Commit d9bd0541 authored by Dave Airlie's avatar Dave Airlie
Browse files

Merge tag 'amd-drm-next-5.16-2021-10-29' of... 

Merge tag 'amd-drm-next-5.16-2021-10-29' of https://gitlab.freedesktop.org/agd5f/linux

 into drm-next

amd-drm-next-5.16-2021-10-29:

amdgpu:
- RAS fixes
- Fix a potential memory leak in device tear down
- Add a stutter mode quirk
- Misc display fixes
- Further display FP refactoring
- Display USB4 fixes
- Display DP2.0 fixes
- DCN 3.1 fixes
- Display 8 ch audio fix
- Fix DMA mask regression for SI parts
- Aldebaran fixes

amdkfd:
- userptr fix
- BO lifetime fix
- Misc code cleanup

UAPI:
- Minor header cleanup (no functional change)

Signed-off-by: default avatarDave Airlie <airlied@redhat.com>
From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20211029184338.4863-1-alexander.deucher@amd.com
parents 31fa8cbc 403475be

drivers/gpu/drm/amd/amdgpu/amdgpu.h

+1 −0
Original line number Diff line number Diff line
@@ -205,6 +205,7 @@ extern struct amdgpu_mgpu_info mgpu_info; 
extern int amdgpu_ras_enable;

extern uint amdgpu_ras_mask;

extern int amdgpu_bad_page_threshold;

extern bool amdgpu_ignore_bad_page_threshold;

extern struct amdgpu_watchdog_timer amdgpu_watchdog_timer;

extern int amdgpu_async_gfx_ring;

extern int amdgpu_mcbp;

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

+2 −0
Original line number Diff line number Diff line
@@ -279,6 +279,8 @@ int amdgpu_amdkfd_gpuvm_sync_memory( 
		struct kgd_dev *kgd, struct kgd_mem *mem, bool intr);

int amdgpu_amdkfd_gpuvm_map_gtt_bo_to_kernel(struct kgd_dev *kgd,

		struct kgd_mem *mem, void **kptr, uint64_t *size);

void amdgpu_amdkfd_gpuvm_unmap_gtt_bo_from_kernel(struct kgd_dev *kgd, struct kgd_mem *mem);



int amdgpu_amdkfd_gpuvm_restore_process_bos(void *process_info,

					    struct dma_fence **ef);

int amdgpu_amdkfd_gpuvm_get_vm_fault_info(struct kgd_dev *kgd,

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

+27 −10
Original line number Diff line number Diff line
@@ -1871,6 +1871,16 @@ int amdgpu_amdkfd_gpuvm_map_gtt_bo_to_kernel(struct kgd_dev *kgd, 
	return ret;

}



void amdgpu_amdkfd_gpuvm_unmap_gtt_bo_from_kernel(struct kgd_dev *kgd, struct kgd_mem *mem)

{

	struct amdgpu_bo *bo = mem->bo;



	amdgpu_bo_reserve(bo, true);

	amdgpu_bo_kunmap(bo);

	amdgpu_bo_unpin(bo);

	amdgpu_bo_unreserve(bo);

}



int amdgpu_amdkfd_gpuvm_get_vm_fault_info(struct kgd_dev *kgd,

					      struct kfd_vm_fault_info *mem)

{
@@ -2041,18 +2051,25 @@ static int update_invalid_user_pages(struct amdkfd_process_info *process_info, 
		/* Get updated user pages */

		ret = amdgpu_ttm_tt_get_user_pages(bo, bo->tbo.ttm->pages);

		if (ret) {

			pr_debug("%s: Failed to get user pages: %d\n",

				__func__, ret);

			pr_debug("Failed %d to get user pages\n", ret);



			/* Return error -EBUSY or -ENOMEM, retry restore */

			/* Return -EFAULT bad address error as success. It will

			 * fail later with a VM fault if the GPU tries to access

			 * it. Better than hanging indefinitely with stalled

			 * user mode queues.

			 *

			 * Return other error -EBUSY or -ENOMEM to retry restore

			 */

			if (ret != -EFAULT)

				return ret;

		}

		} else {



			/*

			 * FIXME: Cannot ignore the return code, must hold

			 * notifier_lock

			 */

			amdgpu_ttm_tt_get_user_pages_done(bo->tbo.ttm);

		}



		/* Mark the BO as valid unless it was invalidated

		 * again concurrently.

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

+1 −1
Original line number Diff line number Diff line
@@ -3852,8 +3852,8 @@ void amdgpu_device_fini_hw(struct amdgpu_device *adev) 


void amdgpu_device_fini_sw(struct amdgpu_device *adev)

{

	amdgpu_device_ip_fini(adev);

	amdgpu_fence_driver_sw_fini(adev);

	amdgpu_device_ip_fini(adev);

	release_firmware(adev->firmware.gpu_info_fw);

	adev->firmware.gpu_info_fw = NULL;

	adev->accel_working = false;

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

+17 −0
Original line number Diff line number Diff line
@@ -931,6 +931,7 @@ int amdgpu_discovery_set_ip_blocks(struct amdgpu_device *adev) 
		adev->ip_versions[OSSSYS_HWIP][0] = IP_VERSION(4, 0, 0);

		adev->ip_versions[HDP_HWIP][0] = IP_VERSION(4, 0, 0);

		adev->ip_versions[SDMA0_HWIP][0] = IP_VERSION(4, 0, 0);

		adev->ip_versions[SDMA1_HWIP][0] = IP_VERSION(4, 0, 0);

		adev->ip_versions[DF_HWIP][0] = IP_VERSION(2, 1, 0);

		adev->ip_versions[NBIO_HWIP][0] = IP_VERSION(6, 1, 0);

		adev->ip_versions[UMC_HWIP][0] = IP_VERSION(6, 0, 0);
@@ -951,6 +952,7 @@ int amdgpu_discovery_set_ip_blocks(struct amdgpu_device *adev) 
		adev->ip_versions[OSSSYS_HWIP][0] = IP_VERSION(4, 0, 1);

		adev->ip_versions[HDP_HWIP][0] = IP_VERSION(4, 0, 1);

		adev->ip_versions[SDMA0_HWIP][0] = IP_VERSION(4, 0, 1);

		adev->ip_versions[SDMA1_HWIP][0] = IP_VERSION(4, 0, 1);

		adev->ip_versions[DF_HWIP][0] = IP_VERSION(2, 5, 0);

		adev->ip_versions[NBIO_HWIP][0] = IP_VERSION(6, 2, 0);

		adev->ip_versions[UMC_HWIP][0] = IP_VERSION(6, 1, 0);
@@ -1009,6 +1011,7 @@ int amdgpu_discovery_set_ip_blocks(struct amdgpu_device *adev) 
		adev->ip_versions[OSSSYS_HWIP][0] = IP_VERSION(4, 2, 0);

		adev->ip_versions[HDP_HWIP][0] = IP_VERSION(4, 2, 0);

		adev->ip_versions[SDMA0_HWIP][0] = IP_VERSION(4, 2, 0);

		adev->ip_versions[SDMA1_HWIP][0] = IP_VERSION(4, 2, 0);

		adev->ip_versions[DF_HWIP][0] = IP_VERSION(3, 6, 0);

		adev->ip_versions[NBIO_HWIP][0] = IP_VERSION(7, 4, 0);

		adev->ip_versions[UMC_HWIP][0] = IP_VERSION(6, 1, 1);
@@ -1018,6 +1021,7 @@ int amdgpu_discovery_set_ip_blocks(struct amdgpu_device *adev) 
		adev->ip_versions[SMUIO_HWIP][0] = IP_VERSION(11, 0, 2);

		adev->ip_versions[GC_HWIP][0] = IP_VERSION(9, 4, 0);

		adev->ip_versions[UVD_HWIP][0] = IP_VERSION(7, 2, 0);

		adev->ip_versions[UVD_HWIP][1] = IP_VERSION(7, 2, 0);

		adev->ip_versions[VCE_HWIP][0] = IP_VERSION(4, 1, 0);

		adev->ip_versions[DCI_HWIP][0] = IP_VERSION(12, 1, 0);

		break;
@@ -1030,6 +1034,13 @@ int amdgpu_discovery_set_ip_blocks(struct amdgpu_device *adev) 
		adev->ip_versions[OSSSYS_HWIP][0] = IP_VERSION(4, 2, 1);

		adev->ip_versions[HDP_HWIP][0] = IP_VERSION(4, 2, 1);

		adev->ip_versions[SDMA0_HWIP][0] = IP_VERSION(4, 2, 2);

		adev->ip_versions[SDMA1_HWIP][0] = IP_VERSION(4, 2, 2);

		adev->ip_versions[SDMA1_HWIP][1] = IP_VERSION(4, 2, 2);

		adev->ip_versions[SDMA1_HWIP][2] = IP_VERSION(4, 2, 2);

		adev->ip_versions[SDMA1_HWIP][3] = IP_VERSION(4, 2, 2);

		adev->ip_versions[SDMA1_HWIP][4] = IP_VERSION(4, 2, 2);

		adev->ip_versions[SDMA1_HWIP][5] = IP_VERSION(4, 2, 2);

		adev->ip_versions[SDMA1_HWIP][6] = IP_VERSION(4, 2, 2);

		adev->ip_versions[DF_HWIP][0] = IP_VERSION(3, 6, 1);

		adev->ip_versions[NBIO_HWIP][0] = IP_VERSION(7, 4, 1);

		adev->ip_versions[UMC_HWIP][0] = IP_VERSION(6, 1, 2);
@@ -1039,6 +1050,7 @@ int amdgpu_discovery_set_ip_blocks(struct amdgpu_device *adev) 
		adev->ip_versions[SMUIO_HWIP][0] = IP_VERSION(11, 0, 3);

		adev->ip_versions[GC_HWIP][0] = IP_VERSION(9, 4, 1);

		adev->ip_versions[UVD_HWIP][0] = IP_VERSION(2, 5, 0);

		adev->ip_versions[UVD_HWIP][1] = IP_VERSION(2, 5, 0);

		break;

	case CHIP_ALDEBARAN:

		aldebaran_reg_base_init(adev);
@@ -1049,6 +1061,10 @@ int amdgpu_discovery_set_ip_blocks(struct amdgpu_device *adev) 
		adev->ip_versions[OSSSYS_HWIP][0] = IP_VERSION(4, 4, 0);

		adev->ip_versions[HDP_HWIP][0] = IP_VERSION(4, 4, 0);

		adev->ip_versions[SDMA0_HWIP][0] = IP_VERSION(4, 4, 0);

		adev->ip_versions[SDMA0_HWIP][1] = IP_VERSION(4, 4, 0);

		adev->ip_versions[SDMA0_HWIP][2] = IP_VERSION(4, 4, 0);

		adev->ip_versions[SDMA0_HWIP][3] = IP_VERSION(4, 4, 0);

		adev->ip_versions[SDMA0_HWIP][4] = IP_VERSION(4, 4, 0);

		adev->ip_versions[DF_HWIP][0] = IP_VERSION(3, 6, 2);

		adev->ip_versions[NBIO_HWIP][0] = IP_VERSION(7, 4, 4);

		adev->ip_versions[UMC_HWIP][0] = IP_VERSION(6, 7, 0);
@@ -1058,6 +1074,7 @@ int amdgpu_discovery_set_ip_blocks(struct amdgpu_device *adev) 
		adev->ip_versions[SMUIO_HWIP][0] = IP_VERSION(13, 0, 2);

		adev->ip_versions[GC_HWIP][0] = IP_VERSION(9, 4, 2);

		adev->ip_versions[UVD_HWIP][0] = IP_VERSION(2, 6, 0);

		adev->ip_versions[UVD_HWIP][1] = IP_VERSION(2, 6, 0);

		adev->ip_versions[XGMI_HWIP][0] = IP_VERSION(6, 1, 0);

		break;

	default: