diff options
Diffstat (limited to 'drivers/misc/habanalabs/common/firmware_if.c')
| -rw-r--r-- | drivers/misc/habanalabs/common/firmware_if.c | 157 |
1 files changed, 102 insertions, 55 deletions
diff --git a/drivers/misc/habanalabs/common/firmware_if.c b/drivers/misc/habanalabs/common/firmware_if.c index c9a12980218a..09706c571e95 100644 --- a/drivers/misc/habanalabs/common/firmware_if.c +++ b/drivers/misc/habanalabs/common/firmware_if.c @@ -90,9 +90,10 @@ int hl_fw_send_pci_access_msg(struct hl_device *hdev, u32 opcode) int hl_fw_send_cpu_message(struct hl_device *hdev, u32 hw_queue_id, u32 *msg, u16 len, u32 timeout, u64 *result) { + struct hl_hw_queue *queue = &hdev->kernel_queues[hw_queue_id]; struct cpucp_packet *pkt; dma_addr_t pkt_dma_addr; - u32 tmp; + u32 tmp, expected_ack_val; int rc = 0; pkt = hdev->asic_funcs->cpu_accessible_dma_pool_alloc(hdev, len, @@ -115,14 +116,23 @@ int hl_fw_send_cpu_message(struct hl_device *hdev, u32 hw_queue_id, u32 *msg, goto out; } + /* set fence to a non valid value */ + pkt->fence = UINT_MAX; + rc = hl_hw_queue_send_cb_no_cmpl(hdev, hw_queue_id, len, pkt_dma_addr); if (rc) { dev_err(hdev->dev, "Failed to send CB on CPU PQ (%d)\n", rc); goto out; } + if (hdev->asic_prop.fw_app_security_map & + CPU_BOOT_DEV_STS0_PKT_PI_ACK_EN) + expected_ack_val = queue->pi; + else + expected_ack_val = CPUCP_PACKET_FENCE_VAL; + rc = hl_poll_timeout_memory(hdev, &pkt->fence, tmp, - (tmp == CPUCP_PACKET_FENCE_VAL), 1000, + (tmp == expected_ack_val), 1000, timeout, true); hl_hw_queue_inc_ci_kernel(hdev, hw_queue_id); @@ -279,8 +289,74 @@ int hl_fw_send_heartbeat(struct hl_device *hdev) return rc; } +static int fw_read_errors(struct hl_device *hdev, u32 boot_err0_reg, + u32 cpu_security_boot_status_reg) +{ + u32 err_val, security_val; + + /* Some of the firmware status codes are deprecated in newer f/w + * versions. In those versions, the errors are reported + * in different registers. Therefore, we need to check those + * registers and print the exact errors. Moreover, there + * may be multiple errors, so we need to report on each error + * separately. Some of the error codes might indicate a state + * that is not an error per-se, but it is an error in production + * environment + */ + err_val = RREG32(boot_err0_reg); + if (!(err_val & CPU_BOOT_ERR0_ENABLED)) + return 0; + + if (err_val & CPU_BOOT_ERR0_DRAM_INIT_FAIL) + dev_err(hdev->dev, + "Device boot error - DRAM initialization failed\n"); + if (err_val & CPU_BOOT_ERR0_FIT_CORRUPTED) + dev_err(hdev->dev, "Device boot error - FIT image corrupted\n"); + if (err_val & CPU_BOOT_ERR0_TS_INIT_FAIL) + dev_err(hdev->dev, + "Device boot error - Thermal Sensor initialization failed\n"); + if (err_val & CPU_BOOT_ERR0_DRAM_SKIPPED) + dev_warn(hdev->dev, + "Device boot warning - Skipped DRAM initialization\n"); + + if (err_val & CPU_BOOT_ERR0_BMC_WAIT_SKIPPED) { + if (hdev->bmc_enable) + dev_warn(hdev->dev, + "Device boot error - Skipped waiting for BMC\n"); + else + err_val &= ~CPU_BOOT_ERR0_BMC_WAIT_SKIPPED; + } + + if (err_val & CPU_BOOT_ERR0_NIC_DATA_NOT_RDY) + dev_err(hdev->dev, + "Device boot error - Serdes data from BMC not available\n"); + if (err_val & CPU_BOOT_ERR0_NIC_FW_FAIL) + dev_err(hdev->dev, + "Device boot error - NIC F/W initialization failed\n"); + if (err_val & CPU_BOOT_ERR0_SECURITY_NOT_RDY) + dev_warn(hdev->dev, + "Device boot warning - security not ready\n"); + if (err_val & CPU_BOOT_ERR0_SECURITY_FAIL) + dev_err(hdev->dev, "Device boot error - security failure\n"); + if (err_val & CPU_BOOT_ERR0_EFUSE_FAIL) + dev_err(hdev->dev, "Device boot error - eFuse failure\n"); + if (err_val & CPU_BOOT_ERR0_PLL_FAIL) + dev_err(hdev->dev, "Device boot error - PLL failure\n"); + + security_val = RREG32(cpu_security_boot_status_reg); + if (security_val & CPU_BOOT_DEV_STS0_ENABLED) + dev_dbg(hdev->dev, "Device security status %#x\n", + security_val); + + if (err_val & ~CPU_BOOT_ERR0_ENABLED) + return -EIO; + + return 0; +} + int hl_fw_cpucp_info_get(struct hl_device *hdev, - u32 cpu_security_boot_status_reg) + u32 cpu_security_boot_status_reg, + u32 boot_err0_reg) { struct asic_fixed_properties *prop = &hdev->asic_prop; struct cpucp_packet pkt = {}; @@ -314,6 +390,12 @@ int hl_fw_cpucp_info_get(struct hl_device *hdev, goto out; } + rc = fw_read_errors(hdev, boot_err0_reg, cpu_security_boot_status_reg); + if (rc) { + dev_err(hdev->dev, "Errors in device boot\n"); + goto out; + } + memcpy(&prop->cpucp_info, cpucp_info_cpu_addr, sizeof(prop->cpucp_info)); @@ -483,58 +565,6 @@ int hl_fw_cpucp_pll_info_get(struct hl_device *hdev, u16 pll_index, return rc; } -static void fw_read_errors(struct hl_device *hdev, u32 boot_err0_reg, - u32 cpu_security_boot_status_reg) -{ - u32 err_val, security_val; - - /* Some of the firmware status codes are deprecated in newer f/w - * versions. In those versions, the errors are reported - * in different registers. Therefore, we need to check those - * registers and print the exact errors. Moreover, there - * may be multiple errors, so we need to report on each error - * separately. Some of the error codes might indicate a state - * that is not an error per-se, but it is an error in production - * environment - */ - err_val = RREG32(boot_err0_reg); - if (!(err_val & CPU_BOOT_ERR0_ENABLED)) - return; - - if (err_val & CPU_BOOT_ERR0_DRAM_INIT_FAIL) - dev_err(hdev->dev, - "Device boot error - DRAM initialization failed\n"); - if (err_val & CPU_BOOT_ERR0_FIT_CORRUPTED) - dev_err(hdev->dev, "Device boot error - FIT image corrupted\n"); - if (err_val & CPU_BOOT_ERR0_TS_INIT_FAIL) - dev_err(hdev->dev, - "Device boot error - Thermal Sensor initialization failed\n"); - if (err_val & CPU_BOOT_ERR0_DRAM_SKIPPED) - dev_warn(hdev->dev, - "Device boot warning - Skipped DRAM initialization\n"); - if (err_val & CPU_BOOT_ERR0_BMC_WAIT_SKIPPED) - dev_warn(hdev->dev, - "Device boot error - Skipped waiting for BMC\n"); - if (err_val & CPU_BOOT_ERR0_NIC_DATA_NOT_RDY) - dev_err(hdev->dev, - "Device boot error - Serdes data from BMC not available\n"); - if (err_val & CPU_BOOT_ERR0_NIC_FW_FAIL) - dev_err(hdev->dev, - "Device boot error - NIC F/W initialization failed\n"); - if (err_val & CPU_BOOT_ERR0_SECURITY_NOT_RDY) - dev_warn(hdev->dev, - "Device boot warning - security not ready\n"); - if (err_val & CPU_BOOT_ERR0_SECURITY_FAIL) - dev_err(hdev->dev, "Device boot error - security failure\n"); - if (err_val & CPU_BOOT_ERR0_EFUSE_FAIL) - dev_err(hdev->dev, "Device boot error - eFuse failure\n"); - - security_val = RREG32(cpu_security_boot_status_reg); - if (security_val & CPU_BOOT_DEV_STS0_ENABLED) - dev_dbg(hdev->dev, "Device security status %#x\n", - security_val); -} - static void detect_cpu_boot_status(struct hl_device *hdev, u32 status) { /* Some of the status codes below are deprecated in newer f/w @@ -659,6 +689,9 @@ int hl_fw_read_preboot_status(struct hl_device *hdev, u32 cpu_boot_status_reg, prop->fw_security_disabled = true; } + dev_dbg(hdev->dev, "Firmware preboot security status %#x\n", + security_status); + dev_dbg(hdev->dev, "Firmware preboot hard-reset is %s\n", prop->hard_reset_done_by_fw ? "enabled" : "disabled"); @@ -753,6 +786,10 @@ int hl_fw_init_cpu(struct hl_device *hdev, u32 cpu_boot_status_reg, if (prop->fw_boot_cpu_security_map & CPU_BOOT_DEV_STS0_FW_HARD_RST_EN) prop->hard_reset_done_by_fw = true; + + dev_dbg(hdev->dev, + "Firmware boot CPU security status %#x\n", + prop->fw_boot_cpu_security_map); } dev_dbg(hdev->dev, "Firmware boot CPU hard-reset is %s\n", @@ -826,6 +863,10 @@ int hl_fw_init_cpu(struct hl_device *hdev, u32 cpu_boot_status_reg, goto out; } + rc = fw_read_errors(hdev, boot_err0_reg, cpu_security_boot_status_reg); + if (rc) + return rc; + /* Clear reset status since we need to read again from app */ prop->hard_reset_done_by_fw = false; @@ -837,6 +878,10 @@ int hl_fw_init_cpu(struct hl_device *hdev, u32 cpu_boot_status_reg, if (prop->fw_app_security_map & CPU_BOOT_DEV_STS0_FW_HARD_RST_EN) prop->hard_reset_done_by_fw = true; + + dev_dbg(hdev->dev, + "Firmware application CPU security status %#x\n", + prop->fw_app_security_map); } dev_dbg(hdev->dev, "Firmware application CPU hard-reset is %s\n", @@ -844,6 +889,8 @@ int hl_fw_init_cpu(struct hl_device *hdev, u32 cpu_boot_status_reg, dev_info(hdev->dev, "Successfully loaded firmware to device\n"); + return 0; + out: fw_read_errors(hdev, boot_err0_reg, cpu_security_boot_status_reg); |