Fixed post reset and ring_hang issues

Issues include:
	SWDEV-480250
	SWDEV-480255
	SWDEV-480248
Known issue:
	`amd-smi event` has threads taking events from the same device
which, in the case of resetting gpus, makes it seem like some gpus have
reset mulitple times and other have not reset at all.

Signed-off-by: gabrpham <Gabriel.Pham@amd.com>
Change-Id: Ic7dcc214e0366fc1532ece579d915d34d35d5407
This commit is contained in:
gabrpham
2024-11-14 14:39:59 -06:00
committato da Maisam Arif
parent 1586005a5b
commit bd01cfc203
7 ha cambiato i file con 1466 aggiunte e 177 eliminazioni
+1 -1
Vedi File
@@ -69,7 +69,7 @@ AMDSMI_MAX_CACHE_TYPES = 10
AMDSMI_MAX_NUM_XGMI_PHYSICAL_LINK = 64
AMDSMI_GPU_UUID_SIZE = 38
MAX_AMDSMI_NAME_LENGTH = 64
MAX_EVENT_NOTIFICATION_MSG_SIZE = 64
MAX_EVENT_NOTIFICATION_MSG_SIZE = 96
class AmdSmiInitFlags(IntEnum):
+8 -6
Vedi File
@@ -1300,7 +1300,7 @@ struct_amdsmi_evt_notification_data_t._pack_ = 1 # source:False
struct_amdsmi_evt_notification_data_t._fields_ = [
('processor_handle', ctypes.POINTER(None)),
('event', amdsmi_evt_notification_type_t),
('message', ctypes.c_char * 64),
('message', ctypes.c_char * 96),
('PADDING_0', ctypes.c_ubyte * 4),
]
@@ -1741,6 +1741,7 @@ struct_amdsmi_gpu_xcp_metrics_t._fields_ = [
('gfx_busy_acc', ctypes.c_uint64 * 8),
]
amdsmi_gpu_xcp_metrics_t = struct_amdsmi_gpu_xcp_metrics_t
class struct_amdsmi_gpu_metrics_t(Structure):
pass
@@ -2869,11 +2870,12 @@ __all__ = \
'amdsmi_gpu_cache_info_t', 'amdsmi_gpu_control_counter',
'amdsmi_gpu_counter_group_supported', 'amdsmi_gpu_create_counter',
'amdsmi_gpu_destroy_counter', 'amdsmi_gpu_metrics_t',
'amdsmi_gpu_read_counter', 'amdsmi_gpu_xgmi_error_status',
'amdsmi_hsmp_freqlimit_src_names', 'amdsmi_hsmp_metrics_table_t',
'amdsmi_init', 'amdsmi_init_flags_t',
'amdsmi_init_gpu_event_notification', 'amdsmi_io_bw_encoding_t',
'amdsmi_io_link_type_t', 'amdsmi_is_P2P_accessible',
'amdsmi_gpu_read_counter', 'amdsmi_gpu_xcp_metrics_t',
'amdsmi_gpu_xgmi_error_status', 'amdsmi_hsmp_freqlimit_src_names',
'amdsmi_hsmp_metrics_table_t', 'amdsmi_init',
'amdsmi_init_flags_t', 'amdsmi_init_gpu_event_notification',
'amdsmi_io_bw_encoding_t', 'amdsmi_io_link_type_t',
'amdsmi_is_P2P_accessible',
'amdsmi_is_gpu_power_management_enabled', 'amdsmi_kfd_info_t',
'amdsmi_link_id_bw_type_t', 'amdsmi_link_metrics_t',
'amdsmi_link_type_t', 'amdsmi_memory_page_status_t',