Commit cafd86cb authored by Dave Airlie's avatar Dave Airlie
Browse files

Merge tag 'amd-drm-fixes-6.9-2024-03-21' of... 

Merge tag 'amd-drm-fixes-6.9-2024-03-21' of https://gitlab.freedesktop.org/agd5f/linux

 into drm-next

amd-drm-fixes-6.9-2024-03-21:

amdgpu:
- Freesync fixes
- UAF IOCTL fixes
- Fix mmhub client ID mapping
- IH 7.0 fix
- DML2 fixes
- VCN 4.0.6 fix
- GART bind fix
- GPU reset fix
- SR-IOV fix
- OD table handling fixes
- Fix TA handling on boards without display hardware
- DML1 fix
- ABM fix
- eDP panel fix
- DPPCLK fix
- HDCP fix
- Revert incorrect error case handling in ioremap
- VPE fix
- HDMI fixes
- SDMA 4.4.2 fix
- Other misc fixes

amdkfd:
- Fix duplicate BO handling in process restore

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

From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240321220514.1418288-1-alexander.deucher@amd.com
parents 921074ab bc55c344

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

+1 −1
Original line number Diff line number Diff line
@@ -146,7 +146,7 @@ int amdgpu_amdkfd_drm_client_create(struct amdgpu_device *adev) 
{

	int ret;



	if (!adev->kfd.init_complete)

	if (!adev->kfd.init_complete || adev->kfd.client.dev)

		return 0;



	ret = drm_client_init(&adev->ddev, &adev->kfd.client, "kfd",

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

+10 −4
Original line number Diff line number Diff line
@@ -2869,15 +2869,17 @@ int amdgpu_amdkfd_gpuvm_restore_process_bos(void *info, struct dma_fence __rcu * 


	mutex_lock(&process_info->lock);



	drm_exec_init(&exec, 0, 0);

	drm_exec_init(&exec, DRM_EXEC_IGNORE_DUPLICATES, 0);

	drm_exec_until_all_locked(&exec) {

		list_for_each_entry(peer_vm, &process_info->vm_list_head,

				    vm_list_node) {

			ret = amdgpu_vm_lock_pd(peer_vm, &exec, 2);

			drm_exec_retry_on_contention(&exec);

			if (unlikely(ret))

			if (unlikely(ret)) {

				pr_err("Locking VM PD failed, ret: %d\n", ret);

				goto ttm_reserve_fail;

			}

		}



		/* Reserve all BOs and page tables/directory. Add all BOs from

		 * kfd_bo_list to ctx.list
@@ -2889,10 +2891,12 @@ int amdgpu_amdkfd_gpuvm_restore_process_bos(void *info, struct dma_fence __rcu * 
			gobj = &mem->bo->tbo.base;

			ret = drm_exec_prepare_obj(&exec, gobj, 1);

			drm_exec_retry_on_contention(&exec);

			if (unlikely(ret))

			if (unlikely(ret)) {

				pr_err("drm_exec_prepare_obj failed, ret: %d\n", ret);

				goto ttm_reserve_fail;

			}

		}

	}



	amdgpu_sync_create(&sync_obj);
@@ -2950,8 +2954,10 @@ int amdgpu_amdkfd_gpuvm_restore_process_bos(void *info, struct dma_fence __rcu * 
	 * validations above would invalidate DMABuf imports again.

	 */

	ret = process_validate_vms(process_info, &exec.ticket);

	if (ret)

	if (ret) {

		pr_debug("Validating VMs failed, ret: %d\n", ret);

		goto validate_map_fail;

	}



	/* Update mappings not managed by KFD */

	list_for_each_entry(peer_vm, &process_info->vm_list_head,

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

+6 −10
Original line number Diff line number Diff line
@@ -4040,10 +4040,8 @@ int amdgpu_device_init(struct amdgpu_device *adev, 
	 * early on during init and before calling to RREG32.

	 */

	adev->reset_domain = amdgpu_reset_create_reset_domain(SINGLE_DEVICE, "amdgpu-reset-dev");

	if (!adev->reset_domain) {

		r = -ENOMEM;

		goto unmap_memory;

	}

	if (!adev->reset_domain)

		return -ENOMEM;



	/* detect hw virtualization here */

	amdgpu_detect_virtualization(adev);
@@ -4053,7 +4051,7 @@ int amdgpu_device_init(struct amdgpu_device *adev, 
	r = amdgpu_device_get_job_timeout_settings(adev);

	if (r) {

		dev_err(adev->dev, "invalid lockup_timeout parameter syntax\n");

		goto unmap_memory;

		return r;

	}



	amdgpu_device_set_mcbp(adev);
@@ -4061,12 +4059,12 @@ int amdgpu_device_init(struct amdgpu_device *adev, 
	/* early init functions */

	r = amdgpu_device_ip_early_init(adev);

	if (r)

		goto unmap_memory;

		return r;



	/* Get rid of things like offb */

	r = drm_aperture_remove_conflicting_pci_framebuffers(adev->pdev, &amdgpu_kms_driver);

	if (r)

		goto unmap_memory;

		return r;



	/* Enable TMZ based on IP_VERSION */

	amdgpu_gmc_tmz_set(adev);
@@ -4076,7 +4074,7 @@ int amdgpu_device_init(struct amdgpu_device *adev, 
	if (adev->gmc.xgmi.supported) {

		r = adev->gfxhub.funcs->get_xgmi_info(adev);

		if (r)

			goto unmap_memory;

			return r;

	}



	/* enable PCIE atomic ops */
@@ -4345,8 +4343,6 @@ int amdgpu_device_init(struct amdgpu_device *adev, 
failed:

	amdgpu_vf_error_trans_all(adev);



unmap_memory:

	iounmap(adev->rmmio);

	return r;

}

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

+4 −1
Original line number Diff line number Diff line
@@ -2479,8 +2479,11 @@ static void amdgpu_drv_delayed_reset_work_handler(struct work_struct *work) 
	}

	for (i = 0; i < mgpu_info.num_dgpu; i++) {

		adev = mgpu_info.gpu_ins[i].adev;

		if (!adev->kfd.init_complete)

		if (!adev->kfd.init_complete) {

			kgd2kfd_init_zone_device(adev);

			amdgpu_amdkfd_device_init(adev);

			amdgpu_amdkfd_drm_client_create(adev);

		}

		amdgpu_ttm_set_buffer_funcs_status(adev, true);

	}

}

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

+1 −1
Original line number Diff line number Diff line
@@ -687,7 +687,7 @@ int amdgpu_gfx_enable_kgq(struct amdgpu_device *adev, int xcc_id) 
	r = amdgpu_ring_test_helper(kiq_ring);

	spin_unlock(&kiq->ring_lock);

	if (r)

		DRM_ERROR("KCQ enable failed\n");

		DRM_ERROR("KGQ enable failed\n");



	return r;

}