| 9dec27bb | 07-May-2024 |
Didi Freiman <[email protected]> |
accel/habanalabs: gradual sleep in polling memory macro
It’s better to avoid long sleeps right from the beginning of the polling since the data may be available much sooner than the sleep period. Be
accel/habanalabs: gradual sleep in polling memory macro
It’s better to avoid long sleeps right from the beginning of the polling since the data may be available much sooner than the sleep period. Because polling host memory is inexpensive, this change gradually increases the sleep time up to the user-requested period.
Signed-off-by: Didi Freiman <[email protected]> Reviewed-by: Ofir Bitton <[email protected]> Signed-off-by: Ofir Bitton <[email protected]>
show more ...
|
| 0199e639 | 13-May-2024 |
Tomer Tayar <[email protected]> |
accel/habanalabs: move heartbeat work initialization to early init
The device heartbeat work is currently initialized at device_heartbeat_schedule() which is called at the end of hl_device_init(). H
accel/habanalabs: move heartbeat work initialization to early init
The device heartbeat work is currently initialized at device_heartbeat_schedule() which is called at the end of hl_device_init(). However hl_device_init() can fail at a previous step, and in such a case, a subsequent call to hl_device_fini() will lead to calling cleanup_resources() and accessing this work uninitialized.
As there is no real need to re-initialize this work every time it is rescheduled, move this initialization to device_early_init() to be done once and early enough.
Signed-off-by: Tomer Tayar <[email protected]> Reviewed-by: Ofir Bitton <[email protected]> Signed-off-by: Ofir Bitton <[email protected]>
show more ...
|
| 795f93e6 | 16-Apr-2024 |
Tomer Tayar <[email protected]> |
accel/habanalabs: revise print on EQ heartbeat failure
Don't print the "previous EQ index" value in case of a EQ heartbeat failure, because it is incremented along with the EQ CI and therefore redun
accel/habanalabs: revise print on EQ heartbeat failure
Don't print the "previous EQ index" value in case of a EQ heartbeat failure, because it is incremented along with the EQ CI and therefore redundant.
In addition, as the CPU-CP PI is zeroed when it reaches a value that is twice the queue size, add a value of the CI with a similar wrap around, to make it easier to compare the values.
Signed-off-by: Tomer Tayar <[email protected]> Reviewed-by: Ofir Bitton <[email protected]> Signed-off-by: Ofir Bitton <[email protected]>
show more ...
|
| 9ee446f9 | 09-Apr-2024 |
Farah Kassabri <[email protected]> |
accel/habanalabs: add more info upon cpu pkt timeout
In order to have better debuggability upon encountering FW issues, We are adding additional info once CPU packet timeout expires.
Signed-off-by:
accel/habanalabs: add more info upon cpu pkt timeout
In order to have better debuggability upon encountering FW issues, We are adding additional info once CPU packet timeout expires.
Signed-off-by: Farah Kassabri <[email protected]> Reviewed-by: Ofir Bitton <[email protected]> Signed-off-by: Ofir Bitton <[email protected]>
show more ...
|
| fda92282 | 04-Apr-2024 |
Ilia Levi <[email protected]> |
accel/habanalabs: additional print in device-in-use info
When device release triggers a hard reset, there is a printout of the cause. Currently listed causes (that increment context refcount) are ac
accel/habanalabs: additional print in device-in-use info
When device release triggers a hard reset, there is a printout of the cause. Currently listed causes (that increment context refcount) are active command submissions and exported DMA buffer objects. In any other case, the printout emits "unknown reason". We identify and print another reason - allocated command buffers.
Signed-off-by: Ilia Levi <[email protected]> Reviewed-by: Ofir Bitton <[email protected]> Signed-off-by: Ofir Bitton <[email protected]>
show more ...
|
| 61f4f624 | 03-Apr-2024 |
Tal Cohen <[email protected]> |
accel/habanalabs: disable EQ interrupt after disabling pci
When sending disable pci msg towards firmware, there is a possibility that an EQ packet is already pending, disabling EQ interrupt will pre
accel/habanalabs: disable EQ interrupt after disabling pci
When sending disable pci msg towards firmware, there is a possibility that an EQ packet is already pending, disabling EQ interrupt will prevent this from happening. The interrupt will be re-enabled after reset.
Signed-off-by: Tal Cohen <[email protected]> Reviewed-by: Ofir Bitton <[email protected]> Signed-off-by: Ofir Bitton <[email protected]>
show more ...
|
| 52fbab90 | 04-Apr-2024 |
Farah Kassabri <[email protected]> |
accel/habanalabs: change the heartbeat scheduling point
Currently we schedule the heartbeat thread at late init, only then we set the INTS_REGISTER packet which enables events to be received from fi
accel/habanalabs: change the heartbeat scheduling point
Currently we schedule the heartbeat thread at late init, only then we set the INTS_REGISTER packet which enables events to be received from firmware.
Init may take some time and we want to give firmware 2 full cycles of heartbeat thread after it received INTS_REGISTER.
The patch will move the heartbeat thread scheduling to be after driver is done with all initializations.
Signed-off-by: Farah Kassabri <[email protected]> Reviewed-by: Ofir Bitton <[email protected]> Signed-off-by: Ofir Bitton <[email protected]>
show more ...
|
| 3d613b0c | 12-Mar-2024 |
Tomer Tayar <[email protected]> |
accel/habanalabs: add a common handler for clock change events
As the new dynamic EQ includes clock change events which are common and not ASIC-specific, add a common handler for these events.
Sign
accel/habanalabs: add a common handler for clock change events
As the new dynamic EQ includes clock change events which are common and not ASIC-specific, add a common handler for these events.
Signed-off-by: Tomer Tayar <[email protected]> Reviewed-by: Ofir Bitton <[email protected]> Signed-off-by: Ofir Bitton <[email protected]>
show more ...
|
| 93a296dd | 12-Mar-2024 |
Tomer Tayar <[email protected]> |
accel/habanalabs: move hl_eq_heartbeat_event_handle() to common code
hl_eq_heartbeat_event_handle() doesn't have ASIC specific code, and therefore can be moved from Gaudi2-only code to common code,
accel/habanalabs: move hl_eq_heartbeat_event_handle() to common code
hl_eq_heartbeat_event_handle() doesn't have ASIC specific code, and therefore can be moved from Gaudi2-only code to common code, and possibly used for other ASICs.
Signed-off-by: Tomer Tayar <[email protected]> Reviewed-by: Ofir Bitton <[email protected]> Signed-off-by: Ofir Bitton <[email protected]>
show more ...
|
| 5f6ad3c6 | 13-Mar-2024 |
Tomer Tayar <[email protected]> |
accel/habanalabs: add an EQ size ASIC property
Future supported ASICs might use the dynamic EQ mechanism with the firmware, and in that case the EQ size won't be equal to the default HL_EQ_SIZE_IN_B
accel/habanalabs: add an EQ size ASIC property
Future supported ASICs might use the dynamic EQ mechanism with the firmware, and in that case the EQ size won't be equal to the default HL_EQ_SIZE_IN_BYTES value. Add an ASIC property to enable overriding this value.
Signed-off-by: Tomer Tayar <[email protected]> Reviewed-by: Ofir Bitton <[email protected]> Signed-off-by: Ofir Bitton <[email protected]>
show more ...
|
| c754bcf9 | 10-Mar-2024 |
Tomer Tayar <[email protected]> |
accel/habanalabs/gaudi2: revise return value handling in gaudi2_hbm_sei_handle_read_err()
The return value in gaudi2_hbm_sei_handle_read_err() is boolean and not a bitmask, so there is need for "|=
accel/habanalabs/gaudi2: revise return value handling in gaudi2_hbm_sei_handle_read_err()
The return value in gaudi2_hbm_sei_handle_read_err() is boolean and not a bitmask, so there is need for "|= true". In addition, rename the 'rc' variable, as no "return code" is returned here but an indication if a hard reset is required.
Signed-off-by: Tomer Tayar <[email protected]> Reviewed-by: Ofir Bitton <[email protected]> Signed-off-by: Ofir Bitton <[email protected]>
show more ...
|