diff options
| -rw-r--r-- | Documentation/ABI/testing/debugfs-driver-habanalabs | 72 | ||||
| -rw-r--r-- | Documentation/ABI/testing/sysfs-driver-habanalabs | 12 | ||||
| -rw-r--r-- | drivers/accel/habanalabs/common/device.c | 25 | ||||
| -rw-r--r-- | drivers/accel/habanalabs/common/firmware_if.c | 123 | ||||
| -rw-r--r-- | drivers/accel/habanalabs/common/habanalabs.h | 15 | ||||
| -rw-r--r-- | drivers/accel/habanalabs/common/habanalabs_drv.c | 37 | ||||
| -rw-r--r-- | drivers/accel/habanalabs/common/habanalabs_ioctl.c | 55 | ||||
| -rw-r--r-- | drivers/accel/habanalabs/common/hwmon.c | 4 | ||||
| -rw-r--r-- | drivers/accel/habanalabs/common/memory.c | 7 | ||||
| -rw-r--r-- | drivers/accel/habanalabs/common/mmu/mmu.c | 1 | ||||
| -rw-r--r-- | drivers/accel/habanalabs/common/sysfs.c | 42 | ||||
| -rw-r--r-- | drivers/accel/habanalabs/gaudi2/gaudi2.c | 74 | ||||
| -rw-r--r-- | drivers/accel/habanalabs/include/gaudi2/asic_reg/gaudi2_regs.h | 13 | ||||
| -rw-r--r-- | drivers/accel/habanalabs/include/hw_ip/pci/pci_general.h | 1 | ||||
| -rw-r--r-- | include/linux/habanalabs/cpucp_if.h | 8 | ||||
| -rw-r--r-- | include/uapi/drm/habanalabs_accel.h | 28 |
16 files changed, 333 insertions, 184 deletions
diff --git a/Documentation/ABI/testing/debugfs-driver-habanalabs b/Documentation/ABI/testing/debugfs-driver-habanalabs index 042fd125fbc9..a7a432dc4015 100644 --- a/Documentation/ABI/testing/debugfs-driver-habanalabs +++ b/Documentation/ABI/testing/debugfs-driver-habanalabs @@ -1,4 +1,4 @@ -What: /sys/kernel/debug/accel/<n>/addr +What: /sys/kernel/debug/accel/<parent_device>/addr Date: Jan 2019 KernelVersion: 5.1 Contact: ogabbay@kernel.org @@ -8,34 +8,34 @@ Description: Sets the device address to be used for read or write through only when the IOMMU is disabled. The acceptable value is a string that starts with "0x" -What: /sys/kernel/debug/accel/<n>/clk_gate +What: /sys/kernel/debug/accel/<parent_device>/clk_gate Date: May 2020 KernelVersion: 5.8 Contact: ogabbay@kernel.org Description: This setting is now deprecated as clock gating is handled solely by the f/w -What: /sys/kernel/debug/accel/<n>/command_buffers +What: /sys/kernel/debug/accel/<parent_device>/command_buffers Date: Jan 2019 KernelVersion: 5.1 Contact: ogabbay@kernel.org Description: Displays a list with information about the currently allocated command buffers -What: /sys/kernel/debug/accel/<n>/command_submission +What: /sys/kernel/debug/accel/<parent_device>/command_submission Date: Jan 2019 KernelVersion: 5.1 Contact: ogabbay@kernel.org Description: Displays a list with information about the currently active command submissions -What: /sys/kernel/debug/accel/<n>/command_submission_jobs +What: /sys/kernel/debug/accel/<parent_device>/command_submission_jobs Date: Jan 2019 KernelVersion: 5.1 Contact: ogabbay@kernel.org Description: Displays a list with detailed information about each JOB (CB) of each active command submission -What: /sys/kernel/debug/accel/<n>/data32 +What: /sys/kernel/debug/accel/<parent_device>/data32 Date: Jan 2019 KernelVersion: 5.1 Contact: ogabbay@kernel.org @@ -50,7 +50,7 @@ Description: Allows the root user to read or write directly through the If the IOMMU is disabled, it also allows the root user to read or write from the host a device VA of a host mapped memory -What: /sys/kernel/debug/accel/<n>/data64 +What: /sys/kernel/debug/accel/<parent_device>/data64 Date: Jan 2020 KernelVersion: 5.6 Contact: ogabbay@kernel.org @@ -65,7 +65,7 @@ Description: Allows the root user to read or write 64 bit data directly If the IOMMU is disabled, it also allows the root user to read or write from the host a device VA of a host mapped memory -What: /sys/kernel/debug/accel/<n>/data_dma +What: /sys/kernel/debug/accel/<parent_device>/data_dma Date: Apr 2021 KernelVersion: 5.13 Contact: ogabbay@kernel.org @@ -83,7 +83,7 @@ Description: Allows the root user to read from the device's internal workloads. Only supported on GAUDI at this stage. -What: /sys/kernel/debug/accel/<n>/device +What: /sys/kernel/debug/accel/<parent_device>/device Date: Jan 2019 KernelVersion: 5.1 Contact: ogabbay@kernel.org @@ -91,14 +91,14 @@ Description: Enables the root user to set the device to specific state. Valid values are "disable", "enable", "suspend", "resume". User can read this property to see the valid values -What: /sys/kernel/debug/accel/<n>/device_release_watchdog_timeout +What: /sys/kernel/debug/accel/<parent_device>/device_release_watchdog_timeout Date: Oct 2022 KernelVersion: 6.2 Contact: ttayar@habana.ai Description: The watchdog timeout value in seconds for a device release upon certain error cases, after which the device is reset. -What: /sys/kernel/debug/accel/<n>/dma_size +What: /sys/kernel/debug/accel/<parent_device>/dma_size Date: Apr 2021 KernelVersion: 5.13 Contact: ogabbay@kernel.org @@ -108,7 +108,7 @@ Description: Specify the size of the DMA transaction when using DMA to read When the write is finished, the user can read the "data_dma" blob -What: /sys/kernel/debug/accel/<n>/dump_razwi_events +What: /sys/kernel/debug/accel/<parent_device>/dump_razwi_events Date: Aug 2022 KernelVersion: 5.20 Contact: fkassabri@habana.ai @@ -117,7 +117,7 @@ Description: Dumps all razwi events to dmesg if exist. the routine will clear the status register. Usage: cat dump_razwi_events -What: /sys/kernel/debug/accel/<n>/dump_security_violations +What: /sys/kernel/debug/accel/<parent_device>/dump_security_violations Date: Jan 2021 KernelVersion: 5.12 Contact: ogabbay@kernel.org @@ -125,14 +125,14 @@ Description: Dumps all security violations to dmesg. This will also ack all security violations meanings those violations will not be dumped next time user calls this API -What: /sys/kernel/debug/accel/<n>/engines +What: /sys/kernel/debug/accel/<parent_device>/engines Date: Jul 2019 KernelVersion: 5.3 Contact: ogabbay@kernel.org Description: Displays the status registers values of the device engines and their derived idle status -What: /sys/kernel/debug/accel/<n>/i2c_addr +What: /sys/kernel/debug/accel/<parent_device>/i2c_addr Date: Jan 2019 KernelVersion: 5.1 Contact: ogabbay@kernel.org @@ -140,7 +140,7 @@ Description: Sets I2C device address for I2C transaction that is generated by the device's CPU, Not available when device is loaded with secured firmware -What: /sys/kernel/debug/accel/<n>/i2c_bus +What: /sys/kernel/debug/accel/<parent_device>/i2c_bus Date: Jan 2019 KernelVersion: 5.1 Contact: ogabbay@kernel.org @@ -148,7 +148,7 @@ Description: Sets I2C bus address for I2C transaction that is generated by the device's CPU, Not available when device is loaded with secured firmware -What: /sys/kernel/debug/accel/<n>/i2c_data +What: /sys/kernel/debug/accel/<parent_device>/i2c_data Date: Jan 2019 KernelVersion: 5.1 Contact: ogabbay@kernel.org @@ -157,7 +157,7 @@ Description: Triggers an I2C transaction that is generated by the device's reading from the file generates a read transaction, Not available when device is loaded with secured firmware -What: /sys/kernel/debug/accel/<n>/i2c_len +What: /sys/kernel/debug/accel/<parent_device>/i2c_len Date: Dec 2021 KernelVersion: 5.17 Contact: obitton@habana.ai @@ -165,7 +165,7 @@ Description: Sets I2C length in bytes for I2C transaction that is generated b the device's CPU, Not available when device is loaded with secured firmware -What: /sys/kernel/debug/accel/<n>/i2c_reg +What: /sys/kernel/debug/accel/<parent_device>/i2c_reg Date: Jan 2019 KernelVersion: 5.1 Contact: ogabbay@kernel.org @@ -173,35 +173,35 @@ Description: Sets I2C register id for I2C transaction that is generated by the device's CPU, Not available when device is loaded with secured firmware -What: /sys/kernel/debug/accel/<n>/led0 +What: /sys/kernel/debug/accel/<parent_device>/led0 Date: Jan 2019 KernelVersion: 5.1 Contact: ogabbay@kernel.org Description: Sets the state of the first S/W led on the device, Not available when device is loaded with secured firmware -What: /sys/kernel/debug/accel/<n>/led1 +What: /sys/kernel/debug/accel/<parent_device>/led1 Date: Jan 2019 KernelVersion: 5.1 Contact: ogabbay@kernel.org Description: Sets the state of the second S/W led on the device, Not available when device is loaded with secured firmware -What: /sys/kernel/debug/accel/<n>/led2 +What: /sys/kernel/debug/accel/<parent_device>/led2 Date: Jan 2019 KernelVersion: 5.1 Contact: ogabbay@kernel.org Description: Sets the state of the third S/W led on the device, Not available when device is loaded with secured firmware -What: /sys/kernel/debug/accel/<n>/memory_scrub +What: /sys/kernel/debug/accel/<parent_device>/memory_scrub Date: May 2022 KernelVersion: 5.19 Contact: dhirschfeld@habana.ai Description: Allows the root user to scrub the dram memory. The scrubbing value can be set using the debugfs file memory_scrub_val. -What: /sys/kernel/debug/accel/<n>/memory_scrub_val +What: /sys/kernel/debug/accel/<parent_device>/memory_scrub_val Date: May 2022 KernelVersion: 5.19 Contact: dhirschfeld@habana.ai @@ -209,7 +209,7 @@ Description: The value to which the dram will be set to when the user scrubs the dram using 'memory_scrub' debugfs file and the scrubbing value when using module param 'memory_scrub' -What: /sys/kernel/debug/accel/<n>/mmu +What: /sys/kernel/debug/accel/<parent_device>/mmu Date: Jan 2019 KernelVersion: 5.1 Contact: ogabbay@kernel.org @@ -219,7 +219,7 @@ Description: Displays the hop values and physical address for a given ASID e.g. to display info about VA 0x1000 for ASID 1 you need to do: echo "1 0x1000" > /sys/kernel/debug/accel/0/mmu -What: /sys/kernel/debug/accel/<n>/mmu_error +What: /sys/kernel/debug/accel/<parent_device>/mmu_error Date: Mar 2021 KernelVersion: 5.12 Contact: fkassabri@habana.ai @@ -229,7 +229,7 @@ Description: Check and display page fault or access violation mmu errors for echo "0x200" > /sys/kernel/debug/accel/0/mmu_error cat /sys/kernel/debug/accel/0/mmu_error -What: /sys/kernel/debug/accel/<n>/monitor_dump +What: /sys/kernel/debug/accel/<parent_device>/monitor_dump Date: Mar 2022 KernelVersion: 5.19 Contact: osharabi@habana.ai @@ -243,7 +243,7 @@ Description: Allows the root user to dump monitors status from the device's This interface doesn't support concurrency in the same device. Only supported on GAUDI. -What: /sys/kernel/debug/accel/<n>/monitor_dump_trig +What: /sys/kernel/debug/accel/<parent_device>/monitor_dump_trig Date: Mar 2022 KernelVersion: 5.19 Contact: osharabi@habana.ai @@ -253,14 +253,14 @@ Description: Triggers dump of monitor data. The value to trigger the operatio When the write is finished, the user can read the "monitor_dump" blob -What: /sys/kernel/debug/accel/<n>/set_power_state +What: /sys/kernel/debug/accel/<parent_device>/set_power_state Date: Jan 2019 KernelVersion: 5.1 Contact: ogabbay@kernel.org Description: Sets the PCI power state. Valid values are "1" for D0 and "2" for D3Hot -What: /sys/kernel/debug/accel/<n>/skip_reset_on_timeout +What: /sys/kernel/debug/accel/<parent_device>/skip_reset_on_timeout Date: Jun 2021 KernelVersion: 5.13 Contact: ynudelman@habana.ai @@ -268,7 +268,7 @@ Description: Sets the skip reset on timeout option for the device. Value of "0" means device will be reset in case some CS has timed out, otherwise it will not be reset. -What: /sys/kernel/debug/accel/<n>/state_dump +What: /sys/kernel/debug/accel/<parent_device>/state_dump Date: Oct 2021 KernelVersion: 5.15 Contact: ynudelman@habana.ai @@ -279,7 +279,7 @@ Description: Gets the state dump occurring on a CS timeout or failure. Writing an integer X discards X state dumps, so that the next read would return X+1-st newest state dump. -What: /sys/kernel/debug/accel/<n>/stop_on_err +What: /sys/kernel/debug/accel/<parent_device>/stop_on_err Date: Mar 2020 KernelVersion: 5.6 Contact: ogabbay@kernel.org @@ -287,13 +287,13 @@ Description: Sets the stop-on_error option for the device engines. Value of "0" is for disable, otherwise enable. Relevant only for GOYA and GAUDI. -What: /sys/kernel/debug/accel/<n>/timeout_locked +What: /sys/kernel/debug/accel/<parent_device>/timeout_locked Date: Sep 2021 KernelVersion: 5.16 Contact: obitton@habana.ai Description: Sets the command submission timeout value in seconds. -What: /sys/kernel/debug/accel/<n>/userptr +What: /sys/kernel/debug/accel/<parent_device>/userptr Date: Jan 2019 KernelVersion: 5.1 Contact: ogabbay@kernel.org @@ -301,7 +301,7 @@ Description: Displays a list with information about the current user pointers (user virtual addresses) that are pinned and mapped to DMA addresses -What: /sys/kernel/debug/accel/<n>/userptr_lookup +What: /sys/kernel/debug/accel/<parent_device>/userptr_lookup Date: Oct 2021 KernelVersion: 5.15 Contact: ogabbay@kernel.org @@ -309,7 +309,7 @@ Description: Allows to search for specific user pointers (user virtual addresses) that are pinned and mapped to DMA addresses, and see their resolution to the specific dma address. -What: /sys/kernel/debug/accel/<n>/vm +What: /sys/kernel/debug/accel/<parent_device>/vm Date: Jan 2019 KernelVersion: 5.1 Contact: ogabbay@kernel.org diff --git a/Documentation/ABI/testing/sysfs-driver-habanalabs b/Documentation/ABI/testing/sysfs-driver-habanalabs index c63ca1ad500d..4244f5af4b54 100644 --- a/Documentation/ABI/testing/sysfs-driver-habanalabs +++ b/Documentation/ABI/testing/sysfs-driver-habanalabs @@ -149,6 +149,18 @@ Contact: ogabbay@kernel.org Description: Displays the current clock frequency, in Hz, of the MME compute engine. This property is valid only for the Goya ASIC family +What: /sys/class/accel/accel<n>/device/module_id +Date: Nov 2023 +KernelVersion: not yet upstreamed +Contact: ogabbay@kernel.org +Description: Displays the device's module id + +What: /sys/class/accel/accel<n>/device/parent_device +Date: Nov 2023 +KernelVersion: 6.8 +Contact: ttayar@habana.ai +Description: Displays the name of the parent device of the accel device + What: /sys/class/accel/accel<n>/device/pci_addr Date: Jan 2019 KernelVersion: 5.1 diff --git a/drivers/accel/habanalabs/common/device.c b/drivers/accel/habanalabs/common/device.c index 9711e8fc979d..a365791a9f5c 100644 --- a/drivers/accel/habanalabs/common/device.c +++ b/drivers/accel/habanalabs/common/device.c @@ -853,6 +853,9 @@ static int device_early_init(struct hl_device *hdev) gaudi2_set_asic_funcs(hdev); strscpy(hdev->asic_name, "GAUDI2B", sizeof(hdev->asic_name)); break; + case ASIC_GAUDI2C: + gaudi2_set_asic_funcs(hdev); + strscpy(hdev->asic_name, "GAUDI2C", sizeof(hdev->asic_name)); break; default: dev_err(hdev->dev, "Unrecognized ASIC type %d\n", @@ -1041,18 +1044,21 @@ static bool is_pci_link_healthy(struct hl_device *hdev) return (vendor_id == PCI_VENDOR_ID_HABANALABS); } -static void hl_device_eq_heartbeat(struct hl_device *hdev) +static int hl_device_eq_heartbeat_check(struct hl_device *hdev) { - u64 event_mask = HL_NOTIFIER_EVENT_DEVICE_RESET | HL_NOTIFIER_EVENT_DEVICE_UNAVAILABLE; struct asic_fixed_properties *prop = &hdev->asic_prop; if (!prop->cpucp_info.eq_health_check_supported) - return; + return 0; - if (hdev->eq_heartbeat_received) + if (hdev->eq_heartbeat_received) { hdev->eq_heartbeat_received = false; - else - hl_device_cond_reset(hdev, HL_DRV_RESET_HARD, event_mask); + } else { + dev_err(hdev->dev, "EQ heartbeat event was not received!\n"); + return -EIO; + } + + return 0; } static void hl_device_heartbeat(struct work_struct *work) @@ -1069,10 +1075,9 @@ static void hl_device_heartbeat(struct work_struct *work) /* * For EQ health check need to check if driver received the heartbeat eq event * in order to validate the eq is working. + * Only if both the EQ is healthy and we managed to send the next heartbeat reschedule. */ - hl_device_eq_heartbeat(hdev); - - if (!hdev->asic_funcs->send_heartbeat(hdev)) + if ((!hl_device_eq_heartbeat_check(hdev)) && (!hdev->asic_funcs->send_heartbeat(hdev))) goto reschedule; if (hl_device_operational(hdev, NULL)) @@ -2035,7 +2040,7 @@ device_reset: if (ctx) hl_ctx_put(ctx); - return hl_device_reset(hdev, flags); + return hl_device_reset(hdev, flags | HL_DRV_RESET_HARD); } static void hl_notifier_event_send(struct hl_notifier_event *notifier_event, u64 event_mask) diff --git a/drivers/accel/habanalabs/common/firmware_if.c b/drivers/accel/habanalabs/common/firmware_if.c index 47e8384134aa..3558a6a8e192 100644 --- a/drivers/accel/habanalabs/common/firmware_if.c +++ b/drivers/accel/habanalabs/common/firmware_if.c @@ -646,39 +646,27 @@ int hl_fw_send_heartbeat(struct hl_device *hdev) return rc; } -static bool fw_report_boot_dev0(struct hl_device *hdev, u32 err_val, - u32 sts_val) +static bool fw_report_boot_dev0(struct hl_device *hdev, u32 err_val, u32 sts_val) { bool err_exists = false; if (!(err_val & CPU_BOOT_ERR0_ENABLED)) return false; - if (err_val & CPU_BOOT_ERR0_DRAM_INIT_FAIL) { - dev_err(hdev->dev, - "Device boot error - DRAM initialization failed\n"); - err_exists = true; - } + 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) { + if (err_val & CPU_BOOT_ERR0_FIT_CORRUPTED) dev_err(hdev->dev, "Device boot error - FIT image corrupted\n"); - err_exists = true; - } - if (err_val & CPU_BOOT_ERR0_TS_INIT_FAIL) { - dev_err(hdev->dev, - "Device boot error - Thermal Sensor initialization failed\n"); - err_exists = true; - } + 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_BMC_WAIT_SKIPPED) { if (hdev->bmc_enable) { - dev_err(hdev->dev, - "Device boot error - Skipped waiting for BMC\n"); - err_exists = true; + dev_err(hdev->dev, "Device boot error - Skipped waiting for BMC\n"); } else { - dev_info(hdev->dev, - "Device boot message - Skipped waiting for BMC\n"); + dev_info(hdev->dev, "Device boot message - Skipped waiting for BMC\n"); /* This is an info so we don't want it to disable the * device */ @@ -686,48 +674,29 @@ static bool fw_report_boot_dev0(struct hl_device *hdev, u32 err_val, } } - if (err_val & CPU_BOOT_ERR0_NIC_DATA_NOT_RDY) { - dev_err(hdev->dev, - "Device boot error - Serdes data from BMC not available\n"); - err_exists = true; - } + 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"); - err_exists = true; - } + 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_err(hdev->dev, - "Device boot warning - security not ready\n"); - err_exists = true; - } + if (err_val & CPU_BOOT_ERR0_SECURITY_NOT_RDY) + dev_err(hdev->dev, "Device boot warning - security not ready\n"); - if (err_val & CPU_BOOT_ERR0_SECURITY_FAIL) { + if (err_val & CPU_BOOT_ERR0_SECURITY_FAIL) dev_err(hdev->dev, "Device boot error - security failure\n"); - err_exists = true; - } - if (err_val & CPU_BOOT_ERR0_EFUSE_FAIL) { + if (err_val & CPU_BOOT_ERR0_EFUSE_FAIL) dev_err(hdev->dev, "Device boot error - eFuse failure\n"); - err_exists = true; - } - if (err_val & CPU_BOOT_ERR0_SEC_IMG_VER_FAIL) { + if (err_val & CPU_BOOT_ERR0_SEC_IMG_VER_FAIL) dev_err(hdev->dev, "Device boot error - Failed to load preboot secondary image\n"); - err_exists = true; - } - if (err_val & CPU_BOOT_ERR0_PLL_FAIL) { + if (err_val & CPU_BOOT_ERR0_PLL_FAIL) dev_err(hdev->dev, "Device boot error - PLL failure\n"); - err_exists = true; - } - if (err_val & CPU_BOOT_ERR0_TMP_THRESH_INIT_FAIL) { + if (err_val & CPU_BOOT_ERR0_TMP_THRESH_INIT_FAIL) dev_err(hdev->dev, "Device boot error - Failed to set threshold for temperature sensor\n"); - err_exists = true; - } if (err_val & CPU_BOOT_ERR0_DEVICE_UNUSABLE_FAIL) { /* Ignore this bit, don't prevent driver loading */ @@ -735,52 +704,32 @@ static bool fw_report_boot_dev0(struct hl_device *hdev, u32 err_val, err_val &= ~CPU_BOOT_ERR0_DEVICE_UNUSABLE_FAIL; } - if (err_val & CPU_BOOT_ERR0_BINNING_FAIL) { + if (err_val & CPU_BOOT_ERR0_BINNING_FAIL) dev_err(hdev->dev, "Device boot error - binning failure\n"); - err_exists = true; - } if (sts_val & CPU_BOOT_DEV_STS0_ENABLED) dev_dbg(hdev->dev, "Device status0 %#x\n", sts_val); + if (err_val & CPU_BOOT_ERR0_DRAM_SKIPPED) + dev_err(hdev->dev, "Device boot warning - Skipped DRAM initialization\n"); + + if (err_val & CPU_BOOT_ERR_ENG_ARC_MEM_SCRUB_FAIL) + dev_err(hdev->dev, "Device boot error - ARC memory scrub failed\n"); + + /* All warnings should go here in order not to reach the unknown error validation */ if (err_val & CPU_BOOT_ERR0_EEPROM_FAIL) { dev_err(hdev->dev, "Device boot error - EEPROM failure detected\n"); err_exists = true; } - /* All warnings should go here in order not to reach the unknown error validation */ - if (err_val & CPU_BOOT_ERR0_DRAM_SKIPPED) { - dev_warn(hdev->dev, - "Device boot warning - Skipped DRAM initialization\n"); - /* This is a warning so we don't want it to disable the - * device - */ - err_val &= ~CPU_BOOT_ERR0_DRAM_SKIPPED; - } + if (err_val & CPU_BOOT_ERR0_PRI_IMG_VER_FAIL) + dev_warn(hdev->dev, "Device boot warning - Failed to load preboot primary image\n"); - if (err_val & CPU_BOOT_ERR0_PRI_IMG_VER_FAIL) { - dev_warn(hdev->dev, - "Device boot warning - Failed to load preboot primary image\n"); - /* This is a warning so we don't want it to disable the - * device as we have a secondary preboot image - */ - err_val &= ~CPU_BOOT_ERR0_PRI_IMG_VER_FAIL; - } - - if (err_val & CPU_BOOT_ERR0_TPM_FAIL) { - dev_warn(hdev->dev, - "Device boot warning - TPM failure\n"); - /* This is a warning so we don't want it to disable the - * device - */ - err_val &= ~CPU_BOOT_ERR0_TPM_FAIL; - } + if (err_val & CPU_BOOT_ERR0_TPM_FAIL) + dev_warn(hdev->dev, "Device boot warning - TPM failure\n"); - if (!err_exists && (err_val & ~CPU_BOOT_ERR0_ENABLED)) { - dev_err(hdev->dev, - "Device boot error - unknown ERR0 error 0x%08x\n", err_val); + if (err_val & CPU_BOOT_ERR_FATAL_MASK) err_exists = true; - } /* return error only if it's in the predefined mask */ if (err_exists && ((err_val & ~CPU_BOOT_ERR0_ENABLED) & @@ -3295,6 +3244,14 @@ int hl_fw_get_sec_attest_info(struct hl_device *hdev, struct cpucp_sec_attest_in HL_CPUCP_SEC_ATTEST_INFO_TINEOUT_USEC); } +int hl_fw_get_dev_info_signed(struct hl_device *hdev, + struct cpucp_dev_info_signed *dev_info_signed, u32 nonce) +{ + return hl_fw_get_sec_attest_data(hdev, CPUCP_PACKET_INFO_SIGNED_GET, dev_info_signed, + sizeof(struct cpucp_dev_info_signed), nonce, + HL_CPUCP_SEC_ATTEST_INFO_TINEOUT_USEC); +} + int hl_fw_send_generic_request(struct hl_device *hdev, enum hl_passthrough_type sub_opcode, dma_addr_t buff, u32 *size) { diff --git a/drivers/accel/habanalabs/common/habanalabs.h b/drivers/accel/habanalabs/common/habanalabs.h index 1655c101c705..2a900c9941fe 100644 --- a/drivers/accel/habanalabs/common/habanalabs.h +++ b/drivers/accel/habanalabs/common/habanalabs.h @@ -1262,6 +1262,7 @@ struct hl_dec { * @ASIC_GAUDI_SEC: Gaudi secured device (HL-2000). * @ASIC_GAUDI2: Gaudi2 device. * @ASIC_GAUDI2B: Gaudi2B device. + * @ASIC_GAUDI2C: Gaudi2C device. */ enum hl_asic_type { ASIC_INVALID, @@ -1270,6 +1271,7 @@ enum hl_asic_type { ASIC_GAUDI_SEC, ASIC_GAUDI2, ASIC_GAUDI2B, + ASIC_GAUDI2C, }; struct hl_cs_parser; @@ -3519,6 +3521,9 @@ struct hl_device { u8 heartbeat; }; +/* Retrieve PCI device name in case of a PCI device or dev name in simulator */ +#define HL_DEV_NAME(hdev) \ + ((hdev)->pdev ? dev_name(&(hdev)->pdev->dev) : "NA-DEVICE") /** * struct hl_cs_encaps_sig_handle - encapsulated signals handle structure @@ -3594,6 +3599,14 @@ static inline bool hl_is_fw_sw_ver_below(struct hl_device *hdev, u32 fw_sw_major return false; } +static inline bool hl_is_fw_sw_ver_equal_or_greater(struct hl_device *hdev, u32 fw_sw_major, + u32 fw_sw_minor) +{ + return (hdev->fw_sw_major_ver > fw_sw_major || + (hdev->fw_sw_major_ver == fw_sw_major && + hdev->fw_sw_minor_ver >= fw_sw_minor)); +} + /* * Kernel module functions that can be accessed by entire module */ @@ -3954,6 +3967,8 @@ long hl_fw_get_max_power(struct hl_device *hdev); void hl_fw_set_max_power(struct hl_device *hdev); int hl_fw_get_sec_attest_info(struct hl_device *hdev, struct cpucp_sec_attest_info *sec_attest_info, u32 nonce); +int hl_fw_get_dev_info_signed(struct hl_device *hdev, + struct cpucp_dev_info_signed *dev_info_signed, u32 nonce); int hl_set_voltage(struct hl_device *hdev, int sensor_index, u32 attr, long value); int hl_set_current(struct hl_device *hdev, int sensor_index, u32 attr, long value); int hl_set_power(struct hl_device *hdev, int sensor_index, u32 attr, long value); diff --git a/drivers/accel/habanalabs/common/habanalabs_drv.c b/drivers/accel/habanalabs/common/habanalabs_drv.c index 306a5bc9bf89..e542fd40e16c 100644 --- a/drivers/accel/habanalabs/common/habanalabs_drv.c +++ b/drivers/accel/habanalabs/common/habanalabs_drv.c @@ -141,6 +141,9 @@ static enum hl_asic_type get_asic_type(struct hl_device *hdev) case REV_ID_B: asic_type = ASIC_GAUDI2B; break; + case REV_ID_C: + asic_type = ASIC_GAUDI2C; + break; default: break; } @@ -670,6 +673,38 @@ static pci_ers_result_t hl_pci_err_slot_reset(struct pci_dev *pdev) return PCI_ERS_RESULT_RECOVERED; } +static void hl_pci_reset_prepare(struct pci_dev *pdev) +{ + struct hl_device *hdev; + + hdev = pci_get_drvdata(pdev); + if (!hdev) + return; + + hdev->disabled = true; +} + +static void hl_pci_reset_done(struct pci_dev *pdev) +{ + struct hl_device *hdev; + u32 flags; + + hdev = pci_get_drvdata(pdev); + if (!hdev) + return; + + /* + * Schedule a thread to trigger hard reset. + * The reason for this handler, is for rare cases where the driver is up + * and FLR occurs. This is valid only when working with no VM, so FW handles FLR + * and resets the device. FW will go back preboot stage, so driver needs to perform + * hard reset in order to load FW fit again. + */ + flags = HL_DRV_RESET_HARD | HL_DRV_RESET_BYPASS_REQ_TO_FW; + + hl_device_reset(hdev, flags); +} + static const struct dev_pm_ops hl_pm_ops = { .suspend = hl_pmops_suspend, .resume = hl_pmops_resume, @@ -679,6 +714,8 @@ static const struct pci_error_handlers hl_pci_err_handler = { .error_detected = hl_pci_err_detected, .slot_reset = hl_pci_err_slot_reset, .resume = hl_pci_err_resume, + .reset_prepare = hl_pci_reset_prepare, + .reset_done = hl_pci_reset_done, }; static struct pci_driver hl_pci_driver = { diff --git a/drivers/accel/habanalabs/common/habanalabs_ioctl.c b/drivers/accel/habanalabs/common/habanalabs_ioctl.c index 8ef36effb95b..1dd6e23172ca 100644 --- a/drivers/accel/habanalabs/common/habanalabs_ioctl.c +++ b/drivers/accel/habanalabs/common/habanalabs_ioctl.c @@ -19,6 +19,9 @@ #include <asm/msr.h> +/* make sure there is space for all the signed info */ +static_assert(sizeof(struct cpucp_info) <= SEC_DEV_INFO_BUF_SZ); + static u32 hl_debug_struct_size[HL_DEBUG_OP_TIMESTAMP + 1] = { [HL_DEBUG_OP_ETR] = sizeof(struct hl_debug_params_etr), [HL_DEBUG_OP_ETF] = sizeof(struct hl_debug_params_etf), @@ -685,7 +688,7 @@ static int sec_attest_info(struct hl_fpriv *hpriv, struct hl_info_args *args) if (!sec_attest_info) return -ENOMEM; - info = kmalloc(sizeof(*info), GFP_KERNEL); + info = kzalloc(sizeof(*info), GFP_KERNEL); if (!info) { rc = -ENOMEM; goto free_sec_attest_info; @@ -719,6 +722,53 @@ free_sec_attest_info: return rc; } +static int dev_info_signed(struct hl_fpriv *hpriv, struct hl_info_args *args) +{ + void __user *out = (void __user *) (uintptr_t) args->return_pointer; + struct cpucp_dev_info_signed *dev_info_signed; + struct hl_info_signed *info; + u32 max_size = args->return_size; + int rc; + + if ((!max_size) || (!out)) + return -EINVAL; + + dev_info_signed = kzalloc(sizeof(*dev_info_signed), GFP_KERNEL); + if (!dev_info_signed) + return -ENOMEM; + + info = kzalloc(sizeof(*info), GFP_KERNEL); + if (!info) { + rc = -ENOMEM; + goto free_dev_info_signed; + } + + rc = hl_fw_get_dev_info_signed(hpriv->hdev, + dev_info_signed, args->sec_attest_nonce); + if (rc) + goto free_info; + + info->nonce = le32_to_cpu(dev_info_signed->nonce); + info->info_sig_len = dev_info_signed->info_sig_len; + info->pub_data_len = le16_to_cpu(dev_info_signed->pub_data_len); + info->certificate_len = le16_to_cpu(dev_info_signed->certificate_len); + info->dev_info_len = sizeof(struct cpucp_info); + memcpy(&info->info_sig, &dev_info_signed->info_sig, sizeof(info->info_sig)); + memcpy(&info->public_data, &dev_info_signed->public_data, sizeof(info->public_data)); + memcpy(&info->certificate, &dev_info_signed->certificate, sizeof(info->certificate)); + memcpy(&info->dev_info, &dev_info_signed->info, info->dev_info_len); + + rc = copy_to_user(out, info, min_t(size_t, max_size, sizeof(*info))) ? -EFAULT : 0; + +free_info: + kfree(info); +free_dev_info_signed: + kfree(dev_info_signed); + + return rc; +} + + static int eventfd_register(struct hl_fpriv *hpriv, struct hl_info_args *args) { int rc; @@ -1089,6 +1139,9 @@ static int _hl_info_ioctl(struct hl_fpriv *hpriv, void *data, case HL_INFO_FW_GENERIC_REQ: return send_fw_generic_request(hdev, args); + case HL_INFO_DEV_SIGNED: + return dev_info_signed(hpriv, args); + default: dev_err(dev, "Invalid request %d\n", args->op); rc = -EINVAL; diff --git a/drivers/accel/habanalabs/common/hwmon.c b/drivers/accel/habanalabs/common/hwmon.c index 8598056216e7..1ee2ee07e9ed 100644 --- a/drivers/accel/habanalabs/common/hwmon.c +++ b/drivers/accel/habanalabs/common/hwmon.c @@ -578,10 +578,6 @@ int hl_get_temperature(struct hl_device *hdev, CPUCP_PKT_CTL_OPCODE_SHIFT); pkt.sensor_index = __cpu_to_le16(sensor_index); pkt.type = __cpu_to_le16(attr); - - dev_dbg(hdev->dev, "get temp, ctl 0x%x, sensor %d, type %d\n", - pkt.ctl, pkt.sensor_index, pkt.type); - rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt), 0, &result); diff --git a/drivers/accel/habanalabs/common/memory.c b/drivers/accel/habanalabs/common/memory.c index 0b8689fe0b64..3348ad12c237 100644 --- a/drivers/accel/habanalabs/common/memory.c +++ b/drivers/accel/habanalabs/common/memory.c @@ -955,8 +955,8 @@ static int map_phys_pg_pack(struct hl_ctx *ctx, u64 vaddr, (i + 1) == phys_pg_pack->npages); if (rc) { dev_err(hdev->dev, - "map failed for handle %u, npages: %llu, mapped: %llu", - phys_pg_pack->handle, phys_pg_pack->npages, + "map failed (%d) for handle %u, npages: %llu, mapped: %llu\n", + rc, phys_pg_pack->handle, phys_pg_pa |