[mellanox] Integrate HW-MGMT Version 7.0030.2008 (sonic-net#17170)

* [Mellanox] Don't populate arm64 Kconfig when integrating hw-mgmt

Signed-off-by: Vivek Reddy <[email protected]>

* Intgerate HW-MGMT 7.0030.2008 Changes

 ## Patch List
* 0285-UBUNTU-SAUCE-mlxbf-gige-Fix-intermittent-no-ip-issue.patch :
* 0286-pinctrl-Introduce-struct-pinfunction-and-PINCTRL_PIN.patch :
* 0287-pinctrl-mlxbf3-Add-pinctrl-driver-support.patch :
* 0288-UBUNTU-SAUCE-gpio-mmio-handle-ngpios-properly-in-bgp.patch :
* 0289-UBUNTU-SAUCE-gpio-mlxbf3-Add-gpio-driver-support.patch :
* 0291-mlxsw-core_hwmon-Align-modules-label-name-assignment.patch :
* 0292-mlxsw-i2c-Limit-single-transaction-buffer-size.patch :
* 0293-mlxsw-reg-Limit-MTBR-register-records-buffer-by-one-.patch :
* 0296-UBUNTU-SAUCE-mmc-sdhci-of-dwcmshc-Add-runtime-PM-ope.patch :
* 0298-UBUNTU-SAUCE-mlxbf-ptm-use-0444-instead-of-S_IRUGO.patch :
* 0299-UBUNTU-SAUCE-mlxbf-ptm-add-atx-debugfs-nodes.patch :
* 0300-UBUNTU-SAUCE-mlxbf-ptm-update-module-version.patch :
* 0301-UBUNTU-SAUCE-mlxbf-gige-Fix-kernel-panic-at-shutdown.patch :
* 0302-UBUNTU-SAUCE-mlxbf-bootctl-support-SMC-call-for-sett.patch :
* 0303-UBUNTU-SAUCE-Add-BF3-related-ACPI-config-and-Ring-de.patch :
* 0306-dt-bindings-trivial-devices-Add-infineon-xdpe1a2g7.patch :
* 0307-leds-mlxreg-Add-support-for-new-flavour-of-capabilit.patch :
* 0308-leds-mlxreg-Remove-code-for-amber-LED-colour.patch :
* 0308-platform_data-mlxreg-Add-capability-bit-and-mask-fie.patch :
* 0309-hwmon-mlxreg-fan-Add-support-for-new-flavour-of-capa.patch :
* 0310-hwmon-mlxreg-fan-Extend-number-of-supporetd-fans.patch :
* 0317-platform-mellanox-Introduce-support-for-switches-equ.patch :
* 0318-mellanox-Relocate-mlx-platform-driver.patch :
* 0319-UBUNTU-SAUCE-mlxbf-tmfifo-fix-potential-race.patch :
* 0320-UBUNTU-SAUCE-mlxbf-tmfifo-Drop-the-Rx-packet-if-no-m.patch :
* 0321-UBUNTU-SAUCE-mlxbf-tmfifo-Drop-jumbo-frames.patch :
* 0322-UBUNTU-SAUCE-mlxbf-tmfifo.c-Amend-previous-tmfifo-pa.patch :
* 0323-mlxbf_gige-add-set_link_ksettings-ethtool-callback.patch :
* 0324-mlxbf_gige-fix-white-space-in-mlxbf_gige_eth_ioctl.patch :
* 0325-UBUNTU-SAUCE-mlxbf-bootctl-Fix-kernel-panic-due-to-b.patch :
* 0326-platform-mellanox-mlxreg-hotplug-Add-support-for-new.patch :
* 0327-platform-mellanox-mlx-platform-Change-register-name.patch :
* 0328-platform-mellanox-mlx-platform-Add-support-for-new-X.patch :

* [Mellanox] Remove thermal zone related code and replace with new one

* Revert "Revert "[Mellanox] Align PSU temperature sysfs node name with hw-management change (sonic-net#16820)" (sonic-net#16956)"

This reverts commit c2edc6f.

---------

Signed-off-by: Vivek Reddy <[email protected]>
Co-authored-by: Junchao-Mellanox <[email protected]>
Co-authored-by: Junchao-Mellanox <[email protected]>

platform/mellanox/hw-management.mk

@@ -16,7 +16,7 @@
 #
 # Mellanox HW Management
 
-MLNX_HW_MANAGEMENT_VERSION = 7.0030.1011
+MLNX_HW_MANAGEMENT_VERSION = 7.0030.2008
 
 export MLNX_HW_MANAGEMENT_VERSION
 

platform/mellanox/hw-management/hwmgmt_nonup_patches

@@ -66,26 +66,8 @@
 0167-DS-lan743x-Add-support-for-fixed-phy.patch
 0168-TMP-mlxsw-minimal-Ignore-error-reading-SPAD-register.patch
 0171-platform-mellanox-mlxreg-lc-Fix-cleanup-on-failure-a.patch
-0172-DS-platform-mlx-platform-Add-SPI-path-for-rack-switc.patch
 0174-DS-mlxsw-core_linecards-Skip-devlink-and-provisionin.patch
 0181-Revert-Fix-out-of-bounds-memory-accesses-in-thermal.patch
-0182-platform-mellanox-Introduce-support-of-new-Nvidia-L1.patch
-0183-platform-mellanox-Split-initialization-procedure.patch
-0184-platform-mellanox-Split-logic-in-init-and-exit-flow.patch
-0185-platform-mellanox-Extend-all-systems-with-I2C-notifi.patch
-0187-platform_data-mlxreg-Add-field-with-mapped-resource-.patch
-0188-i2c-mux-Add-register-map-based-mux-driver.patch
-0189-i2c-mlxcpld-Allow-driver-to-run-on-ARM64-architectur.patch
-0190-i2c-mlxcpld-Modify-base-address-type.patch
-0191-i2c-mlxcpld-Allow-to-configure-base-address-of-regis.patch
-0192-i2c-mlxcpld-Add-support-for-extended-transaction-len.patch
-0193-platform-mellanox-mlx-platform-Add-mux-selection-reg.patch
-0194-platform-mellanox-mlx-platform-Move-bus-shift-assign.patch
-0195-platform-mellanox-Add-support-for-dynamic-I2C-channe.patch
-0196-platform-mellanox-Relocate-mlx-platform-driver.patch
-0197-platform-mellanox-Add-initial-support-for-PCIe-based.patch
-0198-platform-mellanox-Introduce-support-for-switches-bas.patch
-0199-platform-mellanox-mlx-platform-Add-reset-and-extend-.patch
 0200-dt-bindings-i2c-mellanox-i2c-mlxbf-convert-txt-to-YA.patch
 0203-i2c-mlxbf-remove-IRQF_ONESHOT.patch
 0206-i2c-mlxbf-add-multi-slave-functionality.patch
@@ -116,15 +98,11 @@
 0231-mlxbf_gige-remove-own-module-name-define-and-use-KBU.patch
 0232-UBUNTU-SAUCE-mlxbf_gige-add-ethtool-mlxbf_gige_set_r.patch
 0233-UBUNTU-SAUCE-Fix-OOB-handling-RX-packets-in-heavy-tr.patch
-0234-UBUNTU-SAUCE-mlxbf_gige-add-validation-of-ACPI-table.patch
-0235-UBUNTU-SAUCE-mlxbf_gige-set-driver-version-to-1.27.patch
 0236-UBUNTU-SAUCE-mlxbf_gige-clear-MDIO-gateway-lock-afte.patch
 0237-mlxbf_gige-compute-MDIO-period-based-on-i1clk.patch
 0238-net-mlxbf_gige-Fix-an-IS_ERR-vs-NULL-bug-in-mlxbf_gi.patch
 0239-UBUNTU-SAUCE-mlxbf_gige-add-MDIO-support-for-BlueFie.patch
 0240-UBUNTU-SAUCE-mlxbf_gige-support-10M-100M-1G-speeds-o.patch
-0241-UBUNTU-SAUCE-mlxbf_gige-add-BlueField-3-Serdes-confi.patch
-0242-UBUNTU-SAUCE-mlxbf_gige-add-BlueField-3-ethtool_ops.patch
 0243-UBUNTU-SAUCE-bluefield_edac-Add-SMC-support.patch
 0244-UBUNTU-SAUCE-bluefield_edac-Update-license-and-copyr.patch
 0245-gpio-mlxbf2-Convert-to-device-PM-ops.patch
@@ -150,20 +128,40 @@
 0266-UBUNTU-SAUCE-mlxbf-pmc-Bug-fix-for-BlueField-3-count.patch
 0267-UBUNTU-SAUCE-mmc-sdhci-of-dwcmshc-add-the-missing-de.patch
 0268-DS-mlxsw-core_linecards-Disable-firmware-bundling-ma.patch
-0269-platform-mellanox-Cosmetic-changes.patch
-0270-platform-mellanox-Fix-order-in-exit-flow.patch
-0271-platform-mellanox-Add-new-attributes.patch
-0272-platform-mellanox-Change-register-offset-addresses.patch
-0273-platform-mellanox-Add-field-upgrade-capability-regis.patch
-0274-platform-mellanox-Modify-reset-causes-description.patch
 0275-mlxsw-Use-u16-for-local_port-field-instead-of-u8.patch
 0276-mlxsw-minimal-Change-type-for-local-port.patch
 0277-mlxsw-i2c-Fix-chunk-size-setting-in-output-mailbox-b.patch
-0278-platform-mellanox-mlx-platform-Modify-graceful-shutd.patch
-0279-platform-mellanox-mlx-platform-Fix-signals-polarity-.patch
-0280-platform-mellanox-mlxreg-hotplug-Extend-condition-fo.patch
-0281-platform-mellanox-mlx-platform-Modify-health-and-pow.patch
-0282-platform-mellanox-mlx-platform-add-support-of-5th-CP.patch
-0283-mlxsw-core_hwmon-Align-modules-label-name-assignment.patch
-0284-platform-mellanox-mlx-platform-fix-CPLD4-PN-report.patch
+0285-UBUNTU-SAUCE-mlxbf-gige-Fix-intermittent-no-ip-issue.patch
+0286-pinctrl-Introduce-struct-pinfunction-and-PINCTRL_PIN.patch
+0287-pinctrl-mlxbf3-Add-pinctrl-driver-support.patch
+0288-UBUNTU-SAUCE-gpio-mmio-handle-ngpios-properly-in-bgp.patch
+0289-UBUNTU-SAUCE-gpio-mlxbf3-Add-gpio-driver-support.patch
+0291-mlxsw-core_hwmon-Align-modules-label-name-assignment.patch
+0292-mlxsw-i2c-Limit-single-transaction-buffer-size.patch
+0293-mlxsw-reg-Limit-MTBR-register-records-buffer-by-one-.patch
+0296-UBUNTU-SAUCE-mmc-sdhci-of-dwcmshc-Add-runtime-PM-ope.patch
+0298-UBUNTU-SAUCE-mlxbf-ptm-use-0444-instead-of-S_IRUGO.patch
+0299-UBUNTU-SAUCE-mlxbf-ptm-add-atx-debugfs-nodes.patch
+0300-UBUNTU-SAUCE-mlxbf-ptm-update-module-version.patch
+0301-UBUNTU-SAUCE-mlxbf-gige-Fix-kernel-panic-at-shutdown.patch
+0302-UBUNTU-SAUCE-mlxbf-bootctl-support-SMC-call-for-sett.patch
+0303-UBUNTU-SAUCE-Add-BF3-related-ACPI-config-and-Ring-de.patch
+0306-dt-bindings-trivial-devices-Add-infineon-xdpe1a2g7.patch
+0307-leds-mlxreg-Add-support-for-new-flavour-of-capabilit.patch
+0308-leds-mlxreg-Remove-code-for-amber-LED-colour.patch
+0308-platform_data-mlxreg-Add-capability-bit-and-mask-fie.patch
+0309-hwmon-mlxreg-fan-Add-support-for-new-flavour-of-capa.patch
+0310-hwmon-mlxreg-fan-Extend-number-of-supporetd-fans.patch
+0317-platform-mellanox-Introduce-support-for-switches-equ.patch
+0318-mellanox-Relocate-mlx-platform-driver.patch
+0319-UBUNTU-SAUCE-mlxbf-tmfifo-fix-potential-race.patch
+0320-UBUNTU-SAUCE-mlxbf-tmfifo-Drop-the-Rx-packet-if-no-m.patch
+0321-UBUNTU-SAUCE-mlxbf-tmfifo-Drop-jumbo-frames.patch
+0322-UBUNTU-SAUCE-mlxbf-tmfifo.c-Amend-previous-tmfifo-pa.patch
+0323-mlxbf_gige-add-set_link_ksettings-ethtool-callback.patch
+0324-mlxbf_gige-fix-white-space-in-mlxbf_gige_eth_ioctl.patch
+0325-UBUNTU-SAUCE-mlxbf-bootctl-Fix-kernel-panic-due-to-b.patch
+0326-platform-mellanox-mlxreg-hotplug-Add-support-for-new.patch
+0327-platform-mellanox-mlx-platform-Change-register-name.patch
+0328-platform-mellanox-mlx-platform-Add-support-for-new-X.patch
 9002-TMP-fix-for-fan-minimum-speed.patch

platform/mellanox/integration-scripts.mk

@@ -98,15 +98,16 @@ endif
 							--kernel_version $(KERNEL_VERSION) \
 							--hw_mgmt_ver ${MLNX_HW_MANAGEMENT_VERSION} $(LOG_SIMPLE)
 
-	$(BUILD_WORKDIR)/$($(MLNX_HW_MANAGEMENT)_SRC_PATH)/hw-mgmt/recipes-kernel/linux/deploy_kernel_patches.py \
-							--dst_accepted_folder $(PTCH_DIR) \
-							--dst_candidate_folder $(NON_UP_PTCH_DIR) \
-							--series_file $(PTCH_LIST) \
-							--config_file $(KCFG_LIST_ARM) \
-							--config_file_downstream $(KCFG_DOWN_LIST_ARM) \
-							--kernel_version $(KERNEL_VERSION) \
-							--arch arm64 \
-							--os_type sonic $(LOG_SIMPLE)
+	# Disable Writing KConfigs for arm64 platform
+	# $(BUILD_WORKDIR)/$($(MLNX_HW_MANAGEMENT)_SRC_PATH)/hw-mgmt/recipes-kernel/linux/deploy_kernel_patches.py \
+	# 						--dst_accepted_folder $(PTCH_DIR) \
+	# 						--dst_candidate_folder $(NON_UP_PTCH_DIR) \
+	# 						--series_file $(PTCH_LIST) \
+	# 						--config_file $(KCFG_LIST_ARM) \
+	# 						--config_file_downstream $(KCFG_DOWN_LIST_ARM) \
+	# 						--kernel_version $(KERNEL_VERSION) \
+	# 						--arch arm64 \
+	# 						--os_type sonic $(LOG_SIMPLE)
 
 	$(BUILD_WORKDIR)/$($(MLNX_HW_MANAGEMENT)_SRC_PATH)/hw-mgmt/recipes-kernel/linux/deploy_kernel_patches.py \
 							--dst_accepted_folder $(PTCH_DIR) \

platform/mellanox/mlnx-platform-api/sonic_platform/fan.py

@@ -216,7 +216,10 @@ def get_target_speed(self):
         """
         try:
             # Get PSU fan target speed according to current system cooling level
-            cooling_level = utils.read_int_from_file('/run/hw-management/thermal/cooling_cur_state', log_func=None)
+            pwm = utils.read_int_from_file('/run/hw-management/thermal/pwm1', log_func=None)
+            if pwm >= PWM_MAX:
+                pwm = PWM_MAX - 1
+            cooling_level = int(pwm / PWM_MAX * 10)
             return int(self.PSU_FAN_SPEED[cooling_level], 16)
         except Exception:
             return self.get_speed()

platform/mellanox/mlnx-platform-api/sonic_platform/psu.py

@@ -242,8 +242,8 @@ def __init__(self, psu_index):
 
         self.psu_power_max_capacity = os.path.join(PSU_PATH, "config/psu{}_power_capacity".format(self.index))
 
-        self.psu_temp = os.path.join(PSU_PATH, 'thermal/psu{}_temp'.format(self.index))
-        self.psu_temp_threshold = os.path.join(PSU_PATH, 'thermal/psu{}_temp_max'.format(self.index))
+        self.psu_temp = os.path.join(PSU_PATH, 'thermal/psu{}_temp1'.format(self.index))
+        self.psu_temp_threshold = os.path.join(PSU_PATH, 'thermal/psu{}_temp1_max'.format(self.index))
 
         self.psu_power_slope = os.path.join(PSU_PATH, self.PSU_POWER_SLOPE.format(self.index))
 

platform/mellanox/mlnx-platform-api/sonic_platform/thermal.py

@@ -65,16 +65,16 @@
     "psu thermals":
     {
         "name": "PSU-{} Temp",
-        "temperature": "psu{}_temp",
-        "high_threshold": "psu{}_temp_max",
+        "temperature": "psu{}_temp1",
+        "high_threshold": "psu{}_temp1_max",
         "type": "indexable"
     },
     "chassis thermals": [
         {
             "name": "ASIC",
             "temperature": "asic",
-            "high_threshold": "mlxsw/temp_trip_hot",
-            "high_critical_threshold": "mlxsw/temp_trip_crit"
+            "high_threshold": "asic_temp_emergency",
+            "high_critical_threshold": "asic_temp_trip_crit"
         },
         {
             "name": "Ambient Port Side Temp",
@@ -105,8 +105,8 @@
         {
             "name": "Gearbox {} Temp",
             "temperature": "gearbox{}_temp_input",
-            "high_threshold": "mlxsw-gearbox{}/temp_trip_hot",
-            "high_critical_threshold": "mlxsw-gearbox{}/temp_trip_crit",
+            "high_threshold": "gearbox{}_temp_emergency",
+            "high_critical_threshold": "gearbox{}_temp_trip_crit",
             "type": "indexable"
         },
         {
@@ -135,8 +135,8 @@
     'linecard thermals': {
         "name": "Gearbox {} Temp",
         "temperature": "gearbox{}_temp_input",
-        "high_threshold": "mlxsw-gearbox{}/temp_trip_hot",
-        "high_critical_threshold": "mlxsw-gearbox{}/temp_trip_crit",
+        "high_threshold": "gearbox{}_temp_emergency",
+        "high_critical_threshold": "gearbox{}_temp_trip_crit",
         "type": "indexable"
     }
 }
@@ -268,16 +268,6 @@ def _check_thermal_sysfs_existence(file_path):
 
 
 class Thermal(ThermalBase):
-    thermal_algorithm_status = False
-    # Expect cooling level, used for caching the cooling level value before commiting to hardware
-    expect_cooling_level = None
-    # Expect cooling state
-    expect_cooling_state = None
-    # Last committed cooling level
-    last_set_cooling_level = None
-    last_set_cooling_state = None
-    last_set_psu_cooling_level = None
-
     def __init__(self, name, temp_file, high_th_file, high_crit_th_file, position):
         """
         index should be a string for category ambient and int for other categories

platform/mellanox/mlnx-platform-api/tests/conftest.py

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2021-2022 NVIDIA CORPORATION & AFFILIATES.
+# Copyright (c) 2021-2023 NVIDIA CORPORATION & AFFILIATES.
 # Apache-2.0
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
@@ -42,14 +42,3 @@ def auto_recover_mock():
     utils.read_str_from_file = origin_read_str_from_file
     utils.write_file = origin_write_file
     utils.read_float_from_file = origin_read_float_from_file
-
-
-@pytest.fixture(scope='function', autouse=True)
-def auto_reset_cooling_level():
-    from sonic_platform.thermal import Thermal
-    yield
-    Thermal.expect_cooling_level = None
-    Thermal.expect_cooling_state = None
-    Thermal.last_set_cooling_level = None
-    Thermal.last_set_cooling_state = None
-    Thermal.last_set_psu_cooling_level = None

platform/mellanox/mlnx-platform-api/tests/test_fan_api.py

@@ -124,8 +124,8 @@ def test_psu_fan_basic(self, mock_path_exists, mock_powergood, mock_presence, mo
         assert fan.get_presence() is False
         mock_path_exists.return_value = True
         assert fan.get_presence() is True
-        mock_read_int.return_value = 7
-        assert fan.get_target_speed() == 70
+        mock_read_int.return_value = int(255 / 10 * 7)
+        assert fan.get_target_speed() == 60
         mock_read_int.return_value = FAN_DIR_VALUE_INTAKE
         assert fan.get_direction() == Fan.FAN_DIRECTION_INTAKE
         mock_read_int.return_value = FAN_DIR_VALUE_EXHAUST