Merge tag 'amd-drm-next-6.18-2025-10-09' of https://gitlab.freedesktop.org/agd5f/linux into drm-next

amd-drm-next-6.18-2025-10-09:

amdgpu:
- DC DCE6 fixes
- GPU reset fixes
- Secure diplay messaging cleanup
- MES fix
- GPUVM locking fixes
- PMFW messaging cleanup
- PCI US/DS switch handling fix
- VCN queue reset fix
- DC FPU handling fix
- DCN 3.5 fix
- DC mirroring fix

amdkfd:
- Fix kfd process ref leak
- mmap write lock handling fix
- Fix comments in IOCTL

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

From: Alex Deucher <alexander.deucher@amd.com>
Link: https://lore.kernel.org/r/20251009162915.981503-1-alexander.deucher@amd.com

Author: airlied

drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c

@@ -2586,12 +2586,17 @@ static int update_invalid_user_pages(struct amdkfd_process_info *process_info,
 			 * from the KFD, trigger a segmentation fault in VM debug mode.
 			 */
 			if (amdgpu_ttm_adev(bo->tbo.bdev)->debug_vm_userptr) {
+				struct kfd_process *p;
+
 				pr_err("Pid %d unmapped memory before destroying userptr at GPU addr 0x%llx\n",
 								pid_nr(process_info->pid), mem->va);
 
 				// Send GPU VM fault to user space
-				kfd_signal_vm_fault_event_with_userptr(kfd_lookup_process_by_pid(process_info->pid),
-								mem->va);
+				p = kfd_lookup_process_by_pid(process_info->pid);
+				if (p) {
+					kfd_signal_vm_fault_event_with_userptr(p, mem->va);
+					kfd_unref_process(p);
+				}
 			}
 
 			ret = 0;

drivers/gpu/drm/amd/amdgpu/amdgpu_device.c

@@ -6389,23 +6389,28 @@ static int amdgpu_device_sched_resume(struct list_head *device_list,
 		if (!drm_drv_uses_atomic_modeset(adev_to_drm(tmp_adev)) && !job_signaled)
 			drm_helper_resume_force_mode(adev_to_drm(tmp_adev));
 
-		if (tmp_adev->asic_reset_res)
-			r = tmp_adev->asic_reset_res;
-
-		tmp_adev->asic_reset_res = 0;
-
-		if (r) {
+		if (tmp_adev->asic_reset_res) {
 			/* bad news, how to tell it to userspace ?
 			 * for ras error, we should report GPU bad status instead of
 			 * reset failure
 			 */
 			if (reset_context->src != AMDGPU_RESET_SRC_RAS ||
 			    !amdgpu_ras_eeprom_check_err_threshold(tmp_adev))
-				dev_info(tmp_adev->dev, "GPU reset(%d) failed\n",
-					atomic_read(&tmp_adev->gpu_reset_counter));
-			amdgpu_vf_error_put(tmp_adev, AMDGIM_ERROR_VF_GPU_RESET_FAIL, 0, r);
+				dev_info(
+					tmp_adev->dev,
+					"GPU reset(%d) failed with error %d \n",
+					atomic_read(
+						&tmp_adev->gpu_reset_counter),
+					tmp_adev->asic_reset_res);
+			amdgpu_vf_error_put(tmp_adev,
+					    AMDGIM_ERROR_VF_GPU_RESET_FAIL, 0,
+					    tmp_adev->asic_reset_res);
+			if (!r)
+				r = tmp_adev->asic_reset_res;
+			tmp_adev->asic_reset_res = 0;
 		} else {
-			dev_info(tmp_adev->dev, "GPU reset(%d) succeeded!\n", atomic_read(&tmp_adev->gpu_reset_counter));
+			dev_info(tmp_adev->dev, "GPU reset(%d) succeeded!\n",
+				 atomic_read(&tmp_adev->gpu_reset_counter));
 			if (amdgpu_acpi_smart_shift_update(tmp_adev,
 							   AMDGPU_SS_DEV_D0))
 				dev_warn(tmp_adev->dev,
@@ -7157,28 +7162,35 @@ void amdgpu_pci_resume(struct pci_dev *pdev)
 
 static void amdgpu_device_cache_switch_state(struct amdgpu_device *adev)
 {
-	struct pci_dev *parent = pci_upstream_bridge(adev->pdev);
+	struct pci_dev *swus, *swds;
 	int r;
 
-	if (!parent || parent->vendor != PCI_VENDOR_ID_ATI)
+	swds = pci_upstream_bridge(adev->pdev);
+	if (!swds || swds->vendor != PCI_VENDOR_ID_ATI ||
+	    pci_pcie_type(swds) != PCI_EXP_TYPE_DOWNSTREAM)
+		return;
+	swus = pci_upstream_bridge(swds);
+	if (!swus ||
+	    (swus->vendor != PCI_VENDOR_ID_ATI &&
+	     swus->vendor != PCI_VENDOR_ID_AMD) ||
+	    pci_pcie_type(swus) != PCI_EXP_TYPE_UPSTREAM)
 		return;
 
 	/* If already saved, return */
 	if (adev->pcie_reset_ctx.swus)
 		return;
 	/* Upstream bridge is ATI, assume it's SWUS/DS architecture */
-	r = pci_save_state(parent);
+	r = pci_save_state(swds);
 	if (r)
 		return;
-	adev->pcie_reset_ctx.swds_pcistate = pci_store_saved_state(parent);
+	adev->pcie_reset_ctx.swds_pcistate = pci_store_saved_state(swds);
 
-	parent = pci_upstream_bridge(parent);
-	r = pci_save_state(parent);
+	r = pci_save_state(swus);
 	if (r)
 		return;
-	adev->pcie_reset_ctx.swus_pcistate = pci_store_saved_state(parent);
+	adev->pcie_reset_ctx.swus_pcistate = pci_store_saved_state(swus);
 
-	adev->pcie_reset_ctx.swus = parent;
+	adev->pcie_reset_ctx.swus = swus;
 }
 
 static void amdgpu_device_load_switch_state(struct amdgpu_device *adev)

drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c

@@ -1102,6 +1102,9 @@ uint32_t amdgpu_kiq_rreg(struct amdgpu_device *adev, uint32_t reg, uint32_t xcc_
 
 	might_sleep();
 	while (r < 1 && cnt++ < MAX_KIQ_REG_TRY) {
+		if (amdgpu_in_reset(adev))
+			goto failed_kiq_read;
+
 		msleep(MAX_KIQ_REG_BAILOUT_INTERVAL);
 		r = amdgpu_fence_wait_polling(ring, seq, MAX_KIQ_REG_WAIT);
 	}
@@ -1171,6 +1174,8 @@ void amdgpu_kiq_wreg(struct amdgpu_device *adev, uint32_t reg, uint32_t v, uint3
 
 	might_sleep();
 	while (r < 1 && cnt++ < MAX_KIQ_REG_TRY) {
+		if (amdgpu_in_reset(adev))
+			goto failed_kiq_write;
 
 		msleep(MAX_KIQ_REG_BAILOUT_INTERVAL);
 		r = amdgpu_fence_wait_polling(ring, seq, MAX_KIQ_REG_WAIT);

drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c

@@ -1421,14 +1421,10 @@ int amdgpu_driver_open_kms(struct drm_device *dev, struct drm_file *file_priv)
 
 	amdgpu_debugfs_vm_init(file_priv);
 
-	r = amdgpu_vm_init(adev, &fpriv->vm, fpriv->xcp_id);
+	r = amdgpu_vm_init(adev, &fpriv->vm, fpriv->xcp_id, pasid);
 	if (r)
 		goto error_pasid;
 
-	r = amdgpu_vm_set_pasid(adev, &fpriv->vm, pasid);
-	if (r)
-		goto error_vm;
-
 	fpriv->prt_va = amdgpu_vm_bo_add(adev, &fpriv->vm, NULL);
 	if (!fpriv->prt_va) {
 		r = -ENOMEM;
@@ -1468,10 +1464,8 @@ int amdgpu_driver_open_kms(struct drm_device *dev, struct drm_file *file_priv)
 	amdgpu_vm_fini(adev, &fpriv->vm);
 
 error_pasid:
-	if (pasid) {
+	if (pasid)
 		amdgpu_pasid_free(pasid);
-		amdgpu_vm_set_pasid(adev, &fpriv->vm, 0);
-	}
 
 	kfree(fpriv);
 

drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c

@@ -2352,7 +2352,7 @@ static int psp_securedisplay_initialize(struct psp_context *psp)
 	}
 
 	ret = psp_ta_load(psp, &psp->securedisplay_context.context);
-	if (!ret) {
+	if (!ret && !psp->securedisplay_context.context.resp_status) {
 		psp->securedisplay_context.context.initialized = true;
 		mutex_init(&psp->securedisplay_context.mutex);
 	} else

drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c

@@ -726,12 +726,12 @@ amdgpu_userq_bo_validate(struct amdgpu_device *adev, struct drm_exec *exec,
 	struct amdgpu_bo *bo;
 	int ret;
 
-	spin_lock(&vm->invalidated_lock);
+	spin_lock(&vm->status_lock);
 	while (!list_empty(&vm->invalidated)) {
 		bo_va = list_first_entry(&vm->invalidated,
 					 struct amdgpu_bo_va,
 					 base.vm_status);
-		spin_unlock(&vm->invalidated_lock);
+		spin_unlock(&vm->status_lock);
 
 		bo = bo_va->base.bo;
 		ret = drm_exec_prepare_obj(exec, &bo->tbo.base, 2);
@@ -748,9 +748,9 @@ amdgpu_userq_bo_validate(struct amdgpu_device *adev, struct drm_exec *exec,
 		if (ret)
 			return ret;
 
-		spin_lock(&vm->invalidated_lock);
+		spin_lock(&vm->status_lock);
 	}
-	spin_unlock(&vm->invalidated_lock);
+	spin_unlock(&vm->status_lock);
 
 	return 0;
 }