habanalabs: Add separate poll interval value for protocol

Currently we're using the same poll interval value for both
COMMs protocol(for sending a command and waits for an ACK)
and the device CPU boot phases status waits.
On COMMs protocol this interval should be much lower than the
device CPU boot which may take long time to change status.

Signed-off-by: farah kassabri <fkassabri@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
This commit is contained in:
farah kassabri 2022-04-13 18:16:34 +03:00 committed by Greg Kroah-Hartman
parent b0b09b7a8b
commit de3484dfaa
3 changed files with 8 additions and 1 deletions

View File

@ -1589,7 +1589,7 @@ static int hl_fw_dynamic_wait_for_status(struct hl_device *hdev,
le32_to_cpu(dyn_regs->cpu_cmd_status_to_host),
status,
FIELD_GET(COMMS_STATUS_STATUS_MASK, status) == expected_status,
hdev->fw_poll_interval_usec,
hdev->fw_comms_poll_interval_usec,
timeout);
if (rc) {

View File

@ -64,6 +64,7 @@
#define HL_CPUCP_MON_DUMP_TIMEOUT_USEC 10000000 /* 10s */
#define HL_FW_STATUS_POLL_INTERVAL_USEC 10000 /* 10ms */
#define HL_FW_COMMS_STATUS_PLDM_POLL_INTERVAL_USEC 1000000 /* 1s */
#define HL_PCI_ELBI_TIMEOUT_MSEC 10 /* 10ms */
@ -2717,6 +2718,9 @@ struct hl_reset_info {
* session.
* @open_counter: number of successful device open operations.
* @fw_poll_interval_usec: FW status poll interval in usec.
* used for CPU boot status
* @fw_comms_poll_interval_usec: FW comms/protocol poll interval in usec.
* used for COMMs protocols cmds(COMMS_STS_*)
* @card_type: Various ASICs have several card types. This indicates the card
* type of the current device.
* @major: habanalabs kernel driver major.
@ -2847,6 +2851,8 @@ struct hl_device {
u64 open_counter;
u64 fw_poll_interval_usec;
ktime_t last_successful_open_ktime;
u64 fw_comms_poll_interval_usec;
enum cpucp_card_types card_type;
u32 major;
u32 high_pll;

View File

@ -301,6 +301,7 @@ static int fixup_device_params(struct hl_device *hdev)
hdev->asic_prop.fw_security_enabled = is_asic_secured(hdev->asic_type);
hdev->fw_poll_interval_usec = HL_FW_STATUS_POLL_INTERVAL_USEC;
hdev->fw_comms_poll_interval_usec = HL_FW_STATUS_POLL_INTERVAL_USEC;
hdev->stop_on_err = true;
hdev->reset_info.curr_reset_cause = HL_RESET_CAUSE_UNKNOWN;