-
Notifications
You must be signed in to change notification settings - Fork 1.4k
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
[Mellanox] Update HW-MGMT package to new version V.7.0030.1011 (#16239)
- Why I did it 1. Update Mellanox HW-MGMT package to newer version V.7.0030.1011 2. Replace the SONiC PMON Thermal control algorithm with the one inside the HW-MGMT package on all Nvidia platforms 3. Support Spectrum-4 systems - How I did it 1. Update the HW-MGMT package version number and submodule pointer 2. Remove the thermal control algorithm implementation from Mellanox platform API 3. Revise the patch to HW-MGMT package which will disable HW-MGMT from running on SIMX 4. Update the downstream kernel patch list Signed-off-by: Kebo Liu <kebol@nvidia.com>
- Loading branch information
1 parent
60f5610
commit 27f15d4
Showing
195 changed files
with
36,511 additions
and
3,133 deletions.
There are no files selected for viewing
76 changes: 4 additions & 72 deletions
76
device/mellanox/x86_64-mlnx_msn2700-r0/thermal_policy.json
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -1,80 +1,12 @@ | ||
| { | ||
| { | ||
| "thermal_control_algorithm": { | ||
| "run_at_boot_up": "true", | ||
| "fan_speed_when_suspend": "60" | ||
| }, | ||
| "info_types": [ | ||
| { | ||
| "type": "fan_info" | ||
| }, | ||
| { | ||
| "type": "psu_info" | ||
| }, | ||
| { | ||
| "type": "chassis_info" | ||
| } | ||
|
|
||
| ], | ||
| "policies": [ | ||
| { | ||
| "name": "any fan absence", | ||
| "conditions": [ | ||
| { | ||
| "type": "fan.any.absence" | ||
| } | ||
| ], | ||
| "actions": [ | ||
| { | ||
| "type": "fan.all.set_speed", | ||
| "speed": "100" | ||
| } | ||
| ] | ||
| }, | ||
| { | ||
| "name": "any psu absence", | ||
| "conditions": [ | ||
| { | ||
| "type": "psu.any.absence" | ||
| } | ||
| ], | ||
| "actions": [ | ||
| { | ||
| "type": "fan.all.set_speed", | ||
| "speed": "100" | ||
| } | ||
| ] | ||
| }, | ||
| { | ||
| "name": "any fan broken", | ||
| "conditions": [ | ||
| { | ||
| "type": "fan.any.fault" | ||
| } | ||
| ], | ||
| "actions": [ | ||
| { | ||
| "type": "fan.all.set_speed", | ||
| "speed": "100" | ||
| } | ||
| ] | ||
| }, | ||
| { | ||
| "name": "all fan and psu presence", | ||
| "conditions": [ | ||
| { | ||
| "type": "fan.all.presence" | ||
| }, | ||
| { | ||
| "type": "psu.all.presence" | ||
| }, | ||
| { | ||
| "type": "fan.all.good" | ||
| } | ||
| ], | ||
| "actions": [ | ||
| { | ||
| "type": "thermal.recover" | ||
| } | ||
| ] | ||
| } | ||
|
|
||
| ] | ||
| } | ||
| } |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
144 changes: 89 additions & 55 deletions
144
platform/mellanox/hw-management/0002-Disable-hw-mgmt-on-SimX-platforms.patch
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -1,69 +1,103 @@ | ||
| 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 2/4] Disable hw-mgmt on SimX platforms | ||
| From eb3a76d7fbd0cbf2c370ecadd912960b094403d6 Mon Sep 17 00:00:00 2001 | ||
| From: Junchao-Mellanox <junchao@nvidia.com> | ||
| Date: Wed, 23 Aug 2023 14:33:44 +0800 | ||
| Subject: [PATCH] [PATCH 2/4] Disable hw-mgmt on SimX platforms | ||
|
|
||
| --- | ||
| usr/usr/bin/hw-management-ready.sh | 11 +++++++---- | ||
| usr/usr/bin/hw-management.sh | 9 +++++++++ | ||
| 2 files changed, 16 insertions(+), 4 deletions(-) | ||
| usr/usr/bin/hw-management-ready.sh | 3 --- | ||
| usr/usr/bin/hw-management.sh | 21 +++++++++------------ | ||
| 2 files changed, 9 insertions(+), 15 deletions(-) | ||
|
|
||
| diff --git a/usr/usr/bin/hw-management-ready.sh b/usr/usr/bin/hw-management-ready.sh | ||
| index 88672a8..7558c68 100755 | ||
| index 840bb0b..2f8547f 100755 | ||
| --- a/usr/usr/bin/hw-management-ready.sh | ||
| +++ b/usr/usr/bin/hw-management-ready.sh | ||
| @@ -51,17 +51,20 @@ if [ -d /var/run/hw-management ]; then | ||
| rm -fr /var/run/hw-management | ||
| fi | ||
|
|
||
| -case $board_type in | ||
| -VMOD0014) | ||
| +if [ -z "$(lspci -vvv | grep SimX)" ]; then | ||
| + case $board_type in | ||
| + VMOD0014) | ||
| if [ ! -d /sys/devices/pci0000:00/0000:00:1f.0/NVSN2201:00/mlxreg-hotplug/hwmon ]; then | ||
| timeout 180 bash -c 'until [ -d /sys/devices/pci0000:00/0000:00:1f.0/NVSN2201:00/mlxreg-hotplug/hwmon ]; do sleep 0.2; done' | ||
| fi | ||
| ;; | ||
| -*) | ||
| + *) | ||
| if [ ! -d /sys/devices/platform/mlxplat/mlxreg-hotplug/hwmon ]; then | ||
| timeout 180 bash -c 'until [ -d /sys/devices/platform/mlxplat/mlxreg-hotplug/hwmon ]; do sleep 0.2; done' | ||
| fi | ||
| ;; | ||
| -esac | ||
| + esac | ||
| +fi | ||
| + | ||
| echo "Start Chassis HW management service." | ||
| logger -t hw-management -p daemon.notice "Start Chassis HW management service." | ||
| @@ -56,9 +56,6 @@ fi | ||
| # environment, TC need to be stopped. | ||
| if [ -n "$(lspci -vvv | grep SimX)" ]; then | ||
| case $product_sku in | ||
| - HI130|HI122) | ||
| - # Let the TC continue to run | ||
| - ;; | ||
| *) | ||
| if systemctl is-enabled --quiet hw-management-tc; then | ||
| echo "Stopping and disabling hw-management-tc on SimX" | ||
| diff --git a/usr/usr/bin/hw-management.sh b/usr/usr/bin/hw-management.sh | ||
| index 1ee05b5..50d922b 100755 | ||
| index d3914d1..a60dba9 100755 | ||
| --- a/usr/usr/bin/hw-management.sh | ||
| +++ b/usr/usr/bin/hw-management.sh | ||
| @@ -2310,6 +2310,13 @@ do_chip_down() | ||
| /usr/bin/hw-management-thermal-events.sh change hotplug_asic down %S %p | ||
| } | ||
| @@ -545,7 +545,7 @@ function restore_i2c_bus_frequency_default() | ||
| function find_regio_sysfs_path_helper() | ||
| { | ||
| # Find hwmon{n} sysfs path for regio device | ||
| - case $board_type in | ||
| + case $board_type in | ||
| VMOD0014) | ||
| for path in /sys/devices/pci0000:00/*/NVSN2201:*/mlxreg-io/hwmon/hwmon*; do | ||
| if [ -d "$path" ]; then | ||
| @@ -732,10 +732,10 @@ set_jtag_gpio() | ||
| gpio_tdi=$((gpiobase+jtag_tdi)) | ||
| echo $gpio_tdi > /sys/class/gpio/"$export_unexport" | ||
|
|
||
| +check_simx() | ||
| +{ | ||
| + if [ -n "$(lspci -vvv | grep SimX)" ]; then | ||
| + exit 0 | ||
| - # In SN2201 system. | ||
| + # In SN2201 system. | ||
| # GPIO0 for CPU request to reset the Main Board I2C Mux. | ||
| - # GPIO1 for CPU control the CPU Board MUX when doing the ISP programming. | ||
| - # GPIO13 for CPU request Main Board JTAG control signal. | ||
| + # GPIO1 for CPU control the CPU Board MUX when doing the ISP programming. | ||
| + # GPIO13 for CPU request Main Board JTAG control signal. | ||
| if [ "$board_type" == "VMOD0014" ]; then | ||
| mux_reset=27 | ||
| jtag_mux_en=33 | ||
| @@ -1294,7 +1294,7 @@ connect_msn4700_msn4600_A1() | ||
| # msn4600C with removed A2D | ||
| connect_table+=(${msn4600C_A1_base_connect_table[@]}) | ||
| else | ||
| - # msn4700/msn4600 respin | ||
| + # msn4700/msn4600 respin | ||
| connect_table+=(${msn4700_msn4600_A1_base_connect_table[@]}) | ||
| fi | ||
| add_cpu_board_to_connection_table | ||
| @@ -2144,7 +2144,7 @@ create_symbolic_links() | ||
| fi | ||
| if [ ! -d $thermal_path ]; then | ||
| mkdir $thermal_path | ||
| - fi | ||
| + fi | ||
| +} | ||
| + | ||
| __usage=" | ||
| Usage: $(basename "$0") [Options] | ||
|
|
||
| @@ -2335,6 +2342,8 @@ Options: | ||
| force-reload Performs hw-management 'stop' and the 'start. | ||
| " | ||
| if [ ! -d $config_path ]; then | ||
| mkdir $config_path | ||
| fi | ||
| @@ -2341,7 +2341,7 @@ do_start() | ||
| check_system | ||
| set_asic_pci_id | ||
|
|
||
| +check_simx | ||
| + | ||
| case $ACTION in | ||
| start) | ||
| if [ -d /var/run/hw-management ]; then | ||
| - asic_control=$(< $config_path/asic_control) | ||
| + asic_control=$(< $config_path/asic_control) | ||
| if [[ $asic_control -ne 0 ]]; then | ||
| get_asic_bus | ||
| get_asic2_bus | ||
| @@ -2379,9 +2379,9 @@ do_start() | ||
| else | ||
| ln -sf /etc/sensors3.conf $config_path/lm_sensors_config | ||
| fi | ||
| - if [ -v "lm_sensors_labels" ] && [ -f $lm_sensors_labels ]; then | ||
| + if [ -v "lm_sensors_labels" ] && [ -f $lm_sensors_labels ]; then | ||
| ln -sf $lm_sensors_labels $config_path/lm_sensors_labels | ||
| - fi | ||
| + fi | ||
| if [ -v "thermal_control_config" ] && [ -f $thermal_control_config ]; then | ||
| ln -sf $thermal_control_config $config_path/tc_config.json | ||
| else | ||
| @@ -2528,9 +2528,6 @@ do_chip_up_down() | ||
| check_simx() | ||
| { | ||
| case $sku in | ||
| - HI130|HI122) | ||
| - # Let the initialization go through | ||
| - ;; | ||
| *) | ||
| if [ -n "$(lspci -vvv | grep SimX)" ]; then | ||
| exit 0 | ||
| -- | ||
| 2.20.1 | ||
| 1.9.1 | ||
|
|
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Oops, something went wrong.