diff options
author | Ohad Sharabi <osharabi@habana.ai> | 2021-02-08 14:53:56 +0200 |
---|---|---|
committer | Oded Gabbay <ogabbay@kernel.org> | 2021-04-09 14:09:22 +0300 |
commit | 5d6a198f9dba12c78f82a0436d64bd683c031b13 (patch) | |
tree | 046f7912a19af19db27ebf3547e9d1eec246f52f /drivers/misc/habanalabs/include | |
parent | habanalabs: change default CS timeout to 30 seconds (diff) | |
download | linux-dev-5d6a198f9dba12c78f82a0436d64bd683c031b13.tar.xz linux-dev-5d6a198f9dba12c78f82a0436d64bd683c031b13.zip |
habanalabs: reset device in case of sync error
As the F/wW is the first to detect out of sync event, a new event is
added to notify the driver on such event. In which case the driver
performs hard reset.
Signed-off-by: Ohad Sharabi <osharabi@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
Diffstat (limited to 'drivers/misc/habanalabs/include')
-rw-r--r-- | drivers/misc/habanalabs/include/common/cpucp_if.h | 9 | ||||
-rw-r--r-- | drivers/misc/habanalabs/include/gaudi/gaudi_async_events.h | 1 | ||||
-rw-r--r-- | drivers/misc/habanalabs/include/goya/goya_async_events.h | 1 |
3 files changed, 11 insertions, 0 deletions
diff --git a/drivers/misc/habanalabs/include/common/cpucp_if.h b/drivers/misc/habanalabs/include/common/cpucp_if.h index b77c1c16c32c..bf4e7900d8c8 100644 --- a/drivers/misc/habanalabs/include/common/cpucp_if.h +++ b/drivers/misc/habanalabs/include/common/cpucp_if.h @@ -28,6 +28,14 @@ #define CPUCP_PKT_HBM_ECC_INFO_HBM_CH_SHIFT 6 #define CPUCP_PKT_HBM_ECC_INFO_HBM_CH_MASK 0x000007C0 +/* + * info of the pkt queue pointers in the first async occurrence + */ +struct cpucp_pkt_sync_err { + __le32 pi; + __le32 ci; +}; + struct hl_eq_hbm_ecc_data { /* SERR counter */ __le32 sec_cnt; @@ -77,6 +85,7 @@ struct hl_eq_entry { struct hl_eq_ecc_data ecc_data; struct hl_eq_hbm_ecc_data hbm_ecc_data; struct hl_eq_sm_sei_data sm_sei_data; + struct cpucp_pkt_sync_err pkt_sync_err; __le64 data[7]; }; }; diff --git a/drivers/misc/habanalabs/include/gaudi/gaudi_async_events.h b/drivers/misc/habanalabs/include/gaudi/gaudi_async_events.h index 49335e8334b4..0a0fa57024f8 100644 --- a/drivers/misc/habanalabs/include/gaudi/gaudi_async_events.h +++ b/drivers/misc/habanalabs/include/gaudi/gaudi_async_events.h @@ -303,6 +303,7 @@ enum gaudi_async_event_id { GAUDI_EVENT_NIC3_QP1 = 619, GAUDI_EVENT_NIC4_QP0 = 620, GAUDI_EVENT_NIC4_QP1 = 621, + GAUDI_EVENT_PKT_QUEUE_OUT_SYNC = 647, GAUDI_EVENT_FIX_POWER_ENV_S = 658, GAUDI_EVENT_FIX_POWER_ENV_E = 659, GAUDI_EVENT_FIX_THERMAL_ENV_S = 660, diff --git a/drivers/misc/habanalabs/include/goya/goya_async_events.h b/drivers/misc/habanalabs/include/goya/goya_async_events.h index 5fb92362fc5f..09081401cb1d 100644 --- a/drivers/misc/habanalabs/include/goya/goya_async_events.h +++ b/drivers/misc/habanalabs/include/goya/goya_async_events.h @@ -188,6 +188,7 @@ enum goya_async_event_id { GOYA_ASYNC_EVENT_ID_HALT_MACHINE = 485, GOYA_ASYNC_EVENT_ID_INTS_REGISTER = 486, GOYA_ASYNC_EVENT_ID_SOFT_RESET = 487, + GOYA_ASYNC_EVENT_PKT_QUEUE_OUT_SYNC = 506, GOYA_ASYNC_EVENT_ID_FIX_POWER_ENV_S = 507, GOYA_ASYNC_EVENT_ID_FIX_POWER_ENV_E = 508, GOYA_ASYNC_EVENT_ID_FIX_THERMAL_ENV_S = 509, |