Merge branch 'V.7.0040.1000_BR'

t

README.md

@@ -194,13 +194,13 @@ CONFIG_EDAC_AMD64=m
 CONFIG_HW_RANDOM_AMD=m
 CONFIG_AMD_XGBE=m
 CONFIG_AMD_XGBE_DCB=y
-CONFIG_AMD_XGBE_HAVE_ECC=y
 CONFIG_X86_AMD_PLATFORM_DEVICE=y
 CONFIG_CPU_SUP_AMD=y
 CONFIG_X86_MCE_AMD=y
 CONFIG_USB_NET_DRIVERS=m
 CONFIG_USB_USBNET=m
 CONFIG_USB_NET_CDCETHER=m
+CONFIG_HOTPLUG_PCI_PCIE=n
 
 For arm64 architecture:
 CONFIG_NET_VENDOR_MELLANOX=y
@@ -289,6 +289,7 @@ CONFIG_SENSORS_UCD9000=m
 CONFIG_SENSORS_UCD9200=m
 CONFIG_FUSE_FS=m
 CONFIG_SENSORS_ARM_SCMI=m
+CONFIG_HOTPLUG_PCI_PCIE=n
 
 ```
 **Note:**
@@ -325,6 +326,8 @@ sudo apt-get install devscripts build-essential lintian
 - Go into the thermal-control base folder and build the Debian package.
 - Run: `debuild -us -uc -b`
 - To build for ARM64 architecture, run `debuild -us -uc -b -aarm64`
+- To build without lm_sensor dependecy (for Sonic-based OS) run 'debuild --set-envvar=LM_DEPENDS=0 -us -uc -b'
+or 'export LM_DEPENDS=0 && dpkg-buildpackage -us -uc -b'
 - Find in upper folder the builded `.deb` package (for example `hw-management_1.mlnx.18.12.2018_amd64.deb`).
 
 **For converting .deb package to .rpm package:**

debian/Release.txt

@@ -1,3 +1,46 @@
+================================================================================
+- V.7.0040.1000
+- Sun , 30 June 2024 
+--------------------------------------------------------------------------------
+
+- New features 
+    o  Add support for QM3400 Blackmamba - ES level quality
+    o  Add support for SN4280 SmartSwitch Bobcat - ES level quality
+    o  Add support for N5110_LD Juliet Scaleout PO + TTM - ES level quality
+    o  Add support in VPD parser for System VPD vendor specific SSD SED PSID block
+
+- Bug fixes
+	#3649551	SN4700 : [Independent Module] | on r-leopard-41 with IM enabled, there was a thermal overload. 
+	#3878328	SN4700 : Switch rebooted with "Thermal Overload" because ASIC thermal is not available 
+	#3885405	TC: [Thermal Algorithm] | Blacklist is malfunctions
+	#3883147	TC: [Thermal Algorithm] | Counts errors even it was paused by black list
+	#3879220	SN3420 : Thermal control: increase PWM minimum speed (20%->25%) to work around fan state issue reported by smond
+	#3895891	SPC1: [systemctl is-system-running] | SPC1 stuck in starting state after config reload - System was not started – lmsensor dependency issue
+	#3900159	QM3400: [Kernel 6.1] thermal/module#_temp_crit: Input/output error 
+	#3900138	QM3400: [Kernel 6.1] Can't get value of subfeature temp input for front panel 
+	#3882472	QM3000 | QM3400:  Mismatch system names in TC config (qm3400 instead q3200)
+	#3948113	Switch is freezing after generating hw-mgmt dump few times in row 
+	#3852236	ARM: Kernel oops symptoms after boot: Unable to handle kernel paging address xxx when BSP Drivers are used
+	NA		msn5400 | msn5600 | sn4280 :TC: fix asic sensor mask in sensor_parameters
+	NA		vpd parser: Sanity check is done only for 'MLNX' fru types
+	NA		Multi ASIC system: kernel config CONFIG_HOTPLUG_PCI_PCIE (kernel 6.1) is required to be disabled for the sw_reset on multi asic systems 
+	NA		TC: missing support of correct PWM calculation for systems with amb_{X} sensor count  != 2 
+	NA		MSN4700 | MQM9520 :Some PSU1 labels are incorrectly marked as PSU2.
+	NA		QM3000 | QM3400 :voltmon1 and voltmon4 symlinks pointing to curr2 sensors Instead of curr3 sensors.
+	NA		QM3000 : ASIC PCIE mapping was wrong
+	NA		Deployment tool : Missing support for Kconfig per Kernel major version
+	NA		vpd-parser: In case onie "Base MAC Address" filed ends with zero byte - vpd-parser cut last byte in output.
+
+    o  For detailed patch list: Please view:  https://github.com/Mellanox/hw-mgmt/blob/V.7.0040.1000_BR/recipes-kernel/linux/Patch_Status_Table.txt
+
+ - Known issues and limitations:
+
+    o Systems like sn2700 which contain delta 460 PSU may have "Error getting sensor data: dps460/#25: Can't read"
+      which is a temporary inaccessibility of certain alarm attributes read from the PSU.
+    o Systems may show a message of WARNING kernel: … supply vcc not found, using dummy regulator" 
+    o Systems SN2010, SN2100, SN2410, SN2700 and SN2740 (and their "-B" variants) require the following flag in kernel cmdline:
+      "acpi_enforce_resources=lax acpi=noirq".
+
 ================================================================================
 - V.7.0030.4000
 - Mon , 1 Apr 2024 

debian/changelog

@@ -1,4 +1,4 @@
-hw-management (1.mlnx.7.0030.4000) unstable; urgency=low
+hw-management (1.mlnx.7.0040.1000) unstable; urgency=low
   [ MLNX ] 
 
- -- Yehuda Yehudai <yyehudai@nvidia.com> Fri, 05 Apr 2024 11:10:00 +0300
+ -- Yehuda Yehudai <yyehudai@nvidia.com> Sat, 29 Jun 2024 17:10:00 +0300

debian/control

@@ -8,7 +8,7 @@ Homepage: http://www.nvidia.com
 
 Package:hw-management
 Architecture: any
-Depends: ${misc:Depends}, ${shlibs:Depends}, lsb-base (>= 3.0-6), python2.7 | python3, xxd, lm-sensors, libiio-utils, dmidecode, i2c-tools
+Depends: ${misc:Depends}, ${shlibs:Depends}, ${dist:Depends}, lsb-base (>= 3.0-6), python2.7 | python3, xxd, libiio-utils, dmidecode, i2c-tools
 Description: Thermal control and chassis management for Nvidia systems
  This package supports Nvidia switches family for chassis
  management and thermal control.

debian/hw-management.hw-management-sync.service

@@ -0,0 +1,19 @@
+[Unit]
+Description=Hw-management events sync service of Nvidia systems
+After=hw-management.service
+Requires=hw-management.service
+PartOf=hw-management.service
+
+StartLimitIntervalSec=1200
+StartLimitBurst=5
+
+[Service]
+ExecStart=/bin/sh -c "/usr/bin/hw_management_sync.py"
+ExecStop=/bin/kill $MAINPID
+TimeoutStopSec=1
+
+Restart=on-failure
+RestartSec=10s
+
+[Install]
+WantedBy=multi-user.target

debian/rules

@@ -4,9 +4,20 @@ pname:=hw-management
 
 pwd=$(shell pwd)
 
+#debuild -sa -us -uc -eLM_DEPENDS=1
+
+ifeq ($(LM_DEPENDS),0)
+	DEPENDS = -Vdist:Depends=""
+else
+	DEPENDS = -Vdist:Depends="lm-sensors"
+endif
+
 %:
 	dh $@
 
+override_dh_gencontrol:
+	dh_gencontrol -- $(DEPENDS)
+
 override_dh_auto_configure:
 
 override_dh_auto_build:
@@ -23,6 +34,7 @@ override_dh_auto_install:
 ifeq ($(DEB_HOST_ARCH),arm64)
 	mv debian/$(pname)/usr/bin/iorw.sh debian/$(pname)/usr/bin/iorw
 	cp usr/etc/modules-load.d/05-hw-management-modules-arm64.conf debian/$(pname)/etc/modules-load.d/05-hw-management-modules.conf
+	cp usr/etc/modprobe.d/hw-management-arm64.conf debian/$(pname)/etc/modprobe.d/hw-management.conf
 	dh_installdirs -p$(pname) lib/systemd/system-shutdown
 	cp usr/usr/bin/hw-management-kexec-notifier.sh debian/$(pname)/lib/systemd/system-shutdown
 endif
@@ -38,14 +50,17 @@ endif
 override_dh_installinit:
 	dh_installinit --name=hw-management
 	dh_installinit --name=hw-management-tc
+	dh_installinit --name=hw-management-sync
 
 override_dh_systemd_enable:
 	dh_systemd_enable --name=hw-management
 	dh_systemd_enable --name=hw-management-tc
+	dh_systemd_enable --name=hw-management-sync
 
 override_dh_systemd_start:
 	dh_systemd_start --name=hw-management
 	dh_systemd_start --name=hw-management-tc
+	dh_systemd_start --name=hw-management-sync
 
 override_dh_strip_nondeterminism: