OFF;
-
-	if (signal == SIGNAL_TYPE_EDP &&
-			link->dc->hwss.edp_backlight_control)
-		link->dc->hwss.edp_power_control(link, false);
-	else if (dmcu != NULL && dmcu->funcs->lock_phy)
+	/*
+	 * Add the logic to extract BOTH power up and power down sequences
+	 * from enable/disable link output and only call edp panel control
+	 * in enable_link_dp and disable_link_dp once.
+	 */
+	if (dmcu != NULL && dmcu->funcs->lock_phy)
 		dmcu->funcs->unlock_phy(dmcu);
 	dc->link_srv->dp_trace_source_sequence(link, DPCD_SOURCE_SEQ_AFTER_DISABLE_LINK_PHY);
 }
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c
index 5403e9399a46..422fbf79da64 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c
@@ -2113,6 +2113,15 @@ void dcn20_optimize_bandwidth(
 	if (hubbub->funcs->program_compbuf_size)
 		hubbub->funcs->program_compbuf_size(hubbub, context->bw_ctx.bw.dcn.compbuf_size_kb, true);
 
+	if (context->bw_ctx.bw.dcn.clk.fw_based_mclk_switching) {
+		dc_dmub_srv_p_state_delegate(dc,
+			true, context);
+		context->bw_ctx.bw.dcn.clk.p_state_change_support = true;
+		dc->clk_mgr->clks.fw_based_mclk_switching = true;
+	} else {
+		dc->clk_mgr->clks.fw_based_mclk_switching = false;
+	}
+
 	dc->clk_mgr->funcs->update_clocks(
 			dc->clk_mgr,
 			context,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c
index 0e071fbc9154..8263a07f265f 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c
@@ -983,13 +983,36 @@ void dcn30_set_disp_pattern_generator(const struct dc *dc,
 }
 
 void dcn30_prepare_bandwidth(struct dc *dc,
- 	struct dc_state *context)
+	struct dc_state *context)
 {
+	bool p_state_change_support = context->bw_ctx.bw.dcn.clk.p_state_change_support;
+	/* Any transition into an FPO config should disable MCLK switching first to avoid
+	 * driver and FW P-State synchronization issues.
+	 */
+	if (context->bw_ctx.bw.dcn.clk.fw_based_mclk_switching || dc->clk_mgr->clks.fw_based_mclk_switching) {
+		dc->optimized_required = true;
+		context->bw_ctx.bw.dcn.clk.p_state_change_support = false;
+	}
+
 	if (dc->clk_mgr->dc_mode_softmax_enabled)
 		if (dc->clk_mgr->clks.dramclk_khz <= dc->clk_mgr->bw_params->dc_mode_softmax_memclk * 1000 &&
 				context->bw_ctx.bw.dcn.clk.dramclk_khz > dc->clk_mgr->bw_params->dc_mode_softmax_memclk * 1000)
 			dc->clk_mgr->funcs->set_max_memclk(dc->clk_mgr, dc->clk_mgr->bw_params->clk_table.entries[dc->clk_mgr->bw_params->clk_table.num_entries - 1].memclk_mhz);
 
 	dcn20_prepare_bandwidth(dc, context);
+	/*
+	 * enabled -> enabled: do not disable
+	 * enabled -> disabled: disable
+	 * disabled -> enabled: don't care
+	 * disabled -> disabled: don't care
+	 */
+	if (!context->bw_ctx.bw.dcn.clk.fw_based_mclk_switching)
+		dc_dmub_srv_p_state_delegate(dc, false, context);
+
+	if (context->bw_ctx.bw.dcn.clk.fw_based_mclk_switching || dc->clk_mgr->clks.fw_based_mclk_switching) {
+		/* After disabling P-State, restore the original value to ensure we get the correct P-State
+		 * on the next optimize. */
+		context->bw_ctx.bw.dcn.clk.p_state_change_support = p_state_change_support;
+	}
 }
 
diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c
index 965f5ceb33f7..67a34cda3774 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c
@@ -701,7 +701,9 @@ static const struct dc_plane_cap plane_cap = {
 			.argb8888 = 167,
 			.nv12 = 167,
 			.fp16 = 167
-	}
+	},
+	16,
+	16
 };
 
 static const struct dc_debug_options debug_defaults_drv = {
diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c
index 7ac6e69cff37..62ce36c75c4d 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c
@@ -295,6 +295,10 @@ void dcn31_init_hw(struct dc *dc)
 	if (dc->res_pool->hubbub->funcs->init_crb)
 		dc->res_pool->hubbub->funcs->init_crb(dc->res_pool->hubbub);
 #endif
+
+	// Get DMCUB capabilities
+	dc_dmub_srv_query_caps_cmd(dc->ctx->dmub_srv->dmub);
+	dc->caps.dmub_caps.psr = dc->ctx->dmub_srv->dmub->feature_caps.psr;
 }
 
 void dcn31_dsc_pg_control(
diff --git a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_dccg.c b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_dccg.c
index 6f879265ad9c..de7bfba2c179 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_dccg.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_dccg.c
@@ -274,7 +274,7 @@ static void dccg314_set_dpstreamclk(
 	}
 }
 
-void dccg314_init(struct dccg *dccg)
+static void dccg314_init(struct dccg *dccg)
 {
 	int otg_inst;
 
diff --git a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c
index 50ed7e09d5ba..abeeede38fb3 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c
@@ -885,7 +885,7 @@ static const struct dc_plane_cap plane_cap = {
 static const struct dc_debug_options debug_defaults_drv = {
 	.disable_z10 = false,
 	.enable_z9_disable_interface = true,
-	.minimum_z8_residency_time = 3080,
+	.minimum_z8_residency_time = 2000,
 	.psr_skip_crtc_disable = true,
 	.disable_dmcu = true,
 	.force_abm_enable = false,
@@ -1696,6 +1696,23 @@ static void dcn314_get_panel_config_defaults(struct dc_panel_config *panel_confi
 	*panel_config = panel_config_defaults;
 }
 
+static bool filter_modes_for_single_channel_workaround(struct dc *dc,
+		struct dc_state *context)
+{
+	// Filter 2K@240Hz+8K@24fps above combination timing if memory only has single dimm LPDDR
+	if (dc->clk_mgr->bw_params->vram_type == 34 && dc->clk_mgr->bw_params->num_channels < 2) {
+		int total_phy_pix_clk = 0;
+
+		for (int i = 0; i < context->stream_count; i++)
+			if (context->res_ctx.pipe_ctx[i].stream)
+				total_phy_pix_clk += context->res_ctx.pipe_ctx[i].stream->phy_pix_clk;
+
+		if (total_phy_pix_clk >= (1148928+826260)) //2K@240Hz+8K@24fps
+			return true;
+	}
+	return false;
+}
+
 bool dcn314_validate_bandwidth(struct dc *dc,
 		struct dc_state *context,
 		bool fast_validate)
@@ -1711,6 +1728,9 @@ bool dcn314_validate_bandwidth(struct dc *dc,
 
 	BW_VAL_TRACE_COUNT();
 
+	if (filter_modes_for_single_channel_workaround(dc, context))
+		goto validate_fail;
+
 	DC_FP_START();
 	// do not support self refresh only
 	out = dcn30_internal_validate_bw(dc, context, pipes, &pipe_cnt, &vlevel, fast_validate, false);
diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c
index db0974fe58ab..1f5ee5cde6e1 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c
@@ -948,6 +948,7 @@ void dcn32_init_hw(struct dc *dc)
 	if (dc->ctx->dmub_srv) {
 		dc_dmub_srv_query_caps_cmd(dc->ctx->dmub_srv->dmub);
 		dc->caps.dmub_caps.psr = dc->ctx->dmub_srv->dmub->feature_caps.psr;
+		dc->caps.dmub_caps.mclk_sw = dc->ctx->dmub_srv->dmub->feature_caps.fw_assisted_mclk_switch;
 	}
 }
 
diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c
index e30d1f60695d..22dd1ebea618 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c
@@ -324,7 +324,6 @@ static const struct dcn10_link_enc_shift le_shift = {
 
 static const struct dcn10_link_enc_mask le_mask = {
 	LINK_ENCODER_MASK_SH_LIST_DCN31(_MASK), \
-
 	//DPCS_DCN31_MASK_SH_LIST(_MASK)
 };
 
@@ -2024,7 +2023,7 @@ int dcn32_populate_dml_pipes_from_context(
 	// In general cases we want to keep the dram clock change requirement
 	// (prefer configs that support MCLK switch). Only override to false
 	// for SubVP
-	if (subvp_in_use)
+	if (context->bw_ctx.bw.dcn.clk.fw_based_mclk_switching || subvp_in_use)
 		context->bw_ctx.dml.soc.dram_clock_change_requirement_final = false;
 	else
 		context->bw_ctx.dml.soc.dram_clock_change_requirement_final = true;
@@ -2080,6 +2079,14 @@ static struct resource_funcs dcn32_res_pool_funcs = {
 	.restore_mall_state = dcn32_restore_mall_state,
 };
 
+static uint32_t read_pipe_fuses(struct dc_context *ctx)
+{
+	uint32_t value = REG_READ(CC_DC_PIPE_DIS);
+	/* DCN32 support max 4 pipes */
+	value = value & 0xf;
+	return value;
+}
+
 
 static bool dcn32_resource_construct(
 	uint8_t num_virtual_links,
@@ -2093,27 +2100,28 @@ static bool dcn32_resource_construct(
 	uint32_t pipe_fuses = 0;
 	uint32_t num_pipes  = 4;
 
-	#undef REG_STRUCT
-	#define REG_STRUCT bios_regs
-		bios_regs_init();
-
-	#undef REG_STRUCT
-	#define REG_STRUCT clk_src_regs
-		clk_src_regs_init(0, A),
-		clk_src_regs_init(1, B),
-		clk_src_regs_init(2, C),
-		clk_src_regs_init(3, D),
-		clk_src_regs_init(4, E);
-	#undef REG_STRUCT
-	#define REG_STRUCT abm_regs
-		abm_regs_init(0),
-		abm_regs_init(1),
-		abm_regs_init(2),
-		abm_regs_init(3);
-
-	#undef REG_STRUCT
-	#define REG_STRUCT dccg_regs
-		dccg_regs_init();
+#undef REG_STRUCT
+#define REG_STRUCT bios_regs
+	bios_regs_init();
+
+#undef REG_STRUCT
+#define REG_STRUCT clk_src_regs
+	clk_src_regs_init(0, A),
+	clk_src_regs_init(1, B),
+	clk_src_regs_init(2, C),
+	clk_src_regs_init(3, D),
+	clk_src_regs_init(4, E);
+
+#undef REG_STRUCT
+#define REG_STRUCT abm_regs
+	abm_regs_init(0),
+	abm_regs_init(1),
+	abm_regs_init(2),
+	abm_regs_init(3);
+
+#undef REG_STRUCT
+#define REG_STRUCT dccg_regs
+	dccg_regs_init();
 
 	DC_FP_START();
 
@@ -2122,7 +2130,7 @@ static bool dcn32_resource_construct(
 	pool->base.res_cap = &res_cap_dcn32;
 	/* max number of pipes for ASIC before checking for pipe fuses */
 	num_pipes  = pool->base.res_cap->num_timing_generator;
-	pipe_fuses = REG_READ(CC_DC_PIPE_DIS);
+	pipe_fuses = read_pipe_fuses(ctx);
 
 	for (i = 0; i < pool->base.res_cap->num_timing_generator; i++)
 		if (pipe_fuses & 1 << i)
diff --git a/drivers/gpu/drm/amd/display/dc/dcn321/dcn321_resource.c b/drivers/gpu/drm/amd/display/dc/dcn321/dcn321_resource.c
index e5ab7f3077c4..a60ddb343d13 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn321/dcn321_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn321/dcn321_resource.c
@@ -1632,6 +1632,14 @@ static struct resource_funcs dcn321_res_pool_funcs = {
 	.restore_mall_state = dcn32_restore_mall_state,
 };
 
+static uint32_t read_pipe_fuses(struct dc_context *ctx)
+{
+	uint32_t value = REG_READ(CC_DC_PIPE_DIS);
+	/* DCN321 support max 4 pipes */
+	value = value & 0xf;
+	return value;
+}
+
 
 static bool dcn321_resource_construct(
 	uint8_t num_virtual_links,
@@ -1674,7 +1682,7 @@ static bool dcn321_resource_construct(
 	pool->base.res_cap = &res_cap_dcn321;
 	/* max number of pipes for ASIC before checking for pipe fuses */
 	num_pipes  = pool->base.res_cap->num_timing_generator;
-	pipe_fuses = REG_READ(CC_DC_PIPE_DIS);
+	pipe_fuses = read_pipe_fuses(ctx);
 
 	for (i = 0; i < pool->base.res_cap->num_timing_generator; i++)
 		if (pipe_fuses & 1 << i)
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c
index 38d1f2be8cf3..f1c1a4b5fcac 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c
@@ -917,19 +917,19 @@ void dcn20_populate_dml_writeback_from_context(struct dc *dc,
 }
 
 void dcn20_fpu_set_wb_arb_params(struct mcif_arb_params *wb_arb_params,
-                                struct dc_state *context,
-                                display_e2e_pipe_params_st *pipes,
-                                int pipe_cnt, int i)
+				 struct dc_state *context,
+				 display_e2e_pipe_params_st *pipes,
+				 int pipe_cnt, int i)
 {
-       int k;
+	int k;
 
-       dc_assert_fp_enabled();
+	dc_assert_fp_enabled();
 
-       for (k = 0; k < sizeof(wb_arb_params->cli_watermark)/sizeof(wb_arb_params->cli_watermark[0]); k++) {
-               wb_arb_params->cli_watermark[k] = get_wm_writeback_urgent(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
-               wb_arb_params->pstate_watermark[k] = get_wm_writeback_dram_clock_change(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
-       }
-       wb_arb_params->time_per_pixel = 16.0 * 1000 / (context->res_ctx.pipe_ctx[i].stream->phy_pix_clk / 1000); /* 4 bit fraction, ms */
+	for (k = 0; k < sizeof(wb_arb_params->cli_watermark)/sizeof(wb_arb_params->cli_watermark[0]); k++) {
+		wb_arb_params->cli_watermark[k] = get_wm_writeback_urgent(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
+		wb_arb_params->pstate_watermark[k] = get_wm_writeback_dram_clock_change(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
+	}
+	wb_arb_params->time_per_pixel = 16.0 * 1000 / (context->res_ctx.pipe_ctx[i].stream->phy_pix_clk / 1000); /* 4 bit fraction, ms */
 }
 
 static bool is_dtbclk_required(struct dc *dc, struct dc_state *context)
@@ -1037,11 +1037,11 @@ static void dcn20_adjust_freesync_v_startup(
 	*vstartup_start = ((newVstartup > *vstartup_start) ? newVstartup : *vstartup_start);
 }
 
-void dcn20_calculate_dlg_params(
-		struct dc *dc, struct dc_state *context,
-		display_e2e_pipe_params_st *pipes,
-		int pipe_cnt,
-		int vlevel)
+void dcn20_calculate_dlg_params(struct dc *dc,
+				struct dc_state *context,
+				display_e2e_pipe_params_st *pipes,
+				int pipe_cnt,
+				int vlevel)
 {
 	int i, pipe_idx;
 
@@ -1083,6 +1083,7 @@ void dcn20_calculate_dlg_params(
 		pipes[pipe_idx].pipe.dest.vupdate_offset = get_vupdate_offset(&context->bw_ctx.dml, pipes, pipe_cnt, pipe_idx);
 		pipes[pipe_idx].pipe.dest.vupdate_width = get_vupdate_width(&context->bw_ctx.dml, pipes, pipe_cnt, pipe_idx);
 		pipes[pipe_idx].pipe.dest.vready_offset = get_vready_offset(&context->bw_ctx.dml, pipes, pipe_cnt, pipe_idx);
+
 		if (context->res_ctx.pipe_ctx[i].stream->mall_stream_config.type == SUBVP_PHANTOM) {
 			// Phantom pipe requires that DET_SIZE = 0 and no unbounded requests
 			context->res_ctx.pipe_ctx[i].det_buffer_size_kb = 0;
@@ -1091,6 +1092,7 @@ void dcn20_calculate_dlg_params(
 			context->res_ctx.pipe_ctx[i].det_buffer_size_kb = context->bw_ctx.dml.ip.det_buffer_size_kbytes;
 			context->res_ctx.pipe_ctx[i].unbounded_req = pipes[pipe_idx].pipe.src.unbounded_req_mode;
 		}
+
 		if (context->bw_ctx.bw.dcn.clk.dppclk_khz < pipes[pipe_idx].clks_cfg.dppclk_mhz * 1000)
 			context->bw_ctx.bw.dcn.clk.dppclk_khz = pipes[pipe_idx].clks_cfg.dppclk_mhz * 1000;
 		context->res_ctx.pipe_ctx[i].plane_res.bw.dppclk_khz =
@@ -1118,6 +1120,7 @@ void dcn20_calculate_dlg_params(
 		if (!context->res_ctx.pipe_ctx[i].stream)
 			continue;
 
+		/* cstate disabled on 201 */
 		if (dc->ctx->dce_version == DCN_VERSION_2_01)
 			cstate_en = false;
 
@@ -1201,11 +1204,10 @@ static void swizzle_to_dml_params(
 	}
 }
 
-int dcn20_populate_dml_pipes_from_context(
-		struct dc *dc,
-		struct dc_state *context,
-		display_e2e_pipe_params_st *pipes,
-		bool fast_validate)
+int dcn20_populate_dml_pipes_from_context(struct dc *dc,
+					  struct dc_state *context,
+					  display_e2e_pipe_params_st *pipes,
+					  bool fast_validate)
 {
 	int pipe_cnt, i;
 	bool synchronized_vblank = true;
@@ -1257,6 +1259,8 @@ int dcn20_populate_dml_pipes_from_context(
 
 		pipes[pipe_cnt].clks_cfg.refclk_mhz = dc->res_pool->ref_clocks.dchub_ref_clock_inKhz / 1000.0;
 
+		pipes[pipe_cnt].pipe.dest.use_maximum_vstartup = dc->ctx->dce_version == DCN_VERSION_2_01;
+
 		pipes[pipe_cnt].dout.dsc_enable = res_ctx->pipe_ctx[i].stream->timing.flags.DSC;
 		/* todo: rotation?*/
 		pipes[pipe_cnt].dout.dsc_slices = res_ctx->pipe_ctx[i].stream->timing.dsc_cfg.num_slices_h;
@@ -1296,8 +1300,7 @@ int dcn20_populate_dml_pipes_from_context(
 			pipes[pipe_cnt].pipe.dest.pixel_rate_mhz *= 2;
 		pipes[pipe_cnt].pipe.dest.otg_inst = res_ctx->pipe_ctx[i].stream_res.tg->inst;
 		pipes[pipe_cnt].dout.dp_lanes = 4;
-		if (res_ctx->pipe_ctx[i].stream->link)
-			pipes[pipe_cnt].dout.dp_rate = dm_dp_rate_na;
+		pipes[pipe_cnt].dout.dp_rate = dm_dp_rate_na;
 		pipes[pipe_cnt].dout.is_virtual = 0;
 		pipes[pipe_cnt].pipe.dest.vtotal_min = res_ctx->pipe_ctx[i].stream->adjust.v_total_min;
 		pipes[pipe_cnt].pipe.dest.vtotal_max = res_ctx->pipe_ctx[i].stream->adjust.v_total_max;
@@ -1357,7 +1360,6 @@ int dcn20_populate_dml_pipes_from_context(
 			pipes[pipe_cnt].dout.is_virtual = 1;
 			pipes[pipe_cnt].dout.output_type = dm_dp;
 			pipes[pipe_cnt].dout.dp_lanes = 4;
-			pipes[pipe_cnt].dout.dp_rate = dm_dp_rate_hbr2;
 		}
 
 		switch (res_ctx->pipe_ctx[i].stream->timing.display_color_depth) {
@@ -1507,6 +1509,7 @@ int dcn20_populate_dml_pipes_from_context(
 			default:
 				break;
 			}
+
 			pipes[pipe_cnt].pipe.src.viewport_y_y = scl->viewport.y;
 			pipes[pipe_cnt].pipe.src.viewport_y_c = scl->viewport_c.y;
 			pipes[pipe_cnt].pipe.src.viewport_x_y = scl->viewport.x;
@@ -1615,13 +1618,12 @@ int dcn20_populate_dml_pipes_from_context(
 	return pipe_cnt;
 }
 
-void dcn20_calculate_wm(
-		struct dc *dc, struct dc_state *context,
-		display_e2e_pipe_params_st *pipes,
-		int *out_pipe_cnt,
-		int *pipe_split_from,
-		int vlevel,
-		bool fast_validate)
+void dcn20_calculate_wm(struct dc *dc, struct dc_state *context,
+			display_e2e_pipe_params_st *pipes,
+			int *out_pipe_cnt,
+			int *pipe_split_from,
+			int vlevel,
+			bool fast_validate)
 {
 	int pipe_cnt, i, pipe_idx;
 
@@ -1733,8 +1735,11 @@ void dcn20_calculate_wm(
 	context->bw_ctx.bw.dcn.watermarks.a.frac_urg_bw_flip = get_fraction_of_urgent_bandwidth_imm_flip(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
 }
 
-void dcn20_update_bounding_box(struct dc *dc, struct _vcs_dpi_soc_bounding_box_st *bb,
-		struct pp_smu_nv_clock_table *max_clocks, unsigned int *uclk_states, unsigned int num_states)
+void dcn20_update_bounding_box(struct dc *dc,
+			       struct _vcs_dpi_soc_bounding_box_st *bb,
+			       struct pp_smu_nv_clock_table *max_clocks,
+			       unsigned int *uclk_states,
+			       unsigned int num_states)
 {
 	int num_calculated_states = 0;
 	int min_dcfclk = 0;
@@ -1796,9 +1801,8 @@ void dcn20_update_bounding_box(struct dc *dc, struct _vcs_dpi_soc_bounding_box_s
 	bb->clock_limits[num_calculated_states].state = bb->num_states;
 }
 
-void dcn20_cap_soc_clocks(
-		struct _vcs_dpi_soc_bounding_box_st *bb,
-		struct pp_smu_nv_clock_table max_clocks)
+void dcn20_cap_soc_clocks(struct _vcs_dpi_soc_bounding_box_st *bb,
+			  struct pp_smu_nv_clock_table max_clocks)
 {
 	int i;
 
@@ -1954,80 +1958,80 @@ validate_out:
 }
 
 bool dcn20_validate_bandwidth_fp(struct dc *dc,
-                                struct dc_state *context,
-                                bool fast_validate)
+				 struct dc_state *context,
+				 bool fast_validate)
 {
-       bool voltage_supported = false;
-       bool full_pstate_supported = false;
-       bool dummy_pstate_supported = false;
-       double p_state_latency_us;
+	bool voltage_supported = false;
+	bool full_pstate_supported = false;
+	bool dummy_pstate_supported = false;
+	double p_state_latency_us;
 
-       dc_assert_fp_enabled();
+	dc_assert_fp_enabled();
 
-       p_state_latency_us = context->bw_ctx.dml.soc.dram_clock_change_latency_us;
-       context->bw_ctx.dml.soc.disable_dram_clock_change_vactive_support =
-               dc->debug.disable_dram_clock_change_vactive_support;
-       context->bw_ctx.dml.soc.allow_dram_clock_one_display_vactive =
-               dc->debug.enable_dram_clock_change_one_display_vactive;
+	p_state_latency_us = context->bw_ctx.dml.soc.dram_clock_change_latency_us;
+	context->bw_ctx.dml.soc.disable_dram_clock_change_vactive_support =
+		dc->debug.disable_dram_clock_change_vactive_support;
+	context->bw_ctx.dml.soc.allow_dram_clock_one_display_vactive =
+		dc->debug.enable_dram_clock_change_one_display_vactive;
 
-       /*Unsafe due to current pipe merge and split logic*/
-       ASSERT(context != dc->current_state);
+	/*Unsafe due to current pipe merge and split logic*/
+	ASSERT(context != dc->current_state);
 
-       if (fast_validate) {
-               return dcn20_validate_bandwidth_internal(dc, context, true);
-       }
+	if (fast_validate) {
+		return dcn20_validate_bandwidth_internal(dc, context, true);
+	}
 
-       // Best case, we support full UCLK switch latency
-       voltage_supported = dcn20_validate_bandwidth_internal(dc, context, false);
-       full_pstate_supported = context->bw_ctx.bw.dcn.clk.p_state_change_support;
+	// Best case, we support full UCLK switch latency
+	voltage_supported = dcn20_validate_bandwidth_internal(dc, context, false);
+	full_pstate_supported = context->bw_ctx.bw.dcn.clk.p_state_change_support;
 
-       if (context->bw_ctx.dml.soc.dummy_pstate_latency_us == 0 ||
-               (voltage_supported && full_pstate_supported)) {
-               context->bw_ctx.bw.dcn.clk.p_state_change_support = full_pstate_supported;
-               goto restore_dml_state;
-       }
+	if (context->bw_ctx.dml.soc.dummy_pstate_latency_us == 0 ||
+		(voltage_supported && full_pstate_supported)) {
+		context->bw_ctx.bw.dcn.clk.p_state_change_support = full_pstate_supported;
+		goto restore_dml_state;
+	}
 
-       // Fallback: Try to only support G6 temperature read latency
-       context->bw_ctx.dml.soc.dram_clock_change_latency_us = context->bw_ctx.dml.soc.dummy_pstate_latency_us;
+	// Fallback: Try to only support G6 temperature read latency
+	context->bw_ctx.dml.soc.dram_clock_change_latency_us = context->bw_ctx.dml.soc.dummy_pstate_latency_us;
 
-       voltage_supported = dcn20_validate_bandwidth_internal(dc, context, false);
-       dummy_pstate_supported = context->bw_ctx.bw.dcn.clk.p_state_change_support;
+	voltage_supported = dcn20_validate_bandwidth_internal(dc, context, false);
+	dummy_pstate_supported = context->bw_ctx.bw.dcn.clk.p_state_change_support;
 
-       if (voltage_supported && (dummy_pstate_supported || !(context->stream_count))) {
-               context->bw_ctx.bw.dcn.clk.p_state_change_support = false;
-               goto restore_dml_state;
-       }
+	if (voltage_supported && (dummy_pstate_supported || !(context->stream_count))) {
+		context->bw_ctx.bw.dcn.clk.p_state_change_support = false;
+		goto restore_dml_state;
+	}
 
-       // ERROR: fallback is supposed to always work.
-       ASSERT(false);
+	// ERROR: fallback is supposed to always work.
+	ASSERT(false);
 
 restore_dml_state:
-       context->bw_ctx.dml.soc.dram_clock_change_latency_us = p_state_latency_us;
-       return voltage_supported;
+	context->bw_ctx.dml.soc.dram_clock_change_latency_us = p_state_latency_us;
+	return voltage_supported;
 }
 
 void dcn20_fpu_set_wm_ranges(int i,
-                            struct pp_smu_wm_range_sets *ranges,
-                            struct _vcs_dpi_soc_bounding_box_st *loaded_bb)
+			     struct pp_smu_wm_range_sets *ranges,
+			     struct _vcs_dpi_soc_bounding_box_st *loaded_bb)
 {
-       dc_assert_fp_enabled();
+	dc_assert_fp_enabled();
 
-       ranges->reader_wm_sets[i].min_fill_clk_mhz = (i > 0) ? (loaded_bb->clock_limits[i - 1].dram_speed_mts / 16) + 1 : 0;
-       ranges->reader_wm_sets[i].max_fill_clk_mhz = loaded_bb->clock_limits[i].dram_speed_mts / 16;
+	ranges->reader_wm_sets[i].min_fill_clk_mhz = (i > 0) ? (loaded_bb->clock_limits[i - 1].dram_speed_mts / 16) + 1 : 0;
+	ranges->reader_wm_sets[i].max_fill_clk_mhz = loaded_bb->clock_limits[i].dram_speed_mts / 16;
 }
 
 void dcn20_fpu_adjust_dppclk(struct vba_vars_st *v,
-                            int vlevel,
-                            int max_mpc_comb,
-                            int pipe_idx,
-                            bool is_validating_bw)
+			     int vlevel,
+			     int max_mpc_comb,
+			     int pipe_idx,
+			     bool is_validating_bw)
 {
-       dc_assert_fp_enabled();
+	dc_assert_fp_enabled();
 
-       if (is_validating_bw)
-               v->RequiredDPPCLK[vlevel][max_mpc_comb][pipe_idx] *= 2;
-       else
-               v->RequiredDPPCLK[vlevel][max_mpc_comb][pipe_idx] /= 2;
+	if (is_validating_bw)
+		v->RequiredDPPCLK[vlevel][max_mpc_comb][pipe_idx] *= 2;
+	else
+		v->RequiredDPPCLK[vlevel][max_mpc_comb][pipe_idx] /= 2;
 }
 
 int dcn21_populate_dml_pipes_from_context(struct dc *dc,
@@ -2329,7 +2333,7 @@ void dcn21_update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_params
 		k++;
 	}
 
-	memcpy(dcn2_1_soc.clock_limits, s, sizeof(dcn2_1_soc.clock_limits));
+	memcpy(&dcn2_1_soc.clock_limits, s, sizeof(dcn2_1_soc.clock_limits));
 
 	if (clk_table->num_entries) {
 		dcn2_1_soc.num_states = clk_table->num_entries + 1;
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn30/dcn30_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn30/dcn30_fpu.c
index 80972ee5e55b..a352c703e258 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn30/dcn30_fpu.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn30/dcn30_fpu.c
@@ -368,7 +368,9 @@ void dcn30_fpu_update_soc_for_wm_a(struct dc *dc, struct dc_state *context)
 	dc_assert_fp_enabled();
 
 	if (dc->clk_mgr->bw_params->wm_table.nv_entries[WM_A].valid) {
-		context->bw_ctx.dml.soc.dram_clock_change_latency_us = dc->clk_mgr->bw_params->wm_table.nv_entries[WM_A].dml_input.pstate_latency_us;
+		if (!context->bw_ctx.bw.dcn.clk.fw_based_mclk_switching ||
+				context->bw_ctx.dml.soc.dram_clock_change_latency_us == 0)
+			context->bw_ctx.dml.soc.dram_clock_change_latency_us = dc->clk_mgr->bw_params->wm_table.nv_entries[WM_A].dml_input.pstate_latency_us;
 		context->bw_ctx.dml.soc.sr_enter_plus_exit_time_us = dc->clk_mgr->bw_params->wm_table.nv_entries[WM_A].dml_input.sr_enter_plus_exit_time_us;
 		context->bw_ctx.dml.soc.sr_exit_time_us = dc->clk_mgr->bw_params->wm_table.nv_entries[WM_A].dml_input.sr_exit_time_us;
 	}
@@ -563,6 +565,20 @@ void dcn30_fpu_calculate_wm_and_dlg(
 		pipe_idx++;
 	}
 
+	// WA: restrict FPO to use first non-strobe mode (NV24 BW issue)
+	if (context->bw_ctx.bw.dcn.clk.fw_based_mclk_switching &&
+			dc->dml.soc.num_chans <= 4 &&
+			context->bw_ctx.dml.vba.DRAMSpeed <= 1700 &&
+			context->bw_ctx.dml.vba.DRAMSpeed >= 1500) {
+
+		for (i = 0; i < dc->dml.soc.num_states; i++) {
+			if (dc->dml.soc.clock_limits[i].dram_speed_mts > 1700) {
+				context->bw_ctx.dml.vba.DRAMSpeed = dc->dml.soc.clock_limits[i].dram_speed_mts;
+				break;
+			}
+		}
+	}
+
 	dcn20_calculate_dlg_params(dc, context, pipes, pipe_cnt, vlevel);
 
 	if (!pstate_en)
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 b37d14369a62..59836570603a 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
@@ -222,7 +222,7 @@ struct _vcs_dpi_ip_params_st dcn3_15_ip = {
 	.maximum_dsc_bits_per_component = 10,
 	.dsc422_native_support = false,
 	.is_line_buffer_bpp_fixed = true,
-	.line_buffer_fixed_bpp = 49,
+	.line_buffer_fixed_bpp = 48,
 	.line_buffer_size_bits = 789504,
 	.max_line_buffer_lines = 12,
 	.writeback_interface_buffer_size_kbytes = 90,
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn314/dcn314_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn314/dcn314_fpu.c
index 44082f65de1f..9e54e3d0eb78 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn314/dcn314_fpu.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn314/dcn314_fpu.c
@@ -149,8 +149,8 @@ static struct _vcs_dpi_soc_bounding_box_st dcn3_14_soc = {
 	.num_states = 5,
 	.sr_exit_time_us = 16.5,
 	.sr_enter_plus_exit_time_us = 18.5,
-	.sr_exit_z8_time_us = 210.0,
-	.sr_enter_plus_exit_z8_time_us = 310.0,
+	.sr_exit_z8_time_us = 268.0,
+	.sr_enter_plus_exit_z8_time_us = 393.0,
 	.writeback_latency_us = 12.0,
 	.dram_channel_width_bytes = 4,
 	.round_trip_ping_latency_dcfclk_cycles = 106,
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c
index 4548320217fc..47beb4ea779d 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c
@@ -109,7 +109,7 @@ struct _vcs_dpi_soc_bounding_box_st dcn3_2_soc = {
 		{
 			.state = 0,
 			.dcfclk_mhz = 1564.0,
-			.fabricclk_mhz = 400.0,
+			.fabricclk_mhz = 2500.0,
 			.dispclk_mhz = 2150.0,
 			.dppclk_mhz = 2150.0,
 			.phyclk_mhz = 810.0,
@@ -117,7 +117,7 @@ struct _vcs_dpi_soc_bounding_box_st dcn3_2_soc = {
 			.phyclk_d32_mhz = 625.0,
 			.socclk_mhz = 1200.0,
 			.dscclk_mhz = 716.667,
-			.dram_speed_mts = 16000.0,
+			.dram_speed_mts = 18000.0,
 			.dtbclk_mhz = 1564.0,
 		},
 	},
@@ -148,7 +148,7 @@ struct _vcs_dpi_soc_bounding_box_st dcn3_2_soc = {
 	.max_avg_fabric_bw_use_normal_percent = 60.0,
 	.max_avg_dram_bw_use_normal_strobe_percent = 50.0,
 	.max_avg_dram_bw_use_normal_percent = 15.0,
-	.num_chans = 8,
+	.num_chans = 24,
 	.dram_channel_width_bytes = 2,
 	.fabric_datapath_to_dcn_data_return_bytes = 64,
 	.return_bus_width_bytes = 64,
@@ -1331,6 +1331,11 @@ static void dcn32_calculate_dlg_params(struct dc *dc, struct dc_state *context,
 			context->bw_ctx.dml.vba.DRAMClockChangeSupport[vlevel][context->bw_ctx.dml.vba.maxMpcComb]
 					!= dm_dram_clock_change_unsupported;
 
+	/* Pstate change might not be supported by hardware, but it might be
+	 * possible with firmware driven vertical blank stretching.
+	 */
+	context->bw_ctx.bw.dcn.clk.p_state_change_support |= context->bw_ctx.bw.dcn.clk.fw_based_mclk_switching;
+
 	context->bw_ctx.bw.dcn.clk.dppclk_khz = 0;
 	context->bw_ctx.bw.dcn.clk.dtbclk_en = is_dtbclk_required(dc, context);
 	context->bw_ctx.bw.dcn.clk.ref_dtbclk_khz = context->bw_ctx.dml.vba.DTBCLKPerState[vlevel] * 1000;
@@ -2871,3 +2876,9 @@ bool dcn32_find_vactive_pipe(struct dc *dc, const struct dc_state *context, uint
 	}
 	return vactive_found;
 }
+
+void dcn32_set_clock_limits(const struct _vcs_dpi_soc_bounding_box_st *soc_bb)
+{
+	dc_assert_fp_enabled();
+	dcn3_2_soc.clock_limits[0].dcfclk_mhz = 1200.0;
+}
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.h b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.h
index 9a0806a0e2ef..dcf512cd3072 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.h
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.h
@@ -80,4 +80,6 @@ void dcn32_assign_fpo_vactive_candidate(struct dc *dc, const struct dc_state *co
 
 bool dcn32_find_vactive_pipe(struct dc *dc, const struct dc_state *context, uint32_t vactive_margin_req);
 
+void dcn32_set_clock_limits(const struct _vcs_dpi_soc_bounding_box_st *soc_bb);
+
 #endif
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn321/dcn321_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn321/dcn321_fpu.c
index 57b9bd896678..342a1bcb4927 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn321/dcn321_fpu.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn321/dcn321_fpu.c
@@ -106,16 +106,16 @@ struct _vcs_dpi_soc_bounding_box_st dcn3_21_soc = {
 	.clock_limits = {
 		{
 			.state = 0,
-			.dcfclk_mhz = 1564.0,
-			.fabricclk_mhz = 400.0,
-			.dispclk_mhz = 2150.0,
-			.dppclk_mhz = 2150.0,
+			.dcfclk_mhz = 1434.0,
+			.fabricclk_mhz = 2250.0,
+			.dispclk_mhz = 1720.0,
+			.dppclk_mhz = 1720.0,
 			.phyclk_mhz = 810.0,
 			.phyclk_d18_mhz = 667.0,
-			.phyclk_d32_mhz = 625.0,
+			.phyclk_d32_mhz = 313.0,
 			.socclk_mhz = 1200.0,
-			.dscclk_mhz = 716.667,
-			.dram_speed_mts = 1600.0,
+			.dscclk_mhz = 573.333,
+			.dram_speed_mts = 16000.0,
 			.dtbclk_mhz = 1564.0,
 		},
 	},
@@ -125,14 +125,14 @@ struct _vcs_dpi_soc_bounding_box_st dcn3_21_soc = {
 	.sr_exit_z8_time_us = 285.0,
 	.sr_enter_plus_exit_z8_time_us = 320,
 	.writeback_latency_us = 12.0,
-	.round_trip_ping_latency_dcfclk_cycles = 263,
+	.round_trip_ping_latency_dcfclk_cycles = 207,
 	.urgent_latency_pixel_data_only_us = 4,
 	.urgent_latency_pixel_mixed_with_vm_data_us = 4,
 	.urgent_latency_vm_data_only_us = 4,
-	.fclk_change_latency_us = 20,
-	.usr_retraining_latency_us = 2,
-	.smn_latency_us = 2,
-	.mall_allocated_for_dcn_mbytes = 64,
+	.fclk_change_latency_us = 7,
+	.usr_retraining_latency_us = 0,
+	.smn_latency_us = 0,
+	.mall_allocated_for_dcn_mbytes = 32,
 	.urgent_out_of_order_return_per_channel_pixel_only_bytes = 4096,
 	.urgent_out_of_order_return_per_channel_pixel_and_vm_bytes = 4096,
 	.urgent_out_of_order_return_per_channel_vm_only_bytes = 4096,
diff --git a/drivers/gpu/drm/amd/display/dc/link/link_dpms.c b/drivers/gpu/drm/amd/display/dc/link/link_dpms.c
index 027ad1f0144d..2267fb097830 100644
--- a/drivers/gpu/drm/amd/display/dc/link/link_dpms.c
+++ b/drivers/gpu/drm/amd/display/dc/link/link_dpms.c
@@ -1927,6 +1927,11 @@ static void disable_link_dp(struct dc_link *link,
 
 	dp_disable_link_phy(link, link_res, signal);
 
+	if (link->connector_signal == SIGNAL_TYPE_EDP) {
+		if (!link->dc->config.edp_no_power_sequencing)
+			link->dc->hwss.edp_power_control(link, false);
+	}
+
 	if (signal == SIGNAL_TYPE_DISPLAY_PORT_MST)
 		/* set the sink to SST mode after disabling the link */
 		enable_mst_on_sink(link, false);
diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training.c
index 170f33835930..579fa222810d 100644
--- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training.c
+++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training.c
@@ -1596,7 +1596,10 @@ bool perform_link_training_with_retries(
 				 * Report and continue with eDP panel mode to
 				 * perform eDP link training with right settings
 				 */
-				cp_psp->funcs.enable_assr(cp_psp->handle, link);
+				bool result;
+				result = cp_psp->funcs.enable_assr(cp_psp->handle, link);
+				if (!result && link->panel_mode != DP_PANEL_MODE_EDP)
+					panel_mode = DP_PANEL_MODE_DEFAULT;
 			}
 		}
 
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 d895046787bc..8d1df863659c 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
@@ -83,6 +83,7 @@ void dp_set_panel_mode(struct dc_link *link, enum dp_panel_mode panel_mode)
 			ASSERT(result == DC_OK);
 		}
 	}
+	link->panel_mode = panel_mode;
 	DC_LOG_DETECTION_DP_CAPS("Link: %d eDP panel mode supported: %d "
 		 "eDP panel mode enabled: %d \n",
 		 link->link_index,
diff --git a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn32.c b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn32.c
index a76da0131add..9c20516be066 100644
--- a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn32.c
+++ b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn32.c
@@ -130,12 +130,13 @@ void dmub_dcn32_reset(struct dmub_srv *dmub)
 	REG_WRITE(DMCUB_INBOX1_WPTR, 0);
 	REG_WRITE(DMCUB_OUTBOX1_RPTR, 0);
 	REG_WRITE(DMCUB_OUTBOX1_WPTR, 0);
+	REG_WRITE(DMCUB_OUTBOX0_RPTR, 0);
+	REG_WRITE(DMCUB_OUTBOX0_WPTR, 0);
 	REG_WRITE(DMCUB_SCRATCH0, 0);
 }
 
 void dmub_dcn32_reset_release(struct dmub_srv *dmub)
 {
-	REG_WRITE(DMCUB_GPINT_DATAIN1, 0);
 	REG_UPDATE(MMHUBBUB_SOFT_RESET, DMUIF_SOFT_RESET, 0);
 	REG_WRITE(DMCUB_SCRATCH15, dmub->psp_version & 0x001100FF);
 	REG_UPDATE_2(DMCUB_CNTL, DMCUB_ENABLE, 1, DMCUB_TRACEPORT_EN, 1);
diff --git a/drivers/gpu/drm/amd/display/include/signal_types.h b/drivers/gpu/drm/amd/display/include/signal_types.h
index beed70179bb5..23a308c3eccb 100644
--- a/drivers/gpu/drm/amd/display/include/signal_types.h
+++ b/drivers/gpu/drm/amd/display/include/signal_types.h
@@ -104,6 +104,7 @@ static inline bool dc_is_audio_capable_signal(enum signal_type signal)
 {
 	return (signal == SIGNAL_TYPE_DISPLAY_PORT ||
 		signal == SIGNAL_TYPE_DISPLAY_PORT_MST ||
+		signal == SIGNAL_TYPE_VIRTUAL ||
 		dc_is_hdmi_signal(signal));
 }
 
diff --git a/drivers/gpu/drm/amd/display/modules/power/power_helpers.c b/drivers/gpu/drm/amd/display/modules/power/power_helpers.c
index 0d3a983cb9ec..51e76bce92ea 100644
--- a/drivers/gpu/drm/amd/display/modules/power/power_helpers.c
+++ b/drivers/gpu/drm/amd/display/modules/power/power_helpers.c
@@ -927,6 +927,10 @@ bool psr_su_set_dsc_slice_height(struct dc *dc, struct dc_link *link,
 
 	pic_height = stream->timing.v_addressable +
 		stream->timing.v_border_top + stream->timing.v_border_bottom;
+
+	if (stream->timing.dsc_cfg.num_slices_v == 0)
+		return false;
+
 	slice_height = pic_height / stream->timing.dsc_cfg.num_slices_v;
 	config->dsc_slice_height = slice_height;
 
diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h
index 7944ce80e5c3..df3baaab0037 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h
@@ -62,8 +62,8 @@
 #define CTF_OFFSET_HOTSPOT		5
 #define CTF_OFFSET_MEM			5
 
-static const int pmfw_decoded_link_speed[5] = {1, 2, 3, 4, 5};
-static const int pmfw_decoded_link_width[7] = {0, 1, 2, 4, 8, 12, 16};
+extern const int pmfw_decoded_link_speed[5];
+extern const int pmfw_decoded_link_width[7];
 
 #define DECODE_GEN_SPEED(gen_speed_idx)		(pmfw_decoded_link_speed[gen_speed_idx])
 #define DECODE_LANE_WIDTH(lane_width_idx)	(pmfw_decoded_link_width[lane_width_idx])
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 73175c993da9..393c6a7b9609 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
@@ -85,6 +85,9 @@ MODULE_FIRMWARE("amdgpu/smu_13_0_10.bin");
 static const int link_width[] = {0, 1, 2, 4, 8, 12, 16};
 static const int link_speed[] = {25, 50, 80, 160};
 
+const int pmfw_decoded_link_speed[5] = {1, 2, 3, 4, 5};
+const int pmfw_decoded_link_width[7] = {0, 1, 2, 4, 8, 12, 16};
+
 int smu_v13_0_init_microcode(struct smu_context *smu)
 {
 	struct amdgpu_device *adev = smu->adev;
diff --git a/drivers/gpu/drm/armada/armada_drv.c b/drivers/gpu/drm/armada/armada_drv.c
index 22efd0f29521..e120144d4b47 100644
--- a/drivers/gpu/drm/armada/armada_drv.c
+++ b/drivers/gpu/drm/armada/armada_drv.c
@@ -97,7 +97,6 @@ static int armada_drm_bind(struct device *dev)
 	if (ret) {
 		dev_err(dev, "[" DRM_NAME ":%s] can't kick out simple-fb: %d\n",
 			__func__, ret);
-		kfree(priv);
 		return ret;
 	}
 
diff --git a/drivers/gpu/drm/display/drm_dp_aux_dev.c b/drivers/gpu/drm/display/drm_dp_aux_dev.c
index 098e482e65a2..29555b9f03c8 100644
--- a/drivers/gpu/drm/display/drm_dp_aux_dev.c
+++ b/drivers/gpu/drm/display/drm_dp_aux_dev.c
@@ -330,7 +330,7 @@ int drm_dp_aux_dev_init(void)
 {
 	int res;
 
-	drm_dp_aux_dev_class = class_create(THIS_MODULE, "drm_dp_aux_dev");
+	drm_dp_aux_dev_class = class_create("drm_dp_aux_dev");
 	if (IS_ERR(drm_dp_aux_dev_class)) {
 		return PTR_ERR(drm_dp_aux_dev_class);
 	}
diff --git a/drivers/gpu/drm/drm_buddy.c b/drivers/gpu/drm/drm_buddy.c
index 3d1f50f481cf..7098f125b54a 100644
--- a/drivers/gpu/drm/drm_buddy.c
+++ b/drivers/gpu/drm/drm_buddy.c
@@ -146,8 +146,8 @@ int drm_buddy_init(struct drm_buddy *mm, u64 size, u64 chunk_size)
 		unsigned int order;
 		u64 root_size;
 
-		root_size = rounddown_pow_of_two(size);
-		order = ilog2(root_size) - ilog2(chunk_size);
+		order = ilog2(size) - ilog2(chunk_size);
+		root_size = chunk_size << order;
 
 		root = drm_block_alloc(mm, NULL, order, offset);
 		if (!root)
diff --git a/drivers/gpu/drm/drm_mipi_dsi.c b/drivers/gpu/drm/drm_mipi_dsi.c
index 7900a4707d7c..295382cd09b0 100644
--- a/drivers/gpu/drm/drm_mipi_dsi.c
+++ b/drivers/gpu/drm/drm_mipi_dsi.c
@@ -160,7 +160,7 @@ of_mipi_dsi_device_add(struct mipi_dsi_host *host, struct device_node *node)
 	int ret;
 	u32 reg;
 
-	if (of_modalias_node(node, info.type, sizeof(info.type)) < 0) {
+	if (of_alias_from_compatible(node, info.type, sizeof(info.type)) < 0) {
 		drm_err(host, "modalias failure on %pOF\n", node);
 		return ERR_PTR(-EINVAL);
 	}
diff --git a/drivers/gpu/drm/drm_sysfs.c b/drivers/gpu/drm/drm_sysfs.c
index 62ce80b3eebc..f62767ff34b2 100644
--- a/drivers/gpu/drm/drm_sysfs.c
+++ b/drivers/gpu/drm/drm_sysfs.c
@@ -142,7 +142,7 @@ int drm_sysfs_init(void)
 {
 	int err;
 
-	drm_class = class_create(THIS_MODULE, "drm");
+	drm_class = class_create("drm");
 	if (IS_ERR(drm_class))
 		return PTR_ERR(drm_class);
 
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_drv.c b/drivers/gpu/drm/etnaviv/etnaviv_drv.c
index 44ca803237a5..31a7f59ccb49 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_drv.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_drv.c
@@ -22,7 +22,6 @@
 #include "etnaviv_gem.h"
 #include "etnaviv_mmu.h"
 #include "etnaviv_perfmon.h"
-#include "common.xml.h"
 
 /*
  * DRM operations:
@@ -476,47 +475,7 @@ static const struct drm_ioctl_desc etnaviv_ioctls[] = {
 	ETNA_IOCTL(PM_QUERY_SIG, pm_query_sig, DRM_RENDER_ALLOW),
 };
 
-static void etnaviv_fop_show_fdinfo(struct seq_file *m, struct file *f)
-{
-	struct drm_file *file = f->private_data;
-	struct drm_device *dev = file->minor->dev;
-	struct etnaviv_drm_private *priv = dev->dev_private;
-	struct etnaviv_file_private *ctx = file->driver_priv;
-
-	/*
-	 * For a description of the text output format used here, see
-	 * Documentation/gpu/drm-usage-stats.rst.
-	 */
-	seq_printf(m, "drm-driver:\t%s\n", dev->driver->name);
-	seq_printf(m, "drm-client-id:\t%u\n", ctx->id);
-
-	for (int i = 0; i < ETNA_MAX_PIPES; i++) {
-		struct etnaviv_gpu *gpu = priv->gpu[i];
-		char engine[10] = "UNK";
-		int cur = 0;
-
-		if (!gpu)
-			continue;
-
-		if (gpu->identity.features & chipFeatures_PIPE_2D)
-			cur = snprintf(engine, sizeof(engine), "2D");
-		if (gpu->identity.features & chipFeatures_PIPE_3D)
-			cur = snprintf(engine + cur, sizeof(engine) - cur,
-				       "%s3D", cur ? "/" : "");
-		if (gpu->identity.nn_core_count > 0)
-			cur = snprintf(engine + cur, sizeof(engine) - cur,
-				       "%sNN", cur ? "/" : "");
-
-		seq_printf(m, "drm-engine-%s:\t%llu ns\n", engine,
-			   ctx->sched_entity[i].elapsed_ns);
-	}
-}
-
-static const struct file_operations fops = {
-	.owner = THIS_MODULE,
-	DRM_GEM_FOPS,
-	.show_fdinfo = etnaviv_fop_show_fdinfo,
-};
+DEFINE_DRM_GEM_FOPS(fops);
 
 static const struct drm_driver etnaviv_drm_driver = {
 	.driver_features    = DRIVER_GEM | DRIVER_RENDER,
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem_prime.c b/drivers/gpu/drm/etnaviv/etnaviv_gem_prime.c
index 7031db145a77..3524b5811682 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_gem_prime.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_gem_prime.c
@@ -91,7 +91,15 @@ static void *etnaviv_gem_prime_vmap_impl(struct etnaviv_gem_object *etnaviv_obj)
 static int etnaviv_gem_prime_mmap_obj(struct etnaviv_gem_object *etnaviv_obj,
 		struct vm_area_struct *vma)
 {
-	return dma_buf_mmap(etnaviv_obj->base.dma_buf, vma, 0);
+	int ret;
+
+	ret = dma_buf_mmap(etnaviv_obj->base.dma_buf, vma, 0);
+	if (!ret) {
+		/* Drop the reference acquired by drm_gem_mmap_obj(). */
+		drm_gem_object_put(&etnaviv_obj->base);
+	}
+
+	return ret;
 }
 
 static const struct etnaviv_gem_ops etnaviv_gem_prime_ops = {
diff --git a/drivers/gpu/drm/i915/display/icl_dsi.c b/drivers/gpu/drm/i915/display/icl_dsi.c
index ad78148e0788..c9aeba0ecf91 100644
--- a/drivers/gpu/drm/i915/display/icl_dsi.c
+++ b/drivers/gpu/drm/i915/display/icl_dsi.c
@@ -1140,7 +1140,7 @@ static void gen11_dsi_powerup_panel(struct intel_encoder *encoder)
 
 	/* panel power on related mipi dsi vbt sequences */
 	intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_POWER_ON);
-	intel_dsi_msleep(intel_dsi, intel_dsi->panel_on_delay);
+	msleep(intel_dsi->panel_on_delay);
 	intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_DEASSERT_RESET);
 	intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_INIT_OTP);
 	intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_DISPLAY_ON);
diff --git a/drivers/gpu/drm/i915/display/intel_dsi_vbt.c b/drivers/gpu/drm/i915/display/intel_dsi_vbt.c
index 695b0d69a4cb..c7935ea498c4 100644
--- a/drivers/gpu/drm/i915/display/intel_dsi_vbt.c
+++ b/drivers/gpu/drm/i915/display/intel_dsi_vbt.c
@@ -763,17 +763,6 @@ void intel_dsi_vbt_exec_sequence(struct intel_dsi *intel_dsi,
 		gpiod_set_value_cansleep(intel_dsi->gpio_backlight, 0);
 }
 
-void intel_dsi_msleep(struct intel_dsi *intel_dsi, int msec)
-{
-	struct intel_connector *connector = intel_dsi->attached_connector;
-
-	/* For v3 VBTs in vid-mode the delays are part of the VBT sequences */
-	if (is_vid_mode(intel_dsi) && connector->panel.vbt.dsi.seq_version >= 3)
-		return;
-
-	msleep(msec);
-}
-
 void intel_dsi_log_params(struct intel_dsi *intel_dsi)
 {
 	struct drm_i915_private *i915 = to_i915(intel_dsi->base.base.dev);
diff --git a/drivers/gpu/drm/i915/display/intel_dsi_vbt.h b/drivers/gpu/drm/i915/display/intel_dsi_vbt.h
index dc642c1fe7ef..468d873fab1a 100644
--- a/drivers/gpu/drm/i915/display/intel_dsi_vbt.h
+++ b/drivers/gpu/drm/i915/display/intel_dsi_vbt.h
@@ -16,7 +16,6 @@ void intel_dsi_vbt_gpio_init(struct intel_dsi *intel_dsi, bool panel_is_on);
 void intel_dsi_vbt_gpio_cleanup(struct intel_dsi *intel_dsi);
 void intel_dsi_vbt_exec_sequence(struct intel_dsi *intel_dsi,
 				 enum mipi_seq seq_id);
-void intel_dsi_msleep(struct intel_dsi *intel_dsi, int msec);
 void intel_dsi_log_params(struct intel_dsi *intel_dsi);
 
 #endif /* __INTEL_DSI_VBT_H__ */
diff --git a/drivers/gpu/drm/i915/display/skl_scaler.c b/drivers/gpu/drm/i915/display/skl_scaler.c
index 473d53610b92..0e7e014fcc71 100644
--- a/drivers/gpu/drm/i915/display/skl_scaler.c
+++ b/drivers/gpu/drm/i915/display/skl_scaler.c
@@ -111,6 +111,8 @@ skl_update_scaler(struct intel_crtc_state *crtc_state, bool force_detach,
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	const struct drm_display_mode *adjusted_mode =
 		&crtc_state->hw.adjusted_mode;
+	int pipe_src_w = drm_rect_width(&crtc_state->pipe_src);
+	int pipe_src_h = drm_rect_height(&crtc_state->pipe_src);
 	int min_src_w, min_src_h, min_dst_w, min_dst_h;
 	int max_src_w, max_src_h, max_dst_w, max_dst_h;
 
@@ -207,6 +209,21 @@ skl_update_scaler(struct intel_crtc_state *crtc_state, bool force_detach,
 		return -EINVAL;
 	}
 
+	/*
+	 * The pipe scaler does not use all the bits of PIPESRC, at least
+	 * on the earlier platforms. So even when we're scaling a plane
+	 * the *pipe* source size must not be too large. For simplicity
+	 * we assume the limits match the scaler source size limits. Might
+	 * not be 100% accurate on all platforms, but good enough for now.
+	 */
+	if (pipe_src_w > max_src_w || pipe_src_h > max_src_h) {
+		drm_dbg_kms(&dev_priv->drm,
+			    "scaler_user index %u.%u: pipe src size %ux%u "
+			    "is out of scaler range\n",
+			    crtc->pipe, scaler_user, pipe_src_w, pipe_src_h);
+		return -EINVAL;
+	}
+
 	/* mark this plane as a scaler user in crtc_state */
 	scaler_state->scaler_users |= (1 << scaler_user);
 	drm_dbg_kms(&dev_priv->drm, "scaler_user index %u.%u: "
diff --git a/drivers/gpu/drm/i915/display/vlv_dsi.c b/drivers/gpu/drm/i915/display/vlv_dsi.c
index 028965ab442d..61d008d4e5f1 100644
--- a/drivers/gpu/drm/i915/display/vlv_dsi.c
+++ b/drivers/gpu/drm/i915/display/vlv_dsi.c
@@ -737,7 +737,6 @@ static void intel_dsi_pre_enable(struct intel_atomic_state *state,
 {
 	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
 	struct intel_crtc *crtc = to_intel_crtc(pipe_config->uapi.crtc);
-	struct intel_connector *connector = to_intel_connector(conn_state->connector);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	enum pipe pipe = crtc->pipe;
 	enum port port;
@@ -779,21 +778,10 @@ static void intel_dsi_pre_enable(struct intel_atomic_state *state,
 	if (!IS_GEMINILAKE(dev_priv))
 		intel_dsi_prepare(encoder, pipe_config);
 
+	/* Give the panel time to power-on and then deassert its reset */
 	intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_POWER_ON);
-
-	/*
-	 * Give the panel time to power-on and then deassert its reset.
-	 * Depending on the VBT MIPI sequences version the deassert-seq
-	 * may contain the necessary delay, intel_dsi_msleep() will skip
-	 * the delay in that case. If there is no deassert-seq, then an
-	 * unconditional msleep is used to give the panel time to power-on.
-	 */
-	if (connector->panel.vbt.dsi.sequence[MIPI_SEQ_DEASSERT_RESET]) {
-		intel_dsi_msleep(intel_dsi, intel_dsi->panel_on_delay);
-		intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_DEASSERT_RESET);
-	} else {
-		msleep(intel_dsi->panel_on_delay);
-	}
+	msleep(intel_dsi->panel_on_delay);
+	intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_DEASSERT_RESET);
 
 	if (IS_GEMINILAKE(dev_priv)) {
 		glk_cold_boot = glk_dsi_enable_io(encoder);
@@ -827,7 +815,7 @@ static void intel_dsi_pre_enable(struct intel_atomic_state *state,
 		msleep(20); /* XXX */
 		for_each_dsi_port(port, intel_dsi->ports)
 			dpi_send_cmd(intel_dsi, TURN_ON, false, port);
-		intel_dsi_msleep(intel_dsi, 100);
+		msleep(100);
 
 		intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_DISPLAY_ON);
 
@@ -949,7 +937,7 @@ static void intel_dsi_post_disable(struct intel_atomic_state *state,
 	/* Assert reset */
 	intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_ASSERT_RESET);
 
-	intel_dsi_msleep(intel_dsi, intel_dsi->panel_off_delay);
+	msleep(intel_dsi->panel_off_delay);
 	intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_POWER_OFF);
 
 	intel_dsi->panel_power_off_time = ktime_get_boottime();
diff --git a/drivers/gpu/drm/i915/gem/selftests/huge_pages.c b/drivers/gpu/drm/i915/gem/selftests/huge_pages.c
index defece0bcb81..99f39a5feca1 100644
--- a/drivers/gpu/drm/i915/gem/selftests/huge_pages.c
+++ b/drivers/gpu/drm/i915/gem/selftests/huge_pages.c
@@ -115,7 +115,7 @@ static int get_huge_pages(struct drm_i915_gem_object *obj)
 		do {
 			struct page *page;
 
-			GEM_BUG_ON(order >= MAX_ORDER);
+			GEM_BUG_ON(order > MAX_ORDER);
 			page = alloc_pages(GFP | __GFP_ZERO, order);
 			if (!page)
 				goto err;
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_huc.c b/drivers/gpu/drm/i915/gt/uc/intel_huc.c
index aefdaa62da99..04724ff56ded 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_huc.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_huc.c
@@ -190,7 +190,7 @@ static int gsc_notifier(struct notifier_block *nb, unsigned long action, void *d
 	return 0;
 }
 
-void intel_huc_register_gsc_notifier(struct intel_huc *huc, struct bus_type *bus)
+void intel_huc_register_gsc_notifier(struct intel_huc *huc, const struct bus_type *bus)
 {
 	int ret;
 
@@ -206,7 +206,7 @@ void intel_huc_register_gsc_notifier(struct intel_huc *huc, struct bus_type *bus
 	}
 }
 
-void intel_huc_unregister_gsc_notifier(struct intel_huc *huc, struct bus_type *bus)
+void intel_huc_unregister_gsc_notifier(struct intel_huc *huc, const struct bus_type *bus)
 {
 	if (!huc->delayed_load.nb.notifier_call)
 		return;
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_huc.h b/drivers/gpu/drm/i915/gt/uc/intel_huc.h
index db555b3c1f56..0789184d81a2 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_huc.h
+++ b/drivers/gpu/drm/i915/gt/uc/intel_huc.h
@@ -52,8 +52,8 @@ int intel_huc_check_status(struct intel_huc *huc);
 void intel_huc_update_auth_status(struct intel_huc *huc);
 bool intel_huc_is_authenticated(struct intel_huc *huc);
 
-void intel_huc_register_gsc_notifier(struct intel_huc *huc, struct bus_type *bus);
-void intel_huc_unregister_gsc_notifier(struct intel_huc *huc, struct bus_type *bus);
+void intel_huc_register_gsc_notifier(struct intel_huc *huc, const struct bus_type *bus);
+void intel_huc_unregister_gsc_notifier(struct intel_huc *huc, const struct bus_type *bus);
 
 static inline bool intel_huc_is_supported(struct intel_huc *huc)
 {
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c
index 24765c30a0e1..c36e68e23a14 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c
@@ -635,9 +635,10 @@ static bool is_ver_8bit(struct intel_uc_fw_ver *ver)
 	return ver->major < 0xFF && ver->minor < 0xFF && ver->patch < 0xFF;
 }
 
-static bool guc_check_version_range(struct intel_uc_fw *uc_fw)
+static int guc_check_version_range(struct intel_uc_fw *uc_fw)
 {
 	struct intel_guc *guc = container_of(uc_fw, struct intel_guc, fw);
+	struct intel_gt *gt = __uc_fw_to_gt(uc_fw);
 
 	/*
 	 * GuC version number components are defined as being 8-bits.
@@ -646,24 +647,24 @@ static bool guc_check_version_range(struct intel_uc_fw *uc_fw)
 	 */
 
 	if (!is_ver_8bit(&uc_fw->file_selected.ver)) {
-		gt_warn(__uc_fw_to_gt(uc_fw), "%s firmware: invalid file version: 0x%02X:%02X:%02X\n",
+		gt_warn(gt, "%s firmware: invalid file version: 0x%02X:%02X:%02X\n",
 			intel_uc_fw_type_repr(uc_fw->type),
 			uc_fw->file_selected.ver.major,
 			uc_fw->file_selected.ver.minor,
 			uc_fw->file_selected.ver.patch);
-		return false;
+		return -EINVAL;
 	}
 
 	if (!is_ver_8bit(&guc->submission_version)) {
-		gt_warn(__uc_fw_to_gt(uc_fw), "%s firmware: invalid submit version: 0x%02X:%02X:%02X\n",
+		gt_warn(gt, "%s firmware: invalid submit version: 0x%02X:%02X:%02X\n",
 			intel_uc_fw_type_repr(uc_fw->type),
 			guc->submission_version.major,
 			guc->submission_version.minor,
 			guc->submission_version.patch);
-		return false;
+		return -EINVAL;
 	}
 
-	return true;
+	return i915_inject_probe_error(gt->i915, -EINVAL);
 }
 
 static int check_fw_header(struct intel_gt *gt,
@@ -772,8 +773,11 @@ int intel_uc_fw_fetch(struct intel_uc_fw *uc_fw)
 	if (err)
 		goto fail;
 
-	if (uc_fw->type == INTEL_UC_FW_TYPE_GUC && !guc_check_version_range(uc_fw))
-		goto fail;
+	if (uc_fw->type == INTEL_UC_FW_TYPE_GUC) {
+		err = guc_check_version_range(uc_fw);
+		if (err)
+			goto fail;
+	}
 
 	if (uc_fw->file_wanted.ver.major && uc_fw->file_selected.ver.major) {
 		/* Check the file's major version was as it claimed */
diff --git a/drivers/gpu/drm/i915/i915_pci.c b/drivers/gpu/drm/i915/i915_pci.c
index cddb6e197972..2a012da8ccfa 100644
--- a/drivers/gpu/drm/i915/i915_pci.c
+++ b/drivers/gpu/drm/i915/i915_pci.c
@@ -1134,6 +1134,8 @@ static const struct intel_gt_definition xelpmp_extra_gt[] = {
 static const struct intel_device_info mtl_info = {
 	XE_HP_FEATURES,
 	XE_LPDP_FEATURES,
+	.__runtime.cpu_transcoder_mask = BIT(TRANSCODER_A) | BIT(TRANSCODER_B) |
+			       BIT(TRANSCODER_C) | BIT(TRANSCODER_D),
 	/*
 	 * Real graphics IP version will be obtained from hardware GMD_ID
 	 * register.  Value provided here is just for sanity checking.
diff --git a/drivers/gpu/drm/nouveau/dispnv50/disp.c b/drivers/gpu/drm/nouveau/dispnv50/disp.c
index ed9d374147b8..5bb777ff1313 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/disp.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/disp.c
@@ -363,6 +363,35 @@ nv50_outp_atomic_check_view(struct drm_encoder *encoder,
 	return 0;
 }
 
+static void
+nv50_outp_atomic_fix_depth(struct drm_encoder *encoder, struct drm_crtc_state *crtc_state)
+{
+	struct nv50_head_atom *asyh = nv50_head_atom(crtc_state);
+	struct nouveau_encoder *nv_encoder = nouveau_encoder(encoder);
+	struct drm_display_mode *mode = &asyh->state.adjusted_mode;
+	unsigned int max_rate, mode_rate;
+
+	switch (nv_encoder->dcb->type) {
+	case DCB_OUTPUT_DP:
+		max_rate = nv_encoder->dp.link_nr * nv_encoder->dp.link_bw;
+
+		/* we don't support more than 10 anyway */
+		asyh->or.bpc = min_t(u8, asyh->or.bpc, 10);
+
+		/* reduce the bpc until it works out */
+		while (asyh->or.bpc > 6) {
+			mode_rate = DIV_ROUND_UP(mode->clock * asyh->or.bpc * 3, 8);
+			if (mode_rate <= max_rate)
+				break;
+
+			asyh->or.bpc -= 2;
+		}
+		break;
+	default:
+		break;
+	}
+}
+
 static int
 nv50_outp_atomic_check(struct drm_encoder *encoder,
 		       struct drm_crtc_state *crtc_state,
@@ -381,6 +410,9 @@ nv50_outp_atomic_check(struct drm_encoder *encoder,
 	if (crtc_state->mode_changed || crtc_state->connectors_changed)
 		asyh->or.bpc = connector->display_info.bpc;
 
+	/* We might have to reduce the bpc */
+	nv50_outp_atomic_fix_depth(encoder, crtc_state);
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_backlight.c b/drivers/gpu/drm/nouveau/nouveau_backlight.c
index 40409a29f5b6..91b5ecc57538 100644
--- a/drivers/gpu/drm/nouveau/nouveau_backlight.c
+++ b/drivers/gpu/drm/nouveau/nouveau_backlight.c
@@ -33,6 +33,7 @@
 #include <linux/apple-gmux.h>
 #include <linux/backlight.h>
 #include <linux/idr.h>
+#include <drm/drm_probe_helper.h>
 
 #include "nouveau_drv.h"
 #include "nouveau_reg.h"
@@ -299,8 +300,12 @@ nv50_backlight_init(struct nouveau_backlight *bl,
 	struct nouveau_drm *drm = nouveau_drm(nv_encoder->base.base.dev);
 	struct nvif_object *device = &drm->client.device.object;
 
+	/*
+	 * Note when this runs the connectors have not been probed yet,
+	 * so nv_conn->base.status is not set yet.
+	 */
 	if (!nvif_rd32(device, NV50_PDISP_SOR_PWM_CTL(ffs(nv_encoder->dcb->or) - 1)) ||
-	    nv_conn->base.status != connector_status_connected)
+	    drm_helper_probe_detect(&nv_conn->base, NULL, false) != connector_status_connected)
 		return -ENODEV;
 
 	if (nv_conn->type == DCB_CONNECTOR_eDP) {
diff --git a/drivers/gpu/drm/nouveau/nouveau_dp.c b/drivers/gpu/drm/nouveau/nouveau_dp.c
index e00876f92aee..d49b4875fc3c 100644
--- a/drivers/gpu/drm/nouveau/nouveau_dp.c
+++ b/drivers/gpu/drm/nouveau/nouveau_dp.c
@@ -263,8 +263,6 @@ nouveau_dp_irq(struct work_struct *work)
 }
 
 /* TODO:
- * - Use the minimum possible BPC here, once we add support for the max bpc
- *   property.
  * - Validate against the DP caps advertised by the GPU (we don't check these
  *   yet)
  */
@@ -276,7 +274,11 @@ nv50_dp_mode_valid(struct drm_connector *connector,
 {
 	const unsigned int min_clock = 25000;
 	unsigned int max_rate, mode_rate, ds_max_dotclock, clock = mode->clock;
-	const u8 bpp = connector->display_info.bpc * 3;
+	/* Check with the minmum bpc always, so we can advertise better modes.
+	 * In particlar not doing this causes modes to be dropped on HDR
+	 * displays as we might check with a bpc of 16 even.
+	 */
+	const u8 bpp = 6 * 3;
 
 	if (mode->flags & DRM_MODE_FLAG_INTERLACE && !outp->caps.dp_interlace)
 		return MODE_NO_INTERLACE;
diff --git a/drivers/gpu/drm/nouveau/nouveau_gem.c b/drivers/gpu/drm/nouveau/nouveau_gem.c
index f77e44958037..ab9062e50977 100644
--- a/drivers/gpu/drm/nouveau/nouveau_gem.c
+++ b/drivers/gpu/drm/nouveau/nouveau_gem.c
@@ -645,7 +645,7 @@ nouveau_gem_pushbuf_reloc_apply(struct nouveau_cli *cli,
 				struct drm_nouveau_gem_pushbuf_reloc *reloc,
 				struct drm_nouveau_gem_pushbuf_bo *bo)
 {
-	long ret = 0;
+	int ret = 0;
 	unsigned i;
 
 	for (i = 0; i < req->nr_relocs; i++) {
@@ -653,6 +653,7 @@ nouveau_gem_pushbuf_reloc_apply(struct nouveau_cli *cli,
 		struct drm_nouveau_gem_pushbuf_bo *b;
 		struct nouveau_bo *nvbo;
 		uint32_t data;
+		long lret;
 
 		if (unlikely(r->bo_index >= req->nr_buffers)) {
 			NV_PRINTK(err, cli, "reloc bo index invalid\n");
@@ -703,13 +704,18 @@ nouveau_gem_pushbuf_reloc_apply(struct nouveau_cli *cli,
 				data |= r->vor;
 		}
 
-		ret = dma_resv_wait_timeout(nvbo->bo.base.resv,
-					    DMA_RESV_USAGE_BOOKKEEP,
-					    false, 15 * HZ);
-		if (ret == 0)
+		lret = dma_resv_wait_timeout(nvbo->bo.base.resv,
+					     DMA_RESV_USAGE_BOOKKEEP,
+					     false, 15 * HZ);
+		if (!lret)
 			ret = -EBUSY;
+		else if (lret > 0)
+			ret = 0;
+		else
+			ret = lret;
+
 		if (ret) {
-			NV_PRINTK(err, cli, "reloc wait_idle failed: %ld\n",
+			NV_PRINTK(err, cli, "reloc wait_idle failed: %d\n",
 				  ret);
 			break;
 		}
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gf108.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gf108.c
index 76678dd60f93..c4c6f67af7cc 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gf108.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gf108.c
@@ -31,6 +31,7 @@ gf108_fb = {
 	.init = gf100_fb_init,
 	.init_page = gf100_fb_init_page,
 	.intr = gf100_fb_intr,
+	.sysmem.flush_page_init = gf100_fb_sysmem_flush_page_init,
 	.ram_new = gf108_ram_new,
 	.default_bigpage = 17,
 };
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gk104.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gk104.c
index f73442ccb424..433fa966ba23 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gk104.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gk104.c
@@ -77,6 +77,7 @@ gk104_fb = {
 	.init = gf100_fb_init,
 	.init_page = gf100_fb_init_page,
 	.intr = gf100_fb_intr,
+	.sysmem.flush_page_init = gf100_fb_sysmem_flush_page_init,
 	.ram_new = gk104_ram_new,
 	.default_bigpage = 17,
 	.clkgate_pack = gk104_fb_clkgate_pack,
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gk110.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gk110.c
index 45d6cdffafee..4dc283dedf8b 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gk110.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gk110.c
@@ -59,6 +59,7 @@ gk110_fb = {
 	.init = gf100_fb_init,
 	.init_page = gf100_fb_init_page,
 	.intr = gf100_fb_intr,
+	.sysmem.flush_page_init = gf100_fb_sysmem_flush_page_init,
 	.ram_new = gk104_ram_new,
 	.default_bigpage = 17,
 	.clkgate_pack = gk110_fb_clkgate_pack,
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gm107.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gm107.c
index de52462a92bf..90bfff616d35 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gm107.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gm107.c
@@ -31,6 +31,7 @@ gm107_fb = {
 	.init = gf100_fb_init,
 	.init_page = gf100_fb_init_page,
 	.intr = gf100_fb_intr,
+	.sysmem.flush_page_init = gf100_fb_sysmem_flush_page_init,
 	.ram_new = gm107_ram_new,
 	.default_bigpage = 17,
 };
diff --git a/drivers/gpu/drm/panel/panel-novatek-nt35950.c b/drivers/gpu/drm/panel/panel-novatek-nt35950.c
index abf752b36a52..8b108ac80b55 100644
--- a/drivers/gpu/drm/panel/panel-novatek-nt35950.c
+++ b/drivers/gpu/drm/panel/panel-novatek-nt35950.c
@@ -585,8 +585,12 @@ static int nt35950_probe(struct mipi_dsi_device *dsi)
 		       DRM_MODE_CONNECTOR_DSI);
 
 	ret = drm_panel_of_backlight(&nt->panel);
-	if (ret)
+	if (ret) {
+		if (num_dsis == 2)
+			mipi_dsi_device_unregister(nt->dsi[1]);
+
 		return dev_err_probe(dev, ret, "Failed to get backlight\n");
+	}
 
 	drm_panel_add(&nt->panel);
 
@@ -602,6 +606,10 @@ static int nt35950_probe(struct mipi_dsi_device *dsi)
 
 		ret = mipi_dsi_attach(nt->dsi[i]);
 		if (ret < 0) {
+			/* If we fail to attach to either host, we're done */
+			if (num_dsis == 2)
+				mipi_dsi_device_unregister(nt->dsi[1]);
+
 			return dev_err_probe(dev, ret,
 					     "Cannot attach to DSI%d host.\n", i);
 		}
diff --git a/drivers/gpu/drm/panel/panel-orisetech-otm8009a.c b/drivers/gpu/drm/panel/panel-orisetech-otm8009a.c
index b4729a94c34a..898b892f1143 100644
--- a/drivers/gpu/drm/panel/panel-orisetech-otm8009a.c
+++ b/drivers/gpu/drm/panel/panel-orisetech-otm8009a.c
@@ -471,7 +471,7 @@ static int otm8009a_probe(struct mipi_dsi_device *dsi)
 		       DRM_MODE_CONNECTOR_DSI);
 
 	ctx->bl_dev = devm_backlight_device_register(dev, dev_name(dev),
-						     dsi->host->dev, ctx,
+						     dev, ctx,
 						     &otm8009a_backlight_ops,
 						     NULL);
 	if (IS_ERR(ctx->bl_dev)) {
diff --git a/drivers/gpu/drm/panfrost/panfrost_mmu.c b/drivers/gpu/drm/panfrost/panfrost_mmu.c
index 666a5e53fe19..e961fa27702c 100644
--- a/drivers/gpu/drm/panfrost/panfrost_mmu.c
+++ b/drivers/gpu/drm/panfrost/panfrost_mmu.c
@@ -504,6 +504,7 @@ static int panfrost_mmu_map_fault_addr(struct panfrost_device *pfdev, int as,
 		if (IS_ERR(pages[i])) {
 			mutex_unlock(&bo->base.pages_lock);
 			ret = PTR_ERR(pages[i]);
+			pages[i] = NULL;
 			goto err_pages;
 		}
 	}
diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c b/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c
index 38554ca2fc39..ca73b8ccc29f 100644
--- a/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c
+++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c
@@ -843,6 +843,8 @@ static void vop2_enable(struct vop2 *vop2)
 		return;
 	}
 
+	regcache_sync(vop2->map);
+
 	if (vop2->data->soc_id == 3566)
 		vop2_writel(vop2, RK3568_OTP_WIN_EN, 1);
 
@@ -871,6 +873,8 @@ static void vop2_disable(struct vop2 *vop2)
 
 	pm_runtime_put_sync(vop2->dev);
 
+	regcache_mark_dirty(vop2->map);
+
 	clk_disable_unprepare(vop2->aclk);
 	clk_disable_unprepare(vop2->hclk);
 }
diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c
index 3e2d453296dd..172e63c87bfc 100644
--- a/drivers/gpu/drm/scheduler/sched_main.c
+++ b/drivers/gpu/drm/scheduler/sched_main.c
@@ -313,7 +313,8 @@ static void drm_sched_start_timeout(struct drm_gpu_scheduler *sched)
  */
 void drm_sched_fault(struct drm_gpu_scheduler *sched)
 {
-	mod_delayed_work(sched->timeout_wq, &sched->work_tdr, 0);
+	if (sched->ready)
+		mod_delayed_work(sched->timeout_wq, &sched->work_tdr, 0);
 }
 EXPORT_SYMBOL(drm_sched_fault);
 
@@ -939,12 +940,6 @@ drm_sched_get_cleanup_job(struct drm_gpu_scheduler *sched)
 
 	spin_unlock(&sched->job_list_lock);
 
-	if (job) {
-		job->entity->elapsed_ns += ktime_to_ns(
-			ktime_sub(job->s_fence->finished.timestamp,
-				  job->s_fence->scheduled.timestamp));
-	}
-
 	return job;
 }
 
diff --git a/drivers/gpu/drm/tests/drm_buddy_test.c b/drivers/gpu/drm/tests/drm_buddy_test.c
index f8ee714df396..09ee6f6af896 100644
--- a/drivers/gpu/drm/tests/drm_buddy_test.c
+++ b/drivers/gpu/drm/tests/drm_buddy_test.c
@@ -89,7 +89,8 @@ static int check_block(struct kunit *test, struct drm_buddy *mm,
 		err = -EINVAL;
 	}
 
-	if (!is_power_of_2(block_size)) {
+	/* We can't use is_power_of_2() for a u64 on 32-bit systems. */
+	if (block_size & (block_size - 1)) {
 		kunit_err(test, "block size not power of two\n");
 		err = -EINVAL;
 	}
diff --git a/drivers/gpu/drm/ttm/ttm_bo_vm.c b/drivers/gpu/drm/ttm/ttm_bo_vm.c
index 4bca6b54520a..4212b8c91dd4 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_vm.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_vm.c
@@ -261,7 +261,7 @@ vm_fault_t ttm_bo_vm_fault_reserved(struct vm_fault *vmf,
 		 * encryption bits. This is because the exact location of the
 		 * data may not be known at mmap() time and may also change
 		 * at arbitrary times while the data is mmap'ed.
-		 * See vmf_insert_mixed_prot() for a discussion.
+		 * See vmf_insert_pfn_prot() for a discussion.
 		 */
 		ret = vmf_insert_pfn_prot(vma, address, pfn, prot);
 
diff --git a/drivers/gpu/drm/ttm/ttm_pool.c b/drivers/gpu/drm/ttm/ttm_pool.c
index 18c342a919a2..4db3982057be 100644
--- a/drivers/gpu/drm/ttm/ttm_pool.c
+++ b/drivers/gpu/drm/ttm/ttm_pool.c
@@ -47,11 +47,6 @@
 
 #include "ttm_module.h"
 
-#define TTM_MAX_ORDER (PMD_SHIFT - PAGE_SHIFT)
-#define __TTM_DIM_ORDER (TTM_MAX_ORDER + 1)
-/* Some architectures have a weird PMD_SHIFT */
-#define TTM_DIM_ORDER (__TTM_DIM_ORDER <= MAX_ORDER ? __TTM_DIM_ORDER : MAX_ORDER)
-
 /**
  * struct ttm_pool_dma - Helper object for coherent DMA mappings
  *
@@ -70,11 +65,11 @@ module_param(page_pool_size, ulong, 0644);
 
 static atomic_long_t allocated_pages;
 
-static struct ttm_pool_type global_write_combined[TTM_DIM_ORDER];
-static struct ttm_pool_type global_uncached[TTM_DIM_ORDER];
+static struct ttm_pool_type global_write_combined[MAX_ORDER + 1];
+static struct ttm_pool_type global_uncached[MAX_ORDER + 1];
 
-static struct ttm_pool_type global_dma32_write_combined[TTM_DIM_ORDER];
-static struct ttm_pool_type global_dma32_uncached[TTM_DIM_ORDER];
+static struct ttm_pool_type global_dma32_write_combined[MAX_ORDER + 1];
+static struct ttm_pool_type global_dma32_uncached[MAX_ORDER + 1];
 
 static spinlock_t shrinker_lock;
 static struct list_head shrinker_list;
@@ -449,7 +444,7 @@ int ttm_pool_alloc(struct ttm_pool *pool, struct ttm_tt *tt,
 	else
 		gfp_flags |= GFP_HIGHUSER;
 
-	for (order = min_t(unsigned int, TTM_MAX_ORDER, __fls(num_pages));
+	for (order = min_t(unsigned int, MAX_ORDER, __fls(num_pages));
 	     num_pages;
 	     order = min_t(unsigned int, order, __fls(num_pages))) {
 		struct ttm_pool_type *pt;
@@ -568,7 +563,7 @@ void ttm_pool_init(struct ttm_pool *pool, struct device *dev,
 
 	if (use_dma_alloc) {
 		for (i = 0; i < TTM_NUM_CACHING_TYPES; ++i)
-			for (j = 0; j < TTM_DIM_ORDER; ++j)
+			for (j = 0; j <= MAX_ORDER; ++j)
 				ttm_pool_type_init(&pool->caching[i].orders[j],
 						   pool, i, j);
 	}
@@ -588,7 +583,7 @@ void ttm_pool_fini(struct ttm_pool *pool)
 
 	if (pool->use_dma_alloc) {
 		for (i = 0; i < TTM_NUM_CACHING_TYPES; ++i)
-			for (j = 0; j < TTM_DIM_ORDER; ++j)
+			for (j = 0; j <= MAX_ORDER; ++j)
 				ttm_pool_type_fini(&pool->caching[i].orders[j]);
 	}
 
@@ -642,7 +637,7 @@ static void ttm_pool_debugfs_header(struct seq_file *m)
 	unsigned int i;
 
 	seq_puts(m, "\t ");
-	for (i = 0; i < TTM_DIM_ORDER; ++i)
+	for (i = 0; i <= MAX_ORDER; ++i)
 		seq_printf(m, " ---%2u---", i);
 	seq_puts(m, "\n");
 }
@@ -653,7 +648,7 @@ static void ttm_pool_debugfs_orders(struct ttm_pool_type *pt,
 {
 	unsigned int i;
 
-	for (i = 0; i < TTM_DIM_ORDER; ++i)
+	for (i = 0; i <= MAX_ORDER; ++i)
 		seq_printf(m, " %8u", ttm_pool_type_count(&pt[i]));
 	seq_puts(m, "\n");
 }
@@ -756,16 +751,13 @@ int ttm_pool_mgr_init(unsigned long num_pages)
 {
 	unsigned int i;
 
-	BUILD_BUG_ON(TTM_DIM_ORDER > MAX_ORDER);
-	BUILD_BUG_ON(TTM_DIM_ORDER < 1);
-
 	if (!page_pool_size)
 		page_pool_size = num_pages;
 
 	spin_lock_init(&shrinker_lock);
 	INIT_LIST_HEAD(&shrinker_list);
 
-	for (i = 0; i < TTM_DIM_ORDER; ++i) {
+	for (i = 0; i <= MAX_ORDER; ++i) {
 		ttm_pool_type_init(&global_write_combined[i], NULL,
 				   ttm_write_combined, i);
 		ttm_pool_type_init(&global_uncached[i], NULL, ttm_uncached, i);
@@ -798,7 +790,7 @@ void ttm_pool_mgr_fini(void)
 {
 	unsigned int i;
 
-	for (i = 0; i < TTM_DIM_ORDER; ++i) {
+	for (i = 0; i <= MAX_ORDER; ++i) {
 		ttm_pool_type_fini(&global_write_combined[i]);
 		ttm_pool_type_fini(&global_uncached[i]);
 
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_so.c b/drivers/gpu/drm/vmwgfx/vmwgfx_so.c
index 5af4db6d1f18..d199e718cb2d 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_so.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_so.c
@@ -71,7 +71,7 @@ struct vmw_view {
 	unsigned view_id;              /* Immutable */
 	u32 cmd_size;                  /* Immutable */
 	bool committed;                /* Protected by binding_mutex */
-	u32 cmd[1];                    /* Immutable */
+	u32 cmd[];		       /* Immutable */
 };
 
 static int vmw_view_create(struct vmw_resource *res);