From: Saeed Mahameed saeedm@nvidia.com
[ Upstream commit 631079e08aa4a20b73e70de4cf457886194f029f ]
Prior to this patch only one "mlx5" thermal zone could have been registered regardless of the number of individual mlx5 devices in the system.
To fix this setup a unique name per device to register its own thermal zone.
In order to not register a thermal zone for a virtual device (VF/SF) add a check for PF device type.
The new name is a concatenation between "mlx5_" and "<PCI_DEV_BDF>", which will also help associating a thermal zone with its PCI device.
$ lspci | grep ConnectX 00:04.0 Ethernet controller: Mellanox Technologies MT2892 Family [ConnectX-6 Dx] 00:05.0 Ethernet controller: Mellanox Technologies MT2892 Family [ConnectX-6 Dx]
$ cat /sys/devices/virtual/thermal/thermal_zone0/type mlx5_0000:00:04.0 $ cat /sys/devices/virtual/thermal/thermal_zone1/type mlx5_0000:00:05.0
Fixes: c1fef618d611 ("net/mlx5: Implement thermal zone") CC: Sandipan Patra spatra@nvidia.com Signed-off-by: Saeed Mahameed saeedm@nvidia.com Signed-off-by: Sasha Levin sashal@kernel.org --- .../net/ethernet/mellanox/mlx5/core/thermal.c | 19 ++++++++++++------- 1 file changed, 12 insertions(+), 7 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/thermal.c b/drivers/net/ethernet/mellanox/mlx5/core/thermal.c index e47fa6fb836f1..89a22ff04cb60 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/thermal.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/thermal.c @@ -68,14 +68,19 @@ static struct thermal_zone_device_ops mlx5_thermal_ops = {
int mlx5_thermal_init(struct mlx5_core_dev *mdev) { + char data[THERMAL_NAME_LENGTH]; struct mlx5_thermal *thermal; - struct thermal_zone_device *tzd; - const char *data = "mlx5"; + int err;
- tzd = thermal_zone_get_zone_by_name(data); - if (!IS_ERR(tzd)) + if (!mlx5_core_is_pf(mdev) && !mlx5_core_is_ecpf(mdev)) return 0;
+ err = snprintf(data, sizeof(data), "mlx5_%s", dev_name(mdev->device)); + if (err < 0 || err >= sizeof(data)) { + mlx5_core_err(mdev, "Failed to setup thermal zone name, %d\n", err); + return -EINVAL; + } + thermal = kzalloc(sizeof(*thermal), GFP_KERNEL); if (!thermal) return -ENOMEM; @@ -88,10 +93,10 @@ int mlx5_thermal_init(struct mlx5_core_dev *mdev) &mlx5_thermal_ops, NULL, 0, MLX5_THERMAL_POLL_INT_MSEC); if (IS_ERR(thermal->tzdev)) { - dev_err(mdev->device, "Failed to register thermal zone device (%s) %ld\n", - data, PTR_ERR(thermal->tzdev)); + err = PTR_ERR(thermal->tzdev); + mlx5_core_err(mdev, "Failed to register thermal zone device (%s) %d\n", data, err); kfree(thermal); - return -EINVAL; + return err; }
mdev->thermal = thermal;