[PATCH 04/12] accel/habanalabs: align to latest firmware specs
Ofir Bitton
obitton at habana.ai
Wed May 17 18:03:18 UTC 2023
On 16/05/2023 12:30, Oded Gabbay wrote:
> Update the firmware common interface files with the latest version.
>
> Signed-off-by: Oded Gabbay <ogabbay at kernel.org>
> ---
> .../habanalabs/include/common/cpucp_if.h | 18 ++++----
> .../habanalabs/include/common/hl_boot_if.h | 41 ++++---------------
> 2 files changed, 16 insertions(+), 43 deletions(-)
>
> diff --git a/drivers/accel/habanalabs/include/common/cpucp_if.h b/drivers/accel/habanalabs/include/common/cpucp_if.h
> index f68308cc2524..33807b839c37 100644
> --- a/drivers/accel/habanalabs/include/common/cpucp_if.h
> +++ b/drivers/accel/habanalabs/include/common/cpucp_if.h
> @@ -359,7 +359,7 @@ struct hl_eq_entry {
> union {
> __le64 data_placeholder;
> struct hl_eq_ecc_data ecc_data;
> - struct hl_eq_hbm_ecc_data hbm_ecc_data; /* Gaudi1 HBM */
> + struct hl_eq_hbm_ecc_data hbm_ecc_data; /* Obsolete */
> struct hl_eq_sm_sei_data sm_sei_data;
> struct cpucp_pkt_sync_err pkt_sync_err;
> struct hl_eq_fw_alive fw_alive;
> @@ -653,7 +653,7 @@ enum pq_init_status {
> * which address is passed via the CpuCp packet. In addition, the host's driver
> * passes the max size it allows the CpuCP to write to the structure, to prevent
> * data corruption in case of mismatched driver/FW versions.
> - * Relevant only to Gaudi.
> + * Obsolete.
> *
> * CPUCP_PACKET_GENERIC_PASSTHROUGH -
> * Generic opcode for all firmware info that is only passed to host
> @@ -868,19 +868,19 @@ struct cpucp_array_data_packet {
> enum cpucp_led_index {
> CPUCP_LED0_INDEX = 0,
> CPUCP_LED1_INDEX,
> - CPUCP_LED2_INDEX
> + CPUCP_LED2_INDEX,
> + CPUCP_LED_MAX_INDEX = CPUCP_LED2_INDEX
> };
>
> /*
> * enum cpucp_packet_rc - Error return code
> * @cpucp_packet_success -> in case of success.
> - * @cpucp_packet_invalid -> this is to support Goya and Gaudi platform.
> + * @cpucp_packet_invalid -> this is to support first generation platforms.
> * @cpucp_packet_fault -> in case of processing error like failing to
> * get device binding or semaphore etc.
> - * @cpucp_packet_invalid_pkt -> when cpucp packet is un-supported. This is
> - * supported Greco onwards.
> + * @cpucp_packet_invalid_pkt -> when cpucp packet is un-supported.
> * @cpucp_packet_invalid_params -> when checking parameter like length of buffer
> - * or attribute value etc. Supported Greco onwards.
> + * or attribute value etc.
> * @cpucp_packet_rc_max -> It indicates size of enum so should be at last.
> */
> enum cpucp_packet_rc {
> @@ -1365,7 +1365,7 @@ struct cpucp_dev_info_signed {
> #define DCORE_MON_REGS_SZ 512
> /*
> * struct dcore_monitor_regs_data - DCORE monitor regs data.
> - * the structure follows sync manager block layout. relevant only to Gaudi.
> + * the structure follows sync manager block layout. Obsolete.
> * @mon_pay_addrl: array of payload address low bits.
> * @mon_pay_addrh: array of payload address high bits.
> * @mon_pay_data: array of payload data.
> @@ -1380,7 +1380,7 @@ struct dcore_monitor_regs_data {
> __le32 mon_status[DCORE_MON_REGS_SZ];
> };
>
> -/* contains SM data for each SYNC_MNGR (relevant only to Gaudi) */
> +/* contains SM data for each SYNC_MNGR (Obsolete) */
> struct cpucp_monitor_dump {
> struct dcore_monitor_regs_data sync_mngr_w_s;
> struct dcore_monitor_regs_data sync_mngr_e_s;
> diff --git a/drivers/accel/habanalabs/include/common/hl_boot_if.h b/drivers/accel/habanalabs/include/common/hl_boot_if.h
> index c58d76a2705c..cff79f7f9f75 100644
> --- a/drivers/accel/habanalabs/include/common/hl_boot_if.h
> +++ b/drivers/accel/habanalabs/include/common/hl_boot_if.h
> @@ -35,6 +35,7 @@ enum cpu_boot_err {
> CPU_BOOT_ERR_TPM_FAIL = 20,
> CPU_BOOT_ERR_TMP_THRESH_INIT_FAIL = 21,
> CPU_BOOT_ERR_EEPROM_FAIL = 22,
> + CPU_BOOT_ERR_ENG_ARC_MEM_SCRUB_FAIL = 23,
> CPU_BOOT_ERR_ENABLED = 31,
> CPU_BOOT_ERR_SCND_EN = 63,
> CPU_BOOT_ERR_LAST = 64 /* we have 2 registers of 32 bits */
> @@ -51,6 +52,7 @@ enum cpu_boot_err {
> (1 << CPU_BOOT_ERR_DEVICE_UNUSABLE_FAIL) | \
> (1 << CPU_BOOT_ERR_BINNING_FAIL) | \
> (1 << CPU_BOOT_ERR_DRAM_SKIPPED) | \
> + (1 << CPU_BOOT_ERR_ENG_ARC_MEM_SCRUB_FAIL) | \
> (1 << CPU_BOOT_ERR_EEPROM_FAIL))
>
> /*
> @@ -132,6 +134,9 @@ enum cpu_boot_err {
> * CPU_BOOT_ERR_EEPROM_FAIL Failed reading EEPROM data. Defaults
> * are used.
> *
> + * CPU_BOOT_ERR_ENG_ARC_MEM_SCRUB_FAIL Failed scrubbing the Engines/ARCFarm
> + * memories. Boot disabled until reset.
> + *
> * CPU_BOOT_ERR0_ENABLED Error registers enabled.
> * This is a main indication that the
> * running FW populates the error
> @@ -157,6 +162,7 @@ enum cpu_boot_err {
> #define CPU_BOOT_ERR0_TPM_FAIL (1 << CPU_BOOT_ERR_TPM_FAIL)
> #define CPU_BOOT_ERR0_TMP_THRESH_INIT_FAIL (1 << CPU_BOOT_ERR_TMP_THRESH_INIT_FAIL)
> #define CPU_BOOT_ERR0_EEPROM_FAIL (1 << CPU_BOOT_ERR_EEPROM_FAIL)
> +#define CPU_BOOT_ERR0_ENG_ARC_MEM_SCRUB_FAIL (1 << CPU_BOOT_ERR_ENG_ARC_MEM_SCRUB_FAIL)
> #define CPU_BOOT_ERR0_ENABLED (1 << CPU_BOOT_ERR_ENABLED)
> #define CPU_BOOT_ERR1_ENABLED (1 << CPU_BOOT_ERR_ENABLED)
>
> @@ -744,36 +750,6 @@ struct comms_status {
> };
> };
>
> -/**
> - * HL_MODULES_MAX_NUM is determined by the size of modules_mask in struct
> - * hl_component_versions
> - */
> -enum hl_modules {
> - HL_MODULES_BOOT_INFO = 0,
> - HL_MODULES_EEPROM,
> - HL_MODULES_FDT,
> - HL_MODULES_I2C,
> - HL_MODULES_LZ4,
> - HL_MODULES_MBEDTLS,
> - HL_MODULES_MAX_NUM = 16
> -};
> -
> -/**
> - * HL_COMPONENTS_MAX_NUM is determined by the size of components_mask in
> - * struct cpucp_versions
> - */
> -enum hl_components {
> - HL_COMPONENTS_PID = 0,
> - HL_COMPONENTS_MGMT,
> - HL_COMPONENTS_PREBOOT,
> - HL_COMPONENTS_PPBOOT,
> - HL_COMPONENTS_ARMCP,
> - HL_COMPONENTS_CPLD,
> - HL_COMPONENTS_UBOOT,
> - HL_COMPONENTS_FUSE,
> - HL_COMPONENTS_MAX_NUM = 16
> -};
> -
> #define NAME_MAX_LEN 32 /* bytes */
> struct hl_module_data {
> __u8 name[NAME_MAX_LEN];
> @@ -787,8 +763,6 @@ struct hl_module_data {
> * @component: version of the component itself.
> * @fw_os: Firmware OS Version.
> * @comp_name: Name of the component.
> - * @modules_mask: i'th bit (from LSB) is a flag - on if module i in enum
> - * hl_modules is used.
> * @modules_counter: number of set bits in modules_mask.
> * @reserved: reserved for future use.
> * @modules: versions of the component's modules. Elborated explanation in
> @@ -800,9 +774,8 @@ struct hl_component_versions {
> __u8 component[VERSION_MAX_LEN];
> __u8 fw_os[VERSION_MAX_LEN];
> __u8 comp_name[NAME_MAX_LEN];
> - __le16 modules_mask;
> __u8 modules_counter;
> - __u8 reserved[1];
> + __u8 reserved[3];
> struct hl_module_data modules[];
> };
>
Reviewed-by: Ofir Bitton <obitton at habana.ai>
More information about the dri-devel
mailing list