aboutsummaryrefslogtreecommitdiffstatshomepage
path: root/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
diff options
context:
space:
mode:
authorIdo Schimmel <idosch@nvidia.com>2023-03-17 16:32:59 +0100
committerDavid S. Miller <davem@davemloft.net>2023-03-19 15:23:11 +0000
commit6d206b1ea9f48433a96edec7028586db1d947911 (patch)
tree1e5ed6da1a3562efa16fcf86461198ebfac573e2 /drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
parentnet: sfp: fix state loss when updating state_hw_mask (diff)
downloadwireguard-linux-6d206b1ea9f48433a96edec7028586db1d947911.tar.xz
wireguard-linux-6d206b1ea9f48433a96edec7028586db1d947911.zip
mlxsw: core_thermal: Fix fan speed in maximum cooling state
The cooling levels array is supposed to prevent the system fans from being configured below a 20% duty cycle as otherwise some of them get stuck at 0 RPM. Due to an off-by-one error, the last element in the array was not initialized, causing it to be set to zero, which in turn lead to fans being configured with a 0% duty cycle in maximum cooling state. Since commit 332fdf951df8 ("mlxsw: thermal: Fix out-of-bounds memory accesses") the contents of the array are static. Therefore, instead of fixing the initialization of the array, simply remove it and adjust thermal_cooling_device_ops::set_cur_state() so that the configured duty cycle is never set below 20%. Before: # cat /sys/class/thermal/thermal_zone0/cdev0/type mlxsw_fan # echo 10 > /sys/class/thermal/thermal_zone0/cdev0/cur_state # cat /sys/class/hwmon/hwmon0/name mlxsw # cat /sys/class/hwmon/hwmon0/pwm1 0 After: # cat /sys/class/thermal/thermal_zone0/cdev0/type mlxsw_fan # echo 10 > /sys/class/thermal/thermal_zone0/cdev0/cur_state # cat /sys/class/hwmon/hwmon0/name mlxsw # cat /sys/class/hwmon/hwmon0/pwm1 255 This bug was uncovered when the thermal subsystem repeatedly tried to configure the cooling devices to their maximum state due to another issue [1]. This resulted in the fans being stuck at 0 RPM, which eventually lead to the system undergoing thermal shutdown. [1] https://lore.kernel.org/netdev/ZA3CFNhU4AbtsP4G@shredder/ Fixes: a421ce088ac8 ("mlxsw: core: Extend cooling device with cooling levels") Signed-off-by: Ido Schimmel <idosch@nvidia.com> Reviewed-by: Vadim Pasternak <vadimp@nvidia.com> Signed-off-by: Petr Machata <petrm@nvidia.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to '')
-rw-r--r--drivers/net/ethernet/mellanox/mlxsw/core_thermal.c7
1 files changed, 1 insertions, 6 deletions
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c b/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
index c5240d38c9db..09ed6e5fa6c3 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
@@ -105,7 +105,6 @@ struct mlxsw_thermal {
struct thermal_zone_device *tzdev;
int polling_delay;
struct thermal_cooling_device *cdevs[MLXSW_MFCR_PWMS_MAX];
- u8 cooling_levels[MLXSW_THERMAL_MAX_STATE + 1];
struct thermal_trip trips[MLXSW_THERMAL_NUM_TRIPS];
struct mlxsw_cooling_states cooling_states[MLXSW_THERMAL_NUM_TRIPS];
struct mlxsw_thermal_area line_cards[];
@@ -468,7 +467,7 @@ static int mlxsw_thermal_set_cur_state(struct thermal_cooling_device *cdev,
return idx;
/* Normalize the state to the valid speed range. */
- state = thermal->cooling_levels[state];
+ state = max_t(unsigned long, MLXSW_THERMAL_MIN_STATE, state);
mlxsw_reg_mfsc_pack(mfsc_pl, idx, mlxsw_state_to_duty(state));
err = mlxsw_reg_write(thermal->core, MLXSW_REG(mfsc), mfsc_pl);
if (err) {
@@ -859,10 +858,6 @@ int mlxsw_thermal_init(struct mlxsw_core *core,
}
}
- /* Initialize cooling levels per PWM state. */
- for (i = 0; i < MLXSW_THERMAL_MAX_STATE; i++)
- thermal->cooling_levels[i] = max(MLXSW_THERMAL_MIN_STATE, i);
-
thermal->polling_delay = bus_info->low_frequency ?
MLXSW_THERMAL_SLOW_POLL_INT :
MLXSW_THERMAL_POLL_INT;