Merge tag 'amd-drm-next-5.7-2020-03-10' of git://people.freedesktop.org/~agd5f/linux into drm-next

amd-drm-next-5.7-2020-03-10:

amdgpu:
- SR-IOV fixes
- Fix up fallout from drm load/unload callback removal
- Navi, renoir power management watermark fixes
- Refactor smu parameter handling
- Display FEC fixes
- Display DCC fixes
- HDCP fixes
- Add support for USB-C PD firmware updates
- Pollock detection fix
- Rework compute ring priority handling
- RAS fixes
- Misc cleanups

amdkfd:
- Consolidate more gfx config details in amdgpu
- Consolidate bo alloc flags
- Improve code comments
- SDMA MQD fixes
- Misc cleanups

gpu scheduler:
- Add suport for modifying the sched list

uapi:
- Clarify comments about GEM_CREATE flags that are not used by userspace.
  The kernel driver has always prevented userspace from using these.
  They are only used internally in the kernel driver.

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

From: Alex Deucher <alexdeucher@gmail.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200310212748.4519-1-alexander.deucher@amd.com

1 files changed, 32 insertions, 5 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index 930633a0ed64..ce8548d5fbf3 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -721,6 +721,9 @@ int amdgpu_ras_error_query(struct amdgpu_device *adev,
 		if (adev->nbio.funcs->query_ras_error_count)
 			adev->nbio.funcs->query_ras_error_count(adev, &err_data);
 		break;
+	case AMDGPU_RAS_BLOCK__XGMI_WAFL:
+		amdgpu_xgmi_query_ras_error_count(adev, &err_data);
+		break;
 	default:
 		break;
 	}
@@ -1110,6 +1113,35 @@ void amdgpu_ras_debugfs_create(struct amdgpu_device *adev,
 				       &amdgpu_ras_debugfs_ops);
 }
 
+void amdgpu_ras_debugfs_create_all(struct amdgpu_device *adev)
+{
+	struct amdgpu_ras *con = amdgpu_ras_get_context(adev);
+	struct ras_manager *obj, *tmp;
+	struct ras_fs_if fs_info;
+
+	/*
+	 * it won't be called in resume path, no need to check
+	 * suspend and gpu reset status
+	 */
+	if (!con)
+		return;
+
+	amdgpu_ras_debugfs_create_ctrl_node(adev);
+
+	list_for_each_entry_safe(obj, tmp, &con->head, node) {
+		if (!obj)
+			continue;
+
+		if (amdgpu_ras_is_supported(adev, obj->head.block) &&
+			(obj->attr_inuse == 1)) {
+			sprintf(fs_info.debugfs_name, "%s_err_inject",
+					ras_block_str(obj->head.block));
+			fs_info.head = obj->head;
+			amdgpu_ras_debugfs_create(adev, &fs_info);
+		}
+	}
+}
+
 void amdgpu_ras_debugfs_remove(struct amdgpu_device *adev,
 		struct ras_common_if *head)
 {
@@ -1142,7 +1174,6 @@ static void amdgpu_ras_debugfs_remove_all(struct amdgpu_device *adev)
 static int amdgpu_ras_fs_init(struct amdgpu_device *adev)
 {
 	amdgpu_ras_sysfs_create_feature_node(adev);
-	amdgpu_ras_debugfs_create_ctrl_node(adev);
 
 	return 0;
 }
@@ -1846,8 +1877,6 @@ int amdgpu_ras_late_init(struct amdgpu_device *adev,
 			goto interrupt;
 	}
 
-	amdgpu_ras_debugfs_create(adev, fs_info);
-
 	r = amdgpu_ras_sysfs_create(adev, fs_info);
 	if (r)
 		goto sysfs;
@@ -1856,7 +1885,6 @@ int amdgpu_ras_late_init(struct amdgpu_device *adev,
 cleanup:
 	amdgpu_ras_sysfs_remove(adev, ras_block);
 sysfs:
-	amdgpu_ras_debugfs_remove(adev, ras_block);
 	if (ih_info->cb)
 		amdgpu_ras_interrupt_remove_handler(adev, ih_info);
 interrupt:
@@ -1873,7 +1901,6 @@ void amdgpu_ras_late_fini(struct amdgpu_device *adev,
 		return;
 
 	amdgpu_ras_sysfs_remove(adev, ras_block);
-	amdgpu_ras_debugfs_remove(adev, ras_block);
 	if (ih_info->cb)
                 amdgpu_ras_interrupt_remove_handler(adev, ih_info);
 	amdgpu_ras_feature_enable(adev, ras_block, 0);