drm/amdgpu: Unify ras block interface for each ras block

1. Define unified ops interface for each block.
2. Add ras_block_match function pointer in ops interface, each ras block can customize specail match function to identify itself.
3. Add amdgpu_ras_block_match_default new function. If a ras block doesn't define .ras_block_match, default execute amdgpu_ras_block_match_default to identify this ras block.
4. Define unified basic ras block data for each ras block.
5. Create dedicated amdgpu device ras block link list to manage all of the ras blocks.
6. Add amdgpu_ras_register_ras_block new function interface for each ras block to register itself to ras controlling block.
Signed-off-by: Nyipechai <YiPeng.Chai@amd.com>
Reviewed-by: NHawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: NJohn Clements <john.clements@amd.com>
Reviewed-by: NTao Zhou <tao.zhou1@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

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

@@ -1091,6 +1091,8 @@ struct amdgpu_device {
 	uint32_t                        ip_versions[MAX_HWIP][HWIP_MAX_INSTANCE];
 
 	bool				ram_is_direct_mapped;
+
+	struct list_head                ras_list;
 };
 
 static inline struct amdgpu_device *drm_to_adev(struct drm_device *ddev)

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

@@ -3519,6 +3519,8 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 
 	INIT_LIST_HEAD(&adev->reset_list);
 
+	INIT_LIST_HEAD(&adev->ras_list);
+
 	INIT_DELAYED_WORK(&adev->delayed_init_work,
 			  amdgpu_device_delayed_init_work_handler);
 	INIT_DELAYED_WORK(&adev->gfx.gfx_off_delay_work,

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

@@ -866,6 +866,40 @@ static int amdgpu_ras_enable_all_features(struct amdgpu_device *adev,
 }
 /* feature ctl end */
 
+int amdgpu_ras_block_match_default(struct amdgpu_ras_block_object* block_obj, enum amdgpu_ras_block block)
+{
+	if(!block_obj)
+		return -EINVAL;
+
+	if (block_obj->block == block)
+		return 0;
+
+	return -EINVAL;
+}
+
+static struct amdgpu_ras_block_object* amdgpu_ras_get_ras_block(struct amdgpu_device *adev,
+					enum amdgpu_ras_block block, uint32_t sub_block_index)
+{
+	struct amdgpu_ras_block_object *obj, *tmp;
+
+	if (block >= AMDGPU_RAS_BLOCK__LAST)
+		return NULL;
+
+	if (!amdgpu_ras_is_supported(adev, block))
+		return NULL;
+
+	list_for_each_entry_safe(obj, tmp, &adev->ras_list, node) {
+		if (obj->ras_block_match) {
+			if (obj->ras_block_match(obj, block, sub_block_index) == 0)
+				return obj;
+		} else {
+			if (amdgpu_ras_block_match_default(obj, block) == 0)
+				return obj;
+		}
+	}
+
+	return NULL;
+}
 
 static void amdgpu_ras_mca_query_error_status(struct amdgpu_device *adev,
 					      struct ras_common_if *ras_block,
@@ -2776,3 +2810,15 @@ static void amdgpu_register_bad_pages_mca_notifier(struct amdgpu_device *adev)
 	}
 }
 #endif
+/* Register each ip ras block into amdgpu ras */
+int amdgpu_ras_register_ras_block(struct amdgpu_device *adev,
+		struct amdgpu_ras_block_object* ras_block_obj)
+{
+	if (!adev || !ras_block_obj)
+		return -EINVAL;
+
+	INIT_LIST_HEAD(&ras_block_obj->node);
+	list_add_tail(&ras_block_obj->node, &adev->ras_list);
+
+	return 0;
+}

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

@@ -484,6 +484,33 @@ struct ras_debug_if {
 	};
 	int op;
 };
+
+struct amdgpu_ras_block_object {
+	/* block name */
+	char name[32];
+
+	enum amdgpu_ras_block block;
+
+	uint32_t sub_block_index;
+
+	/* ras block link */
+	struct list_head node;
+
+	int (*ras_block_match)(struct amdgpu_ras_block_object *block_obj, enum amdgpu_ras_block block, uint32_t sub_block_index);
+	int (*ras_late_init)(struct amdgpu_device *adev, void *ras_info);
+	void (*ras_fini)(struct amdgpu_device *adev);
+	const struct amdgpu_ras_block_hw_ops *hw_ops;
+};
+
+struct amdgpu_ras_block_hw_ops {
+	int  (*ras_error_inject)(struct amdgpu_device *adev, void *inject_if);
+	void (*query_ras_error_count)(struct amdgpu_device *adev,void *ras_error_status);
+	void (*query_ras_error_status)(struct amdgpu_device *adev);
+	void (*query_ras_error_address)(struct amdgpu_device *adev, void *ras_error_status);
+	void (*reset_ras_error_count)(struct amdgpu_device *adev);
+	void (*reset_ras_error_status)(struct amdgpu_device *adev);
+};
+
 /* work flow
  * vbios
  * 1: ras feature enable (enabled by default)
@@ -667,4 +694,5 @@ const char *get_ras_block_str(struct ras_common_if *ras_block);
 
 bool amdgpu_ras_is_poison_mode_supported(struct amdgpu_device *adev);
 
+int amdgpu_ras_register_ras_block(struct amdgpu_device *adev, struct amdgpu_ras_block_object* ras_block_obj);
 #endif