[Mellanox] Advance hw-mgmt to v.7.0020.4104 (sonic-net#13372)

stephenxs · mssonicbld · commit 087176e839c9 · 2023-02-17T13:51:32.000Z
- Why I did it Advance hw-mgmt service to V.7.0020.4100 Add missing thermal sensors that are supported by hw-mgmt package Delay system health service before hw-mgmt has started on Mellanox platform in order to avoid reading some sensors before ready. Depends on sonic-net/sonic-linux-kernel#305 - How I did it 1. Update hw mgmt version 2. Add missing sensors 3. Delay service - How to verify it Regression test. Signed-off-by: Stephen Sun <stephens@nvidia.com>
diff --git a/device/mellanox/x86_64-mlnx_msn2010-r0/platform.json b/device/mellanox/x86_64-mlnx_msn2010-r0/platform.json
@@ -67,6 +67,9 @@
             },
             {
                 "name": "CPU Core 3 Temp"
+            },
+            {
+                "name": "SODIMM 1 Temp"
             }
         ],
         "sfps": [
diff --git a/device/mellanox/x86_64-mlnx_msn2100-r0/platform.json b/device/mellanox/x86_64-mlnx_msn2100-r0/platform.json
@@ -67,6 +67,9 @@
             },
             {
                 "name": "CPU Core 3 Temp"
+            },
+            {
+                "name": "SODIMM 1 Temp"
             }
         ],
         "sfps": [
diff --git a/device/mellanox/x86_64-mlnx_msn2410-r0/platform.json b/device/mellanox/x86_64-mlnx_msn2410-r0/platform.json
@@ -114,6 +114,9 @@
             },
             {
                 "name": "CPU Pack Temp"
+            },
+            {
+                "name": "SODIMM 1 Temp"
             }
         ],
         "sfps": [
diff --git a/device/mellanox/x86_64-mlnx_msn2700-r0/platform.json b/device/mellanox/x86_64-mlnx_msn2700-r0/platform.json
@@ -114,6 +114,9 @@
             },
             {
                 "name": "CPU Pack Temp"
+            },
+            {
+                "name": "SODIMM 1 Temp"
             }
         ],
         "sfps": [
diff --git a/device/mellanox/x86_64-nvidia_sn2201-r0/platform.json b/device/mellanox/x86_64-nvidia_sn2201-r0/platform.json
@@ -101,6 +101,9 @@
             },
             {
                 "name": "ASIC"
+            },
+            {
+                "name": "SODIMM 1 Temp"
             }
         ],
         "sfps": [{
diff --git a/platform/mellanox/hw-management.mk b/platform/mellanox/hw-management.mk
@@ -16,7 +16,7 @@
 #
 # Mellanox HW Management
 
-MLNX_HW_MANAGEMENT_VERSION = 7.0020.3006
+MLNX_HW_MANAGEMENT_VERSION = 7.0020.4104
 
 export MLNX_HW_MANAGEMENT_VERSION
 
diff --git a/platform/mellanox/hw-management/0001-Make-SONiC-determine-reboot-cause-service-start-afte.patch b/platform/mellanox/hw-management/0001-Make-SONiC-determine-reboot-cause-service-start-afte.patch
@@ -1,16 +1,16 @@
-From 1a1011b6da491d35001df5a7204d4eecb2769767 Mon Sep 17 00:00:00 2001
+From 489764eb124e03087eb408dec27d769fa4f98459 Mon Sep 17 00:00:00 2001
 From: keboliu <kebol@mellanox.com>
 Date: Fri, 15 Jan 2021 14:41:16 +0800
-Subject: [PATCH] Make SONiC determine-reboot-cause service start after hw-mgmt
- service
+Subject: [PATCH 1/4] Make SONiC determine-reboot-cause service start after
+ hw-mgmt service
 
 Signed-off-by: Kebo Liu <kebol@nvidia.com>
 ---
  debian/hw-management.hw-management.service | 1 +
  1 file changed, 1 insertion(+)
 
 diff --git a/debian/hw-management.hw-management.service b/debian/hw-management.hw-management.service
-index 39a2a54..2104b87 100755
+index 8bdcaef..1c25ffb 100755
 --- a/debian/hw-management.hw-management.service
 +++ b/debian/hw-management.hw-management.service
 @@ -1,6 +1,7 @@
@@ -22,5 +22,5 @@ index 39a2a54..2104b87 100755
  [Service]
  Type=oneshot
 -- 
-1.9.1
+2.20.1
 
diff --git a/platform/mellanox/hw-management/0002-Disable-hw-mgmt-on-SimX-platforms.patch b/platform/mellanox/hw-management/0002-Disable-hw-mgmt-on-SimX-platforms.patch
@@ -1,59 +1,47 @@
-From 79dadd5b0d2f5e860b525c12d4d3843607b03a9f Mon Sep 17 00:00:00 2001
+From 422b64397f2f33b394d037820f0ceb4c09e3a725 Mon Sep 17 00:00:00 2001
 From: Alexander Allen <arallen@nvidia.com>
 Date: Fri, 21 Jan 2022 16:47:19 +0000
-Subject: [PATCH] Disable hw-mgmt on SimX platforms
+Subject: [PATCH 2/4] Disable hw-mgmt on SimX platforms
 
 ---
- usr/usr/bin/hw-management-ready.sh | 31 ++++++++++++++++--------------
+ usr/usr/bin/hw-management-ready.sh | 11 +++++++----
  usr/usr/bin/hw-management.sh       |  9 +++++++++
- 2 files changed, 26 insertions(+), 14 deletions(-)
+ 2 files changed, 16 insertions(+), 4 deletions(-)
 
 diff --git a/usr/usr/bin/hw-management-ready.sh b/usr/usr/bin/hw-management-ready.sh
-index 5a9698c..364f906 100755
+index 88672a8..7558c68 100755
 --- a/usr/usr/bin/hw-management-ready.sh
 +++ b/usr/usr/bin/hw-management-ready.sh
-@@ -51,19 +51,22 @@ if [ -d /var/run/hw-management ]; then
+@@ -51,17 +51,20 @@ if [ -d /var/run/hw-management ]; then
  	rm -fr /var/run/hw-management
  fi
  
 -case $board_type in
 -VMOD0014)
--	while [ ! -d /sys/devices/pci0000:00/0000:00:1f.0/NVSN2201:00/mlxreg-hotplug/hwmon ]
--	do
--		sleep 1
--	done
--	;;
++if [ -z "$(lspci -vvv | grep SimX)" ]; then
++    case $board_type in
++    VMOD0014)
+ 	if [ ! -d /sys/devices/pci0000:00/0000:00:1f.0/NVSN2201:00/mlxreg-hotplug/hwmon ]; then
+ 		timeout 180 bash -c 'until [ -d /sys/devices/pci0000:00/0000:00:1f.0/NVSN2201:00/mlxreg-hotplug/hwmon ]; do sleep 0.2; done'
+ 	fi
+ 	;;
 -*)
--	while [ ! -d /sys/devices/platform/mlxplat/mlxreg-hotplug/hwmon ]
--	do
--		sleep 1
--	done
--	;;
++    *)
+ 	if [ ! -d /sys/devices/platform/mlxplat/mlxreg-hotplug/hwmon ]; then
+ 		timeout 180 bash -c 'until [ -d /sys/devices/platform/mlxplat/mlxreg-hotplug/hwmon ]; do sleep 0.2; done'
+ 	fi
+ 	;;
 -esac
-+if [ -z "$(lspci -vvv | grep SimX)" ]; then
-+	case $board_type in
-+	VMOD0014)
-+		while [ ! -d /sys/devices/pci0000:00/0000:00:1f.0/NVSN2201:00/mlxreg-hotplug/hwmon ]
-+		do
-+			sleep 1
-+		done
-+		;;
-+	*)
-+		while [ ! -d /sys/devices/platform/mlxplat/mlxreg-hotplug/hwmon ]
-+		do
-+			sleep 1
-+		done
-+		;;
-+	esac
++    esac
 +fi
 +
  echo "Start Chassis HW management service."
  logger -t hw-management -p daemon.notice "Start Chassis HW management service."
 diff --git a/usr/usr/bin/hw-management.sh b/usr/usr/bin/hw-management.sh
-index ebfabb0..c0c038e 100755
+index 1ee05b5..50d922b 100755
 --- a/usr/usr/bin/hw-management.sh
 +++ b/usr/usr/bin/hw-management.sh
-@@ -1495,6 +1495,13 @@ do_chip_down()
+@@ -2310,6 +2310,13 @@ do_chip_down()
  	/usr/bin/hw-management-thermal-events.sh change hotplug_asic down %S %p
  }
  
@@ -67,7 +55,7 @@ index ebfabb0..c0c038e 100755
  __usage="
  Usage: $(basename "$0") [Options]
  
-@@ -1520,6 +1527,8 @@ Options:
+@@ -2335,6 +2342,8 @@ Options:
  	force-reload	Performs hw-management 'stop' and the 'start.
  "
  
@@ -77,5 +65,5 @@ index ebfabb0..c0c038e 100755
  	start)
  		if [ -d /var/run/hw-management ]; then
 -- 
-2.17.1
+2.20.1
 
diff --git a/platform/mellanox/hw-management/0003-Remove-unused-non-upstream-kernel-modules-from-load.patch b/platform/mellanox/hw-management/0003-Remove-unused-non-upstream-kernel-modules-from-load.patch
@@ -1,14 +1,14 @@
-From 14b06a12802fc0e15116a64f419d002d0d21d695 Mon Sep 17 00:00:00 2001
+From 439639e939f896f9aee42a4dbd5216feb728220c Mon Sep 17 00:00:00 2001
 From: Alexander Allen <arallen@nvidia.com>
 Date: Thu, 17 Feb 2022 04:19:50 +0000
-Subject: [PATCH] Remove unused non-upstream kernel modules from load
+Subject: [PATCH 3/4] Remove unused non-upstream kernel modules from load
 
 ---
  usr/etc/modules-load.d/05-hw-management-modules.conf | 2 --
  1 file changed, 2 deletions(-)
 
 diff --git a/usr/etc/modules-load.d/05-hw-management-modules.conf b/usr/etc/modules-load.d/05-hw-management-modules.conf
-index 39f621e..c0980bc 100644
+index cfcfaa4..dd3b5ca 100644
 --- a/usr/etc/modules-load.d/05-hw-management-modules.conf
 +++ b/usr/etc/modules-load.d/05-hw-management-modules.conf
 @@ -15,8 +15,6 @@ xdpe12284
@@ -21,5 +21,5 @@ index 39f621e..c0980bc 100644
  gpio-pca953x
  pmbus
 -- 
-2.17.1
+2.20.1
 
diff --git a/platform/mellanox/hw-management/0004-Make-system-health-service-starts-after-hw-managemen.patch b/platform/mellanox/hw-management/0004-Make-system-health-service-starts-after-hw-managemen.patch
@@ -0,0 +1,29 @@
+From 038bce6bf808ec9d082e96fec4184e060b3a85a9 Mon Sep 17 00:00:00 2001
+From: Stephen Sun <stephens@nvidia.com>
+Date: Mon, 28 Nov 2022 03:55:14 +0000
+Subject: [PATCH 4/4] Make system-health service starts after hw-management to
+ avoid failures
+
+On SN2410, it can fail to read the file led_status_capability if it starts from ONIE
+
+Signed-off-by: Stephen Sun <stephens@nvidia.com>
+---
+ debian/hw-management.hw-management.service | 2 +-
+ 1 file changed, 1 insertion(+), 1 deletion(-)
+
+diff --git a/debian/hw-management.hw-management.service b/debian/hw-management.hw-management.service
+index 1c25ffb..0fbd877 100755
+--- a/debian/hw-management.hw-management.service
++++ b/debian/hw-management.hw-management.service
+@@ -1,7 +1,7 @@
+ [Unit]
+ Description=Chassis HW management service of Mellanox systems
+ Documentation=man:hw-management.service(8)
+-Before=determine-reboot-cause.service
++Before=determine-reboot-cause.service system-health.service
+ 
+ [Service]
+ Type=oneshot
+-- 
+2.20.1
+
diff --git a/platform/mellanox/hw-management/hw-mgmt b/platform/mellanox/hw-management/hw-mgmt
@@ -1 +1 @@
-Subproject commit 137109ed15be147a99b59ceb9dfa1799688dfb71
+Subproject commit 9c3f6b2d6ac4be2eda936522f369ff8920deb4e2

Original file line number	Diff line number	Diff line change
`@@ -67,6 +67,9 @@`
`67`	`67`	`},`
`68`	`68`	`{`
`69`	`69`	`"name": "CPU Core 3 Temp"`
	`70`	`+ },`
	`71`	`+ {`
	`72`	`+ "name": "SODIMM 1 Temp"`
`70`	`73`	`}`
`71`	`74`	`],`
`72`	`75`	`"sfps": [`
Original file line number	Diff line number	Diff line change
`@@ -114,6 +114,9 @@`
`114`	`114`	`},`
`115`	`115`	`{`
`116`	`116`	`"name": "CPU Pack Temp"`
	`117`	`+ },`
	`118`	`+ {`
	`119`	`+ "name": "SODIMM 1 Temp"`
`117`	`120`	`}`
`118`	`121`	`],`
`119`	`122`	`"sfps": [`
Original file line number	Diff line number	Diff line change
`@@ -101,6 +101,9 @@`
`101`	`101`	`},`
`102`	`102`	`{`
`103`	`103`	`"name": "ASIC"`
	`104`	`+ },`
	`105`	`+ {`
	`106`	`+ "name": "SODIMM 1 Temp"`
`104`	`107`	`}`
`105`	`108`	`],`
`106`	`109`	`"sfps": [{`
Original file line number	Diff line number	Diff line change
`@@ -16,7 +16,7 @@`
`16`	`16`	`#`
`17`	`17`	`# Mellanox HW Management`
`18`	`18`
`19`		`-MLNX_HW_MANAGEMENT_VERSION = 7.0020.3006`
	`19`	`+MLNX_HW_MANAGEMENT_VERSION = 7.0020.4104`
`20`	`20`
`21`	`21`	`export MLNX_HW_MANAGEMENT_VERSION`
`22`	`22`